From 83dee04507d4cf3096075916af0991f935419135 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micha=C5=82=20Pogoda?= <mipo57@e-science.pl>
Date: Thu, 9 Feb 2023 14:30:35 +0100
Subject: [PATCH] Added integration tests
---
tests/{detectors => integration}/__init__.py | 0
.../ccl_configuration}/__init__.py | 0
.../marek_kowalski_pojechal_do_wroclawia.ccl | 112 ++++++++++++++++++
.../test_ccl_configuration.py | 11 ++
.../__init__.py | 0
.../test_wiktorner_jsonl_configuration.py | 11 ++
.../wiktorner_jsonl.jsonl | 1 +
tests/{detectors/ner => unit}/__init__.py | 0
.../phone => unit/detectors}/__init__.py | 0
.../url => unit/detectors/date}/__init__.py | 0
tests/{ => unit}/detectors/date/test_en.py | 0
tests/{ => unit}/detectors/date/test_pl.py | 0
tests/{ => unit}/detectors/date/test_ru.py | 0
.../user => unit/detectors/email}/__init__.py | 0
.../{ => unit}/detectors/email/test_email.py | 0
.../detectors/ner}/__init__.py | 0
tests/{ => unit}/detectors/ner/test_ner.py | 0
.../detectors/phone}/__init__.py | 0
.../{ => unit}/detectors/phone/test_phone.py | 0
.../detectors/url}/__init__.py | 0
tests/{ => unit}/detectors/url/test_url.py | 0
.../detectors/user}/__init__.py | 0
tests/{ => unit}/detectors/user/test_user.py | 0
.../dictionaries}/__init__.py | 0
.../dictionaries/morphosyntactic/__init__.py | 0
.../morphosyntactic/test_ner_file.py | 0
.../morphosyntactic/test_ner_file_nkjp.py | 0
tests/unit/input_parsers/__init__.py | 0
tests/{ => unit}/input_parsers/test_ccl.py | 0
.../input_parsers/test_wiktor_ner.py | 0
tests/unit/pipeline/__init__.py | 0
tests/{ => unit}/pipeline/test_default.py | 0
.../pipeline/test_sequential_jsonl.py | 0
tests/unit/replacers/__init__.py | 0
.../replacers/test_date_replacer.py | 0
.../replacers/test_email_replacer.py | 0
.../{ => unit}/replacers/test_ner_replacer.py | 0
.../{ => unit}/replacers/test_tag_replacer.py | 0
.../replacers/test_user_replacer.py | 0
.../suppressors/test_order_based.py | 0
tests/{ => unit}/test_annotation_mapping.py | 0
tests/{ => unit}/test_string_replacements.py | 0
42 files changed, 135 insertions(+)
rename tests/{detectors => integration}/__init__.py (100%)
rename tests/{detectors/date => integration/ccl_configuration}/__init__.py (100%)
create mode 100644 tests/integration/ccl_configuration/marek_kowalski_pojechal_do_wroclawia.ccl
create mode 100644 tests/integration/ccl_configuration/test_ccl_configuration.py
rename tests/{detectors/email => integration/wiktorner_jsonl_configuration}/__init__.py (100%)
create mode 100644 tests/integration/wiktorner_jsonl_configuration/test_wiktorner_jsonl_configuration.py
create mode 100644 tests/integration/wiktorner_jsonl_configuration/wiktorner_jsonl.jsonl
rename tests/{detectors/ner => unit}/__init__.py (100%)
rename tests/{detectors/phone => unit/detectors}/__init__.py (100%)
rename tests/{detectors/url => unit/detectors/date}/__init__.py (100%)
rename tests/{ => unit}/detectors/date/test_en.py (100%)
rename tests/{ => unit}/detectors/date/test_pl.py (100%)
rename tests/{ => unit}/detectors/date/test_ru.py (100%)
rename tests/{detectors/user => unit/detectors/email}/__init__.py (100%)
rename tests/{ => unit}/detectors/email/test_email.py (100%)
rename tests/{dictionaries => unit/detectors/ner}/__init__.py (100%)
rename tests/{ => unit}/detectors/ner/test_ner.py (100%)
rename tests/{dictionaries/morphosyntactic => unit/detectors/phone}/__init__.py (100%)
rename tests/{ => unit}/detectors/phone/test_phone.py (100%)
rename tests/{input_parsers => unit/detectors/url}/__init__.py (100%)
rename tests/{ => unit}/detectors/url/test_url.py (100%)
rename tests/{pipeline => unit/detectors/user}/__init__.py (100%)
rename tests/{ => unit}/detectors/user/test_user.py (100%)
rename tests/{replacers => unit/dictionaries}/__init__.py (100%)
create mode 100644 tests/unit/dictionaries/morphosyntactic/__init__.py
rename tests/{ => unit}/dictionaries/morphosyntactic/test_ner_file.py (100%)
rename tests/{ => unit}/dictionaries/morphosyntactic/test_ner_file_nkjp.py (100%)
create mode 100644 tests/unit/input_parsers/__init__.py
rename tests/{ => unit}/input_parsers/test_ccl.py (100%)
rename tests/{ => unit}/input_parsers/test_wiktor_ner.py (100%)
create mode 100644 tests/unit/pipeline/__init__.py
rename tests/{ => unit}/pipeline/test_default.py (100%)
rename tests/{ => unit}/pipeline/test_sequential_jsonl.py (100%)
create mode 100644 tests/unit/replacers/__init__.py
rename tests/{ => unit}/replacers/test_date_replacer.py (100%)
rename tests/{ => unit}/replacers/test_email_replacer.py (100%)
