o hG@@sddlZddlmZejjejjgZddlmZddl m m Z dZ dZ ddZdZd Zd d Zd Zd ZddZdZdZddZd1ddZdZddZdZdZddZddZd Zd!d"Z d#Z!d$d%Z"d&Z#d'd(Z$d)Z%d*d+Z&d,'Z(d-)Z*d.Z+d/d0Z,dS)2N)compare_ignoring_whitespace)CoNLLa # 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 _ _ a # 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 advcl _ SpaceAfter=No 6 . . PUNCT . _ 5 punct _ _ cCHd}dg}tjtd}t|||}t||}d|}t|tdS)Nz!{}=source >nsubj {} >csubj=bad {}z&relabelNamedEdge -edge bad -reln advcl input_str{:C}) r conll2docSAMPLE_DOC_INPUTssurgeonprocess_doc_one_operationconvert_response_to_docformatrSAMPLE_DOC_EXPECTEDsemgrex_patternssurgeon_editsdocssurgeon_response updated_docresultr\/var/www/html/env_mimamsha/lib/python3.10/site-packages/stanza/tests/server/test_ssurgeon.pytest_ssurgeon_same_length%s   ra # text = Jennifer has lovely antennae. # sent_id = 12 # comment = if you're in to that kind of thing 1 Jennifer Jennifer PROPN NNP Number=Sing 2 nsubj _ start_char=0|end_char=8|ner=S-PERSON 2 has have VERB VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 0 root _ start_char=9|end_char=12|ner=O 3 lovely lovely ADJ JJ Degree=Pos 4 amod _ start_char=13|end_char=19|ner=O 4 antennae antenna NOUN NNS Number=Plur 2 obj _ start_char=20|end_char=28|ner=O|SpaceAfter=No 5 . . PUNCT . _ 2 punct _ start_char=28|end_char=29|ner=O a # text = Jennifer has lovely blue antennae. # sent_id = 12 # comment = if you're in to that kind of thing 1 Jennifer Jennifer PROPN NNP Number=Sing 2 nsubj _ ner=S-PERSON 2 has have VERB VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 0 root _ ner=O 3 lovely lovely ADJ JJ Degree=Pos 5 amod _ ner=O 4 blue blue ADJ JJ _ 5 amod _ ner=O 5 antennae antenna NOUN NNS Number=Plur 2 obj _ SpaceAfter=No|ner=O 6 . . PUNCT . _ 2 punct _ ner=O cCr)Nz'{word:antennae}=antennae !> {word:blue}znaddDep -gov antennae -reln amod -word blue -lemma blue -cpos ADJ -pos JJ -ner O -position -antennae -after " "rr) rrADD_WORD_DOC_INPUTr r r r rADD_WORD_DOC_EXPECTEDrrrrtest_ssurgeon_different_lengthLs   ra # sent_id = 25 # text = It's not yours! # comment = negation 1 It it PRON PRP Number=Sing|Person=2|PronType=Prs 4 nsubj _ SpaceAfter=No 2 's be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 4 cop _ _ 3 not not PART RB Polarity=Neg 4 advmod _ _ 4 yours yours PRON PRP Gender=Neut|Number=Sing|Person=2|Poss=Yes|PronType=Prs 0 root _ SpaceAfter=No 5 ! ! PUNCT . _ 4 punct _ _ a # sent_id = 25 # text = It's not yours! # comment = negation 1-2 It's _ _ _ _ _ _ _ _ 1 It it PRON PRP Number=Sing|Person=2|PronType=Prs 4 nsubj _ _ 2 's be AUX VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 4 cop _ _ 3 not not PART RB Polarity=Neg 4 advmod _ _ 4 yours yours PRON PRP Gender=Neut|Number=Sing|Person=2|Poss=Yes|PronType=Prs 0 root _ SpaceAfter=No 5 ! ! PUNCT . _ 4 punct _ _ cCJd}ddg}tjtd}t|||}t||}d|}t|tdS)zN Test that converting a document, adding a new MWT, works