w:iAdZddlmZddlZddlmZddlmZmZm Z m Z m Z m Z ddl mZmZmZmZddl mZmZmZmZmZmZmZmZmZmZmZgdZd Zd ZGd d e Z!Gd de"Z#dZ$Gddej%e"Z%ddZ&dZ'dS)zOSupport for constructing markup streams from files, strings, or other sources. )chainN)expat) html_entities html_parser text_typeunichrStringIOBytesIO)AttrsQNameStream stripentities) STARTENDXML_DECLDOCTYPETEXTSTART_NSEND_NS START_CDATA END_CDATAPICOMMENT)ET ParseError XMLParserXML HTMLParserHTMLzrestructuredtext enc#|Kt|jd}td|D}t ||fdfV|jrt|jdfV|D]}t|D]}|Vt|dfV|j rt|j dfVdSdS)zConvert a given ElementTree element to a markup stream. :param element: an ElementTree element :return: a markup stream {c\g|])\}}t|d|f*S)r!)r lstrip).0attrvalues D/var/www/html/trac/venv/lib/python3.11/site-packages/genshi/input.py zET..(sE777"tU$++c**++U3777Nr+N) r tagr#r itemsrtextrrrtail)elementtag_nameattrschilditems r'rr!s W['',,--H 77&-mmoo777 8 8E (E"N 2222|1GL.0000uII  DJJJJ  x ''''|1GL.00000011r)ceZdZdZddZdS)rzWException raised when fatal syntax errors are found in the input being parsed. Nr+c||_|r|d|zz }t|||pd|_||_||_dS)a:Exception initializer. :param message: the error message from the parser :param filename: the path to the file that was parsed :param lineno: the number of the line on which the error was encountered :param offset: the column number where the error was encountered z, in zN)msg Exception__init__filenamelinenooffset)selfmessager:r;r<s r'r9zParseError.__init__;sV  * w) )G4))) .J   r)r*)__name__ __module__ __qualname____doc__r9r)r'rr6s2r)rceZdZdZdejDZde dZ ddZ dZ dZ d Zdd Zd Zd Zd ZdZdZdZdZdZdZdZdZdZdZdZdS)raGenerator-based XML parser based on roughly equivalent code in Kid/ElementTree. The parsing is initiated by iterating over the parser object: >>> parser = XMLParser(StringIO('Foo')) >>> for kind, data, pos in parser: ... print('%s %s' % (kind, data)) START (QName('root'), Attrs([(QName('id'), '2')])) START (QName('child'), Attrs()) TEXT Foo END child END root c"g|] \}}d||fz S)zrCr$namer&s r'r(zXMLParser.\s2999kdE)T5M9999r) utf-8NcP||_||_tj|d}d|_t |drd|_d|_|j|_ |j |_ |j |_ |j|_|j|_|j|_|j|_|j|_|j|_|j|_|j|_|j|_| tj!|"|j#|_$||_g|_%dS)aInitialize the parser for the given XML input. :param source: the XML text as a file-like object :param filename: the name of the file, if appropriate :param encoding: the encoding of the file; if not specified, the encoding is assumed to be ASCII, UTF-8, or UTF-16, or whatever the encoding specified in the XML declaration (if any) }Treturns_unicodeN)&sourcer:r ParserCreate buffer_texthasattrrLordered_attributes _handle_startStartElementHandler _handle_endEndElementHandler _handle_dataCharacterDataHandler_handle_doctypeStartDoctypeDeclHandler_handle_start_nsStartNamespaceDeclHandler_handle_end_nsEndNamespaceDeclHandler_handle_start_cdataStartCdataSectionHandler_handle_end_cdataEndCdataSectionHandler _handle_piProcessingInstructionHandler_handle_xml_declXmlDeclHandler_handle_commentCommentHandler _handle_otherDefaultHandlerSetParamEntityParsingXML_PARAM_ENTITY_PARSING_ALWAYS UseForeignDTD_build_foreignExternalEntityRefHandler_queue)r=rMr:encodingparsers r'r9zXMLParser.__init__`s   #Hc22! 6, - - *%)F "$(!%)%7"#'#3 &*&7#)-)=&+/+@()-)<&*.*B'(,(>%.2o+ $ 5 $ 4!% 2$$U%JKKK*.