rename tests/{ => unit}/replacers/test_ner_replacer.py (100%)
rename tests/{ => unit}/replacers/test_tag_replacer.py (100%)
rename tests/{ => unit}/replacers/test_user_replacer.py (100%)
rename tests/{ => unit}/suppressors/test_order_based.py (100%)
rename tests/{ => unit}/test_annotation_mapping.py (100%)
rename tests/{ => unit}/test_string_replacements.py (100%)
diff --git a/tests/detectors/__init__.py b/tests/integration/__init__.py
similarity index 100%
rename from tests/detectors/__init__.py
rename to tests/integration/__init__.py
diff --git a/tests/detectors/date/__init__.py b/tests/integration/ccl_configuration/__init__.py
similarity index 100%
rename from tests/detectors/date/__init__.py
rename to tests/integration/ccl_configuration/__init__.py
diff --git a/tests/integration/ccl_configuration/marek_kowalski_pojechal_do_wroclawia.ccl b/tests/integration/ccl_configuration/marek_kowalski_pojechal_do_wroclawia.ccl
new file mode 100644
index 0000000..453acb9
--- /dev/null
+++ b/tests/integration/ccl_configuration/marek_kowalski_pojechal_do_wroclawia.ccl
@@ -0,0 +1,112 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE chunkList SYSTEM "ccl.dtd">
+<chunkList>
+ <chunk type="p" id="ch1">
+ <sentence id="s1">
+ <tok>
+ <orth>Jan</orth>
+ <lex disamb="1"><base>Jan</base><ctag>subst:sg:nom:m1</ctag></lex>
+ <ann chan="person_first_nam" head="1">1</ann>
+ <ann chan="person_last_nam">0</ann>
+ <ann chan="city_nam">0</ann>
+ </tok>
+ <tok>
+ <orth>Kowalski</orth>
+ <lex disamb="1"><base>Kowalski</base><ctag>subst:sg:nom:m1</ctag></lex>
+ <ann chan="person_first_nam">0</ann>
+ <ann chan="person_last_nam" head="1">1</ann>
+ <ann chan="city_nam">0</ann>
+ </tok>
+ <tok>
+ <orth>(</orth>
+ <lex disamb="1"><base>(</base><ctag>interp</ctag></lex>
+ <ann chan="person_first_nam">0</ann>
+ <ann chan="person_last_nam">0</ann>
+ <ann chan="city_nam">0</ann>
+ </tok>
+ <ns/>
+ <tok>
+ <orth>numer</orth>
+ <lex disamb="1"><base>numer</base><ctag>subst:sg:nom:m3</ctag></lex>
+ <ann chan="person_first_nam">0</ann>
+ <ann chan="person_last_nam">0</ann>
+ <ann chan="city_nam">0</ann>
+ </tok>
+ <tok>
+ <orth>telefonu</orth>
+ <lex disamb="1"><base>telefon</base><ctag>subst:sg:gen:m3</ctag></lex>
+ <ann chan="person_first_nam">0</ann>
+ <ann chan="person_last_nam">0</ann>
+ <ann chan="city_nam">0</ann>
+ </tok>
+ <tok>
+ <orth>123</orth>
+ <lex disamb="1"><base>123</base><ctag>num:pl:nom:m1:rec</ctag></lex>
+ <ann chan="person_first_nam">0</ann>
+ <ann chan="person_last_nam">0</ann>
+ <ann chan="city_nam">0</ann>
+ </tok>
+ <ns/>
+ <tok>
+ <orth>-</orth>
+ <lex disamb="1"><base>-</base><ctag>interp</ctag></lex>
+ <ann chan="person_first_nam">0</ann>
+ <ann chan="person_last_nam">0</ann>
+ <ann chan="city_nam">0</ann>
+ </tok>
+ <ns/>
+ <tok>
+ <orth>456</orth>
+ <lex disamb="1"><base>456</base><ctag>num:pl:nom:m1:rec</ctag></lex>
+ <ann chan="person_first_nam">0</ann>
+ <ann chan="person_last_nam">0</ann>
+ <ann chan="city_nam">0</ann>
+ </tok>
+ <ns/>
+ <tok>
+ <orth>-</orth>
+ <lex disamb="1"><base>-</base><ctag>interp</ctag></lex>
+ <ann chan="person_first_nam">0</ann>
+ <ann chan="person_last_nam">0</ann>
+ <ann chan="city_nam">0</ann>
+ </tok>
+ <ns/>
+ <tok>
+ <orth>789</orth>
+ <lex disamb="1"><base>789</base><ctag>num:pl:nom:m1:rec</ctag></lex>
+ <ann chan="person_first_nam">0</ann>
+ <ann chan="person_last_nam">0</ann>
+ <ann chan="city_nam">0</ann>
+ </tok>
+ <ns/>
+ <tok>
+ <orth>)</orth>
+ <lex disamb="1"><base>)</base><ctag>interp</ctag></lex>
+ <ann chan="person_first_nam">0</ann>
+ <ann chan="person_last_nam">0</ann>
+ <ann chan="city_nam">0</ann>
+ </tok>
+ <tok>
+ <orth>miesza</orth>
+ <lex disamb="1"><base>mieszać</base><ctag>fin:sg:ter:imperf</ctag></lex>
+ <ann chan="person_first_nam">0</ann>
+ <ann chan="person_last_nam">0</ann>
+ <ann chan="city_nam">0</ann>
+ </tok>
+ <tok>
+ <orth>we</orth>
+ <lex disamb="1"><base>w</base><ctag>prep:acc:wok</ctag></lex>
+ <ann chan="person_first_nam">0</ann>
+ <ann chan="person_last_nam">0</ann>
+ <ann chan="city_nam">0</ann>
+ </tok>
+ <tok>
+ <orth>Wrocławiu</orth>
+ <lex disamb="1"><base>Wrocław</base><ctag>subst:sg:loc:m3</ctag></lex>
+ <ann chan="person_first_nam">0</ann>
+ <ann chan="person_last_nam">0</ann>
+ <ann chan="city_nam" head="1">1</ann>
+ </tok>
+ </sentence>
+ </chunk>
+</chunkList>
\ No newline at end of file
diff --git a/tests/integration/ccl_configuration/test_ccl_configuration.py b/tests/integration/ccl_configuration/test_ccl_configuration.py
new file mode 100644
index 0000000..3c6f4c3
--- /dev/null