as expected {word:It}=it . {word:/'s/}=sBEditNode -node it -is_mwt true -is_first_mwt true -mwt_text It'sBEditNode -node s -is_mwt true -is_first_mwt false -mwt_text It'srrN) rrBECOME_MWT_DOC_INPUTr r r r rBECOME_MWT_DOC_EXPECTEDrrrrtest_ssurgeon_become_mwtts   r"u # sent_id = newsgroup-groups.google.com_GayMarriage_0ccbb50b41a5830b_ENG_20050321_181500-0005 # text = One of “NCRC4ME’s” 1 One one NUM CD NumType=Card 0 root 0:root _ 2 of of ADP IN _ 4 case 4:case _ 3 “ " PUNCT `` _ 4 punct 4:punct SpaceAfter=No 4-5 NCRC4ME’s _ _ _ _ _ _ _ SpaceAfter=No 4 NCRC4ME NCRC4ME PROPN NNP Number=Sing 1 compound 1:compound _ 5 ’s 's PART POS _ 4 case 4:case _ 6 ” " PUNCT '' _ 4 punct 4:punct _ u # sent_id = newsgroup-groups.google.com_GayMarriage_0ccbb50b41a5830b_ENG_20050321_181500-0005 # text = One of “NCRC4ME’s” 1 One one NUM CD NumType=Card 0 root _ _ 2 of of ADP IN _ 4 case _ _ 3 “ " PUNCT `` _ 4 punct _ SpaceAfter=No 4-5 NCRC4ME’s _ _ _ _ _ _ _ SpaceAfter=No 4 NCRC4ME NCRC4ME PROPN NNP Number=Sing 1 compound _ _ 5 ’s 's PART POS _ 4 case _ _ 6 ” " PUNCT '' _ 4 punct _ _ cCr)a Test that converting a document with an MWT works as expected Note regarding this test: Currently it works because ssurgeon.py doesn't look at the "changed" flag because of a bug in EditNode in CoreNLP 4.5.3 If that is fixed, but the enhanced dependencies aren't fixed, this test will fail because the enhanced dependencies *aren't* removed. Fixing the enhanced dependencies as well will fix that, though. rrrrrN) rrEXISTING_MWT_DOC_INPUTr r r r rEXISTING_MWT_DOC_EXPECTEDrrrr$test_ssurgeon_existing_mwt_no_changes    r%FcCs||dur|}tj|d}t|g}t||}d|}|r7tdt|tdt|tdt|t||dS)NrrINPUTEXPECTEDRESULT)rrr process_docr r printr) input_textexpectedechorrrrrrrcheck_empty_tests    r.a # sent_id = train_78 # text = @user dovrebbe fare pace col cervello # twittiro = IMPLICIT ANALOGY 1 @user @user SYM SYM _ 3 nsubj _ _ 2 dovrebbe dovere AUX VM Mood=Cnd|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 3 aux _ _ 3 fare fare VERB V VerbForm=Inf 0 root _ _ 4 pace pace NOUN S Gender=Fem|Number=Sing 3 obj _ _ 5-6 col _ _ _ _ _ _ _ _ 5 con con ADP E _ 7 case _ _ 6 il il DET RD Definite=Def|Gender=Masc|Number=Sing|PronType=Art 7 det _ _ 7 cervello cervello NOUN S Gender=Masc|Number=Sing 3 obl _ _ cC ttdS)z Test that an MWT which is split into pieces which don't make up the original token results in a correct #text annotation For example, in Italian, "col" splits into "con il", and we want the #text to contain "col" N)r.ITALIAN_MWT_INPUTrrrrtest_ssurgeon_mwt_texts r1u1 # sent_id = train_1114 # text = ““““ buona scuola ““““ # twittiro = EXPLICIT OTHER 1 “ “ PUNCT FB _ 6 punct _ SpaceAfter=No 2 “ “ PUNCT FB _ 6 punct _ SpaceAfter=No 3 “ “ PUNCT FB _ 6 punct _ SpaceAfter=No 4 “ “ PUNCT FB _ 6 punct _ _ 5 buona buono ADJ A Gender=Fem|Number=Sing 6 amod _ _ 6 scuola scuola NOUN S Gender=Fem|Number=Sing 