o iI@sddlZddlZddlZddlmZddlmZmZmZm Z m Z ddl m Z ddl mZddlmZdZGdd d e ZGd d d eZGd d d eZGdddeZdS)N)PIPE) _java_options config_java find_jar_iterfind_jars_within_pathjava)ParserIDependencyGraph)Treez2https://nlp.stanford.edu/software/lex-parser.shtmlc@seZdZdZdZdZdZdZdZ      dd d Z d dZ dddZ dddZ dddZ dddZdddZdddZdS)GenericStanfordParserz Interface to the Stanford Parserz+stanford-parser-(\d+)(\.(\d+))+-models\.jarzstanford-parser\.jarz3edu.stanford.nlp.parser.lexparser.LexicalizedParserFN4edu/stanford/nlp/models/lexparser/englishPCFG.ser.gzutf8-mx4gc Cstt|j|ddt|ddddd}tt|j|ddt|ddd dd} tj|d } t| gt | |_ ||_ ||_ ||_ ||_dS) N)STANFORD_PARSERSTANFORD_CORENLPT)env_vars searchpathurlverboseis_regexcS tj|SNospathdirname model_pathrrN/var/www/edux/Edux_v2/venv/lib/python3.10/site-packages/nltk/parse/stanford.py; z0GenericStanfordParser.__init__..)key)STANFORD_MODELSrcSrrrrrrr!r"Hr#r)maxr_JAR _stanford_url_MODEL_JAR_PATTERNrrsplittupler _classpathr _encodingcorenlp_options java_options) self path_to_jarpath_to_models_jarr encodingrr/r. stanford_jar model_jar stanford_dirrrr!__init__&s<     zGenericStanfordParser.__init__c Csg}g}g}d}|dD]?}|dkrE|r!|t|g}d}q |jr4||d|g}d}q |t|d|gg}q ||d}q t|S)NFr T) splitlinesappenditer_DOUBLE_SPACED_OUTPUT _make_treejoin)r0output_res cur_lines cur_treesblanklinerrr!_parse_trees_outputVs& z)GenericStanfordParser._parse_trees_outputc CsB|jd|jddd|jdddg }|||dd d |D|S) a Use StanfordParser to parse multiple sentences. Takes multiple sentences as a list where each sentence is a list of words. Each sentence will be automatically tagged with this StanfordParser instance's tagger. If whitespaces exists inside a token, then the token will be treated as separate tokens. :param sentences: Input sentences to parse :type sentences: list(list(str)) :rtype: iter(iter(Tree)) -model -sentencesnewline -outputFormat -tokenizedz-escaperz-edu.stanford.nlp.process.PTBEscapingProcessorr8css|]}d|VqdS) Nr>.0sentencerrr! z4GenericStanfordParser.parse_sents.. _MAIN_CLASSr _OUTPUT_FORMATrE_executer>r0 sentencesrcmdrrr! parse_sentsms  z!GenericStanfordParser.parse_sentscCt||g|S)a& Use StanfordParser to parse a sentence. Takes a sentence as a string; before parsing, it will be automatically tokenized and tagged by the Stanford Parser. :param sentence: Input sentence to parse :type sentence: str :rtype: iter(Tree) )nextraw_parse_sentsr0rOrrrr! raw_parse zGenericStanfordParser.raw_parsecCs2|jd|jddd|jg}|||d||S)aI Use StanfordParser to parse multiple sentences. Takes multiple sentences as a list of strings. Each sentence will be automatically tokenized and tagged by the Stanford Parser. :param sentences: Input sentences to parse :type sentences: list(str) :rtype: iter(iter(Tree)) rFrGrHrIr8rRrVrrr!r\s  z%GenericStanfordParser.raw_parse_sentscCrZ)a0 Use StanfordParser to parse a sentence. Takes a sentence as a list of (word, tag) tuples; the sentence must have already been tokenized and tagged. :param sentence: Input sentence to parse :type sentence: list(tuple(str, str)) :rtype: iter(Tree) )r[tagged_parse_sentsr]rrr! tagged_parser_z"GenericStanfordParser.tagged_parsecsRd|jd|jddd|jdddd d d g}|||d fd d|D|S)ad Use StanfordParser to parse multiple sentences. Takes multiple sentences