o i6E@sdZddlmZddlmZmZmZmZmZm Z m Z m Z m Z m Z mZmZmZddlmZmZmZmZmZmZmZmZGdddeZGdddeeZGd d d eZGd d d eZGd ddeZGdddeZGddde Z GdddeZ!GdddeZ"GdddeZ#GdddeZ$eeeeegZ%eeeegZ&ee eegZ'ee eegZ(ee e gZ)GdddeZ*Gddde*Z+Gdd d e*Z,Gd!d"d"e*Z-Gd#d$d$e*Z.Gd%d&d&e*Z/eee"e#e$gZ0eeee!gZ1eeee!gZ2eeee!gZ3Gd'd(d(e*eZ4Gd)d*d*e4Z5Gd+d,d,e4Z6Gd-d.d.e4Z7Gd/d0d0e4Z8 1 2 1 3 4 5d:d6d7Z9e:d8kr]e9d9Sd9S);a Data classes and parser implementations for *incremental* chart parsers, which use dynamic programming to efficiently parse a text. A "chart parser" derives parse trees for a text by iteratively adding "edges" to a "chart". Each "edge" represents a hypothesis about the tree structure for a subsequence of the text. The "chart" is a "blackboard" for composing and combining these hypotheses. A parser is "incremental", if it guarantees that for all i, j where i < j, all edges ending at i are built before any edges ending at j. This is appealing for, say, speech recognizer hypothesis filtering. The main parser class is ``EarleyChartParser``, which is a top-down algorithm, originally formulated by Jay Earley (1970). ) perf_counter) BottomUpPredictCombineRuleBottomUpPredictRuleCachedTopDownPredictRuleChart ChartParserEdgeIEmptyPredictRule"FilteredBottomUpPredictCombineRule!FilteredSingleEdgeFundamentalRuleLeafEdge LeafInitRuleSingleEdgeFundamentalRuleTopDownInitRule)!FeatureBottomUpPredictCombineRuleFeatureBottomUpPredictRule FeatureChartFeatureChartParserFeatureEmptyPredictRule FeatureSingleEdgeFundamentalRuleFeatureTopDownInitRuleFeatureTopDownPredictRulec@sLeZdZddZddZddZddZd d Zd d Zd dZ ddZ dS)IncrementalChartcCs(tdd|D|_i|_i|_dS)Ncss|]}gVqdSN.0xrrQ/var/www/edux/Edux_v2/venv/lib/python3.10/site-packages/nltk/parse/earleychart.py @z.IncrementalChart.initialize..)tuple _positions _edgelists _edge_to_cpls_indexesselfrrr initialize>s zIncrementalChart.initializecCs t|Sr)list iteredgesr&rrredgesIs zIncrementalChart.edgescCsdd|jDS)Ncss|] }|D]}|VqqdSrr)redgelistedgerrrrMsz-IncrementalChart.iteredges..)r#r&rrrr*LzIncrementalChart.iteredgesc sr|j|}ikr t|St}t|}||jvr!||tfdd|D}t|j|||gS)Nc3s|]}|VqdSrrrkey restrictionsrrr^sz*IncrementalChart.select..r#itersortedkeysr!r% _add_indexgetr'endr2r, restr_keysvalsrr1rselectOs    zIncrementalChart.selectcs|D] }tt|std|qtdd|D}|j|<t|jD]!\}}||}|D]tfdd|D}||g q/q%dS)NBad restriction: %scs|]}iVqdSrrrrrrrhr z.IncrementalChart._add_index..c3|] }t|VqdSrgetattrr/r-rrrn hasattrr ValueErrorr!r"r% enumerater# setdefaultappendr'r;r0indexr:r, this_indexr<rrCrr7as   zIncrementalChart._add_indexcsL}|jD]\}}tfdd|D}|||gq dS)Nc3r@rrAr/rCrrrtrDz:IncrementalChart._register_with_indexes..r:r%itemsr!rIrJr'r-r:r;rLr<rrCr_register_with_indexesqs z'IncrementalChart._register_with_indexescCs|j||dSr)r#r:rJ)r'r-rrr _append_edgewszIncrementalChart._append_edgecCst|dS)N)range num_leavesr&rrrr"zr.zIncrementalChart._positionsN) __name__ __module__ __qualname__r(r+r*r=r7rQrRr"rrrrr=s  rc@s$eZdZddZddZddZdS)FeatureIncrementalChartc stj|}ikr t|St}t|}|jvr!