+++ b/tests/integration/ccl_configuration/test_ccl_configuration.py
@@ -0,0 +1,11 @@
+from hydra import initialize, compose
+from hydra.utils import instantiate
+
+def test_ccl_configuration():
+ with initialize(config_path="../../../config", version_base="1.1"):
+ config = compose(config_name="config", overrides=["paths.root_path=../../../", "configuration=ccl"])
+ pipeline = instantiate(config.pipeline)
+
+ result = pipeline.run("./tests/integration/ccl_configuration/marek_kowalski_pojechal_do_wroclawia.ccl")
+
+ assert result == "[OSOBA] [OSOBA] (numer telefonu [DIGITS]) miesza we [MIEJSCE]"
\ No newline at end of file
diff --git a/tests/detectors/email/__init__.py b/tests/integration/wiktorner_jsonl_configuration/__init__.py
similarity index 100%
rename from tests/detectors/email/__init__.py
rename to tests/integration/wiktorner_jsonl_configuration/__init__.py
diff --git a/tests/integration/wiktorner_jsonl_configuration/test_wiktorner_jsonl_configuration.py b/tests/integration/wiktorner_jsonl_configuration/test_wiktorner_jsonl_configuration.py
new file mode 100644
index 0000000..8ce9678
--- /dev/null
+++ b/tests/integration/wiktorner_jsonl_configuration/test_wiktorner_jsonl_configuration.py
@@ -0,0 +1,11 @@
+from hydra import initialize, compose
+from hydra.utils import instantiate
+
+def test_wiktorner_jsonl_configuration():
+ with initialize(config_path="../../../config", version_base="1.1"):
+ config = compose(config_name="config", overrides=["paths.root_path=../../../", "configuration=wiktorner_jsonl"])
+ pipeline = instantiate(config.pipeline)
+
+ result = pipeline.run("./tests/integration/wiktorner_jsonl_configuration/wiktorner_jsonl.jsonl")
+
+ assert result == '{"text": "ROZDZIAŠI. CO NIECO O SAMEJ PIPIDÓWCE Przede wszystkim muszę uprzedzić z góry czytelników, aby się daremnie nie trudzili nad szukaniem wyżej wyrażonego miasteczka na mapach [MIEJSCE] i [MIEJSCE], bo go tam nie znajdą. Nie dlatego, jakoby [MIEJSCE] nie istniała w rzeczywistości i była tylko wytworem fantazji autora, ale po prostu dlatego, że mieszkańcy owego sławnego grodu, urosłszy z czasem w ambicję, uważali tę nazwę jako ubliżającą ich powadze i podali do c. k. namiestnictwa pokorną prośbę o pozwolenie zamienienia jej na inną. Podobne zamiany nazwisk praktykują się dość często w [MIEJSCE], szczególnie u pojedynczych osób, które nie czując się na siłach uszlachetnienia sobą, swymi czynami własnego nazwiska, chcą nazwiskiem uszlachetnić siebie, i tak np."}'
\ No newline at end of file
diff --git a/tests/integration/wiktorner_jsonl_configuration/wiktorner_jsonl.jsonl b/tests/integration/wiktorner_jsonl_configuration/wiktorner_jsonl.jsonl
new file mode 100644
index 0000000..89207fd
--- /dev/null
+++ b/tests/integration/wiktorner_jsonl_configuration/wiktorner_jsonl.jsonl
@@ -0,0 +1 @@
+{"filename": "bb4a16ff-33de-4478-939d-12db67d750b1","text": "ROZDZIAÅ I. CO NIECO O SAMEJ PIPIDÓWCE Przede wszystkim muszÄ™ uprzedzić z góry czytelników, aby siÄ™ daremnie nie trudzili nad szukaniem wyżej wyrażonego miasteczka na mapach Galicji i Lodomerii, bo go tam nie znajdÄ…. Nie dlatego, jakoby Pipidówka nie istniaÅ‚a w rzeczywistoÅ›ci i byÅ‚a tylko wytworem fantazji autora, ale po prostu dlatego, że mieszkaÅ„cy owego sÅ‚awnego grodu, urosÅ‚szy z czasem w ambicjÄ™, uważali tÄ™ nazwÄ™ jako ubliżajÄ…cÄ… ich powadze i podali do c. k. namiestnictwa pokornÄ… proÅ›bÄ™ o pozwolenie zamienienia jej na innÄ…. Podobne zamiany nazwisk praktykujÄ… siÄ™ dość czÄ™sto w Galicji, szczególnie u pojedynczych osób, które nie czujÄ…c siÄ™ na siÅ‚ach uszlachetnienia sobÄ…, swymi czynami wÅ‚asnego nazwiska, chcÄ… nazwiskiem uszlachetnić siebie, i tak np.","tokens": [{"index": 1,"position": [0,8],"orth": "ROZDZIAÅ","lexemes": [{"lemma": "rozdziaÅ‚","mstag": "subst:sg:nom:m3","disamb": true}]},{"index": 2,"position": [9,10],"orth": "I","lexemes": [{"lemma": "I","mstag": "adj:sg:nom:m3:pos","disamb": true}]},{"index": 3,"position": [10,11],"orth": ".","lexemes": [{"lemma": ".","mstag": "interp","disamb": true}]},{"index": 4,"position": [12,14],"orth": "CO","lexemes": [{"lemma": "co","mstag": "conj","disamb": true}]},{"index": 5,"position": [15,20],"orth": "NIECO","lexemes": [{"lemma": "nieco","mstag": "adv","disamb": true}]},{"index": 6,"position": [21,22],"orth": "O","lexemes": [{"lemma": "o","mstag": "prep:loc","disamb": true}]},{"index": 7,"position": [23,28],"orth": "SAMEJ","lexemes": [{"lemma": "sam","mstag": "adj:sg:loc:f:pos","disamb": true}]},{"index": 