U e= @sZdZddlZddlZddlmZdddddd d d d g d ddgdddddd d d d ddg dZeddddZed dddZddZ ddZ d?ddZ ej j fddZdd Zd!d"Zd@d$d%ZdAd(d)ZdBd*d+Zd,d-ZdCd/d0ZdDd1d2Zd3d4ZdEd6d7Zd8d9Zd:d;Zededd>eeeedS)Fa Code for extracting relational triples from the ieer and conll2002 corpora. Relations are stored internally as dictionaries ('reldicts'). The two serialization outputs are "rtuple" and "clause". - An rtuple is a tuple of the form ``(subj, filler, obj)``, where ``subj`` and ``obj`` are pairs of Named Entity mentions, and ``filler`` is the string of words occurring between ``sub`` and ``obj`` (with no intervening NEs). Strings are printed via ``repr()`` to circumvent locale variations in rendering utf-8 encoded strings. - A clause is an atom of the form ``relsym(subjsym, objsym)``, where the relation, subject and object have been canonicalized to single strings. N) defaultdictLOCATION ORGANIZATIONPERSONZDURATIONZDATEZCARDINALPERCENTZMONEYZMEASURELOCPERORGZFACILITYZGPE)ieer conll2002ace)rr r)rrrcCs(z t|WStk r"|YSXdS)zF Expand an NE class name. :type type: str :rtype: str N) short2longKeyErrortyperT/var/www/html/assets/scripts/venv/lib/python3.8/site-packages/nltk/sem/relextract.py_expand?s rcCs(z t|WStk r"|YSXdS)zJ Abbreviate an NE class name. :type type: str :rtype: str N) long2shortrrrrr class_abbrevKs r Fcsfz ||WStk r`|r8|dd|DYSddlm|fdd|DYSXdS)z Join a list into a string, turning tags tuples into tag strings or just words. :param untag: if ``True``, omit the tag from tagged input strings. :type lst: list :rtype: str css|]}|dVqdS)rNr.0tuprrr bsz_join..r tuple2strc3s|]}|VqdS)NrrrrrresN)join TypeErrorZnltk.tagr)lstsepuntagrrr_joinWs  r"cCs4z||dWStk r.|dYSXdS)z` Translate one entity to its ISO Latin value. Inspired by example from effbot.org rN)groupr)mZdefsrrrdescape_entityhsr&cCs<t|ddd}|}td}|t|}|dd}|S)z Convert a list of strings into a canonical symbol. :type lst: list :return: a Unicode string without whitespace :rtype: unicode _Tr!z&(\w+?);.)r"lowerrecompilesubr&replace)rsymZENTrrrlist2symvs    r1cCsZddlm}g}gdg}|D]8}t||s:|d|q||d<||gdg}q|S)a Group a chunk structure into a list of 'semi-relations' of the form (list(str), ``Tree``). In order to facilitate the construction of (``Tree``, string, ``Tree``) triples, this identifies pairs whose first member is a list (possibly empty) of terminal strings, and whose second member is a ``Tree`` of the form (NE_label, terminals). :param tree: a chunk tree :return: a list of pairs (list(str), ``Tree``) :rtype: list of tuple rTreeNr#) nltk.treer3 isinstanceappend)treer3Z semi_relsZsemi_relZdtrrrr tree2semi_rels    r8cCsHg}t|dkrDtt}t|dd| d|d<|dd|d<t|dd|d<t|dd|d<t|dd|d <t|ddd d |d <|dd|d <t|dd|d<t|dd|d<t|ddd||d<|r,td|d |d|d f|||dd}q|S)a Converts the pairs generated by ``tree2semi_rel`` into a 'reldict': a dictionary which stores information about the subject and object NEs plus the filler between them. Additionally, a left and right context of length =< window are captured (within a given input sentence). :param pairs: a pair of list(str) and ``Tree``, as generated by :param window: a threshold for the number of items to include in the left and right context :type window: int :return: 'relation' dictionaries whose keys are 'lcon', 'subjclass', 'subjtext', 'subjsym', 'filler', objclass', objtext', 'objsym' and 'rcon' :rtype: list(defaultdict) rNlconr# subjclasssubjtextsubjsymfillerTr(Zuntagged_fillerobjclassobjtextobjsymrconz (%s(%s, %s)) lenrstrr"labelleavesr1printr6)pairswindowtraceresultreldictrrrsemi_rel2reldicts2  rNr c sr6t|kr6tt|kr*tn tdrlt|krltt|kr`tn td|dks||dkrt|}n&|dkrt|jt|j}ntdt|}fdd}tt||S) a Filter the output of ``semi_rel2reldict`` according to specified NE classes and a filler pattern. The