where each sentence is a list of (word, tag) tuples. The sentences must have already been tokenized and tagged. :param sentences: Input sentences to parse :type sentences: list(list(tuple(str, str))) :rtype: iter(iter(Tree)) /rFrGrHrIrJz -tagSeparatorz-tokenizerFactoryz,edu.stanford.nlp.process.WhitespaceTokenizerz-tokenizerMethodnewCoreLabelTokenizerFactoryr8c3s(|]}dfdd|DVqdS)rKc3s|]}|VqdSrrL)rNtagged tag_separatorrr!rPrQzEGenericStanfordParser.tagged_parse_sents...NrLrMrerr!rPs  z;GenericStanfordParser.tagged_parse_sents..rRrVrrer!r`s2 z(GenericStanfordParser.tagged_parse_sentsc Cs$|j}|d|g|jr||jdt}t|j|dtj dddT}t |t r5|r5| |}| |||jrS|dt||j|ttd\}}n||jt||jttd \}}|d d }|d d }||}Wdn1swYt|jt|dd|S) Nz -encodingrK)optionsrwbF)modedeleter) classpathstdinstdoutstderr)rkrmrns  s)r-extendr.r*r>rrr/tempfileNamedTemporaryFile isinstancestrencodewriteflush _USE_STDINseekrr,rr:namereplacedecoderunlink) r0rXinput_rr3default_options input_filermrnrrr!rUs>           zGenericStanfordParser._execute)NNr rFrrF)__name__ __module__ __qualname____doc__r)r'rSrxr<r7rErYr^r\rar`rUrrrr!r s, 0    'r c,eZdZdZdZfddZddZZS)StanfordParsera >>> parser=StanfordParser( ... model_path="edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz" ... ) # doctest: +SKIP >>> list(parser.raw_parse("the quick brown fox jumps over the lazy dog")) # doctest: +NORMALIZE_WHITESPACE +SKIP [Tree('ROOT', [Tree('NP', [Tree('NP', [Tree('DT', ['the']), Tree('JJ', ['quick']), Tree('JJ', ['brown']), Tree('NN', ['fox'])]), Tree('NP', [Tree('NP', [Tree('NNS', ['jumps'])]), Tree('PP', [Tree('IN', ['over']), Tree('NP', [Tree('DT', ['the']), Tree('JJ', ['lazy']), Tree('NN', ['dog'])])])])])])] >>> sum([list(dep_graphs) for dep_graphs in parser.raw_parse_sents(( ... "the quick brown fox jumps over the lazy dog", ... "the quick grey wolf jumps over the lazy fox" ... ))], []) # doctest: +NORMALIZE_WHITESPACE +SKIP [Tree('ROOT', [Tree('NP', [Tree('NP', [Tree('DT', ['the']), Tree('JJ', ['quick']), Tree('JJ', ['brown']), Tree('NN', ['fox'])]), Tree('NP', [Tree('NP', [Tree('NNS', ['jumps'])]), Tree('PP', [Tree('IN', ['over']), Tree('NP', [Tree('DT', ['the']), Tree('JJ', ['lazy']), Tree('NN', ['dog'])])])])])]), Tree('ROOT', [Tree('NP', [Tree('NP', [Tree('DT', ['the']), Tree('JJ', ['quick']), Tree('JJ', ['grey']), Tree('NN', ['wolf'])]), Tree('NP', [Tree('NP', [Tree('NNS', ['jumps'])]), Tree('PP', [Tree('IN', ['over']), Tree('NP', [Tree('DT', ['the']), Tree('JJ', ['lazy']), Tree('NN', ['fox'])])])])])])] >>> sum([list(dep_graphs) for dep_graphs in parser.parse_sents(( ... "I 'm a dog".split(), ... "This is my friends ' cat ( the tabby )".split(), ... ))], []) # doctest: +NORMALIZE_WHITESPACE +SKIP [Tree('ROOT', [Tree('S', [Tree('NP', [Tree('PRP', ['I'])]), Tree('VP', [Tree('VBP', ["'m"]), Tree('NP', [Tree('DT', ['a']), Tree('NN', ['dog'])])])])]), Tree('ROOT', [Tree('S', [Tree('NP', [Tree('DT', ['This'])]), Tree('VP', [Tree('VBZ', ['is']), Tree('NP', [Tree('NP', [Tree('NP', [Tree('PRP$', ['my']), Tree('NNS', ['friends']), Tree('POS', ["'"])]), Tree('NN', ['cat'])]), Tree('PRN', [Tree('-LRB-', [Tree('', []), Tree('NP', [Tree('DT', ['the']), Tree('NN', ['tabby'])]), Tree('-RRB-', [])])])])])])])] >>> sum([list(dep_graphs) for