o il?@sddlZddlZddlZddlZddlZddlmZddlmZm Z m Z ddl m Z ddl mZddlmZddZd d Zd d ZGd dde ZedkrY ddlZedSdS)N)ZipFilePathPointer)find_dir find_filefind_jars_within_path)ParserI)DependencyGraph)taggedsents_to_conllcCsddlm}|gd}|jS)Nr) RegexpTagger))z\.$.)z\,$,)z\?$?)z\($()z\)$))z\[$[)z\]$])z^-?[0-9]+(\.[0-9]+)?$CD)z(The|the|A|a|An|an)$DT)z&(He|he|She|she|It|it|I|me|Me|You|you)$PRP)z(His|his|Her|her|Its|its)$PRP$)z(my|Your|your|Yours|yours)$r)z (on|On|in|In|at|At|since|Since)$IN)z (for|For|ago|Ago|before|Before)$r)z(till|Till|until|Until)$r)z(by|By|beside|Beside)$r)z(under|Under|below|Below)$r)z(over|Over|above|Above)$r)z (across|Across|through|Through)$r)z(into|Into|towards|Towards)$r)z(onto|Onto|from|From)$r)z.*able$JJ)z.*ness$NN)z.*ly$RB)z.*s$NNS)z.*ing$VBG)z.*ed$VBD)z.*r)nltk.tagr tag)r _taggerrJ/var/www/edux/Edux_v2/venv/lib/python3.10/site-packages/nltk/parse/malt.pymalt_regex_taggers  r!cCsttj|r |}nt|dd}gd}tt|}dd|D}hd}||s+Jttdd|s6Jt |S) zE A module to find MaltParser .jar file and its dependencies. ) MALT_PARSER)env_vars)r$r$cSsh|] }tj|dqS))ospathsplit).0jarrrr Hsz"find_maltparser..> log4j.jar libsvm.jarliblinear-1.8.jarcSs|do |dS)Nz maltparser-z.jar) startswithendswith)irrr Msz!find_maltparser..) r&r'existsrsetrissubsetanyfilterlist)parser_dirname _malt_dirmalt_dependencies _malt_jars_jarsrrr find_maltparser=s    r>cCs*|durdStj|r|St|dddS)z8 A module to find pre-trained MaltParser model. N malt_temp.mco) MALT_MODELF)r#verbose)r&r'r3r)model_filenamerrr find_malt_modelRs  rCc@sbeZdZdZ    dddZddd Zdd d Zdd d ZedddZ dddZ dddZ dS) MaltParsera A class for dependency parsing with MaltParser. The input is the paths to: - (optionally) a maltparser directory - (optionally) the path to a pre-trained MaltParser .mco model file - (optionally) the tagger to use for POS tagging before parsing - (optionally) additional Java arguments Example: >>> from nltk.parse import malt >>> # With MALT_PARSER and MALT_MODEL environment set. >>> mp = malt.MaltParser(model_filename='engmalt.linear-1.7.mco') # doctest: +SKIP >>> mp.parse_one('I shot an elephant in my pajamas .'.split()).tree() # doctest: +SKIP (shot I (elephant an) (in (pajamas my)) .) >>> # Without MALT_PARSER and MALT_MODEL environment. >>> mp = malt.MaltParser('/home/user/maltparser-1.9.2/', '/home/user/engmalt.linear-1.7.mco') # doctest: +SKIP >>> mp.parse_one('I shot an elephant in my pajamas .'.split()).tree() # doctest: +SKIP (shot I (elephant an) (in (pajamas my)) .) r$NcCsZt||_|dur |ng|_t||_|jdk|_t|_|dur'||_ dSt |_ dS)a An interface for parsing with the Malt Parser. :param parser_dirname: The path to the maltparser directory that contains the maltparser-1.x.jar :type parser_dirname: str :param model_filename: The name of the pre-trained model with .mco file extension. If provided, training will not be required. (see http://www.maltparser.org/mco/mco.html and see http://www.patful.com/chalk/node/185) :type model_filename: str :param tagger: The tagger used to POS tag the raw string before formatting to CONLL format. It should behave like `nltk.pos_tag` :type tagger: function :param additional_java_args: This is the additional Java arguments that one can use when calling Maltparser, usually this is the heapsize limits, e.g. `additional_java_args=['-Xmx1024m']` (see https://javarevisited.blogspot.com/2011/05/java-heap-space-memory-size-jvm.html) :type additional_java_args: list Nr?) r> malt_jarsadditional_java_argsrCmodel_trainedtempfile gettempdir working_dirr!tagger)selfr9rBrLrFrrr __init__rs    zMaltParser.