ó âdc@@s“dZddlmZddlZddlmZddlmZm Z ddl m Z m ZddlZddlZddlmZddlmZmZmZdd lmZmZmZmZdd l m!Z!m"Z"m#Z#m$Z$d „Zdd lm%Z%e$r@ydd l&m'Z'Wn!e(k r<dd l)m'Z'nXn8ydd l*m'Z'Wn!e(k rwdd l+m'Z'nXdd„Z,de-fd„ƒYZ.de/fd„ƒYZ0y$ddl m Z ddlm1Z1Wne(k rçnXd„Z2de/fd„ƒYZ3d„Z4ddd„Z5de fd„ƒYZ6ddlm7Z7e7e8d„Z9d „Z:e0Z;e3Z<e4Z=e5Z>eZ?e2Z@e,ZAe6ZBe9ZCe:ZDejEd!d"fkrdd#lm0Z0m3Z3dd$lm5Z5dd%lFm:Z:ydd&lm4Z4Wne(k r nXdd'lm9Z9nejEd(dfkrWddlmZdd)lm2Z2nejEd(d(fkrdd*lGm,Z,dd+lm6Z6ndS(,sê Miscellaneous function (re)definitions from the Py3.4+ standard library for Python 2.6/2.7. - math.ceil (for Python 2.7) - collections.OrderedDict (for Python 2.6) - collections.Counter (for Python 2.6) - collections.ChainMap (for all versions prior to Python 3.3) - itertools.count (for Python 2.6, with step parameter) - subprocess.check_output (for Python 2.6) - reprlib.recursive_repr (for Python 2.6+) - functools.cmp_to_key (for Python 2.6) i(tabsolute_importN(tceil(tMappingtMutableMapping(t itemgetterteq(tproxy(trepeattchaintstarmap(t getaddrinfot SOCK_STREAMterrortsocket(t iteritemst itervaluestPY26tPY3cC@stt|ƒƒS(sZ Return the ceiling of x as an int. This is the smallest integral value >= x. (tinttoldceil(tx((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyRs(tislice(t get_idents...c@s‡fd†}|S(sGDecorator to make a repr function return fillvalue for a recursive callc@smtƒ‰‡‡‡fd†}tˆdƒ|_tˆdƒ|_tˆdƒ|_tˆdiƒ|_|S(Nc@sWt|ƒtƒf}|ˆkr%ˆSˆj|ƒzˆ|ƒ}Wdˆj|ƒX|S(N(tidRtaddtdiscard(tselftkeytresult(t fillvaluet repr_runningt user_function(sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pytwrapper?s  t __module__t__doc__t__name__t__annotations__(tsettgetattrR!R"R#R$(RR (R(RRsc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pytdecorating_function<s  ((RR'((Rsc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pytrecursive_repr9st_LinkcB@seZdZRS(tprevtnextRt __weakref__(R*R+RR,(R#R!t __slots__(((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyR)Xst OrderedDictcB@seZdZd„Zejeed„Zejd„Zd„Z d„Z d„Z e d„Z e d„Zd „ZejZZejZejZejZejZeƒZed „Zdd „Zeƒd „ƒZd „Zd„Ze dd„ƒZ!d„Z"RS(s)Dictionary that remembers insertion ordercO@sÂ|stdƒ‚n|d}|d}t|ƒdkrTtdt|ƒƒ‚ny |jWnLtk r­tƒ|_t|jƒ|_}||_|_i|_ nX|j ||ŽdS(sÅInitialize an ordered dictionary. The signature is the same as regular dictionaries, but keyword arguments are not recommended because their insertion order is arbitrary. s?descriptor '__init__' of 'OrderedDict' object needs an argumentiis$expected at most 1 arguments, got %dN( t TypeErrortlent_OrderedDict__roottAttributeErrorR)t_OrderedDict__hardroott_proxyR*R+t_OrderedDict__mapt_OrderedDict__update(targstkwdsRtroot((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__init__js      c C@s~||krj|ƒ|j|<}|j}|j}||||_|_|_||_||ƒ|_n||||ƒdS(s!od.__setitem__(i, y) <==> od[i]=yN(R5R1R*R+R( RRtvaluet dict_setitemRtLinktlinkR9tlast((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt __setitem__€s    cC@sG|||ƒ|jj|ƒ}|j}|j}||_||_dS(s od.__delitem__(y) <==> del od[y]N(R5tpopR*R+(RRt dict_delitemR>t link_prevt link_next((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt __delitem__Žs     cc@s:|j}|j}x!||k r5|jV|j}qWdS(sod.__iter__() <==> iter(od)N(R1R+R(RR9tcurr((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__iter__™s   cc@s:|j}|j}x!||k r5|jV|j}qWdS(s#od.__reversed__() <==> reversed(od)N(R1R*R(RR9RF((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt __reversed__¢s   cC@s7|j}||_|_|jjƒtj|ƒdS(s.od.clear() -> None. Remove all items from od.N(R1R*R+R5tcleartdict(RR9((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyRI«s  cC@sž|stdƒ‚n|j}|rK|j}|j}||_||_n$|j}|j}||_||_|j}|j|=tj||ƒ}||fS(s™od.popitem() -> (k, v), return and remove a (key, value) pair. Pairs are returned in LIFO order if last is true or FIFO order if false. sdictionary is empty(tKeyErrorR1R*R+RR5RJRA(RR?R9R>RCRDRR;((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pytpopitem²s            cC@s|j|}|j}|j}||_||_|j}|rn|j}||_||_||_|_n+|j}||_||_||_|_dS(sÑMove an existing element to the end (or beginning if last==False). Raises KeyError if the element does not exist. When last=True, acts like a fast version of self[key]=self.pop(key). N(R5R*R+R1(RRR?R>RCRDR9tfirst((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt move_to_endÉs            cC@sqtj}t|ƒd}||jƒ}|||jƒd7}|||jƒ|7}|||jƒ|7}|S(Nii(tsyst getsizeofR0t__dict__R5R3R1(Rtsizeoftntsize((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt __sizeof__ás cC@sC||kr!||}||=|S||jkr?t|ƒ‚n|S(s²od.pop(k[,d]) -> v, remove specified key and return the corresponding value. If key is not found, d is returned if given, otherwise KeyError is raised. (t_OrderedDict__markerRK(RRtdefaultR((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyRAòs  cC@s"||kr||S|||<|S(sDod.setdefault(k[,d]) -> od.get(k,d), also set od[k]=d if k not in od((RRRW((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt setdefaults  cC@s7|sd|jjfSd|jjt|jƒƒfS(sod.__repr__() <==> repr(od)s%s()s%s(%r)(t __class__R#tlisttitems(R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__repr__scC@sdt|ƒjƒ}x'ttƒƒD]}|j|dƒq"W|jd|pNddt|jƒƒfS(s%Return state information for picklingN((tvarstcopyR.RAtNoneRYtiterR[(Rt inst_dicttk((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt __reduce__scC@s |j|ƒS(s!od.copy() -> a shallow copy of od(RY(R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyR^scC@s(|ƒ}x|D]}||| New ordered dictionary with keys from S. If not specified, the value defaults to None. ((tclstiterableR;RR((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pytfromkeyss  cC@sGt|tƒr7tj||ƒo6ttt||ƒƒStj||ƒS(s“od.__eq__(y) <==> od==y. Comparison to another OD is order-sensitive while comparison to a regular mapping is order-insensitive. (t isinstanceR.RJt__eq__talltmapt_eq(Rtother((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyRh$s(N(#R#R!R"R:RJR@R4R)RERGRHRItTrueRLRNRURtupdateR6tkeystvaluesR[t__ne__tobjectRVRAR_RXR(R\RcR^t classmethodRfRh(((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyR.[s0                (R(tnlargestcC@s5|j}x%|D]}||dƒd||>> c = Counter('abcdeabcdabcaba') # count elements from a string >>> c.most_common(3) # three most common elements [('a', 5), ('b', 4), ('c', 3)] >>> sorted(c) # list all unique elements ['a', 'b', 'c', 'd', 'e'] >>> ''.join(sorted(c.elements())) # list elements with repetitions 'aaaaabbbbcccdde' >>> sum(c.values()) # total of all counts 15 >>> c['a'] # count of letter 'a' 5 >>> for elem in 'shazam': # update counts from an iterable ... c[elem] += 1 # by adding 1 to each element's count >>> c['a'] # now there are seven 'a' 7 >>> del c['b'] # remove all 'b' >>> c['b'] # now there are zero 'b' 0 >>> d = Counter('simsalabim') # make another counter >>> c.update(d) # add in the second counter >>> c['a'] # now there are nine 'a' 9 >>> c.clear() # empty the counter >>> c Counter() Note: If a count is set to zero or reduced to zero, it will remain in the counter until the entry is deleted or the counter is cleared: >>> c = Counter('aaabbc') >>> c['b'] -= 2 # reduce the count of 'b' by two >>> c.most_common() # 'b' is still in, but its count is zero [('a', 3), ('c', 1), ('b', 0)] cO@s{|stdƒ‚n|d}|d}t|ƒdkrTtdt|ƒƒ‚ntt|ƒjƒ|j||ŽdS(s Create a new, empty Counter object. And if given, count elements from an input iterable. Or, initialize the count from another mapping of elements to their counts. >>> c = Counter() # a new, empty counter >>> c = Counter('gallahad') # a new counter from an iterable >>> c = Counter({'a': 4, 'b': 2}) # a new counter from a mapping >>> c = Counter(a=4, b=2) # a new counter from keyword args s;descriptor '__init__' of 'Counter' object needs an argumentiis$expected at most 1 arguments, got %dN(R/R0tsuperRzR:Rn(R7R8R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyR:ss   cC@sdS(s1The count of elements not in the Counter is zero.i((RR((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt __missing__ˆscC@sP|dkr.t|jƒdtdƒdtƒStj||jƒdtdƒƒS(sðList the n most common elements and their counts from the most common to the least. If n is None, then list all element counts. >>> Counter('abcdeabcdabcaba').most_common(3) [('a', 5), ('b', 4), ('c', 3)] RitreverseN(R_tsortedR[t _itemgetterRmt_heapqRt(RRS((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt most_commons "cC@stjtt|jƒƒƒS(sIterator over elements repeating each as many times as its count. >>> c = Counter('ABCABC') >>> sorted(c.elements()) ['A', 'A', 'B', 'B', 'C', 'C'] # Knuth's example for prime factors of 1836: 2**2 * 3**3 * 17**1 >>> prime_factors = Counter({2: 2, 3: 3, 17: 1}) >>> product = 1 >>> for factor in prime_factors.elements(): # loop over factors ... product *= factor # and multiply them >>> product 1836 Note, if an element's count has been set to zero or is a negative number, elements() will ignore it. (t_chaint from_iterablet_starmapt_repeatR[(R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pytelementsšscC@stdƒ‚dS(Ns@Counter.fromkeys() is undefined. Use Counter(iterable) instead.(tNotImplementedError(RdRetv((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyRf²scO@s|stdƒ‚n|d}|d}t|ƒdkrTtdt|ƒƒ‚n|rd|dnd}|dk rôt|tƒrä|rË|j}xJ|jƒD]#\}}|||dƒ||>> c = Counter('which') >>> c.update('witch') # add elements from another iterable >>> d = Counter('watch') >>> c.update(d) # add elements from another counter >>> c['h'] # four 'h' in which, witch, and watch 4 s9descriptor 'update' of 'Counter' object needs an argumentiis$expected at most 1 arguments, got %dN( R/R0R_RgRRuR[R{RzRnRy(R7R8RRetself_getRxtcount((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyRn¹s"    cO@s |stdƒ‚n|d}|d}t|ƒdkrTtdt|ƒƒ‚n|rd|dnd}|dk rð|j}t|tƒrÅx\|jƒD]#\}}||dƒ|||>> c = Counter('which') >>> c.subtract('witch') # subtract elements from another iterable >>> c.subtract(Counter('watch')) # subtract elements from another counter >>> c['h'] # 2 in which, minus 1 in witch, minus 1 in watch 0 >>> c['w'] # 1 in which, minus 1 in witch, minus 1 in watch -1 s;descriptor 'subtract' of 'Counter' object needs an argumentiis$expected at most 1 arguments, got %dN(R/R0R_RuRgRR[tsubtract(R7R8RReR‰RxRŠ((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyR‹âs      cC@s |j|ƒS(sReturn a shallow copy.(RY(R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyR^scC@s|jt|ƒffS(N(RYRJ(R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyRc scC@s)||kr%tt|ƒj|ƒndS(sGLike dict.__delitem__() but does not raise KeyError for missing values.N(R{RzRE(RRx((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyRE s cC@s~|sd|jjSy9djtdj|jƒƒƒ}d|jj|fSWn*tk rydj|jjt|ƒƒSXdS(Ns%s()s, s%r: %rs%s({%s})s {0}({1!r})( RYR#tjoinRjt__mod__RR/tformatRJ(RR[((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyR\s! cC@s¦t|tƒstStƒ}xA|jƒD]3\}}|||}|dkr)|||>> Counter('abbb') + Counter('bcc') Counter({'b': 4, 'c': 2, 'a': 1}) i(RgRztNotImplementedR[(RRlRRxRŠtnewcount((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__add__$s  cC@sªt|tƒstStƒ}xA|jƒD]3\}}|||}|dkr)|||>> Counter('abbbc') - Counter('bccd') Counter({'b': 2, 'a': 1}) i(RgRzRR[(RRlRRxRŠR((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__sub__7s  cC@sºt|tƒstStƒ}xU|jƒD]G\}}||}||krQ|n|}|dkr)|||>> Counter('abbb') | Counter('bcc') Counter({'b': 3, 'c': 2, 'a': 1}) i(RgRzRR[(RRlRRxRŠt other_countR((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__or__Js   cC@sxt|tƒstStƒ}xU|jƒD]G\}}||}||krQ|n|}|dkr)|||>> Counter('abbb') & Counter('bcc') Counter({'b': 1}) i(RgRzRR[(RRlRRxRŠR“R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__and__^s   cC@s |tƒS(sEAdds an empty counter, effectively stripping negative and zero counts(Rz(R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__pos__oscC@s tƒ|S(s{Subtracts from an empty counter. Strips positive and zero counts, and flips the sign on negative counts. (Rz(R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__neg__sscC@sMg|jƒD]\}}|dks |^q }x|D] }||=q8W|S(s?Internal method to strip elements with a negative or zero counti(R[(RRxRŠt nonpositive((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt_keep_positivezs1  cC@s7x*|jƒD]\}}||c|7>> c = Counter('abbb') >>> c += Counter('bcc') >>> c Counter({'b': 4, 'c': 2, 'a': 1}) (R[R™(RRlRxRŠ((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__iadd__s cC@s7x*|jƒD]\}}||c|8>> c = Counter('abbbc') >>> c -= Counter('bccd') >>> c Counter({'b': 2, 'a': 1}) (R[R™(RRlRxRŠ((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__isub__Žs cC@sJx=|jƒD]/\}}||}||kr |||>> c = Counter('abbb') >>> c |= Counter('bcc') >>> c Counter({'b': 3, 'c': 2, 'a': 1}) (R[R™(RRlRxR“RŠ((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__ior__›s   cC@sJx=|jƒD]/\}}||}||kr |||>> c = Counter('abbb') >>> c &= Counter('bcc') >>> c Counter({'b': 1}) (R[R™(RRlRxRŠR“((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__iand__ªs   N(R#R!R"R:R|R_RR†RsRfRnR‹R^RcRER\R‘R’R”R•R–R—R™RšR›RœR(((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyRz@s0+    ) #            cO@s›d|krtdƒ‚ntjdtj||Ž}|jƒ\}}|jƒ}|r—|jdƒ}|dkr‚|d}ntj||ƒ‚n|S(s[ For Python 2.6 compatibility: see http://stackoverflow.com/questions/4814970/ tstdouts3stdout argument not allowed, it will be overridden.R7iN( t ValueErrort subprocesstPopentPIPEt communicatetpollRuR_tCalledProcessError(t popenargstkwargstprocesstoutputt unused_errtretcodetcmd((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt check_outputºs    icc@s xtr|V||7}qWdS(s¿ ``itertools.count`` in Py 2.6 doesn't accept a step parameter. This is an enhanced version of ``itertools.count`` for Py2.6 equivalent to ``itertools.count`` in Python 2.7+. N(Rm(tstarttstep((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyRŠÍs tChainMapcB@s×eZdZd„Zd„Zd„Zdd„Zd„Zd„Z d„Z d„Z e Z e ƒd „ƒZed „ƒZd „ZeZdd „Zed „ƒZd„Zd„Zd„Zd„Zd„ZRS(s± A ChainMap groups multiple dicts (or other mappings) together to create a single, updateable view. The underlying mappings are stored in a list. That list is public and can accessed or updated using the *maps* attribute. There is no other state. Lookups search the underlying mappings successively until a key is found. In contrast, writes, updates, and deletions only operate on the first mapping. cG@st|ƒpig|_dS(sInitialize a ChainMap by setting *maps* to the given mappings. If no mappings are provided, a single empty dictionary is used. N(RZtmaps(RR±((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyR:ëscC@st|ƒ‚dS(N(RK(RR((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyR|òscC@sAx1|jD]&}y ||SWq tk r/q Xq W|j|ƒS(N(R±RKR|(RRRv((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt __getitem__õs   cC@s||kr||S|S(N((RRRW((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyRuýscC@sttƒj|jŒƒS(N(R0R%tunionR±(R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__len__scC@sttƒj|jŒƒS(N(R`R%R³R±(R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyRGsc@st‡fd†|jDƒƒS(Nc3@s|]}ˆ|kVqdS(N((t.0tm(R(sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pys s(tanyR±(RR((Rsc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt __contains__scC@s t|jƒS(N(R·R±(R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt__bool__ scC@s%dj|djtt|jƒƒƒS(Ns{0.__class__.__name__}({1})s, (RŽRŒRjtreprR±(R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyR\scG@s|tj||ŒƒS(s?Create a ChainMap with a single dict created from the iterable.(RJRf(RdReR7((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyRfscC@s$|j|jdjƒ|jdŒS(sHNew ChainMap or subclass with a new copy of maps[0] and refs to maps[1:]ii(RYR±R^(R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyR^scC@s(|dkri}n|j||jŒS(s‚ New ChainMap with a new map followed by all previous maps. If no map is provided, an empty dict is used. N(R_RYR±(RR¶((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pyt new_childs  cC@s|j|jdŒS(sNew ChainMap from maps[1:].i(RYR±(R((sc/home/josie/.config/GIMP/2.10/plug-ins/export_layers/pygimplib/_lib/future/future/backports/misc.pytparents(scC@s||jd| s‚   ""    Õ  ÿ{ l (  # Wrapper module for _socket, providing some additional facilities # implemented in Python. """\ This module provides socket operations and some related functions. On Unix, it supports IP (Internet Protocol) and Unix domain sockets. On other systems, it only supports IP. Functions specific for a socket are available as methods of the socket object. Functions: socket() -- create a new socket object socketpair() -- create a pair of new socket objects [*] fromfd() -- create a socket object from an open file descriptor [*] fromshare() -- create a socket object from data received from socket.share() [*] gethostname() -- return the current hostname gethostbyname() -- map a hostname to its IP number gethostbyaddr() -- map an IP number or hostname to DNS info getservbyname() -- map a service name and a protocol name to a port number getprotobyname() -- map a protocol name (e.g. 'tcp') to a number ntohs(), ntohl() -- convert 16, 32 bit int from network to host byte order htons(), htonl() -- convert 16, 32 bit int from host to network byte order inet_aton() -- convert IP addr string (123.45.67.89) to 32-bit packed format inet_ntoa() -- convert 32-bit packed format IP to string (123.45.67.89) socket.getdefaulttimeout() -- get the default timeout value socket.setdefaulttimeout() -- set the default timeout value create_connection() -- connects to an address, with an optional timeout and optional source address. [*] not available on all platforms! Special objects: SocketType -- type object for socket objects error -- exception raised for I/O errors has_ipv6 -- boolean value indicating if IPv6 is supported Integer constants: AF_INET, AF_UNIX -- socket domains (first argument to socket() call) SOCK_STREAM, SOCK_DGRAM, SOCK_RAW -- socket types (second argument) Many other constants may be defined; these may be used in calls to the setsockopt() and getsockopt() methods. """ from __future__ import unicode_literals from __future__ import print_function from __future__ import division from __future__ import absolute_import from future.builtins import super import _socket from _socket import * import os, sys, io try: import errno except ImportError: errno = None EBADF = getattr(errno, 'EBADF', 9) EAGAIN = getattr(errno, 'EAGAIN', 11) EWOULDBLOCK = getattr(errno, 'EWOULDBLOCK', 11) __all__ = ["getfqdn", "create_connection"] __all__.extend(os._get_exports_list(_socket)) _realsocket = socket # WSA error codes if sys.platform.lower().startswith("win"): errorTab = {} errorTab[10004] = "The operation was interrupted." errorTab[10009] = "A bad file handle was passed." errorTab[10013] = "Permission denied." errorTab[10014] = "A fault occurred on the network??" # WSAEFAULT errorTab[10022] = "An invalid operation was attempted." errorTab[10035] = "The socket operation would block" errorTab[10036] = "A blocking operation is already in progress." errorTab[10048] = "The network address is in use." errorTab[10054] = "The connection has been reset." errorTab[10058] = "The network has been shut down." errorTab[10060] = "The operation timed out." errorTab[10061] = "Connection refused." errorTab[10063] = "The name is too long." errorTab[10064] = "The host is down." errorTab[10065] = "The host is unreachable." __all__.append("errorTab") class socket(_socket.socket): """A subclass of _socket.socket adding the makefile() method.""" __slots__ = ["__weakref__", "_io_refs", "_closed"] def __init__(self, family=AF_INET, type=SOCK_STREAM, proto=0, fileno=None): if fileno is None: _socket.socket.__init__(self, family, type, proto) else: _socket.socket.__init__(self, family, type, proto, fileno) self._io_refs = 0 self._closed = False def __enter__(self): return self def __exit__(self, *args): if not self._closed: self.close() def __repr__(self): """Wrap __repr__() to reveal the real class name.""" s = _socket.socket.__repr__(self) if s.startswith(" socket object Return a new socket object connected to the same system resource. """ fd = dup(self.fileno()) sock = self.__class__(self.family, self.type, self.proto, fileno=fd) sock.settimeout(self.gettimeout()) return sock def accept(self): """accept() -> (socket object, address info) Wait for an incoming connection. Return a new socket representing the connection, and the address of the client. For IP sockets, the address info is a pair (hostaddr, port). """ fd, addr = self._accept() sock = socket(self.family, self.type, self.proto, fileno=fd) # Issue #7995: if no default timeout is set and the listening # socket had a (non-zero) timeout, force the new socket in blocking # mode to override platform-specific socket flags inheritance. if getdefaulttimeout() is None and self.gettimeout(): sock.setblocking(True) return sock, addr def makefile(self, mode="r", buffering=None, **_3to2kwargs): """makefile(...) -> an I/O stream connected to the socket The arguments are as for io.open() after the filename, except the only mode characters supported are 'r', 'w' and 'b'. The semantics are similar too. (XXX refactor to share code?) """ if 'newline' in _3to2kwargs: newline = _3to2kwargs['newline']; del _3to2kwargs['newline'] else: newline = None if 'errors' in _3to2kwargs: errors = _3to2kwargs['errors']; del _3to2kwargs['errors'] else: errors = None if 'encoding' in _3to2kwargs: encoding = _3to2kwargs['encoding']; del _3to2kwargs['encoding'] else: encoding = None for c in mode: if c not in ("r", "w", "b"): raise ValueError("invalid mode %r (only r, w, b allowed)") writing = "w" in mode reading = "r" in mode or not writing assert reading or writing binary = "b" in mode rawmode = "" if reading: rawmode += "r" if writing: rawmode += "w" raw = SocketIO(self, rawmode) self._io_refs += 1 if buffering is None: buffering = -1 if buffering < 0: buffering = io.DEFAULT_BUFFER_SIZE if buffering == 0: if not binary: raise ValueError("unbuffered streams must be binary") return raw if reading and writing: buffer = io.BufferedRWPair(raw, raw, buffering) elif reading: buffer = io.BufferedReader(raw, buffering) else: assert writing buffer = io.BufferedWriter(raw, buffering) if binary: return buffer text = io.TextIOWrapper(buffer, encoding, errors, newline) text.mode = mode return text def _decref_socketios(self): if self._io_refs > 0: self._io_refs -= 1 if self._closed: self.close() def _real_close(self, _ss=_socket.socket): # This function should not reference any globals. See issue #808164. _ss.close(self) def close(self): # This function should not reference any globals. See issue #808164. self._closed = True if self._io_refs <= 0: self._real_close() def detach(self): """detach() -> file descriptor Close the socket object without closing the underlying file descriptor. The object cannot be used after this call, but the file descriptor can be reused for other purposes. The file descriptor is returned. """ self._closed = True return super().detach() def fromfd(fd, family, type, proto=0): """ fromfd(fd, family, type[, proto]) -> socket object Create a socket object from a duplicate of the given file descriptor. The remaining arguments are the same as for socket(). """ nfd = dup(fd) return socket(family, type, proto, nfd) if hasattr(_socket.socket, "share"): def fromshare(info): """ fromshare(info) -> socket object Create a socket object from a the bytes object returned by socket.share(pid). """ return socket(0, 0, 0, info) if hasattr(_socket, "socketpair"): def socketpair(family=None, type=SOCK_STREAM, proto=0): """socketpair([family[, type[, proto]]]) -> (socket object, socket object) Create a pair of socket objects from the sockets returned by the platform socketpair() function. The arguments are the same as for socket() except the default family is AF_UNIX if defined on the platform; otherwise, the default is AF_INET. """ if family is None: try: family = AF_UNIX except NameError: family = AF_INET a, b = _socket.socketpair(family, type, proto) a = socket(family, type, proto, a.detach()) b = socket(family, type, proto, b.detach()) return a, b _blocking_errnos = set([EAGAIN, EWOULDBLOCK]) class SocketIO(io.RawIOBase): """Raw I/O implementation for stream sockets. This class supports the makefile() method on sockets. It provides the raw I/O interface on top of a socket object. """ # One might wonder why not let FileIO do the job instead. There are two # main reasons why FileIO is not adapted: # - it wouldn't work under Windows (where you can't used read() and # write() on a socket handle) # - it wouldn't work with socket timeouts (FileIO would ignore the # timeout and consider the socket non-blocking) # XXX More docs def __init__(self, sock, mode): if mode not in ("r", "w", "rw", "rb", "wb", "rwb"): raise ValueError("invalid mode: %r" % mode) io.RawIOBase.__init__(self) self._sock = sock if "b" not in mode: mode += "b" self._mode = mode self._reading = "r" in mode self._writing = "w" in mode self._timeout_occurred = False def readinto(self, b): """Read up to len(b) bytes into the writable buffer *b* and return the number of bytes read. If the socket is non-blocking and no bytes are available, None is returned. If *b* is non-empty, a 0 return value indicates that the connection was shutdown at the other end. """ self._checkClosed() self._checkReadable() if self._timeout_occurred: raise IOError("cannot read from timed out object") while True: try: return self._sock.recv_into(b) except timeout: self._timeout_occurred = True raise # except InterruptedError: # continue except error as e: if e.args[0] in _blocking_errnos: return None raise def write(self, b): """Write the given bytes or bytearray object *b* to the socket and return the number of bytes written. This can be less than len(b) if not all data could be written. If the socket is non-blocking and no bytes could be written None is returned. """ self._checkClosed() self._checkWritable() try: return self._sock.send(b) except error as e: # XXX what about EINTR? if e.args[0] in _blocking_errnos: return None raise def readable(self): """True if the SocketIO is open for reading. """ if self.closed: raise ValueError("I/O operation on closed socket.") return self._reading def writable(self): """True if the SocketIO is open for writing. """ if self.closed: raise ValueError("I/O operation on closed socket.") return self._writing def seekable(self): """True if the SocketIO is open for seeking. """ if self.closed: raise ValueError("I/O operation on closed socket.") return super().seekable() def fileno(self): """Return the file descriptor of the underlying socket. """ self._checkClosed() return self._sock.fileno() @property def name(self): if not self.closed: return self.fileno() else: return -1 @property def mode(self): return self._mode def close(self): """Close the SocketIO object. This doesn't close the underlying socket, except if all references to it have disappeared. """ if self.closed: return io.RawIOBase.close(self) self._sock._decref_socketios() self._sock = None def getfqdn(name=''): """Get fully qualified domain name from name. An empty argument is interpreted as meaning the local host. First the hostname returned by gethostbyaddr() is checked, then possibly existing aliases. In case no FQDN is available, hostname from gethostname() is returned. """ name = name.strip() if not name or name == '0.0.0.0': name = gethostname() try: hostname, aliases, ipaddrs = gethostbyaddr(name) except error: pass else: aliases.insert(0, hostname) for name in aliases: if '.' in name: break else: name = hostname return name # Re-use the same sentinel as in the Python stdlib socket module: from socket import _GLOBAL_DEFAULT_TIMEOUT # Was: _GLOBAL_DEFAULT_TIMEOUT = object() def create_connection(address, timeout=_GLOBAL_DEFAULT_TIMEOUT, source_address=None): """Connect to *address* and return the socket object. Convenience function. Connect to *address* (a 2-tuple ``(host, port)``) and return the socket object. Passing the optional *timeout* parameter will set the timeout on the socket instance before attempting to connect. If no *timeout* is supplied, the global default timeout setting returned by :func:`getdefaulttimeout` is used. If *source_address* is set it must be a tuple of (host, port) for the socket to bind as a source address before making the connection. An host of '' or port 0 tells the OS to use the default. """ host, port = address err = None for res in getaddrinfo(host, port, 0, SOCK_STREAM): af, socktype, proto, canonname, sa = res sock = None try: sock = socket(af, socktype, proto) if timeout is not _GLOBAL_DEFAULT_TIMEOUT: sock.settimeout(timeout) if source_address: sock.bind(source_address) sock.connect(sa) return sock except error as _: err = _ if sock is not None: sock.close() if err is not None: raise err else: raise error("getaddrinfo returns an empty list") """Generic socket server classes. This module tries to capture the various aspects of defining a server: For socket-based servers: - address family: - AF_INET{,6}: IP (Internet Protocol) sockets (default) - AF_UNIX: Unix domain sockets - others, e.g. AF_DECNET are conceivable (see - socket type: - SOCK_STREAM (reliable stream, e.g. TCP) - SOCK_DGRAM (datagrams, e.g. UDP) For request-based servers (including socket-based): - client address verification before further looking at the request (This is actually a hook for any processing that needs to look at the request before anything else, e.g. logging) - how to handle multiple requests: - synchronous (one request is handled at a time) - forking (each request is handled by a new process) - threading (each request is handled by a new thread) The classes in this module favor the server type that is simplest to write: a synchronous TCP/IP server. This is bad class design, but save some typing. (There's also the issue that a deep class hierarchy slows down method lookups.) There are five classes in an inheritance diagram, four of which represent synchronous servers of four types: +------------+ | BaseServer | +------------+ | v +-----------+ +------------------+ | TCPServer |------->| UnixStreamServer | +-----------+ +------------------+ | v +-----------+ +--------------------+ | UDPServer |------->| UnixDatagramServer | +-----------+ +--------------------+ Note that UnixDatagramServer derives from UDPServer, not from UnixStreamServer -- the only difference between an IP and a Unix stream server is the address family, which is simply repeated in both unix server classes. Forking and threading versions of each type of server can be created using the ForkingMixIn and ThreadingMixIn mix-in classes. For instance, a threading UDP server class is created as follows: class ThreadingUDPServer(ThreadingMixIn, UDPServer): pass The Mix-in class must come first, since it overrides a method defined in UDPServer! Setting the various member variables also changes the behavior of the underlying server mechanism. To implement a service, you must derive a class from BaseRequestHandler and redefine its handle() method. You can then run various versions of the service by combining one of the server classes with your request handler class. The request handler class must be different for datagram or stream services. This can be hidden by using the request handler subclasses StreamRequestHandler or DatagramRequestHandler. Of course, you still have to use your head! For instance, it makes no sense to use a forking server if the service contains state in memory that can be modified by requests (since the modifications in the child process would never reach the initial state kept in the parent process and passed to each child). In this case, you can use a threading server, but you will probably have to use locks to avoid two requests that come in nearly simultaneous to apply conflicting changes to the server state. On the other hand, if you are building e.g. an HTTP server, where all data is stored externally (e.g. in the file system), a synchronous class will essentially render the service "deaf" while one request is being handled -- which may be for a very long time if a client is slow to read all the data it has requested. Here a threading or forking server is appropriate. In some cases, it may be appropriate to process part of a request synchronously, but to finish processing in a forked child depending on the request data. This can be implemented by using a synchronous server and doing an explicit fork in the request handler class handle() method. Another approach to handling multiple simultaneous requests in an environment that supports neither threads nor fork (or where these are too expensive or inappropriate for the service) is to maintain an explicit table of partially finished requests and to use select() to decide which request to work on next (or whether to handle a new incoming request). This is particularly important for stream services where each client can potentially be connected for a long time (if threads or subprocesses cannot be used). Future work: - Standard classes for Sun RPC (which uses either UDP or TCP) - Standard mix-in classes to implement various authentication and encryption schemes - Standard framework for select-based multiplexing XXX Open problems: - What to do with out-of-band data? BaseServer: - split generic "request" functionality out into BaseServer class. Copyright (C) 2000 Luke Kenneth Casson Leighton example: read entries from a SQL database (requires overriding get_request() to return a table entry from the database). entry is processed by a RequestHandlerClass. """ # Author of the BaseServer patch: Luke Kenneth Casson Leighton # XXX Warning! # There is a test suite for this module, but it cannot be run by the # standard regression test. # To run it manually, run Lib/test/test_socketserver.py. from __future__ import (absolute_import, print_function) __version__ = "0.4" import socket import select import sys import os import errno try: import threading except ImportError: import dummy_threading as threading __all__ = ["TCPServer","UDPServer","ForkingUDPServer","ForkingTCPServer", "ThreadingUDPServer","ThreadingTCPServer","BaseRequestHandler", "StreamRequestHandler","DatagramRequestHandler", "ThreadingMixIn", "ForkingMixIn"] if hasattr(socket, "AF_UNIX"): __all__.extend(["UnixStreamServer","UnixDatagramServer", "ThreadingUnixStreamServer", "ThreadingUnixDatagramServer"]) def _eintr_retry(func, *args): """restart a system call interrupted by EINTR""" while True: try: return func(*args) except OSError as e: if e.errno != errno.EINTR: raise class BaseServer(object): """Base class for server classes. Methods for the caller: - __init__(server_address, RequestHandlerClass) - serve_forever(poll_interval=0.5) - shutdown() - handle_request() # if you do not use serve_forever() - fileno() -> int # for select() Methods that may be overridden: - server_bind() - server_activate() - get_request() -> request, client_address - handle_timeout() - verify_request(request, client_address) - server_close() - process_request(request, client_address) - shutdown_request(request) - close_request(request) - service_actions() - handle_error() Methods for derived classes: - finish_request(request, client_address) Class variables that may be overridden by derived classes or instances: - timeout - address_family - socket_type - allow_reuse_address Instance variables: - RequestHandlerClass - socket """ timeout = None def __init__(self, server_address, RequestHandlerClass): """Constructor. May be extended, do not override.""" self.server_address = server_address self.RequestHandlerClass = RequestHandlerClass self.__is_shut_down = threading.Event() self.__shutdown_request = False def server_activate(self): """Called by constructor to activate the server. May be overridden. """ pass def serve_forever(self, poll_interval=0.5): """Handle one request at a time until shutdown. Polls for shutdown every poll_interval seconds. Ignores self.timeout. If you need to do periodic tasks, do them in another thread. """ self.__is_shut_down.clear() try: while not self.__shutdown_request: # XXX: Consider using another file descriptor or # connecting to the socket to wake this up instead of # polling. Polling reduces our responsiveness to a # shutdown request and wastes cpu at all other times. r, w, e = _eintr_retry(select.select, [self], [], [], poll_interval) if self in r: self._handle_request_noblock() self.service_actions() finally: self.__shutdown_request = False self.__is_shut_down.set() def shutdown(self): """Stops the serve_forever loop. Blocks until the loop has finished. This must be called while serve_forever() is running in another thread, or it will deadlock. """ self.__shutdown_request = True self.__is_shut_down.wait() def service_actions(self): """Called by the serve_forever() loop. May be overridden by a subclass / Mixin to implement any code that needs to be run during the loop. """ pass # The distinction between handling, getting, processing and # finishing a request is fairly arbitrary. Remember: # # - handle_request() is the top-level call. It calls # select, get_request(), verify_request() and process_request() # - get_request() is different for stream or datagram sockets # - process_request() is the place that may fork a new process # or create a new thread to finish the request # - finish_request() instantiates the request handler class; # this constructor will handle the request all by itself def handle_request(self): """Handle one request, possibly blocking. Respects self.timeout. """ # Support people who used socket.settimeout() to escape # handle_request before self.timeout was available. timeout = self.socket.gettimeout() if timeout is None: timeout = self.timeout elif self.timeout is not None: timeout = min(timeout, self.timeout) fd_sets = _eintr_retry(select.select, [self], [], [], timeout) if not fd_sets[0]: self.handle_timeout() return self._handle_request_noblock() def _handle_request_noblock(self): """Handle one request, without blocking. I assume that select.select has returned that the socket is readable before this function was called, so there should be no risk of blocking in get_request(). """ try: request, client_address = self.get_request() except socket.error: return if self.verify_request(request, client_address): try: self.process_request(request, client_address) except: self.handle_error(request, client_address) self.shutdown_request(request) def handle_timeout(self): """Called if no new request arrives within self.timeout. Overridden by ForkingMixIn. """ pass def verify_request(self, request, client_address): """Verify the request. May be overridden. Return True if we should proceed with this request. """ return True def process_request(self, request, client_address): """Call finish_request. Overridden by ForkingMixIn and ThreadingMixIn. """ self.finish_request(request, client_address) self.shutdown_request(request) def server_close(self): """Called to clean-up the server. May be overridden. """ pass def finish_request(self, request, client_address): """Finish one request by instantiating RequestHandlerClass.""" self.RequestHandlerClass(request, client_address, self) def shutdown_request(self, request): """Called to shutdown and close an individual request.""" self.close_request(request) def close_request(self, request): """Called to clean up an individual request.""" pass def handle_error(self, request, client_address): """Handle an error gracefully. May be overridden. The default is to print a traceback and continue. """ print('-'*40) print('Exception happened during processing of request from', end=' ') print(client_address) import traceback traceback.print_exc() # XXX But this goes to stderr! print('-'*40) class TCPServer(BaseServer): """Base class for various socket-based server classes. Defaults to synchronous IP stream (i.e., TCP). Methods for the caller: - __init__(server_address, RequestHandlerClass, bind_and_activate=True) - serve_forever(poll_interval=0.5) - shutdown() - handle_request() # if you don't use serve_forever() - fileno() -> int # for select() Methods that may be overridden: - server_bind() - server_activate() - get_request() -> request, client_address - handle_timeout() - verify_request(request, client_address) - process_request(request, client_address) - shutdown_request(request) - close_request(request) - handle_error() Methods for derived classes: - finish_request(request, client_address) Class variables that may be overridden by derived classes or instances: - timeout - address_family - socket_type - request_queue_size (only for stream sockets) - allow_reuse_address Instance variables: - server_address - RequestHandlerClass - socket """ address_family = socket.AF_INET socket_type = socket.SOCK_STREAM request_queue_size = 5 allow_reuse_address = False def __init__(self, server_address, RequestHandlerClass, bind_and_activate=True): """Constructor. May be extended, do not override.""" BaseServer.__init__(self, server_address, RequestHandlerClass) self.socket = socket.socket(self.address_family, self.socket_type) if bind_and_activate: self.server_bind() self.server_activate() def server_bind(self): """Called by constructor to bind the socket. May be overridden. """ if self.allow_reuse_address: self.socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1) self.socket.bind(self.server_address) self.server_address = self.socket.getsockname() def server_activate(self): """Called by constructor to activate the server. May be overridden. """ self.socket.listen(self.request_queue_size) def server_close(self): """Called to clean-up the server. May be overridden. """ self.socket.close() def fileno(self): """Return socket file number. Interface required by select(). """ return self.socket.fileno() def get_request(self): """Get the request and client address from the socket. May be overridden. """ return self.socket.accept() def shutdown_request(self, request): """Called to shutdown and close an individual request.""" try: #explicitly shutdown. socket.close() merely releases #the socket and waits for GC to perform the actual close. request.shutdown(socket.SHUT_WR) except socket.error: pass #some platforms may raise ENOTCONN here self.close_request(request) def close_request(self, request): """Called to clean up an individual request.""" request.close() class UDPServer(TCPServer): """UDP server class.""" allow_reuse_address = False socket_type = socket.SOCK_DGRAM max_packet_size = 8192 def get_request(self): data, client_addr = self.socket.recvfrom(self.max_packet_size) return (data, self.socket), client_addr def server_activate(self): # No need to call listen() for UDP. pass def shutdown_request(self, request): # No need to shutdown anything. self.close_request(request) def close_request(self, request): # No need to close anything. pass class ForkingMixIn(object): """Mix-in class to handle each request in a new process.""" timeout = 300 active_children = None max_children = 40 def collect_children(self): """Internal routine to wait for children that have exited.""" if self.active_children is None: return while len(self.active_children) >= self.max_children: # XXX: This will wait for any child process, not just ones # spawned by this library. This could confuse other # libraries that expect to be able to wait for their own # children. try: pid, status = os.waitpid(0, 0) except os.error: pid = None if pid not in self.active_children: continue self.active_children.remove(pid) # XXX: This loop runs more system calls than it ought # to. There should be a way to put the active_children into a # process group and then use os.waitpid(-pgid) to wait for any # of that set, but I couldn't find a way to allocate pgids # that couldn't collide. for child in self.active_children: try: pid, status = os.waitpid(child, os.WNOHANG) except os.error: pid = None if not pid: continue try: self.active_children.remove(pid) except ValueError as e: raise ValueError('%s. x=%d and list=%r' % (e.message, pid, self.active_children)) def handle_timeout(self): """Wait for zombies after self.timeout seconds of inactivity. May be extended, do not override. """ self.collect_children() def service_actions(self): """Collect the zombie child processes regularly in the ForkingMixIn. service_actions is called in the BaseServer's serve_forver loop. """ self.collect_children() def process_request(self, request, client_address): """Fork a new subprocess to process the request.""" pid = os.fork() if pid: # Parent process if self.active_children is None: self.active_children = [] self.active_children.append(pid) self.close_request(request) return else: # Child process. # This must never return, hence os._exit()! try: self.finish_request(request, client_address) self.shutdown_request(request) os._exit(0) except: try: self.handle_error(request, client_address) self.shutdown_request(request) finally: os._exit(1) class ThreadingMixIn(object): """Mix-in class to handle each request in a new thread.""" # Decides how threads will act upon termination of the # main process daemon_threads = False def process_request_thread(self, request, client_address): """Same as in BaseServer but as a thread. In addition, exception handling is done here. """ try: self.finish_request(request, client_address) self.shutdown_request(request) except: self.handle_error(request, client_address) self.shutdown_request(request) def process_request(self, request, client_address): """Start a new thread to process the request.""" t = threading.Thread(target = self.process_request_thread, args = (request, client_address)) t.daemon = self.daemon_threads t.start() class ForkingUDPServer(ForkingMixIn, UDPServer): pass class ForkingTCPServer(ForkingMixIn, TCPServer): pass class ThreadingUDPServer(ThreadingMixIn, UDPServer): pass class ThreadingTCPServer(ThreadingMixIn, TCPServer): pass if hasattr(socket, 'AF_UNIX'): class UnixStreamServer(TCPServer): address_family = socket.AF_UNIX class UnixDatagramServer(UDPServer): address_family = socket.AF_UNIX class ThreadingUnixStreamServer(ThreadingMixIn, UnixStreamServer): pass class ThreadingUnixDatagramServer(ThreadingMixIn, UnixDatagramServer): pass class BaseRequestHandler(object): """Base class for request handler classes. This class is instantiated for each request to be handled. The constructor sets the instance variables request, client_address and server, and then calls the handle() method. To implement a specific service, all you need to do is to derive a class which defines a handle() method. The handle() method can find the request as self.request, the client address as self.client_address, and the server (in case it needs access to per-server information) as self.server. Since a separate instance is created for each request, the handle() method can define arbitrary other instance variariables. """ def __init__(self, request, client_address, server): self.request = request self.client_address = client_address self.server = server self.setup() try: self.handle() finally: self.finish() def setup(self): pass def handle(self): pass def finish(self): pass # The following two classes make it possible to use the same service # class for stream or datagram servers. # Each class sets up these instance variables: # - rfile: a file object from which receives the request is read # - wfile: a file object to which the reply is written # When the handle() method returns, wfile is flushed properly class StreamRequestHandler(BaseRequestHandler): """Define self.rfile and self.wfile for stream sockets.""" # Default buffer sizes for rfile, wfile. # We default rfile to buffered because otherwise it could be # really slow for large data (a getc() call per byte); we make # wfile unbuffered because (a) often after a write() we want to # read and we need to flush the line; (b) big writes to unbuffered # files are typically optimized by stdio even when big reads # aren't. rbufsize = -1 wbufsize = 0 # A timeout to apply to the request socket, if not None. timeout = None # Disable nagle algorithm for this socket, if True. # Use only when wbufsize != 0, to avoid small packets. disable_nagle_algorithm = False def setup(self): self.connection = self.request if self.timeout is not None: self.connection.settimeout(self.timeout) if self.disable_nagle_algorithm: self.connection.