:j dZddlmZddlmZmZmZddlmZm Z ddl m Z m Z ddl mZ ddZd Zd ZGd d Zdd Zy)z Utility functions for parsers. )load)CFGPCFGFeatureGrammar)Chart ChartParser) FeatureChartFeatureChartParser)InsideChartParserNc "t|fi|}t|ts tdt|tr|t }||||St|t r|t}|t}||||S|t}|t}||||S)a Load a grammar from a file, and build a parser based on that grammar. The parser depends on the grammar format, and might also depend on properties of the grammar itself. The following grammar formats are currently supported: - ``'cfg'`` (CFGs: ``CFG``) - ``'pcfg'`` (probabilistic CFGs: ``PCFG``) - ``'fcfg'`` (feature-based CFGs: ``FeatureGrammar``) :type grammar_url: str :param grammar_url: A URL specifying where the grammar is located. The default protocol is ``"nltk:"``, which searches for the file in the the NLTK data package. :type trace: int :param trace: The level of tracing that should be used when parsing a text. ``0`` will generate no tracing output; and higher numbers will produce more verbose tracing output. :param parser: The class used for parsing; should be ``ChartParser`` or a subclass. If None, the class depends on the grammar format. :param chart_class: The class used for storing the chart; should be ``Chart`` or a subclass. Only used for CFGs and feature CFGs. If None, the chart class depends on the grammar format. :type beam_size: int :param beam_size: The maximum length for the parser's edge queue. Only used for probabilistic CFGs. :param load_args: Keyword parameters used when loading the grammar. See ``data.load`` for more information. z1The grammar must be a CFG, or a subclass thereof.)trace beam_size)r chart_class) r isinstancer ValueErrorrr rr r rr) grammar_urlr parserrr load_argsgrammars d/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/nltk/parse/util.py load_parserrsD;,),G gs #OPP'4 >&FgUi@@ G^ , >'F  &KgU DD > F  KgU DDc #Kt|dD]5\}\}}t||d||dddddg }dj|dz}|7yw) a A module to convert a single POS tagged sentence into CONLL format. >>> from nltk import word_tokenize, pos_tag >>> text = "This is a foobar sentence." >>> for line in taggedsent_to_conll(pos_tag(word_tokenize(text))): # doctest: +NORMALIZE_WHITESPACE ... print(line, end="") 1 This _ DT DT _ 0 a _ _ 2 is _ VBZ VBZ _ 0 a _ _ 3 a _ DT DT _ 0 a _ _ 4 foobar _ JJ JJ _ 0 a _ _ 5 sentence _ NN NN _ 0 a _ _ 6 . _ . . _ 0 a _ _ :param sentence: A single input sentence to parse :type sentence: list(tuple(str, str)) :rtype: iter(str) :return: a generator yielding a single sentence in CONLL format. )start_0a  N) enumeratestrjoin)sentenceiwordtag input_strs rtaggedsent_to_conllr)Os\($HA6;D#VT3S#sCcJ IIi(4/ sAA c#LK|D]}t|Ed{dy7 w)aV A module to convert the a POS tagged document stream (i.e. list of list of tuples, a list of sentences) and yield lines in CONLL format. This module yields one line per word and two newlines for end of sentence. >>> from nltk import word_tokenize, sent_tokenize, pos_tag >>> text = "This is a foobar sentence. Is that right?" >>> sentences = [pos_tag(word_tokenize(sent)) for sent in sent_tokenize(text)] >>> for line in taggedsents_to_conll(sentences): # doctest: +NORMALIZE_WHITESPACE ... if line: ... print(line, end="") 1 This _ DT DT _ 0 a _ _ 2 is _ VBZ VBZ _ 0 a _ _ 3 a _ DT DT _ 0 a _ _ 4 foobar _ JJ JJ _ 0 a _ _ 5 sentence _ NN NN _ 0 a _ _ 6 . _ . . _ 0 a _ _ 1 Is _ VBZ VBZ _ 0 a _ _ 2 that _ IN IN _ 0 a _ _ 3 right _ NN NN _ 0 a _ _ 4 ? _ . . _ 0 a _ _ :param sentences: Input sentences to parse :type sentence: list(list(tuple(str, str))) :rtype: iter(str) :return: a generator yielding sentences in CONLL format. Nz )r)) sentencesr$s rtaggedsents_to_conllr,is.B&x000 0s $" $c eZdZdZddZddZy) TestGrammarz Unit tests for CFG. Nc`||_t|d|_||_||_||_y)Nr)r ) test_grammarrcpsuite_accept_reject)selfrr2acceptrejects r__init__zTestGrammar.__init__s-#gQ/   rc|jD]}t|ddzddD]}||D]}|j}t|jj |}|r)|r'tt||D] }t||dk(r|gk(rt d|zd}}|rt d |zd} s std y ) a} Sentences in the test suite are divided into two classes: - grammatical (``accept``) and - ungrammatical (``reject``). If a sentence should parse according to the grammar, the value of ``trees`` will be a non-empty list. If a sentence should be rejected according to the grammar, then the value of ``trees`` will be None. doc: )end)r6r7r6zSentence '%s' failed to parse'TzSentence '%s' received a parse'zAll tests passed!N)r2printsplitlistr1parser) r5 show_treestestkeysenttokenstreestreeacceptedrejecteds rrunzTestGrammar.runsJJ +D $u+# -+ , I,D!ZZ\F v!67E!ed $)(D!$K(h B;",-MPT-T"UU'+H ",-NQU-U"VV'+H#, ,&H)*- +r)NN)F)__name__ __module__ __qualname____doc__r8rKrrr.r.s!+rr.cD||j|}g}|jdD]v}|dk(s|d|vr|jdd}d}t|dk(r'|ddvr |dd v}|d}nt|d}|d}|j}|gk(ro|||fgz }x|S) a Parses a string with one test sentence per line. Lines can optionally begin with: - a bool, saying if the sentence is grammatical or not, or - an int, giving the number of parse trees is should have, The result information is followed by a colon, and then the sentence. Empty lines and lines beginning with a comment char are ignored. :return: a list of tuple of sentences and expected results, where a sentence is a list of str, and a result is None, or bool, or int :param comment_chars: ``str`` of possible comment characters. :param encoding: the encoding of the string, if it is binary Nr rr;r)TruetrueFalsefalse)rTrU)decoder?lenint)string comment_charsencodingr+r$ split_inforesultrFs rextract_test_sentencesr`s$x(ILL&( r>Xa[M9 ^^C+  z?a !} BB#A*::%a=Z]+%a=! R< vv&'' ( r)rNNr)z#%;N)rO nltk.datar nltk.grammarrrrnltk.parse.chartrrnltk.parse.featurechartr r nltk.parse.pchartr rr)r,r.r`rPrrrfsG22/D/DE6Er4#V.+.+b%r