g=iddlZddlZddlZddlZddlZddlmZmZddlm Z m Z m Z m Z ddl mZddlmZddlmZddlmZddlmZd ZGd d eZdd ZGd dZGddeeeZGddeZGddeZdZy)N)ListTuple) _java_options config_java find_jar_iterjava)ParserI)DependencyGraph)TaggerI) TokenizerI)Treez&https://stanfordnlp.github.io/CoreNLP/ceZdZdZy)CoreNLPServerErrorz/Exceptions associated with the Core NLP server.N)__name__ __module__ __qualname____doc__G/var/www/openai/venv/lib/python3.12/site-packages/nltk/parse/corenlp.pyrrs9rrctjtjtj}|jd|f|j d}|j |S)N)socketAF_INET SOCK_STREAMbind getsocknameclose)portsockps rtry_portr#sM ==);); z(CoreNLPServer.__init__..EsJ8Wr)keyi(#z-portzhttp://localhost:)CORENLP_MODELScDtjj|Sr.)r/r0_MODEL_JAR_PATTERNr2s rr5z(CoreNLPServer.__init__..]s288D,C,CZ#Prz-mx2g)listrr1 _stanford_urlmaxr#OSErrorextendstrr*r9r+ _classpathcorenlp_options java_options) r4 path_to_jarpath_to_models_jarr+rBrAr jars stanford_jar model_jars ` r__init__zCoreNLPServer.__init__,s  ")+UVO  %!   4%WX < =~ TN  " "GSY#7 8&tf- ''",! Q   & 1.(5WI7 =z&&T';< =s C/DDcddl}dg}|jr|j|jdjt}t |j |j t||jd|||_ t ||j|jj}|G|jj\}}t|dj|jd t!d D]F} |j#|j$j'|j(d } | j*sFn td t!dD]F} |j#|j$j'|j(d} | j*sFytd#t ||jwxYw#|j,j.$rt1j2d YwxYw#|j,j.$rt1j2d YwxYw)zStarts the CoreNLP server :param stdout, stderr: Specifies where CoreNLP output is redirected. Valid values are 'devnull', 'stdout', 'pipe' rNz/edu.stanford.nlp.pipeline.StanfordCoreNLPServer )optionsr+F) classpathblockingstdoutstderrz-Could not start the server. The error was: {}asciiliverz Could not connect to the server.<readyzThe server is not ready.)requestsrAr>joinrrrBr+rr@popenpoll communicaterformatdecoderangegetcompaturljoinr*ok exceptionsConnectionErrortimesleep) r4rNrOrUcmddefault_options returncode_ stderrdatairesponses rstartzCoreNLPServer.startgs @A    JJt++ ,((=1D--t||D G// DJ  FZZ__&  ! JJ224MAz$$$*F:+<+=H>cl|jj|jjyr.)rW terminatewaitr4s rstopzCoreNLPServer.stops   rc&|j|Sr.)rlrps r __enter__zCoreNLPServer.__enter__s  rc$|jy)NF)rq)r4exc_typeexc_valexc_tbs r__exit__zCoreNLPServer.__exit__s r)NNFNNN)devnullry) rrrr9r1rHrlrqrsrxrrrr%r%(s=L 7D 96v:Ax rr%czeZdZdZ ddZdZddZddZ ddZdZ dd Z d Z d e d e ee e ffd ZdZy)GenericCoreNLPParserz Interface to the CoreNLP Parser.Ncddl}||_||_|dvr td||_||_|j |_y)Nr)posnerNz+tagtype must be either 'pos', 'ner' or None)rUr*encoding ValueErrortagtype strict_jsonSessionsession)r4r*rrrrUs rrHzGenericCoreNLPParser.__init__sI   . .JK K &'') rc@d|D}|j|g|i|S)aParse multiple sentences. Takes multiple sentences as a list where each sentence is a list of words. Each sentence will be automatically tagged with this CoreNLPParser instance's tagger. If a whitespace exists inside a token, then the token will be treated as several tokens. :param sentences: Input sentences to parse :type sentences: list(list(str)) :rtype: iter(iter(Tree)) c3>K|]}dj|ywrJNrV.0wordss r z3GenericCoreNLPParser.parse_sents..<)SXXe_))raw_parse_sents)r4 sentencesargskwargss r parse_sentsz GenericCoreNLPParser.parse_sentss+=)< #t##I????rcxddi}|j|xsit|j|gg|d|i|S)aParse a sentence. Takes a sentence as a string; before parsing, it will be automatically tokenized and tagged by the CoreNLP Parser. :param sentence: Input sentence to parse :type sentence: str :rtype: iter(Tree) ztokenize.whitespacefalse properties)updatenextr)r4sentencerrrdefault_propertiess r raw_parsezGenericCoreNLPParser.raw_parses\4W=!!