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, True) self.rfile = self.connection.makefile('rb', self.rbufsize) self.wfile = self.connection.makefile('wb', self.wbufsize) def finish(self): if not self.wfile.closed: try: self.wfile.flush() except socket.error: # An final socket error may have occurred here, such as # the local error ECONNABORTED. pass self.wfile.close() self.rfile.close() class DatagramRequestHandler(BaseRequestHandler): # XXX Regrettably, I cannot get this working on Linux; # s.recvfrom() doesn't return a meaningful client address. """Define self.rfile and self.wfile for datagram sockets.""" def setup(self): from io import BytesIO self.packet, self.socket = self.request self.rfile = BytesIO(self.packet) self.wfile = BytesIO() def finish(self): self.socket.sendto(self.wfile.getvalue(), self.client_address) """ For Python < 2.7.2. total_ordering in versions prior to 2.7.2 is buggy. See http://bugs.python.org/issue10042 for details. For these versions use code borrowed from Python 2.7.3. From django.utils. """ import sys if sys.version_info >= (2, 7, 2): from functools import total_ordering else: def total_ordering(cls): """Class decorator that fills in missing ordering methods""" convert = { '__lt__': [('__gt__', lambda self, other: not (self < other or self == other)), ('__le__', lambda self, other: self < other or self == other), ('__ge__', lambda self, other: not self < other)], '__le__': [('__ge__', lambda self, other: not self <= other or self == other), ('__lt__', lambda self, other: self <= other and not self == other), ('__gt__', lambda self, other: not self <= other)], '__gt__': [('__lt__', lambda self, other: not (self > other or self == other)), ('__ge__', lambda self, other: self > other or self == other), ('__le__', lambda self, other: not self > other)], '__ge__': [('__le__', lambda self, other: (not self >= other) or self == other), ('__gt__', lambda self, other: self >= other and not self == other), ('__lt__', lambda self, other: not self >= other)] } roots = set(dir(cls)) & set(convert) if not roots: raise ValueError('must define at least one ordering operation: < > <= >=') root = max(roots) # prefer __lt__ to __le__ to __gt__ to __ge__ for opname, opfunc in convert[root]: if opname not in roots: opfunc.__name__ = opname opfunc.__doc__ = getattr(int, opname).__doc__ setattr(cls, opname, opfunc) return cls # Copyright (C) 2001-2007 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """ Backport of the Python 3.3 email package for Python-Future. A package for parsing, handling, and generating email messages. """ from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import # Install the surrogate escape handler here because this is used by many # modules in the email package. from future.utils import surrogateescape surrogateescape.register_surrogateescape() # (Should this be done globally by ``future``?) __version__ = '5.1.0' __all__ = [ 'base64mime', 'charset', 'encoders', 'errors', 'feedparser', 'generator', 'header', 'iterators', 'message', 'message_from_file', 'message_from_binary_file', 'message_from_string', 'message_from_bytes', 'mime', 'parser', 'quoprimime', 'utils', ] # Some convenience routines. Don't import Parser and Message as side-effects # of importing email since those cascadingly import most of the rest of the # email package. def message_from_string(s, *args, **kws): """Parse a string into a Message object model. Optional _class and strict are passed to the Parser constructor. """ from future.backports.email.parser import Parser return Parser(*args, **kws).parsestr(s) def message_from_bytes(s, *args, **kws): """Parse a bytes string into a Message object model. Optional _class and strict are passed to the Parser constructor. """ from future.backports.email.parser import BytesParser return BytesParser(*args, **kws).parsebytes(s) def message_from_file(fp, *args, **kws): """Read a file and parse its contents into a Message object model. Optional _class and strict are passed to the Parser constructor. """ from future.backports.email.parser import Parser return Parser(*args, **kws).parse(fp) def message_from_binary_file(fp, *args, **kws): """Read a binary file and parse its contents into a Message object model. Optional _class and strict are passed to the Parser constructor. """ from future.backports.email.parser import BytesParser return BytesParser(*args, **kws).parse(fp) """ Routines for manipulating RFC2047 encoded words. This is currently a package-private API, but will be considered for promotion to a public API if there is demand. """ from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import from future.builtins import bytes from future.builtins import chr from future.builtins import int from future.builtins import str # An ecoded word looks like this: # # =?charset[*lang]?cte?encoded_string?= # # for more information about charset see the charset module. Here it is one # of the preferred MIME charset names (hopefully; you never know when parsing). # cte (Content Transfer Encoding) is either 'q' or 'b' (ignoring case). In # theory other letters could be used for other encodings, but in practice this # (almost?) never happens. There could be a public API for adding entries # to the CTE tables, but YAGNI for now. 'q' is Quoted Printable, 'b' is # Base64. The meaning of encoded_string should be obvious. 'lang' is optional # as indicated by the brackets (they are not part of the syntax) but is almost # never encountered in practice. # # The general interface for a CTE decoder is that it takes the encoded_string # as its argument, and returns a tuple (cte_decoded_string, defects). The # cte_decoded_string is the original binary that was encoded using the # specified cte. 'defects' is a list of MessageDefect instances indicating any # problems encountered during conversion. 'charset' and 'lang' are the # corresponding strings extracted from the EW, case preserved. # # The general interface for a CTE encoder is that it takes a binary sequence # as input and returns the cte_encoded_string, which is an ascii-only string. # # Each decoder must also supply a length function that takes the binary # sequence as its argument and returns the length of the resulting encoded # string. # # The main API functions for the module are decode, which calls the decoder # referenced by the cte specifier, and encode, which adds the appropriate # RFC 2047 "chrome" to the encoded string, and can optionally automatically # select the shortest possible encoding. See their docstrings below for # details. import re import base64 import binascii import functools from string import ascii_letters, digits from future.backports.email import errors __all__ = ['decode_q', 'encode_q', 'decode_b', 'encode_b', 'len_q', 'len_b', 'decode', 'encode', ] # # Quoted Printable # # regex based decoder. _q_byte_subber = functools.partial(re.compile(br'=([a-fA-F0-9]{2})').sub, lambda m: bytes([int(m.group(1), 16)])) def decode_q(encoded): encoded = bytes(encoded.replace(b'_', b' ')) return _q_byte_subber(encoded), [] # dict mapping bytes to their encoded form class _QByteMap(dict): safe = bytes(b'-!*+/' + ascii_letters.encode('ascii') + digits.encode('ascii')) def __missing__(self, key): if key in self.safe: self[key] = chr(key) else: self[key] = "={:02X}".format(key) return self[key] _q_byte_map = _QByteMap() # In headers spaces are mapped to '_'. _q_byte_map[ord(' ')] = '_' def encode_q(bstring): return str(''.join(_q_byte_map[x] for x in bytes(bstring))) def len_q(bstring): return sum(len(_q_byte_map[x]) for x in bytes(bstring)) # # Base64 # def decode_b(encoded): defects = [] pad_err = len(encoded) % 4 if pad_err: defects.append(errors.InvalidBase64PaddingDefect()) padded_encoded = encoded + b'==='[:4-pad_err] else: padded_encoded = encoded try: # The validate kwarg to b64decode is not supported in Py2.x if not re.match(b'^[A-Za-z0-9+/]*={0,2}$', padded_encoded): raise binascii.Error('Non-base64 digit found') return base64.b64decode(padded_encoded), defects except binascii.Error: # Since we had correct padding, this must an invalid char error. defects = [errors.InvalidBase64CharactersDefect()] # The non-alphabet characters are ignored as far as padding # goes, but we don't know how many there are. So we'll just # try various padding lengths until something works. for i in 0, 1, 2, 3: try: return base64.b64decode(encoded+b'='*i), defects except (binascii.Error, TypeError): # Py2 raises a TypeError if i==0: defects.append(errors.InvalidBase64PaddingDefect()) else: # This should never happen. raise AssertionError("unexpected binascii.Error") def encode_b(bstring): return base64.b64encode(bstring).decode('ascii') def len_b(bstring): groups_of_3, leftover = divmod(len(bstring), 3) # 4 bytes out for each 3 bytes (or nonzero fraction thereof) in. return groups_of_3 * 4 + (4 if leftover else 0) _cte_decoders = { 'q': decode_q, 'b': decode_b, } def decode(ew): """Decode encoded word and return (string, charset, lang, defects) tuple. An RFC 2047/2243 encoded word has the form: =?charset*lang?cte?encoded_string?= where '*lang' may be omitted but the other parts may not be. This function expects exactly such a string (that is, it does not check the syntax and may raise errors if the string is not well formed), and returns the encoded_string decoded first from its Content Transfer Encoding and then from the resulting bytes into unicode using the specified charset. If the cte-decoded string does not successfully decode using the specified character set, a defect is added to the defects list and the unknown octets are replaced by the unicode 'unknown' character \uFDFF. The specified charset and language are returned. The default for language, which is rarely if ever encountered, is the empty string. """ _, charset, cte, cte_string, _ = str(ew).split('?') charset, _, lang = charset.partition('*') cte = cte.lower() # Recover the original bytes and do CTE decoding. bstring = cte_string.encode('ascii', 'surrogateescape') bstring, defects = _cte_decoders[cte](bstring) # Turn the CTE decoded bytes into unicode. try: string = bstring.decode(charset) except UnicodeError: defects.append(errors.UndecodableBytesDefect("Encoded word " "contains bytes not decodable using {} charset".format(charset))) string = bstring.decode(charset, 'surrogateescape') except LookupError: string = bstring.decode('ascii', 'surrogateescape') if charset.lower() != 'unknown-8bit': defects.append(errors.CharsetError("Unknown charset {} " "in encoded word; decoded as unknown bytes".format(charset))) return string, charset, lang, defects _cte_encoders = { 'q': encode_q, 'b': encode_b, } _cte_encode_length = { 'q': len_q, 'b': len_b, } def encode(string, charset='utf-8', encoding=None, lang=''): """Encode string using the CTE encoding that produces the shorter result. Produces an RFC 2047/2243 encoded word of the form: =?charset*lang?cte?encoded_string?= where '*lang' is omitted unless the 'lang' parameter is given a value. Optional argument charset (defaults to utf-8) specifies the charset to use to encode the string to binary before CTE encoding it. Optional argument 'encoding' is the cte specifier for the encoding that should be used ('q' or 'b'); if it is None (the default) the encoding which produces the shortest encoded sequence is used, except that 'q' is preferred if it is up to five characters longer. Optional argument 'lang' (default '') gives the RFC 2243 language string to specify in the encoded word. """ string = str(string) if charset == 'unknown-8bit': bstring = string.encode('ascii', 'surrogateescape') else: bstring = string.encode(charset) if encoding is None: qlen = _cte_encode_length['q'](bstring) blen = _cte_encode_length['b'](bstring) # Bias toward q. 5 is arbitrary. encoding = 'q' if qlen - blen < 5 else 'b' encoded = _cte_encoders[encoding](bstring) if lang: lang = '*' + lang return "=?{0}{1}?{2}?{3}?=".format(charset, lang, encoding, encoded) # Copyright (C) 2002-2007 Python Software Foundation # Contact: email-sig@python.org """Email address parsing code. Lifted directly from rfc822.py. This should eventually be rewritten. """ from __future__ import unicode_literals from __future__ import print_function from __future__ import division from __future__ import absolute_import from future.builtins import int __all__ = [ 'mktime_tz', 'parsedate', 'parsedate_tz', 'quote', ] import time, calendar SPACE = ' ' EMPTYSTRING = '' COMMASPACE = ', ' # Parse a date field _monthnames = ['jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul', 'aug', 'sep', 'oct', 'nov', 'dec', 'january', 'february', 'march', 'april', 'may', 'june', 'july', 'august', 'september', 'october', 'november', 'december'] _daynames = ['mon', 'tue', 'wed', 'thu', 'fri', 'sat', 'sun'] # The timezone table does not include the military time zones defined # in RFC822, other than Z. According to RFC1123, the description in # RFC822 gets the signs wrong, so we can't rely on any such time # zones. RFC1123 recommends that numeric timezone indicators be used # instead of timezone names. _timezones = {'UT':0, 'UTC':0, 'GMT':0, 'Z':0, 'AST': -400, 'ADT': -300, # Atlantic (used in Canada) 'EST': -500, 'EDT': -400, # Eastern 'CST': -600, 'CDT': -500, # Central 'MST': -700, 'MDT': -600, # Mountain 'PST': -800, 'PDT': -700 # Pacific } def parsedate_tz(data): """Convert a date string to a time tuple. Accounts for military timezones. """ res = _parsedate_tz(data) if not res: return if res[9] is None: res[9] = 0 return tuple(res) def _parsedate_tz(data): """Convert date to extended time tuple. The last (additional) element is the time zone offset in seconds, except if the timezone was specified as -0000. In that case the last element is None. This indicates a UTC timestamp that explicitly declaims knowledge of the source timezone, as opposed to a +0000 timestamp that indicates the source timezone really was UTC. """ if not data: return data = data.split() # The FWS after the comma after the day-of-week is optional, so search and # adjust for this. if data[0].endswith(',') or data[0].lower() in _daynames: # There's a dayname here. Skip it del data[0] else: i = data[0].rfind(',') if i >= 0: data[0] = data[0][i+1:] if len(data) == 3: # RFC 850 date, deprecated stuff = data[0].split('-') if len(stuff) == 3: data = stuff + data[1:] if len(data) == 4: s = data[3] i = s.find('+') if i == -1: i = s.find('-') if i > 0: data[3:] = [s[:i], s[i:]] else: data.append('') # Dummy tz if len(data) < 5: return None data = data[:5] [dd, mm, yy, tm, tz] = data mm = mm.lower() if mm not in _monthnames: dd, mm = mm, dd.lower() if mm not in _monthnames: return None mm = _monthnames.index(mm) + 1 if mm > 12: mm -= 12 if dd[-1] == ',': dd = dd[:-1] i = yy.find(':') if i > 0: yy, tm = tm, yy if yy[-1] == ',': yy = yy[:-1] if not yy[0].isdigit(): yy, tz = tz, yy if tm[-1] == ',': tm = tm[:-1] tm = tm.split(':') if len(tm) == 2: [thh, tmm] = tm tss = '0' elif len(tm) == 3: [thh, tmm, tss] = tm elif len(tm) == 1 and '.' in tm[0]: # Some non-compliant MUAs use '.' to separate time elements. tm = tm[0].split('.') if len(tm) == 2: [thh, tmm] = tm tss = 0 elif len(tm) == 3: [thh, tmm, tss] = tm else: return None try: yy = int(yy) dd = int(dd) thh = int(thh) tmm = int(tmm) tss = int(tss) except ValueError: return None # Check for a yy specified in two-digit format, then convert it to the # appropriate four-digit format, according to the POSIX standard. RFC 822 # calls for a two-digit yy, but RFC 2822 (which obsoletes RFC 822) # mandates a 4-digit yy. For more information, see the documentation for # the time module. if yy < 100: # The year is between 1969 and 1999 (inclusive). if yy > 68: yy += 1900 # The year is between 2000 and 2068 (inclusive). else: yy += 2000 tzoffset = None tz = tz.upper() if tz in _timezones: tzoffset = _timezones[tz] else: try: tzoffset = int(tz) except ValueError: pass if tzoffset==0 and tz.startswith('-'): tzoffset = None # Convert a timezone offset into seconds ; -0500 -> -18000 if tzoffset: if tzoffset < 0: tzsign = -1 tzoffset = -tzoffset else: tzsign = 1 tzoffset = tzsign * ( (tzoffset//100)*3600 + (tzoffset % 100)*60) # Daylight Saving Time flag is set to -1, since DST is unknown. return [yy, mm, dd, thh, tmm, tss, 0, 1, -1, tzoffset] def parsedate(data): """Convert a time string to a time tuple.""" t = parsedate_tz(data) if isinstance(t, tuple): return t[:9] else: return t def mktime_tz(data): """Turn a 10-tuple as returned by parsedate_tz() into a POSIX timestamp.""" if data[9] is None: # No zone info, so localtime is better assumption than GMT return time.mktime(data[:8] + (-1,)) else: t = calendar.timegm(data) return t - data[9] def quote(str): """Prepare string to be used in a quoted string. Turns backslash and double quote characters into quoted pairs. These are the only characters that need to be quoted inside a quoted string. Does not add the surrounding double quotes. """ return str.replace('\\', '\\\\').replace('"', '\\"') class AddrlistClass(object): """Address parser class by Ben Escoto. To understand what this class does, it helps to have a copy of RFC 2822 in front of you. Note: this class interface is deprecated and may be removed in the future. Use email.utils.AddressList instead. """ def __init__(self, field): """Initialize a new instance. `field' is an unparsed address header field, containing one or more addresses. """ self.specials = '()<>@,:;.\"[]' self.pos = 0 self.LWS = ' \t' self.CR = '\r\n' self.FWS = self.LWS + self.CR self.atomends = self.specials + self.LWS + self.CR # Note that RFC 2822 now specifies `.' as obs-phrase, meaning that it # is obsolete syntax. RFC 2822 requires that we recognize obsolete # syntax, so allow dots in phrases. self.phraseends = self.atomends.replace('.', '') self.field = field self.commentlist = [] def gotonext(self): """Skip white space and extract comments.""" wslist = [] while self.pos < len(self.field): if self.field[self.pos] in self.LWS + '\n\r': if self.field[self.pos] not in '\n\r': wslist.append(self.field[self.pos]) self.pos += 1 elif self.field[self.pos] == '(': self.commentlist.append(self.getcomment()) else: break return EMPTYSTRING.join(wslist) def getaddrlist(self): """Parse all addresses. Returns a list containing all of the addresses. """ result = [] while self.pos < len(self.field): ad = self.getaddress() if ad: result += ad else: result.append(('', '')) return result def getaddress(self): """Parse the next address.""" self.commentlist = [] self.gotonext() oldpos = self.pos oldcl = self.commentlist plist = self.getphraselist() self.gotonext() returnlist = [] if self.pos >= len(self.field): # Bad email address technically, no domain. if plist: returnlist = [(SPACE.join(self.commentlist), plist[0])] elif self.field[self.pos] in '.@': # email address is just an addrspec # this isn't very efficient since we start over self.pos = oldpos self.commentlist = oldcl addrspec = self.getaddrspec() returnlist = [(SPACE.join(self.commentlist), addrspec)] elif self.field[self.pos] == ':': # address is a group returnlist = [] fieldlen = len(self.field) self.pos += 1 while self.pos < len(self.field): self.gotonext() if self.pos < fieldlen and self.field[self.pos] == ';': self.pos += 1 break returnlist = returnlist + self.getaddress() elif self.field[self.pos] == '<': # Address is a phrase then a route addr routeaddr = self.getrouteaddr() if self.commentlist: returnlist = [(SPACE.join(plist) + ' (' + ' '.join(self.commentlist) + ')', routeaddr)] else: returnlist = [(SPACE.join(plist), routeaddr)] else: if plist: returnlist = [(SPACE.join(self.commentlist), plist[0])] elif self.field[self.pos] in self.specials: self.pos += 1 self.gotonext() if self.pos < len(self.field) and self.field[self.pos] == ',': self.pos += 1 return returnlist def getrouteaddr(self): """Parse a route address (Return-path value). This method just skips all the route stuff and returns the addrspec. """ if self.field[self.pos] != '<': return expectroute = False self.pos += 1 self.gotonext() adlist = '' while self.pos < len(self.field): if expectroute: self.getdomain() expectroute = False elif self.field[self.pos] == '>': self.pos += 1 break elif self.field[self.pos] == '@': self.pos += 1 expectroute = True elif self.field[self.pos] == ':': self.pos += 1 else: adlist = self.getaddrspec() self.pos += 1 break self.gotonext() return adlist def getaddrspec(self): """Parse an RFC 2822 addr-spec.""" aslist = [] self.gotonext() while self.pos < len(self.field): preserve_ws = True if self.field[self.pos] == '.': if aslist and not aslist[-1].strip(): aslist.pop() aslist.append('.') self.pos += 1 preserve_ws = False elif self.field[self.pos] == '"': aslist.append('"%s"' % quote(self.getquote())) elif self.field[self.pos] in self.atomends: if aslist and not aslist[-1].strip(): aslist.pop() break else: aslist.append(self.getatom()) ws = self.gotonext() if preserve_ws and ws: aslist.append(ws) if self.pos >= len(self.field) or self.field[self.pos] != '@': return EMPTYSTRING.join(aslist) aslist.append('@') self.pos += 1 self.gotonext() return EMPTYSTRING.join(aslist) + self.getdomain() def getdomain(self): """Get the complete domain name from an address.""" sdlist = [] while self.pos < len(self.field): if self.field[self.pos] in self.LWS: self.pos += 1 elif self.field[self.pos] == '(': self.commentlist.append(self.getcomment()) elif self.field[self.pos] == '[': sdlist.append(self.getdomainliteral()) elif self.field[self.pos] == '.': self.pos += 1 sdlist.append('.') elif self.field[self.pos] in self.atomends: break else: sdlist.append(self.getatom()) return EMPTYSTRING.join(sdlist) def getdelimited(self, beginchar, endchars, allowcomments=True): """Parse a header fragment delimited by special characters. `beginchar' is the start character for the fragment. If self is not looking at an instance of `beginchar' then getdelimited returns the empty string. `endchars' is a sequence of allowable end-delimiting characters. Parsing stops when one of these is encountered. If `allowcomments' is non-zero, embedded RFC 2822 comments are allowed within the parsed fragment. """ if self.field[self.pos] != beginchar: return '' slist = [''] quote = False self.pos += 1 while self.pos < len(self.field): if quote: slist.append(self.field[self.pos]) quote = False elif self.field[self.pos] in endchars: self.pos += 1 break elif allowcomments and self.field[self.pos] == '(': slist.append(self.getcomment()) continue # have already advanced pos from getcomment elif self.field[self.pos] == '\\': quote = True else: slist.append(self.field[self.pos]) self.pos += 1 return EMPTYSTRING.join(slist) def getquote(self): """Get a quote-delimited fragment from self's field.""" return self.getdelimited('"', '"\r', False) def getcomment(self): """Get a parenthesis-delimited fragment from self's field.""" return self.getdelimited('(', ')\r', True) def getdomainliteral(self): """Parse an RFC 2822 domain-literal.""" return '[%s]' % self.getdelimited('[', ']\r', False) def getatom(self, atomends=None): """Parse an RFC 2822 atom. Optional atomends specifies a different set of end token delimiters (the default is to use self.atomends). This is used e.g. in getphraselist() since phrase endings must not include the `.' (which is legal in phrases).""" atomlist = [''] if atomends is None: atomends = self.atomends while self.pos < len(self.field): if self.field[self.pos] in atomends: break else: atomlist.append(self.field[self.pos]) self.pos += 1 return EMPTYSTRING.join(atomlist) def getphraselist(self): """Parse a sequence of RFC 2822 phrases. A phrase is a sequence of words, which are in turn either RFC 2822 atoms or quoted-strings. Phrases are canonicalized by squeezing all runs of continuous whitespace into one space. """ plist = [] while self.pos < len(self.field): if self.field[self.pos] in self.FWS: self.pos += 1 elif self.field[self.pos] == '"': plist.append(self.getquote()) elif self.field[self.pos] == '(': self.commentlist.append(self.getcomment()) elif self.field[self.pos] in self.phraseends: break else: plist.append(self.getatom(self.phraseends)) return plist class AddressList(AddrlistClass): """An AddressList encapsulates a list of parsed RFC 2822 addresses.""" def __init__(self, field): AddrlistClass.__init__(self, field) if field: self.addresslist = self.getaddrlist() else: self.addresslist = [] def __len__(self): return len(self.addresslist) def __add__(self, other): # Set union newaddr = AddressList(None) newaddr.addresslist = self.addresslist[:] for x in other.addresslist: if not x in self.addresslist: newaddr.addresslist.append(x) return newaddr def __iadd__(self, other): # Set union, in-place for x in other.addresslist: if not x in self.addresslist: self.addresslist.append(x) return self def __sub__(self, other): # Set difference newaddr = AddressList(None) for x in self.addresslist: if not x in other.addresslist: newaddr.addresslist.append(x) return newaddr def __isub__(self, other): # Set difference, in-place for x in other.addresslist: if x in self.addresslist: self.addresslist.remove(x) return self def __getitem__(self, index): # Make indexing, slices, and 'in' work return self.addresslist[index] """Policy framework for the email package. Allows fine grained feature control of how the package parses and emits data. """ from __future__ import unicode_literals from __future__ import print_function from __future__ import division from __future__ import absolute_import from future.builtins import super from future.builtins import str from future.utils import with_metaclass import abc from future.backports.email import header from future.backports.email import charset as _charset from future.backports.email.utils import _has_surrogates __all__ = [ 'Policy', 'Compat32', 'compat32', ] class _PolicyBase(object): """Policy Object basic framework. This class is useless unless subclassed. A subclass should define class attributes with defaults for any values that are to be managed by the Policy object. The constructor will then allow non-default values to be set for these attributes at instance creation time. The instance will be callable, taking these same attributes keyword arguments, and returning a new instance identical to the called instance except for those values changed by the keyword arguments. Instances may be added, yielding new instances with any non-default values from the right hand operand overriding those in the left hand operand. That is, A + B == A() The repr of an instance can be used to reconstruct the object if and only if the repr of the values can be used to reconstruct those values. """ def __init__(self, **kw): """Create new Policy, possibly overriding some defaults. See class docstring for a list of overridable attributes. """ for name, value in kw.items(): if hasattr(self, name): super(_PolicyBase,self).__setattr__(name, value) else: raise TypeError( "{!r} is an invalid keyword argument for {}".format( name, self.__class__.__name__)) def __repr__(self): args = [ "{}={!r}".format(name, value) for name, value in self.__dict__.items() ] return "{}({})".format(self.__class__.__name__, ', '.join(args)) def clone(self, **kw): """Return a new instance with specified attributes changed. The new instance has the same attribute values as the current object, except for the changes passed in as keyword arguments. """ newpolicy = self.__class__.__new__(self.__class__) for attr, value in self.__dict__.items(): object.__setattr__(newpolicy, attr, value) for attr, value in kw.items(): if not hasattr(self, attr): raise TypeError( "{!r} is an invalid keyword argument for {}".format( attr, self.__class__.__name__)) object.__setattr__(newpolicy, attr, value) return newpolicy def __setattr__(self, name, value): if hasattr(self, name): msg = "{!r} object attribute {!r} is read-only" else: msg = "{!r} object has no attribute {!r}" raise AttributeError(msg.format(self.__class__.__name__, name)) def __add__(self, other): """Non-default values from right operand override those from left. The object returned is a new instance of the subclass. """ return self.clone(**other.__dict__) def _append_doc(doc, added_doc): doc = doc.rsplit('\n', 1)[0] added_doc = added_doc.split('\n', 1)[1] return doc + '\n' + added_doc def _extend_docstrings(cls): if cls.__doc__ and cls.__doc__.startswith('+'): cls.__doc__ = _append_doc(cls.__bases__[0].__doc__, cls.__doc__) for name, attr in cls.__dict__.items(): if attr.__doc__ and attr.__doc__.startswith('+'): for c in (c for base in cls.__bases__ for c in base.mro()): doc = getattr(getattr(c, name), '__doc__') if doc: attr.__doc__ = _append_doc(doc, attr.__doc__) break return cls class Policy(with_metaclass(abc.ABCMeta, _PolicyBase)): r"""Controls for how messages are interpreted and formatted. Most of the classes and many of the methods in the email package accept Policy objects as parameters. A Policy object contains a set of values and functions that control how input is interpreted and how output is rendered. For example, the parameter 'raise_on_defect' controls whether or not an RFC violation results in an error being raised or not, while 'max_line_length' controls the maximum length of output lines when a Message is serialized. Any valid attribute may be overridden when a Policy is created by passing it as a keyword argument to the constructor. Policy objects are immutable, but a new Policy object can be created with only certain values changed by calling the Policy instance with keyword arguments. Policy objects can also be added, producing a new Policy object in which the non-default attributes set in the right hand operand overwrite those specified in the left operand. Settable attributes: raise_on_defect -- If true, then defects should be raised as errors. Default: False. linesep -- string containing the value to use as separation between output lines. Default '\n'. cte_type -- Type of allowed content transfer encodings 7bit -- ASCII only 8bit -- Content-Transfer-Encoding: 8bit is allowed Default: 8bit. Also controls the disposition of (RFC invalid) binary data in headers; see the documentation of the binary_fold method. max_line_length -- maximum length of lines, excluding 'linesep', during serialization. None or 0 means no line wrapping is done. Default is 78. """ raise_on_defect = False linesep = '\n' cte_type = '8bit' max_line_length = 78 def handle_defect(self, obj, defect): """Based on policy, either raise defect or call register_defect. handle_defect(obj, defect) defect should be a Defect subclass, but in any case must be an Exception subclass. obj is the object on which the defect should be registered if it is not raised. If the raise_on_defect is True, the defect is raised as an error, otherwise the object and the defect are passed to register_defect. This method is intended to be called by parsers that discover defects. The email package parsers always call it with Defect instances. """ if self.raise_on_defect: raise defect self.register_defect(obj, defect) def register_defect(self, obj, defect): """Record 'defect' on 'obj'. Called by handle_defect if raise_on_defect is False. This method is part of the Policy API so that Policy subclasses can implement custom defect handling. The default implementation calls the append method of the defects attribute of obj. The objects used by the email package by default that get passed to this method will always have a defects attribute with an append method. """ obj.defects.append(defect) def header_max_count(self, name): """Return the maximum allowed number of headers named 'name'. Called when a header is added to a Message object. If the returned value is not 0 or None, and there are already a number of headers with the name 'name' equal to the value returned, a ValueError is raised. Because the default behavior of Message's __setitem__ is to append the value to the list of headers, it is easy to create duplicate headers without realizing it. This method allows certain headers to be limited in the number of instances of that header that may be added to a Message programmatically. (The limit is not observed by the parser, which will faithfully produce as many headers as exist in the message being parsed.) The default implementation returns None for all header names. """ return None @abc.abstractmethod def header_source_parse(self, sourcelines): """Given a list of linesep terminated strings constituting the lines of a single header, return the (name, value) tuple that should be stored in the model. The input lines should retain their terminating linesep characters. The lines passed in by the email package may contain surrogateescaped binary data. """ raise NotImplementedError @abc.abstractmethod def header_store_parse(self, name, value): """Given the header name and the value provided by the application program, return the (name, value) that should be stored in the model. """ raise NotImplementedError @abc.abstractmethod def header_fetch_parse(self, name, value): """Given the header name and the value from the model, return the value to be returned to the application program that is requesting that header. The value passed in by the email package may contain surrogateescaped binary data if the lines were parsed by a BytesParser. The returned value should not contain any surrogateescaped data. """ raise NotImplementedError @abc.abstractmethod def fold(self, name, value): """Given the header name and the value from the model, return a string containing linesep characters that implement the folding of the header according to the policy controls. The value passed in by the email package may contain surrogateescaped binary data if the lines were parsed by a BytesParser. The returned value should not contain any surrogateescaped data. """ raise NotImplementedError @abc.abstractmethod def fold_binary(self, name, value): """Given the header name and the value from the model, return binary data containing linesep characters that implement the folding of the header according to the policy controls. The value passed in by the email package may contain surrogateescaped binary data. """ raise NotImplementedError @_extend_docstrings class Compat32(Policy): """+ This particular policy is the backward compatibility Policy. It replicates the behavior of the email package version 5.1. """ def _sanitize_header(self, name, value): # If the header value contains surrogates, return a Header using # the unknown-8bit charset to encode the bytes as encoded words. if not isinstance(value, str): # Assume it is already a header object return value if _has_surrogates(value): return header.Header(value, charset=_charset.UNKNOWN8BIT, header_name=name) else: return value def header_source_parse(self, sourcelines): """+ The name is parsed as everything up to the ':' and returned unmodified. The value is determined by stripping leading whitespace off the remainder of the first line, joining all subsequent lines together, and stripping any trailing carriage return or linefeed characters. """ name, value = sourcelines[0].split(':', 1) value = value.lstrip(' \t') + ''.join(sourcelines[1:]) return (name, value.rstrip('\r\n')) def header_store_parse(self, name, value): """+ The name and value are returned unmodified. """ return (name, value) def header_fetch_parse(self, name, value): """+ If the value contains binary data, it is converted into a Header object using the unknown-8bit charset. Otherwise it is returned unmodified. """ return self._sanitize_header(name, value) def fold(self, name, value): """+ Headers are folded using the Header folding algorithm, which preserves existing line breaks in the value, and wraps each resulting line to the max_line_length. Non-ASCII binary data are CTE encoded using the unknown-8bit charset. """ return self._fold(name, value, sanitize=True) def fold_binary(self, name, value): """+ Headers are folded using the Header folding algorithm, which preserves existing line breaks in the value, and wraps each resulting line to the max_line_length. If cte_type is 7bit, non-ascii binary data is CTE encoded using the unknown-8bit charset. Otherwise the original source header is used, with its existing line breaks and/or binary data. """ folded = self._fold(name, value, sanitize=self.cte_type=='7bit') return folded.encode('ascii', 'surrogateescape') def _fold(self, name, value, sanitize): parts = [] parts.append('%s: ' % name) if isinstance(value, str): if _has_surrogates(value): if sanitize: h = header.Header(value, charset=_charset.UNKNOWN8BIT, header_name=name) else: # If we have raw 8bit data in a byte string, we have no idea # what the encoding is. There is no safe way to split this # string. If it's ascii-subset, then we could do a normal # ascii split, but if it's multibyte then we could break the # string. There's no way to know so the least harm seems to # be to not split the string and risk it being too long. parts.append(value) h = None else: h = header.Header(value, header_name=name) else: # Assume it is a Header-like object. h = value if h is not None: parts.append(h.encode(linesep=self.linesep, maxlinelen=self.max_line_length)) parts.append(self.linesep) return ''.join(parts) compat32 = Compat32() # Copyright (C) 2002-2007 Python Software Foundation # Author: Ben Gertzfield # Contact: email-sig@python.org """Base64 content transfer encoding per RFCs 2045-2047. This module handles the content transfer encoding method defined in RFC 2045 to encode arbitrary 8-bit data using the three 8-bit bytes in four 7-bit characters encoding known as Base64. It is used in the MIME standards for email to attach images, audio, and text using some 8-bit character sets to messages. This module provides an interface to encode and decode both headers and bodies with Base64 encoding. RFC 2045 defines a method for including character set information in an `encoded-word' in a header. This method is commonly used for 8-bit real names in To:, From:, Cc:, etc. fields, as well as Subject: lines. This module does not do the line wrapping or end-of-line character conversion necessary for proper internationalized headers; it only does dumb encoding and decoding. To deal with the various line wrapping issues, use the email.header module. """ from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import from future.builtins import range from future.builtins import bytes __all__ = [ 'body_decode', 'body_encode', 'decode', 'decodestring', 'header_encode', 'header_length', ] from base64 import b64encode from binascii import b2a_base64, a2b_base64 CRLF = '\r\n' NL = '\n' EMPTYSTRING = '' # See also Charset.py MISC_LEN = 7 # Helpers def header_length(bytearray): """Return the length of s when it is encoded with base64.""" groups_of_3, leftover = divmod(len(bytearray), 3) # 4 bytes out for each 3 bytes (or nonzero fraction thereof) in. n = groups_of_3 * 4 if leftover: n += 4 return n def header_encode(header_bytes, charset='iso-8859-1'): """Encode a single header line with Base64 encoding in a given charset. charset names the character set to use to encode the header. It defaults to iso-8859-1. Base64 encoding is defined in RFC 2045. """ if not header_bytes: return "" if isinstance(header_bytes, str): header_bytes = header_bytes.encode(charset) encoded = b64encode(header_bytes).decode("ascii") return '=?%s?b?%s?=' % (charset, encoded) def body_encode(s, maxlinelen=76, eol=NL): r"""Encode a string with base64. Each line will be wrapped at, at most, maxlinelen characters (defaults to 76 characters). Each line of encoded text will end with eol, which defaults to "\n". Set this to "\r\n" if you will be using the result of this function directly in an email. """ if not s: return s encvec = [] max_unencoded = maxlinelen * 3 // 4 for i in range(0, len(s), max_unencoded): # BAW: should encode() inherit b2a_base64()'s dubious behavior in # adding a newline to the encoded string? enc = b2a_base64(s[i:i + max_unencoded]).decode("ascii") if enc.endswith(NL) and eol != NL: enc = enc[:-1] + eol encvec.append(enc) return EMPTYSTRING.join(encvec) def decode(string): """Decode a raw base64 string, returning a bytes object. This function does not parse a full MIME header value encoded with base64 (like =?iso-8895-1?b?bmloISBuaWgh?=) -- please use the high level email.header class for that functionality. """ if not string: return bytes() elif isinstance(string, str): return a2b_base64(string.encode('raw-unicode-escape')) else: return a2b_base64(string) # For convenience and backwards compatibility w/ standard base64 module body_decode = decode decodestring = decode from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import from future.builtins import str from future.builtins import next # Copyright (C) 2001-2007 Python Software Foundation # Author: Ben Gertzfield, Barry Warsaw # Contact: email-sig@python.org __all__ = [ 'Charset', 'add_alias', 'add_charset', 'add_codec', ] from functools import partial from future.backports import email from future.backports.email import errors from future.backports.email.encoders import encode_7or8bit # Flags for types of header encodings QP = 1 # Quoted-Printable BASE64 = 2 # Base64 SHORTEST = 3 # the shorter of QP and base64, but only for headers # In "=?charset?q?hello_world?=", the =?, ?q?, and ?= add up to 7 RFC2047_CHROME_LEN = 7 DEFAULT_CHARSET = 'us-ascii' UNKNOWN8BIT = 'unknown-8bit' EMPTYSTRING = '' # Defaults CHARSETS = { # input header enc body enc output conv 'iso-8859-1': (QP, QP, None), 'iso-8859-2': (QP, QP, None), 'iso-8859-3': (QP, QP, None), 'iso-8859-4': (QP, QP, None), # iso-8859-5 is Cyrillic, and not especially used # iso-8859-6 is Arabic, also not particularly used # iso-8859-7 is Greek, QP will not make it readable # iso-8859-8 is Hebrew, QP will not make it readable 'iso-8859-9': (QP, QP, None), 'iso-8859-10': (QP, QP, None), # iso-8859-11 is Thai, QP will not make it readable 'iso-8859-13': (QP, QP, None), 'iso-8859-14': (QP, QP, None), 'iso-8859-15': (QP, QP, None), 'iso-8859-16': (QP, QP, None), 'windows-1252':(QP, QP, None), 'viscii': (QP, QP, None), 'us-ascii': (None, None, None), 'big5': (BASE64, BASE64, None), 'gb2312': (BASE64, BASE64, None), 'euc-jp': (BASE64, None, 'iso-2022-jp'), 'shift_jis': (BASE64, None, 'iso-2022-jp'), 'iso-2022-jp': (BASE64, None, None), 'koi8-r': (BASE64, BASE64, None), 'utf-8': (SHORTEST, BASE64, 'utf-8'), } # Aliases for other commonly-used names for character sets. Map # them to the real ones used in email. ALIASES = { 'latin_1': 'iso-8859-1', 'latin-1': 'iso-8859-1', 'latin_2': 'iso-8859-2', 'latin-2': 'iso-8859-2', 'latin_3': 'iso-8859-3', 'latin-3': 'iso-8859-3', 'latin_4': 'iso-8859-4', 'latin-4': 'iso-8859-4', 'latin_5': 'iso-8859-9', 'latin-5': 'iso-8859-9', 'latin_6': 'iso-8859-10', 'latin-6': 'iso-8859-10', 'latin_7': 'iso-8859-13', 'latin-7': 'iso-8859-13', 'latin_8': 'iso-8859-14', 'latin-8': 'iso-8859-14', 'latin_9': 'iso-8859-15', 'latin-9': 'iso-8859-15', 'latin_10':'iso-8859-16', 'latin-10':'iso-8859-16', 'cp949': 'ks_c_5601-1987', 'euc_jp': 'euc-jp', 'euc_kr': 'euc-kr', 'ascii': 'us-ascii', } # Map charsets to their Unicode codec strings. CODEC_MAP = { 'gb2312': 'eucgb2312_cn', 'big5': 'big5_tw', # Hack: We don't want *any* conversion for stuff marked us-ascii, as all # sorts of garbage might be sent to us in the guise of 7-bit us-ascii. # Let that stuff pass through without conversion to/from Unicode. 