o
    h(                  
   @   s   d Z ddlZddlZddlmZ ddlmZ ddlm	Z	m
Z
 ejjZdZdZdZdZd	d
dddddddd	Zdd
dddddddZdZdZdZeee	 ddd ZdZddddd d!Zd"ZG d#d$ d$ZdS )%z1
Tests for setting request properties of servers
    N)Document)TEST_WORKING_DIRcompare_ignoring_whitespacezJoe Smith lives in 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=.]
zKAngela Merkel ist seit 2005 Bundeskanzlerin der Bundesrepublik Deutschland.a  
Sentence #1 (10 tokens):
Angela Merkel ist seit 2005 Bundeskanzlerin der Bundesrepublik Deutschland.

Tokens:
[Text=Angela CharacterOffsetBegin=0 CharacterOffsetEnd=6 PartOfSpeech=PROPN]
[Text=Merkel CharacterOffsetBegin=7 CharacterOffsetEnd=13 PartOfSpeech=PROPN]
[Text=ist CharacterOffsetBegin=14 CharacterOffsetEnd=17 PartOfSpeech=AUX]
[Text=seit CharacterOffsetBegin=18 CharacterOffsetEnd=22 PartOfSpeech=ADP]
[Text=2005 CharacterOffsetBegin=23 CharacterOffsetEnd=27 PartOfSpeech=NUM]
[Text=Bundeskanzlerin CharacterOffsetBegin=28 CharacterOffsetEnd=43 PartOfSpeech=NOUN]
[Text=der CharacterOffsetBegin=44 CharacterOffsetEnd=47 PartOfSpeech=DET]
[Text=Bundesrepublik CharacterOffsetBegin=48 CharacterOffsetEnd=62 PartOfSpeech=PROPN]
[Text=Deutschland CharacterOffsetBegin=63 CharacterOffsetEnd=74 PartOfSpeech=PROPN]
[Text=. CharacterOffsetBegin=74 CharacterOffsetEnd=75 PartOfSpeech=PUNCT]
ztokenize,ssplit,mwt,pos,parsefrz3edu/stanford/nlp/models/pos-tagger/french-ud.taggerz0edu/stanford/nlp/models/srparser/frenchSR.ser.gzz1edu/stanford/nlp/models/mwt/french/french-mwt.tsvz4edu/stanford/nlp/models/mwt/french/french-mwt.taggerz=edu/stanford/nlp/models/mwt/french/french-mwt-statistical.tsvfalsetext)	
annotatorstokenize.language	pos.modelzparse.modelmwt.mappingFilemwt.pos.modelmwt.statisticalMappingFilemwt.preserveCasingoutputFormatz tokenize,ssplit,mwt,pos,depparsez1edu/stanford/nlp/models/parser/nndep/UD_French.gz)r   r	   r
   r   r   r   r   depparse.modelug   Cette enquête préliminaire fait suite aux révélations de l’hebdomadaire quelques jours plus tôt.u  
Sentence #1 (16 tokens):
Cette enquête préliminaire fait suite aux révélations de l’hebdomadaire quelques jours plus tôt.

Tokens:
[Text=Cette CharacterOffsetBegin=0 CharacterOffsetEnd=5 PartOfSpeech=DET]
[Text=enquête CharacterOffsetBegin=6 CharacterOffsetEnd=13 PartOfSpeech=NOUN]
[Text=préliminaire CharacterOffsetBegin=14 CharacterOffsetEnd=26 PartOfSpeech=ADJ]
[Text=fait CharacterOffsetBegin=27 CharacterOffsetEnd=31 PartOfSpeech=VERB]
[Text=suite CharacterOffsetBegin=32 CharacterOffsetEnd=37 PartOfSpeech=NOUN]
[Text=à CharacterOffsetBegin=38 CharacterOffsetEnd=41 PartOfSpeech=ADP]
[Text=les CharacterOffsetBegin=38 CharacterOffsetEnd=41 PartOfSpeech=DET]
[Text=révélations CharacterOffsetBegin=42 CharacterOffsetEnd=53 PartOfSpeech=NOUN]
[Text=de CharacterOffsetBegin=54 CharacterOffsetEnd=56 PartOfSpeech=ADP]
[Text=l’ CharacterOffsetBegin=57 CharacterOffsetEnd=59 PartOfSpeech=NOUN]
[Text=hebdomadaire CharacterOffsetBegin=59 CharacterOffsetEnd=71 PartOfSpeech=ADJ]
[Text=quelques CharacterOffsetBegin=72 CharacterOffsetEnd=80 PartOfSpeech=DET]
[Text=jours CharacterOffsetBegin=81 CharacterOffsetEnd=86 PartOfSpeech=NOUN]
[Text=plus CharacterOffsetBegin=87 CharacterOffsetEnd=91 PartOfSpeech=ADV]
[Text=tôt CharacterOffsetBegin=92 CharacterOffsetEnd=95 PartOfSpeech=ADV]
[Text=. CharacterOffsetBegin=95 CharacterOffsetEnd=96 PartOfSpeech=PUNCT]