*"23 D   <@ '9 DJ   rcddj|jd}|j|xsi|jj |j dt j|i|j|jdd|ji|}|j|j |j S) Njsonz,tokenize,pos,lemma,ssplit,{parser_annotator})parser_annotator) outputFormat annotatorsrz Content-Typeztext/plain; charset=)paramsdataheaderstimeout)strict) rZrrrpostr*rdumpsencoderraise_for_statusr)r4rrrrrks rapi_callzGenericCoreNLPParser.api_calls"HOO!%!6!6P  !!*"23<<$$ HH $**-?"@AT]]+#';DMM?%KL %  !!#}}D$4$4}55rc/Kddi}|j|xsi |jdj||}|dD]!}|j|} t | g#yw)aParse multiple sentences. Takes multiple sentences as a list of strings. Each sentence will be automatically tokenized and tagged. :param sentences: Input sentences to parse. :type sentences: list(str) :rtype: iter(iter(Tree)) zssplit.eolonlytrue rrN)rrrV make_treeiter) r4rr+rrrr parsed_data parsed_senttrees rrz$GenericCoreNLPParser.raw_parse_sentssv f  !!*"23 mmDIIi$8EWmX &{3K>>+.Dv, 4sA'A)c/rK|j|g|i|}|dD]}|j|yw)aParse a piece of text. The text might contain several sentences which will be split by CoreNLP. :param str text: text to be split. :returns: an iterable of syntactic structures. # TODO: should it be an iterable of iterables? rN)rr)r4textrrrparses r parse_textzGenericCoreNLPParser.parse_text&s@$dmmD:4:6:  -E..' '.s57c#Kddi}|j|xsi|j||}|dD]}|dD]}|dxs|dyw) aTokenize a string of text. Skip these tests if CoreNLP is likely not ready. >>> from nltk.test.setup_fixt import check_jar >>> check_jar(CoreNLPServer._JAR, env_vars=("CORENLP",), is_regex=True) The CoreNLP server can be started using the following notation, although we recommend the `with CoreNLPServer() as server:` context manager notation to ensure that the server is always stopped. >>> server = CoreNLPServer() >>> server.start() >>> parser = CoreNLPParser(url=server.url) >>> text = 'Good muffins cost $3.88\nin New York. Please buy me\ntwo of them.\nThanks.' >>> list(parser.tokenize(text)) ['Good', 'muffins', 'cost', '$', '3.88', 'in', 'New', 'York', '.', 'Please', 'buy', 'me', 'two', 'of', 'them', '.', 'Thanks', '.'] >>> s = "The colour of the wall is blue." >>> list( ... parser.tokenize( ... 'The colour of the wall is blue.', ... properties={'tokenize.options': 'americanize=true'}, ... ) ... ) ['The', 'colour', 'of', 'the', 'wall', 'is', 'blue', '.'] >>> server.stop() rztokenize,ssplitrrtokens originalTextwordN)rr)r4rrrresultrtokens rtokenizezGenericCoreNLPParser.tokenize4sl:+,=>!!*"23t0BC{+H!(+N+K|]}dj|ywrrrs rrz1GenericCoreNLPParser.tag_sents..grrr) raw_tag_sents)r4rs r tag_sentszGenericCoreNLPParser.tag_sents[s7=)< .2.@.@.KL.K ! .KLLLs ,rreturnc,|j|gdS)ay Tag a list of tokens. :rtype: list(tuple(str, str)) Skip these tests if CoreNLP is likely not ready. >>> from nltk.test.setup_fixt import check_jar >>> check_jar(CoreNLPServer._JAR, env_vars=("CORENLP",), is_regex=True) The CoreNLP server can be started using the following notation, although we recommend the `with CoreNLPServer() as server:` context manager notation to ensure that the server is always stopped. >>> server = CoreNLPServer() >>> server.start() >>> parser = CoreNLPParser(url=server.url, tagtype='ner') >>> tokens = 'Rami Eid is studying at Stony Brook