diff --git a/.github/contributors/YohannesDatasci.md b/.github/contributors/YohannesDatasci.md new file mode 100644 index 000000000..129c45576 --- /dev/null +++ b/.github/contributors/YohannesDatasci.md @@ -0,0 +1,106 @@ +# spaCy contributor agreement + +This spaCy Contributor Agreement (**"SCA"**) is based on the +[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf). +The SCA applies to any contribution that you make to any product or project +managed by us (the **"project"**), and sets out the intellectual property rights +you grant to us in the contributed materials. The term **"us"** shall mean +[ExplosionAI GmbH](https://explosion.ai/legal). The term +**"you"** shall mean the person or entity identified below. + +If you agree to be bound by these terms, fill in the information requested +below and include the filled-in version with your first pull request, under the +folder [`.github/contributors/`](/.github/contributors/). The name of the file +should be your GitHub username, with the extension `.md`. For example, the user +example_user would create the file `.github/contributors/example_user.md`. + +Read this agreement carefully before signing. These terms and conditions +constitute a binding legal agreement. + +## Contributor Agreement + +1. The term "contribution" or "contributed materials" means any source code, +object code, patch, tool, sample, graphic, specification, manual, +documentation, or any other material posted or submitted by you to the project. + +2. With respect to any worldwide copyrights, or copyright applications and +registrations, in your contribution: + + * you hereby assign to us joint ownership, and to the extent that such + assignment is or becomes invalid, ineffective or unenforceable, you hereby + grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge, + royalty-free, unrestricted license to exercise all rights under those + copyrights. This includes, at our option, the right to sublicense these same + rights to third parties through multiple levels of sublicensees or other + licensing arrangements; + + * you agree that each of us can do all things in relation to your + contribution as if each of us were the sole owners, and if one of us makes + a derivative work of your contribution, the one who makes the derivative + work (or has it made will be the sole owner of that derivative work; + + * you agree that you will not assert any moral rights in your contribution + against us, our licensees or transferees; + + * you agree that we may register a copyright in your contribution and + exercise all ownership rights associated with it; and + + * you agree that neither of us has any duty to consult with, obtain the + consent of, pay or render an accounting to the other for any use or + distribution of your contribution. + +3. With respect to any patents you own, or that you can license without payment +to any third party, you hereby grant to us a perpetual, irrevocable, +non-exclusive, worldwide, no-charge, royalty-free license to: + + * make, have made, use, sell, offer to sell, import, and otherwise transfer + your contribution in whole or in part, alone or in combination with or + included in any product, work or materials arising out of the project to + which your contribution was submitted, and + + * at our option, to sublicense these same rights to third parties through + multiple levels of sublicensees or other licensing arrangements. + +4. Except as set out above, you keep all right, title, and interest in your +contribution. The rights that you grant to us