|tfdd|D}tj|||gS)Nc3s|] }|VqdSr)_get_type_if_possibler/r2r'rrrs z1FeatureIncrementalChart.select..r3r9rr[rr=s    zFeatureIncrementalChart.selectcs|D] }tt|std|qtddD}j|<tjD]"\}}||}|D]tfdd|D}||g q/q%dS)Nr>csr?rrrrrrrr z5FeatureIncrementalChart._add_index..c3"|] }t|VqdSrrZrBr/r-r'rrrs  rErKrr^rr7s   z"FeatureIncrementalChart._add_indexcsN}jD]\}}tfdd|D}|||gq dS)Nc3r\rr]r/r^rrrs zAFeatureIncrementalChart._register_with_indexes..rNrPrr^rrQsz.FeatureIncrementalChart._register_with_indexesN)rVrWrXr=r7rQrrrrrY~s rYc@eZdZddZdS)CompleteFundamentalRuleccsL|}|j||d|dD]}||}||||r#|VqdSNT)startr: is_completelhs)r:r=nextsymmove_dot_forwardinsert_with_backpointer)r'chartgrammar left_edger: right_edgenew_edgerrr_apply_incompletes  z)CompleteFundamentalRule._apply_incompleteNrVrWrXrmrrrrr` r`c@eZdZeZddZdS) CompleterRuleccs*t|ts|j|||EdHdSdSr isinstancer _fundamental_ruleapplyr'rhrir-rrrru zCompleterRule.applyNrVrWrXr`rtrurrrrrq rqc@rp) ScannerRuleccs*t|tr|j|||EdHdSdSrrrrvrrrrurwzScannerRule.applyNrxrrrrrzryrzc@ eZdZdS) PredictorRuleNrVrWrXrrrrr|r|c@r_)FilteredCompleteFundamentalRuleccs&|r||||EdHdSdSr)rc_apply_completervrrrrusz%FilteredCompleteFundamentalRule.applyN)rVrWrXrurrrrrrorc@r_)FeatureCompleteFundamentalRuleccsF|j}|}|j||d|dD] }|||||EdHqdSra)rtr:r=reru)r'rhrirjfrr:rkrrrrms  z0FeatureCompleteFundamentalRule._apply_incompleteNrnrrrrrrorc@eZdZeZdS)FeatureCompleterRuleNrVrWrXrrtrrrrr rc@r)FeatureScannerRuleNrrrrrrrrc@r{)FeaturePredictorRuleNr}rrrrrr~rc@s,eZdZdZeddefddZd ddZdS) IncrementalChartParsera An *incremental* chart parser implementing Jay Earley's parsing algorithm: | For each index end in [0, 1, ..., N]: | For each edge such that edge.end = end: | If edge is incomplete and edge.next is not a part of speech: | Apply PredictorRule to edge | If edge is incomplete and edge.next is a part of speech: | Apply ScannerRule to edge | If edge is complete: | Apply CompleterRule to edge | Return any complete parses in the chart r2cCsh||_||_||_||_g|_g|_|D]}|jdkr"|j|q|jdkr.|j|qtddS)a Create a new Earley chart parser, that uses ``grammar`` to parse texts. :type grammar: CFG :param grammar: The grammar used to parse texts. :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. :type trace_chart_width: int :param trace_chart_width: The default total width reserved for the chart in trace output. The remainder of each line will be used to display edges. :param chart_class: The class that should be used to create the charts used by this parser. rrSz9Incremental inference rules must have NUM_EDGES == 0 or 1N) _grammar_trace_trace_chart_width _chart_class_axioms_inference_rules NUM_EDGESrJrG)r'ristrategytracetrace_chart_width chart_classrulerrr__init__/s  zIncrementalChartParser.