o h@sdZddlZddlZddlZddlmZmZddlmZm Z m Z m Z m Z ddl mZdZddZdd d Zd d d dZGddde ZddZddZedkrUedSdS)a+Invokes the Java semgrex on a document The server client has a method "semgrex" which sends text to Java CoreNLP for processing with a semgrex (SEMantic GRaph regEX) query: https://nlp.stanford.edu/nlp/javadoc/javanlp/edu/stanford/nlp/semgraph/semgrex/SemgrexPattern.html However, this operates on text using the CoreNLP tools, which means the dependency graphs may not align with stanza's depparse module, and this also limits the languages for which it can be used. This module allows for running semgrex commands on the graphs produced by depparse. To use, first process text into a doc using stanza.Pipeline Next, pass the processed doc and a list of semgrex patterns to process_doc in this module. It will run the java semgrex module as a subprocess and return the result in the form of a SemgrexResponse, whose description is in the proto file included with stanza. A minimal example is the main method of this module. Note that launching the subprocess is potentially quite expensive relative to the search if used many times on small documents. Ideally larger texts would be processed, and all of the desired semgrex patterns would be run at once. The worst thing to do would be to call this multiple times on a large document, one invocation per semgrex pattern, as that would serialize the document each time. Included here is a context manager which allows for keeping the same java process open for multiple requests. This saves on the subprocess launching time. It is still important not to wastefully serialize the same document over and over, though. N)SemgrexRequestSemgrexResponse) send_request add_tokenadd_word_to_graphJavaProtobufContextconvert_networkx_graph)CoNLLz7edu.stanford.nlp.semgraph.semgrex.ProcessSemgrexRequestcCs t|ttSN)rr SEMGREX_JAVA)requestr P/var/www/html/env_mimamsha/lib/python3.10/site-packages/stanza/server/semgrex.pysend_semgrex_request-s rFc Cst}t|tr |g}|D]}|j|q t|jD]4\}}|j}|r.t |j ||qd}|j D]} | j D]} t |j| | t|j | |||d}q8q3q|S)Nr)r isinstancestrsemgrexappend enumerate sentencesqueryaddrgraphtokenswordsrtokenr) docsemgrex_patternsenhancedr rsent_idxsentencerword_idxrwordr r r build_request0s$     r$rcGst|||d}t|S)z Returns the result of processing the given semgrex expression on the stanza doc. Currently the return is a SemgrexResponse from CoreNLP.proto r%)r$r)rrrr r r r process_docGsr&cs*eZdZdZdfdd ZddZZS)Semgrexz Semgrex context window This is a context window which keeps a process open. Should allow for multiple requests without launching new java processes each time. Ncstt||ttdSr )superr'__init__rr )self classpath __class__r rr)XszSemgrex.__init__cGst||}||S)z[ Apply each of the semgrex patterns to each of the dependency trees in doc )r$process_request)r*rrr r r rprocess[s  zSemgrex.processr )__name__ __module__ __qualname____doc__r)r/ __classcell__r r r,rr'Qsr'c s t|}t|tr |g}g}t|j|jD]h\}d}t||jD]T\}}|dd}t|j dkr; d|q"d}|j D]5} d| j j | j dj f} t| jdkrZd } nfd d | jD} d d| } d || | fq@q"|r~|q|r||_|S)zT Put comments on the sentences which describe the matching semgrex patterns F  rz%# semgrex pattern |%s| did not match!Tz%d:%srcs,g|]}d|j|jj|jdjfqS)z%s=%d:%sr)name matchIndexrtext).0noder!r r ws$z annotate_doc..z z&# semgrex pattern |%s| matched at %s%s)copydeepcopyrrziprresultreplacelenmatch add_commentr9rr:r<joinr) rsemgrex_resultr matches_onlymatching_sentences graph_resultsentence_matchedsemgrex_patternpattern_resultrE match_word node_matchesr r=r annotate_docbs6      rQcCslt}|jdtddd|jdtddgdd |jd tdd d|jd d dddd|jdd ddd|jddddd|jddddd|}|jrlt|j}dd|D|_Wdn1sgwY|j rxt j |j dd}n t j ddd }|d!}|jrtd"|ttd#tt|g|jRd$|ji}t|||j|j}td"|dS)%a2 Runs a toy example, or can run a given semgrex expression on the given input file. For example: python3 -m stanza.server.semgrex --input_file demo/semgrex_sample.conllu --matches_only to only print sentences that match the semgrex pattern --no_print_input to not print the input z --input_fileNzobj=zzz {}=targetzKSemgrex to apply to the text. The default looks for sentences with objects)rRnargsrSrTz--semgrex_filezFile to read semgrex patterns from - relevant in case the pattern you want to use doesn't work well on the command line, for examplez --print_input print_input store_trueFz9Print the input alongside the output - gets kind of noisy)destactionrSrTz--no_print_input store_falsez?Don't print the input alongside the output - gets kind of noisy)rYrZrTz--matches_onlyz!Only print the matching sentences)rZrSrTz --enhancedz2Use the enhanced dependencies instead of the basiccSsg|] }|r|qSr )strip)r;xr r rr>szmain..) input_fileignore_gappingenztokenize,pos,lemma,depparse) processorsz1Uro ruined modern. Fortunately, Wotc banned him.z{:C}zK---------------------------------------------------------------------------r)argparseArgumentParser add_argumentr parse_args semgrex_fileopen readlinesrr^r conll2docstanzaPipelinerWprintformatr&rrQrI)parserargsfinrnlprHr r rmains2  rr__main__)F)r3rbr?rjstanza.protobufrr$stanza.server.java_protobuf_requestsrrrrrstanza.utils.conllr r rr$r&r'rQrrr0r r r rs""    '