University in NY'.split() >>> parser.tag(tokens) # doctest: +NORMALIZE_WHITESPACE [('Rami', 'PERSON'), ('Eid', 'PERSON'), ('is', 'O'), ('studying', 'O'), ('at', 'O'), ('Stony', 'ORGANIZATION'), ('Brook', 'ORGANIZATION'), ('University', 'ORGANIZATION'), ('in', 'O'), ('NY', 'STATE_OR_PROVINCE')] >>> parser = CoreNLPParser(url=server.url, tagtype='pos') >>> tokens = "What is the airspeed of an unladen swallow ?".split() >>> parser.tag(tokens) # doctest: +NORMALIZE_WHITESPACE [('What', 'WP'), ('is', 'VBZ'), ('the', 'DT'), ('airspeed', 'NN'), ('of', 'IN'), ('an', 'DT'), ('unladen', 'JJ'), ('swallow', 'VB'), ('?', '.')] >>> server.stop() r)r)r4rs rtagzGenericCoreNLPParser.tagjs:~~xj)!,,rc #"Kddd}|jdvsJ|dxx|jz cc<|D]O}|j||}|dDcgc]'}|dDcgc]}|d ||jfc})c}}Qy cc}wcc}}ww) z Tag multiple sentences. Takes multiple sentences as a list where each sentence is a string. :param sentences: Input sentences to tag :type sentences: list(str) :rtype: list(list(list(tuple(str, str))) rztokenize,ssplit,)zssplit.isOneSentencer)r}r~rrrrrN)rr)r4rrr tagged_datatagged_sentencers rrz"GenericCoreNLPParser.raw_tag_sentss%+,  ||~---<(DLL8(!H--=O-PK (3;'?  (@O"1!:!:6]E$,,$78!:(@  "s*A B B B6B ; BB  B)zhttp://localhost:9000utf8NTr.)NrS)FN)rrrrrHrrrrrrrr?rrrrrrrr{r{si* $ *(@$ &6.48!F (%=N M-C-DsCx$9->rr{ceZdZdZdZdZdZy) CoreNLPParseru Skip these tests if CoreNLP is likely not ready. >>> from nltk.test.setup_fixt import check_jar >>> check_jar(CoreNLPServer._JAR, env_vars=("CORENLP",), is_regex=True) The recommended usage of `CoreNLPParser` is using the context manager notation: >>> with CoreNLPServer() as server: ... parser = CoreNLPParser(url=server.url) ... next( ... parser.raw_parse('The quick brown fox jumps over the lazy dog.') ... ).pretty_print() # doctest: +NORMALIZE_WHITESPACE ROOT | S _______________|__________________________ | VP | | _________|___ | | | PP | | | ________|___ | NP | | NP | ____|__________ | | _______|____ | DT JJ JJ NN VBZ IN DT JJ NN . | | | | | | | | | | The quick brown fox jumps over the lazy dog . Alternatively, the server can be started using the following notation. Note that `CoreNLPServer` does not need to be used if the CoreNLP server is started outside of Python. >>> server = CoreNLPServer() >>> server.start() >>> parser = CoreNLPParser(url=server.url) >>> (parse_fox, ), (parse_wolf, ) = parser.raw_parse_sents( ... [ ... 'The quick brown fox jumps over the lazy dog.', ... 'The quick grey wolf jumps over the lazy fox.', ... ] ... ) >>> parse_fox.pretty_print() # doctest: +NORMALIZE_WHITESPACE ROOT | S _______________|__________________________ | VP | | _________|___ | | | PP | | | ________|___ | NP | | NP | ____|__________ | | _______|____ | DT JJ JJ NN VBZ IN DT JJ NN . | | | | | | | | | | The quick brown fox jumps over the lazy dog . >>> parse_wolf.pretty_print() # doctest: +NORMALIZE_WHITESPACE ROOT | S _______________|__________________________ | VP | | _________|___ | | | PP | | | ________|___ | NP | | NP | ____|_________ | | _______|____ | DT JJ JJ NN VBZ IN DT JJ NN . | | | | | | | | | | The quick grey wolf jumps over the lazy fox . >>> (parse_dog, ), (parse_friends, ) = parser.parse_sents( ... [ ... "I 'm a dog".split(), ... "This