8,"position": [29,38],"orth": "PIPIDÓWCE","lexemes": [{"lemma": "Pipidówka","mstag": "subst:sg:loc:f","disamb": true}]},{"index": 9,"position": [39,45],"orth": "Przede","lexemes": [{"lemma": "przed","mstag": "prep:inst:wok","disamb": true}]},{"index": 10,"position": [46,55],"orth": "wszystkim","lexemes": [{"lemma": "wszystko","mstag": "subst:sg:inst:n","disamb": true}]},{"index": 11,"position": [56,61],"orth": "muszÄ™","lexemes": [{"lemma": "musieć","mstag": "fin:sg:pri:imperf","disamb": true}]},{"index": 12,"position": [62,71],"orth": "uprzedzić","lexemes": [{"lemma": "uprzedzić","mstag": "inf:perf","disamb": true}]},{"index": 13,"position": [72,73],"orth": "z","lexemes": [{"lemma": "z","mstag": "prep:gen:nwok","disamb": true}]},{"index": 14,"position": [74,78],"orth": "góry","lexemes": [{"lemma": "góra","mstag": "subst:sg:gen:f","disamb": true}]},{"index": 15,"position": [79,90],"orth": "czytelników","lexemes": [{"lemma": "czytelnik","mstag": "subst:pl:gen:m1","disamb": true}]},{"index": 16,"position": [90,91],"orth": ",","lexemes": [{"lemma": ",","mstag": "interp","disamb": true}]},{"index": 17,"position": [92,95],"orth": "aby","lexemes": [{"lemma": "aby","mstag": "comp","disamb": true}]},{"index": 18,"position": [96,99],"orth": "siÄ™","lexemes": [{"lemma": "siÄ™","mstag": "qub","disamb": true}]},{"index": 19,"position": [100,108],"orth": "daremnie","lexemes": [{"lemma": "daremnie","mstag": "adv:pos","disamb": true}]},{"index": 20,"position": [109,112],"orth": "nie","lexemes": [{"lemma": "nie","mstag": "qub","disamb": true}]},{"index": 21,"position": [113,121],"orth": "trudzili","lexemes": [{"lemma": "trudzić","mstag": "praet:pl:m1:imperf","disamb": true}]},{"index": 22,"position": [122,125],"orth": "nad","lexemes": [{"lemma": "nad","mstag": "prep:inst:nwok","disamb": true}]},{"index": 23,"position": [126,135],"orth": "szukaniem","lexemes": [{"lemma": "szukać","mstag": "ger:sg:inst:n:imperf:aff","disamb": true}]},{"index": 24,"position": [136,141],"orth": "wyżej","lexemes": [{"lemma": "wysoko","mstag": "adv:com","disamb": true}]},{"index": 25,"position": [142,152],"orth": "wyrażonego","lexemes": [{"lemma": "wyrazić","mstag": "ppas:sg:gen:n:perf:aff","disamb": true}]},{"index": 26,"position": [153,163],"orth": "miasteczka","lexemes": [{"lemma": "miasteczko","mstag": "subst:sg:gen:n","disamb": true}]},{"index": 27,"position": [164,166],"orth": "na","lexemes": [{"lemma": "na","mstag": "prep:loc","disamb": true}]},{"index": 28,"position": [167,173],"orth": "mapach","lexemes": [{"lemma": "mapa","mstag": "subst:pl:loc:f","disamb": true}]},{"index": 29,"position": [174,181],"orth": "Galicji","lexemes": [{"lemma": "Galicja","mstag": "subst:sg:gen:f","disamb": true}]},{"index": 30,"position": [182,183],"orth": "i","lexemes": [{"lemma": "i","mstag": "conj","disamb": true}]},{"index": 31,"position": [184,193],"orth": "Lodomerii","lexemes": [{"lemma": "Lodomerii","mstag": "ign","disamb": true}]},{"index": 32,"position": [193,194],"orth": ",","lexemes": [{"lemma": ",","mstag": "interp","disamb": true}]},{"index": 33,"position": [195,197],"orth": "bo","lexemes": [{"lemma": "bo","mstag": "comp","disamb": true}]},{"index": 34,"position": [198,200],"orth": "go","lexemes": [{"lemma": "on","mstag": "ppron3:sg:gen:m1:ter:nakc:npraep","disamb": true}]},{"index": 35,"position": [201,204],"orth": "tam","lexemes": [{"lemma": "tam","mstag": "adv","disamb": true}]},{"index": 36,"position": [205,208],"orth": "nie","lexemes": [{"lemma": "nie","mstag": "qub","disamb": true}]},{"index": 37,"position": [209,215],"orth": "znajdÄ…","lexemes": [{"lemma": "znaleźć","mstag": "fin:pl:ter:perf","disamb": true}]},{"index": 38,"position": [215,216],"orth": ".","lexemes": [{"lemma": ".","mstag": "interp","disamb": true}]},{"index": 39,"position": [217,220],"orth": "Nie","lexemes": [{"lemma": "nie","mstag": "qub","disamb": true}]},{"index": 40,"position": [221,228],"orth": "dlatego","lexemes": [{"lemma": "dlatego","mstag": "adv","disamb": true}]},{"index": 41,"position": [228,229],"orth": ",","lexemes": [{"lemma": ",","mstag": "interp","disamb": true}]},{"index": 42,"position": [230,236],"orth": "jakoby","lexemes": [{"lemma": "jakoby","mstag": "comp","disamb": true}]},{"index": 43,"position": [237,246],"orth": "Pipidówka","lexemes": [{"lemma": "Pipidówka","mstag": "subst:sg:nom:f","disamb": true}]},{"index": 44,"position": [247,250],"orth": "nie","lexemes": [{"lemma": "nie","mstag": "qub","disamb": true}]},{"index": 45,"position": [251,259],"orth": "istniaÅ‚a","lexemes": [{"lemma": "istnieć","mstag": "praet:sg:f:imperf","disamb": true}]},{"index": 