'us-ascii': None, } # Convenience functions for extending the above mappings def add_charset(charset, header_enc=None, body_enc=None, output_charset=None): """Add character set properties to the global registry. charset is the input character set, and must be the canonical name of a character set. Optional header_enc and body_enc is either Charset.QP for quoted-printable, Charset.BASE64 for base64 encoding, Charset.SHORTEST for the shortest of qp or base64 encoding, or None for no encoding. SHORTEST is only valid for header_enc. It describes how message headers and message bodies in the input charset are to be encoded. Default is no encoding. Optional output_charset is the character set that the output should be in. Conversions will proceed from input charset, to Unicode, to the output charset when the method Charset.convert() is called. The default is to output in the same character set as the input. Both input_charset and output_charset must have Unicode codec entries in the module's charset-to-codec mapping; use add_codec(charset, codecname) to add codecs the module does not know about. See the codecs module's documentation for more information. """ if body_enc == SHORTEST: raise ValueError('SHORTEST not allowed for body_enc') CHARSETS[charset] = (header_enc, body_enc, output_charset) def add_alias(alias, canonical): """Add a character set alias. alias is the alias name, e.g. latin-1 canonical is the character set's canonical name, e.g. iso-8859-1 """ ALIASES[alias] = canonical def add_codec(charset, codecname): """Add a codec that map characters in the given charset to/from Unicode. charset is the canonical name of a character set. codecname is the name of a Python codec, as appropriate for the second argument to the unicode() built-in, or to the encode() method of a Unicode string. """ CODEC_MAP[charset] = codecname # Convenience function for encoding strings, taking into account # that they might be unknown-8bit (ie: have surrogate-escaped bytes) def _encode(string, codec): string = str(string) if codec == UNKNOWN8BIT: return string.encode('ascii', 'surrogateescape') else: return string.encode(codec) class Charset(object): """Map character sets to their email properties. This class provides information about the requirements imposed on email for a specific character set. It also provides convenience routines for converting between character sets, given the availability of the applicable codecs. Given a character set, it will do its best to provide information on how to use that character set in an email in an RFC-compliant way. Certain character sets must be encoded with quoted-printable or base64 when used in email headers or bodies. Certain character sets must be converted outright, and are not allowed in email. Instances of this module expose the following information about a character set: input_charset: The initial character set specified. Common aliases are converted to their `official' email names (e.g. latin_1 is converted to iso-8859-1). Defaults to 7-bit us-ascii. header_encoding: If the character set must be encoded before it can be used in an email header, this attribute will be set to Charset.QP (for quoted-printable), Charset.BASE64 (for base64 encoding), or Charset.SHORTEST for the shortest of QP or BASE64 encoding. Otherwise, it will be None. body_encoding: Same as header_encoding, but describes the encoding for the mail message's body, which indeed may be different than the header encoding. Charset.SHORTEST is not allowed for body_encoding. output_charset: Some character sets must be converted before they can be used in email headers or bodies. If the input_charset is one of them, this attribute will contain the name of the charset output will be converted to. Otherwise, it will be None. input_codec: The name of the Python codec used to convert the input_charset to Unicode. If no conversion codec is necessary, this attribute will be None. output_codec: The name of the Python codec used to convert Unicode to the output_charset. If no conversion codec is necessary, this attribute will have the same value as the input_codec. """ def __init__(self, input_charset=DEFAULT_CHARSET): # RFC 2046, $4.1.2 says charsets are not case sensitive. We coerce to # unicode because its .lower() is locale insensitive. If the argument # is already a unicode, we leave it at that, but ensure that the # charset is ASCII, as the standard (RFC XXX) requires. try: if isinstance(input_charset, str): input_charset.encode('ascii') else: input_charset = str(input_charset, 'ascii') except UnicodeError: raise errors.CharsetError(input_charset) input_charset = input_charset.lower() # Set the input charset after filtering through the aliases self.input_charset = ALIASES.get(input_charset, input_charset) # We can try to guess which encoding and conversion to use by the # charset_map dictionary. Try that first, but let the user override # it. henc, benc, conv = CHARSETS.get(self.input_charset, (SHORTEST, BASE64, None)) if not conv: conv = self.input_charset # Set the attributes, allowing the arguments to override the default. self.header_encoding = henc self.body_encoding = benc self.output_charset = ALIASES.get(conv, conv) # Now set the codecs. If one isn't defined for input_charset, # guess and try a Unicode codec with the same name as input_codec. self.input_codec = CODEC_MAP.get(self.input_charset, self.input_charset) self.output_codec = CODEC_MAP.get(self.output_charset, self.output_charset) def __str__(self): return self.input_charset.lower() __repr__ = __str__ def __eq__(self, other): return str(self) == str(other).lower() def __ne__(self, other): return not self.__eq__(other) def get_body_encoding(self): """Return the content-transfer-encoding used for body encoding. This is either the string `quoted-printable' or `base64' depending on the encoding used, or it is a function in which case you should call the function with a single argument, the Message object being encoded. The function should then set the Content-Transfer-Encoding header itself to whatever is appropriate. Returns "quoted-printable" if self.body_encoding is QP. Returns "base64" if self.body_encoding is BASE64. Returns conversion function otherwise. """ assert self.body_encoding != SHORTEST if self.body_encoding == QP: return 'quoted-printable' elif self.body_encoding == BASE64: return 'base64' else: return encode_7or8bit def get_output_charset(self): """Return the output character set. This is self.output_charset if that is not None, otherwise it is self.input_charset. """ return self.output_charset or self.input_charset def header_encode(self, string): """Header-encode a string by converting it first to bytes. The type of encoding (base64 or quoted-printable) will be based on this charset's `header_encoding`. :param string: A unicode string for the header. It must be possible to encode this string to bytes using the character set's output codec. :return: The encoded string, with RFC 2047 chrome. """ codec = self.output_codec or 'us-ascii' header_bytes = _encode(string, codec) # 7bit/8bit encodings return the string unchanged (modulo conversions) encoder_module = self._get_encoder(header_bytes) if encoder_module is None: return string return encoder_module.header_encode(header_bytes, codec) def header_encode_lines(self, string, maxlengths): """Header-encode a string by converting it first to bytes. This is similar to `header_encode()` except that the string is fit into maximum line lengths as given by the argument. :param string: A unicode string for the header. It must be possible to encode this string to bytes using the character set's output codec. :param maxlengths: Maximum line length iterator. Each element returned from this iterator will provide the next maximum line length. This parameter is used as an argument to built-in next() and should never be exhausted. The maximum line lengths should not count the RFC 2047 chrome. These line lengths are only a hint; the splitter does the best it can. :return: Lines of encoded strings, each with RFC 2047 chrome. """ # See which encoding we should use. codec = self.output_codec or 'us-ascii' header_bytes = _encode(string, codec) encoder_module = self._get_encoder(header_bytes) encoder = partial(encoder_module.header_encode, charset=codec) # Calculate the number of characters that the RFC 2047 chrome will # contribute to each line. charset = self.get_output_charset() extra = len(charset) + RFC2047_CHROME_LEN # Now comes the hard part. We must encode bytes but we can't split on # bytes because some character sets are variable length and each # encoded word must stand on its own. So the problem is you have to # encode to bytes to figure out this word's length, but you must split # on characters. This causes two problems: first, we don't know how # many octets a specific substring of unicode characters will get # encoded to, and second, we don't know how many ASCII characters # those octets will get encoded to. Unless we try it. Which seems # inefficient. In the interest of being correct rather than fast (and # in the hope that there will be few encoded headers in any such # message), brute force it. :( lines = [] current_line = [] maxlen = next(maxlengths) - extra for character in string: current_line.append(character) this_line = EMPTYSTRING.join(current_line) length = encoder_module.header_length(_encode(this_line, charset)) if length > maxlen: # This last character doesn't fit so pop it off. current_line.pop() # Does nothing fit on the first line? if not lines and not current_line: lines.append(None) else: separator = (' ' if lines else '') joined_line = EMPTYSTRING.join(current_line) header_bytes = _encode(joined_line, codec) lines.append(encoder(header_bytes)) current_line = [character] maxlen = next(maxlengths) - extra joined_line = EMPTYSTRING.join(current_line) header_bytes = _encode(joined_line, codec) lines.append(encoder(header_bytes)) return lines def _get_encoder(self, header_bytes): if self.header_encoding == BASE64: return email.base64mime elif self.header_encoding == QP: return email.quoprimime elif self.header_encoding == SHORTEST: len64 = email.base64mime.header_length(header_bytes) lenqp = email.quoprimime.header_length(header_bytes) if len64 < lenqp: return email.base64mime else: return email.quoprimime else: return None def body_encode(self, string): """Body-encode a string by converting it first to bytes. The type of encoding (base64 or quoted-printable) will be based on self.body_encoding. If body_encoding is None, we assume the output charset is a 7bit encoding, so re-encoding the decoded string using the ascii codec produces the correct string version of the content. """ if not string: return string if self.body_encoding is BASE64: if isinstance(string, str): string = string.encode(self.output_charset) return email.base64mime.body_encode(string) elif self.body_encoding is QP: # quopromime.body_encode takes a string, but operates on it as if # it were a list of byte codes. For a (minimal) history on why # this is so, see changeset 0cf700464177. To correctly encode a # character set, then, we must turn it into pseudo bytes via the # latin1 charset, which will encode any byte as a single code point # between 0 and 255, which is what body_encode is expecting. if isinstance(string, str): string = string.encode(self.output_charset) string = string.decode('latin1') return email.quoprimime.body_encode(string) else: if isinstance(string, str): string = string.encode(self.output_charset).decode('ascii') return string # Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Encodings and related functions.""" from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import from future.builtins import str __all__ = [ 'encode_7or8bit', 'encode_base64', 'encode_noop', 'encode_quopri', ] try: from base64 import encodebytes as _bencode except ImportError: # Py2 compatibility. TODO: test this! from base64 import encodestring as _bencode from quopri import encodestring as _encodestring def _qencode(s): enc = _encodestring(s, quotetabs=True) # Must encode spaces, which quopri.encodestring() doesn't do return enc.replace(' ', '=20') def encode_base64(msg): """Encode the message's payload in Base64. Also, add an appropriate Content-Transfer-Encoding header. """ orig = msg.get_payload() encdata = str(_bencode(orig), 'ascii') msg.set_payload(encdata) msg['Content-Transfer-Encoding'] = 'base64' def encode_quopri(msg): """Encode the message's payload in quoted-printable. Also, add an appropriate Content-Transfer-Encoding header. """ orig = msg.get_payload() encdata = _qencode(orig) msg.set_payload(encdata) msg['Content-Transfer-Encoding'] = 'quoted-printable' def encode_7or8bit(msg): """Set the Content-Transfer-Encoding header to 7bit or 8bit.""" orig = msg.get_payload() if orig is None: # There's no payload. For backwards compatibility we use 7bit msg['Content-Transfer-Encoding'] = '7bit' return # We play a trick to make this go fast. If encoding/decode to ASCII # succeeds, we know the data must be 7bit, otherwise treat it as 8bit. try: if isinstance(orig, str): orig.encode('ascii') else: orig.decode('ascii') except UnicodeError: charset = msg.get_charset() output_cset = charset and charset.output_charset # iso-2022-* is non-ASCII but encodes to a 7-bit representation if output_cset and output_cset.lower().startswith('iso-2022-'): msg['Content-Transfer-Encoding'] = '7bit' else: msg['Content-Transfer-Encoding'] = '8bit' else: msg['Content-Transfer-Encoding'] = '7bit' if not isinstance(orig, str): msg.set_payload(orig.decode('ascii', 'surrogateescape')) def encode_noop(msg): """Do nothing.""" # Well, not quite *nothing*: in Python3 we have to turn bytes into a string # in our internal surrogateescaped form in order to keep the model # consistent. orig = msg.get_payload() if not isinstance(orig, str): msg.set_payload(orig.decode('ascii', 'surrogateescape')) # Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """email package exception classes.""" from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import from future.builtins import super class MessageError(Exception): """Base class for errors in the email package.""" class MessageParseError(MessageError): """Base class for message parsing errors.""" class HeaderParseError(MessageParseError): """Error while parsing headers.""" class BoundaryError(MessageParseError): """Couldn't find terminating boundary.""" class MultipartConversionError(MessageError, TypeError): """Conversion to a multipart is prohibited.""" class CharsetError(MessageError): """An illegal charset was given.""" # These are parsing defects which the parser was able to work around. class MessageDefect(ValueError): """Base class for a message defect.""" def __init__(self, line=None): if line is not None: super().__init__(line) self.line = line class NoBoundaryInMultipartDefect(MessageDefect): """A message claimed to be a multipart but had no boundary parameter.""" class StartBoundaryNotFoundDefect(MessageDefect): """The claimed start boundary was never found.""" class CloseBoundaryNotFoundDefect(MessageDefect): """A start boundary was found, but not the corresponding close boundary.""" class FirstHeaderLineIsContinuationDefect(MessageDefect): """A message had a continuation line as its first header line.""" class MisplacedEnvelopeHeaderDefect(MessageDefect): """A 'Unix-from' header was found in the middle of a header block.""" class MissingHeaderBodySeparatorDefect(MessageDefect): """Found line with no leading whitespace and no colon before blank line.""" # XXX: backward compatibility, just in case (it was never emitted). MalformedHeaderDefect = MissingHeaderBodySeparatorDefect class MultipartInvariantViolationDefect(MessageDefect): """A message claimed to be a multipart but no subparts were found.""" class InvalidMultipartContentTransferEncodingDefect(MessageDefect): """An invalid content transfer encoding was set on the multipart itself.""" class UndecodableBytesDefect(MessageDefect): """Header contained bytes that could not be decoded""" class InvalidBase64PaddingDefect(MessageDefect): """base64 encoded sequence had an incorrect length""" class InvalidBase64CharactersDefect(MessageDefect): """base64 encoded sequence had characters not in base64 alphabet""" # These errors are specific to header parsing. class HeaderDefect(MessageDefect): """Base class for a header defect.""" def __init__(self, *args, **kw): super().__init__(*args, **kw) class InvalidHeaderDefect(HeaderDefect): """Header is not valid, message gives details.""" class HeaderMissingRequiredValue(HeaderDefect): """A header that must have a value had none""" class NonPrintableDefect(HeaderDefect): """ASCII characters outside the ascii-printable range found""" def __init__(self, non_printables): super().__init__(non_printables) self.non_printables = non_printables def __str__(self): return ("the following ASCII non-printables found in header: " "{}".format(self.non_printables)) class ObsoleteHeaderDefect(HeaderDefect): """Header uses syntax declared obsolete by RFC 5322""" class NonASCIILocalPartDefect(HeaderDefect): """local_part contains non-ASCII characters""" # This defect only occurs during unicode parsing, not when # parsing messages decoded from binary. # Copyright (C) 2004-2006 Python Software Foundation # Authors: Baxter, Wouters and Warsaw # Contact: email-sig@python.org """FeedParser - An email feed parser. The feed parser implements an interface for incrementally parsing an email message, line by line. This has advantages for certain applications, such as those reading email messages off a socket. FeedParser.feed() is the primary interface for pushing new data into the parser. It returns when there's nothing more it can do with the available data. When you have no more data to push into the parser, call .close(). This completes the parsing and returns the root message object. The other advantage of this parser is that it will never raise a parsing exception. Instead, when it finds something unexpected, it adds a 'defect' to the current message. Defects are just instances that live on the message object's .defects attribute. """ from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import from future.builtins import object, range, super from future.utils import implements_iterator, PY3 __all__ = ['FeedParser', 'BytesFeedParser'] import re from future.backports.email import errors from future.backports.email import message from future.backports.email._policybase import compat32 NLCRE = re.compile('\r\n|\r|\n') NLCRE_bol = re.compile('(\r\n|\r|\n)') NLCRE_eol = re.compile('(\r\n|\r|\n)\Z') NLCRE_crack = re.compile('(\r\n|\r|\n)') # RFC 2822 $3.6.8 Optional fields. ftext is %d33-57 / %d59-126, Any character # except controls, SP, and ":". headerRE = re.compile(r'^(From |[\041-\071\073-\176]{1,}:|[\t ])') EMPTYSTRING = '' NL = '\n' NeedMoreData = object() # @implements_iterator class BufferedSubFile(object): """A file-ish object that can have new data loaded into it. You can also push and pop line-matching predicates onto a stack. When the current predicate matches the current line, a false EOF response (i.e. empty string) is returned instead. This lets the parser adhere to a simple abstraction -- it parses until EOF closes the current message. """ def __init__(self): # The last partial line pushed into this object. self._partial = '' # The list of full, pushed lines, in reverse order self._lines = [] # The stack of false-EOF checking predicates. self._eofstack = [] # A flag indicating whether the file has been closed or not. self._closed = False def push_eof_matcher(self, pred): self._eofstack.append(pred) def pop_eof_matcher(self): return self._eofstack.pop() def close(self): # Don't forget any trailing partial line. self._lines.append(self._partial) self._partial = '' self._closed = True def readline(self): if not self._lines: if self._closed: return '' return NeedMoreData # Pop the line off the stack and see if it matches the current # false-EOF predicate. line = self._lines.pop() # RFC 2046, section 5.1.2 requires us to recognize outer level # boundaries at any level of inner nesting. Do this, but be sure it's # in the order of most to least nested. for ateof in self._eofstack[::-1]: if ateof(line): # We're at the false EOF. But push the last line back first. self._lines.append(line) return '' return line def unreadline(self, line): # Let the consumer push a line back into the buffer. assert line is not NeedMoreData self._lines.append(line) def push(self, data): """Push some new data into this object.""" # Handle any previous leftovers data, self._partial = self._partial + data, '' # Crack into lines, but preserve the newlines on the end of each parts = NLCRE_crack.split(data) # The *ahem* interesting behaviour of re.split when supplied grouping # parentheses is that the last element of the resulting list is the # data after the final RE. In the case of a NL/CR terminated string, # this is the empty string. self._partial = parts.pop() #GAN 29Mar09 bugs 1555570, 1721862 Confusion at 8K boundary ending with \r: # is there a \n to follow later? if not self._partial and parts and parts[-1].endswith('\r'): self._partial = parts.pop(-2)+parts.pop() # parts is a list of strings, alternating between the line contents # and the eol character(s). Gather up a list of lines after # re-attaching the newlines. lines = [] for i in range(len(parts) // 2): lines.append(parts[i*2] + parts[i*2+1]) self.pushlines(lines) def pushlines(self, lines): # Reverse and insert at the front of the lines. self._lines[:0] = lines[::-1] def __iter__(self): return self def __next__(self): line = self.readline() if line == '': raise StopIteration return line class FeedParser(object): """A feed-style parser of email.""" def __init__(self, _factory=message.Message, **_3to2kwargs): if 'policy' in _3to2kwargs: policy = _3to2kwargs['policy']; del _3to2kwargs['policy'] else: policy = compat32 """_factory is called with no arguments to create a new message obj The policy keyword specifies a policy object that controls a number of aspects of the parser's operation. The default policy maintains backward compatibility. """ self._factory = _factory self.policy = policy try: _factory(policy=self.policy) self._factory_kwds = lambda: {'policy': self.policy} except TypeError: # Assume this is an old-style factory self._factory_kwds = lambda: {} self._input = BufferedSubFile() self._msgstack = [] if PY3: self._parse = self._parsegen().__next__ else: self._parse = self._parsegen().next self._cur = None self._last = None self._headersonly = False # Non-public interface for supporting Parser's headersonly flag def _set_headersonly(self): self._headersonly = True def feed(self, data): """Push more data into the parser.""" self._input.push(data) self._call_parse() def _call_parse(self): try: self._parse() except StopIteration: pass def close(self): """Parse all remaining data and return the root message object.""" self._input.close() self._call_parse() root = self._pop_message() assert not self._msgstack # Look for final set of defects if root.get_content_maintype() == 'multipart' \ and not root.is_multipart(): defect = errors.MultipartInvariantViolationDefect() self.policy.handle_defect(root, defect) return root def _new_message(self): msg = self._factory(**self._factory_kwds()) if self._cur and self._cur.get_content_type() == 'multipart/digest': msg.set_default_type('message/rfc822') if self._msgstack: self._msgstack[-1].attach(msg) self._msgstack.append(msg) self._cur = msg self._last = msg def _pop_message(self): retval = self._msgstack.pop() if self._msgstack: self._cur = self._msgstack[-1] else: self._cur = None return retval def _parsegen(self): # Create a new message and start by parsing headers. self._new_message() headers = [] # Collect the headers, searching for a line that doesn't match the RFC # 2822 header or continuation pattern (including an empty line). for line in self._input: if line is NeedMoreData: yield NeedMoreData continue if not headerRE.match(line): # If we saw the RFC defined header/body separator # (i.e. newline), just throw it away. Otherwise the line is # part of the body so push it back. if not NLCRE.match(line): defect = errors.MissingHeaderBodySeparatorDefect() self.policy.handle_defect(self._cur, defect) self._input.unreadline(line) break headers.append(line) # Done with the headers, so parse them and figure out what we're # supposed to see in the body of the message. self._parse_headers(headers) # Headers-only parsing is a backwards compatibility hack, which was # necessary in the older parser, which could raise errors. All # remaining lines in the input are thrown into the message body. if self._headersonly: lines = [] while True: line = self._input.readline() if line is NeedMoreData: yield NeedMoreData continue if line == '': break lines.append(line) self._cur.set_payload(EMPTYSTRING.join(lines)) return if self._cur.get_content_type() == 'message/delivery-status': # message/delivery-status contains blocks of headers separated by # a blank line. We'll represent each header block as a separate # nested message object, but the processing is a bit different # than standard message/* types because there is no body for the # nested messages. A blank line separates the subparts. while True: self._input.push_eof_matcher(NLCRE.match) for retval in self._parsegen(): if retval is NeedMoreData: yield NeedMoreData continue break msg = self._pop_message() # We need to pop the EOF matcher in order to tell if we're at # the end of the current file, not the end of the last block # of message headers. self._input.pop_eof_matcher() # The input stream must be sitting at the newline or at the # EOF. We want to see if we're at the end of this subpart, so # first consume the blank line, then test the next line to see # if we're at this subpart's EOF. while True: line = self._input.readline() if line is NeedMoreData: yield NeedMoreData continue break while True: line = self._input.readline() if line is NeedMoreData: yield NeedMoreData continue break if line == '': break # Not at EOF so this is a line we're going to need. self._input.unreadline(line) return if self._cur.get_content_maintype() == 'message': # The message claims to be a message/* type, then what follows is # another RFC 2822 message. for retval in self._parsegen(): if retval is NeedMoreData: yield NeedMoreData continue break self._pop_message() return if self._cur.get_content_maintype() == 'multipart': boundary = self._cur.get_boundary() if boundary is None: # The message /claims/ to be a multipart but it has not # defined a boundary. That's a problem which we'll handle by # reading everything until the EOF and marking the message as # defective. defect = errors.NoBoundaryInMultipartDefect() self.policy.handle_defect(self._cur, defect) lines = [] for line in self._input: if line is NeedMoreData: yield NeedMoreData continue lines.append(line) self._cur.set_payload(EMPTYSTRING.join(lines)) return # Make sure a valid content type was specified per RFC 2045:6.4. if (self._cur.get('content-transfer-encoding', '8bit').lower() not in ('7bit', '8bit', 'binary')): defect = errors.InvalidMultipartContentTransferEncodingDefect() self.policy.handle_defect(self._cur, defect) # Create a line match predicate which matches the inter-part # boundary as well as the end-of-multipart boundary. Don't push # this onto the input stream until we've scanned past the # preamble. separator = '--' + boundary boundaryre = re.compile( '(?P' + re.escape(separator) + r')(?P--)?(?P[ \t]*)(?P\r\n|\r|\n)?$') capturing_preamble = True preamble = [] linesep = False close_boundary_seen = False while True: line = self._input.readline() if line is NeedMoreData: yield NeedMoreData continue if line == '': break mo = boundaryre.match(line) if mo: # If we're looking at the end boundary, we're done with # this multipart. If there was a newline at the end of # the closing boundary, then we need to initialize the # epilogue with the empty string (see below). if mo.group('end'): close_boundary_seen = True linesep = mo.group('linesep') break # We saw an inter-part boundary. Were we in the preamble? if capturing_preamble: if preamble: # According to RFC 2046, the last newline belongs # to the boundary. lastline = preamble[-1] eolmo = NLCRE_eol.search(lastline) if eolmo: preamble[-1] = lastline[:-len(eolmo.group(0))] self._cur.preamble = EMPTYSTRING.join(preamble) capturing_preamble = False self._input.unreadline(line) continue # We saw a boundary separating two parts. Consume any # multiple boundary lines that may be following. Our # interpretation of RFC 2046 BNF grammar does not produce # body parts within such double boundaries. while True: line = self._input.readline() if line is NeedMoreData: yield NeedMoreData continue mo = boundaryre.match(line) if not mo: self._input.unreadline(line) break # Recurse to parse this subpart; the input stream points # at the subpart's first line. self._input.push_eof_matcher(boundaryre.match) for retval in self._parsegen(): if retval is NeedMoreData: yield NeedMoreData continue break # Because of RFC 2046, the newline preceding the boundary # separator actually belongs to the boundary, not the # previous subpart's payload (or epilogue if the previous # part is a multipart). if self._last.get_content_maintype() == 'multipart': epilogue = self._last.epilogue if epilogue == '': self._last.epilogue = None elif epilogue is not None: mo = NLCRE_eol.search(epilogue) if mo: end = len(mo.group(0)) self._last.epilogue = epilogue[:-end] else: payload = self._last._payload if isinstance(payload, str): mo = NLCRE_eol.search(payload) if mo: payload = payload[:-len(mo.group(0))] self._last._payload = payload self._input.pop_eof_matcher() self._pop_message() # Set the multipart up for newline cleansing, which will # happen if we're in a nested multipart. self._last = self._cur else: # I think we must be in the preamble assert capturing_preamble preamble.append(line) # We've seen either the EOF or the end boundary. If we're still # capturing the preamble, we never saw the start boundary. Note # that as a defect and store the captured text as the payload. if capturing_preamble: defect = errors.StartBoundaryNotFoundDefect() self.policy.handle_defect(self._cur, defect) self._cur.set_payload(EMPTYSTRING.join(preamble)) epilogue = [] for line in self._input: if line is NeedMoreData: yield NeedMoreData continue self._cur.epilogue = EMPTYSTRING.join(epilogue) return # If we're not processing the preamble, then we might have seen # EOF without seeing that end boundary...that is also a defect. if not close_boundary_seen: defect = errors.CloseBoundaryNotFoundDefect() self.policy.handle_defect(self._cur, defect) return # Everything from here to the EOF is epilogue. If the end boundary # ended in a newline, we'll need to make sure the epilogue isn't # None if linesep: epilogue = [''] else: epilogue = [] for line in self._input: if line is NeedMoreData: yield NeedMoreData continue epilogue.append(line) # Any CRLF at the front of the epilogue is not technically part of # the epilogue. Also, watch out for an empty string epilogue, # which means a single newline. if epilogue: firstline = epilogue[0] bolmo = NLCRE_bol.match(firstline) if bolmo: epilogue[0] = firstline[len(bolmo.group(0)):] self._cur.epilogue = EMPTYSTRING.join(epilogue) return # Otherwise, it's some non-multipart type, so the entire rest of the # file contents becomes the payload. lines = [] for line in self._input: if line is NeedMoreData: yield NeedMoreData continue lines.append(line) self._cur.set_payload(EMPTYSTRING.join(lines)) def _parse_headers(self, lines): # Passed a list of lines that make up the headers for the current msg lastheader = '' lastvalue = [] for lineno, line in enumerate(lines): # Check for continuation if line[0] in ' \t': if not lastheader: # The first line of the headers was a continuation. This # is illegal, so let's note the defect, store the illegal # line, and ignore it for purposes of headers. defect = errors.FirstHeaderLineIsContinuationDefect(line) self.policy.handle_defect(self._cur, defect) continue lastvalue.append(line) continue if lastheader: self._cur.set_raw(*self.policy.header_source_parse(lastvalue)) lastheader, lastvalue = '', [] # Check for envelope header, i.e. unix-from if line.startswith('From '): if lineno == 0: # Strip off the trailing newline mo = NLCRE_eol.search(line) if mo: line = line[:-len(mo.group(0))] self._cur.set_unixfrom(line) continue elif lineno == len(lines) - 1: # Something looking like a unix-from at the end - it's # probably the first line of the body, so push back the # line and stop. self._input.unreadline(line) return else: # Weirdly placed unix-from line. Note this as a defect # and ignore it. defect = errors.MisplacedEnvelopeHeaderDefect(line) self._cur.defects.append(defect) continue # Split the line on the colon separating field name from value. # There will always be a colon, because if there wasn't the part of # the parser that calls us would have started parsing the body. i = line.find(':') assert i>0, "_parse_headers fed line with no : and no leading WS" lastheader = line[:i] lastvalue = [line] # Done with all the lines, so handle the last header. if lastheader: self._cur.set_raw(*self.policy.header_source_parse(lastvalue)) class BytesFeedParser(FeedParser): """Like FeedParser, but feed accepts bytes.""" def feed(self, data): super().feed(data.decode('ascii', 'surrogateescape')) # Copyright (C) 2001-2010 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Classes to generate plain text from a message object tree.""" from __future__ import print_function from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import from future.builtins import super from future.builtins import str __all__ = ['Generator', 'DecodedGenerator', 'BytesGenerator'] import re import sys import time import random import warnings from io import StringIO, BytesIO from future.backports.email._policybase import compat32 from future.backports.email.header import Header from future.backports.email.utils import _has_surrogates import future.backports.email.charset as _charset UNDERSCORE = '_' NL = '\n' # XXX: no longer used by the code below. fcre = re.compile(r'^From ', re.MULTILINE) class Generator(object): """Generates output from a Message object tree. This basic generator writes the message to the given file object as plain text. """ # # Public interface # def __init__(self, outfp, mangle_from_=True, maxheaderlen=None, **_3to2kwargs): if 'policy' in _3to2kwargs: policy = _3to2kwargs['policy']; del _3to2kwargs['policy'] else: policy = None """Create the generator for message flattening. outfp is the output file-like object for writing the message to. It must have a write() method. Optional mangle_from_ is a flag that, when True (the default), escapes From_ lines in the body of the message by putting a `>' in front of them. Optional maxheaderlen specifies the longest length for a non-continued header. When a header line is longer (in characters, with tabs expanded to 8 spaces) than maxheaderlen, the header will split as defined in the Header class. Set maxheaderlen to zero to disable header wrapping. The default is 78, as recommended (but not required) by RFC 2822. The policy keyword specifies a policy object that controls a number of aspects of the generator's operation. The default policy maintains backward compatibility. """ self._fp = outfp self._mangle_from_ = mangle_from_ self.maxheaderlen = maxheaderlen self.policy = policy def write(self, s): # Just delegate to the file object self._fp.write(s) def flatten(self, msg, unixfrom=False, linesep=None): r"""Print the message object tree rooted at msg to the output file specified when the Generator instance was created. unixfrom is a flag that forces the printing of a Unix From_ delimiter before the first object in the message tree. If the original message has no From_ delimiter, a `standard' one is crafted. By default, this is False to inhibit the printing of any From_ delimiter. Note that for subobjects, no From_ line is printed. linesep specifies the characters used to indicate a new line in the output. The default value is determined by the policy. """ # We use the _XXX constants for operating on data that comes directly # from the msg, and _encoded_XXX constants for operating on data that # has already been converted (to bytes in the BytesGenerator) and # inserted into a temporary buffer. policy = msg.policy if self.policy is None else self.policy if linesep is not None: policy = policy.clone(linesep=linesep) if self.maxheaderlen is not None: policy = policy.clone(max_line_length=self.maxheaderlen) self._NL = policy.linesep self._encoded_NL = self._encode(self._NL) self._EMPTY = '' self._encoded_EMTPY = self._encode('') # Because we use clone (below) when we recursively process message # subparts, and because clone uses the computed policy (not None), # submessages will automatically get set to the computed policy when # they are processed by this code. old_gen_policy = self.policy old_msg_policy = msg.policy try: self.policy = policy msg.policy = policy if unixfrom: ufrom = msg.get_unixfrom() if not ufrom: ufrom = 'From nobody ' + time.ctime(time.time()) self.write(ufrom + self._NL) self._write(msg) finally: self.policy = old_gen_policy msg.policy = old_msg_policy def clone(self, fp): """Clone this generator with the exact same options.""" return self.__class__(fp, self._mangle_from_, None, # Use policy setting, which we've adjusted policy=self.policy) # # Protected interface - undocumented ;/ # # Note that we use 'self.write' when what we are writing is coming from # the source, and self._fp.write when what we are writing is coming from a # buffer (because the Bytes subclass has already had a chance to transform # the data in its write method in that case). This is an entirely # pragmatic split determined by experiment; we could be more general by # always using write and having the Bytes subclass write method detect when # it has already transformed the input; but, since this whole thing is a # hack anyway this seems good enough. # Similarly, we have _XXX and _encoded_XXX attributes that are used on # source and buffer data, respectively. _encoded_EMPTY = '' def _new_buffer(self): # BytesGenerator overrides this to return BytesIO. return StringIO() def _encode(self, s): # BytesGenerator overrides this to encode strings to bytes. return s def _write_lines(self, lines): # We have to transform the line endings. if not lines: return lines = lines.splitlines(True) for line in lines[:-1]: self.write(line.rstrip('\r\n')) self.write(self._NL) laststripped = lines[-1].rstrip('\r\n') self.write(laststripped) if len(lines[-1]) != len(laststripped): self.write(self._NL) def _write(self, msg): # We can't write the headers yet because of the following scenario: # say a multipart message includes the boundary string somewhere in # its body. We'd have to calculate the new boundary /before/ we write # the headers so that we can write the correct Content-Type: # parameter. # # The way we do this, so as to make the _handle_*() methods simpler, # is to cache any subpart writes into a buffer. The we write the # headers and the buffer contents. That way, subpart handlers can # Do The Right Thing, and can still modify the Content-Type: header if # necessary. oldfp = self._fp try: self._fp = sfp = self._new_buffer() self._dispatch(msg) finally: self._fp = oldfp # Write the headers. First we see if the message object wants to # handle that itself. If not, we'll do it generically. meth = getattr(msg, '_write_headers', None) if meth is None: self._write_headers(msg) else: meth(self) self._fp.write(sfp.getvalue()) def _dispatch(self, msg): # Get the Content-Type: for the message, then try to dispatch to # self._handle__(). If there's no handler for the # full MIME type, then dispatch to self._handle_(). If # that's missing too, then dispatch to self._writeBody(). main = msg.get_content_maintype() sub = msg.get_content_subtype() specific = UNDERSCORE.join((main, sub)).replace('-', '_') meth = getattr(self, '_handle_' + specific, None) if meth is None: generic = main.replace('-', '_') meth = getattr(self, '_handle_' + generic, None) if meth is None: meth = self._writeBody meth(msg) # # Default handlers # def _write_headers(self, msg): for h, v in msg.raw_items(): self.write(self.policy.fold(h, v)) # A blank line always separates headers from body self.write(self._NL) # # Handlers for writing types and subtypes # def _handle_text(self, msg): payload = msg.get_payload() if payload is None: return if not isinstance(payload, str): raise TypeError('string payload expected: %s' % type(payload)) if _has_surrogates(msg._payload): charset = msg.get_param('charset') if charset is not None: del msg['content-transfer-encoding'] msg.set_payload(payload, charset) payload = msg.get_payload() if self._mangle_from_: payload = fcre.sub('>From ', payload) self._write_lines(payload) # Default body handler _writeBody = _handle_text def _handle_multipart(self, msg): # The trick here is to write out each part separately, merge them all # together, and then make sure that the boundary we've chosen isn't # present in the payload. msgtexts = [] subparts = msg.get_payload() if subparts is None: subparts = [] elif isinstance(subparts, str): # e.g. a non-strict parse of a message with no starting boundary. self.write(subparts) return elif not isinstance(subparts, list): # Scalar payload subparts = [subparts] for part in subparts: s = self._new_buffer() g = self.clone(s) g.flatten(part, unixfrom=False, linesep=self._NL) msgtexts.append(s.getvalue()) # BAW: What about boundaries that are wrapped in double-quotes? boundary = msg.get_boundary() if not boundary: # Create a boundary that doesn't appear in any of the # message texts. alltext = self._encoded_NL.join(msgtexts) boundary = self._make_boundary(alltext) msg.set_boundary(boundary) # If there's a preamble, write it out, with a trailing CRLF if msg.preamble is not None: if self._mangle_from_: preamble = fcre.sub('>From ', msg.preamble) else: preamble = msg.preamble self._write_lines(preamble) self.write(self._NL) # dash-boundary transport-padding CRLF self.write('--' + boundary + self._NL) # body-part if msgtexts: self._fp.write(msgtexts.pop(0)) # *encapsulation # --> delimiter transport-padding # --> CRLF body-part for body_part in msgtexts: # delimiter transport-padding CRLF self.write(self._NL + '--' + boundary + self._NL) # body-part self._fp.write(body_part) # close-delimiter transport-padding self.write(self._NL + '--' + boundary + '--') if msg.epilogue is not None: self.write(self._NL) if self._mangle_from_: epilogue = fcre.sub('>From ', msg.epilogue) else: epilogue = msg.epilogue self._write_lines(epilogue) def _handle_multipart_signed(self, msg): # The contents of signed parts has to stay unmodified in order to keep # the signature intact per RFC1847 2.1, so we disable header wrapping. # RDM: This isn't enough to completely preserve the part, but it helps. p = self.policy self.policy = p.clone(max_line_length=0) try: self._handle_multipart(msg) finally: self.policy = p def _handle_message_delivery_status(self, msg): # We can't just write the headers directly to self's file object # because this will leave an extra newline between the last header # block and the boundary. Sigh. blocks = [] for part in msg.get_payload(): s = self._new_buffer() g = self.clone(s) g.flatten(part, unixfrom=False, linesep=self._NL) text = s.getvalue() lines = text.split(self._encoded_NL) # Strip off the unnecessary trailing empty line if lines and lines[-1] == self._encoded_EMPTY: blocks.append(self._encoded_NL.join(lines[:-1])) else: blocks.append(text) # Now join all the blocks with an empty line. This has the lovely # effect of separating each block with an empty line, but not adding # an extra one after the last one. self._fp.write(self._encoded_NL.join(blocks)) def _handle_message(self, msg): s = self._new_buffer() g = self.clone(s) # The payload of a message/rfc822 part should be a multipart sequence # of length 1. The zeroth element of the list should be the Message # object for the subpart. Extract that object, stringify it, and # write it out. # Except, it turns out, when it's a string instead, which happens when # and only when HeaderParser is used on a message of mime type # message/rfc822. Such messages are generated by, for example, # Groupwise when forwarding unadorned messages. (Issue 7970.) So # in that case we just emit the string body. payload = msg._payload if isinstance(payload, list): g.flatten(msg.get_payload(0), unixfrom=False, linesep=self._NL) payload = s.getvalue() else: payload = self._encode(payload) self._fp.write(payload) # This used to be a module level function; we use a classmethod for this # and _compile_re so we can continue to provide the module level function # for backward compatibility by doing # _make_boudary = Generator._make_boundary # at the end of the module. It *is* internal, so we could drop that... @classmethod def _make_boundary(cls, text=None): # Craft a random boundary. If text is given, ensure that the chosen # boundary doesn't appear in the text. token = random.randrange(sys.maxsize) boundary = ('=' * 15) + (_fmt % token) + '==' if text is None: return boundary b = boundary counter = 0 while True: cre = cls._compile_re('^--' + re.escape(b) + '(--)?