Constituency parse: 
(ROOT
  (SENT
    (NP (DET Cette)
      (MWN (NOUN enquête) (ADJ préliminaire)))
    (VN
      (MWV (VERB fait) (NOUN suite)))
    (PP (ADP à)
      (NP (DET les) (NOUN révélations)
        (PP (ADP de)
          (NP (NOUN l’)
            (AP (ADJ hebdomadaire))))))
    (NP (DET quelques) (NOUN jours))
    (AdP (ADV plus) (ADV tôt))
    (PUNCT .)))
u>  
Sentence #1 (16 tokens):
Cette enquête préliminaire fait suite aux révélations de l’hebdomadaire quelques jours plus tôt.

Tokens:
[Text=Cette CharacterOffsetBegin=0 CharacterOffsetEnd=5 PartOfSpeech=DET]
[Text=enquête CharacterOffsetBegin=6 CharacterOffsetEnd=13 PartOfSpeech=NOUN]
[Text=préliminaire CharacterOffsetBegin=14 CharacterOffsetEnd=26 PartOfSpeech=ADJ]
[Text=fait CharacterOffsetBegin=27 CharacterOffsetEnd=31 PartOfSpeech=VERB]
[Text=suite CharacterOffsetBegin=32 CharacterOffsetEnd=37 PartOfSpeech=NOUN]
[Text=à CharacterOffsetBegin=38 CharacterOffsetEnd=41 PartOfSpeech=ADP]
[Text=les CharacterOffsetBegin=38 CharacterOffsetEnd=41 PartOfSpeech=DET]
[Text=révélations CharacterOffsetBegin=42 CharacterOffsetEnd=53 PartOfSpeech=NOUN]
[Text=de CharacterOffsetBegin=54 CharacterOffsetEnd=56 PartOfSpeech=ADP]
[Text=l’ CharacterOffsetBegin=57 CharacterOffsetEnd=59 PartOfSpeech=NOUN]
[Text=hebdomadaire CharacterOffsetBegin=59 CharacterOffsetEnd=71 PartOfSpeech=ADJ]
[Text=quelques CharacterOffsetBegin=72 CharacterOffsetEnd=80 PartOfSpeech=DET]
[Text=jours CharacterOffsetBegin=81 CharacterOffsetEnd=86 PartOfSpeech=NOUN]
[Text=plus CharacterOffsetBegin=87 CharacterOffsetEnd=91 PartOfSpeech=ADV]
[Text=tôt CharacterOffsetBegin=92 CharacterOffsetEnd=95 PartOfSpeech=ADV]
[Text=. CharacterOffsetBegin=95 CharacterOffsetEnd=96 PartOfSpeech=PUNCT]

Dependency Parse (enhanced plus plus dependencies):
root(ROOT-0, fait-4)
det(enquête-2, Cette-1)
nsubj(fait-4, enquête-2)
amod(enquête-2, préliminaire-3)
obj(fait-4, suite-5)
case(révélations-8, à-6)
det(révélations-8, les-7)
obl:à(fait-4, révélations-8)
case(l’-10, de-9)
nmod:de(révélations-8, l’-10)
amod(révélations-8, hebdomadaire-11)
det(jours-13, quelques-12)
obl(fait-4, jours-13)
advmod(tôt-15, plus-14)
advmod(jours-13, tôt-15)
punct(fait-4, .-16)
z/out/example_french.jsonzutf-8)encodingu:   Andrés Manuel López Obrador es el presidente de México.esz4edu/stanford/nlp/models/pos-tagger/spanish-ud.taggerz3edu/stanford/nlp/models/mwt/spanish/spanish-mwt.tsvz2edu/stanford/nlp/models/parser/nndep/UD_Spanish.gz)r   r	   r
   r   r   u  
Sentence #1 (10 tokens):
Andrés Manuel López Obrador es el presidente de México.