46,"position": [260,261],"orth": "w","lexemes": [{"lemma": "w","mstag": "prep:loc:nwok","disamb": true}]},{"index": 47,"position": [262,276],"orth": "rzeczywistoÅ›ci","lexemes": [{"lemma": "rzeczywistość","mstag": "subst:sg:loc:f","disamb": true}]},{"index": 48,"position": [277,278],"orth": "i","lexemes": [{"lemma": "i","mstag": "conj","disamb": true}]},{"index": 49,"position": [279,283],"orth": "byÅ‚a","lexemes": [{"lemma": "być","mstag": "praet:sg:f:imperf","disamb": true}]},{"index": 50,"position": [284,289],"orth": "tylko","lexemes": [{"lemma": "tylko","mstag": "qub","disamb": true}]},{"index": 51,"position": [290,298],"orth": "wytworem","lexemes": [{"lemma": "wytwór","mstag": "subst:sg:inst:m3","disamb": true}]},{"index": 52,"position": [299,307],"orth": "fantazji","lexemes": [{"lemma": "fantazja","mstag": "subst:sg:gen:f","disamb": true}]},{"index": 53,"position": [308,314],"orth": "autora","lexemes": [{"lemma": "autor","mstag": "subst:sg:gen:m1","disamb": true}]},{"index": 54,"position": [314,315],"orth": ",","lexemes": [{"lemma": ",","mstag": "interp","disamb": true}]},{"index": 55,"position": [316,319],"orth": "ale","lexemes": [{"lemma": "ale","mstag": "conj","disamb": true}]},{"index": 56,"position": [320,322],"orth": "po","lexemes": [{"lemma": "po","mstag": "prep:acc","disamb": true}]},{"index": 57,"position": [323,329],"orth": "prostu","lexemes": [{"lemma": "prosty","mstag": "adjp","disamb": true}]},{"index": 58,"position": [330,337],"orth": "dlatego","lexemes": [{"lemma": "dlatego","mstag": "adv","disamb": true}]},{"index": 59,"position": [337,338],"orth": ",","lexemes": [{"lemma": ",","mstag": "interp","disamb": true}]},{"index": 60,"position": [339,341],"orth": "że","lexemes": [{"lemma": "że","mstag": "comp","disamb": true}]},{"index": 61,"position": [342,352],"orth": "mieszkaÅ„cy","lexemes": [{"lemma": "mieszkaniec","mstag": "subst:pl:nom:m1","disamb": true}]},{"index": 62,"position": [353,358],"orth": "owego","lexemes": [{"lemma": "ów","mstag": "adj:sg:gen:m3:pos","disamb": true}]},{"index": 63,"position": [359,367],"orth": "sÅ‚awnego","lexemes": [{"lemma": "sÅ‚awny","mstag": "adj:sg:gen:m3:pos","disamb": true}]},{"index": 64,"position": [368,373],"orth": "grodu","lexemes": [{"lemma": "gród","mstag": "subst:sg:gen:m3","disamb": true}]},{"index": 65,"position": [373,374],"orth": ",","lexemes": [{"lemma": ",","mstag": "interp","disamb": true}]},{"index": 66,"position": [375,383],"orth": "urosÅ‚szy","lexemes": [{"lemma": "urosÅ‚szy","mstag": "ign","disamb": true}]},{"index": 67,"position": [384,385],"orth": "z","lexemes": [{"lemma": "z","mstag": "prep:inst:nwok","disamb": true}]},{"index": 68,"position": [386,392],"orth": "czasem","lexemes": [{"lemma": "czas","mstag": "subst:sg:inst:m3","disamb": true}]},{"index": 69,"position": [393,394],"orth": "w","lexemes": [{"lemma": "w","mstag": "prep:acc:nwok","disamb": true}]},{"index": 70,"position": [395,402],"orth": "ambicjÄ™","lexemes": [{"lemma": "ambicja","mstag": "subst:sg:acc:f","disamb": true}]},{"index": 71,"position": [402,403],"orth": ",","lexemes": [{"lemma": ",","mstag": "interp","disamb": true}]},{"index": 72,"position": [404,411],"orth": "uważali","lexemes": [{"lemma": "uważać","mstag": "praet:pl:m1:imperf","disamb": true}]},{"index": 73,"position": [412,414],"orth": "tÄ™","lexemes": [{"lemma": "ten","mstag": "adj:sg:acc:f:pos","disamb": true}]},{"index": 74,"position": [415,420],"orth": "nazwÄ™","lexemes": [{"lemma": "nazwa","mstag": "subst:sg:acc:f","disamb": true}]},{"index": 75,"position": [421,425],"orth": "jako","lexemes": [{"lemma": "jako","mstag": "conj","disamb": true}]},{"index": 76,"position": [426,436],"orth": "ubliżajÄ…cÄ…","lexemes": [{"lemma": "ubliżajÄ…cy","mstag": "adj:sg:acc:f:pos","disamb": true}]},{"index": 77,"position": [437,440],"orth": "ich","lexemes": [{"lemma": "on","mstag": "ppron3:pl:gen:m1:ter:akc:npraep","disamb": true}]},{"index": 78,"position": [441,448],"orth": "powadze","lexemes": [{"lemma": "powaga","mstag": "subst:sg:loc:f","disamb": true}]},{"index": 79,"position": [449,450],"orth": "i","lexemes": [{"lemma": "i","mstag": "conj","disamb": true}]},{"index": 80,"position": [451,457],"orth": "podali","lexemes": [{"lemma": "podać","mstag": "praet:pl:m1:perf","disamb": true}]},{"index": 81,"position": [458,460],"orth": "do","lexemes": [{"lemma": "do","mstag": "prep:gen","disamb": true}]},{"index": 82,"position": [461,462],"orth": "c","lexemes": [{"lemma": "c","mstag": "subst:sg:gen:f","disamb": true}]},{"index": 