__init__Fnullc cs|jstdtjd|jddd}tjd|jddd~}t|D] }|t|q"||j |j |j dd}t }zt t j|jd WnY|||} t || d krktd d || ft|j } | d D] } tt| |d gVqxWdn1swYWdn1swYWdn1swYt |j t |j dS)a Use MaltParser to parse multiple POS tagged 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 sentence: list(list(tuple(str, str))) :return: iter(iter(``DependencyGraph``)) the dependency graph representation of each sentence z0Parser has not been trained. Call train() first.zmalt_input.conll.wFprefixdirmodedeletezmalt_output.conll.parserTrz0MaltParser parsing (%s) failed with exit code %d z top_relation_labelN)rH ExceptionrINamedTemporaryFilerKrwritestrclosegenerate_malt_commandnamer&getcwdchdirr'r(rG_executejoinopenreaditerrremove) rM sentencesrArZ input_file output_filelinecmd _current_pathretinfiletree_strrrr parse_tagged_sentssd         1zMaltParser.parse_tagged_sentscs"fdd|D}j|||dS)an Use MaltParser to parse multiple sentences. Takes a list of sentences, where each sentence is a list of words. Each sentence will be automatically tagged with this MaltParser instance's tagger. :param sentences: Input sentences to parse :type sentence: list(list(str)) :return: iter(DependencyGraph) c3s|]}|VqdS)N)rL)r)sentencerMrr z)MaltParser.parse_sents..rY)rs)rMrjrArZtagged_sentencesrrur parse_sentss zMaltParser.parse_sentscCsdg}||j7}tjdrdnd}|d||jg7}|dg7}tj|j r6|dtj |j dg7}n|d|j g7}|d |g7}|d krM|d |g7}|d |g7}|S) a This function generates the maltparser command use at the terminal. :param inputfilename: path to the input file :type inputfilename: str :param outputfilename: path to the output file :type outputfilename: str javawin;:z-cpzorg.maltparser.Maltz-cz-irVz-oz-m) rFsysplatformr/rerEr&r'r3rGr()rM inputfilenameoutputfilenamerTrnclasspaths_separatorrrr r`s       z MaltParser.generate_malt_commandcCs&|rdntj}tj|||d}|S)N)stdoutstderr) subprocessPIPEPopenwait)rnrAoutputprrr rdszMaltParser._executecCsvtjd|jddd}ddd|D}|t|Wdn1s&wY|j|j|d t |jdS) z Train MaltParser from a list of ``DependencyGraph`` objects :param depgraphs: list of ``DependencyGraph`` objects for training input data :type depgraphs: DependencyGraph malt_train.conll.rPFrQ css|]}|dVqdS) N)to_conll)r)dgrrr rv rwz#MaltParser.train..NrA) rIr\rKrer]r^train_from_filerar&ri)rM depgraphsrArk input_strrrr trains zMaltParser.trainc Cst|trFtjd|jddd/}|}|}|t|Wdn1s*wY|j |j |dWdS1sAwY|j |dd}| ||}|d krbt d d ||fd |_dS) z Train MaltParser from a file :param conll_file: str for the filename of the training input data :type conll_file: str rrPFrQNrlearnrWrz1MaltParser training (%s) failed with exit code %drXT) isinstancerrIr\rKrfrgr]r^rrar`rdr[rerH)rM conll_filerArkconll_input_file conll_strrnrprrr r's(       zMaltParser.train_from_file)r$NNN)FrO)NN)F) __name__ __module__ __qualname____doc__rNrsryr` staticmethodrdrrrrrr rD^s * B   rD__main__)inspectr&rrrI nltk.datarnltk.internalsrrrnltk.parse.apirnltk.parse.dependencygraphrnltk.parse.utilrr!r>rCrDrdoctesttestmodrrrr s(     & gB