*='  r)clfd}t|tS)zGenerator that parses the XML source, yielding markup events. :return: a markup event stream :raises ParseError: if the XML text is not well formed c3`K d}d} |stjdkrj|}|s0t drjdd`d}nEt|tr| d}j|d|stjdkjD]}|Vg_|rdS#t j $r5}t|}t|j |j|jd}~wwxYw) NFrrTrI)lenrorMreadrPrParse isinstancerencode ExpatErrorstrrr:r;r<)bufsizedonedataeventer7r=s r' _generatez"XMLParser.parse.._generatesh I"" :s4;'7'71'<'<#{//88#:&tW55/ $ 0 0T : : :$(J#'DD)$ ::<'+{{7';'; J,,T5999# :s4;'7'71'<'<"&$$# "$DK!"# I I I!ff dmQXqxHHH IsC!C)(C))D-80D((D-r filter _coalescer=rs` r'parsezXMLParser.parsesE  I I I I I0iikk"")))444r)cDt|SNiterrr=s r'__iter__zXMLParser.__iter__DJJLL!!!r)c|j|}|t|jdS)Nru)rExternalEntityParserCreate ParseFiler _external_dtd)r=contextbasesysidpubidrqs r'rmzXMLParser._build_foreigns;66w??!344555qr)c@||}|turad|vr2|}|dt|z dz}d}n |d}|dt|z }|d||f}|j|||fdS)NrHrur+r)_getposr splitlinesrwroappend)r=kindrposlinesr;r<s r'_enqueuezXMLParser._enqueues ;,,..C 4<< t||))Q#e**,q0QQ#d))+q666*C D$,-----r)c|jddfS)Nr+)r:rs r'_getpos_unknownzXMLParser._getpos_unknowns r2&&r)c>|j|jj|jjfSr)r:rCurrentLineNumberCurrentColumnNumberrs r'rzXMLParser._getposs  tz; .0 0r)ctdtt|gdzD}|tt ||fdS)Nc6g|]\}}t||fSrC)r rFs r'r(z+XMLParser._handle_start..s3111 ed U+111r)r)r ziprrrr )r=r,attribr2s r'rRzXMLParser._handle_startsd11T&\\NQ./11122 eeCjj%011111r)cV|tt|dSr)rrr )r=r,s r'rTzXMLParser._handle_ends" c5::&&&&&r)c<|t|dSrrrr=r.s r'rVzXMLParser._handle_data dD!!!!!r)cB|t|||fdSr)rr)r=versionrp standalones r'rdzXMLParser._handle_xml_decls# h(J ?@@@@@r)cB|t|||fdSr)rr)r=rGrrhas_internal_subsets r'rXzXMLParser._handle_doctypes# geU344444r)cD|t|pd|fdSNrv)rr)r=prefixuris r'rZzXMLParser._handle_start_nss% h2s 344444r)c@|t|pddSr)rr)r=rs r'r\zXMLParser._handle_end_nss  ffl+++++r)c:|tdSr)rrrs r'r^zXMLParser._handle_start_cdatas k"""""r)c:|tdSr)rrrs r'r`zXMLParser._handle_end_cdatas i     r)c@|t||fdSr)rr)r=targetrs r'rbzXMLParser._handle_pis  b64.)))))r)c<|t|dSrrrrs r'rfzXMLParser._handle_comment gt$$$$$r)c|dr ttj|dd}|t |dS#t $rY|\}}}tj d|||fz}tj j |_ ||_ ||_|wxYwdS)N&rur+z)undefined entity "%s": line %d, column %d) startswithrrname2codepointrrKeyErrorrrerrorerrorsXML_ERROR_UNDEFINED_ENTITYcoder;r<)r=r.r:r;r<rs r'rhzXMLParser._handle_others ??3    m:4":FGG dD)))))   +/<<>>(&& $O'+VV&<%=>>"\D % %     s AAA#B>NN)r?r@rArBrrr- _entitydefsjoinr{rr9rrrmrrrrRrTrVrdrXrZr\r^r`rbrfrhrCr)r'rrLs  99 /5577999KJJ{++227;;M))))V555@""" ....&'''000222 '''"""AAA555555,,,###!!!***%%%     r)rc ntttt|S)a?Parse the given XML source and return a markup stream. Unlike with `XMLParser`, the returned stream is reusable, meaning it can be iterated over multiple times: >>> xml = XML('FooBar') >>> print(xml) FooBar >>> print(xml.select('elem')) FooBar >>> print(xml.select('elem/text()')) FooBar :param text: the XML source :return: the parsed XML event stream :raises ParseError: if the XML text is not well-formed )r listrr )r.s r'rrs($ $y$0011 2 22r)cxeZdZdZegdZddZdZdZddZ dZ d Z d Z d Z d Zd ZdZdZdS)raUParser for HTML input based on the Python `HTMLParser` module. This class provides the same interface for generating stream events as `XMLParser`, and attempts to automatically balance tags. The parsing is initiated by iterating over the parser object: >>> parser = HTMLParser(BytesIO(u'
  • Foo
