o hS9@sNdZddlZddlmZddlZddlZddlZddlZddlm Z m Z ddl m Z m Z ddlmZddlmZddlmZmZmZmZmZmZmZmZmZmZmZmZmZm Z m!Z!m"Z"d Z#ed d gd d Z$ddZ%ddZ&ddZ'ddZ(d&ddZ)ddZ*d&ddZ+ddZ,ddZ-Gd d!d!ej.Z/d"Z0d#d$Z1e2d%kre1dSdS)'zInvokes the Java ssurgeon on a document "ssurgeon" sends text to Java CoreNLP for processing with a ssurgeon (Semantic graph SURGEON) query The main program in this file gives a very short intro to how to use it. N) namedtuple)misc_to_space_afterspace_after_to_misc)SsurgeonRequestSsurgeonResponse)java_protobuf_requests)CoNLL)IDTEXTLEMMAUPOSXPOSFEATSHEADDEPRELDEPSMISC START_CHAREND_CHARNERWordTokenSentencezAedu.stanford.nlp.semgraph.semgrex.ssurgeon.ProcessSsurgeonRequest SsurgeonEditz9semgrex_pattern ssurgeon_edits ssurgeon_id notes language)NNUniversalEnglish)defaultsc Cs|}td|}g}t|D];\}}|d}dd|D}d|}dd|D}t|dkr3q|d}|dd} |t|| d |d|q|S) Nz + cSs&g|]}|dr|ddqS)#N) startswithstrip).0liner#Q/var/www/html/env_mimamsha/lib/python3.10/site-packages/stanza/server/ssurgeon.py $&z(parse_ssurgeon_edits.. cSs&g|]}|r|ds|qS)r)r r)r!xr#r#r$r%&r&rrz%d)r resplit enumeratejoinlenappendr) ssurgeon_textssurgeon_blocksssurgeon_editsidxblocklinescommentsnotessemgrexssurgeonr#r#r$parse_ssurgeon_editss     r9cCs<t|dd}t|WdS1swYdS)Nutf-8encoding)openr9read) edit_filefinr#r#r$read_ssurgeon_edits/s $rAcCst|ttSN)r send_requestr SSURGEON_JAVA)requestr#r#r$send_ssurgeon_request3srFc Cst}|D]2}|j}|j|_|jD]}|j|q|jdur%|j|_ |j dur.|j |_ |j dur7|j |_ qz4t |j D]+\}}|j}d} |jD]} | jD]} t|j| | t|| || | d} qQqLq>W|Sty} z td||| d} ~ ww)Nrrz#Failed to process sentence {}: {:C})rr8addsemgrex_patternr7r1 operationr. ssurgeon_ididr6languager+ sentencesgraphtokenswordsr add_tokentokenadd_word_to_graph Exception RuntimeErrorformat) docr1rEr8ssurgeon_protorIsent_idxsentencerNword_idxrRworder#r#r$ build_request6s<          r^cCst||||}t||gSrB)rr^)rWrHr1rJr6 ssurgeon_editr#r#r$build_request_one_operationTs r`cCst||}t|S)z Returns the result of processing the given semgrex expression and ssurgeon edits on the stanza doc. Currently the return is a SsurgeonResponse from CoreNLP.proto )r^rF)rWr1rEr#r#r$ process_docXs racCst|||||}t|SrB)r`rF)rWrHr1rJr6rEr#r#r$process_doc_one_operationbsrbcCst|t|jr |jndt|jr|jndt|jr|jndt|jr!|jndt t |j t dt|jr1|jndtdtdtdd|jd|jd|jd|ji}t|j|t<|jr[t |j|t|t<|S)Nis_mwt is_first_mwtmwt_textmwt_misc)r r r\r lemmar coarseTagr posrrfeatures_to_stringconllUFeaturesrrnerrrrisMWT isFirstMWTmwtTextmwtMiscrafter conllUMiscsubstitute_space_misc) word_index graph_word word_entryr#r#r$build_word_entrygs( rwc Cs&t|}zutt|j|jD]g\}\}}|j}g}t|j|jD]\}}t |j |} | | q#|j ddd|j D]} d|| dt<d|| dt<q>|jD]} | jrZqT| j|| jdt<| j|| jdt<qTg} t|D]\} }|ds|drt|t|t<| |qu| d}|t|kr||dr||ds|d7}|t|kr||dr||drt|| t||dtft|d t|ttdi}t||dt|t<||dd rt||dd |t|t<t|t|t<| || |qut|j}t | |}g}t|j!D]\}}| |j"|t|j!dkr6n| |j#q d $|}|D])}|%d s_|%d s_|%ds_|%drh|&d|qE|&|qE||j|<|'qW|St(y}z t)d*||||d}~ww)NcSs|tSrB)r )r(r#r#r$sz)convert_response_to_doc..)keyrrrootrdrcrerfz# text z#text z# text=z#text=z # text = zRSsurgeon could not process sentence {} Ssurgeon result: {} Original sentence: {:C})+copydeepcopyr+ziprMresultrNnoderRrwindexr.sortrzrredgeisExtrasourcetargetdeprremove_space_miscrr-r