under these terms are effective +on the date you first submitted a contribution to us, even if your submission +took place before the date you sign these terms. + +5. You covenant, represent, warrant and agree that: + + * Each contribution that you submit is and shall be an original work of + authorship and you can legally grant the rights set out in this SCA; + + * to the best of your knowledge, each contribution will not violate any + third party's copyrights, trademarks, patents, or other intellectual + property rights; and + + * each contribution shall be in compliance with U.S. export control laws and + other applicable export and import laws. You agree to notify us if you + become aware of any circumstance which would make any of the foregoing + representations inaccurate in any respect. We may publicly disclose your + participation in the project, including the fact that you have signed the SCA. + +6. This SCA is governed by the laws of the State of California and applicable +U.S. Federal law. Any choice of law rules will not apply. + +7. Please place an “x” on one of the applicable statement below. Please do NOT +mark both statements: + + * [X] I am signing on behalf of myself as an individual and no other person + or entity, including my employer, has or will have rights with respect to my + contributions. + + * [ ] I am signing on behalf of my employer or a legal entity and I have the + actual authority to contractually bind that entity. + +## Contributor Details + +| Field | Entry | +|------------------------------- | -------------------- | +| Name | Yohannes | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2020-04-02 | +| GitHub username | YohannesDatasci | +| Website (optional) | | \ No newline at end of file diff --git a/spacy/lang/hy/__init__.py b/spacy/lang/hy/__init__.py new file mode 100644 index 000000000..3320edb6c --- /dev/null +++ b/spacy/lang/hy/__init__.py @@ -0,0 +1,25 @@ +from .stop_words import STOP_WORDS +from .lex_attrs import LEX_ATTRS +from .tag_map import TAG_MAP + + +from ...attrs import LANG +from ...language import Language +from ...tokens import Doc + + +class ArmenianDefaults(Language.Defaults): + lex_attr_getters = dict(Language.Defaults.lex_attr_getters) + lex_attr_getters[LANG] = lambda text: "hy" + + lex_attr_getters.update(LEX_ATTRS) + stop_words = STOP_WORDS + tag_map = TAG_MAP + + +class Armenian(Language): + lang = "hy" + Defaults = ArmenianDefaults + + +__all__ = ["Armenian"] diff --git a/spacy/lang/hy/examples.py b/spacy/lang/hy/examples.py new file mode 100644 index 000000000..b0df31aae --- /dev/null +++ b/spacy/lang/hy/examples.py @@ -0,0 +1,16 @@ +from __future__ import unicode_literals + + +""" +Example sentences to test spaCy and its language models. +>>> from spacy.lang.hy.examples import sentences +>>> docs = nlp.pipe(sentences) +""" + + +sentences = [ + "Լոնդոնը Միացյալ Թագավորության մեծ քաղաք է։", + "Ո՞վ է Ֆրանսիայի նախագահը։", + "Որն է Միացյալ Նահանգների մայրաքաղաքը։", + "Ե՞րբ է ծնվել Բարաք Օբաման։", +] diff --git a/spacy/lang/hy/lex_attrs.py b/spacy/lang/hy/lex_attrs.py new file mode 100644 index 000000000..7c1b9592f --- /dev/null +++ b/spacy/lang/hy/lex_attrs.py @@ -0,0 +1,58 @@ +from __future__ import unicode_literals + +from ...attrs import LIKE_NUM + + +_num_words = [ + "զրօ", + "մէկ", + "երկու", + "երեք", + "չորս", + "հինգ", + "վեց", + "յոթ", + "ութ", + "ինը", + "տասը", + "տասնմեկ", + "տասներկու", + "տասն­երեք", + "տասն­չորս", + "տասն­հինգ", + "տասն­վեց", + "տասն­յոթ", + "տասն­ութ", + "տասն­ինը", + "քսան" "երեսուն", + "քառասուն", + "հիսուն", + "վաթցսուն", + "յոթանասուն", + "ութսուն", + "ինիսուն", + "հարյուր", + "հազար", + "միլիոն", + "միլիարդ", + "տրիլիոն", + "քվինտիլիոն", +] + + +def