0 root _ _ 7 “ “ PUNCT FB _ 6 punct _ SpaceAfter=No 8 “ “ PUNCT FB _ 6 punct _ SpaceAfter=No 9 “ “ PUNCT FB _ 6 punct _ SpaceAfter=No 10 “ “ PUNCT FB _ 6 punct _ SpacesAfter=\n u> # sent_id = train_1114 # text = ““““ buona scuola ““““ # twittiro = EXPLICIT OTHER 1 “ “ PUNCT FB _ 6 punct _ SpaceAfter=No 2 “ “ PUNCT FB _ 6 punct _ SpaceAfter=No 3 “ “ PUNCT FB _ 6 punct _ SpaceAfter=No 4 “ “ PUNCT FB _ 6 punct _ SpaceAfter=Yes 5 buona buono ADJ A Gender=Fem|Number=Sing 6 amod _ _ 6 scuola scuola NOUN S Gender=Fem|Number=Sing 0 root _ _ 7 “ “ PUNCT FB _ 6 punct _ SpaceAfter=No 8 “ “ PUNCT FB _ 6 punct _ SpaceAfter=No 9 “ “ PUNCT FB _ 6 punct _ SpaceAfter=No 10 “ “ PUNCT FB _ 6 punct _ SpacesAfter=\n cCr/)z Test that SpacesAfter goes and comes back the same way Tested using some random example from the UD_Italian-TWITTIRO dataset N)r.ITALIAN_SPACES_AFTER_INPUTrrrrtest_ssurgeon_spaces_after_text r3cCstttdS)z? Test that an unnecessary SpaceAfter=Yes is eliminated N)r.ITALIAN_SPACES_AFTER_YES_INPUTr2rrrrtest_ssurgeon_spaces_after_yes sr6ai # text = Jennifer has lovely antennae. # sent_id = 12 # comment = if you're in to that kind of thing 1 Jennifer _ _ _ Number=Sing 2 nsubj _ ner=S-PERSON 2 has _ _ _ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 0 root _ ner=O 3 lovely _ _ _ Degree=Pos 4 amod _ ner=O 4 antennae _ _ _ Number=Plur 2 obj _ SpaceAfter=No|ner=O 5 . _ _ _ _ 2 punct _ ner=O cCr/z Check that various None fields such as lemma & xpos are not turned into blanks Tests, like regulations, are often written in blood N)r.EMPTY_VALUES_INPUTrrrrtest_ssurgeon_blank_valuesr4r9ug # sent_id = 1 # text = 你喺度搵乜嘢呀？ 1 你 你 PRON _ _ 3 nsubj _ Translit=nei5|Gloss=2SG|SpaceAfter=No 2 喺度 喺度 ADV _ _ 3 advmod _ Translit=hai2dou6|Gloss=PROG|SpaceAfter=No 3 搵 搵 VERB _ _ 0 root _ Translit=wan2|Gloss=find|SpaceAfter=No 4 乜嘢 乜嘢 PRON _ _ 3 obj _ Translit=mat1je5|Gloss=what|SpaceAfter=No 5 呀 呀 PART _ _ 3 discourse:sp _ Translit=aa3|Gloss=SFP|SpaceAfter=No 6 ？ ？ PUNCT _ _ 3 punct _ SpaceAfter=No # sent_id = 2 # text = 咪執返啲嘢去阿哥個新屋度囖。 1 咪 咪 ADV _ _ 2 advmod _ SpaceAfter=No 2 執 執 VERB _ _ 0 root _ SpaceAfter=No 3 返 返 VERB _ _ 2 compound:dir _ SpaceAfter=No 4 啲 啲 NOUN _ NounType=Clf 5 clf:det _ SpaceAfter=No 5 嘢 嘢 NOUN _ _ 3 obj _ SpaceAfter=No 6 去 去 VERB _ _ 2 conj _ SpaceAfter=No 7 阿哥 阿哥 NOUN _ _ 10 nmod _ SpaceAfter=No 8 個 個 NOUN _ NounType=Clf 10 clf:det _ SpaceAfter=No 9 新 新 ADJ _ _ 10 amod _ SpaceAfter=No 10 屋 屋 NOUN _ _ 6 obj _ SpaceAfter=No 11 度 度 ADP _ _ 10 case:loc _ SpaceAfter=No 12 囖 囖 PART _ _ 2 discourse:sp _ SpaceAfter=No 13 。 。 