dep_graphs in parser.tagged_parse_sents(( ... ( ... ("The", "DT"), ... ("quick", "JJ"), ... ("brown", "JJ"), ... ("fox", "NN"), ... ("jumped", "VBD"), ... ("over", "IN"), ... ("the", "DT"), ... ("lazy", "JJ"), ... ("dog", "NN"), ... (".", "."), ... ), ... ))],[]) # doctest: +NORMALIZE_WHITESPACE +SKIP [Tree('ROOT', [Tree('S', [Tree('NP', [Tree('DT', ['The']), Tree('JJ', ['quick']), Tree('JJ', ['brown']), Tree('NN', ['fox'])]), Tree('VP', [Tree('VBD', ['jumped']), Tree('PP', [Tree('IN', ['over']), Tree('NP', [Tree('DT', ['the']), Tree('JJ', ['lazy']), Tree('NN', ['dog'])])])]), Tree('.', ['.'])])])] pennc&tjdtddtj|i|dS)NzcThe StanfordParser will be deprecated Please use nltk.parse.corenlp.CoreNLPParser instead. stacklevelwarningswarnDeprecationWarningsuperr7r0argskwargs __class__rr!r7F zStanfordParser.__init__cCs t|Sr)r fromstringr0resultrrr!r=Ps zStanfordParser._make_treerrrrrTr7r= __classcell__rrrr!rs 2  rcr)StanfordDependencyParsera >>> dep_parser=StanfordDependencyParser( ... model_path="edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz" ... ) # doctest: +SKIP >>> [parse.tree() for parse in dep_parser.raw_parse("The quick brown fox jumps over the lazy dog.")] # doctest: +NORMALIZE_WHITESPACE +SKIP [Tree('jumps', [Tree('fox', ['The', 'quick', 'brown']), Tree('dog', ['over', 'the', 'lazy'])])] >>> [list(parse.triples()) for parse in dep_parser.raw_parse("The quick brown fox jumps over the lazy dog.")] # doctest: +NORMALIZE_WHITESPACE +SKIP [[((u'jumps', u'VBZ'), u'nsubj', (u'fox', u'NN')), ((u'fox', u'NN'), u'det', (u'The', u'DT')), ((u'fox', u'NN'), u'amod', (u'quick', u'JJ')), ((u'fox', u'NN'), u'amod', (u'brown', u'JJ')), ((u'jumps', u'VBZ'), u'nmod', (u'dog', u'NN')), ((u'dog', u'NN'), u'case', (u'over', u'IN')), ((u'dog', u'NN'), u'det', (u'the', u'DT')), ((u'dog', u'NN'), u'amod', (u'lazy', u'JJ'))]] >>> sum([[parse.tree() for parse in dep_graphs] for dep_graphs in dep_parser.raw_parse_sents(( ... "The quick brown fox jumps over the lazy dog.", ... "The quick grey wolf jumps over the lazy fox." ... ))], []) # doctest: +NORMALIZE_WHITESPACE +SKIP [Tree('jumps', [Tree('fox', ['The', 'quick', 'brown']), Tree('dog', ['over', 'the', 'lazy'])]), Tree('jumps', [Tree('wolf', ['The', 'quick', 'grey']), Tree('fox', ['over', 'the', 'lazy'])])] >>> sum([[parse.tree() for parse in dep_graphs] for dep_graphs in dep_parser.parse_sents(( ... "I 'm a dog".split(), ... "This is my friends ' cat ( the tabby )".split(), ... ))], []) # doctest: +NORMALIZE_WHITESPACE +SKIP [Tree('dog', ['I', "'m", 'a']), Tree('cat', ['This', 'is', Tree('friends', ['my', "'"]), Tree('tabby', ['the'])])] >>> sum([[list(parse.triples()) for parse in dep_graphs] for dep_graphs in dep_parser.tagged_parse_sents(( ... ( ... ("The", "DT"), ... ("quick", "JJ"), ... ("brown", "JJ"), ... ("fox", "NN"), ... ("jumped", "VBD"), ... ("over", "IN"), ... ("the", "DT"), ... ("lazy", "JJ"), ... ("dog", "NN"), ... (".", "."), ... ), ... ))],[]) # doctest: +NORMALIZE_WHITESPACE +SKIP [[((u'jumped', u'VBD'), u'nsubj', (u'fox', u'NN')), ((u'fox', u'NN'), u'det', (u'The', u'DT')), ((u'fox', u'NN'), u'amod', (u'quick', u'JJ')), ((u'fox', u'NN'), u'amod', (u'brown', u'JJ')), ((u'jumped', u'VBD'), u'nmod', (u'dog', u'NN')), ((u'dog', u'NN'), u'case', (u'over', u'IN')), ((u'dog', u'NN'), u'det', (u'the', u'DT')), ((u'dog', u'NN'), u'amod', (u'lazy', u'JJ'))]] conll2007cr)NzwThe StanfordDependencyParser will be deprecated Please use nltk.parse.corenlp.CoreNLPDependencyParser instead.rrrrrrr!r7rz!StanfordDependencyParser.