3 d*@sddlmZddlmZdgZy$ddlmZddlmZddZ Wn.e k rpZ ze fddZ WYd d Z [ XnXd d Z d d Z GdddeZddZd S))ParserI)Tree BllipParser)RerankingParser)get_unified_model_parameterscCsdS)Nrrr0/tmp/pip-build-v9q4h5k9/nltk/nltk/parse/bllip.py_ensure_bllip_import_or_errorZsr cCstd|dS)Nz&Couldn't import bllipparser module: %s) ImportError)ierrrr `sNcCsdy$xt|D]\}}|jdq WWn:tk r^}ztd|d|d|WYdd}~XnXdS)NasciizToken z (zH) is non-ASCII. BLLIP Parser currently doesn't support non-ASCII inputs.) enumerateencodeUnicodeEncodeError ValueError)wordsiworderrr _ensure_asciidsrcCstjt|jS)N)r fromstringstrZ ptb_parse) scored_parserrr_scored_parse_to_nltk_treeosrc@s8eZdZdZd ddZddZddZed d d ZdS) rz Interface for parsing with BLLIP Parser. BllipParser objects can be constructed with the ``BllipParser.from_unified_model_dir`` class method or manually using the ``BllipParser`` constructor. NcCsRt|p i}|pi}t|_|jj|f||rN|rN|jjf||d|dS)a Load a BLLIP Parser model from scratch. You'll typically want to use the ``from_unified_model_dir()`` class method to construct this object. :param parser_model: Path to parser model directory :type parser_model: str :param reranker_features: Path the reranker model's features file :type reranker_features: str :param reranker_weights: Path the reranker model's weights file :type reranker_weights: str :param parser_options: optional dictionary of parser options, see ``bllipparser.RerankingParser.RerankingParser.load_parser_options()`` for more information. :type parser_options: dict(str) :param reranker_options: optional dictionary of reranker options, see ``bllipparser.RerankingParser.RerankingParser.load_reranker_model()`` for more information. :type reranker_options: dict(str) )Zfeatures_filenameZweights_filenameN)r rrrpZload_parser_modelZload_reranker_model)selfZ parser_modelZreranker_featuresZreranker_weightsparser_optionsreranker_optionsrrr__init__zs!zBllipParser.__init__ccs0t||jj|}x|D]}t|VqWdS)a Use BLLIP Parser to parse a sentence. Takes a sentence as a list of words; it will be automatically tagged with this BLLIP Parser instance's tagger. :return: An iterator that generates parse trees for the sentence from most likely to least likely. :param sentence: The sentence to be parsed :type sentence: list(str) :rtype: iter(Tree) N)rrparser)rsentence nbest_listrrrrrs   zBllipParser.parsec csng}i}x2t|D]&\}\}}|j||dk r|||<qWt||jj||}x|D]}t|VqXWdS)a Use BLLIP to parse a sentence. Takes a sentence as a list of (word, tag) tuples; the sentence must have already been tokenized and tagged. BLLIP will attempt to use the tags provided but may use others if it can't come up with a complete parse subject to those constraints. You may also specify a tag as ``None`` to leave a token's tag unconstrained. :return: An iterator that generates parse trees for the sentence from most likely to least likely. :param sentence: Input sentence to parse as (word, tag) pairs :type sentence: list(tuple(str, str)) :rtype: iter(Tree) N)r appendrrZ parse_taggedr) rZword_and_tag_pairsrZtag_maprrtagr!rrrr tagged_parses   zBllipParser.tagged_parsecCst|\}}}||||||S)a( Create a ``BllipParser`` object from a unified parsing model directory. Unified parsing model directories are a standardized way of storing BLLIP parser and reranker models together on disk. See ``bllipparser.RerankingParser.get_unified_model_parameters()`` for more information about unified model directories. :return: A ``BllipParser`` object using the parser and reranker models in the model directory. :param model_dir: Path to the unified model directory. :type model_dir: str :param parser_options: optional dictionary of parser options, see ``bllipparser.RerankingParser.RerankingParser.load_parser_options()`` for more information. :type parser_options: dict(str) :param reranker_options: optional dictionary of reranker options, see ``bllipparser.RerankingParser.RerankingParser.load_reranker_model()`` for more information. :type reranker_options: dict(str) :rtype: BllipParser )r)cls model_dirrrZparser_model_dirZreranker_features_filenameZreranker_weights_filenamerrrfrom_unified_model_dirsz"BllipParser.from_unified_model_dir)NNNNN)NN) __name__ __module__ __qualname____doc__rrr$ classmethodr'rrrrrss )c Csddlm}|dj}tdtj|}tddj}dj}dj}x\|||fD]N}td d j|yt|j |}t|WqTt k rtd YqTXqTWx*t |j |D]\}} td || fqWtd t|j ddgtdt|j ddgtdt|j ddgdS)z8This assumes the Python module bllipparser is installed.r)findzmodels/bllip_wsj_no_auxzLoading BLLIP Parsing models...zDone.z#British left waffles on Falklands .z"I saw the man with the telescope .z # ! ? : -z Sentence: %r z(parse failed)z parse %d: %szforcing 'tree' to be 'NN':ANtreeNNz.forcing 'A' to be 'DT' and 'tree' to be 'NNP':DTNNPzforcing 'A' to be 'NNP':)r/N)r0r1)r/r2)r0r3)r/r3)r0N) Z nltk.datar-pathprintrr'splitjoinnextr StopIterationr r$) r-r&ZbllipZ sentence1Z sentence2Zfail1r r0rrrrrdemos4    r:)Znltk.parse.apirZ nltk.treer__all__Z bllipparserrZbllipparser.RerankingParserrr r r rrrr:rrrr s  H