83,"position": [462,463],"orth": ".","lexemes": [{"lemma": ".","mstag": "interp","disamb": true}]},{"index": 84,"position": [464,465],"orth": "k","lexemes": [{"lemma": "K","mstag": "brev:pun","disamb": true}]},{"index": 85,"position": [465,466],"orth": ".","lexemes": [{"lemma": ".","mstag": "interp","disamb": true}]},{"index": 86,"position": [467,480],"orth": "namiestnictwa","lexemes": [{"lemma": "namiestnictwo","mstag": "subst:sg:gen:n","disamb": true}]},{"index": 87,"position": [481,488],"orth": "pokornÄ…","lexemes": [{"lemma": "pokorny","mstag": "adj:sg:acc:f:pos","disamb": true}]},{"index": 88,"position": [489,495],"orth": "proÅ›bÄ™","lexemes": [{"lemma": "proÅ›ba","mstag": "subst:sg:acc:f","disamb": true}]},{"index": 89,"position": [496,497],"orth": "o","lexemes": [{"lemma": "o","mstag": "prep:acc","disamb": true}]},{"index": 90,"position": [498,508],"orth": "pozwolenie","lexemes": [{"lemma": "pozwolić","mstag": "ger:sg:acc:n:perf:aff","disamb": true}]},{"index": 91,"position": [509,520],"orth": "zamienienia","lexemes": [{"lemma": "zamienić","mstag": "ger:sg:gen:n:perf:aff","disamb": true}]},{"index": 92,"position": [521,524],"orth": "jej","lexemes": [{"lemma": "on","mstag": "ppron3:sg:gen:f:ter:akc:npraep","disamb": true}]},{"index": 93,"position": [525,527],"orth": "na","lexemes": [{"lemma": "na","mstag": "prep:acc","disamb": true}]},{"index": 94,"position": [528,532],"orth": "innÄ…","lexemes": [{"lemma": "inny","mstag": "adj:sg:acc:f:pos","disamb": true}]},{"index": 95,"position": [532,533],"orth": ".","lexemes": [{"lemma": ".","mstag": "interp","disamb": true}]},{"index": 96,"position": [534,541],"orth": "Podobne","lexemes": [{"lemma": "podobny","mstag": "adj:pl:nom:f:pos","disamb": true}]},{"index": 97,"position": [542,549],"orth": "zamiany","lexemes": [{"lemma": "zamiana","mstag": "subst:pl:nom:f","disamb": true}]},{"index": 98,"position": [550,557],"orth": "nazwisk","lexemes": [{"lemma": "nazwisko","mstag": "subst:pl:gen:n","disamb": true}]},{"index": 99,"position": [558,568],"orth": "praktykujÄ…","lexemes": [{"lemma": "praktykować","mstag": "fin:pl:ter:imperf","disamb": true}]},{"index": 100,"position": [569,572],"orth": "siÄ™","lexemes": [{"lemma": "siÄ™","mstag": "qub","disamb": true}]},{"index": 101,"position": [573,577],"orth": "dość","lexemes": [{"lemma": "dość","mstag": "qub","disamb": true}]},{"index": 102,"position": [578,584],"orth": "czÄ™sto","lexemes": [{"lemma": "czÄ™sto","mstag": "adv:pos","disamb": true}]},{"index": 103,"position": [585,586],"orth": "w","lexemes": [{"lemma": "w","mstag": "prep:loc:nwok","disamb": true}]},{"index": 104,"position": [587,594],"orth": "Galicji","lexemes": [{"lemma": "Galicja","mstag": "subst:sg:loc:f","disamb": true}]},{"index": 105,"position": [594,595],"orth": ",","lexemes": [{"lemma": ",","mstag": "interp","disamb": true}]},{"index": 106,"position": [596,607],"orth": "szczególnie","lexemes": [{"lemma": "szczególnie","mstag": "qub","disamb": true}]},{"index": 107,"position": [608,609],"orth": "u","lexemes": [{"lemma": "u","mstag": "prep:gen","disamb": true}]},{"index": 108,"position": [610,622],"orth": "pojedynczych","lexemes": [{"lemma": "pojedynczy","mstag": "adj:pl:gen:f:pos","disamb": true}]},{"index": 109,"position": [623,627],"orth": "osób","lexemes": [{"lemma": "osoba","mstag": "subst:pl:gen:f","disamb": true}]},{"index": 110,"position": [627,628],"orth": ",","lexemes": [{"lemma": ",","mstag": "interp","disamb": true}]},{"index": 111,"position": [629,634],"orth": "które","lexemes": [{"lemma": "który","mstag": "adj:pl:nom:f:pos","disamb": true}]},{"index": 112,"position": [635,638],"orth": "nie","lexemes": [{"lemma": "nie","mstag": "qub","disamb": true}]},{"index": 113,"position": [639,645],"orth": "czujÄ…c","lexemes": [{"lemma": "czuć","mstag": "pcon:imperf","disamb": true}]},{"index": 114,"position": [646,649],"orth": "siÄ™","lexemes": [{"lemma": "siÄ™","mstag": "qub","disamb": true}]},{"index": 115,"position": [650,652],"orth": "na","lexemes": [{"lemma": "na","mstag": "prep:loc","disamb": true}]},{"index": 116,"position": [653,659],"orth": "siÅ‚ach","lexemes": [{"lemma": "siÅ‚a","mstag": "subst:pl:loc:f","disamb": true}]},{"index": 117,"position": [660,675],"orth": "uszlachetnienia","lexemes": [{"lemma": "uszlachetnić","mstag": "ger:sg:gen:n:perf:aff","disamb": true}]},{"index": 118,"position": [676,680],"orth": "sobÄ…","lexemes": [{"lemma": "siebie","mstag": "siebie:inst","disamb": true}]},{"index": 119,"position": [680,681],"orth": ",","lexemes": [{"lemma": ",","mstag": "interp","disamb": true}]},{"index": 