__init__NcCs(|dur|j}|j}t|}|j|||}|j}|j|d}|r.t| ||j D]}t| ||}||||||q1|j } t |dD]B} |dkr[td| dt|j| d} | r| } | D]#} t| ||| }||| ||||D] }|| kr| |qqk| seqO|S)NrSz * Processing queue: )r:)r_trace_new_edgesr)rcheck_coveragerrrUprintpretty_format_leavesrrurrTr=popr:rJ)r'tokensrtrace_new_edgesrhritrace_edge_widthaxiom new_edgesinference_rulesr:agendar-rrlrrr chart_parseZs>       z"IncrementalChartParser.chart_parser)rVrWrX__doc__BU_LC_INCREMENTAL_STRATEGYrrrrrrrrs +rc@r_)EarleyChartParsercKtj||tfi|dSr)rrEARLEY_STRATEGYr'ri parser_argsrrrrszEarleyChartParser.__init__NrVrWrXrrrrrr~rorc@r_)IncrementalTopDownChartParsercKrr)rrTD_INCREMENTAL_STRATEGYrrrrr  z&IncrementalTopDownChartParser.__init__Nrrrrrrrorc@r_)IncrementalBottomUpChartParsercKrr)rrBU_INCREMENTAL_STRATEGYrrrrrrz'IncrementalBottomUpChartParser.__init__Nrrrrrrrorc@r_)(IncrementalBottomUpLeftCornerChartParsercKrr)rrrrrrrrrz1IncrementalBottomUpLeftCornerChartParser.__init__Nrrrrrrrorc@r_) IncrementalLeftCornerChartParsercKs*|stdtj||tfi|dS)NzNIncrementalLeftCornerParser only works for grammars without empty productions.) is_nonemptyrGrrLC_INCREMENTAL_STRATEGYrrrrrs z)IncrementalLeftCornerChartParser.__init__Nrrrrrrrorc@seZdZedefddZdS)FeatureIncrementalChartParsercKs tj||f|||d|dS)N)rrr)rr)r'rirrrrrrrrs z&FeatureIncrementalChartParser.__init__N)rVrWrX"BU_LC_INCREMENTAL_FEATURE_STRATEGYrYrrrrrrs rc@r_)FeatureEarleyChartParsercKrr)rrEARLEY_FEATURE_STRATEGYrrrrrrz!FeatureEarleyChartParser.__init__Nrrrrrrrorc@r_)$FeatureIncrementalTopDownChartParsercKrr)rrTD_INCREMENTAL_FEATURE_STRATEGYrrrrrrz-FeatureIncrementalTopDownChartParser.__init__Nrrrrrrrorc@r_)%FeatureIncrementalBottomUpChartParsercKrr)rrBU_INCREMENTAL_FEATURE_STRATEGYrrrrrrz.FeatureIncrementalBottomUpChartParser.__init__Nrrrrrrrorc@r_)/FeatureIncrementalBottomUpLeftCornerChartParsercKrr)rrrrrrrrrz8FeatureIncrementalBottomUpLeftCornerChartParser.__init__NrrrrrrrorTF$I saw John with a dog with my cookiecCsddl}ddl}ddlm}|} |rtdt| tdt||} t| tt| |d} t} | | } t | | }t| } |rVt ||ksVJd|rb|D]}t|qZntdt ||rrtd | dSdS) z0 A demonstration of the Earley parsers. rN) demo_grammarz * Grammarz * Sentence:)rzNot all parses foundz Nr trees:zTime:) systimenltk.parse.chartrrsplitrrrr)parsesrblen) print_times print_grammar print_treesrsent numparsesrrrrirearleytrhrtreerrrdemos6      r__main__N)TFTrrr);rrrrrrrrrrr r r r r rrnltk.parse.featurechartrrrrrrrrrrYr`rqrzr|rrrrrrrrrrrrrrrrrrrrrrrrrrrVrrrrs <(A6    _  0