Tokens:
[Text=Andrés CharacterOffsetBegin=0 CharacterOffsetEnd=6 PartOfSpeech=PROPN]
[Text=Manuel CharacterOffsetBegin=7 CharacterOffsetEnd=13 PartOfSpeech=PROPN]
[Text=López CharacterOffsetBegin=14 CharacterOffsetEnd=19 PartOfSpeech=PROPN]
[Text=Obrador CharacterOffsetBegin=20 CharacterOffsetEnd=27 PartOfSpeech=PROPN]
[Text=es CharacterOffsetBegin=28 CharacterOffsetEnd=30 PartOfSpeech=AUX]
[Text=el CharacterOffsetBegin=31 CharacterOffsetEnd=33 PartOfSpeech=DET]
[Text=presidente CharacterOffsetBegin=34 CharacterOffsetEnd=44 PartOfSpeech=NOUN]
[Text=de CharacterOffsetBegin=45 CharacterOffsetEnd=47 PartOfSpeech=ADP]
[Text=México CharacterOffsetBegin=48 CharacterOffsetEnd=54 PartOfSpeech=PROPN]
[Text=. CharacterOffsetBegin=54 CharacterOffsetEnd=55 PartOfSpeech=PUNCT]

Dependency Parse (enhanced plus plus dependencies):
root(ROOT-0, presidente-7)
nsubj(presidente-7, Andrés-1)
flat(Andrés-1, Manuel-2)
flat(Andrés-1, López-3)
flat(Andrés-1, Obrador-4)
cop(presidente-7, es-5)
det(presidente-7, el-6)
case(México-9, de-8)
nmod:de(presidente-7, México-9)
punct(presidente-7, .-10)
c                   @   s@   e Zd Zejdddd Zdd Zdd Zd	d
 Zdd Z	dS )TestServerRequestclass)scopec                 c   s"    t jddd}|V  |  dS )z Client to run tests on ztokenize,ssplit,posstanza_request_tests_server)r   	server_idN)corenlpCoreNLPClientstop)selfclient r   b/var/www/html/env_mimamsha/lib/python3.10/site-packages/stanza/tests/server/test_server_request.pycorenlp_client   s   z TestServerRequest.corenlp_clientc                 C   s4   |j tdd}t|t | t}t|tsJ dS )zJ Basic test of making a request, test default output format is a Document r   )output_formatN)annotateEN_DOCr   EN_DOC_GOLD
isinstancer   r   r   annr   r   r   
test_basic   s   

zTestServerRequest.test_basicc                 C   s6   |j ttdd}t|t |j ttd}t|t dS )zB Test using a Python dictionary to specify all request properties r   
propertiesr    )r)   N)r!   ES_DOCES_PROPSr   ES_PROPS_GOLD
FRENCH_DOCFRENCH_CUSTOM_PROPSFRENCH_CUSTOM_GOLDr%   r   r   r   test_python_dict   s   
z"TestServerRequest.test_python_dictc                 C   s   |j tddd}t|t dS )zG Test using a Stanford CoreNLP supported languages as a properties key germanr   r(   N)r!   
GERMAN_DOCr   GERMAN_DOC_GOLDr%   r   r   r   test_lang_setting   s   z#TestServerRequest.test_lang_settingc                 C   s"   |j ttddd}|tksJ dS )z/ Test setting the annotators and output_format ztokenize,ssplit,mwt,posjson)r)   r   r    N)r!   r-   FRENCH_EXTRA_PROPSFRENCH_JSON_GOLDr%   r   r   r   !test_annotators_and_output_format   s   z3TestServerRequest.test_annotators_and_output_formatN)
__name__
__module____qualname__pytestfixturer   r'   r0   r4   r8   r   r   r   r   r      s    

r   )__doc__r5   r<   stanza.serverserverr   stanza.protobufr   stanza.testsr   r   markr   
pytestmarkr"   r#   r2   r3   r.   r6   r-   r/   FRENCH_EXTRA_GOLDloadsopenreadr7   r*   r+   r,   r   r   r   r   r   <module>   sT    
	')