PUNCT _ _ 2 punct _ SpaceAfter=No cCr/r7)r.CANTONESE_MISC_WORDS_INPUTrrrrtest_ssurgeon_misc_wordsAr4r;a # sent_id = train_78 # text = @user dovrebbe fare pace colcervello # twittiro = IMPLICIT ANALOGY 1 @user @user SYM SYM _ 3 nsubj _ _ 2 dovrebbe dovere AUX VM Mood=Cnd|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 3 aux _ _ 3 fare fare VERB V VerbForm=Inf 0 root _ _ 4 pace pace NOUN S Gender=Fem|Number=Sing 3 obj _ _ 5-6 col _ _ _ _ _ _ _ SpaceAfter=No 5 con con ADP E _ 7 case _ _ 6 il il DET RD Definite=Def|Gender=Masc|Number=Sing|PronType=Art 7 det _ _ 7 cervello cervello NOUN S Gender=Masc|Number=Sing 3 obl _ RandomFeature=foo cCr/z Check the SpaceAfter=No on an MWT (rather than a word) the RandomFeature=foo is on account of a silly bug in the initial version of passing in MWT misc features N)r.ITALIAN_MWT_SPACE_AFTER_INPUTrrrrtest_ssurgeon_mwt_space_afterW r>aa # sent_id = train_78 # text = @user dovrebbe farepacecolcervello # twittiro = IMPLICIT ANALOGY 1 @user @user SYM SYM _ 3 nsubj _ _ 2 dovrebbe dovere AUX VM Mood=Cnd|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 3 aux _ _ 3-4 farepace _ _ _ _ _ _ _ Players=GonnaPlay|SpaceAfter=No 3 fare fare VERB V VerbForm=Inf 0 root _ _ 4 pace pace NOUN S Gender=Fem|Number=Sing 3 obj _ _ 5-6 col _ _ _ _ _ _ _ Haters=GonnaHate|SpaceAfter=No 5 con con ADP E _ 7 case _ _ 6 il il DET RD Definite=Def|Gender=Masc|Number=Sing|PronType=Art 7 det _ _ 7 cervello cervello NOUN S Gender=Masc|Number=Sing 3 obl _ RandomFeature=foo cCr/r<)r.ITALIAN_MWT_MISC_INPUTrrrrtest_ssurgeon_mwt_miscor?rAu` # sent_id = 1 # text = غلام رهڻ سان ماڻهو منافق ٿئي ٿو . 1 غلام غلام NOUN NN__اسم Case=Acc|Gender=Masc|Number=Sing|Person=3 2 compound _ _ 2 رهڻ ره VERB VB__فعل Number=Sing 6 advcl _ _ 3 سان سان ADP IN__حرفِ_جر Number=Sing 2 mark _ _ 4 ماڻهو ماڻهو NOUN NN__اسم Case=Nom|Gender=Masc|Number=Sing|Person=3 6 nsubj _ _ 5 منافق منافق ADJ JJ__صفت Case=Acc|Number=Sing|Person=3 6 xcomp _ _ 6 ٿئي ٿي VERB VB__فعل Number=Sing _ _ _ _ 7 ٿو ٿو AUX VB__فعل Number=Sing 6 aux _ _ 8 . . PUNCT -__پورو_دم _ 6 punct _ _ uc # sent_id = 1 # text = غلام رهڻ سان ماڻهو منافق ٿئي ٿو . 1 غلام غلام NOUN NN__اسم Case=Acc|Gender=Masc|Number=Sing|Person=3 2 compound _ _ 2 رهڻ ره VERB VB__فعل Number=Sing 6 advcl _ _ 3 سان سان ADP IN__حرفِ_جر Number=Sing 2 mark _ _ 4 ماڻهو ماڻهو NOUN NN__اسم Case=Nom|Gender=Masc|Number=Sing|Person=3 6 nsubj _ _ 5 منافق منافق ADJ JJ__صفت Case=Acc|Number=Sing|Person=3 6 xcomp _ _ 6 ٿئي ٿي VERB VB__فعل Number=Sing 0 root _ _ 7 ٿو ٿو AUX VB__فعل Number=Sing 6 aux _ _ 8 . . PUNCT -__پورو_دم _ 6 punct _ _ z {}=root !< {} setRoots root cCsxtt}tjddgddddg}||ksJtjtd}t||}t||}t ||}d |}|t ks:Jd S) zF A user / contributor sent a dependency file with blank roots z {}=root !< {}z setRoots root1UniversalEnglish)rr ssurgeon_idnoteslanguagerrN) r parse_ssurgeon_edits SINDHI_EDIT SsurgeonEditrrSINDHI_ROOT_EXAMPLE build_requestr)r r SINDHI_ROOT_EXPECTED)editsexpected_edits blank_dep_docrequestresponserrrrr"test_ssurgeon_rewrite_sindhi_rootss       rS)NF)-pytest stanza.testsrmarktravisclient pytestmarkstanza.utils.conllrstanza.server.ssurgeonserverr r rrrrrr r!r"r#r$r%r.r0r1r2r5r3r6r8r9r:r;r=r>r@rAlstriprKstriprMrIrSrrrrsP