$', re.MULTILINE) if not cre.search(text): break b = boundary + '.' + str(counter) counter += 1 return b @classmethod def _compile_re(cls, s, flags): return re.compile(s, flags) class BytesGenerator(Generator): """Generates a bytes version of a Message object tree. Functionally identical to the base Generator except that the output is bytes and not string. When surrogates were used in the input to encode bytes, these are decoded back to bytes for output. If the policy has cte_type set to 7bit, then the message is transformed such that the non-ASCII bytes are properly content transfer encoded, using the charset unknown-8bit. The outfp object must accept bytes in its write method. """ # Bytes versions of this constant for use in manipulating data from # the BytesIO buffer. _encoded_EMPTY = b'' def write(self, s): self._fp.write(str(s).encode('ascii', 'surrogateescape')) def _new_buffer(self): return BytesIO() def _encode(self, s): return s.encode('ascii') def _write_headers(self, msg): # This is almost the same as the string version, except for handling # strings with 8bit bytes. for h, v in msg.raw_items(): self._fp.write(self.policy.fold_binary(h, v)) # A blank line always separates headers from body self.write(self._NL) def _handle_text(self, msg): # If the string has surrogates the original source was bytes, so # just write it back out. if msg._payload is None: return if _has_surrogates(msg._payload) and not self.policy.cte_type=='7bit': if self._mangle_from_: msg._payload = fcre.sub(">From ", msg._payload) self._write_lines(msg._payload) else: super(BytesGenerator,self)._handle_text(msg) # Default body handler _writeBody = _handle_text @classmethod def _compile_re(cls, s, flags): return re.compile(s.encode('ascii'), flags) _FMT = '[Non-text (%(type)s) part of message omitted, filename %(filename)s]' class DecodedGenerator(Generator): """Generates a text representation of a message. Like the Generator base class, except that non-text parts are substituted with a format string representing the part. """ def __init__(self, outfp, mangle_from_=True, maxheaderlen=78, fmt=None): """Like Generator.__init__() except that an additional optional argument is allowed. Walks through all subparts of a message. If the subpart is of main type `text', then it prints the decoded payload of the subpart. Otherwise, fmt is a format string that is used instead of the message payload. fmt is expanded with the following keywords (in %(keyword)s format): type : Full MIME type of the non-text part maintype : Main MIME type of the non-text part subtype : Sub-MIME type of the non-text part filename : Filename of the non-text part description: Description associated with the non-text part encoding : Content transfer encoding of the non-text part The default value for fmt is None, meaning [Non-text (%(type)s) part of message omitted, filename %(filename)s] """ Generator.__init__(self, outfp, mangle_from_, maxheaderlen) if fmt is None: self._fmt = _FMT else: self._fmt = fmt def _dispatch(self, msg): for part in msg.walk(): maintype = part.get_content_maintype() if maintype == 'text': print(part.get_payload(decode=False), file=self) elif maintype == 'multipart': # Just skip this pass else: print(self._fmt % { 'type' : part.get_content_type(), 'maintype' : part.get_content_maintype(), 'subtype' : part.get_content_subtype(), 'filename' : part.get_filename('[no filename]'), 'description': part.get('Content-Description', '[no description]'), 'encoding' : part.get('Content-Transfer-Encoding', '[no encoding]'), }, file=self) # Helper used by Generator._make_boundary _width = len(repr(sys.maxsize-1)) _fmt = '%%0%dd' % _width # Backward compatibility _make_boundary = Generator._make_boundary # Copyright (C) 2002-2007 Python Software Foundation # Author: Ben Gertzfield, Barry Warsaw # Contact: email-sig@python.org """Header encoding and decoding functionality.""" from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import from future.builtins import bytes, range, str, super, zip __all__ = [ 'Header', 'decode_header', 'make_header', ] import re import binascii from future.backports import email from future.backports.email import base64mime from future.backports.email.errors import HeaderParseError import future.backports.email.charset as _charset # Helpers from future.backports.email.quoprimime import _max_append, header_decode Charset = _charset.Charset NL = '\n' SPACE = ' ' BSPACE = b' ' SPACE8 = ' ' * 8 EMPTYSTRING = '' MAXLINELEN = 78 FWS = ' \t' USASCII = Charset('us-ascii') UTF8 = Charset('utf-8') # Match encoded-word strings in the form =?charset?q?Hello_World?= ecre = re.compile(r''' =\? # literal =? (?P[^?]*?) # non-greedy up to the next ? is the charset \? # literal ? (?P[qb]) # either a "q" or a "b", case insensitive \? # literal ? (?P.*?) # non-greedy up to the next ?= is the encoded string \?= # literal ?= ''', re.VERBOSE | re.IGNORECASE | re.MULTILINE) # Field name regexp, including trailing colon, but not separating whitespace, # according to RFC 2822. Character range is from tilde to exclamation mark. # For use with .match() fcre = re.compile(r'[\041-\176]+:$') # Find a header embedded in a putative header value. Used to check for # header injection attack. _embeded_header = re.compile(r'\n[^ \t]+:') def decode_header(header): """Decode a message header value without converting charset. Returns a list of (string, charset) pairs containing each of the decoded parts of the header. Charset is None for non-encoded parts of the header, otherwise a lower-case string containing the name of the character set specified in the encoded string. header may be a string that may or may not contain RFC2047 encoded words, or it may be a Header object. An email.errors.HeaderParseError may be raised when certain decoding error occurs (e.g. a base64 decoding exception). """ # If it is a Header object, we can just return the encoded chunks. if hasattr(header, '_chunks'): return [(_charset._encode(string, str(charset)), str(charset)) for string, charset in header._chunks] # If no encoding, just return the header with no charset. if not ecre.search(header): return [(header, None)] # First step is to parse all the encoded parts into triplets of the form # (encoded_string, encoding, charset). For unencoded strings, the last # two parts will be None. words = [] for line in header.splitlines(): parts = ecre.split(line) first = True while parts: unencoded = parts.pop(0) if first: unencoded = unencoded.lstrip() first = False if unencoded: words.append((unencoded, None, None)) if parts: charset = parts.pop(0).lower() encoding = parts.pop(0).lower() encoded = parts.pop(0) words.append((encoded, encoding, charset)) # Now loop over words and remove words that consist of whitespace # between two encoded strings. import sys droplist = [] for n, w in enumerate(words): if n>1 and w[1] and words[n-2][1] and words[n-1][0].isspace(): droplist.append(n-1) for d in reversed(droplist): del words[d] # The next step is to decode each encoded word by applying the reverse # base64 or quopri transformation. decoded_words is now a list of the # form (decoded_word, charset). decoded_words = [] for encoded_string, encoding, charset in words: if encoding is None: # This is an unencoded word. decoded_words.append((encoded_string, charset)) elif encoding == 'q': word = header_decode(encoded_string) decoded_words.append((word, charset)) elif encoding == 'b': paderr = len(encoded_string) % 4 # Postel's law: add missing padding if paderr: encoded_string += '==='[:4 - paderr] try: word = base64mime.decode(encoded_string) except binascii.Error: raise HeaderParseError('Base64 decoding error') else: decoded_words.append((word, charset)) else: raise AssertionError('Unexpected encoding: ' + encoding) # Now convert all words to bytes and collapse consecutive runs of # similarly encoded words. collapsed = [] last_word = last_charset = None for word, charset in decoded_words: if isinstance(word, str): word = bytes(word, 'raw-unicode-escape') if last_word is None: last_word = word last_charset = charset elif charset != last_charset: collapsed.append((last_word, last_charset)) last_word = word last_charset = charset elif last_charset is None: last_word += BSPACE + word else: last_word += word collapsed.append((last_word, last_charset)) return collapsed def make_header(decoded_seq, maxlinelen=None, header_name=None, continuation_ws=' '): """Create a Header from a sequence of pairs as returned by decode_header() decode_header() takes a header value string and returns a sequence of pairs of the format (decoded_string, charset) where charset is the string name of the character set. This function takes one of those sequence of pairs and returns a Header instance. Optional maxlinelen, header_name, and continuation_ws are as in the Header constructor. """ h = Header(maxlinelen=maxlinelen, header_name=header_name, continuation_ws=continuation_ws) for s, charset in decoded_seq: # None means us-ascii but we can simply pass it on to h.append() if charset is not None and not isinstance(charset, Charset): charset = Charset(charset) h.append(s, charset) return h class Header(object): def __init__(self, s=None, charset=None, maxlinelen=None, header_name=None, continuation_ws=' ', errors='strict'): """Create a MIME-compliant header that can contain many character sets. Optional s is the initial header value. If None, the initial header value is not set. You can later append to the header with .append() method calls. s may be a byte string or a Unicode string, but see the .append() documentation for semantics. Optional charset serves two purposes: it has the same meaning as the charset argument to the .append() method. It also sets the default character set for all subsequent .append() calls that omit the charset argument. If charset is not provided in the constructor, the us-ascii charset is used both as s's initial charset and as the default for subsequent .append() calls. The maximum line length can be specified explicitly via maxlinelen. For splitting the first line to a shorter value (to account for the field header which isn't included in s, e.g. `Subject') pass in the name of the field in header_name. The default maxlinelen is 78 as recommended by RFC 2822. continuation_ws must be RFC 2822 compliant folding whitespace (usually either a space or a hard tab) which will be prepended to continuation lines. errors is passed through to the .append() call. """ if charset is None: charset = USASCII elif not isinstance(charset, Charset): charset = Charset(charset) self._charset = charset self._continuation_ws = continuation_ws self._chunks = [] if s is not None: self.append(s, charset, errors) if maxlinelen is None: maxlinelen = MAXLINELEN self._maxlinelen = maxlinelen if header_name is None: self._headerlen = 0 else: # Take the separating colon and space into account. self._headerlen = len(header_name) + 2 def __str__(self): """Return the string value of the header.""" self._normalize() uchunks = [] lastcs = None lastspace = None for string, charset in self._chunks: # We must preserve spaces between encoded and non-encoded word # boundaries, which means for us we need to add a space when we go # from a charset to None/us-ascii, or from None/us-ascii to a # charset. Only do this for the second and subsequent chunks. # Don't add a space if the None/us-ascii string already has # a space (trailing or leading depending on transition) nextcs = charset if nextcs == _charset.UNKNOWN8BIT: original_bytes = string.encode('ascii', 'surrogateescape') string = original_bytes.decode('ascii', 'replace') if uchunks: hasspace = string and self._nonctext(string[0]) if lastcs not in (None, 'us-ascii'): if nextcs in (None, 'us-ascii') and not hasspace: uchunks.append(SPACE) nextcs = None elif nextcs not in (None, 'us-ascii') and not lastspace: uchunks.append(SPACE) lastspace = string and self._nonctext(string[-1]) lastcs = nextcs uchunks.append(string) return EMPTYSTRING.join(uchunks) # Rich comparison operators for equality only. BAW: does it make sense to # have or explicitly disable <, <=, >, >= operators? def __eq__(self, other): # other may be a Header or a string. Both are fine so coerce # ourselves to a unicode (of the unencoded header value), swap the # args and do another comparison. return other == str(self) def __ne__(self, other): return not self == other def append(self, s, charset=None, errors='strict'): """Append a string to the MIME header. Optional charset, if given, should be a Charset instance or the name of a character set (which will be converted to a Charset instance). A value of None (the default) means that the charset given in the constructor is used. s may be a byte string or a Unicode string. If it is a byte string (i.e. isinstance(s, str) is false), then charset is the encoding of that byte string, and a UnicodeError will be raised if the string cannot be decoded with that charset. If s is a Unicode string, then charset is a hint specifying the character set of the characters in the string. In either case, when producing an RFC 2822 compliant header using RFC 2047 rules, the string will be encoded using the output codec of the charset. If the string cannot be encoded to the output codec, a UnicodeError will be raised. Optional `errors' is passed as the errors argument to the decode call if s is a byte string. """ if charset is None: charset = self._charset elif not isinstance(charset, Charset): charset = Charset(charset) if not isinstance(s, str): input_charset = charset.input_codec or 'us-ascii' if input_charset == _charset.UNKNOWN8BIT: s = s.decode('us-ascii', 'surrogateescape') else: s = s.decode(input_charset, errors) # Ensure that the bytes we're storing can be decoded to the output # character set, otherwise an early error is raised. output_charset = charset.output_codec or 'us-ascii' if output_charset != _charset.UNKNOWN8BIT: try: s.encode(output_charset, errors) except UnicodeEncodeError: if output_charset!='us-ascii': raise charset = UTF8 self._chunks.append((s, charset)) def _nonctext(self, s): """True if string s is not a ctext character of RFC822. """ return s.isspace() or s in ('(', ')', '\\') def encode(self, splitchars=';, \t', maxlinelen=None, linesep='\n'): r"""Encode a message header into an RFC-compliant format. There are many issues involved in converting a given string for use in an email header. Only certain character sets are readable in most email clients, and as header strings can only contain a subset of 7-bit ASCII, care must be taken to properly convert and encode (with Base64 or quoted-printable) header strings. In addition, there is a 75-character length limit on any given encoded header field, so line-wrapping must be performed, even with double-byte character sets. Optional maxlinelen specifies the maximum length of each generated line, exclusive of the linesep string. Individual lines may be longer than maxlinelen if a folding point cannot be found. The first line will be shorter by the length of the header name plus ": " if a header name was specified at Header construction time. The default value for maxlinelen is determined at header construction time. Optional splitchars is a string containing characters which should be given extra weight by the splitting algorithm during normal header wrapping. This is in very rough support of RFC 2822's `higher level syntactic breaks': split points preceded by a splitchar are preferred during line splitting, with the characters preferred in the order in which they appear in the string. Space and tab may be included in the string to indicate whether preference should be given to one over the other as a split point when other split chars do not appear in the line being split. Splitchars does not affect RFC 2047 encoded lines. Optional linesep is a string to be used to separate the lines of the value. The default value is the most useful for typical Python applications, but it can be set to \r\n to produce RFC-compliant line separators when needed. """ self._normalize() if maxlinelen is None: maxlinelen = self._maxlinelen # A maxlinelen of 0 means don't wrap. For all practical purposes, # choosing a huge number here accomplishes that and makes the # _ValueFormatter algorithm much simpler. if maxlinelen == 0: maxlinelen = 1000000 formatter = _ValueFormatter(self._headerlen, maxlinelen, self._continuation_ws, splitchars) lastcs = None hasspace = lastspace = None for string, charset in self._chunks: if hasspace is not None: hasspace = string and self._nonctext(string[0]) import sys if lastcs not in (None, 'us-ascii'): if not hasspace or charset not in (None, 'us-ascii'): formatter.add_transition() elif charset not in (None, 'us-ascii') and not lastspace: formatter.add_transition() lastspace = string and self._nonctext(string[-1]) lastcs = charset hasspace = False lines = string.splitlines() if lines: formatter.feed('', lines[0], charset) else: formatter.feed('', '', charset) for line in lines[1:]: formatter.newline() if charset.header_encoding is not None: formatter.feed(self._continuation_ws, ' ' + line.lstrip(), charset) else: sline = line.lstrip() fws = line[:len(line)-len(sline)] formatter.feed(fws, sline, charset) if len(lines) > 1: formatter.newline() if self._chunks: formatter.add_transition() value = formatter._str(linesep) if _embeded_header.search(value): raise HeaderParseError("header value appears to contain " "an embedded header: {!r}".format(value)) return value def _normalize(self): # Step 1: Normalize the chunks so that all runs of identical charsets # get collapsed into a single unicode string. chunks = [] last_charset = None last_chunk = [] for string, charset in self._chunks: if charset == last_charset: last_chunk.append(string) else: if last_charset is not None: chunks.append((SPACE.join(last_chunk), last_charset)) last_chunk = [string] last_charset = charset if last_chunk: chunks.append((SPACE.join(last_chunk), last_charset)) self._chunks = chunks class _ValueFormatter(object): def __init__(self, headerlen, maxlen, continuation_ws, splitchars): self._maxlen = maxlen self._continuation_ws = continuation_ws self._continuation_ws_len = len(continuation_ws) self._splitchars = splitchars self._lines = [] self._current_line = _Accumulator(headerlen) def _str(self, linesep): self.newline() return linesep.join(self._lines) def __str__(self): return self._str(NL) def newline(self): end_of_line = self._current_line.pop() if end_of_line != (' ', ''): self._current_line.push(*end_of_line) if len(self._current_line) > 0: if self._current_line.is_onlyws(): self._lines[-1] += str(self._current_line) else: self._lines.append(str(self._current_line)) self._current_line.reset() def add_transition(self): self._current_line.push(' ', '') def feed(self, fws, string, charset): # If the charset has no header encoding (i.e. it is an ASCII encoding) # then we must split the header at the "highest level syntactic break" # possible. Note that we don't have a lot of smarts about field # syntax; we just try to break on semi-colons, then commas, then # whitespace. Eventually, this should be pluggable. if charset.header_encoding is None: self._ascii_split(fws, string, self._splitchars) return # Otherwise, we're doing either a Base64 or a quoted-printable # encoding which means we don't need to split the line on syntactic # breaks. We can basically just find enough characters to fit on the # current line, minus the RFC 2047 chrome. What makes this trickier # though is that we have to split at octet boundaries, not character # boundaries but it's only safe to split at character boundaries so at # best we can only get close. encoded_lines = charset.header_encode_lines(string, self._maxlengths()) # The first element extends the current line, but if it's None then # nothing more fit on the current line so start a new line. try: first_line = encoded_lines.pop(0) except IndexError: # There are no encoded lines, so we're done. return if first_line is not None: self._append_chunk(fws, first_line) try: last_line = encoded_lines.pop() except IndexError: # There was only one line. return self.newline() self._current_line.push(self._continuation_ws, last_line) # Everything else are full lines in themselves. for line in encoded_lines: self._lines.append(self._continuation_ws + line) def _maxlengths(self): # The first line's length. yield self._maxlen - len(self._current_line) while True: yield self._maxlen - self._continuation_ws_len def _ascii_split(self, fws, string, splitchars): # The RFC 2822 header folding algorithm is simple in principle but # complex in practice. Lines may be folded any place where "folding # white space" appears by inserting a linesep character in front of the # FWS. The complication is that not all spaces or tabs qualify as FWS, # and we are also supposed to prefer to break at "higher level # syntactic breaks". We can't do either of these without intimate # knowledge of the structure of structured headers, which we don't have # here. So the best we can do here is prefer to break at the specified # splitchars, and hope that we don't choose any spaces or tabs that # aren't legal FWS. (This is at least better than the old algorithm, # where we would sometimes *introduce* FWS after a splitchar, or the # algorithm before that, where we would turn all white space runs into # single spaces or tabs.) parts = re.split("(["+FWS+"]+)", fws+string) if parts[0]: parts[:0] = [''] else: parts.pop(0) for fws, part in zip(*[iter(parts)]*2): self._append_chunk(fws, part) def _append_chunk(self, fws, string): self._current_line.push(fws, string) if len(self._current_line) > self._maxlen: # Find the best split point, working backward from the end. # There might be none, on a long first line. for ch in self._splitchars: for i in range(self._current_line.part_count()-1, 0, -1): if ch.isspace(): fws = self._current_line[i][0] if fws and fws[0]==ch: break prevpart = self._current_line[i-1][1] if prevpart and prevpart[-1]==ch: break else: continue break else: fws, part = self._current_line.pop() if self._current_line._initial_size > 0: # There will be a header, so leave it on a line by itself. self.newline() if not fws: # We don't use continuation_ws here because the whitespace # after a header should always be a space. fws = ' ' self._current_line.push(fws, part) return remainder = self._current_line.pop_from(i) self._lines.append(str(self._current_line)) self._current_line.reset(remainder) class _Accumulator(list): def __init__(self, initial_size=0): self._initial_size = initial_size super().__init__() def push(self, fws, string): self.append((fws, string)) def pop_from(self, i=0): popped = self[i:] self[i:] = [] return popped def pop(self): if self.part_count()==0: return ('', '') return super().pop() def __len__(self): return sum((len(fws)+len(part) for fws, part in self), self._initial_size) def __str__(self): return EMPTYSTRING.join((EMPTYSTRING.join((fws, part)) for fws, part in self)) def reset(self, startval=None): if startval is None: startval = [] self[:] = startval self._initial_size = 0 def is_onlyws(self): return self._initial_size==0 and (not self or str(self).isspace()) def part_count(self): return super().__len__() """Representing and manipulating email headers via custom objects. This module provides an implementation of the HeaderRegistry API. The implementation is designed to flexibly follow RFC5322 rules. Eventually HeaderRegistry will be a public API, but it isn't yet, and will probably change some before that happens. """ from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import from future.builtins import super from future.builtins import str from future.utils import text_to_native_str from future.backports.email import utils from future.backports.email import errors from future.backports.email import _header_value_parser as parser class Address(object): def __init__(self, display_name='', username='', domain='', addr_spec=None): """Create an object represeting a full email address. An address can have a 'display_name', a 'username', and a 'domain'. In addition to specifying the username and domain separately, they may be specified together by using the addr_spec keyword *instead of* the username and domain keywords. If an addr_spec string is specified it must be properly quoted according to RFC 5322 rules; an error will be raised if it is not. An Address object has display_name, username, domain, and addr_spec attributes, all of which are read-only. The addr_spec and the string value of the object are both quoted according to RFC5322 rules, but without any Content Transfer Encoding. """ # This clause with its potential 'raise' may only happen when an # application program creates an Address object using an addr_spec # keyword. The email library code itself must always supply username # and domain. if addr_spec is not None: if username or domain: raise TypeError("addrspec specified when username and/or " "domain also specified") a_s, rest = parser.get_addr_spec(addr_spec) if rest: raise ValueError("Invalid addr_spec; only '{}' " "could be parsed from '{}'".format( a_s, addr_spec)) if a_s.all_defects: raise a_s.all_defects[0] username = a_s.local_part domain = a_s.domain self._display_name = display_name self._username = username self._domain = domain @property def display_name(self): return self._display_name @property def username(self): return self._username @property def domain(self): return self._domain @property def addr_spec(self): """The addr_spec (username@domain) portion of the address, quoted according to RFC 5322 rules, but with no Content Transfer Encoding. """ nameset = set(self.username) if len(nameset) > len(nameset-parser.DOT_ATOM_ENDS): lp = parser.quote_string(self.username) else: lp = self.username if self.domain: return lp + '@' + self.domain if not lp: return '<>' return lp def __repr__(self): return "Address(display_name={!r}, username={!r}, domain={!r})".format( self.display_name, self.username, self.domain) def __str__(self): nameset = set(self.display_name) if len(nameset) > len(nameset-parser.SPECIALS): disp = parser.quote_string(self.display_name) else: disp = self.display_name if disp: addr_spec = '' if self.addr_spec=='<>' else self.addr_spec return "{} <{}>".format(disp, addr_spec) return self.addr_spec def __eq__(self, other): if type(other) != type(self): return False return (self.display_name == other.display_name and self.username == other.username and self.domain == other.domain) class Group(object): def __init__(self, display_name=None, addresses=None): """Create an object representing an address group. An address group consists of a display_name followed by colon and an list of addresses (see Address) terminated by a semi-colon. The Group is created by specifying a display_name and a possibly empty list of Address objects. A Group can also be used to represent a single address that is not in a group, which is convenient when manipulating lists that are a combination of Groups and individual Addresses. In this case the display_name should be set to None. In particular, the string representation of a Group whose display_name is None is the same as the Address object, if there is one and only one Address object in the addresses list. """ self._display_name = display_name self._addresses = tuple(addresses) if addresses else tuple() @property def display_name(self): return self._display_name @property def addresses(self): return self._addresses def __repr__(self): return "Group(display_name={!r}, addresses={!r}".format( self.display_name, self.addresses) def __str__(self): if self.display_name is None and len(self.addresses)==1: return str(self.addresses[0]) disp = self.display_name if disp is not None: nameset = set(disp) if len(nameset) > len(nameset-parser.SPECIALS): disp = parser.quote_string(disp) adrstr = ", ".join(str(x) for x in self.addresses) adrstr = ' ' + adrstr if adrstr else adrstr return "{}:{};".format(disp, adrstr) def __eq__(self, other): if type(other) != type(self): return False return (self.display_name == other.display_name and self.addresses == other.addresses) # Header Classes # class BaseHeader(str): """Base class for message headers. Implements generic behavior and provides tools for subclasses. A subclass must define a classmethod named 'parse' that takes an unfolded value string and a dictionary as its arguments. The dictionary will contain one key, 'defects', initialized to an empty list. After the call the dictionary must contain two additional keys: parse_tree, set to the parse tree obtained from parsing the header, and 'decoded', set to the string value of the idealized representation of the data from the value. (That is, encoded words are decoded, and values that have canonical representations are so represented.) The defects key is intended to collect parsing defects, which the message parser will subsequently dispose of as appropriate. The parser should not, insofar as practical, raise any errors. Defects should be added to the list instead. The standard header parsers register defects for RFC compliance issues, for obsolete RFC syntax, and for unrecoverable parsing errors. The parse method may add additional keys to the dictionary. In this case the subclass must define an 'init' method, which will be passed the dictionary as its keyword arguments. The method should use (usually by setting them as the value of similarly named attributes) and remove all the extra keys added by its parse method, and then use super to call its parent class with the remaining arguments and keywords. The subclass should also make sure that a 'max_count' attribute is defined that is either None or 1. XXX: need to better define this API. """ def __new__(cls, name, value): kwds = {'defects': []} cls.parse(value, kwds) if utils._has_surrogates(kwds['decoded']): kwds['decoded'] = utils._sanitize(kwds['decoded']) self = str.__new__(cls, kwds['decoded']) # del kwds['decoded'] self.init(name, **kwds) return self def init(self, name, **_3to2kwargs): defects = _3to2kwargs['defects']; del _3to2kwargs['defects'] parse_tree = _3to2kwargs['parse_tree']; del _3to2kwargs['parse_tree'] self._name = name self._parse_tree = parse_tree self._defects = defects @property def name(self): return self._name @property def defects(self): return tuple(self._defects) def __reduce__(self): return ( _reconstruct_header, ( self.__class__.__name__, self.__class__.__bases__, str(self), ), self.__dict__) @classmethod def _reconstruct(cls, value): return str.__new__(cls, value) def fold(self, **_3to2kwargs): policy = _3to2kwargs['policy']; del _3to2kwargs['policy'] """Fold header according to policy. The parsed representation of the header is folded according to RFC5322 rules, as modified by the policy. If the parse tree contains surrogateescaped bytes, the bytes are CTE encoded using the charset 'unknown-8bit". Any non-ASCII characters in the parse tree are CTE encoded using charset utf-8. XXX: make this a policy setting. The returned value is an ASCII-only string possibly containing linesep characters, and ending with a linesep character. The string includes the header name and the ': ' separator. """ # At some point we need to only put fws here if it was in the source. header = parser.Header([ parser.HeaderLabel([ parser.ValueTerminal(self.name, 'header-name'), parser.ValueTerminal(':', 'header-sep')]), parser.CFWSList([parser.WhiteSpaceTerminal(' ', 'fws')]), self._parse_tree]) return header.fold(policy=policy) def _reconstruct_header(cls_name, bases, value): return type(text_to_native_str(cls_name), bases, {})._reconstruct(value) class UnstructuredHeader(object): max_count = None value_parser = staticmethod(parser.get_unstructured) @classmethod def parse(cls, value, kwds): kwds['parse_tree'] = cls.value_parser(value) kwds['decoded'] = str(kwds['parse_tree']) class UniqueUnstructuredHeader(UnstructuredHeader): max_count = 1 class DateHeader(object): """Header whose value consists of a single timestamp. Provides an additional attribute, datetime, which is either an aware datetime using a timezone, or a naive datetime if the timezone in the input string is -0000. Also accepts a datetime as input. The 'value' attribute is the normalized form of the timestamp, which means it is the output of format_datetime on the datetime. """ max_count = None # This is used only for folding, not for creating 'decoded'. value_parser = staticmethod(parser.get_unstructured) @classmethod def parse(cls, value, kwds): if not value: kwds['defects'].append(errors.HeaderMissingRequiredValue()) kwds['datetime'] = None kwds['decoded'] = '' kwds['parse_tree'] = parser.TokenList() return if isinstance(value, str): value = utils.parsedate_to_datetime(value) kwds['datetime'] = value kwds['decoded'] = utils.format_datetime(kwds['datetime']) kwds['parse_tree'] = cls.value_parser(kwds['decoded']) def init(self, *args, **kw): self._datetime = kw.pop('datetime') super().init(*args, **kw) @property def datetime(self): return self._datetime class UniqueDateHeader(DateHeader): max_count = 1 class AddressHeader(object): max_count = None @staticmethod def value_parser(value): address_list, value = parser.get_address_list(value) assert not value, 'this should not happen' return address_list @classmethod def parse(cls, value, kwds): if isinstance(value, str): # We are translating here from the RFC language (address/mailbox) # to our API language (group/address). kwds['parse_tree'] = address_list = cls.value_parser(value) groups = [] for addr in address_list.addresses: groups.append(Group(addr.display_name, [Address(mb.display_name or '', mb.local_part or '', mb.domain or '') for mb in addr.all_mailboxes])) defects = list(address_list.all_defects) else: # Assume it is Address/Group stuff if not hasattr(value, '__iter__'): value = [value] groups = [Group(None, [item]) if not hasattr(item, 'addresses') else item for item in value] defects = [] kwds['groups'] = groups kwds['defects'] = defects kwds['decoded'] = ', '.join([str(item) for item in groups]) if 'parse_tree' not in kwds: kwds['parse_tree'] = cls.value_parser(kwds['decoded']) def init(self, *args, **kw): self._groups = tuple(kw.pop('groups')) self._addresses = None super().init(*args, **kw) @property def groups(self): return self._groups @property def addresses(self): if self._addresses is None: self._addresses = tuple([address for group in self._groups for address in group.addresses]) return self._addresses class UniqueAddressHeader(AddressHeader): max_count = 1 class SingleAddressHeader(AddressHeader): @property def address(self): if len(self.addresses)!=1: raise ValueError(("value of single address header {} is not " "a single address").format(self.name)) return self.addresses[0] class UniqueSingleAddressHeader(SingleAddressHeader): max_count = 1 class MIMEVersionHeader(object): max_count = 1 value_parser = staticmethod(parser.parse_mime_version) @classmethod def parse(cls, value, kwds): kwds['parse_tree'] = parse_tree = cls.value_parser(value) kwds['decoded'] = str(parse_tree) kwds['defects'].extend(parse_tree.all_defects) kwds['major'] = None if parse_tree.minor is None else parse_tree.major kwds['minor'] = parse_tree.minor if parse_tree.minor is not None: kwds['version'] = '{}.{}'.format(kwds['major'], kwds['minor']) else: kwds['version'] = None def init(self, *args, **kw): self._version = kw.pop('version') self._major = kw.pop('major') self._minor = kw.pop('minor') super().init(*args, **kw) @property def major(self): return self._major @property def minor(self): return self._minor @property def version(self): return self._version class ParameterizedMIMEHeader(object): # Mixin that handles the params dict. Must be subclassed and # a property value_parser for the specific header provided. max_count = 1 @classmethod def parse(cls, value, kwds): kwds['parse_tree'] = parse_tree = cls.value_parser(value) kwds['decoded'] = str(parse_tree) kwds['defects'].extend(parse_tree.all_defects) if parse_tree.params is None: kwds['params'] = {} else: # The MIME RFCs specify that parameter ordering is arbitrary. kwds['params'] = dict((utils._sanitize(name).lower(), utils._sanitize(value)) for name, value in parse_tree.params) def init(self, *args, **kw): self._params = kw.pop('params') super().init(*args, **kw) @property def params(self): return self._params.copy() class ContentTypeHeader(ParameterizedMIMEHeader): value_parser = staticmethod(parser.parse_content_type_header) def init(self, *args, **kw): super().init(*args, **kw) self._maintype = utils._sanitize(self._parse_tree.maintype) self._subtype = utils._sanitize(self._parse_tree.subtype) @property def maintype(self): return self._maintype @property def subtype(self): return self._subtype @property def content_type(self): return self.maintype + '/' + self.subtype class ContentDispositionHeader(ParameterizedMIMEHeader): value_parser = staticmethod(parser.parse_content_disposition_header) def init(self, *args, **kw): super().init(*args, **kw) cd = self._parse_tree.content_disposition self._content_disposition = cd if cd is None else utils._sanitize(cd) @property def content_disposition(self): return self._content_disposition class ContentTransferEncodingHeader(object): max_count = 1 value_parser = staticmethod(parser.parse_content_transfer_encoding_header) @classmethod def parse(cls, value, kwds): kwds['parse_tree'] = parse_tree = cls.value_parser(value) kwds['decoded'] = str(parse_tree) kwds['defects'].extend(parse_tree.all_defects) def init(self, *args, **kw): super().init(*args, **kw) self._cte = utils._sanitize(self._parse_tree.cte) @property def cte(self): return self._cte # The header factory # _default_header_map = { 'subject': UniqueUnstructuredHeader, 'date': UniqueDateHeader, 'resent-date': DateHeader, 'orig-date': UniqueDateHeader, 'sender': UniqueSingleAddressHeader, 'resent-sender': SingleAddressHeader, 'to': UniqueAddressHeader, 'resent-to': AddressHeader, 'cc': UniqueAddressHeader, 'resent-cc': AddressHeader, 'bcc': UniqueAddressHeader, 'resent-bcc': AddressHeader, 'from': UniqueAddressHeader, 'resent-from': AddressHeader, 'reply-to': UniqueAddressHeader, 'mime-version': MIMEVersionHeader, 'content-type': ContentTypeHeader, 'content-disposition': ContentDispositionHeader, 'content-transfer-encoding': ContentTransferEncodingHeader, } class HeaderRegistry(object): """A header_factory and header registry.""" def __init__(self, base_class=BaseHeader, default_class=UnstructuredHeader, use_default_map=True): """Create a header_factory that works with the Policy API. base_class is the class that will be the last class in the created header class's __bases__ list. default_class is the class that will be used if "name" (see __call__) does not appear in the registry. use_default_map controls whether or not the default mapping of names to specialized classes is copied in to the registry when the factory is created. The default is True. """ self.registry = {} self.base_class = base_class self.default_class = default_class if use_default_map: self.registry.update(_default_header_map) def map_to_type(self, name, cls): """Register cls as the specialized class for handling "name" headers. """ self.registry[name.lower()] = cls def __getitem__(self, name): cls = self.registry.get(name.lower(), self.default_class) return type(text_to_native_str('_'+cls.__name__), (cls, self.base_class), {}) def __call__(self, name, value): """Create a header instance for header 'name' from 'value'. Creates a header instance by creating a specialized class for parsing and representing the specified header by combining the factory base_class with a specialized class from the registry or the default_class, and passing the name and value to the constructed class's constructor. """ return self[name](name, value) # Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Various types of useful iterators and generators.""" from __future__ import print_function from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import __all__ = [ 'body_line_iterator', 'typed_subpart_iterator', 'walk', # Do not include _structure() since it's part of the debugging API. ] import sys from io import StringIO # This function will become a method of the Message class def walk(self): """Walk over the message tree, yielding each subpart. The walk is performed in depth-first order. This method is a generator. """ yield self if self.is_multipart(): for subpart in self.get_payload(): for subsubpart in subpart.walk(): yield subsubpart # These two functions are imported into the Iterators.py interface module. def body_line_iterator(msg, decode=False): """Iterate over the parts, returning string payloads line-by-line. Optional decode (default False) is passed through to .get_payload(). """ for subpart in msg.walk(): payload = subpart.get_payload(decode=decode) if isinstance(payload, str): for line in StringIO(payload): yield line def typed_subpart_iterator(msg, maintype='text', subtype=None): """Iterate over the subparts with a given MIME type. Use `maintype' as the main MIME type to match against; this defaults to "text". Optional `subtype' is the MIME subtype to match against; if omitted, only the main type is matched. """ for subpart in msg.walk(): if subpart.get_content_maintype() == maintype: if subtype is None or subpart.get_content_subtype() == subtype: yield subpart def _structure(msg, fp=None, level=0, include_default=False): """A handy debugging aid""" if fp is None: fp = sys.stdout tab = ' ' * (level * 4) print(tab + msg.get_content_type(), end='', file=fp) if include_default: print(' [%s]' % msg.get_default_type(), file=fp) else: print(file=fp) if msg.is_multipart(): for subpart in msg.get_payload(): _structure(subpart, fp, level+1, include_default) # -*- coding: utf-8 -*- # Copyright (C) 2001-2007 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Basic message object for the email package object model.""" from __future__ import absolute_import, division, unicode_literals from future.builtins import list, range, str, zip __all__ = ['Message'] import re import uu import base64 import binascii from io import BytesIO, StringIO # Intrapackage imports from future.utils import as_native_str from future.backports.email import utils from future.backports.email import errors from future.backports.email._policybase import compat32 from future.backports.email import charset as _charset from future.backports.email._encoded_words import decode_b Charset = _charset.Charset SEMISPACE = '; ' # Regular expression that matches `special' characters in parameters, the # existence of which force quoting of the parameter value. tspecials = re.compile(r'[ \(\)<>@,;:\\"/\[\]\?