r rmisc_space_piecesrslistr5rrOtext spaces_afterr,r add_commentrebuild_dependenciesrTrUrV)rWsemgrex_responserYrZssurgeon_resultssurgeon_graphrO graph_noderurvrzr mwt_tokensword_start_idxr\ word_end_idxmwt_token_entry old_comments token_text token_idxrR sentence_textcommentr]r#r#r$convert_response_to_docsx       $$       0  Hrcs4eZdZdZd fdd ZddZd ddZZS) Ssurgeonz Ssurgeon 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||ttdSrB)superr__init__rrD)self classpath __class__r#r$rszSsurgeon.__init__cCst||}||S)z\ Apply each of the ssurgeon patterns to each of the dependency trees in doc )r^process_request)rrWr1rEr#r#r$processs  zSsurgeon.processcCst|||||}||S)zI Convenience method - build one operation, then apply it )r`r)rrWrHr1rJr6rEr#r#r$process_one_operations zSsurgeon.process_one_operationrBNN)__name__ __module__ __qualname____doc__rrr __classcell__r#r#rr$rs ra # sent_id = 271 # text = Hers is easy to clean. # previous = What did the dealer like about Alex's car? # comment = extraction/raising via "tough extraction" and clausal subject 1 Hers hers PRON PRP Gender=Fem|Number=Sing|Person=3|Poss=Yes|PronType=Prs 3 nsubj _ _ 2 is be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 3 cop _ _ 3 easy easy ADJ JJ Degree=Pos 0 root _ _ 4 to to PART TO _ 5 mark _ _ 5 clean clean VERB VB VerbForm=Inf 3 csubj _ SpaceAfter=No 6 . . PUNCT . _ 5 punct _ _ c sJz tjjddWn tyYnwt}|jdtddd|jdtddd|jdtdd d|jd td d d|jd dddd|jdtddd|jdtddd|jdtddd|jdtdgddd|jdddd d!d"|jd#dd$d%d&|j rt j }nt j j g}jrtjjd'g}jg}t||}n0jrȈjstd(tjjstjfd)d*}|}ntjtd+g}dg}t||}|D]I\}}jrtd,|t||}t|} t || } |durt!|d-dd} | "d.| Wdn 1swYqtd/| qdS)0Nr:r;z --input_fileznsubj {} >csubj=bad {}zrSemgrex to apply to the text. A default detects words which have both an nsubj and a csubj. Default: %(default)sr8z&relabelNamedEdge -edge bad -reln advcl*zSsurgeon edits to apply based on the Semgrex. Can have multiple edits in a row. A default exists to transform csubj into advcl. Default: %(default)s)rrnargsrz --print_input print_input store_trueFzPPrint the input alongside the output - gets kind of noisy. Default: %(default)s)destrrrz--no_print_input store_falsez?Don't print the input alongside the output - gets kind of noisy)rrr input_filezvCannot process multiple files without knowing where to send them - please set --output_dir in order to use --input_dirc3sptjD].}jrtj|sqtjj|}tjj|}t d||ft j |d|fVqdS)NzProcessing %s to %sr) oslistdir input_dir input_filterr)matchpathr, output_dirprintr conll2doc) doc_filenamedoc_path output_pathargsr#r$ read_docsszmain..read_docs) input_strz{:C}wz{:C} z{:C} )#sysstdout reconfigureAttributeErrorargparseArgumentParser add_argumentstr parse_argsr?rArr7r8rrr output_filer~rr ValueErrorrrexistsmakedirs SAMPLE_DOCrrrVr^rFrr=write) parserr1docsoutputs input_outputrrWoutputssurgeon_requestssurgeon_response updated_docfoutr#rr$mains`           r__main__r)3rr collectionsrr|rr)rstanza.models.common.utilsrrstanza.protobufrr stanza.serverrstanza.utils.conllrstanza.models.common.docr r r r r rrrrrrrrrrrrDrr9rArFr^r`rarbrwrJavaProtobufContextrrrrr#r#r#r$s@   H  M B