__init__cC t|ddS)Nroottop_relation_labelr rrrr!r= z#StanfordDependencyParser._make_treerrrrr!rTs 0  rcsJeZdZdZdZdZdZdZdZdZ fddZ dd d Z d d Z Z S)StanfordNeuralDependencyParserar >>> from nltk.parse.stanford import StanfordNeuralDependencyParser # doctest: +SKIP >>> dep_parser=StanfordNeuralDependencyParser(java_options='-mx4g')# doctest: +SKIP >>> [parse.tree() for parse in dep_parser.raw_parse("The quick brown fox jumps over the lazy dog.")] # doctest: +NORMALIZE_WHITESPACE +SKIP [Tree('jumps', [Tree('fox', ['The', 'quick', 'brown']), Tree('dog', ['over', 'the', 'lazy']), '.'])] >>> [list(parse.triples()) for parse in dep_parser.raw_parse("The quick brown fox jumps over the lazy dog.")] # doctest: +NORMALIZE_WHITESPACE +SKIP [[((u'jumps', u'VBZ'), u'nsubj', (u'fox', u'NN')), ((u'fox', u'NN'), u'det', (u'The', u'DT')), ((u'fox', u'NN'), u'amod', (u'quick', u'JJ')), ((u'fox', u'NN'), u'amod', (u'brown', u'JJ')), ((u'jumps', u'VBZ'), u'nmod', (u'dog', u'NN')), ((u'dog', u'NN'), u'case', (u'over', u'IN')), ((u'dog', u'NN'), u'det', (u'the', u'DT')), ((u'dog', u'NN'), u'amod', (u'lazy', u'JJ')), ((u'jumps', u'VBZ'), u'punct', (u'.', u'.'))]] >>> sum([[parse.tree() for parse in dep_graphs] for dep_graphs in dep_parser.raw_parse_sents(( ... "The quick brown fox jumps over the lazy dog.", ... "The quick grey wolf jumps over the lazy fox." ... ))], []) # doctest: +NORMALIZE_WHITESPACE +SKIP [Tree('jumps', [Tree('fox', ['The', 'quick', 'brown']), Tree('dog', ['over', 'the', 'lazy']), '.']), Tree('jumps', [Tree('wolf', ['The', 'quick', 'grey']), Tree('fox', ['over', 'the', 'lazy']), '.'])] >>> sum([[parse.tree() for parse in dep_graphs] for dep_graphs in dep_parser.parse_sents(( ... "I 'm a dog".split(), ... "This is my friends ' cat ( the tabby )".split(), ... ))], []) # doctest: +NORMALIZE_WHITESPACE +SKIP [Tree('dog', ['I', "'m", 'a']), Tree('cat', ['This', 'is', Tree('friends', ['my', "'"]), Tree('tabby', ['-LRB-', 'the', '-RRB-'])])] conllz)edu.stanford.nlp.pipeline.StanfordCoreNLPz%stanford-corenlp-(\d+)(\.(\d+))+\.jarz,stanford-corenlp-(\d+)(\.(\d+))+-models\.jarTcs4tjdtddtj|i||jd7_dS)Nz}The StanfordNeuralDependencyParser will be deprecated Please use nltk.parse.corenlp.CoreNLPDependencyParser instead.rrz(-annotators tokenize,ssplit,pos,depparse)rrrrr7r.rrrr!r7sz'StanfordNeuralDependencyParser.__init__FcCstd)z Currently unimplemented because the neural dependency parser (and the StanfordCoreNLP pipeline class) doesn't support passing in pre- tagged tokens. zxtagged_parse[_sents] is not supported by StanfordNeuralDependencyParser; use parse[_sents] or raw_parse[_sents] instead.)NotImplementedError)r0rWrrrr!r`sz1StanfordNeuralDependencyParser.tagged_parse_sentscCr)NROOTrr rrrr!r=rz)StanfordNeuralDependencyParser._make_treer)rrrrrTrSr'r)rxr<r7r`r=rrrrr!rs   r)rrqr subprocessrnltk.internalsrrrrrnltk.parse.apirnltk.parse.dependencygraphr nltk.treer r(r rrrrrrr!s    vCA