o rZh=@sddlmZddlmZddlTddlTddlmZddlm Z Gddde Z Gdd d Z Gd d d Z Gd d d e ZGddde ZeGddde ZdS))total_ordering) ElementTree)*)raise_unorderable_types)Treec@s`eZdZdZ     dddZdddZd d Zd d Zdd dZddZ ddfddZ dS)NombankCorpusReadera Corpus reader for the nombank corpus, which augments the Penn Treebank with information about the predicate argument structure of every noun instance. The corpus consists of two parts: the predicate-argument annotations themselves, and a set of "frameset files" which define the argument labels used by the annotations, on a per-noun basis. Each "frameset file" contains one or more predicates, such as ``'turn'`` or ``'turn_on'``, each of which is divided into coarse-grained word senses called "rolesets". For each "roleset", the frameset file provides descriptions of the argument roles, along with examples. Nutf8cCsLt|tr t|||_t||_t||||||_||_||_ ||_ dS)a :param root: The root directory for this corpus. :param nomfile: The name of the file containing the predicate- argument annotations (relative to ``root``). :param framefiles: A list or regexp specifying the frameset fileids for this corpus. :param parse_fileid_xform: A transform that should be applied to the fileids in this corpus. This should be a function of one argument (a fileid) that returns a string (the new fileid). :param parse_corpus: The corpus containing the parse trees corresponding to this corpus. These parse trees are necessary to resolve the tree pointers used by nombank. N) isinstancestrZfind_corpus_fileidsZ_fileidslist CorpusReader__init___nomfile _nounsfile_parse_fileid_xform _parse_corpus)selfrootZnomfile framefilesZ nounsfileparse_fileid_xform parse_corpusencodingrI/var/www/auris/lib/python3.10/site-packages/nltk/corpus/reader/nombank.pyr s    zNombankCorpusReader.__init__csDidurfddd<tjfddjdS)z :return: a corpus view that acts as a list of ``NombankInstance`` objects, one for each noun in the corpus. Ncs |jkSNbaseforminstrrrMs z/NombankCorpusReader.instances..instance_filtercsj|fiSr)_read_instance_block)stream)kwargsrrrr Psr)StreamBackedCorpusViewabspathrr)rrr)rr$rr instancesFs   zNombankCorpusReader.instancescCt||jt||jdS)z :return: a corpus view that acts as a list of strings, one for each line in the predicate-argument annotation file. r%)r&r'rread_line_blockrrrrrlinesT   zNombankCorpusReader.linescCs|dd}|dd}|dddd}d|}||vr'td |||}t|}Wd n1s@wY| d D] }|j d |krW|SqJtd |d|)zE :return: the xml description for the given roleset. .r perc-sign%oneslashonezero1/10 1-slash-10 frames/%s.xmlFrameset file for %s not foundNpredicate/rolesetidzRoleset z not found in ) splitreplacefileids ValueErrorr'openrparsegetrootfindallZattrib)rZ roleset_idr framefilefpetreerolesetrrrrC_s     zNombankCorpusReader.rolesetc Cs|durd|}||vrtd||g}n|}g}|D](}||}t|}Wdn1s;wY||dq t |S)zA :return: list of xml descriptions for rolesets. Nr4r5r6) r:r;r'r<rr=r>appendr?ZLazyConcatenation)rrr@rZrsetsrArBrrrrolesetsus  zNombankCorpusReader.rolesetscCr))z :return: a corpus view that acts as a list of all noun lemmas in this corpus (from the nombank.1.0.words file). r%)r&r'rr*rr+rrrnounsr-zNombankCorpusReader.nounscCsdS)NTrrrrrr szNombankCorpusReader.cCsJg}tdD]}|}|r"t||j|j}||r"||q|S)Nd)rangereadlinestripNombankInstancer=rrrD)rr#r!blockilinerrrrr"s    z(NombankCorpusReader._read_instance_block)rNNNr r) __name__ __module__ __qualname____doc__rr(r,rCrErFr"rrrrrs &  rc@sVeZdZ dddZeddZddZdd Zd d Zeed d Z e dddZ dS)rKNc CsN||_ ||_ ||_ ||_ ||_ ||_ ||_ t||_ | |_ dSr) fileidsentnumwordnumr sensenumber predicatepredidtuple argumentsr) rrSrTrUrrVrWrXrZrrrrrs$  zNombankInstance.