is my friends ' cat ( the tabby )".split(), ... ] ... ) >>> parse_dog.pretty_print() # doctest: +NORMALIZE_WHITESPACE ROOT | S _______|____ | VP | ________|___ NP | NP | | ___|___ PRP VBP DT NN | | | | I 'm a dog >>> parse_friends.pretty_print() # doctest: +NORMALIZE_WHITESPACE ROOT | S ____|___________ | VP | ___________|_____________ | | NP | | _______|________________________ | | NP | | | | | _____|_______ | | | NP | NP | | NP | | | ______|_________ | | ___|____ | DT VBZ PRP$ NNS POS NN -LRB- DT NN -RRB- | | | | | | | | | | This is my friends ' cat -LRB- the tabby -RRB- >>> parse_john, parse_mary, = parser.parse_text( ... 'John loves Mary. Mary walks.' ... ) >>> parse_john.pretty_print() # doctest: +NORMALIZE_WHITESPACE ROOT | S _____|_____________ | VP | | ____|___ | NP | NP | | | | | NNP VBZ NNP . | | | | John loves Mary . >>> parse_mary.pretty_print() # doctest: +NORMALIZE_WHITESPACE ROOT | S _____|____ NP VP | | | | NNP VBZ . | | | Mary walks . Special cases >>> next( ... parser.raw_parse( ... 'NASIRIYA, Iraq—Iraqi doctors who treated former prisoner of war ' ... 'Jessica Lynch have angrily dismissed claims made in her biography ' ... 'that she was raped by her Iraqi captors.' ... ) ... ).height() 14 >>> next( ... parser.raw_parse( ... "The broader Standard & Poor's 500 Index <.SPX> was 0.46 points lower, or " ... '0.05 percent, at 997.02.' ... ) ... ).height() 11 >>> server.stop() pennrc2tj|dS)Nr)r fromstringr4rs rrzCoreNLPParser.make_treeFsvg//rNrrrr_OUTPUT_FORMATrrrrrrrsZxN0rrceZdZdZdZdZdZy)CoreNLPDependencyParseraDependency parser. Skip these tests if CoreNLP is likely not ready. >>> from nltk.test.setup_fixt import check_jar >>> check_jar(CoreNLPServer._JAR, env_vars=("CORENLP",), is_regex=True) The recommended usage of `CoreNLPParser` is using the context manager notation: >>> with CoreNLPServer() as server: ... dep_parser = CoreNLPDependencyParser(url=server.url) ... parse, = dep_parser.raw_parse( ... 'The quick brown fox jumps over the lazy dog.' ... ) ... print(parse.to_conll(4)) # doctest: +NORMALIZE_WHITESPACE The DT 4 det quick JJ 4 amod brown JJ 4 amod fox NN 5 nsubj jumps VBZ 0 ROOT over IN 9 case the DT 9 det lazy JJ 9 amod dog NN 5 obl . . 5 punct Alternatively, the server can be started using the following notation. Note that `CoreNLPServer` does not need to be used if the CoreNLP server is started outside of Python. >>> server = CoreNLPServer() >>> server.start() >>> dep_parser = CoreNLPDependencyParser(url=server.url) >>> parse, = dep_parser.raw_parse('The quick brown fox jumps over the lazy dog.') >>> print(parse.tree()) # doctest: +NORMALIZE_WHITESPACE (jumps (fox The quick brown) (dog over the lazy) .) >>> for governor, dep, dependent in parse.triples(): ... print(governor, dep, dependent) # doctest: +NORMALIZE_WHITESPACE ('jumps', 'VBZ') nsubj ('fox', 'NN') ('fox', 'NN') det ('The', 'DT') ('fox', 'NN') amod ('quick', 'JJ') ('fox', 'NN') amod ('brown', 'JJ') ('jumps', 'VBZ') obl ('dog', 'NN') ('dog', 'NN') case ('over', 'IN') ('dog', 'NN') det ('the', 'DT') ('dog', 'NN') amod ('lazy', 'JJ') ('jumps', 'VBZ') punct ('.', '.') >>> (parse_fox, ), (parse_dog, ) = dep_parser.raw_parse_sents( ... [ ... 