=]') def _splitparam(param): # Split header parameters. BAW: this may be too simple. It isn't # strictly RFC 2045 (section 5.1) compliant, but it catches most headers # found in the wild. We may eventually need a full fledged parser. # RDM: we might have a Header here; for now just stringify it. a, sep, b = str(param).partition(';') if not sep: return a.strip(), None return a.strip(), b.strip() def _formatparam(param, value=None, quote=True): """Convenience function to format and return a key=value pair. This will quote the value if needed or if quote is true. If value is a three tuple (charset, language, value), it will be encoded according to RFC2231 rules. If it contains non-ascii characters it will likewise be encoded according to RFC2231 rules, using the utf-8 charset and a null language. """ if value is not None and len(value) > 0: # A tuple is used for RFC 2231 encoded parameter values where items # are (charset, language, value). charset is a string, not a Charset # instance. RFC 2231 encoded values are never quoted, per RFC. if isinstance(value, tuple): # Encode as per RFC 2231 param += '*' value = utils.encode_rfc2231(value[2], value[0], value[1]) return '%s=%s' % (param, value) else: try: value.encode('ascii') except UnicodeEncodeError: param += '*' value = utils.encode_rfc2231(value, 'utf-8', '') return '%s=%s' % (param, value) # BAW: Please check this. I think that if quote is set it should # force quoting even if not necessary. if quote or tspecials.search(value): return '%s="%s"' % (param, utils.quote(value)) else: return '%s=%s' % (param, value) else: return param def _parseparam(s): # RDM This might be a Header, so for now stringify it. s = ';' + str(s) plist = [] while s[:1] == ';': s = s[1:] end = s.find(';') while end > 0 and (s.count('"', 0, end) - s.count('\\"', 0, end)) % 2: end = s.find(';', end + 1) if end < 0: end = len(s) f = s[:end] if '=' in f: i = f.index('=') f = f[:i].strip().lower() + '=' + f[i+1:].strip() plist.append(f.strip()) s = s[end:] return plist def _unquotevalue(value): # This is different than utils.collapse_rfc2231_value() because it doesn't # try to convert the value to a unicode. Message.get_param() and # Message.get_params() are both currently defined to return the tuple in # the face of RFC 2231 parameters. if isinstance(value, tuple): return value[0], value[1], utils.unquote(value[2]) else: return utils.unquote(value) class Message(object): """Basic message object. A message object is defined as something that has a bunch of RFC 2822 headers and a payload. It may optionally have an envelope header (a.k.a. Unix-From or From_ header). If the message is a container (i.e. a multipart or a message/rfc822), then the payload is a list of Message objects, otherwise it is a string. Message objects implement part of the `mapping' interface, which assumes there is exactly one occurrence of the header per message. Some headers do in fact appear multiple times (e.g. Received) and for those headers, you must use the explicit API to set or get all the headers. Not all of the mapping methods are implemented. """ def __init__(self, policy=compat32): self.policy = policy self._headers = list() self._unixfrom = None self._payload = None self._charset = None # Defaults for multipart messages self.preamble = self.epilogue = None self.defects = [] # Default content type self._default_type = 'text/plain' @as_native_str(encoding='utf-8') def __str__(self): """Return the entire formatted message as a string. This includes the headers, body, and envelope header. """ return self.as_string() def as_string(self, unixfrom=False, maxheaderlen=0): """Return the entire formatted message as a (unicode) string. Optional `unixfrom' when True, means include the Unix From_ envelope header. This is a convenience method and may not generate the message exactly as you intend. For more flexibility, use the flatten() method of a Generator instance. """ from future.backports.email.generator import Generator fp = StringIO() g = Generator(fp, mangle_from_=False, maxheaderlen=maxheaderlen) g.flatten(self, unixfrom=unixfrom) return fp.getvalue() def is_multipart(self): """Return True if the message consists of multiple parts.""" return isinstance(self._payload, list) # # Unix From_ line # def set_unixfrom(self, unixfrom): self._unixfrom = unixfrom def get_unixfrom(self): return self._unixfrom # # Payload manipulation. # def attach(self, payload): """Add the given payload to the current payload. The current payload will always be a list of objects after this method is called. If you want to set the payload to a scalar object, use set_payload() instead. """ if self._payload is None: self._payload = [payload] else: self._payload.append(payload) def get_payload(self, i=None, decode=False): """Return a reference to the payload. The payload will either be a list object or a string. If you mutate the list object, you modify the message's payload in place. Optional i returns that index into the payload. Optional decode is a flag indicating whether the payload should be decoded or not, according to the Content-Transfer-Encoding header (default is False). When True and the message is not a multipart, the payload will be decoded if this header's value is `quoted-printable' or `base64'. If some other encoding is used, or the header is missing, or if the payload has bogus data (i.e. bogus base64 or uuencoded data), the payload is returned as-is. If the message is a multipart and the decode flag is True, then None is returned. """ # Here is the logic table for this code, based on the email5.0.0 code: # i decode is_multipart result # ------ ------ ------------ ------------------------------ # None True True None # i True True None # None False True _payload (a list) # i False True _payload element i (a Message) # i False False error (not a list) # i True False error (not a list) # None False False _payload # None True False _payload decoded (bytes) # Note that Barry planned to factor out the 'decode' case, but that # isn't so easy now that we handle the 8 bit data, which needs to be # converted in both the decode and non-decode path. if self.is_multipart(): if decode: return None if i is None: return self._payload else: return self._payload[i] # For backward compatibility, Use isinstance and this error message # instead of the more logical is_multipart test. if i is not None and not isinstance(self._payload, list): raise TypeError('Expected list, got %s' % type(self._payload)) payload = self._payload # cte might be a Header, so for now stringify it. cte = str(self.get('content-transfer-encoding', '')).lower() # payload may be bytes here. if isinstance(payload, str): payload = str(payload) # for Python-Future, so surrogateescape works if utils._has_surrogates(payload): bpayload = payload.encode('ascii', 'surrogateescape') if not decode: try: payload = bpayload.decode(self.get_param('charset', 'ascii'), 'replace') except LookupError: payload = bpayload.decode('ascii', 'replace') elif decode: try: bpayload = payload.encode('ascii') except UnicodeError: # This won't happen for RFC compliant messages (messages # containing only ASCII codepoints in the unicode input). # If it does happen, turn the string into bytes in a way # guaranteed not to fail. bpayload = payload.encode('raw-unicode-escape') if not decode: return payload if cte == 'quoted-printable': return utils._qdecode(bpayload) elif cte == 'base64': # XXX: this is a bit of a hack; decode_b should probably be factored # out somewhere, but I haven't figured out where yet. value, defects = decode_b(b''.join(bpayload.splitlines())) for defect in defects: self.policy.handle_defect(self, defect) return value elif cte in ('x-uuencode', 'uuencode', 'uue', 'x-uue'): in_file = BytesIO(bpayload) out_file = BytesIO() try: uu.decode(in_file, out_file, quiet=True) return out_file.getvalue() except uu.Error: # Some decoding problem return bpayload if isinstance(payload, str): return bpayload return payload def set_payload(self, payload, charset=None): """Set the payload to the given value. Optional charset sets the message's default character set. See set_charset() for details. """ self._payload = payload if charset is not None: self.set_charset(charset) def set_charset(self, charset): """Set the charset of the payload to a given character set. charset can be a Charset instance, a string naming a character set, or None. If it is a string it will be converted to a Charset instance. If charset is None, the charset parameter will be removed from the Content-Type field. Anything else will generate a TypeError. The message will be assumed to be of type text/* encoded with charset.input_charset. It will be converted to charset.output_charset and encoded properly, if needed, when generating the plain text representation of the message. MIME headers (MIME-Version, Content-Type, Content-Transfer-Encoding) will be added as needed. """ if charset is None: self.del_param('charset') self._charset = None return if not isinstance(charset, Charset): charset = Charset(charset) self._charset = charset if 'MIME-Version' not in self: self.add_header('MIME-Version', '1.0') if 'Content-Type' not in self: self.add_header('Content-Type', 'text/plain', charset=charset.get_output_charset()) else: self.set_param('charset', charset.get_output_charset()) if charset != charset.get_output_charset(): self._payload = charset.body_encode(self._payload) if 'Content-Transfer-Encoding' not in self: cte = charset.get_body_encoding() try: cte(self) except TypeError: self._payload = charset.body_encode(self._payload) self.add_header('Content-Transfer-Encoding', cte) def get_charset(self): """Return the Charset instance associated with the message's payload. """ return self._charset # # MAPPING INTERFACE (partial) # def __len__(self): """Return the total number of headers, including duplicates.""" return len(self._headers) def __getitem__(self, name): """Get a header value. Return None if the header is missing instead of raising an exception. Note that if the header appeared multiple times, exactly which occurrence gets returned is undefined. Use get_all() to get all the values matching a header field name. """ return self.get(name) def __setitem__(self, name, val): """Set the value of a header. Note: this does not overwrite an existing header with the same field name. Use __delitem__() first to delete any existing headers. """ max_count = self.policy.header_max_count(name) if max_count: lname = name.lower() found = 0 for k, v in self._headers: if k.lower() == lname: found += 1 if found >= max_count: raise ValueError("There may be at most {} {} headers " "in a message".format(max_count, name)) self._headers.append(self.policy.header_store_parse(name, val)) def __delitem__(self, name): """Delete all occurrences of a header, if present. Does not raise an exception if the header is missing. """ name = name.lower() newheaders = list() for k, v in self._headers: if k.lower() != name: newheaders.append((k, v)) self._headers = newheaders def __contains__(self, name): return name.lower() in [k.lower() for k, v in self._headers] def __iter__(self): for field, value in self._headers: yield field def keys(self): """Return a list of all the message's header field names. These will be sorted in the order they appeared in the original message, or were added to the message, and may contain duplicates. Any fields deleted and re-inserted are always appended to the header list. """ return [k for k, v in self._headers] def values(self): """Return a list of all the message's header values. These will be sorted in the order they appeared in the original message, or were added to the message, and may contain duplicates. Any fields deleted and re-inserted are always appended to the header list. """ return [self.policy.header_fetch_parse(k, v) for k, v in self._headers] def items(self): """Get all the message's header fields and values. These will be sorted in the order they appeared in the original message, or were added to the message, and may contain duplicates. Any fields deleted and re-inserted are always appended to the header list. """ return [(k, self.policy.header_fetch_parse(k, v)) for k, v in self._headers] def get(self, name, failobj=None): """Get a header value. Like __getitem__() but return failobj instead of None when the field is missing. """ name = name.lower() for k, v in self._headers: if k.lower() == name: return self.policy.header_fetch_parse(k, v) return failobj # # "Internal" methods (public API, but only intended for use by a parser # or generator, not normal application code. # def set_raw(self, name, value): """Store name and value in the model without modification. This is an "internal" API, intended only for use by a parser. """ self._headers.append((name, value)) def raw_items(self): """Return the (name, value) header pairs without modification. This is an "internal" API, intended only for use by a generator. """ return iter(self._headers.copy()) # # Additional useful stuff # def get_all(self, name, failobj=None): """Return a list of all the values for the named field. These will be sorted in the order they appeared in the original message, and may contain duplicates. Any fields deleted and re-inserted are always appended to the header list. If no such fields exist, failobj is returned (defaults to None). """ values = [] name = name.lower() for k, v in self._headers: if k.lower() == name: values.append(self.policy.header_fetch_parse(k, v)) if not values: return failobj return values def add_header(self, _name, _value, **_params): """Extended header setting. name is the header field to add. keyword arguments can be used to set additional parameters for the header field, with underscores converted to dashes. Normally the parameter will be added as key="value" unless value is None, in which case only the key will be added. If a parameter value contains non-ASCII characters it can be specified as a three-tuple of (charset, language, value), in which case it will be encoded according to RFC2231 rules. Otherwise it will be encoded using the utf-8 charset and a language of ''. Examples: msg.add_header('content-disposition', 'attachment', filename='bud.gif') msg.add_header('content-disposition', 'attachment', filename=('utf-8', '', 'Fußballer.ppt')) msg.add_header('content-disposition', 'attachment', filename='Fußballer.ppt')) """ parts = [] for k, v in _params.items(): if v is None: parts.append(k.replace('_', '-')) else: parts.append(_formatparam(k.replace('_', '-'), v)) if _value is not None: parts.insert(0, _value) self[_name] = SEMISPACE.join(parts) def replace_header(self, _name, _value): """Replace a header. Replace the first matching header found in the message, retaining header order and case. If no matching header was found, a KeyError is raised. """ _name = _name.lower() for i, (k, v) in zip(range(len(self._headers)), self._headers): if k.lower() == _name: self._headers[i] = self.policy.header_store_parse(k, _value) break else: raise KeyError(_name) # # Use these three methods instead of the three above. # def get_content_type(self): """Return the message's content type. The returned string is coerced to lower case of the form `maintype/subtype'. If there was no Content-Type header in the message, the default type as given by get_default_type() will be returned. Since according to RFC 2045, messages always have a default type this will always return a value. RFC 2045 defines a message's default type to be text/plain unless it appears inside a multipart/digest container, in which case it would be message/rfc822. """ missing = object() value = self.get('content-type', missing) if value is missing: # This should have no parameters return self.get_default_type() ctype = _splitparam(value)[0].lower() # RFC 2045, section 5.2 says if its invalid, use text/plain if ctype.count('/') != 1: return 'text/plain' return ctype def get_content_maintype(self): """Return the message's main content type. This is the `maintype' part of the string returned by get_content_type(). """ ctype = self.get_content_type() return ctype.split('/')[0] def get_content_subtype(self): """Returns the message's sub-content type. This is the `subtype' part of the string returned by get_content_type(). """ ctype = self.get_content_type() return ctype.split('/')[1] def get_default_type(self): """Return the `default' content type. Most messages have a default content type of text/plain, except for messages that are subparts of multipart/digest containers. Such subparts have a default content type of message/rfc822. """ return self._default_type def set_default_type(self, ctype): """Set the `default' content type. ctype should be either "text/plain" or "message/rfc822", although this is not enforced. The default content type is not stored in the Content-Type header. """ self._default_type = ctype def _get_params_preserve(self, failobj, header): # Like get_params() but preserves the quoting of values. BAW: # should this be part of the public interface? missing = object() value = self.get(header, missing) if value is missing: return failobj params = [] for p in _parseparam(value): try: name, val = p.split('=', 1) name = name.strip() val = val.strip() except ValueError: # Must have been a bare attribute name = p.strip() val = '' params.append((name, val)) params = utils.decode_params(params) return params def get_params(self, failobj=None, header='content-type', unquote=True): """Return the message's Content-Type parameters, as a list. The elements of the returned list are 2-tuples of key/value pairs, as split on the `=' sign. The left hand side of the `=' is the key, while the right hand side is the value. If there is no `=' sign in the parameter the value is the empty string. The value is as described in the get_param() method. Optional failobj is the object to return if there is no Content-Type header. Optional header is the header to search instead of Content-Type. If unquote is True, the value is unquoted. """ missing = object() params = self._get_params_preserve(missing, header) if params is missing: return failobj if unquote: return [(k, _unquotevalue(v)) for k, v in params] else: return params def get_param(self, param, failobj=None, header='content-type', unquote=True): """Return the parameter value if found in the Content-Type header. Optional failobj is the object to return if there is no Content-Type header, or the Content-Type header has no such parameter. Optional header is the header to search instead of Content-Type. Parameter keys are always compared case insensitively. The return value can either be a string, or a 3-tuple if the parameter was RFC 2231 encoded. When it's a 3-tuple, the elements of the value are of the form (CHARSET, LANGUAGE, VALUE). Note that both CHARSET and LANGUAGE can be None, in which case you should consider VALUE to be encoded in the us-ascii charset. You can usually ignore LANGUAGE. The parameter value (either the returned string, or the VALUE item in the 3-tuple) is always unquoted, unless unquote is set to False. If your application doesn't care whether the parameter was RFC 2231 encoded, it can turn the return value into a string as follows: param = msg.get_param('foo') param = email.utils.collapse_rfc2231_value(rawparam) """ if header not in self: return failobj for k, v in self._get_params_preserve(failobj, header): if k.lower() == param.lower(): if unquote: return _unquotevalue(v) else: return v return failobj def set_param(self, param, value, header='Content-Type', requote=True, charset=None, language=''): """Set a parameter in the Content-Type header. If the parameter already exists in the header, its value will be replaced with the new value. If header is Content-Type and has not yet been defined for this message, it will be set to "text/plain" and the new parameter and value will be appended as per RFC 2045. An alternate header can specified in the header argument, and all parameters will be quoted as necessary unless requote is False. If charset is specified, the parameter will be encoded according to RFC 2231. Optional language specifies the RFC 2231 language, defaulting to the empty string. Both charset and language should be strings. """ if not isinstance(value, tuple) and charset: value = (charset, language, value) if header not in self and header.lower() == 'content-type': ctype = 'text/plain' else: ctype = self.get(header) if not self.get_param(param, header=header): if not ctype: ctype = _formatparam(param, value, requote) else: ctype = SEMISPACE.join( [ctype, _formatparam(param, value, requote)]) else: ctype = '' for old_param, old_value in self.get_params(header=header, unquote=requote): append_param = '' if old_param.lower() == param.lower(): append_param = _formatparam(param, value, requote) else: append_param = _formatparam(old_param, old_value, requote) if not ctype: ctype = append_param else: ctype = SEMISPACE.join([ctype, append_param]) if ctype != self.get(header): del self[header] self[header] = ctype def del_param(self, param, header='content-type', requote=True): """Remove the given parameter completely from the Content-Type header. The header will be re-written in place without the parameter or its value. All values will be quoted as necessary unless requote is False. Optional header specifies an alternative to the Content-Type header. """ if header not in self: return new_ctype = '' for p, v in self.get_params(header=header, unquote=requote): if p.lower() != param.lower(): if not new_ctype: new_ctype = _formatparam(p, v, requote) else: new_ctype = SEMISPACE.join([new_ctype, _formatparam(p, v, requote)]) if new_ctype != self.get(header): del self[header] self[header] = new_ctype def set_type(self, type, header='Content-Type', requote=True): """Set the main type and subtype for the Content-Type header. type must be a string in the form "maintype/subtype", otherwise a ValueError is raised. This method replaces the Content-Type header, keeping all the parameters in place. If requote is False, this leaves the existing header's quoting as is. Otherwise, the parameters will be quoted (the default). An alternative header can be specified in the header argument. When the Content-Type header is set, we'll always also add a MIME-Version header. """ # BAW: should we be strict? if not type.count('/') == 1: raise ValueError # Set the Content-Type, you get a MIME-Version if header.lower() == 'content-type': del self['mime-version'] self['MIME-Version'] = '1.0' if header not in self: self[header] = type return params = self.get_params(header=header, unquote=requote) del self[header] self[header] = type # Skip the first param; it's the old type. for p, v in params[1:]: self.set_param(p, v, header, requote) def get_filename(self, failobj=None): """Return the filename associated with the payload if present. The filename is extracted from the Content-Disposition header's `filename' parameter, and it is unquoted. If that header is missing the `filename' parameter, this method falls back to looking for the `name' parameter. """ missing = object() filename = self.get_param('filename', missing, 'content-disposition') if filename is missing: filename = self.get_param('name', missing, 'content-type') if filename is missing: return failobj return utils.collapse_rfc2231_value(filename).strip() def get_boundary(self, failobj=None): """Return the boundary associated with the payload if present. The boundary is extracted from the Content-Type header's `boundary' parameter, and it is unquoted. """ missing = object() boundary = self.get_param('boundary', missing) if boundary is missing: return failobj # RFC 2046 says that boundaries may begin but not end in w/s return utils.collapse_rfc2231_value(boundary).rstrip() def set_boundary(self, boundary): """Set the boundary parameter in Content-Type to 'boundary'. This is subtly different than deleting the Content-Type header and adding a new one with a new boundary parameter via add_header(). The main difference is that using the set_boundary() method preserves the order of the Content-Type header in the original message. HeaderParseError is raised if the message has no Content-Type header. """ missing = object() params = self._get_params_preserve(missing, 'content-type') if params is missing: # There was no Content-Type header, and we don't know what type # to set it to, so raise an exception. raise errors.HeaderParseError('No Content-Type header found') newparams = [] foundp = False for pk, pv in params: if pk.lower() == 'boundary': newparams.append(('boundary', '"%s"' % boundary)) foundp = True else: newparams.append((pk, pv)) if not foundp: # The original Content-Type header had no boundary attribute. # Tack one on the end. BAW: should we raise an exception # instead??? newparams.append(('boundary', '"%s"' % boundary)) # Replace the existing Content-Type header with the new value newheaders = [] for h, v in self._headers: if h.lower() == 'content-type': parts = [] for k, v in newparams: if v == '': parts.append(k) else: parts.append('%s=%s' % (k, v)) val = SEMISPACE.join(parts) newheaders.append(self.policy.header_store_parse(h, val)) else: newheaders.append((h, v)) self._headers = newheaders def get_content_charset(self, failobj=None): """Return the charset parameter of the Content-Type header. The returned string is always coerced to lower case. If there is no Content-Type header, or if that header has no charset parameter, failobj is returned. """ missing = object() charset = self.get_param('charset', missing) if charset is missing: return failobj if isinstance(charset, tuple): # RFC 2231 encoded, so decode it, and it better end up as ascii. pcharset = charset[0] or 'us-ascii' try: # LookupError will be raised if the charset isn't known to # Python. UnicodeError will be raised if the encoded text # contains a character not in the charset. as_bytes = charset[2].encode('raw-unicode-escape') charset = str(as_bytes, pcharset) except (LookupError, UnicodeError): charset = charset[2] # charset characters must be in us-ascii range try: charset.encode('us-ascii') except UnicodeError: return failobj # RFC 2046, $4.1.2 says charsets are not case sensitive return charset.lower() def get_charsets(self, failobj=None): """Return a list containing the charset(s) used in this message. The returned list of items describes the Content-Type headers' charset parameter for this message and all the subparts in its payload. Each item will either be a string (the value of the charset parameter in the Content-Type header of that part) or the value of the 'failobj' parameter (defaults to None), if the part does not have a main MIME type of "text", or the charset is not defined. The list will contain one string for each part of the message, plus one for the container message (i.e. self), so that a non-multipart message will still return a list of length 1. """ return [part.get_content_charset(failobj) for part in self.walk()] # I.e. def walk(self): ... from future.backports.email.iterators import walk # Copyright (C) 2001-2007 Python Software Foundation # Author: Barry Warsaw, Thomas Wouters, Anthony Baxter # Contact: email-sig@python.org """A parser of RFC 2822 and MIME email messages.""" from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import __all__ = ['Parser', 'HeaderParser', 'BytesParser', 'BytesHeaderParser'] import warnings from io import StringIO, TextIOWrapper from future.backports.email.feedparser import FeedParser, BytesFeedParser from future.backports.email.message import Message from future.backports.email._policybase import compat32 class Parser(object): def __init__(self, _class=Message, **_3to2kwargs): """Parser of RFC 2822 and MIME email messages. Creates an in-memory object tree representing the email message, which can then be manipulated and turned over to a Generator to return the textual representation of the message. The string must be formatted as a block of RFC 2822 headers and header continuation lines, optionally preceeded by a `Unix-from' header. The header block is terminated either by the end of the string or by a blank line. _class is the class to instantiate for new message objects when they must be created. This class must have a constructor that can take zero arguments. Default is Message.Message. The policy keyword specifies a policy object that controls a number of aspects of the parser's operation. The default policy maintains backward compatibility. """ if 'policy' in _3to2kwargs: policy = _3to2kwargs['policy']; del _3to2kwargs['policy'] else: policy = compat32 self._class = _class self.policy = policy def parse(self, fp, headersonly=False): """Create a message structure from the data in a file. Reads all the data from the file and returns the root of the message structure. Optional headersonly is a flag specifying whether to stop parsing after reading the headers or not. The default is False, meaning it parses the entire contents of the file. """ feedparser = FeedParser(self._class, policy=self.policy) if headersonly: feedparser._set_headersonly() while True: data = fp.read(8192) if not data: break feedparser.feed(data) return feedparser.close() def parsestr(self, text, headersonly=False): """Create a message structure from a string. Returns the root of the message structure. Optional headersonly is a flag specifying whether to stop parsing after reading the headers or not. The default is False, meaning it parses the entire contents of the file. """ return self.parse(StringIO(text), headersonly=headersonly) class HeaderParser(Parser): def parse(self, fp, headersonly=True): return Parser.parse(self, fp, True) def parsestr(self, text, headersonly=True): return Parser.parsestr(self, text, True) class BytesParser(object): def __init__(self, *args, **kw): """Parser of binary RFC 2822 and MIME email messages. Creates an in-memory object tree representing the email message, which can then be manipulated and turned over to a Generator to return the textual representation of the message. The input must be formatted as a block of RFC 2822 headers and header continuation lines, optionally preceeded by a `Unix-from' header. The header block is terminated either by the end of the input or by a blank line. _class is the class to instantiate for new message objects when they must be created. This class must have a constructor that can take zero arguments. Default is Message.Message. """ self.parser = Parser(*args, **kw) def parse(self, fp, headersonly=False): """Create a message structure from the data in a binary file. Reads all the data from the file and returns the root of the message structure. Optional headersonly is a flag specifying whether to stop parsing after reading the headers or not. The default is False, meaning it parses the entire contents of the file. """ fp = TextIOWrapper(fp, encoding='ascii', errors='surrogateescape') with fp: return self.parser.parse(fp, headersonly) def parsebytes(self, text, headersonly=False): """Create a message structure from a byte string. Returns the root of the message structure. Optional headersonly is a flag specifying whether to stop parsing after reading the headers or not. The default is False, meaning it parses the entire contents of the file. """ text = text.decode('ASCII', errors='surrogateescape') return self.parser.parsestr(text, headersonly) class BytesHeaderParser(BytesParser): def parse(self, fp, headersonly=True): return BytesParser.parse(self, fp, headersonly=True) def parsebytes(self, text, headersonly=True): return BytesParser.parsebytes(self, text, headersonly=True) """This will be the home for the policy that hooks in the new code that adds all the email6 features. """ from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import from future.builtins import super from future.standard_library.email._policybase import (Policy, Compat32, compat32, _extend_docstrings) from future.standard_library.email.utils import _has_surrogates from future.standard_library.email.headerregistry import HeaderRegistry as HeaderRegistry __all__ = [ 'Compat32', 'compat32', 'Policy', 'EmailPolicy', 'default', 'strict', 'SMTP', 'HTTP', ] @_extend_docstrings class EmailPolicy(Policy): """+ PROVISIONAL The API extensions enabled by this policy are currently provisional. Refer to the documentation for details. This policy adds new header parsing and folding algorithms. Instead of simple strings, headers are custom objects with custom attributes depending on the type of the field. The folding algorithm fully implements RFCs 2047 and 5322. In addition to the settable attributes listed above that apply to all Policies, this policy adds the following additional attributes: refold_source -- if the value for a header in the Message object came from the parsing of some source, this attribute indicates whether or not a generator should refold that value when transforming the message back into stream form. The possible values are: none -- all source values use original folding long -- source values that have any line that is longer than max_line_length will be refolded all -- all values are refolded. The default is 'long'. header_factory -- a callable that takes two arguments, 'name' and 'value', where 'name' is a header field name and 'value' is an unfolded header field value, and returns a string-like object that represents that header. A default header_factory is provided that understands some of the RFC5322 header field types. (Currently address fields and date fields have special treatment, while all other fields are treated as unstructured. This list will be completed before the extension is marked stable.) """ refold_source = 'long' header_factory = HeaderRegistry() def __init__(self, **kw): # Ensure that each new instance gets a unique header factory # (as opposed to clones, which share the factory). if 'header_factory' not in kw: object.__setattr__(self, 'header_factory', HeaderRegistry()) super().__init__(**kw) def header_max_count(self, name): """+ The implementation for this class returns the max_count attribute from the specialized header class that would be used to construct a header of type 'name'. """ return self.header_factory[name].max_count # The logic of the next three methods is chosen such that it is possible to # switch a Message object between a Compat32 policy and a policy derived # from this class and have the results stay consistent. This allows a # Message object constructed with this policy to be passed to a library # that only handles Compat32 objects, or to receive such an object and # convert it to use the newer style by just changing its policy. It is # also chosen because it postpones the relatively expensive full rfc5322 # parse until as late as possible when parsing from source, since in many # applications only a few headers will actually be inspected. def header_source_parse(self, sourcelines): """+ The name is parsed as everything up to the ':' and returned unmodified. The value is determined by stripping leading whitespace off the remainder of the first line, joining all subsequent lines together, and stripping any trailing carriage return or linefeed characters. (This is the same as Compat32). """ name, value = sourcelines[0].split(':', 1) value = value.lstrip(' \t') + ''.join(sourcelines[1:]) return (name, value.rstrip('\r\n')) def header_store_parse(self, name, value): """+ The name is returned unchanged. If the input value has a 'name' attribute and it matches the name ignoring case, the value is returned unchanged. Otherwise the name and value are passed to header_factory method, and the resulting custom header object is returned as the value. In this case a ValueError is raised if the input value contains CR or LF characters. """ if hasattr(value, 'name') and value.name.lower() == name.lower(): return (name, value) if isinstance(value, str) and len(value.splitlines())>1: raise ValueError("Header values may not contain linefeed " "or carriage return characters") return (name, self.header_factory(name, value)) def header_fetch_parse(self, name, value): """+ If the value has a 'name' attribute, it is returned to unmodified. Otherwise the name and the value with any linesep characters removed are passed to the header_factory method, and the resulting custom header object is returned. Any surrogateescaped bytes get turned into the unicode unknown-character glyph. """ if hasattr(value, 'name'): return value return self.header_factory(name, ''.join(value.splitlines())) def fold(self, name, value): """+ Header folding is controlled by the refold_source policy setting. A value is considered to be a 'source value' if and only if it does not have a 'name' attribute (having a 'name' attribute means it is a header object of some sort). If a source value needs to be refolded according to the policy, it is converted into a custom header object by passing the name and the value with any linesep characters removed to the header_factory method. Folding of a custom header object is done by calling its fold method with the current policy. Source values are split into lines using splitlines. If the value is not to be refolded, the lines are rejoined using the linesep from the policy and returned. The exception is lines containing non-ascii binary data. In that case the value is refolded regardless of the refold_source setting, which causes the binary data to be CTE encoded using the unknown-8bit charset. """ return self._fold(name, value, refold_binary=True) def fold_binary(self, name, value): """+ The same as fold if cte_type is 7bit, except that the returned value is bytes. If cte_type is 8bit, non-ASCII binary data is converted back into bytes. Headers with binary data are not refolded, regardless of the refold_header setting, since there is no way to know whether the binary data consists of single byte characters or multibyte characters. """ folded = self._fold(name, value, refold_binary=self.cte_type=='7bit') return folded.encode('ascii', 'surrogateescape') def _fold(self, name, value, refold_binary=False): if hasattr(value, 'name'): return value.fold(policy=self) maxlen = self.max_line_length if self.max_line_length else float('inf') lines = value.splitlines() refold = (self.refold_source == 'all' or self.refold_source == 'long' and (lines and len(lines[0])+len(name)+2 > maxlen or any(len(x) > maxlen for x in lines[1:]))) if refold or refold_binary and _has_surrogates(value): return self.header_factory(name, ''.join(lines)).fold(policy=self) return name + ': ' + self.linesep.join(lines) + self.linesep default = EmailPolicy() # Make the default policy use the class default header_factory del default.header_factory strict = default.clone(raise_on_defect=True) SMTP = default.clone(linesep='\r\n') HTTP = default.clone(linesep='\r\n', max_line_length=None) # Copyright (C) 2001-2006 Python Software Foundation # Author: Ben Gertzfield # Contact: email-sig@python.org """Quoted-printable content transfer encoding per RFCs 2045-2047. This module handles the content transfer encoding method defined in RFC 2045 to encode US ASCII-like 8-bit data called `quoted-printable'. It is used to safely encode text that is in a character set similar to the 7-bit US ASCII character set, but that includes some 8-bit characters that are normally not allowed in email bodies or headers. Quoted-printable is very space-inefficient for encoding binary files; use the email.base64mime module for that instead. This module provides an interface to encode and decode both headers and bodies with quoted-printable encoding. RFC 2045 defines a method for including character set information in an `encoded-word' in a header. This method is commonly used for 8-bit real names in To:/From:/Cc: etc. fields, as well as Subject: lines. This module does not do the line wrapping or end-of-line character conversion necessary for proper internationalized headers; it only does dumb encoding and decoding. To deal with the various line wrapping issues, use the email.header module. """ from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import from future.builtins import bytes, chr, dict, int, range, super __all__ = [ 'body_decode', 'body_encode', 'body_length', 'decode', 'decodestring', 'header_decode', 'header_encode', 'header_length', 'quote', 'unquote', ] import re import io from string import ascii_letters, digits, hexdigits CRLF = '\r\n' NL = '\n' EMPTYSTRING = '' # Build a mapping of octets to the expansion of that octet. Since we're only # going to have 256 of these things, this isn't terribly inefficient # space-wise. Remember that headers and bodies have different sets of safe # characters. Initialize both maps with the full expansion, and then override # the safe bytes with the more compact form. _QUOPRI_HEADER_MAP = dict((c, '=%02X' % c) for c in range(256)) _QUOPRI_BODY_MAP = _QUOPRI_HEADER_MAP.copy() # Safe header bytes which need no encoding. for c in bytes(b'-!*+/' + ascii_letters.encode('ascii') + digits.encode('ascii')): _QUOPRI_HEADER_MAP[c] = chr(c) # Headers have one other special encoding; spaces become underscores. _QUOPRI_HEADER_MAP[ord(' ')] = '_' # Safe body bytes which need no encoding. for c in bytes(b' !"#$%&\'()*+,-./0123456789:;<>' b'?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`' b'abcdefghijklmnopqrstuvwxyz{|}~\t'): _QUOPRI_BODY_MAP[c] = chr(c) # Helpers def header_check(octet): """Return True if the octet should be escaped with header quopri.""" return chr(octet) != _QUOPRI_HEADER_MAP[octet] def body_check(octet): """Return True if the octet should be escaped with body quopri.""" return chr(octet) != _QUOPRI_BODY_MAP[octet] def header_length(bytearray): """Return a header quoted-printable encoding length. Note that this does not include any RFC 2047 chrome added by `header_encode()`. :param bytearray: An array of bytes (a.k.a. octets). :return: The length in bytes of the byte array when it is encoded with quoted-printable for headers. """ return sum(len(_QUOPRI_HEADER_MAP[octet]) for octet in bytearray) def body_length(bytearray): """Return a body quoted-printable encoding length. :param bytearray: An array of bytes (a.k.a. octets). :return: The length in bytes of the byte array when it is encoded with quoted-printable for bodies. """ return sum(len(_QUOPRI_BODY_MAP[octet]) for octet in bytearray) def _max_append(L, s, maxlen, extra=''): if not isinstance(s, str): s = chr(s) if not L: L.append(s.lstrip()) elif len(L[-1]) + len(s) <= maxlen: L[-1] += extra + s else: L.append(s.lstrip()) def unquote(s): """Turn a string in the form =AB to the ASCII character with value 0xab""" return chr(int(s[1:3], 16)) def quote(c): return '=%02X' % ord(c) def header_encode(header_bytes, charset='iso-8859-1'): """Encode a single header line with quoted-printable (like) encoding. Defined in RFC 2045, this `Q' encoding is similar to quoted-printable, but used specifically for email header fields to allow charsets with mostly 7 bit characters (and some 8 bit) to remain more or less readable in non-RFC 2045 aware mail clients. charset names the character set to use in the RFC 2046 header. It defaults to iso-8859-1. """ # Return empty headers as an empty string. if not header_bytes: return '' # Iterate over every byte, encoding if necessary. encoded = [] for octet in header_bytes: encoded.append(_QUOPRI_HEADER_MAP[octet]) # Now add the RFC chrome to each encoded chunk and glue the chunks # together. return '=?%s?q?%s?=' % (charset, EMPTYSTRING.join(encoded)) class _body_accumulator(io.StringIO): def __init__(self, maxlinelen, eol, *args, **kw): super().__init__(*args, **kw) self.eol = eol self.maxlinelen = self.room = maxlinelen def write_str(self, s): """Add string s to the accumulated body.""" self.write(s) self.room -= len(s) def newline(self): """Write eol, then start new line.""" self.write_str(self.eol) self.room = self.maxlinelen def write_soft_break(self): """Write a soft break, then start a new line.""" self.write_str('=') self.newline() def write_wrapped(self, s, extra_room=0): """Add a soft line break if needed, then write s.""" if self.room < len(s) + extra_room: self.write_soft_break() self.write_str(s) def write_char(self, c, is_last_char): if not is_last_char: # Another character follows on this line, so we must leave # extra room, either for it or a soft break, and whitespace # need not be quoted. self.write_wrapped(c, extra_room=1) elif c not in ' \t': # For this and remaining cases, no more characters follow, # so there is no need to reserve extra room (since a hard # break will immediately follow). self.write_wrapped(c) elif self.room >= 3: # It's a whitespace character at end-of-line, and we have room # for the three-character quoted encoding. self.write(quote(c)) elif self.room == 2: # There's room for the whitespace character and a soft break. self.write(c) self.write_soft_break() else: # There's room only for a soft break. The quoted whitespace # will be the only content on the subsequent line. self.write_soft_break() self.write(quote(c)) def body_encode(body, maxlinelen=76, eol=NL): """Encode with quoted-printable, wrapping at maxlinelen characters. Each line of encoded text will end with eol, which defaults to "\\n". Set this to "\\r\\n" if you will be using the result of this function directly in an email. Each line will be wrapped at, at most, maxlinelen characters before the eol string (maxlinelen defaults to 76 characters, the maximum value permitted by RFC 2045). Long lines will have the 'soft line break' quoted-printable character "=" appended to them, so the decoded text will be identical to the original text. The minimum maxlinelen is 4 to have room for a quoted character ("=XX") followed by a soft line break. Smaller values will generate a ValueError. """ if maxlinelen < 4: raise ValueError("maxlinelen must be at least 4") if not body: return body # The last line may or may not end in eol, but all other lines do. last_has_eol = (body[-1] in '\r\n') # This accumulator will make it easier to build the encoded body. encoded_body = _body_accumulator(maxlinelen, eol) lines = body.splitlines() last_line_no = len(lines) - 1 for line_no, line in enumerate(lines): last_char_index = len(line) - 1 for i, c in enumerate(line): if body_check(ord(c)): c = quote(c) encoded_body.write_char(c, i==last_char_index) # Add an eol if input line had eol. All input lines have eol except # possibly the last one. if line_no < last_line_no or last_has_eol: encoded_body.newline() return encoded_body.getvalue() # BAW: I'm not sure if the intent was for the signature of this function to be # the same as base64MIME.decode() or not... def decode(encoded, eol=NL): """Decode a quoted-printable string. Lines are separated with eol, which defaults to \\n. """ if not encoded: return encoded # BAW: see comment in encode() above. Again, we're building up the # decoded string with string concatenation, which could be done much more # efficiently. decoded = '' for line in encoded.splitlines(): line = line.rstrip() if not line: decoded += eol continue i = 0 n = len(line) while i < n: c = line[i] if c != '=': decoded += c i += 1 # Otherwise, c == "=". Are we at the end of the line? If so, add # a soft line break. elif i+1 == n: i += 1 continue # Decode if in form =AB elif i+2 < n and line[i+1] in hexdigits and line[i+2] in hexdigits: decoded += unquote(line[i:i+3]) i += 3 # Otherwise, not in form =AB, pass literally else: decoded += c i += 1 if i == n: decoded += eol # Special case if original string did not end with eol if encoded[-1] not in '\r\n' and decoded.endswith(eol): decoded = decoded[:-1] return decoded # For convenience and backwards compatibility w/ standard base64 module body_decode = decode decodestring = decode def _unquote_match(match): """Turn a match in the form =AB to the ASCII character with value 0xab""" s = match.group(0) return unquote(s) # Header decoding is done a bit differently def header_decode(s): """Decode a string encoded with RFC 2045 MIME header `Q' encoding. This function does not parse a full MIME header value encoded with quoted-printable (like =?iso-8895-1?q?Hello_World?=) -- please use the high level email.header class for that functionality. """ s = s.replace('_', ' ') return re.sub(r'=[a-fA-F0-9]{2}', _unquote_match, s, re.ASCII) # Copyright (C) 2001-2010 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Miscellaneous utilities.""" from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import from future import utils from future.builtins import bytes, int, str __all__ = [ 'collapse_rfc2231_value', 'decode_params', 'decode_rfc2231', 'encode_rfc2231', 'formataddr', 'formatdate', 'format_datetime', 'getaddresses', 'make_msgid', 'mktime_tz', 'parseaddr', 'parsedate', 'parsedate_tz', 'parsedate_to_datetime', 'unquote', ] import os import re if utils.PY2: re.ASCII = 0 import time import base64 import random import socket from future.backports import datetime from future.backports.urllib.parse import quote as url_quote, unquote as url_unquote import warnings from io import StringIO from future.backports.email._parseaddr import quote from future.backports.email._parseaddr import AddressList as _AddressList from future.backports.email._parseaddr import mktime_tz from future.backports.email._parseaddr import parsedate, parsedate_tz, _parsedate_tz from quopri import decodestring as _qdecode # Intrapackage imports from future.backports.email.encoders import _bencode, _qencode from future.backports.email.charset import Charset COMMASPACE = ', ' EMPTYSTRING = '' UEMPTYSTRING = '' CRLF = '\r\n' TICK = "'" specialsre = re.compile(r'[][\\()<>@,:;".]') escapesre = re.compile(r'[\\"]') # How to figure out if we are processing strings that come from a byte # source with undecodable characters. _has_surrogates = re.compile( '([^\ud800-\udbff]|\A)[\udc00-\udfff]([^\udc00-\udfff]|\Z)').search # How to deal with a string containing bytes before handing it to the # application through the 'normal' interface. def _sanitize(string): # Turn any escaped bytes into unicode 'unknown' char. original_bytes = string.encode('ascii', 'surrogateescape') return original_bytes.decode('ascii', 'replace') # Helpers def formataddr(pair, charset='utf-8'): """The inverse of parseaddr(), this takes a 2-tuple of the form (realname, email_address) and returns the string value suitable for an RFC 2822 From, To or Cc header. If the first element of pair is false, then the second element is returned unmodified. Optional charset if given is the character set that is used to encode realname in case realname is not ASCII safe. Can be an instance of str or a Charset-like object which has a header_encode method. Default is 'utf-8'. """ name, address = pair # The address MUST (per RFC) be ascii, so raise an UnicodeError if it isn't. address.encode('ascii') if name: try: name.encode('ascii') except UnicodeEncodeError: if isinstance(charset, str): charset = Charset(charset) encoded_name = charset.header_encode(name) return "%s <%s>" % (encoded_name, address) else: quotes = '' if specialsre.search(name): quotes = '"' name = escapesre.sub(r'\\\g<0>', name) return '%s%s%s <%s>' % (quotes, name, quotes, address) return address def getaddresses(fieldvalues): """Return a list of (REALNAME, EMAIL) for each fieldvalue.""" all = COMMASPACE.join(fieldvalues) a = _AddressList(all) return a.addresslist ecre = re.compile(r''' =\? # literal =? (?P[^?]