o h@spdZddlZddlZddlmZddlmZejj Z dZ dZ dZ ddZd d Zd Zd Zd ZddZddZdS)z Misc tests for the server N)compare_ignoring_whitespacezJoe Smith lives in California.a Sentence #1 (6 tokens): Joe Smith lives in California. Tokens: [Text=Joe CharacterOffsetBegin=0 CharacterOffsetEnd=3 PartOfSpeech=NNP Lemma=Joe NamedEntityTag=PERSON] [Text=Smith CharacterOffsetBegin=4 CharacterOffsetEnd=9 PartOfSpeech=NNP Lemma=Smith NamedEntityTag=PERSON] [Text=lives CharacterOffsetBegin=10 CharacterOffsetEnd=15 PartOfSpeech=VBZ Lemma=live NamedEntityTag=O] [Text=in CharacterOffsetBegin=16 CharacterOffsetEnd=18 PartOfSpeech=IN Lemma=in NamedEntityTag=O] [Text=California CharacterOffsetBegin=19 CharacterOffsetEnd=29 PartOfSpeech=NNP Lemma=California NamedEntityTag=STATE_OR_PROVINCE] [Text=. CharacterOffsetBegin=29 CharacterOffsetEnd=30 PartOfSpeech=. Lemma=. NamedEntityTag=O] Dependency Parse (enhanced plus plus dependencies): root(ROOT-0, lives-3) compound(Smith-2, Joe-1) nsubj(lives-3, Smith-2) case(California-5, in-4) obl:in(lives-3, California-5) punct(lives-3, .-6) Extracted the following NER entity mentions: Joe Smith PERSON PERSON:0.9972202681743931 California STATE_OR_PROVINCE LOCATION:0.9990868267559281 Extracted the following KBP triples: 1.0 Joe Smith per:statesorprovinces_of_residence California a Sentence #1 (6 tokens): Joe Smith lives in California. Tokens: [Text=Joe CharacterOffsetBegin=0 CharacterOffsetEnd=3 PartOfSpeech=NNP] [Text=Smith CharacterOffsetBegin=4 CharacterOffsetEnd=9 PartOfSpeech=NNP] [Text=lives CharacterOffsetBegin=10 CharacterOffsetEnd=15 PartOfSpeech=VBZ] [Text=in CharacterOffsetBegin=16 CharacterOffsetEnd=18 PartOfSpeech=IN] [Text=California CharacterOffsetBegin=19 CharacterOffsetEnd=29 PartOfSpeech=NNP] [Text=. CharacterOffsetBegin=29 CharacterOffsetEnd=30 PartOfSpeech=.] cCstjddd}|jtddd}t|tWdn1swYtjddd}|jtdd }t|tWddS1sCwYdS) zd Test case of starting server with Spanish defaults, and then requesting default English properties spanishtest_spanish_english_request) properties server_idenglishtext)r output_formatNtest_english_request)r )corenlp CoreNLPClientannotateEN_DOCr EN_DOC_GOLD)clientannr_/var/www/html/env_mimamsha/lib/python3.10/site-packages/stanza/tests/server/test_server_misc.pyr 8s  "r c Cstjddgdd0}tjddgdd }|t}Wdn1s%wYWddSWddS1s=wYdS) z Test case of creating a client with start_server=False and a set of annotators The annotators should be used instead of the server's default annotators test_default_annotatorsr)tokenizessplitposlemmanerdepparse)rr annotatorsF)rrr) start_serverr rN)r r r r)rclient2rrrrrEs "r)r)) ))rr )r# ) )uI am 𝒚̂𝒊 random textcCstjddgddidH}|t}ttttD]2\}\}}|jdj |}|j |dks/J|j |dks8J|j |dksAJ|j |dksJJqWddS1sVwYdS) z? Test case of asking for codepoints from the English tokenizer rrtokenize.codepointtruerrrrN)r r r codepoint_doc enumeratezipexpected_codepointsexpected_characterssentencetokencodepointOffsetBegincodepointOffsetEnd beginCharendChar)rri codepoints charactersr7rrrtest_codepointsVs  "r?cCsd}tjddgddidJ}||}|jdjdj}|jdjdj}|||}|d ks1J|jd jdj}|jd jdj}|||}|d ksOJWd d S1sZwYd S) zD Test case of extracting the correct sentence text using codepoints u0Unban mox opal 🐱. This is a second sentence.rrr.r/r0ruUnban mox opal 🐱.rzThis is a second sentence.N)r r r r6r7r8r9)rrr text_starttext_end sentence_textrrrtest_codepoint_textbs     "rD)__doc__pytestre stanza.serverserverr stanza.testsrmarkr pytestmarkrrEN_DOC_POS_ONLY_GOLDr rr4r5r1r?rDrrrrs