'The quick brown fox jumps over the lazy dog.', ... 'The quick grey wolf jumps over the lazy fox.', ... ] ... ) >>> print(parse_fox.to_conll(4)) # doctest: +NORMALIZE_WHITESPACE The DT 4 det quick JJ 4 amod brown JJ 4 amod fox NN 5 nsubj jumps VBZ 0 ROOT over IN 9 case the DT 9 det lazy JJ 9 amod dog NN 5 obl . . 5 punct >>> print(parse_dog.to_conll(4)) # doctest: +NORMALIZE_WHITESPACE The DT 4 det quick JJ 4 amod grey JJ 4 amod wolf NN 5 nsubj jumps VBZ 0 ROOT over IN 9 case the DT 9 det lazy JJ 9 amod fox NN 5 obl . . 5 punct >>> (parse_dog, ), (parse_friends, ) = dep_parser.parse_sents( ... [ ... "I 'm a dog".split(), ... "This is my friends ' cat ( the tabby )".split(), ... ] ... ) >>> print(parse_dog.to_conll(4)) # doctest: +NORMALIZE_WHITESPACE I PRP 4 nsubj 'm VBP 4 cop a DT 4 det dog NN 0 ROOT >>> print(parse_friends.to_conll(4)) # doctest: +NORMALIZE_WHITESPACE This DT 6 nsubj is VBZ 6 cop my PRP$ 4 nmod:poss friends NNS 6 nmod:poss ' POS 4 case cat NN 0 ROOT ( -LRB- 9 punct the DT 9 det tabby NN 6 dep ) -RRB- 9 punct >>> parse_john, parse_mary, = dep_parser.parse_text( ... 'John loves Mary. Mary walks.' ... ) >>> print(parse_john.to_conll(4)) # doctest: +NORMALIZE_WHITESPACE John NNP 2 nsubj loves VBZ 0 ROOT Mary NNP 2 obj . . 2 punct >>> print(parse_mary.to_conll(4)) # doctest: +NORMALIZE_WHITESPACE Mary NNP 2 nsubj walks VBZ 0 ROOT . . 2 punct Special cases Non-breaking space inside of a token. >>> len( ... next( ... dep_parser.raw_parse( ... 'Anhalt said children typically treat a 20-ounce soda bottle as one ' ... 'serving, while it actually contains 2 1/2 servings.' ... ) ... ).nodes ... ) 23 Phone numbers. >>> len( ... next( ... dep_parser.raw_parse('This is not going to crash: 01 111 555.') ... ).nodes ... ) 10 >>> print( ... next( ... dep_parser.raw_parse('The underscore _ should not simply disappear.') ... ).to_conll(4) ... ) # doctest: +NORMALIZE_WHITESPACE The DT 2 det underscore NN 7 nsubj _ NFP 7 punct should MD 7 aux not RB 7 advmod simply RB 7 advmod disappear VB 0 ROOT . . 7 punct >>> print( ... next( ... dep_parser.raw_parse( ... 'for all of its insights into the dream world of teen life , and its electronic expression through ' ... 'cyber culture , the film gives no quarter to anyone seeking to pull a cohesive story out of its 2 ' ... '1/2-hour running time .' ... ) ... ).to_conll(4) ... ) # doctest: +NORMALIZE_WHITESPACE +ELLIPSIS for IN 2 case all DT 24 obl of IN 5 case its PRP$ 5 nmod:poss insights NNS 2 nmod into IN 9 case the DT 9 det dream NN 9 compound world NN 5 nmod of IN 12 case teen NN 12 compound ... >>> server.stop() conll2007depparsecNtdtt|DdS)Nc3DK|]}dj|ddyw)rJrNr)rn_itemss rrz4CoreNLPDependencyParser.make_tree..s' 8G%8s rJ)cell_separator)r sorted transformrs rrz!CoreNLPDependencyParser.make_trees+ %i&78    rNrrrrrrJsob!N! rrc #K|dD]<}|d}|d|dz }|d|d|d|d|ddt|d |d ddf >yw) NbasicDependencies dependentrrrhrlemmar}governordep)r?)r dependencydependent_indexrs rrr s23 $[1"?Q#67   &M 'N %L %L   :& ' u     4sAA)r) rosr/rrctypingrrnltk.internalsrrrrnltk.parse.apir nltk.parse.dependencygraphr nltk.tag.apir nltk.tokenize.apir nltk.treer r;EnvironmentErrorrr#r%r{rrrrrrrs JJ"6 (8 :): FFRr7Jrja0(a0H| 2| ~ r