*?) # non-greedy up to the next ? is the charset \? # literal ? (?P[qb]) # either a "q" or a "b", case insensitive \? # literal ? (?P.*?) # non-greedy up to the next ?= is the atom \?= # literal ?= ''', re.VERBOSE | re.IGNORECASE) def _format_timetuple_and_zone(timetuple, zone): return '%s, %02d %s %04d %02d:%02d:%02d %s' % ( ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'][timetuple[6]], timetuple[2], ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'][timetuple[1] - 1], timetuple[0], timetuple[3], timetuple[4], timetuple[5], zone) def formatdate(timeval=None, localtime=False, usegmt=False): """Returns a date string as specified by RFC 2822, e.g.: Fri, 09 Nov 2001 01:08:47 -0000 Optional timeval if given is a floating point time value as accepted by gmtime() and localtime(), otherwise the current time is used. Optional localtime is a flag that when True, interprets timeval, and returns a date relative to the local timezone instead of UTC, properly taking daylight savings time into account. Optional argument usegmt means that the timezone is written out as an ascii string, not numeric one (so "GMT" instead of "+0000"). This is needed for HTTP, and is only used when localtime==False. """ # Note: we cannot use strftime() because that honors the locale and RFC # 2822 requires that day and month names be the English abbreviations. if timeval is None: timeval = time.time() if localtime: now = time.localtime(timeval) # Calculate timezone offset, based on whether the local zone has # daylight savings time, and whether DST is in effect. if time.daylight and now[-1]: offset = time.altzone else: offset = time.timezone hours, minutes = divmod(abs(offset), 3600) # Remember offset is in seconds west of UTC, but the timezone is in # minutes east of UTC, so the signs differ. if offset > 0: sign = '-' else: sign = '+' zone = '%s%02d%02d' % (sign, hours, minutes // 60) else: now = time.gmtime(timeval) # Timezone offset is always -0000 if usegmt: zone = 'GMT' else: zone = '-0000' return _format_timetuple_and_zone(now, zone) def format_datetime(dt, usegmt=False): """Turn a datetime into a date string as specified in RFC 2822. If usegmt is True, dt must be an aware datetime with an offset of zero. In this case 'GMT' will be rendered instead of the normal +0000 required by RFC2822. This is to support HTTP headers involving date stamps. """ now = dt.timetuple() if usegmt: if dt.tzinfo is None or dt.tzinfo != datetime.timezone.utc: raise ValueError("usegmt option requires a UTC datetime") zone = 'GMT' elif dt.tzinfo is None: zone = '-0000' else: zone = dt.strftime("%z") return _format_timetuple_and_zone(now, zone) def make_msgid(idstring=None, domain=None): """Returns a string suitable for RFC 2822 compliant Message-ID, e.g: <20020201195627.33539.96671@nightshade.la.mastaler.com> Optional idstring if given is a string used to strengthen the uniqueness of the message id. Optional domain if given provides the portion of the message id after the '@'. It defaults to the locally defined hostname. """ timeval = time.time() utcdate = time.strftime('%Y%m%d%H%M%S', time.gmtime(timeval)) pid = os.getpid() randint = random.randrange(100000) if idstring is None: idstring = '' else: idstring = '.' + idstring if domain is None: domain = socket.getfqdn() msgid = '<%s.%s.%s%s@%s>' % (utcdate, pid, randint, idstring, domain) return msgid def parsedate_to_datetime(data): _3to2list = list(_parsedate_tz(data)) dtuple, tz, = [_3to2list[:-1]] + _3to2list[-1:] if tz is None: return datetime.datetime(*dtuple[:6]) return datetime.datetime(*dtuple[:6], tzinfo=datetime.timezone(datetime.timedelta(seconds=tz))) def parseaddr(addr): addrs = _AddressList(addr).addresslist if not addrs: return '', '' return addrs[0] # rfc822.unquote() doesn't properly de-backslash-ify in Python pre-2.3. def unquote(str): """Remove quotes from a string.""" if len(str) > 1: if str.startswith('"') and str.endswith('"'): return str[1:-1].replace('\\\\', '\\').replace('\\"', '"') if str.startswith('<') and str.endswith('>'): return str[1:-1] return str # RFC2231-related functions - parameter encoding and decoding def decode_rfc2231(s): """Decode string according to RFC 2231""" parts = s.split(TICK, 2) if len(parts) <= 2: return None, None, s return parts def encode_rfc2231(s, charset=None, language=None): """Encode string according to RFC 2231. If neither charset nor language is given, then s is returned as-is. If charset is given but not language, the string is encoded using the empty string for language. """ s = url_quote(s, safe='', encoding=charset or 'ascii') if charset is None and language is None: return s if language is None: language = '' return "%s'%s'%s" % (charset, language, s) rfc2231_continuation = re.compile(r'^(?P\w+)\*((?P[0-9]+)\*?)?$', re.ASCII) def decode_params(params): """Decode parameters list according to RFC 2231. params is a sequence of 2-tuples containing (param name, string value). """ # Copy params so we don't mess with the original params = params[:] new_params = [] # Map parameter's name to a list of continuations. The values are a # 3-tuple of the continuation number, the string value, and a flag # specifying whether a particular segment is %-encoded. rfc2231_params = {} name, value = params.pop(0) new_params.append((name, value)) while params: name, value = params.pop(0) if name.endswith('*'): encoded = True else: encoded = False value = unquote(value) mo = rfc2231_continuation.match(name) if mo: name, num = mo.group('name', 'num') if num is not None: num = int(num) rfc2231_params.setdefault(name, []).append((num, value, encoded)) else: new_params.append((name, '"%s"' % quote(value))) if rfc2231_params: for name, continuations in rfc2231_params.items(): value = [] extended = False # Sort by number continuations.sort() # And now append all values in numerical order, converting # %-encodings for the encoded segments. If any of the # continuation names ends in a *, then the entire string, after # decoding segments and concatenating, must have the charset and # language specifiers at the beginning of the string. for num, s, encoded in continuations: if encoded: # Decode as "latin-1", so the characters in s directly # represent the percent-encoded octet values. # collapse_rfc2231_value treats this as an octet sequence. s = url_unquote(s, encoding="latin-1") extended = True value.append(s) value = quote(EMPTYSTRING.join(value)) if extended: charset, language, value = decode_rfc2231(value) new_params.append((name, (charset, language, '"%s"' % value))) else: new_params.append((name, '"%s"' % value)) return new_params def collapse_rfc2231_value(value, errors='replace', fallback_charset='us-ascii'): if not isinstance(value, tuple) or len(value) != 3: return unquote(value) # While value comes to us as a unicode string, we need it to be a bytes # object. We do not want bytes() normal utf-8 decoder, we want a straight # interpretation of the string as character bytes. charset, language, text = value rawbytes = bytes(text, 'raw-unicode-escape') try: return str(rawbytes, charset, errors) except LookupError: # charset is not a known codec. return unquote(text) # # datetime doesn't provide a localtime function yet, so provide one. Code # adapted from the patch in issue 9527. This may not be perfect, but it is # better than not having it. # def localtime(dt=None, isdst=-1): """Return local time as an aware datetime object. If called without arguments, return current time. Otherwise *dt* argument should be a datetime instance, and it is converted to the local time zone according to the system time zone database. If *dt* is naive (that is, dt.tzinfo is None), it is assumed to be in local time. In this case, a positive or zero value for *isdst* causes localtime to presume initially that summer time (for example, Daylight Saving Time) is or is not (respectively) in effect for the specified time. A negative value for *isdst* causes the localtime() function to attempt to divine whether summer time is in effect for the specified time. """ if dt is None: return datetime.datetime.now(datetime.timezone.utc).astimezone() if dt.tzinfo is not None: return dt.astimezone() # We have a naive datetime. Convert to a (localtime) timetuple and pass to # system mktime together with the isdst hint. System mktime will return # seconds since epoch. tm = dt.timetuple()[:-1] + (isdst,) seconds = time.mktime(tm) localtm = time.localtime(seconds) try: delta = datetime.timedelta(seconds=localtm.tm_gmtoff) tz = datetime.timezone(delta, localtm.tm_zone) except AttributeError: # Compute UTC offset and compare with the value implied by tm_isdst. # If the values match, use the zone name implied by tm_isdst. delta = dt - datetime.datetime(*time.gmtime(seconds)[:6]) dst = time.daylight and localtm.tm_isdst > 0 gmtoff = -(time.altzone if dst else time.timezone) if delta == datetime.timedelta(seconds=gmtoff): tz = datetime.timezone(delta, time.tzname[dst]) else: tz = datetime.timezone(delta) return dt.replace(tzinfo=tz) # Copyright (C) 2001-2006 Python Software Foundation # Author: Keith Dart # Contact: email-sig@python.org """Class representing application/* type MIME documents.""" from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import from future.backports.email import encoders from future.backports.email.mime.nonmultipart import MIMENonMultipart __all__ = ["MIMEApplication"] class MIMEApplication(MIMENonMultipart): """Class for generating application/* MIME documents.""" def __init__(self, _data, _subtype='octet-stream', _encoder=encoders.encode_base64, **_params): """Create an application/* type MIME document. _data is a string containing the raw application data. _subtype is the MIME content type subtype, defaulting to 'octet-stream'. _encoder is a function which will perform the actual encoding for transport of the application data, defaulting to base64 encoding. Any additional keyword arguments are passed to the base class constructor, which turns them into parameters on the Content-Type header. """ if _subtype is None: raise TypeError('Invalid application MIME subtype') MIMENonMultipart.__init__(self, 'application', _subtype, **_params) self.set_payload(_data) _encoder(self) # Copyright (C) 2001-2007 Python Software Foundation # Author: Anthony Baxter # Contact: email-sig@python.org """Class representing audio/* type MIME documents.""" from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import __all__ = ['MIMEAudio'] import sndhdr from io import BytesIO from future.backports.email import encoders from future.backports.email.mime.nonmultipart import MIMENonMultipart _sndhdr_MIMEmap = {'au' : 'basic', 'wav' :'x-wav', 'aiff':'x-aiff', 'aifc':'x-aiff', } # There are others in sndhdr that don't have MIME types. :( # Additional ones to be added to sndhdr? midi, mp3, realaudio, wma?? def _whatsnd(data): """Try to identify a sound file type. sndhdr.what() has a pretty cruddy interface, unfortunately. This is why we re-do it here. It would be easier to reverse engineer the Unix 'file' command and use the standard 'magic' file, as shipped with a modern Unix. """ hdr = data[:512] fakefile = BytesIO(hdr) for testfn in sndhdr.tests: res = testfn(hdr, fakefile) if res is not None: return _sndhdr_MIMEmap.get(res[0]) return None class MIMEAudio(MIMENonMultipart): """Class for generating audio/* MIME documents.""" def __init__(self, _audiodata, _subtype=None, _encoder=encoders.encode_base64, **_params): """Create an audio/* type MIME document. _audiodata is a string containing the raw audio data. If this data can be decoded by the standard Python `sndhdr' module, then the subtype will be automatically included in the Content-Type header. Otherwise, you can specify the specific audio subtype via the _subtype parameter. If _subtype is not given, and no subtype can be guessed, a TypeError is raised. _encoder is a function which will perform the actual encoding for transport of the image data. It takes one argument, which is this Image instance. It should use get_payload() and set_payload() to change the payload to the encoded form. It should also add any Content-Transfer-Encoding or other headers to the message as necessary. The default encoding is Base64. Any additional keyword arguments are passed to the base class constructor, which turns them into parameters on the Content-Type header. """ if _subtype is None: _subtype = _whatsnd(_audiodata) if _subtype is None: raise TypeError('Could not find audio MIME subtype') MIMENonMultipart.__init__(self, 'audio', _subtype, **_params) self.set_payload(_audiodata) _encoder(self) # Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Base class for MIME specializations.""" from __future__ import absolute_import, division, unicode_literals from future.backports.email import message __all__ = ['MIMEBase'] class MIMEBase(message.Message): """Base class for MIME specializations.""" def __init__(self, _maintype, _subtype, **_params): """This constructor adds a Content-Type: and a MIME-Version: header. The Content-Type: header is taken from the _maintype and _subtype arguments. Additional parameters for this header are taken from the keyword arguments. """ message.Message.__init__(self) ctype = '%s/%s' % (_maintype, _subtype) self.add_header('Content-Type', ctype, **_params) self['MIME-Version'] = '1.0' # Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Class representing image/* type MIME documents.""" from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import __all__ = ['MIMEImage'] import imghdr from future.backports.email import encoders from future.backports.email.mime.nonmultipart import MIMENonMultipart class MIMEImage(MIMENonMultipart): """Class for generating image/* type MIME documents.""" def __init__(self, _imagedata, _subtype=None, _encoder=encoders.encode_base64, **_params): """Create an image/* type MIME document. _imagedata is a string containing the raw image data. If this data can be decoded by the standard Python `imghdr' module, then the subtype will be automatically included in the Content-Type header. Otherwise, you can specify the specific image subtype via the _subtype parameter. _encoder is a function which will perform the actual encoding for transport of the image data. It takes one argument, which is this Image instance. It should use get_payload() and set_payload() to change the payload to the encoded form. It should also add any Content-Transfer-Encoding or other headers to the message as necessary. The default encoding is Base64. Any additional keyword arguments are passed to the base class constructor, which turns them into parameters on the Content-Type header. """ if _subtype is None: _subtype = imghdr.what(None, _imagedata) if _subtype is None: raise TypeError('Could not guess image MIME subtype') MIMENonMultipart.__init__(self, 'image', _subtype, **_params) self.set_payload(_imagedata) _encoder(self) # Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Class representing message/* MIME documents.""" from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import __all__ = ['MIMEMessage'] from future.backports.email import message from future.backports.email.mime.nonmultipart import MIMENonMultipart class MIMEMessage(MIMENonMultipart): """Class representing message/* MIME documents.""" def __init__(self, _msg, _subtype='rfc822'): """Create a message/* type MIME document. _msg is a message object and must be an instance of Message, or a derived class of Message, otherwise a TypeError is raised. Optional _subtype defines the subtype of the contained message. The default is "rfc822" (this is defined by the MIME standard, even though the term "rfc822" is technically outdated by RFC 2822). """ MIMENonMultipart.__init__(self, 'message', _subtype) if not isinstance(_msg, message.Message): raise TypeError('Argument is not an instance of Message') # It's convenient to use this base class method. We need to do it # this way or we'll get an exception message.Message.attach(self, _msg) # And be sure our default type is set correctly self.set_default_type('message/rfc822') # Copyright (C) 2002-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Base class for MIME multipart/* type messages.""" from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import __all__ = ['MIMEMultipart'] from future.backports.email.mime.base import MIMEBase class MIMEMultipart(MIMEBase): """Base class for MIME multipart/* type messages.""" def __init__(self, _subtype='mixed', boundary=None, _subparts=None, **_params): """Creates a multipart/* type message. By default, creates a multipart/mixed message, with proper Content-Type and MIME-Version headers. _subtype is the subtype of the multipart content type, defaulting to `mixed'. boundary is the multipart boundary string. By default it is calculated as needed. _subparts is a sequence of initial subparts for the payload. It must be an iterable object, such as a list. You can always attach new subparts to the message by using the attach() method. Additional parameters for the Content-Type header are taken from the keyword arguments (or passed into the _params argument). """ MIMEBase.__init__(self, 'multipart', _subtype, **_params) # Initialise _payload to an empty list as the Message superclass's # implementation of is_multipart assumes that _payload is a list for # multipart messages. self._payload = [] if _subparts: for p in _subparts: self.attach(p) if boundary: self.set_boundary(boundary) # Copyright (C) 2002-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Base class for MIME type messages that are not multipart.""" from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import __all__ = ['MIMENonMultipart'] from future.backports.email import errors from future.backports.email.mime.base import MIMEBase class MIMENonMultipart(MIMEBase): """Base class for MIME multipart/* type messages.""" def attach(self, payload): # The public API prohibits attaching multiple subparts to MIMEBase # derived subtypes since none of them are, by definition, of content # type multipart/* raise errors.MultipartConversionError( 'Cannot attach additional subparts to non-multipart/*') # Copyright (C) 2001-2006 Python Software Foundation # Author: Barry Warsaw # Contact: email-sig@python.org """Class representing text/* type MIME documents.""" from __future__ import unicode_literals from __future__ import division from __future__ import absolute_import __all__ = ['MIMEText'] from future.backports.email.encoders import encode_7or8bit from future.backports.email.mime.nonmultipart import MIMENonMultipart class MIMEText(MIMENonMultipart): """Class for generating text/* type MIME documents.""" def __init__(self, _text, _subtype='plain', _charset=None): """Create a text/* type MIME document. _text is the string for this message object. _subtype is the MIME sub content type, defaulting to "plain". _charset is the character set parameter added to the Content-Type header. This defaults to "us-ascii". Note that as a side-effect, the Content-Transfer-Encoding header will also be set. """ # If no _charset was specified, check to see if there are non-ascii # characters present. If not, use 'us-ascii', otherwise use utf-8. # XXX: This can be removed once #7304 is fixed. if _charset is None: try: _text.encode('us-ascii') _charset = 'us-ascii' except UnicodeEncodeError: _charset = 'utf-8' MIMENonMultipart.__init__(self, 'text', _subtype, **{'charset': _charset}) self.set_payload(_text, _charset) """ General functions for HTML manipulation, backported from Py3. Note that this uses Python 2.7 code with the corresponding Python 3 module names and locations. """ from __future__ import unicode_literals _escape_map = {ord('&'): '&', ord('<'): '<', ord('>'): '>'} _escape_map_full = {ord('&'): '&', ord('<'): '<', ord('>'): '>', ord('"'): '"', ord('\''): '''} # NB: this is a candidate for a bytes/string polymorphic interface def escape(s, quote=True): """ Replace special characters "&", "<" and ">" to HTML-safe sequences. If the optional flag quote is true (the default), the quotation mark characters, both double quote (") and single quote (') characters are also translated. """ assert not isinstance(s, bytes), 'Pass a unicode string' if quote: return s.translate(_escape_map_full) return s.translate(_escape_map) """A parser for HTML and XHTML. Backported for python-future from Python 3.3. """ # This file is based on sgmllib.py, but the API is slightly different. # XXX There should be a way to distinguish between PCDATA (parsed # character data -- the normal case), RCDATA (replaceable character # data -- only char and entity references and end tags are special) # and CDATA (character data -- only end tags are special). from __future__ import (absolute_import, division, print_function, unicode_literals) from future.builtins import * from future.backports import _markupbase import re import warnings # Regular expressions used for parsing interesting_normal = re.compile('[&<]') incomplete = re.compile('&[a-zA-Z#]') entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]') charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]') starttagopen = re.compile('<[a-zA-Z]') piclose = re.compile('>') commentclose = re.compile(r'--\s*>') tagfind = re.compile('([a-zA-Z][-.a-zA-Z0-9:_]*)(?:\s|/(?!>))*') # see http://www.w3.org/TR/html5/tokenization.html#tag-open-state # and http://www.w3.org/TR/html5/tokenization.html#tag-name-state tagfind_tolerant = re.compile('[a-zA-Z][^\t\n\r\f />\x00]*') # Note: # 1) the strict attrfind isn't really strict, but we can't make it # correctly strict without breaking backward compatibility; # 2) if you change attrfind remember to update locatestarttagend too; # 3) if you change attrfind and/or locatestarttagend the parser will # explode, so don't do it. attrfind = re.compile( r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*' r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?') attrfind_tolerant = re.compile( r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*' r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*') locatestarttagend = re.compile(r""" <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name (?:\s+ # whitespace before attribute name (?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name (?:\s*=\s* # value indicator (?:'[^']*' # LITA-enclosed value |\"[^\"]*\" # LIT-enclosed value |[^'\">\s]+ # bare value ) )? ) )* \s* # trailing whitespace """, re.VERBOSE) locatestarttagend_tolerant = re.compile(r""" <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name (?:[\s/]* # optional whitespace before attribute name (?:(?<=['"\s/])[^\s/>][^\s/=>]* # attribute name (?:\s*=+\s* # value indicator (?:'[^']*' # LITA-enclosed value |"[^"]*" # LIT-enclosed value |(?!['"])[^>\s]* # bare value ) (?:\s*,)* # possibly followed by a comma )?(?:\s|/(?!>))* )* )? \s* # trailing whitespace """, re.VERBOSE) endendtag = re.compile('>') # the HTML 5 spec, section 8.1.2.2, doesn't allow spaces between # ') class HTMLParseError(Exception): """Exception raised for all parse errors.""" def __init__(self, msg, position=(None, None)): assert msg self.msg = msg self.lineno = position[0] self.offset = position[1] def __str__(self): result = self.msg if self.lineno is not None: result = result + ", at line %d" % self.lineno if self.offset is not None: result = result + ", column %d" % (self.offset + 1) return result class HTMLParser(_markupbase.ParserBase): """Find tags and other markup and call handler functions. Usage: p = HTMLParser() p.feed(data) ... p.close() Start tags are handled by calling self.handle_starttag() or self.handle_startendtag(); end tags by self.handle_endtag(). The data between tags is passed from the parser to the derived class by calling self.handle_data() with the data as argument (the data may be split up in arbitrary chunks). Entity references are passed by calling self.handle_entityref() with the entity reference as the argument. Numeric character references are passed to self.handle_charref() with the string containing the reference as the argument. """ CDATA_CONTENT_ELEMENTS = ("script", "style") def __init__(self, strict=False): """Initialize and reset this instance. If strict is set to False (the default) the parser will parse invalid markup, otherwise it will raise an error. Note that the strict mode is deprecated. """ if strict: warnings.warn("The strict mode is deprecated.", DeprecationWarning, stacklevel=2) self.strict = strict self.reset() def reset(self): """Reset this instance. Loses all unprocessed data.""" self.rawdata = '' self.lasttag = '???' self.interesting = interesting_normal self.cdata_elem = None _markupbase.ParserBase.reset(self) def feed(self, data): r"""Feed data to the parser. Call this as often as you want, with as little or as much text as you want (may include '\n'). """ self.rawdata = self.rawdata + data self.goahead(0) def close(self): """Handle any buffered data.""" self.goahead(1) def error(self, message): raise HTMLParseError(message, self.getpos()) __starttag_text = None def get_starttag_text(self): """Return full source of start tag: '<...>'.""" return self.__starttag_text def set_cdata_mode(self, elem): self.cdata_elem = elem.lower() self.interesting = re.compile(r'' % self.cdata_elem, re.I) def clear_cdata_mode(self): self.interesting = interesting_normal self.cdata_elem = None # Internal -- handle data as far as reasonable. May leave state # and data to be processed by a subsequent call. If 'end' is # true, force handling all data as if followed by EOF marker. def goahead(self, end): rawdata = self.rawdata i = 0 n = len(rawdata) while i < n: match = self.interesting.search(rawdata, i) # < or & if match: j = match.start() else: if self.cdata_elem: break j = n if i < j: self.handle_data(rawdata[i:j]) i = self.updatepos(i, j) if i == n: break startswith = rawdata.startswith if startswith('<', i): if starttagopen.match(rawdata, i): # < + letter k = self.parse_starttag(i) elif startswith("', i + 1) if k < 0: k = rawdata.find('<', i + 1) if k < 0: k = i + 1 else: k += 1 self.handle_data(rawdata[i:k]) i = self.updatepos(i, k) elif startswith("&#", i): match = charref.match(rawdata, i) if match: name = match.group()[2:-1] self.handle_charref(name) k = match.end() if not startswith(';', k-1): k = k - 1 i = self.updatepos(i, k) continue else: if ";" in rawdata[i:]: #bail by consuming &# self.handle_data(rawdata[0:2]) i = self.updatepos(i, 2) break elif startswith('&', i): match = entityref.match(rawdata, i) if match: name = match.group(1) self.handle_entityref(name) k = match.end() if not startswith(';', k-1): k = k - 1 i = self.updatepos(i, k) continue match = incomplete.match(rawdata, i) if match: # match.group() will contain at least 2 chars if end and match.group() == rawdata[i:]: if self.strict: self.error("EOF in middle of entity or char ref") else: if k <= i: k = n i = self.updatepos(i, i + 1) # incomplete break elif (i + 1) < n: # not the end of the buffer, and can't be confused # with some other construct self.handle_data("&") i = self.updatepos(i, i + 1) else: break else: assert 0, "interesting.search() lied" # end while if end and i < n and not self.cdata_elem: self.handle_data(rawdata[i:n]) i = self.updatepos(i, n) self.rawdata = rawdata[i:] # Internal -- parse html declarations, return length or -1 if not terminated # See w3.org/TR/html5/tokenization.html#markup-declaration-open-state # See also parse_declaration in _markupbase def parse_html_declaration(self, i): rawdata = self.rawdata assert rawdata[i:i+2] == ' gtpos = rawdata.find('>', i+9) if gtpos == -1: return -1 self.handle_decl(rawdata[i+2:gtpos]) return gtpos+1 else: return self.parse_bogus_comment(i) # Internal -- parse bogus comment, return length or -1 if not terminated # see http://www.w3.org/TR/html5/tokenization.html#bogus-comment-state def parse_bogus_comment(self, i, report=1): rawdata = self.rawdata assert rawdata[i:i+2] in ('', i+2) if pos == -1: return -1 if report: self.handle_comment(rawdata[i+2:pos]) return pos + 1 # Internal -- parse processing instr, return end or -1 if not terminated def parse_pi(self, i): rawdata = self.rawdata assert rawdata[i:i+2] == ' if not match: return -1 j = match.start() self.handle_pi(rawdata[i+2: j]) j = match.end() return j # Internal -- handle starttag, return end or -1 if not terminated def parse_starttag(self, i): self.__starttag_text = None endpos = self.check_for_whole_start_tag(i) if endpos < 0: return endpos rawdata = self.rawdata self.__starttag_text = rawdata[i:endpos] # Now parse the data between i+1 and j into a tag and attrs attrs = [] match = tagfind.match(rawdata, i+1) assert match, 'unexpected call to parse_starttag()' k = match.end() self.lasttag = tag = match.group(1).lower() while k < endpos: if self.strict: m = attrfind.match(rawdata, k) else: m = attrfind_tolerant.match(rawdata, k) if not m: break attrname, rest, attrvalue = m.group(1, 2, 3) if not rest: attrvalue = None elif attrvalue[:1] == '\'' == attrvalue[-1:] or \ attrvalue[:1] == '"' == attrvalue[-1:]: attrvalue = attrvalue[1:-1] if attrvalue: attrvalue = self.unescape(attrvalue) attrs.append((attrname.lower(), attrvalue)) k = m.end() end = rawdata[k:endpos].strip() if end not in (">", "/>"): lineno, offset = self.getpos() if "\n" in self.__starttag_text: lineno = lineno + self.__starttag_text.count("\n") offset = len(self.__starttag_text) \ - self.__starttag_text.rfind("\n") else: offset = offset + len(self.__starttag_text) if self.strict: self.error("junk characters in start tag: %r" % (rawdata[k:endpos][:20],)) self.handle_data(rawdata[i:endpos]) return endpos if end.endswith('/>'): # XHTML-style empty tag: self.handle_startendtag(tag, attrs) else: self.handle_starttag(tag, attrs) if tag in self.CDATA_CONTENT_ELEMENTS: self.set_cdata_mode(tag) return endpos # Internal -- check to see if we have a complete starttag; return end # or -1 if incomplete. def check_for_whole_start_tag(self, i): rawdata = self.rawdata if self.strict: m = locatestarttagend.match(rawdata, i) else: m = locatestarttagend_tolerant.match(rawdata, i) if m: j = m.end() next = rawdata[j:j+1] if next == ">": return j + 1 if next == "/": if rawdata.startswith("/>", j): return j + 2 if rawdata.startswith("/", j): # buffer boundary return -1 # else bogus input if self.strict: self.updatepos(i, j + 1) self.error("malformed empty start tag") if j > i: return j else: return i + 1 if next == "": # end of input return -1 if next in ("abcdefghijklmnopqrstuvwxyz=/" "ABCDEFGHIJKLMNOPQRSTUVWXYZ"): # end of input in or before attribute value, or we have the # '/' from a '/>' ending return -1 if self.strict: self.updatepos(i, j) self.error("malformed start tag") if j > i: return j else: return i + 1 raise AssertionError("we should not get here!") # Internal -- parse endtag, return end or -1 if incomplete def parse_endtag(self, i): rawdata = self.rawdata assert rawdata[i:i+2] == " if not match: return -1 gtpos = match.end() match = endtagfind.match(rawdata, i) # if not match: if self.cdata_elem is not None: self.handle_data(rawdata[i:gtpos]) return gtpos if self.strict: self.error("bad end tag: %r" % (rawdata[i:gtpos],)) # find the name: w3.org/TR/html5/tokenization.html#tag-name-state namematch = tagfind_tolerant.match(rawdata, i+2) if not namematch: # w3.org/TR/html5/tokenization.html#end-tag-open-state if rawdata[i:i+3] == '': return i+3 else: return self.parse_bogus_comment(i) tagname = namematch.group().lower() # consume and ignore other stuff between the name and the > # Note: this is not 100% correct, since we might have things like # , but looking for > after tha name should cover # most of the cases and is much simpler gtpos = rawdata.find('>', namematch.end()) self.handle_endtag(tagname) return gtpos+1 elem = match.group(1).lower() # script or style if self.cdata_elem is not None: if elem != self.cdata_elem: self.handle_data(rawdata[i:gtpos]) return gtpos self.handle_endtag(elem.lower()) self.clear_cdata_mode() return gtpos # Overridable -- finish processing of start+end tag: def handle_startendtag(self, tag, attrs): self.handle_starttag(tag, attrs) self.handle_endtag(tag) # Overridable -- handle start tag def handle_starttag(self, tag, attrs): pass # Overridable -- handle end tag def handle_endtag(self, tag): pass # Overridable -- handle character reference def handle_charref(self, name): pass # Overridable -- handle entity reference def handle_entityref(self, name): pass # Overridable -- handle data def handle_data(self, data): pass # Overridable -- handle comment def handle_comment(self, data): pass # Overridable -- handle declaration def handle_decl(self, decl): pass # Overridable -- handle processing instruction def handle_pi(self, data): pass def unknown_decl(self, data): if self.strict: self.error("unknown declaration: %r" % (data,)) # Internal -- helper to remove special character quoting def unescape(self, s): if '&' not in s: return s def replaceEntities(s): s = s.groups()[0] try: if s[0] == "#": s = s[1:] if s[0] in ['x','X']: c = int(s[1:].rstrip(';'), 16) else: c = int(s.rstrip(';')) return chr(c) except ValueError: return '&#' + s else: from future.backports.html.entities import html5 if s in html5: return html5[s] elif s.endswith(';'): return '&' + s for x in range(2, len(s)): if s[:x] in html5: return html5[s[:x]] + s[x:] else: return '&' + s return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+;|\w{1,32};?))", replaceEntities, s) """HTTP/1.1 client library A backport of the Python 3.3 http/client.py module for python-future. HTTPConnection goes through a number of "states", which define when a client may legally make another request or fetch the response for a particular request. This diagram details these state transitions: (null) | | HTTPConnection() v Idle | | putrequest() v Request-started | | ( putheader() )* endheaders() v Request-sent | | response = getresponse() v Unread-response [Response-headers-read] |\____________________ | | | response.read() | putrequest() v v Idle Req-started-unread-response ______/| / | response.read() | | ( putheader() )* endheaders() v v Request-started Req-sent-unread-response | | response.read() v Request-sent This diagram presents the following rules: -- a second request may not be started until {response-headers-read} -- a response [object] cannot be retrieved until {request-sent} -- there is no differentiation between an unread response body and a partially read response body Note: this enforcement is applied by the HTTPConnection class. The HTTPResponse class does not enforce this state machine, which implies sophisticated clients may accelerate the request/response pipeline. Caution should be taken, though: accelerating the states beyond the above pattern may imply knowledge of the server's connection-close behavior for certain requests. For example, it is impossible to tell whether the server will close the connection UNTIL the response headers have been read; this means that further requests cannot be placed into the pipeline until it is known that the server will NOT be closing the connection. Logical State __state __response ------------- ------- ---------- Idle _CS_IDLE None Request-started _CS_REQ_STARTED None Request-sent _CS_REQ_SENT None Unread-response _CS_IDLE Req-started-unread-response _CS_REQ_STARTED Req-sent-unread-response _CS_REQ_SENT """ from __future__ import (absolute_import, division, print_function, unicode_literals) from future.builtins import bytes, int, str, super from future.utils import PY2 from future.backports.email import parser as email_parser from future.backports.email import message as email_message from future.backports.misc import create_connection as socket_create_connection import io import os import socket import collections from future.backports.urllib.parse import urlsplit import warnings from array import array __all__ = ["HTTPResponse", "HTTPConnection", "HTTPException", "NotConnected", "UnknownProtocol", "UnknownTransferEncoding", "UnimplementedFileMode", "IncompleteRead", "InvalidURL", "ImproperConnectionState", "CannotSendRequest", "CannotSendHeader", "ResponseNotReady", "BadStatusLine", "error", "responses"] HTTP_PORT = 80 HTTPS_PORT = 443 _UNKNOWN = 'UNKNOWN' # connection states _CS_IDLE = 'Idle' _CS_REQ_STARTED = 'Request-started' _CS_REQ_SENT = 'Request-sent' # status codes # informational CONTINUE = 100 SWITCHING_PROTOCOLS = 101 PROCESSING = 102 # successful OK = 200 CREATED = 201 ACCEPTED = 202 NON_AUTHORITATIVE_INFORMATION = 203 NO_CONTENT = 204 RESET_CONTENT = 205 PARTIAL_CONTENT = 206 MULTI_STATUS = 207 IM_USED = 226 # redirection MULTIPLE_CHOICES = 300 MOVED_PERMANENTLY = 301 FOUND = 302 SEE_OTHER = 303 NOT_MODIFIED = 304 USE_PROXY = 305 TEMPORARY_REDIRECT = 307 # client error BAD_REQUEST = 400 UNAUTHORIZED = 401 PAYMENT_REQUIRED = 402 FORBIDDEN = 403 NOT_FOUND = 404 METHOD_NOT_ALLOWED = 405 NOT_ACCEPTABLE = 406 PROXY_AUTHENTICATION_REQUIRED = 407 REQUEST_TIMEOUT = 408 CONFLICT = 409 GONE = 410 LENGTH_REQUIRED = 411 PRECONDITION_FAILED = 412 REQUEST_ENTITY_TOO_LARGE = 413 REQUEST_URI_TOO_LONG = 414 UNSUPPORTED_MEDIA_TYPE = 415 REQUESTED_RANGE_NOT_SATISFIABLE = 416 EXPECTATION_FAILED = 417 UNPROCESSABLE_ENTITY = 422 LOCKED = 423 FAILED_DEPENDENCY = 424 UPGRADE_REQUIRED = 426 PRECONDITION_REQUIRED = 428 TOO_MANY_REQUESTS = 429 REQUEST_HEADER_FIELDS_TOO_LARGE = 431 # server error INTERNAL_SERVER_ERROR = 500 NOT_IMPLEMENTED = 501 BAD_GATEWAY = 502 SERVICE_UNAVAILABLE = 503 GATEWAY_TIMEOUT = 504 HTTP_VERSION_NOT_SUPPORTED = 505 INSUFFICIENT_STORAGE = 507 NOT_EXTENDED = 510 NETWORK_AUTHENTICATION_REQUIRED = 511 # Mapping status codes to official W3C names responses = { 100: 'Continue', 101: 'Switching Protocols', 200: 'OK', 201: 'Created', 202: 'Accepted', 203: 'Non-Authoritative Information', 204: 'No Content', 205: 'Reset Content', 206: 'Partial Content', 300: 'Multiple Choices', 301: 'Moved Permanently', 302: 'Found', 303: 'See Other', 304: 'Not Modified', 305: 'Use Proxy', 306: '(Unused)', 307: 'Temporary Redirect', 400: 'Bad Request', 401: 'Unauthorized', 402: 'Payment Required', 403: 'Forbidden', 404: 'Not Found', 405: 'Method Not Allowed', 406: 'Not Acceptable', 407: 'Proxy Authentication Required', 408: 'Request Timeout', 409: 'Conflict', 410: 'Gone', 411: 'Length Required', 412: 'Precondition Failed', 413: 'Request Entity Too Large', 414: 'Request-URI Too Long', 415: 'Unsupported Media Type', 416: 'Requested Range Not Satisfiable', 417: 'Expectation Failed', 428: 'Precondition Required', 429: 'Too Many Requests', 431: 'Request Header Fields Too Large', 500: 'Internal Server Error', 501: 'Not Implemented', 502: 'Bad Gateway', 503: 'Service Unavailable', 504: 'Gateway Timeout', 505: 'HTTP Version Not Supported', 511: 'Network Authentication Required', } # maximal amount of data to read at one time in _safe_read MAXAMOUNT = 1048576 # maximal line length when calling readline(). _MAXLINE = 65536 _MAXHEADERS = 100 class HTTPMessage(email_message.Message): # XXX The only usage of this method is in # http.server.CGIHTTPRequestHandler. Maybe move the code there so # that it doesn't need to be part of the public API. The API has # never been defined so this could cause backwards compatibility # issues. def getallmatchingheaders(self, name): """Find all header lines matching a given header name. Look through the list of headers and find all lines matching a given header name (and their continuation lines). A list of the lines is returned, without interpretation. If the header does not occur, an empty list is returned. If the header occurs multiple times, all occurrences are returned. Case is not important in the header name. """ name = name.lower() + ':' n = len(name) lst = [] hit = 0 for line in self.keys(): if line[:n].lower() == name: hit = 1 elif not line[:1].isspace(): hit = 0 if hit: lst.append(line) return lst def parse_headers(fp, _class=HTTPMessage): """Parses only RFC2822 headers from a file pointer. email Parser wants to see strings rather than bytes. But a TextIOWrapper around self.rfile would buffer too many bytes from the stream, bytes which we later need to read as bytes. So we read the correct bytes here, as bytes, for email Parser to parse. """ headers = [] while True: line = fp.readline(_MAXLINE + 1) if len(line) > _MAXLINE: raise LineTooLong("header line") headers.append(line) if len(headers) > _MAXHEADERS: raise HTTPException("got more than %d headers" % _MAXHEADERS) if line in (b'\r\n', b'\n', b''): break hstring = bytes(b'').join(headers).decode('iso-8859-1') return email_parser.Parser(_class=_class).parsestr(hstring) _strict_sentinel = object() class HTTPResponse(io.RawIOBase): # See RFC 2616 sec 19.6 and RFC 1945 sec 6 for details. # The bytes from the socket object are iso-8859-1 strings. # See RFC 2616 sec 2.2 which notes an exception for MIME-encoded # text following RFC 2047. The basic status line parsing only # accepts iso-8859-1. def __init__(self, sock, debuglevel=0, strict=_strict_sentinel, method=None, url=None): # If the response includes a content-length header, we need to # make sure that the client doesn't read more than the # specified number of bytes. If it does, it will block until # the server times out and closes the connection. This will # happen if a self.fp.read() is done (without a size) whether # self.fp is buffered or not. So, no self.fp.read() by # clients unless they know what they are doing. self.fp = sock.makefile("rb") self.debuglevel = debuglevel if strict is not _strict_sentinel: warnings.warn("the 'strict' argument isn't supported anymore; " "http.client now always assumes HTTP/1.x compliant servers.", DeprecationWarning, 2) self._method = method # The HTTPResponse object is returned via urllib. The clients # of http and urllib expect different attributes for the # headers. headers is used here and supports urllib. msg is # provided as a backwards compatibility layer for http # clients. self.headers = self.msg = None # from the Status-Line of the response self.version = _UNKNOWN # HTTP-Version self.status = _UNKNOWN # Status-Code self.reason = _UNKNOWN # Reason-Phrase self.chunked = _UNKNOWN # is "chunked" being used? self.chunk_left = _UNKNOWN # bytes left to read in current chunk self.length = _UNKNOWN # number of bytes left in response self.will_close = _UNKNOWN # conn will close at end of response def _read_status(self): line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1") if len(line) > _MAXLINE: raise LineTooLong("status line") if self.debuglevel > 0: print("reply:", repr(line)) if not line: # Presumably, the server closed the connection before # sending a valid response. raise BadStatusLine(line) try: version, status, reason = line.split(None, 2) except ValueError: try: version, status = line.split(None, 1) reason = "" except ValueError: # empty version will cause next test to fail. version = "" if not version.startswith("HTTP/"): self._close_conn() raise BadStatusLine(line) # The status code is a three-digit number try: status = int(status) if status < 100 or status > 999: raise BadStatusLine(line) except ValueError: raise BadStatusLine(line) return version, status, reason def begin(self): if self.headers is not None: # we've already started reading the response return # read until we get a non-100 response while True: version, status, reason = self._read_status() if status != CONTINUE: break # skip the header from the 100 response while True: skip = self.fp.readline(_MAXLINE + 1) if len(skip) > _MAXLINE: raise LineTooLong("header line") skip = skip.strip() if not skip: break if self.debuglevel > 0: print("header:", skip) self.code = self.status = status self.reason = reason.strip() if version in ("HTTP/1.0", "HTTP/0.9"): # Some servers might still return "0.9", treat it as 1.0 anyway self.version = 10 elif version.startswith("HTTP/1."): self.version = 11 # use HTTP/1.1 code for HTTP/1.x where x>=1 else: raise UnknownProtocol(version) self.headers = self.msg = parse_headers(self.fp) if self.debuglevel > 0: for hdr in self.headers: print("header:", hdr, end=" ") # are we using the chunked-style of transfer encoding? tr_enc = self.headers.get("transfer-encoding") if tr_enc and tr_enc.lower() == "chunked": self.chunked = True self.chunk_left = None else: self.chunked = False # will the connection close at the end of the response? self.will_close = self._check_close() # do we have a Content-Length? # NOTE: RFC 2616, S4.4, #3 says we ignore this if tr_enc is "chunked" self.length = None length = self.headers.get("content-length") # are we using the chunked-style of transfer encoding? tr_enc = self.headers.get("transfer-encoding") if length and not self.chunked: try: self.length = int(length) except ValueError: self.length = None else: if self.length < 0: # ignore nonsensical negative lengths self.length = None else: self.length = None # does the body have a fixed length? (of zero) if (status == NO_CONTENT or status == NOT_MODIFIED or 100 <= status < 200 or # 1xx codes self._method == "HEAD"): self.length = 0 # if the connection remains open, and we aren't using chunked, and # a content-length was not provided, then assume that the connection # WILL close. if (not self.will_close and not self.chunked and self.length is None): self.will_close = True def _check_close(self): conn = self.headers.get("connection") if self.version == 11: # An HTTP/1.1 proxy is assumed to stay open unless # explicitly closed. conn = self.headers.get("connection") if conn and "close" in conn.lower(): return True return False # Some HTTP/1.0 implementations have support for persistent # connections, using rules different than HTTP/1.1. # For older HTTP, Keep-Alive indicates persistent connection. if self.headers.get("keep-alive"): return False # At least Akamai returns a "Connection: Keep-Alive" header, # which was supposed to be sent by the client. if conn and "keep-alive" in conn.lower(): return False # Proxy-Connection is a netscape hack. pconn = self.headers.get("proxy-connection") if pconn and "keep-alive" in pconn.lower(): return False # otherwise, assume it will close return True def _close_conn(self): fp = self.fp self.fp = None fp.close() def close(self): super().close() # set "closed" flag if self.fp: self._close_conn() # These implementations are for the benefit of io.BufferedReader. # XXX This class should probably be revised to act more like # the "raw stream" that BufferedReader expects. def flush(self): super().flush() if self.fp: self.fp.flush() def readable(self): return True # End of "raw stream" methods def isclosed(self): """True if the connection is closed.""" # NOTE: it is possible that we will not ever call self.close(). This # case occurs when will_close is TRUE, length is None, and we # read up to the last byte, but NOT past it. # # IMPLIES: if will_close is FALSE, then self.close() will ALWAYS be # called, meaning self.isclosed() is meaningful. return self.fp is None def read(self, amt=None): if self.fp is None: return bytes(b"") if self._method == "HEAD": self._close_conn() return bytes(b"") if amt is not None: # Amount is given, so call base class version # (which is implemented in terms of self.readinto) return bytes(super(HTTPResponse, self).read(amt)) else: # Amount is not given (unbounded read) so we must check self.length # and self.chunked if self.chunked: return self._readall_chunked() if self.length is None: s = self.fp.read() else: try: s = self._safe_read(self.length) except IncompleteRead: self._close_conn() raise self.length = 0 self._close_conn() # we read everything return bytes(s) def readinto(self, b): if self.fp is None: return 0 if self._method == "HEAD": self._close_conn() return 0 if self.chunked: return self._readinto_chunked(b) if self.length is not None: if len(b) > self.length: # clip the read to the "end of response" b = memoryview(b)[0:self.length] # we do not use _safe_read() here because this may be a .will_close # connection, and the user is reading more bytes than will be provided # (for example, reading in 1k chunks) if PY2: data = self.fp.read(len(b)) n = len(data) b[:n] = data else: n = self.fp.readinto(b) if not n and b: # Ideally, we would raise IncompleteRead if the content-length # wasn't satisfied, but it might break compatibility. self._close_conn() elif self.length is not None: self.length -= n if not self.length: self._close_conn() return n def _read_next_chunk_size(self): # Read the next chunk size from the file line = self.fp.readline(_MAXLINE + 1) if len(line) > _MAXLINE: raise LineTooLong("chunk size") i = line.find(b";") if i >= 0: line = line[:i] # strip chunk-extensions try: return int(line, 16) except ValueError: # close the connection as protocol synchronisation is # probably lost self._close_conn() raise def _read_and_discard_trailer(self): # read and discard trailer up to the CRLF terminator ### note: we shouldn't have any trailers! while True: line = self.fp.readline(_MAXLINE + 1) if len(line) > _MAXLINE: raise LineTooLong("trailer line") if not line: # a vanishingly small number of sites EOF without # sending the trailer break if line in (b'\r\n', b'\n', b''): break def _readall_chunked(self): assert self.chunked != _UNKNOWN chunk_left = self.chunk_left value = [] while True: if chunk_left is None: try: chunk_left = self._read_next_chunk_size() if chunk_left == 0: break except ValueError: raise IncompleteRead(bytes(b'').join(value)) value.append(self._safe_read(chunk_left)) # we read the whole chunk, get another self._safe_read(2) # toss the CRLF at the end of the chunk chunk_left = None self._read_and_discard_trailer() # we read everything; close the "file" self._close_conn() return bytes(b'').join(value) def _readinto_chunked(self, b): assert self.chunked != _UNKNOWN chunk_left = self.chunk_left total_bytes = 0 mvb = memoryview(b) while True: if chunk_left is None: try: chunk_left = self._read_next_chunk_size() if chunk_left == 0: break except ValueError: raise IncompleteRead(bytes(b[0:total_bytes])) if len(mvb) < chunk_left: n = self._safe_readinto(mvb) self.chunk_left = chunk_left - n return total_bytes + n elif len(mvb) == chunk_left: n = self._safe_readinto(mvb) self._safe_read(2) # toss the CRLF at the end of the chunk self.chunk_left = None return total_bytes + n else: temp_mvb = mvb[0:chunk_left] n = self._safe_readinto(temp_mvb) mvb = mvb[n:] total_bytes += n # we read the whole chunk, get another self._safe_read(2) # toss the CRLF at the end of the chunk chunk_left = None self._read_and_discard_trailer() # we read everything; close the "file" self._close_conn() return total_bytes def _safe_read(self, amt): """Read the number of bytes requested, compensating for partial reads. Normally, we have a blocking socket, but a read() can be interrupted by a signal (resulting in a partial read). Note that we cannot distinguish between EOF and an interrupt when zero bytes have been read. IncompleteRead() will be raised in this situation. This function should be used when bytes "should" be present for reading. If the bytes are truly not available (due to EOF), then the IncompleteRead exception can be used to detect the problem. """ s = [] while amt > 0: chunk = self.fp.read(min(amt, MAXAMOUNT)) if not chunk: raise IncompleteRead(bytes(b'').join(s), amt) s.append(chunk) amt -= len(chunk) return bytes(b"").join(s) def _safe_readinto(self, b): """Same as _safe_read, but for reading into a buffer.""" total_bytes = 0 mvb = memoryview(b) while total_bytes < len(b): if MAXAMOUNT < len(mvb): temp_mvb = mvb[0:MAXAMOUNT] n = self.fp.readinto(temp_mvb) else: n = self.fp.readinto(mvb) if not n: raise IncompleteRead(bytes(mvb[0:total_bytes]), len(b)) mvb = mvb[n:] total_bytes += n return total_bytes def fileno(self): return self.fp.fileno() def getheader(self, name, default=None): if self.headers is None: raise ResponseNotReady() headers = self.headers.get_all(name) or default if isinstance(headers, str) or not hasattr(headers, '__iter__'): return headers else: return ', '.join(headers) def getheaders(self): """Return list of (header, value) tuples.""" if self.headers is None: raise ResponseNotReady() return list(self.headers.items()) # We override IOBase.__iter__ so that it doesn't check for closed-ness def __iter__(self): return self # For compatibility with old-style urllib responses. def info(self): return self.headers def geturl(self): return self.url def getcode(self): return self.status class HTTPConnection(object): _http_vsn = 11 _http_vsn_str = 'HTTP/1.1' response_class = HTTPResponse default_port = HTTP_PORT auto_open = 1 debuglevel = 0 def __init__(self, host, port=None, strict=_strict_sentinel, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None): if strict is not _strict_sentinel: warnings.warn("the 'strict' argument isn't supported anymore; " "http.client now always assumes HTTP/1.x compliant servers.", DeprecationWarning, 2) self.timeout = timeout self.source_address = source_address self.sock = None self._buffer = [] self.__response = None self.__state = _CS_IDLE self._method = None self._tunnel_host = None self._tunnel_port = None self._tunnel_headers = {} self._set_hostport(host, port) def set_tunnel(self, host, port=None, headers=None): """ Sets up the host and the port for the HTTP CONNECT Tunnelling. The headers argument should be a mapping of extra HTTP headers to send with the CONNECT request. """ self._tunnel_host = host self._tunnel_port = port if headers: self._tunnel_headers = headers else: self._tunnel_headers.clear() def _set_hostport(self, host, port): if port is None: i = host.rfind(':') j = host.rfind(']') # ipv6 addresses have [...] if i > j: try: port = int(host[i+1:]) except ValueError: if host[i+1:] == "": # http://foo.com:/ == http://foo.com/ port = self.default_port else: raise InvalidURL("nonnumeric port: '%s'" % host[i+1:]) host = host[:i] else: port = self.default_port if host and host[0] == '[' and host[-1] == ']': host = host[1:-1] self.host = host self.port = port def set_debuglevel(self, level): self.debuglevel = level def _tunnel(self): self._set_hostport(self._tunnel_host, self._tunnel_port) connect_str = "CONNECT %s:%d HTTP/1.0\r\n" % (self.host, self.port) connect_bytes = connect_str.encode("ascii") self.send(connect_bytes) for header, value in self._tunnel_headers.items(): header_str = "%s: %s\r\n" % (header, value) header_bytes = header_str.encode("latin-1") self.send(header_bytes) self.send(bytes(b'\r\n')) response = self.response_class(self.sock, method=self._method) (version, code, message) = response._read_status() if code != 200: self.close() raise socket.error("Tunnel connection failed: %d %s" % (code, message.strip())) while True: line = response.fp.readline(_MAXLINE + 1) if len(line) > _MAXLINE: raise LineTooLong("header line") if not line: # for sites which EOF without sending a trailer break if line in (b'\r\n', b'\n', b''): break def connect(self): """Connect to the host and port specified in __init__.""" self.sock = socket_create_connection((self.host,self.port), self.timeout, self.source_address) if self._tunnel_host: self._tunnel() def close(self): """Close the connection to the HTTP server.""" if self.sock: self.sock.close() # close it manually... there may be other refs self.sock = None if self.__response: self.__response.close() self.__response = None self.__state = _CS_IDLE def send(self, data): """Send `data' to the server. ``data`` can be a string object, a bytes object, an array object, a file-like object that supports a .read() method, or an iterable object. """ if self.sock is None: if self.auto_open: self.connect() else: raise NotConnected() if self.debuglevel > 0: print("send:", repr(data)) blocksize = 8192 # Python 2.7 array objects have a read method which is incompatible # with the 2-arg calling syntax below. if hasattr(data, "read") and not isinstance(data, array): if self.debuglevel > 0: print("sendIng a read()able") encode = False try: mode = data.mode except AttributeError: # io.BytesIO and other file-like objects don't have a `mode` # attribute. pass else: if "b" not in mode: encode = True if self.debuglevel > 0: print("encoding file using iso-8859-1") while 1: datablock = data.read(blocksize) if not datablock: break if encode: datablock = datablock.encode("iso-8859-1") self.sock.sendall(datablock) return try: self.sock.sendall(data) except TypeError: if isinstance(data, collections.Iterable): for d in data: self.sock.sendall(d) else: raise TypeError("data should be a bytes-like object " "or an iterable, got %r" % type(data)) def _output(self, s): """Add a line of output to the current request buffer. Assumes that the line does *not* end with \\r\\n. """ self._buffer.append(s) def _send_output(self, message_body=None): """Send the currently buffered request and clear the buffer. Appends an extra \\r\\n to the buffer. A message_body may be specified, to be appended to the request. """ self._buffer.extend((bytes(b""), bytes(b""))) msg = bytes(b"\r\n").join(self._buffer) del self._buffer[:] # If msg and message_body are sent in a single send() call, # it will avoid performance problems caused by the interaction # between delayed ack and the Nagle algorithm. if isinstance(message_body, bytes): msg += message_body message_body = None self.send(msg) if message_body is not None: # message_body was not a string (i.e. it is a file), and # we must run the risk of Nagle. self.send(message_body) def putrequest(self, method, url, skip_host=0, skip_accept_encoding=0): """Send a request to the server. `method' specifies an HTTP request method, e.g. 'GET'. `url' specifies the object being requested, e.g. '/index.html'. `skip_host' if True does not add automatically a 'Host:' header `skip_accept_encoding' if True does not add automatically an 'Accept-Encoding:' header """ # if a prior response has been completed, then forget about it. if self.__response and self.__response.isclosed(): self.__response = None # in certain cases, we cannot issue another request on this connection. # this occurs when: # 1) we are in the process of sending a request. (_CS_REQ_STARTED) # 2) a response to a previous request has signalled that it is going # to close the connection upon completion. # 3) the headers for the previous response have not been read, thus # we cannot determine whether point (2) is true. (_CS_REQ_SENT) # # if there is no prior response, then we can request at will. # # if point (2) is true, then we will have passed the socket to the # response (effectively meaning, "there is no prior response"), and # will open a new one when a new request is made. # # Note: if a prior response exists, then we *can* start a new request. # We are not allowed to begin fetching the response to this new # request, however, until that prior response is complete. # if self.__state == _CS_IDLE: self.__state = _CS_REQ_STARTED else: raise CannotSendRequest(self.__state) # Save the method we use, we need it later in the response phase self._method = method if not url: url = '/' request = '%s %s %s' % (method, url, self._http_vsn_str) # Non-ASCII characters should have been eliminated earlier self._output(request.encode('ascii')) if self._http_vsn == 11: # Issue some standard headers for better HTTP/1.1 compliance if not skip_host: # this header is issued *only* for HTTP/1.1 # connections. more specifically, this means it is # only issued when the client uses the new # HTTPConnection() class. backwards-compat clients # will be using HTTP/1.0 and those clients may be # issuing this header themselves. we should NOT issue # it twice; some web servers (such as Apache) barf # when they see two Host: headers # If we need a non-standard port,include it in the # header. If the request is going through a proxy, # but the host of the actual URL, not the host of the # proxy. netloc = '' if url.startswith('http'): nil, netloc, nil, nil, nil = urlsplit(url) if netloc: try: netloc_enc = netloc.encode("ascii") except UnicodeEncodeError: netloc_enc = netloc.encode("idna") self.putheader('Host', netloc_enc) else: try: host_enc = self.host.encode("ascii") except UnicodeEncodeError: host_enc = self.host.encode("idna") # As per RFC 273, IPv6 address should be wrapped with [] # when used as Host header if self.host.find(':') >= 0: host_enc = bytes(b'[' + host_enc + b']') if self.port == self.default_port: self.putheader('Host', host_enc) else: host_enc = host_enc.decode("ascii") self.putheader('Host', "%s:%s" % (host_enc, self.port)) # note: we are assuming that clients will not attempt to set these # headers since *this* library must deal with the # consequences. this also means that when the supporting # libraries are updated to recognize other forms, then this # code should be changed (removed or updated). # we only want a Content-Encoding of "identity" since we don't # support encodings such as x-gzip or x-deflate. if not skip_accept_encoding: self.putheader('Accept-Encoding', 'identity') # we can accept "chunked" Transfer-Encodings, but no others # NOTE: no TE header implies *only* "chunked" #self.putheader('TE', 'chunked') # if TE is supplied in the header, then it must appear in a # Connection header. #self.putheader('Connection', 'TE') else: # For HTTP/1.0, the server will assume "not chunked" pass def putheader(self, header, *values): """Send a request header line to the server. For example: h.putheader('Accept', 'text/html') """ if self.__state != _CS_REQ_STARTED: raise CannotSendHeader() if hasattr(header, 'encode'): header = header.encode('ascii') values = list(values) for i, one_value in enumerate(values): if hasattr(one_value, 'encode'): values[i] = one_value.encode('latin-1') elif isinstance(one_value, int): values[i] = str(one_value).encode('ascii') value = bytes(b'\r\n\t').join(values) header = header + bytes(b': ') + value self._output(header) def endheaders(self, message_body=None): """Indicate that the last header line has been sent to the server. This method sends the request to the server. The optional message_body argument can be used to pass a message body associated with the request. The message body will be sent in the same packet as the message headers if it is a string, otherwise it is sent as a separate packet. """ if self.__state == _CS_REQ_STARTED: self.__state = _CS_REQ_SENT else: raise CannotSendHeader() self._send_output(message_body) def request(self, method, url, body=None, headers={}): """Send a complete request to the server.""" self._send_request(method, url, body, headers) def _set_content_length(self, body): # Set the content-length based on the body. thelen = None try: thelen = str(len(body)) except TypeError as te: # If this is a file-like object, try to # fstat its file descriptor try: thelen = str(os.fstat(body.fileno()).st_size) except (AttributeError, OSError): # Don't send a length if this failed if self.debuglevel > 0: print("Cannot stat!!") if thelen is not None: self.putheader('Content-Length', thelen) def _send_request(self, method, url, body, headers): # Honor explicitly requested Host: and Accept-Encoding: headers. header_names = dict.fromkeys([k.lower() for k in headers]) skips = {} if 'host' in header_names: skips['skip_host'] = 1 if 'accept-encoding' in header_names: skips['skip_accept_encoding'] = 1 self.putrequest(method, url, **skips) if body is not None and ('content-length' not in header_names): self._set_content_length(body) for hdr, value in headers.items(): self.putheader(hdr, value) if isinstance(body, str): # RFC 2616 Section 3.7.1 says that text default has a # default charset of iso-8859-1. body = body.encode('iso-8859-1') self.endheaders(body) def getresponse(self): """Get the response from the server. If the HTTPConnection is in the correct state, returns an instance of HTTPResponse or of whatever object is returned by class the response_class variable. If a request has not been sent or if a previous response has not be handled, ResponseNotReady is raised. If the HTTP response indicates that the connection should be closed, then it will be closed before the response is returned. When the connection is closed, the underlying socket is closed. """ # if a prior response has been completed, then forget about it. if self.__response and self.__response.isclosed(): self.__response = None # if a prior response exists, then it must be completed (otherwise, we # cannot read this response's header to determine the connection-close # behavior) # # note: if a prior response existed, but was connection-close, then the # socket and response were made independent of this HTTPConnection # object since a new request requires that we open a whole new # connection # # this means the prior response had one of two states: # 1) will_close: this connection was reset and the prior socket and # response operate independently # 2) persistent: the response was retained and we await its # isclosed() status to become true. # if self.__state != _CS_REQ_SENT or self.__response: raise ResponseNotReady(self.__state) if self.debuglevel > 0: response = self.response_class(self.sock, self.debuglevel, method=self._method) else: response = self.response_class(self.sock, method=self._method) response.begin() assert response.will_close != _UNKNOWN self.__state = _CS_IDLE if response.will_close: # this effectively passes the connection to the response self.close() else: # remember this, so we can tell when it is complete self.__response = response return response try: import ssl from ssl import SSLContext except ImportError: pass else: class HTTPSConnection(HTTPConnection): "This class allows communication via SSL." default_port = HTTPS_PORT # XXX Should key_file and cert_file be deprecated in favour of context? def __init__(self, host, port=None, key_file=None, cert_file=None, strict=_strict_sentinel, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None, **_3to2kwargs): if 'check_hostname' in _3to2kwargs: check_hostname = _3to2kwargs['check_hostname']; del _3to2kwargs['check_hostname'] else: check_hostname = None if 'context' in _3to2kwargs: context = _3to2kwargs['context']; del _3to2kwargs['context'] else: context = None super(HTTPSConnection, self).__init__(host, port, strict, timeout, source_address) self.key_file = key_file self.cert_file = cert_file if context is None: # Some reasonable defaults context = ssl.SSLContext(ssl.PROTOCOL_SSLv23) context.options |= ssl.OP_NO_SSLv2 will_verify = context.verify_mode != ssl.CERT_NONE if check_hostname is None: check_hostname = will_verify elif check_hostname and not will_verify: raise ValueError("check_hostname needs a SSL context with " "either CERT_OPTIONAL or CERT_REQUIRED") if key_file or cert_file: context.load_cert_chain(cert_file, key_file) self._context = context self._check_hostname = check_hostname def connect(self): "Connect to a host on a given (SSL) port." sock = socket_create_connection((self.host, self.port), self.timeout, self.source_address) if self._tunnel_host: self.sock = sock self._tunnel() server_hostname = self.host if ssl.HAS_SNI else None self.sock = self._context.wrap_socket(sock, server_hostname=server_hostname) try: if self._check_hostname: ssl.match_hostname(self.sock.getpeercert(), self.host) except Exception: self.sock.shutdown(socket.SHUT_RDWR) self.sock.close() raise __all__.append("HTTPSConnection") # ###################################### # # We use the old HTTPSConnection class from Py2.7, because ssl.SSLContext # # doesn't exist in the Py2.7 stdlib # class HTTPSConnection(HTTPConnection): # "This class allows communication via SSL." # default_port = HTTPS_PORT # def __init__(self, host, port=None, key_file=None, cert_file=None, # strict=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, # source_address=None): # HTTPConnection.__init__(self, host, port, strict, timeout, # source_address) # self.key_file = key_file # self.cert_file = cert_file # def connect(self): # "Connect to a host on a given (SSL) port." # sock = socket_create_connection((self.host, self.port), # self.timeout, self.source_address) # if self._tunnel_host: # self.sock = sock # self._tunnel() # self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file) # __all__.append("HTTPSConnection") # ###################################### class HTTPException(Exception): # Subclasses that define an __init__ must call Exception.__init__ # or define self.args. Otherwise, str() will fail. pass class NotConnected(HTTPException): pass class InvalidURL(HTTPException): pass class UnknownProtocol(HTTPException): def __init__(self, version): self.args = version, self.version = version class UnknownTransferEncoding(HTTPException): pass class UnimplementedFileMode(HTTPException): pass class IncompleteRead(HTTPException): def __init__(self, partial, expected=None): self.args = partial, self.partial = partial self.expected = expected def __repr__(self): if self.expected is not None: e = ', %i more expected' % self.expected else: e = '' return 'IncompleteRead(%i bytes read%s)' % (len(self.partial), e) def __str__(self): return repr(self) class ImproperConnectionState(HTTPException): pass class CannotSendRequest(ImproperConnectionState): pass class CannotSendHeader(ImproperConnectionState): pass class ResponseNotReady(ImproperConnectionState): pass class BadStatusLine(HTTPException): def __init__(self, line): if not line: line = repr(line) self.args = line, self.line = line class LineTooLong(HTTPException): def __init__(self, line_type): HTTPException.__init__(self, "got more than %d bytes when reading %s" % (_MAXLINE, line_type)) # for backwards compatibility error = HTTPException #### # Copyright 2000 by Timothy O'Malley # # All Rights Reserved # # Permission to use, copy, modify, and distribute this software # and its documentation for any purpose and without fee is hereby # granted, provided that the above copyright notice appear in all # copies and that both that copyright notice and this permission # notice appear in supporting documentation, and that the name of # Timothy O'Malley not be used in advertising or publicity # pertaining to distribution of the software without specific, written # prior permission. # # Timothy O'Malley DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS # SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY # AND FITNESS, IN NO EVENT SHALL Timothy O'Malley BE LIABLE FOR # ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES # WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, # WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS # ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR # PERFORMANCE OF THIS SOFTWARE. # #### # # Id: Cookie.py,v 2.29 2000/08/23 05:28:49 timo Exp # by Timothy O'Malley # # Cookie.py is a Python module for the handling of HTTP # cookies as a Python dictionary. See RFC 2109 for more # information on cookies. # # The original idea to treat Cookies as a dictionary came from # Dave Mitchell (davem@magnet.com) in 1995, when he released the # first version of nscookie.py. # #### r""" http.cookies module ported to python-future from Py3.3 Here's a sample session to show how to use this module. At the moment, this is the only documentation. The Basics ---------- Importing is easy... >>> from http import cookies Most of the time you start by creating a cookie. >>> C = cookies.SimpleCookie() Once you've created your Cookie, you can add values just as if it were a dictionary. >>> C = cookies.SimpleCookie() >>> C["fig"] = "newton" >>> C["sugar"] = "wafer" >>> C.output() 'Set-Cookie: fig=newton\r\nSet-Cookie: sugar=wafer' Notice that the printable representation of a Cookie is the appropriate format for a Set-Cookie: header. This is the default behavior. You can change the header and printed attributes by using the .output() function >>> C = cookies.SimpleCookie() >>> C["rocky"] = "road" >>> C["rocky"]["path"] = "/cookie" >>> print(C.output(header="Cookie:")) Cookie: rocky=road; Path=/cookie >>> print(C.output(attrs=[], header="Cookie:")) Cookie: rocky=road The load() method of a Cookie extracts cookies from a string. In a CGI script, you would use this method to extract the cookies from the HTTP_COOKIE environment variable. >>> C = cookies.SimpleCookie() >>> C.load("chips=ahoy; vienna=finger") >>> C.output() 'Set-Cookie: chips=ahoy\r\nSet-Cookie: vienna=finger' The load() method is darn-tootin smart about identifying cookies within a string. Escaped quotation marks, nested semicolons, and other such trickeries do not confuse it. >>> C = cookies.SimpleCookie() >>> C.load('keebler="E=everybody; L=\\"Loves\\"; fudge=\\012;";') >>> print(C) Set-Cookie: keebler="E=everybody; L=\"Loves\"; fudge=\012;" Each element of the Cookie also supports all of the RFC 2109 Cookie attributes. Here's an example which sets the Path attribute. >>> C = cookies.SimpleCookie() >>> C["oreo"] = "doublestuff" >>> C["oreo"]["path"] = "/" >>> print(C) Set-Cookie: oreo=doublestuff; Path=/ Each dictionary element has a 'value' attribute, which gives you back the value associated with the key. >>> C = cookies.SimpleCookie() >>> C["twix"] = "none for you" >>> C["twix"].value 'none for you' The SimpleCookie expects that all values should be standard strings. Just to be sure, SimpleCookie invokes the str() builtin to convert the value to a string, when the values are set dictionary-style. >>> C = cookies.SimpleCookie() >>> C["number"] = 7 >>> C["string"] = "seven" >>> C["number"].value '7' >>> C["string"].value 'seven' >>> C.output() 'Set-Cookie: number=7\r\nSet-Cookie: string=seven' Finis. """ from __future__ import unicode_literals from __future__ import print_function from __future__ import division from __future__ import absolute_import from future.builtins import chr, dict, int, str from future.utils import PY2, as_native_str # # Import our required modules # import re re.ASCII = 0 # for py2 compatibility import string __all__ = ["CookieError", "BaseCookie", "SimpleCookie"] _nulljoin = ''.join _semispacejoin = '; '.join _spacejoin = ' '.join # # Define an exception visible to External modules # class CookieError(Exception): pass # These quoting routines conform to the RFC2109 specification, which in # turn references the character definitions from RFC2068. They provide # a two-way quoting algorithm. Any non-text character is translated # into a 4 character sequence: a forward-slash followed by the # three-digit octal equivalent of the character. Any '\' or '"' is # quoted with a preceeding '\' slash. # # These are taken from RFC2068 and RFC2109. # _LegalChars is the list of chars which don't require "'s # _Translator hash-table for fast quoting # _LegalChars = string.ascii_letters + string.digits + "!#$%&'*+-.^_`|~:" _Translator = { '\000' : '\\000', '\001' : '\\001', '\002' : '\\002', '\003' : '\\003', '\004' : '\\004', '\005' : '\\005', '\006' : '\\006', '\007' : '\\007', '\010' : '\\010', '\011' : '\\011', '\012' : '\\012', '\013' : '\\013', '\014' : '\\014', '\015' : '\\015', '\016' : '\\016', '\017' : '\\017', '\020' : '\\020', '\021' : '\\021', '\022' : '\\022', '\023' : '\\023', '\024' : '\\024', '\025' : '\\025', '\026' : '\\026', '\027' : '\\027', '\030' : '\\030', '\031' : '\\031', '\032' : '\\032', '\033' : '\\033', '\034' : '\\034', '\035' : '\\035', '\036' : '\\036', '\037' : '\\037', # Because of the way browsers really handle cookies (as opposed # to what the RFC says) we also encode , and ; ',' : '\\054', ';' : '\\073', '"' : '\\"', '\\' : '\\\\', '\177' : '\\177', '\200' : '\\200', '\201' : '\\201', '\202' : '\\202', '\203' : '\\203', '\204' : '\\204', '\205' : '\\205', '\206' : '\\206', '\207' : '\\207', '\210' : '\\210', '\211' : '\\211', '\212' : '\\212', '\213' : '\\213', '\214' : '\\214', '\215' : '\\215', '\216' : '\\216', '\217' : '\\217', '\220' : '\\220', '\221' : '\\221', '\222' : '\\222', '\223' : '\\223', '\224' : '\\224', '\225' : '\\225', '\226' : '\\226', '\227' : '\\227', '\230' : '\\230', '\231' : '\\231', '\232' : '\\232', '\233' : '\\233', '\234' : '\\234', '\235' : '\\235', '\236' : '\\236', '\237' : '\\237', '\240' : '\\240', '\241' : '\\241', '\242' : '\\242', '\243' : '\\243', '\244' : '\\244', '\245' : '\\245', '\246' : '\\246', '\247' : '\\247', '\250' : '\\250', '\251' : '\\251', '\252' : '\\252', '\253' : '\\253', '\254' : '\\254', '\255' : '\\255', '\256' : '\\256', '\257' : '\\257', '\260' : '\\260', '\261' : '\\261', '\262' : '\\262', '\263' : '\\263', '\264' : '\\264', '\265' : '\\265', '\266' : '\\266', '\267' : '\\267', '\270' : '\\270', '\271' : '\\271', '\272' : '\\272', '\273' : '\\273', '\274' : '\\274', '\275' : '\\275', '\276' : '\\276', '\277' : '\\277', '\300' : '\\300', '\301' : '\\301', '\302' : '\\302', '\303' : '\\303', '\304' : '\\304', '\305' : '\\305', '\306' : '\\306', '\307' : '\\307', '\310' : '\\310', '\311' : '\\311', '\312' : '\\312', '\313' : '\\313', '\314' : '\\314', '\315' : '\\315', '\316' : '\\316', '\317' : '\\317', '\320' : '\\320', '\321' : '\\321', '\322' : '\\322', '\323' : '\\323', '\324' : '\\324', '\325' : '\\325', '\326' : '\\326', '\327' : '\\327', '\330' : '\\330', '\331' : '\\331', '\332' : '\\332', '\333' : '\\333', '\334' : '\\334', '\335' : '\\335', '\336' : '\\336', '\337' : '\\337', '\340' : '\\340', '\341' : '\\341', '\342' : '\\342', '\343' : '\\343', '\344' : '\\344', '\345' : '\\345', '\346' : '\\346', '\347' : '\\347', '\350' : '\\350', '\351' : '\\351', '\352' : '\\352', '\353' : '\\353', '\354' : '\\354', '\355' : '\\355', '\356' : '\\356', '\357' : '\\357', '\360' : '\\360', '\361' : '\\361', '\362' : '\\362', '\363' : '\\363', '\364' : '\\364', '\365' : '\\365', '\366' : '\\366', '\367' : '\\367', '\370' : '\\370', '\371' : '\\371', '\372' : '\\372', '\373' : '\\373', '\374' : '\\374', '\375' : '\\375', '\376' : '\\376', '\377' : '\\377' } def _quote(str, LegalChars=_LegalChars): r"""Quote a string for use in a cookie header. If the string does not need to be double-quoted, then just return the string. Otherwise, surround the string in doublequotes and quote (with a \) special characters. """ if all(c in LegalChars for c in str): return str else: return '"' + _nulljoin(_Translator.get(s, s) for s in str) + '"' _OctalPatt = re.compile(r"\\[0-3][0-7][0-7]") _QuotePatt = re.compile(r"[\\].") def _unquote(mystr): # If there aren't any doublequotes, # then there can't be any special characters. See RFC 2109. if len(mystr) < 2: return mystr if mystr[0] != '"' or mystr[-1] != '"': return mystr # We have to assume that we must decode this string. # Down to work. # Remove the "s mystr = mystr[1:-1] # Check for special sequences. Examples: # \012 --> \n # \" --> " # i = 0 n = len(mystr) res = [] while 0 <= i < n: o_match = _OctalPatt.search(mystr, i) q_match = _QuotePatt.search(mystr, i) if not o_match and not q_match: # Neither matched res.append(mystr[i:]) break # else: j = k = -1 if o_match: j = o_match.start(0) if q_match: k = q_match.start(0) if q_match and (not o_match or k < j): # QuotePatt matched res.append(mystr[i:k]) res.append(mystr[k+1]) i = k + 2 else: # OctalPatt matched res.append(mystr[i:j]) res.append(chr(int(mystr[j+1:j+4], 8))) i = j + 4 return _nulljoin(res) # The _getdate() routine is used to set the expiration time in the cookie's HTTP # header. By default, _getdate() returns the current time in the appropriate # "expires" format for a Set-Cookie header. The one optional argument is an # offset from now, in seconds. For example, an offset of -3600 means "one hour # ago". The offset may be a floating point number. # _weekdayname = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'] _monthname = [None, 'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'] def _getdate(future=0, weekdayname=_weekdayname, monthname=_monthname): from time import gmtime, time now = time() year, month, day, hh, mm, ss, wd, y, z = gmtime(now + future) return "%s, %02d %3s %4d %02d:%02d:%02d GMT" % \ (weekdayname[wd], day, monthname[month], year, hh, mm, ss) class Morsel(dict): """A class to hold ONE (key, value) pair. In a cookie, each such pair may have several attributes, so this class is used to keep the attributes associated with the appropriate key,value pair. This class also includes a coded_value attribute, which is used to hold the network representation of the value. This is most useful when Python objects are pickled for network transit. """ # RFC 2109 lists these attributes as reserved: # path comment domain # max-age secure version # # For historical reasons, these attributes are also reserved: # expires # # This is an extension from Microsoft: # httponly # # This dictionary provides a mapping from the lowercase # variant on the left to the appropriate traditional # formatting on the right. _reserved = { "expires" : "expires", "path" : "Path", "comment" : "Comment", "domain" : "Domain", "max-age" : "Max-Age", "secure" : "secure", "httponly" : "httponly", "version" : "Version", } _flags = set(['secure', 'httponly']) def __init__(self): # Set defaults self.key = self.value = self.coded_value = None # Set default attributes for key in self._reserved: dict.__setitem__(self, key, "") def __setitem__(self, K, V): K = K.lower() if not K in self._reserved: raise CookieError("Invalid Attribute %s" % K) dict.__setitem__(self, K, V) def isReservedKey(self, K): return K.lower() in self._reserved def set(self, key, val, coded_val, LegalChars=_LegalChars): # First we verify that the key isn't a reserved word # Second we make sure it only contains legal characters if key.lower() in self._reserved: raise CookieError("Attempt to set a reserved key: %s" % key) if any(c not in LegalChars for c in key): raise CookieError("Illegal key value: %s" % key) # It's a good key, so save it. self.key = key self.value = val self.coded_value = coded_val def output(self, attrs=None, header="Set-Cookie:"): return "%s %s" % (header, self.OutputString(attrs)) __str__ = output @as_native_str() def __repr__(self): if PY2 and isinstance(self.value, unicode): val = str(self.value) # make it a newstr to remove the u prefix else: val = self.value return '<%s: %s=%s>' % (self.__class__.__name__, str(self.key), repr(val)) def js_output(self, attrs=None): # Print javascript return """ """ % (self.OutputString(attrs).replace('"', r'\"')) def OutputString(self, attrs=None): # Build up our result # result = [] append = result.append # First, the key=value pair append("%s=%s" % (self.key, self.coded_value)) # Now add any defined attributes if attrs is None: attrs = self._reserved items = sorted(self.items()) for key, value in items: if value == "": continue if key not in attrs: continue if key == "expires" and isinstance(value, int): append("%s=%s" % (self._reserved[key], _getdate(value))) elif key == "max-age" and isinstance(value, int): append("%s=%d" % (self._reserved[key], value)) elif key == "secure": append(str(self._reserved[key])) elif key == "httponly": append(str(self._reserved[key])) else: append("%s=%s" % (self._reserved[key], value)) # Return the result return _semispacejoin(result) # # Pattern for finding cookie # # This used to be strict parsing based on the RFC2109 and RFC2068 # specifications. I have since discovered that MSIE 3.0x doesn't # follow the character rules outlined in those specs. As a # result, the parsing rules here are less strict. # _LegalCharsPatt = r"[\w\d!#%&'~_`><@,:/\$\*\+\-\.\^\|\)\(\?\}\{\=]" _CookiePattern = re.compile(r""" (?x) # This is a verbose pattern (?P # Start of group 'key' """ + _LegalCharsPatt + r"""+? # Any word of at least one letter ) # End of group 'key' ( # Optional group: there may not be a value. \s*=\s* # Equal Sign (?P # Start of group 'val' "(?:[^\\"]|\\.)*" # Any doublequoted string | # or \w{3},\s[\w\d\s-]{9,11}\s[\d:]{8}\sGMT # Special case for "expires" attr | # or """ + _LegalCharsPatt + r"""* # Any word or empty string ) # End of group 'val' )? # End of optional value group \s* # Any number of spaces. (\s+|;|$) # Ending either at space, semicolon, or EOS. """, re.ASCII) # May be removed if safe. # At long last, here is the cookie class. Using this class is almost just like # using a dictionary. See this module's docstring for example usage. # class BaseCookie(dict): """A container class for a set of Morsels.""" def value_decode(self, val): """real_value, coded_value = value_decode(STRING) Called prior to setting a cookie's value from the network representation. The VALUE is the value read from HTTP header. Override this function to modify the behavior of cookies. """ return val, val def value_encode(self, val): """real_value, coded_value = value_encode(VALUE) Called prior to setting a cookie's value from the dictionary representation. The VALUE is the value being assigned. Override this function to modify the behavior of cookies. """ strval = str(val) return strval, strval def __init__(self, input=None): if input: self.load(input) def __set(self, key, real_value, coded_value): """Private method for setting a cookie's value""" M = self.get(key, Morsel()) M.set(key, real_value, coded_value) dict.__setitem__(self, key, M) def __setitem__(self, key, value): """Dictionary style assignment.""" rval, cval = self.value_encode(value) self.__set(key, rval, cval) def output(self, attrs=None, header="Set-Cookie:", sep="\015\012"): """Return a string suitable for HTTP.""" result = [] items = sorted(self.items()) for key, value in items: result.append(value.output(attrs, header)) return sep.join(result) __str__ = output @as_native_str() def __repr__(self): l = [] items = sorted(self.items()) for key, value in items: if PY2 and isinstance(value.value, unicode): val = str(value.value) # make it a newstr to remove the u prefix else: val = value.value l.append('%s=%s' % (str(key), repr(val))) return '<%s: %s>' % (self.__class__.__name__, _spacejoin(l)) def js_output(self, attrs=None): """Return a string suitable for JavaScript.""" result = [] items = sorted(self.items()) for key, value in items: result.append(value.js_output(attrs)) return _nulljoin(result) def load(self, rawdata): """Load cookies from a string (presumably HTTP_COOKIE) or from a dictionary. Loading cookies from a dictionary 'd' is equivalent to calling: map(Cookie.__setitem__, d.keys(), d.values()) """ if isinstance(rawdata, str): self.__parse_string(rawdata) else: # self.update() wouldn't call our custom __setitem__ for key, value in rawdata.items(): self[key] = value return def __parse_string(self, mystr, patt=_CookiePattern): i = 0 # Our starting point n = len(mystr) # Length of string M = None # current morsel while 0 <= i < n: # Start looking for a cookie match = patt.search(mystr, i) if not match: # No more cookies break key, value = match.group("key"), match.group("val") i = match.end(0) # Parse the key, value in case it's metainfo if key[0] == "$": # We ignore attributes which pertain to the cookie # mechanism as a whole. See RFC 2109. # (Does anyone care?) if M: M[key[1:]] = value elif key.lower() in Morsel._reserved: if M: if value is None: if key.lower() in Morsel._flags: M[key] = True else: M[key] = _unquote(value) elif value is not None: rval, cval = self.value_decode(value) self.__set(key, rval, cval) M = self[key] class SimpleCookie(BaseCookie): """ SimpleCookie supports strings as cookie values. When setting the value using the dictionary assignment notation, SimpleCookie calls the builtin str() to convert the value to a string. Values received from HTTP are kept as strings. """ def value_decode(self, val): return _unquote(val), val def value_encode(self, val): strval = str(val) return strval, _quote(strval) """HTTP server classes. From Python 3.3 Note: BaseHTTPRequestHandler doesn't implement any HTTP request; see SimpleHTTPRequestHandler for simple implementations of GET, HEAD and POST, and CGIHTTPRequestHandler for CGI scripts. It does, however, optionally implement HTTP/1.1 persistent connections, as of version 0.3. Notes on CGIHTTPRequestHandler ------------------------------ This class implements GET and POST requests to cgi-bin scripts. If the os.fork() function is not present (e.g. on Windows), subprocess.Popen() is used as a fallback, with slightly altered semantics. In all cases, the implementation is intentionally naive -- all requests are executed synchronously. SECURITY WARNING: DON'T USE THIS CODE UNLESS YOU ARE INSIDE A FIREWALL -- it may execute arbitrary Python code or external programs. Note that status code 200 is sent prior to execution of a CGI script, so scripts cannot send other status codes such as 302 (redirect). XXX To do: - log requests even later (to capture byte count) - log user-agent header and other interesting goodies - send error log to separate file """ from __future__ import (absolute_import, division, print_function, unicode_literals) from future import utils from future.builtins import * # See also: # # HTTP Working Group T. Berners-Lee # INTERNET-DRAFT R. T. Fielding # H. Frystyk Nielsen # Expires September 8, 1995 March 8, 1995 # # URL: http://www.ics.uci.edu/pub/ietf/http/draft-ietf-http-v10-spec-00.txt # # and # # Network Working Group R. Fielding # Request for Comments: 2616 et al # Obsoletes: 2068 June 1999 # Category: Standards Track # # URL: http://www.faqs.org/rfcs/rfc2616.html # Log files # --------- # # Here's a quote from the NCSA httpd docs about log file format. # # | The logfile format is as follows. Each line consists of: # | # | host rfc931 authuser [DD/Mon/YYYY:hh:mm:ss] "request" ddd bbbb # | # | host: Either the DNS name or the IP number of the remote client # | rfc931: Any information returned by identd for this person, # | - otherwise. # | authuser: If user sent a userid for authentication, the user name, # | - otherwise. # | DD: Day # | Mon: Month (calendar name) # | YYYY: Year # | hh: hour (24-hour format, the machine's timezone) # | mm: minutes # | ss: seconds # | request: The first line of the HTTP request as sent by the client. # | ddd: the status code returned by the server, - if not available. # | bbbb: the total number of bytes sent, # | *not including the HTTP/1.0 header*, - if not available # | # | You can determine the name of the file accessed through request. # # (Actually, the latter is only true if you know the server configuration # at the time the request was made!) __version__ = "0.6" __all__ = ["HTTPServer", "BaseHTTPRequestHandler"] from future.backports import html from future.backports.http import client as http_client from future.backports.urllib import parse as urllib_parse from future.backports import socketserver import io import mimetypes import os import posixpath import select import shutil import socket # For gethostbyaddr() import sys import time import copy import argparse # Default error message template DEFAULT_ERROR_MESSAGE = """\ Error response

Error response

Error code: %(code)d

Message: %(message)s.