120,"position": [682,687],"orth": "swymi","lexemes": [{"lemma": "swój","mstag": "adj:pl:inst:m3:pos","disamb": true}]},{"index": 121,"position": [688,695],"orth": "czynami","lexemes": [{"lemma": "czyn","mstag": "subst:pl:inst:m3","disamb": true}]},{"index": 122,"position": [696,704],"orth": "wÅ‚asnego","lexemes": [{"lemma": "wÅ‚asny","mstag": "adj:sg:gen:n:pos","disamb": true}]},{"index": 123,"position": [705,713],"orth": "nazwiska","lexemes": [{"lemma": "nazwisko","mstag": "subst:sg:gen:n","disamb": true}]},{"index": 124,"position": [713,714],"orth": ",","lexemes": [{"lemma": ",","mstag": "interp","disamb": true}]},{"index": 125,"position": [715,719],"orth": "chcÄ…","lexemes": [{"lemma": "chcieć","mstag": "fin:pl:ter:imperf","disamb": true}]},{"index": 126,"position": [720,730],"orth": "nazwiskiem","lexemes": [{"lemma": "nazwisko","mstag": "subst:sg:inst:n","disamb": true}]},{"index": 127,"position": [731,743],"orth": "uszlachetnić","lexemes": [{"lemma": "uszlachetnić","mstag": "inf:perf","disamb": true}]},{"index": 128,"position": [744,750],"orth": "siebie","lexemes": [{"lemma": "siebie","mstag": "siebie:acc","disamb": true}]},{"index": 129,"position": [750,751],"orth": ",","lexemes": [{"lemma": ",","mstag": "interp","disamb": true}]},{"index": 130,"position": [752,753],"orth": "i","lexemes": [{"lemma": "i","mstag": "conj","disamb": true}]},{"index": 131,"position": [754,757],"orth": "tak","lexemes": [{"lemma": "tak","mstag": "adv:pos","disamb": true}]},{"index": 132,"position": [758,760],"orth": "np","lexemes": [{"lemma": "na przykÅ‚ad","mstag": "brev:pun","disamb": true}]},{"index": 133,"position": [760,761],"orth": ".","lexemes": [{"lemma": ".","mstag": "interp","disamb": true}]}],"entities": [{"text": "Galicji","type": "nam_loc_historical_region","tokens": [28,29],"positions": [174,181]},{"text": "Lodomerii","type": "nam_loc_gpe_admin1","tokens": [30,31],"positions": [184,193]},{"text": "Pipidówka","type": "nam_loc_gpe_city","tokens": [42,43],"positions": [237,246]},{"text": "Galicji","type": "nam_loc_gpe_admin1","tokens": [103,104],"positions": [587,594]}]}
\ No newline at end of file
diff --git a/tests/detectors/ner/__init__.py b/tests/unit/__init__.py
similarity index 100%
rename from tests/detectors/ner/__init__.py
rename to tests/unit/__init__.py
diff --git a/tests/detectors/phone/__init__.py b/tests/unit/detectors/__init__.py
similarity index 100%
rename from tests/detectors/phone/__init__.py
rename to tests/unit/detectors/__init__.py
diff --git a/tests/detectors/url/__init__.py b/tests/unit/detectors/date/__init__.py
similarity index 100%
rename from tests/detectors/url/__init__.py
rename to tests/unit/detectors/date/__init__.py
diff --git a/tests/detectors/date/test_en.py b/tests/unit/detectors/date/test_en.py
similarity index 100%
rename from tests/detectors/date/test_en.py
rename to tests/unit/detectors/date/test_en.py
diff --git a/tests/detectors/date/test_pl.py b/tests/unit/detectors/date/test_pl.py
similarity index 100%
rename from tests/detectors/date/test_pl.py
rename to tests/unit/detectors/date/test_pl.py
diff --git a/tests/detectors/date/test_ru.py b/tests/unit/detectors/date/test_ru.py
similarity index 100%
rename from tests/detectors/date/test_ru.py
rename to tests/unit/detectors/date/test_ru.py
diff --git a/tests/detectors/user/__init__.py b/tests/unit/detectors/email/__init__.py
similarity index 100%
rename from tests/detectors/user/__init__.py
rename to tests/unit/detectors/email/__init__.py
diff --git a/tests/detectors/email/test_email.py b/tests/unit/detectors/email/test_email.py
similarity index 100%
rename from tests/detectors/email/test_email.py
rename to tests/unit/detectors/email/test_email.py
diff --git a/tests/dictionaries/__init__.py b/tests/unit/detectors/ner/__init__.py
similarity index 100%
rename from tests/dictionaries/__init__.py
rename to tests/unit/detectors/ner/__init__.py
diff --git a/tests/detectors/ner/test_ner.py b/tests/unit/detectors/ner/test_ner.py
similarity index 100%
rename from tests/detectors/ner/test_ner.py
rename to tests/unit/detectors/ner/test_ner.py
diff --git a/tests/dictionaries/morphosyntactic/__init__.py b/tests/unit/detectors/phone/__init__.py
similarity index 100%
rename from tests/dictionaries/morphosyntactic/__init__.py
rename to tests/unit/detectors/phone/__init__.py
diff --git a/tests/detectors/phone/test_phone.py b/tests/unit/detectors/phone/test_phone.py
similarity index 100%
rename from tests/detectors/phone/test_phone.py
rename to tests/unit/detectors/phone/test_phone.py
diff --git a/tests/input_parsers/__init__.py b/tests/unit/detectors/url/__init__.py