parameters ``subjclass`` and ``objclass`` can be used to restrict the Named Entities to particular types (any of 'LOCATION', 'ORGANIZATION', 'PERSON', 'DURATION', 'DATE', 'CARDINAL', 'PERCENT', 'MONEY', 'MEASURE'). :param subjclass: the class of the subject Named Entity. :type subjclass: str :param objclass: the class of the object Named Entity. :type objclass: str :param doc: input document :type doc: ieer document or a list of chunk trees :param corpus: name of the corpus to take as input; possible values are 'ieer' and 'conll2002' :type corpus: str :param pattern: a regular expression for filtering the fillers of retrieved triples. :type pattern: SRE_Pattern :param window: filters out fillers which exceed this threshold :type window: int :return: see ``mk_reldicts`` :rtype: list(defaultdict) z;your value for the subject type has not been recognized: %sz:your value for the object type has not been recognized: %sr r r zcorpus type not recognizedcs:|dko8t|dko8|do8|dkS)Nr<r?r@)rDsplitmatch)xr@patternr<rJrrs   zextract_rels..) NE_CLASSESr ValueErrorr8textheadlinerNlistfilter) r<r@doccorpusrTrJrIZreldictsZ relfilterrrSr extract_relss,   r^cCsrt|d|d|dt|d|dg}d}|rH|dg|}d|}|rb||d |d }t|}||S) zy Pretty print the reldict as an rtuple. :param reldict: a relation dictionary :type reldict: defaultdict r<r=r?r@rAz[%s: %r] %r [%s: %r]r;z...%r)rCz(%r...)rr6tuple)rMr;rCitemsformatZ printargsrrrrtuples  rbcCs||d|df}d|S)z Print the relation in clausal form. :param reldict: a relation dictionary :type reldict: defaultdict :param relsym: a label for the relation :type relsym: str r>rBz %s(%r, %r)r)rMrelsymr`rrrclausesrdTc Cs~ddlm}|r`z(ddl}|d}|}|dWn&tk r^ddl}|dYnXt d}t t dt d | D]}| |D]} |rt | jt d td d | d |dD]\} t t| dd|rz,| d| d| jf} |d| |Wqtk rYqXqqq|rzz8|dt t dt d|D]} t | qPWntk rxYnXdS)a. Select pairs of organizations and locations whose mentions occur with an intervening occurrence of the preposition "in". If the sql parameter is set to True, then the entity pairs are loaded into an in-memory database, and subsequently pulled out using an SQL "SELECT" query. rr Nz:memory:zPcreate table Locations (OrgName text, LocationName text, DocID text)z/Cannot import sqlite; sql flag will be ignored.z.*\bin\b(?!\b.+ing)z'IEER: in(ORG, LOC) -- just the clauses:-============================================================r rr r]rTINrcr=rAzJinsert into Locations values (?, ?, ?)zTselect OrgName from Locations where LocationName = 'Atlanta'z,Extract data from SQL table: ORGs in Atlantaz---------------) nltk.corpusr sqlite3connectcursorexecute ImportErrorwarningswarnr,r-rHfileids parsed_docsdocnor^rdcommit NameError) rKsqlr rl connectioncurrqrifiler\relrbrowrrrin_demo2sZ       r~c Csddlm}d}t|tj}ttdtd|D]d}||D]T}d}}|rtt|jtdd}}t d d |d |d D]}tt |||d qqJqs z"ieer_headlines..z%s: %s)rkr r4r3rHrs)r3Ztreesr7rrerieer_headliness   rr#c Csddlm}d}t|tj}ttdtd|dD]D}d}}|rVd}}td d |d |d d D]}tt|||dqjq>dS)zh Find the copula+'van' relation ('of') in the Dutch tagged training corpus from CoNLL 2002. rr z ( is/V| # 3rd sing present and was/V| # past forms of the verb zijn ('be') werd/V| # and also present wordt/V # past of worden ('become) ) .* # followed by anything van/Prep # followed by van ('of') z;Dutch CoNLL2002: van(PER, ORG) -- raw rtuples with context:rfz ned.trainFTrr r rOr]rTrJrN) rkr r,r-rrH chunked_sentsr^rb)rKr ZvnvZVANr\r;rCr|rrrconllneds&   rcsxddlm}d}t|tjttdtdfdd|dD}|dd D]}tt|d d qXtdS) Nrrz. .* ( de/SP| del/SP ) z=Spanish CoNLL2002: de(ORG, LOC) -- just the first 10 clauses:rfc s(g|] }tdd|ddD]}|qqS)r rr rh)r^)rr\r|DErrrszconllesp..z esp.trainrOrrj)rkr r,r-rrHrrd)r derelsrrrrconllesps  rc Csttdtdtd}g}ttjjddD]F\}}t|}t dd|d|dd }|D]}t|d t |qfqsl     ( =  G 3 '