__init__cCs2|jdd}|dddd}|d|jS)zThe name of the roleset used by this instance's predicate. Use ``nombank.roleset() `` to look up information about the roleset.r0r/r2r3r1r.)rr9rV)rrrrrrCszNombankInstance.rolesetcCsd|j|j|jS)Nz')formatrSrTrUr+rrr__repr__s zNombankInstance.__repr__cCsXd|j|j|j|j|j}|j|jdff}t|D]\}}|d|d|7}q|S)Nz{} {} {} {} {}rel -) r\rSrTrUrrVrZrWsorted)rsitemsarglocargidrrr__str__szNombankInstance.__str__cCs6|jdurdS|j|jvrdS|j|j|jSr)rrSr:Z parsed_sentsrTr+rrr _get_trees zNombankInstance._get_treezs The parse tree corresponding to this instance, or None if the corresponding tree is not available.)docc s|}t|dkrtd||dd\}}}}}|ddfddtD} t| dkr8td||dur@||}t|}t|}| ddd\} } t| } g} D]}|dd\}}| t||fq[t|||||| | | | S) Nz Badly formatted nombank line: %rcs"g|] \}}d|vr|qS)z-rel)pop).0rMpargsrr s"z)NombankInstance.parse..rr`) r8lenr; enumerateintNombankTreePointerr=rDrK)rbrrpiecesrSrTrUrrVr^ZpredlocrXrWrZargrdrerrnrr=s:      zNombankInstance.parser)NN) rOrPrQrpropertyrCr]rfrgtree staticmethodr=rrrrrKs 1  rKc@seZdZdZddZdS)NombankPointeran A pointer used by nombank to identify one or more constituents in a parse tree. ``NombankPointer`` is an abstract base class with three concrete subclasses: - ``NombankTreePointer`` is used to point to single constituents. - ``NombankSplitTreePointer`` is used to point to 'split' constituents, which consist of a sequence of two or more ``NombankTreePointer`` pointers. - ``NombankChainTreePointer`` is used to point to entire trace chains in a tree. It consists of a sequence of pieces, which can be ``NombankTreePointer`` or ``NombankSplitTreePointer`` pointers. cCs|jtkrtdSr) __class__r{NotImplementedErrorr+rrrrEs zNombankPointer.__init__N)rOrPrQrRrrrrrr{6s r{c@,eZdZddZddZddZddZd S) NombankChainTreePointercC ||_dSrrvrrvrrrrKz NombankChainTreePointer.__init__cCddd|jDS)Nrcs|]}d|VqdSz%sNrrlrmrrr Rz2NombankChainTreePointer.__str__..joinrvr+rrrrfQzNombankChainTreePointer.__str__cCd|S)Nzrr+rrrr]Tz NombankChainTreePointer.__repr__c*durtdtdfdd|jDS)NParse tree not availablez*CHAIN*cg|]}|qSrselectrryrrrpZz2NombankChainTreePointer.select..r;rrvrryrrrrWzNombankChainTreePointer.selectNrOrPrQrrfr]rrrrrrJs  rc@r~) NombankSplitTreePointercCrrrrrrrr^rz NombankSplitTreePointer.__init__cCr)N,csrrrrrrrrdrz2NombankSplitTreePointer.__str__..rr+rrrrfcrzNombankSplitTreePointer.__str__cCr)Nzrr+rrrr]frz NombankSplitTreePointer.__repr__cr)Nrz*SPLIT*crrrrrrrrplrz2NombankSplitTreePointer.select..rrrrrrirzNombankSplitTreePointer.selectNrrrrrr]s  rc@s\eZdZdZddZeddZddZdd Zd d Z d d Z ddZ ddZ ddZ dS)ruz@ wordnum:height*wordnum:height*... wordnum:height, cCs||_||_dSrrUheight)rrUrrrrrws zNombankTreePointer.__init__cCs|d}t|dkrtdd|DS|d}t|dkr(tdd|DS|d}t|dkr9td |tt|d t|dS) NrrqcSg|]}t|qSrrur=rleltrrrrprz,NombankTreePointer.parse..rcSrrrrrrrrpr:zbad nombank pointer %rr)r8rrrrr;rurt)rbrvrrrr={s         zNombankTreePointer.parsecCs|jd|jS)Nrrr+rrrrfszNombankTreePointer.__str__cCsd|j|jfS)NzNombankTreePointer(%d, %d)rr+rrrr]szNombankTreePointer.__repr__cCsPt|ttfr|jd}t|ttfst|ts||uS|j|jko'|j|jkSNr)r rrrvrurUrrotherrrr__eq__s   zNombankTreePointer.__eq__cCs ||k Srrrrrr__ne__s zNombankTreePointer.__ne__cCs\t|ttfr|jd}t|ttfst|ts t|t|kS|j|j f|j|j fkSr)r rrrvrur7rUrrrrr__lt__s   zNombankTreePointer.__lt__cCs|durtd|||S)Nr)r;treeposrrrrrszNombankTreePointer.selectcCs|durtd|g}g}d} t|dtrLt|t|kr%|dn|dd7<|dt|dkrC||d|dn%||n||jkr`t|dt||jdS|d7}|q)z} Convert this pointer to a standard 'tree position' pointer, given that it points to the given tree. NrrTrq) r;r rrrrDrkrUrYr)rrystackrrUrrrrs&   zNombankTreePointer.treeposN)rOrPrQrRrrzr=rfr]rrrrrrrrrruos   ruN) functoolsrZ xml.etreerZnltk.corpus.reader.apiZnltk.corpus.reader.utilZnltk.internalsrZ nltk.treerr rrKr{rrrurrrrs