Error code explanation: %(code)s - %(explain)s.

""" DEFAULT_ERROR_CONTENT_TYPE = "text/html;charset=utf-8" def _quote_html(html): return html.replace("&", "&").replace("<", "<").replace(">", ">") class HTTPServer(socketserver.TCPServer): allow_reuse_address = 1 # Seems to make sense in testing environment def server_bind(self): """Override server_bind to store the server name.""" socketserver.TCPServer.server_bind(self) host, port = self.socket.getsockname()[:2] self.server_name = socket.getfqdn(host) self.server_port = port class BaseHTTPRequestHandler(socketserver.StreamRequestHandler): """HTTP request handler base class. The following explanation of HTTP serves to guide you through the code as well as to expose any misunderstandings I may have about HTTP (so you don't need to read the code to figure out I'm wrong :-). HTTP (HyperText Transfer Protocol) is an extensible protocol on top of a reliable stream transport (e.g. TCP/IP). The protocol recognizes three parts to a request: 1. One line identifying the request type and path 2. An optional set of RFC-822-style headers 3. An optional data part The headers and data are separated by a blank line. The first line of the request has the form where is a (case-sensitive) keyword such as GET or POST, is a string containing path information for the request, and should be the string "HTTP/1.0" or "HTTP/1.1". is encoded using the URL encoding scheme (using %xx to signify the ASCII character with hex code xx). The specification specifies that lines are separated by CRLF but for compatibility with the widest range of clients recommends servers also handle LF. Similarly, whitespace in the request line is treated sensibly (allowing multiple spaces between components and allowing trailing whitespace). Similarly, for output, lines ought to be separated by CRLF pairs but most clients grok LF characters just fine. If the first line of the request has the form (i.e. is left out) then this is assumed to be an HTTP 0.9 request; this form has no optional headers and data part and the reply consists of just the data. The reply form of the HTTP 1.x protocol again has three parts: 1. One line giving the response code 2. An optional set of RFC-822-style headers 3. The data Again, the headers and data are separated by a blank line. The response code line has the form where is the protocol version ("HTTP/1.0" or "HTTP/1.1"), is a 3-digit response code indicating success or failure of the request, and is an optional human-readable string explaining what the response code means. This server parses the request and the headers, and then calls a function specific to the request type (). Specifically, a request SPAM will be handled by a method do_SPAM(). If no such method exists the server sends an error response to the client. If it exists, it is called with no arguments: do_SPAM() Note that the request name is case sensitive (i.e. SPAM and spam are different requests). The various request details are stored in instance variables: - client_address is the client IP address in the form (host, port); - command, path and version are the broken-down request line; - headers is an instance of email.message.Message (or a derived class) containing the header information; - rfile is a file object open for reading positioned at the start of the optional input data part; - wfile is a file object open for writing. IT IS IMPORTANT TO ADHERE TO THE PROTOCOL FOR WRITING! The first thing to be written must be the response line. Then follow 0 or more header lines, then a blank line, and then the actual data (if any). The meaning of the header lines depends on the command executed by the server; in most cases, when data is returned, there should be at least one header line of the form Content-type: / where and should be registered MIME types, e.g. "text/html" or "text/plain". """ # The Python system version, truncated to its first component. sys_version = "Python/" + sys.version.split()[0] # The server software version. You may want to override this. # The format is multiple whitespace-separated strings, # where each string is of the form name[/version]. server_version = "BaseHTTP/" + __version__ error_message_format = DEFAULT_ERROR_MESSAGE error_content_type = DEFAULT_ERROR_CONTENT_TYPE # The default request version. This only affects responses up until # the point where the request line is parsed, so it mainly decides what # the client gets back when sending a malformed request line. # Most web servers default to HTTP 0.9, i.e. don't send a status line. default_request_version = "HTTP/0.9" def parse_request(self): """Parse a request (internal). The request should be stored in self.raw_requestline; the results are in self.command, self.path, self.request_version and self.headers. Return True for success, False for failure; on failure, an error is sent back. """ self.command = None # set in case of error on the first line self.request_version = version = self.default_request_version self.close_connection = 1 requestline = str(self.raw_requestline, 'iso-8859-1') requestline = requestline.rstrip('\r\n') self.requestline = requestline words = requestline.split() if len(words) == 3: command, path, version = words if version[:5] != 'HTTP/': self.send_error(400, "Bad request version (%r)" % version) return False try: base_version_number = version.split('/', 1)[1] version_number = base_version_number.split(".") # RFC 2145 section 3.1 says there can be only one "." and # - major and minor numbers MUST be treated as # separate integers; # - HTTP/2.4 is a lower version than HTTP/2.13, which in # turn is lower than HTTP/12.3; # - Leading zeros MUST be ignored by recipients. if len(version_number) != 2: raise ValueError version_number = int(version_number[0]), int(version_number[1]) except (ValueError, IndexError): self.send_error(400, "Bad request version (%r)" % version) return False if version_number >= (1, 1) and self.protocol_version >= "HTTP/1.1": self.close_connection = 0 if version_number >= (2, 0): self.send_error(505, "Invalid HTTP Version (%s)" % base_version_number) return False elif len(words) == 2: command, path = words self.close_connection = 1 if command != 'GET': self.send_error(400, "Bad HTTP/0.9 request type (%r)" % command) return False elif not words: return False else: self.send_error(400, "Bad request syntax (%r)" % requestline) return False self.command, self.path, self.request_version = command, path, version # Examine the headers and look for a Connection directive. try: self.headers = http_client.parse_headers(self.rfile, _class=self.MessageClass) except http_client.LineTooLong: self.send_error(400, "Line too long") return False conntype = self.headers.get('Connection', "") if conntype.lower() == 'close': self.close_connection = 1 elif (conntype.lower() == 'keep-alive' and self.protocol_version >= "HTTP/1.1"): self.close_connection = 0 # Examine the headers and look for an Expect directive expect = self.headers.get('Expect', "") if (expect.lower() == "100-continue" and self.protocol_version >= "HTTP/1.1" and self.request_version >= "HTTP/1.1"): if not self.handle_expect_100(): return False return True def handle_expect_100(self): """Decide what to do with an "Expect: 100-continue" header. If the client is expecting a 100 Continue response, we must respond with either a 100 Continue or a final response before waiting for the request body. The default is to always respond with a 100 Continue. You can behave differently (for example, reject unauthorized requests) by overriding this method. This method should either return True (possibly after sending a 100 Continue response) or send an error response and return False. """ self.send_response_only(100) self.flush_headers() return True def handle_one_request(self): """Handle a single HTTP request. You normally don't need to override this method; see the class __doc__ string for information on how to handle specific HTTP commands such as GET and POST. """ try: self.raw_requestline = self.rfile.readline(65537) if len(self.raw_requestline) > 65536: self.requestline = '' self.request_version = '' self.command = '' self.send_error(414) return if not self.raw_requestline: self.close_connection = 1 return if not self.parse_request(): # An error code has been sent, just exit return mname = 'do_' + self.command if not hasattr(self, mname): self.send_error(501, "Unsupported method (%r)" % self.command) return method = getattr(self, mname) method() self.wfile.flush() #actually send the response if not already done. except socket.timeout as e: #a read or a write timed out. Discard this connection self.log_error("Request timed out: %r", e) self.close_connection = 1 return def handle(self): """Handle multiple requests if necessary.""" self.close_connection = 1 self.handle_one_request() while not self.close_connection: self.handle_one_request() def send_error(self, code, message=None): """Send and log an error reply. Arguments are the error code, and a detailed message. The detailed message defaults to the short entry matching the response code. This sends an error response (so it must be called before any output has been generated), logs the error, and finally sends a piece of HTML explaining the error to the user. """ try: shortmsg, longmsg = self.responses[code] except KeyError: shortmsg, longmsg = '???', '???' if message is None: message = shortmsg explain = longmsg self.log_error("code %d, message %s", code, message) # using _quote_html to prevent Cross Site Scripting attacks (see bug #1100201) content = (self.error_message_format % {'code': code, 'message': _quote_html(message), 'explain': explain}) self.send_response(code, message) self.send_header("Content-Type", self.error_content_type) self.send_header('Connection', 'close') self.end_headers() if self.command != 'HEAD' and code >= 200 and code not in (204, 304): self.wfile.write(content.encode('UTF-8', 'replace')) def send_response(self, code, message=None): """Add the response header to the headers buffer and log the response code. Also send two standard headers with the server software version and the current date. """ self.log_request(code) self.send_response_only(code, message) self.send_header('Server', self.version_string()) self.send_header('Date', self.date_time_string()) def send_response_only(self, code, message=None): """Send the response header only.""" if message is None: if code in self.responses: message = self.responses[code][0] else: message = '' if self.request_version != 'HTTP/0.9': if not hasattr(self, '_headers_buffer'): self._headers_buffer = [] self._headers_buffer.append(("%s %d %s\r\n" % (self.protocol_version, code, message)).encode( 'latin-1', 'strict')) def send_header(self, keyword, value): """Send a MIME header to the headers buffer.""" if self.request_version != 'HTTP/0.9': if not hasattr(self, '_headers_buffer'): self._headers_buffer = [] self._headers_buffer.append( ("%s: %s\r\n" % (keyword, value)).encode('latin-1', 'strict')) if keyword.lower() == 'connection': if value.lower() == 'close': self.close_connection = 1 elif value.lower() == 'keep-alive': self.close_connection = 0 def end_headers(self): """Send the blank line ending the MIME headers.""" if self.request_version != 'HTTP/0.9': self._headers_buffer.append(b"\r\n") self.flush_headers() def flush_headers(self): if hasattr(self, '_headers_buffer'): self.wfile.write(b"".join(self._headers_buffer)) self._headers_buffer = [] def log_request(self, code='-', size='-'): """Log an accepted request. This is called by send_response(). """ self.log_message('"%s" %s %s', self.requestline, str(code), str(size)) def log_error(self, format, *args): """Log an error. This is called when a request cannot be fulfilled. By default it passes the message on to log_message(). Arguments are the same as for log_message(). XXX This should go to the separate error log. """ self.log_message(format, *args) def log_message(self, format, *args): """Log an arbitrary message. This is used by all other logging functions. Override it if you have specific logging wishes. The first argument, FORMAT, is a format string for the message to be logged. If the format string contains any % escapes requiring parameters, they should be specified as subsequent arguments (it's just like printf!). The client ip and current date/time are prefixed to every message. """ sys.stderr.write("%s - - [%s] %s\n" % (self.address_string(), self.log_date_time_string(), format%args)) def version_string(self): """Return the server software version string.""" return self.server_version + ' ' + self.sys_version def date_time_string(self, timestamp=None): """Return the current date and time formatted for a message header.""" if timestamp is None: timestamp = time.time() year, month, day, hh, mm, ss, wd, y, z = time.gmtime(timestamp) s = "%s, %02d %3s %4d %02d:%02d:%02d GMT" % ( self.weekdayname[wd], day, self.monthname[month], year, hh, mm, ss) return s def log_date_time_string(self): """Return the current time formatted for logging.""" now = time.time() year, month, day, hh, mm, ss, x, y, z = time.localtime(now) s = "%02d/%3s/%04d %02d:%02d:%02d" % ( day, self.monthname[month], year, hh, mm, ss) return s weekdayname = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'] monthname = [None, 'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'] def address_string(self): """Return the client address.""" return self.client_address[0] # Essentially static class variables # The version of the HTTP protocol we support. # Set this to HTTP/1.1 to enable automatic keepalive protocol_version = "HTTP/1.0" # MessageClass used to parse headers MessageClass = http_client.HTTPMessage # Table mapping response codes to messages; entries have the # form {code: (shortmessage, longmessage)}. # See RFC 2616 and 6585. responses = { 100: ('Continue', 'Request received, please continue'), 101: ('Switching Protocols', 'Switching to new protocol; obey Upgrade header'), 200: ('OK', 'Request fulfilled, document follows'), 201: ('Created', 'Document created, URL follows'), 202: ('Accepted', 'Request accepted, processing continues off-line'), 203: ('Non-Authoritative Information', 'Request fulfilled from cache'), 204: ('No Content', 'Request fulfilled, nothing follows'), 205: ('Reset Content', 'Clear input form for further input.'), 206: ('Partial Content', 'Partial content follows.'), 300: ('Multiple Choices', 'Object has several resources -- see URI list'), 301: ('Moved Permanently', 'Object moved permanently -- see URI list'), 302: ('Found', 'Object moved temporarily -- see URI list'), 303: ('See Other', 'Object moved -- see Method and URL list'), 304: ('Not Modified', 'Document has not changed since given time'), 305: ('Use Proxy', 'You must use proxy specified in Location to access this ' 'resource.'), 307: ('Temporary Redirect', 'Object moved temporarily -- see URI list'), 400: ('Bad Request', 'Bad request syntax or unsupported method'), 401: ('Unauthorized', 'No permission -- see authorization schemes'), 402: ('Payment Required', 'No payment -- see charging schemes'), 403: ('Forbidden', 'Request forbidden -- authorization will not help'), 404: ('Not Found', 'Nothing matches the given URI'), 405: ('Method Not Allowed', 'Specified method is invalid for this resource.'), 406: ('Not Acceptable', 'URI not available in preferred format.'), 407: ('Proxy Authentication Required', 'You must authenticate with ' 'this proxy before proceeding.'), 408: ('Request Timeout', 'Request timed out; try again later.'), 409: ('Conflict', 'Request conflict.'), 410: ('Gone', 'URI no longer exists and has been permanently removed.'), 411: ('Length Required', 'Client must specify Content-Length.'), 412: ('Precondition Failed', 'Precondition in headers is false.'), 413: ('Request Entity Too Large', 'Entity is too large.'), 414: ('Request-URI Too Long', 'URI is too long.'), 415: ('Unsupported Media Type', 'Entity body in unsupported format.'), 416: ('Requested Range Not Satisfiable', 'Cannot satisfy request range.'), 417: ('Expectation Failed', 'Expect condition could not be satisfied.'), 428: ('Precondition Required', 'The origin server requires the request to be conditional.'), 429: ('Too Many Requests', 'The user has sent too many requests ' 'in a given amount of time ("rate limiting").'), 431: ('Request Header Fields Too Large', 'The server is unwilling to ' 'process the request because its header fields are too large.'), 500: ('Internal Server Error', 'Server got itself in trouble'), 501: ('Not Implemented', 'Server does not support this operation'), 502: ('Bad Gateway', 'Invalid responses from another server/proxy.'), 503: ('Service Unavailable', 'The server cannot process the request due to a high load'), 504: ('Gateway Timeout', 'The gateway server did not receive a timely response'), 505: ('HTTP Version Not Supported', 'Cannot fulfill request.'), 511: ('Network Authentication Required', 'The client needs to authenticate to gain network access.'), } class SimpleHTTPRequestHandler(BaseHTTPRequestHandler): """Simple HTTP request handler with GET and HEAD commands. This serves files from the current directory and any of its subdirectories. The MIME type for files is determined by calling the .guess_type() method. The GET and HEAD requests are identical except that the HEAD request omits the actual contents of the file. """ server_version = "SimpleHTTP/" + __version__ def do_GET(self): """Serve a GET request.""" f = self.send_head() if f: self.copyfile(f, self.wfile) f.close() def do_HEAD(self): """Serve a HEAD request.""" f = self.send_head() if f: f.close() def send_head(self): """Common code for GET and HEAD commands. This sends the response code and MIME headers. Return value is either a file object (which has to be copied to the outputfile by the caller unless the command was HEAD, and must be closed by the caller under all circumstances), or None, in which case the caller has nothing further to do. """ path = self.translate_path(self.path) f = None if os.path.isdir(path): if not self.path.endswith('/'): # redirect browser - doing basically what apache does self.send_response(301) self.send_header("Location", self.path + "/") self.end_headers() return None for index in "index.html", "index.htm": index = os.path.join(path, index) if os.path.exists(index): path = index break else: return self.list_directory(path) ctype = self.guess_type(path) try: f = open(path, 'rb') except IOError: self.send_error(404, "File not found") return None self.send_response(200) self.send_header("Content-type", ctype) fs = os.fstat(f.fileno()) self.send_header("Content-Length", str(fs[6])) self.send_header("Last-Modified", self.date_time_string(fs.st_mtime)) self.end_headers() return f def list_directory(self, path): """Helper to produce a directory listing (absent index.html). Return value is either a file object, or None (indicating an error). In either case, the headers are sent, making the interface the same as for send_head(). """ try: list = os.listdir(path) except os.error: self.send_error(404, "No permission to list directory") return None list.sort(key=lambda a: a.lower()) r = [] displaypath = html.escape(urllib_parse.unquote(self.path)) enc = sys.getfilesystemencoding() title = 'Directory listing for %s' % displaypath r.append('') r.append('\n') r.append('' % enc) r.append('%s\n' % title) r.append('\n

%s

' % title) r.append('
\n
    ') for name in list: fullname = os.path.join(path, name) displayname = linkname = name # Append / for directories or @ for symbolic links if os.path.isdir(fullname): displayname = name + "/" linkname = name + "/" if os.path.islink(fullname): displayname = name + "@" # Note: a link to a directory displays with @ and links with / r.append('
  • %s
    • ' % (urllib_parse.quote(linkname), html.escape(displayname))) # # Use this instead: # r.append('
  • %s
    • ' # % (urllib.quote(linkname), cgi.escape(displayname))) r.append('
\n
\n\n\n') encoded = '\n'.join(r).encode(enc) f = io.BytesIO() f.write(encoded) f.seek(0) self.send_response(200) self.send_header("Content-type", "text/html; charset=%s" % enc) self.send_header("Content-Length", str(len(encoded))) self.end_headers() return f def translate_path(self, path): """Translate a /-separated PATH to the local filename syntax. Components that mean special things to the local file system (e.g. drive or directory names) are ignored. (XXX They should probably be diagnosed.) """ # abandon query parameters path = path.split('?',1)[0] path = path.split('#',1)[0] path = posixpath.normpath(urllib_parse.unquote(path)) words = path.split('/') words = filter(None, words) path = os.getcwd() for word in words: drive, word = os.path.splitdrive(word) head, word = os.path.split(word) if word in (os.curdir, os.pardir): continue path = os.path.join(path, word) return path def copyfile(self, source, outputfile): """Copy all data between two file objects. The SOURCE argument is a file object open for reading (or anything with a read() method) and the DESTINATION argument is a file object open for writing (or anything with a write() method). The only reason for overriding this would be to change the block size or perhaps to replace newlines by CRLF -- note however that this the default server uses this to copy binary data as well. """ shutil.copyfileobj(source, outputfile) def guess_type(self, path): """Guess the type of a file. Argument is a PATH (a filename). Return value is a string of the form type/subtype, usable for a MIME Content-type header. The default implementation looks the file's extension up in the table self.extensions_map, using application/octet-stream as a default; however it would be permissible (if slow) to look inside the data to make a better guess. """ base, ext = posixpath.splitext(path) if ext in self.extensions_map: return self.extensions_map[ext] ext = ext.lower() if ext in self.extensions_map: return self.extensions_map[ext] else: return self.extensions_map[''] if not mimetypes.inited: mimetypes.init() # try to read system mime.types extensions_map = mimetypes.types_map.copy() extensions_map.update({ '': 'application/octet-stream', # Default '.py': 'text/plain', '.c': 'text/plain', '.h': 'text/plain', }) # Utilities for CGIHTTPRequestHandler def _url_collapse_path(path): """ Given a URL path, remove extra '/'s and '.' path elements and collapse any '..' references and returns a colllapsed path. Implements something akin to RFC-2396 5.2 step 6 to parse relative paths. The utility of this function is limited to is_cgi method and helps preventing some security attacks. Returns: A tuple of (head, tail) where tail is everything after the final / and head is everything before it. Head will always start with a '/' and, if it contains anything else, never have a trailing '/'. Raises: IndexError if too many '..' occur within the path. """ # Similar to os.path.split(os.path.normpath(path)) but specific to URL # path semantics rather than local operating system semantics. path_parts = path.split('/') head_parts = [] for part in path_parts[:-1]: if part == '..': head_parts.pop() # IndexError if more '..' than prior parts elif part and part != '.': head_parts.append( part ) if path_parts: tail_part = path_parts.pop() if tail_part: if tail_part == '..': head_parts.pop() tail_part = '' elif tail_part == '.': tail_part = '' else: tail_part = '' splitpath = ('/' + '/'.join(head_parts), tail_part) collapsed_path = "/".join(splitpath) return collapsed_path nobody = None def nobody_uid(): """Internal routine to get nobody's uid""" global nobody if nobody: return nobody try: import pwd except ImportError: return -1 try: nobody = pwd.getpwnam('nobody')[2] except KeyError: nobody = 1 + max(x[2] for x in pwd.getpwall()) return nobody def executable(path): """Test for executable file.""" return os.access(path, os.X_OK) class CGIHTTPRequestHandler(SimpleHTTPRequestHandler): """Complete HTTP server with GET, HEAD and POST commands. GET and HEAD also support running CGI scripts. The POST command is *only* implemented for CGI scripts. """ # Determine platform specifics have_fork = hasattr(os, 'fork') # Make rfile unbuffered -- we need to read one line and then pass # the rest to a subprocess, so we can't use buffered input. rbufsize = 0 def do_POST(self): """Serve a POST request. This is only implemented for CGI scripts. """ if self.is_cgi(): self.run_cgi() else: self.send_error(501, "Can only POST to CGI scripts") def send_head(self): """Version of send_head that support CGI scripts""" if self.is_cgi(): return self.run_cgi() else: return SimpleHTTPRequestHandler.send_head(self) def is_cgi(self): """Test whether self.path corresponds to a CGI script. Returns True and updates the cgi_info attribute to the tuple (dir, rest) if self.path requires running a CGI script. Returns False otherwise. If any exception is raised, the caller should assume that self.path was rejected as invalid and act accordingly. The default implementation tests whether the normalized url path begins with one of the strings in self.cgi_directories (and the next character is a '/' or the end of the string). """ collapsed_path = _url_collapse_path(self.path) dir_sep = collapsed_path.find('/', 1) head, tail = collapsed_path[:dir_sep], collapsed_path[dir_sep+1:] if head in self.cgi_directories: self.cgi_info = head, tail return True return False cgi_directories = ['/cgi-bin', '/htbin'] def is_executable(self, path): """Test whether argument path is an executable file.""" return executable(path) def is_python(self, path): """Test whether argument path is a Python script.""" head, tail = os.path.splitext(path) return tail.lower() in (".py", ".pyw") def run_cgi(self): """Execute a CGI script.""" path = self.path dir, rest = self.cgi_info i = path.find('/', len(dir) + 1) while i >= 0: nextdir = path[:i] nextrest = path[i+1:] scriptdir = self.translate_path(nextdir) if os.path.isdir(scriptdir): dir, rest = nextdir, nextrest i = path.find('/', len(dir) + 1) else: break # find an explicit query string, if present. i = rest.rfind('?') if i >= 0: rest, query = rest[:i], rest[i+1:] else: query = '' # dissect the part after the directory name into a script name & # a possible additional path, to be stored in PATH_INFO. i = rest.find('/') if i >= 0: script, rest = rest[:i], rest[i:] else: script, rest = rest, '' scriptname = dir + '/' + script scriptfile = self.translate_path(scriptname) if not os.path.exists(scriptfile): self.send_error(404, "No such CGI script (%r)" % scriptname) return if not os.path.isfile(scriptfile): self.send_error(403, "CGI script is not a plain file (%r)" % scriptname) return ispy = self.is_python(scriptname) if self.have_fork or not ispy: if not self.is_executable(scriptfile): self.send_error(403, "CGI script is not executable (%r)" % scriptname) return # Reference: http://hoohoo.ncsa.uiuc.edu/cgi/env.html # XXX Much of the following could be prepared ahead of time! env = copy.deepcopy(os.environ) env['SERVER_SOFTWARE'] = self.version_string() env['SERVER_NAME'] = self.server.server_name env['GATEWAY_INTERFACE'] = 'CGI/1.1' env['SERVER_PROTOCOL'] = self.protocol_version env['SERVER_PORT'] = str(self.server.server_port) env['REQUEST_METHOD'] = self.command uqrest = urllib_parse.unquote(rest) env['PATH_INFO'] = uqrest env['PATH_TRANSLATED'] = self.translate_path(uqrest) env['SCRIPT_NAME'] = scriptname if query: env['QUERY_STRING'] = query env['REMOTE_ADDR'] = self.client_address[0] authorization = self.headers.get("authorization") if authorization: authorization = authorization.split() if len(authorization) == 2: import base64, binascii env['AUTH_TYPE'] = authorization[0] if authorization[0].lower() == "basic": try: authorization = authorization[1].encode('ascii') if utils.PY3: # In Py3.3, was: authorization = base64.decodebytes(authorization).\ decode('ascii') else: # Backport to Py2.7: authorization = base64.decodestring(authorization).\ decode('ascii') except (binascii.Error, UnicodeError): pass else: authorization = authorization.split(':') if len(authorization) == 2: env['REMOTE_USER'] = authorization[0] # XXX REMOTE_IDENT if self.headers.get('content-type') is None: env['CONTENT_TYPE'] = self.headers.get_content_type() else: env['CONTENT_TYPE'] = self.headers['content-type'] length = self.headers.get('content-length') if length: env['CONTENT_LENGTH'] = length referer = self.headers.get('referer') if referer: env['HTTP_REFERER'] = referer accept = [] for line in self.headers.getallmatchingheaders('accept'): if line[:1] in "\t\n\r ": accept.append(line.strip()) else: accept = accept + line[7:].split(',') env['HTTP_ACCEPT'] = ','.join(accept) ua = self.headers.get('user-agent') if ua: env['HTTP_USER_AGENT'] = ua co = filter(None, self.headers.get_all('cookie', [])) cookie_str = ', '.join(co) if cookie_str: env['HTTP_COOKIE'] = cookie_str # XXX Other HTTP_* headers # Since we're setting the env in the parent, provide empty # values to override previously set values for k in ('QUERY_STRING', 'REMOTE_HOST', 'CONTENT_LENGTH', 'HTTP_USER_AGENT', 'HTTP_COOKIE', 'HTTP_REFERER'): env.setdefault(k, "") self.send_response(200, "Script output follows") self.flush_headers() decoded_query = query.replace('+', ' ') if self.have_fork: # Unix -- fork as we should args = [script] if '=' not in decoded_query: args.append(decoded_query) nobody = nobody_uid() self.wfile.flush() # Always flush before forking pid = os.fork() if pid != 0: # Parent pid, sts = os.waitpid(pid, 0) # throw away additional data [see bug #427345] while select.select([self.rfile], [], [], 0)[0]: if not self.rfile.read(1): break if sts: self.log_error("CGI script exit status %#x", sts) return # Child try: try: os.setuid(nobody) except os.error: pass os.dup2(self.rfile.fileno(), 0) os.dup2(self.wfile.fileno(), 1) os.execve(scriptfile, args, env) except: self.server.handle_error(self.request, self.client_address) os._exit(127) else: # Non-Unix -- use subprocess import subprocess cmdline = [scriptfile] if self.is_python(scriptfile): interp = sys.executable if interp.lower().endswith("w.exe"): # On Windows, use python.exe, not pythonw.exe interp = interp[:-5] + interp[-4:] cmdline = [interp, '-u'] + cmdline if '=' not in query: cmdline.append(query) self.log_message("command: %s", subprocess.list2cmdline(cmdline)) try: nbytes = int(length) except (TypeError, ValueError): nbytes = 0 p = subprocess.Popen(cmdline, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, env = env ) if self.command.lower() == "post" and nbytes > 0: data = self.rfile.read(nbytes) else: data = None # throw away additional data [see bug #427345] while select.select([self.rfile._sock], [], [], 0)[0]: if not self.rfile._sock.recv(1): break stdout, stderr = p.communicate(data) self.wfile.write(stdout) if stderr: self.log_error('%s', stderr) p.stderr.close() p.stdout.close() status = p.returncode if status: self.log_error("CGI script exit status %#x", status) else: self.log_message("CGI script exited OK") def test(HandlerClass = BaseHTTPRequestHandler, ServerClass = HTTPServer, protocol="HTTP/1.0", port=8000): """Test the HTTP request handler class. This runs an HTTP server on port 8000 (or the first command line argument). """ server_address = ('', port) HandlerClass.protocol_version = protocol httpd = ServerClass(server_address, HandlerClass) sa = httpd.socket.getsockname() print("Serving HTTP on", sa[0], "port", sa[1], "...") try: httpd.serve_forever() except KeyboardInterrupt: print("\nKeyboard interrupt received, exiting.") httpd.server_close() sys.exit(0) if __name__ == '__main__': parser = argparse.ArgumentParser() parser.add_argument('--cgi', action='store_true', help='Run as CGI Server') parser.add_argument('port', action='store', default=8000, type=int, nargs='?', help='Specify alternate port [default: 8000]') args = parser.parse_args() if args.cgi: test(HandlerClass=CGIHTTPRequestHandler, port=args.port) else: test(HandlerClass=SimpleHTTPRequestHandler, port=args.port) """ test package backported for python-future. Its primary purpose is to allow use of "import test.support" for running the Python standard library unit tests using the new Python 3 stdlib import location. Python 3 renamed test.test_support to test.support. """