'.encode('utf-8')), encoding='utf-8') >>> for kind, data, pos in parser: ... print('%s %s' % (kind, data)) START (QName('ul'), Attrs([(QName('compact'), 'compact')])) START (QName('li'), Attrs()) TEXT Foo END li END ul ) arearbasefontbrcolframehrimginputisindexlinkmetaparamNctj|||_||_||_g|_g|_dS)aInitialize the parser for the given HTML input. :param source: the HTML text as a file-like object :param filename: the name of the file, if known :param filename: encoding of the file; ignored if the input is unicode N)rrr9rMr:rpro _open_tags)r=rMr:rps r'r9zHTMLParser.__init__+sB ''---      r)clfd}t|tS)zGenerator that parses the HTML source, yielding markup events. :return: a markup event stream :raises ParseError: if the HTML text is not well formed c3K jr*tj j}| j}n j} d}d} |st jdkr||}|s d}n9t|tstd ||st jdk jD] \}}}|||fVg _|r; j }| |D]}tt||fVdS#t $r)} t#| } t%| jd} ~ wwxYw)NrtFrurTz0source returned bytes, but no encoding specified)rpcodecs getreaderrMrwrorxcloserzr UnicodeErrorfeedrreverserr r8r}rr:) readerrMr~rrrr open_tagsr,rr7r=s r'rz#HTMLParser.parse.._generate?s} %)$-88 ,, 5"",s4;'7'71'<'<%{{733#, JJLLL#'DD#-dI#>#>g&23e&f&f f IIdOOO#,s4;'7'71'<'<,0;..dC"D#o----"$DK$(O !))+++#,77C"%uSzz3"66666%& 5 5 5 !ff dm444  5sC7D76D77 E*$E%%E*rrs` r'rzHTMLParser.parse9sA " 5" 5" 5" 5" 5Fiikk"")))444r)cDt|Srrrs r'rzHTMLParser.__iter__drr)cl||}|j|||fdSr)rror)r=rrrs r'rzHTMLParser._enqueuegs7 ;,,..C D$,-----r)cD|\}}|j||fSr)getposr:)r=r;columns r'rzHTMLParser._getposls" vv..r)cg}|D]:\}}||}|t|t|f;|tt|t |f||jvr*|tt|dS|j|dSr) rr rrrr _EMPTY_ELEMSrr)r=r,r fixed_attribrGr&s r'handle_starttagzHTMLParser.handle_starttagps ! E EKD%}   tmE.B.B C D D D D eeCjj% *=*=>??? $# # # MM#uSzz * * * * * O " "3 ' ' ' ' 'r)c||jvr}|jrx|j}|tt |||krdS|jtdSdSdSr)rrpoprrr lower)r=r,open_tags r' handle_endtagzHTMLParser.handle_endtag}s d' ' '/ ?..00 c5??333>>##syy{{22E /    ( '  r)c<|t|dSrrrs r' handle_datazHTMLParser.handle_datarr)c|dr&tt|ddd}ntt|}|t |dS)Nxru)rrrintrrr=rGr.s r'handle_charrefzHTMLParser.handle_charrefsn ::<< " "3 ' ' %#d122h++,,DD#d))$$D dD!!!!!r)c ttj|}n#t$rd|z}YnwxYw|t |dS)Nz&%s;)rrrrrrrs r'handle_entityrefzHTMLParser.handle_entityrefs` !-6t<==DD ! ! !D=DDD ! dD!!!!!s "44c$|dr |dd} |dd\}}n#t$r|}d}YnwxYw|t||fdS)N?r+rurv)endswithsplit ValueErrorrrstrip)r=rrs r' handle_pizHTMLParser.handle_pis ==   9D ::dA..LFDD   FDDD  b6<<>>4::<<899999s;A  A c<|t|dSrrrs r'handle_commentzHTMLParser.handle_commentrr)rr)r?r@rArB frozensetrr9rrrrrrrrrrrrCr)r'rrs"9'''((L    )5)5)5V""".... /// ( ( (""""""""" : : :%%%%%r)rc  t|tr8ttt t |dSttt t ||S)aMParse the given HTML source and return a markup stream. Unlike with `HTMLParser`, the returned stream is reusable, meaning it can be iterated over multiple times: >>> html = HTML('

Foo

', encoding='utf-8') >>> print(html)

Foo

>>> print(html.select('h1'))

Foo

>>> print(html.select('h1/text()')) Foo :param text: the HTML source :return: the parsed XML event stream :raises ParseError: if the HTML text is not well-formed, and error recovery fails N)rp)rzrr rrr r )r.rps r'rrsk&$ ""Gd:htnntDDDEEFFF $z'$--(CCCDD E EEr)c#Kg}d}t|dgD]Z\}}}|tur||||})|r&td||fV|dd=d}|r|||fV[dS)z3Coalesces adjacent TEXT events into a single event.N)NNNrv)rrrr)streamtextbuftextposrrrs r'rrsGG *<)=>> & &dC 4<< NN4  BGGG,,g5555AAAJ &D#o%%% & &r)r)(rB itertoolsrr xml.parsersr genshi.compatrrrrr r genshi.corer r r rrrrrrrrrrrr__all__ __docformat__rr8robjectrrrrrrCr)r'rsE ,,,,,,,,,,,,,,,,;;;;;;;;;;;;DDDDDDDDDDDDDDDDDDDDDDDDDD I H H% 111*,qqqqqqqqh333*M%M%M%M%M%'M%M%M%`FFFF6&&&&&r)