similarity index 100%
rename from tests/input_parsers/__init__.py
rename to tests/unit/detectors/url/__init__.py
diff --git a/tests/detectors/url/test_url.py b/tests/unit/detectors/url/test_url.py
similarity index 100%
rename from tests/detectors/url/test_url.py
rename to tests/unit/detectors/url/test_url.py
diff --git a/tests/pipeline/__init__.py b/tests/unit/detectors/user/__init__.py
similarity index 100%
rename from tests/pipeline/__init__.py
rename to tests/unit/detectors/user/__init__.py
diff --git a/tests/detectors/user/test_user.py b/tests/unit/detectors/user/test_user.py
similarity index 100%
rename from tests/detectors/user/test_user.py
rename to tests/unit/detectors/user/test_user.py
diff --git a/tests/replacers/__init__.py b/tests/unit/dictionaries/__init__.py
similarity index 100%
rename from tests/replacers/__init__.py
rename to tests/unit/dictionaries/__init__.py
diff --git a/tests/unit/dictionaries/morphosyntactic/__init__.py b/tests/unit/dictionaries/morphosyntactic/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/dictionaries/morphosyntactic/test_ner_file.py b/tests/unit/dictionaries/morphosyntactic/test_ner_file.py
similarity index 100%
rename from tests/dictionaries/morphosyntactic/test_ner_file.py
rename to tests/unit/dictionaries/morphosyntactic/test_ner_file.py
diff --git a/tests/dictionaries/morphosyntactic/test_ner_file_nkjp.py b/tests/unit/dictionaries/morphosyntactic/test_ner_file_nkjp.py
similarity index 100%
rename from tests/dictionaries/morphosyntactic/test_ner_file_nkjp.py
rename to tests/unit/dictionaries/morphosyntactic/test_ner_file_nkjp.py
diff --git a/tests/unit/input_parsers/__init__.py b/tests/unit/input_parsers/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/input_parsers/test_ccl.py b/tests/unit/input_parsers/test_ccl.py
similarity index 100%
rename from tests/input_parsers/test_ccl.py
rename to tests/unit/input_parsers/test_ccl.py
diff --git a/tests/input_parsers/test_wiktor_ner.py b/tests/unit/input_parsers/test_wiktor_ner.py
similarity index 100%
rename from tests/input_parsers/test_wiktor_ner.py
rename to tests/unit/input_parsers/test_wiktor_ner.py
diff --git a/tests/unit/pipeline/__init__.py b/tests/unit/pipeline/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/pipeline/test_default.py b/tests/unit/pipeline/test_default.py
similarity index 100%
rename from tests/pipeline/test_default.py
rename to tests/unit/pipeline/test_default.py
diff --git a/tests/pipeline/test_sequential_jsonl.py b/tests/unit/pipeline/test_sequential_jsonl.py
similarity index 100%
rename from tests/pipeline/test_sequential_jsonl.py
rename to tests/unit/pipeline/test_sequential_jsonl.py
diff --git a/tests/unit/replacers/__init__.py b/tests/unit/replacers/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/replacers/test_date_replacer.py b/tests/unit/replacers/test_date_replacer.py
similarity index 100%
rename from tests/replacers/test_date_replacer.py
rename to tests/unit/replacers/test_date_replacer.py
diff --git a/tests/replacers/test_email_replacer.py b/tests/unit/replacers/test_email_replacer.py
similarity index 100%
rename from tests/replacers/test_email_replacer.py
rename to tests/unit/replacers/test_email_replacer.py
diff --git a/tests/replacers/test_ner_replacer.py b/tests/unit/replacers/test_ner_replacer.py
similarity index 100%
rename from tests/replacers/test_ner_replacer.py
rename to tests/unit/replacers/test_ner_replacer.py
diff --git a/tests/replacers/test_tag_replacer.py b/tests/unit/replacers/test_tag_replacer.py
similarity index 100%
rename from tests/replacers/test_tag_replacer.py
rename to tests/unit/replacers/test_tag_replacer.py
diff --git a/tests/replacers/test_user_replacer.py b/tests/unit/replacers/test_user_replacer.py
similarity index 100%
rename from tests/replacers/test_user_replacer.py
rename to tests/unit/replacers/test_user_replacer.py
diff --git a/tests/suppressors/test_order_based.py b/tests/unit/suppressors/test_order_based.py
similarity index 100%
rename from tests/suppressors/test_order_based.py
rename to tests/unit/suppressors/test_order_based.py
diff --git a/tests/test_annotation_mapping.py b/tests/unit/test_annotation_mapping.py
similarity index 100%
rename from tests/test_annotation_mapping.py
rename to tests/unit/test_annotation_mapping.py
diff --git a/tests/test_string_replacements.py b/tests/unit/test_string_replacements.py
similarity index 100%
rename from tests/test_string_replacements.py
rename to tests/unit/test_string_replacements.py
--
GitLab