like_num(text): + if text.startswith(("+", "-", "±", "~")): + text = text[1:] + text = text.replace(",", "").replace(".", "") + if text.isdigit(): + return True + if text.count("/") == 1: + num, denom = text.split("/") + if num.isdigit() and denom.isdigit(): + return True + if text.lower() in _num_words: + return True + return False + + +LEX_ATTRS = {LIKE_NUM: like_num} diff --git a/spacy/lang/hy/stop_words.py b/spacy/lang/hy/stop_words.py new file mode 100644 index 000000000..c671956a4 --- /dev/null +++ b/spacy/lang/hy/stop_words.py @@ -0,0 +1,110 @@ +from __future__ import unicode_literals + + +STOP_WORDS = set( + """ +նա +ողջը +այստեղ +ենք +նա +էիր +որպես +ուրիշ +բոլորը +այն +այլ +նույնչափ +էի +մի +և +ողջ +ես +ոմն +հետ +նրանք +ամենքը +ըստ +ինչ-ինչ +այսպես +համայն +մի +նաև +նույնքան +դա +ովևէ +համար +այնտեղ +էին +որոնք +սույն +ինչ-որ +ամենը +նույնպիսի +ու +իր +որոշ +միևնույն +ի +այնպիսի +մենք +ամեն ոք +նույն +երբևէ +այն +որևէ +ին +այդպես +նրա +որը +վրա +դու +էինք +այդպիսի +էիք +յուրաքանչյուրը +եմ +պիտի +այդ +ամբողջը +հետո +եք +ամեն +այլ +կամ +այսքան +որ +այնպես +այսինչ +բոլոր +է +մեկնումեկը +այդչափ +այնքան +ամբողջ +երբևիցե +այնչափ +ամենայն +մյուս +այնինչ +իսկ +այդտեղ +այս +սա +են +ամեն ինչ +որևիցե +ում +մեկը +այդ +դուք +այսչափ +այդքան +այսպիսի +էր +յուրաքանչյուր +այս +մեջ +թ +""".split() +) diff --git a/spacy/lang/hy/tag_map.py b/spacy/lang/hy/tag_map.py new file mode 100644 index 000000000..90690c22e --- /dev/null +++ b/spacy/lang/hy/tag_map.py @@ -0,0 +1,2478 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ...symbols import POS, SYM, ADJ, NUM, DET, ADV, ADP, X, VERB, NOUN +from ...symbols import PROPN, PART, INTJ, PRON, SCONJ, AUX, CCONJ + +TAG_MAP = { + "ADJ_Abbr=Yes": {POS: ADJ, "Abbr": "Yes"}, + "ADJ_Degree=Pos|NumForm=Word|NumType=Ord": { + POS: ADJ, + "Degree": "Pos", + "NumForm": "Word", + "NumType": "Ord", + }, + "ADJ_Degree=Pos": {POS: ADJ, "Degree": "Pos"}, + "ADJ_Degree=Pos|Style=Coll": {POS: ADJ, "Degree": "Pos", "Style": "Coll"}, + "ADJ_Degree=Pos|Style=Expr": {POS: ADJ, "Degree": "Pos", "Style": "Expr"}, + "ADJ_Degree=Sup": {POS: ADJ, "Degree": "Sup"}, + "ADJ_NumForm=Digit|NumType=Ord": {POS: ADJ, "NumForm": "Digit", "NumType": "Ord"}, + "ADJ_NumForm=Word|NumType=Card": {POS: ADJ, "NumForm": "Word", "NumType": "Card"}, + "ADJ_NumForm=Word|NumType=Ord": {POS: ADJ, "NumForm": "Word", "NumType": "Ord"}, + "ADJ_Style=Coll": {POS: ADJ, "Style": "Coll"}, + "ADJ_Style=Expr": {POS: ADJ, "Style": "Expr"}, + "ADP_AdpType=Post|Case=Dat": {POS: ADP, "AdpType": "Post", "Case": "Dat"}, + "ADP_AdpType=Post|Case=Nom": {POS: ADP, "AdpType": "Post", "Case": "Nom"}, + "ADP_AdpType=Post|Number=Plur|Person=3": { + POS: ADP, + "AdpType": "Post", + "Number": "Plur", + "Person": "3", + }, + "ADP_AdpType=Post": {POS: ADP, "AdpType": "Post"}, + "ADP_AdpType=Prep": {POS: ADP, "AdpType": "Prep"}, + "ADP_AdpType=Prep|Style=Arch": {POS: ADP, "AdpType": "Prep", "Style": "Arch"}, + "ADV_Degree=Cmp": {POS: ADV, "Degree": "Cmp"}, + "ADV_Degree=Pos": {POS: ADV, "Degree": "Pos"}, + "ADV_Degree=Sup": {POS: ADV, "Degree": "Sup"}, + "ADV_Distance=Dist|PronType=Dem": {POS: ADV, "Distance": "Dist", "PronType": "Dem"}, + "ADV_Distance=Dist|PronType=Exc": {POS: ADV, "Distance": "Dist", "PronType": "Exc"}, + "ADV_Distance=Med|PronType=Dem": {POS: ADV, "Distance": "Med", "PronType": "Dem"}, + "ADV_Distance=Med|PronType=Dem|Style=Coll": { + POS: ADV, + "Distance": "Med", + "PronType": "Dem", + "Style": "Coll", + }, + "ADV_NumForm=Word|NumType=Card|PronType=Tot": { + POS: ADV, + "NumForm": "Word", + "NumType": "Card", + "PronType": "Tot", + }, + "ADV_PronType=Dem": {POS: ADV, "PronType": "Dem"}, + "ADV_PronType=Exc": {POS: ADV, "PronType": "Exc"}, + "ADV_PronType=Ind": {POS: ADV, "PronType": "Ind"}, + "ADV_PronType=Int": {POS: ADV, "PronType": "Int"}, + "ADV_PronType=Int|Style=Coll": {POS: ADV, "PronType": "Int", "Style": "Coll"}, + "ADV_PronType=Rel": {POS: ADV, "PronType": "Rel"}, + "ADV_Style=Coll": {POS: ADV, "Style": "Coll"}, + "ADV_Style=Rare": {POS: ADV, "Style": "Rare"}, + "AUX_Aspect=Imp|Mood=Ind|Number=Plur|Person=1|Polarity=Neg|Tense=Pres|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Plur", + "Person": "1", + "Polarity": "Neg", + "Tense": "Pres", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Plur|Person=2|Polarity=Pos|Tense=Pres|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Plur", + "Person": "2", + "Polarity": "Pos", + "Tense": "Pres", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Polarity=Neg|Tense=Imp|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Plur", + "Person": "3", + "Polarity": "Neg", + "Tense": "Imp", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Polarity=Neg|Tense=Pres|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Plur", + "Person": "3", + "Polarity": "Neg", + "Tense": "Pres", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Polarity=Pos|Tense=Imp|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Plur", + "Person": "3", + "Polarity": "Pos", + "Tense": "Imp", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Plur", + "Person": "3", + "Polarity": "Pos", + "Tense": "Pres", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Sing|Person=1|Polarity=Neg|Tense=Imp|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "1", + "Polarity": "Neg", + "Tense": "Imp", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Sing|Person=1|Polarity=Neg|Tense=Pres|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "1", + "Polarity": "Neg", + "Tense": "Pres", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Sing|Person=1|Polarity=Pos|Tense=Imp|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "1", + "Polarity": "Pos", + "Tense": "Imp", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Sing|Person=1|Polarity=Pos|Tense=Pres|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "1", + "Polarity": "Pos", + "Tense": "Pres", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Sing|Person=2|Polarity=Neg|Tense=Pres|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "2", + "Polarity": "Neg", + "Tense": "Pres", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Sing|Person=2|Polarity=Pos|Tense=Pres|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "2", + "Polarity": "Pos", + "Tense": "Pres", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Polarity=Neg|Tense=Imp|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Neg", + "Tense": "Imp", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Polarity=Neg|Tense=Pres|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Neg", + "Tense": "Pres", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Imp|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Tense": "Imp", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Tense=Pres|VerbForm=Fin": { + POS: AUX, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Tense": "Pres", + "VerbForm": "Fin", + }, + "AUX_Aspect=Imp|VerbForm=Part": {POS: AUX, "Aspect": "Imp", "VerbForm": "Part"}, + "AUX_Aspect=Perf|VerbForm=Part": {POS: AUX, "Aspect": "Perf", "VerbForm": "Part"}, + "AUX_Aspect=Prosp|VerbForm=Part": {POS: AUX, "Aspect": "Prosp", "VerbForm": "Part"}, + "AUX_Polarity=Pos": {POS: AUX, "Polarity": "Pos"}, + "CCONJ_ConjType=Comp": {POS: CCONJ, "ConjType": "Comp"}, + "CCONJ_ConjType=Comp|Style=Coll": {POS: CCONJ, "ConjType": "Comp", "Style": "Coll"}, + "DET_Case=Gen|Distance=Med|Number=Plur|Poss=Yes|PronType=Dem": { + POS: DET, + "Case": "Gen", + "Distance": "Med", + "Number": "Plur", + "Poss": "Yes", + "PronType": "Dem", + }, + "DET_Case=Gen|Distance=Med|Number=Sing|Poss=Yes|PronType=Dem": { + POS: DET, + "Case": "Gen", + "Distance": "Med", + "Number": "Sing", + "Poss": "Yes", + "PronType": "Dem", + }, + "DET_Case=Gen|Number=Plur|Person=1|Poss=Yes|PronType=Prs": { + POS: DET, + "Case": "Gen", + "Number": "Plur", + "Person": "1", + "Poss": "Yes", + "PronType": "Prs", + }, + "DET_Case=Gen|Number=Plur|Person=2|Polite=Infm|Poss=Yes|PronType=Prs": { + POS: DET, + "Case": "Gen", + "Number": "Plur", + "Person": "2", + "Polite": "Infm", + "Poss": "Yes", + "PronType": "Prs", + }, + "DET_Case=Gen|Number=Plur|Person=3|Poss=Yes|PronType=Emp": { + POS: DET, + "Case": "Gen", + "Number": "Plur", + "Person": "3", + "Poss": "Yes", + "PronType": "Emp", + }, + "DET_Case=Gen|Number=Plur|Person=3|Poss=Yes|PronType=Emp|Reflex=Yes": { + POS: DET, + "Case": "Gen", + "Number": "Plur", + "Person": "3", + "Poss": "Yes", + "PronType": "Emp", + "Reflex": "Yes", + }, + "DET_Case=Gen|Number=Sing|Person=1|Poss=Yes|PronType=Prs": { + POS: DET, + "Case": "Gen", + "Number": "Sing", + "Person": "1", + "Poss": "Yes", + "PronType": "Prs", + }, + "DET_Case=Gen|Number=Sing|Person=2|Polite=Infm|Poss=Yes|PronType=Prs": { + POS: DET, + "Case": "Gen", + "Number": "Sing", + "Person": "2", + "Polite": "Infm", + "Poss": "Yes", + "PronType": "Prs", + }, + "DET_Case=Gen|Number=Sing|Person=3|Poss=Yes|PronType=Emp": { + POS: DET, + "Case": "Gen", + "Number": "Sing", + "Person": "3", + "Poss": "Yes", + "PronType": "Emp", + }, + "DET_Case=Gen|Number=Sing|Person=3|Poss=Yes|PronType=Emp|Reflex=Yes": { + POS: DET, + "Case": "Gen", + "Number": "Sing", + "Person": "3", + "Poss": "Yes", + "PronType": "Emp", + "Reflex": "Yes", + }, + "DET_Case=Gen|Number=Sing|Person=3|Poss=Yes|PronType=Prs": { + POS: DET, + "Case": "Gen", + "Number": "Sing", + "Person": "3", + "Poss": "Yes", + "PronType": "Prs", + }, + "DET_Case=Gen|Number=Sing|Poss=Yes|PronType=Rel": { + POS: DET, + "Case": "Gen", + "Number": "Sing", + "Poss": "Yes", + "PronType": "Rel", + }, + "DET_Distance=Dist|PronType=Dem": {POS: DET, "Distance": "Dist", "PronType": "Dem"}, + "DET_Distance=Dist|PronType=Dem|Style=Coll": { + POS: DET, + "Distance": "Dist", + "PronType": "Dem", + "Style": "Coll", + }, + "DET_Distance=Dist|PronType=Dem|Style=Vrnc": { + POS: DET, + "Distance": "Dist", + "PronType": "Dem", + "Style": "Vrnc", + }, + "DET_Distance=Med|PronType=Dem": {POS: DET, "Distance": "Med", "PronType": "Dem"}, + "DET_Distance=Med|PronType=Dem|Style=Coll": { + POS: DET, + "Distance": "Med", + "PronType": "Dem", + "Style": "Coll", + }, + "DET_Distance=Prox|PronType=Dem": {POS: DET, "Distance": "Prox", "PronType": "Dem"}, + "DET_Distance=Prox|PronType=Dem|Style=Coll": { + POS: DET, + "Distance": "Prox", + "PronType": "Dem", + "Style": "Coll", + }, + "DET_PronType=Art": {POS: DET, "PronType": "Art"}, + "DET_PronType=Exc": {POS: DET, "PronType": "Exc"}, + "DET_PronType=Ind": {POS: DET, "PronType": "Ind"}, + "DET_PronType=Int": {POS: DET, "PronType": "Int"}, + "DET_PronType=Tot": {POS: DET, "PronType": "Tot"}, + "DET_PronType=Tot|Style=Arch": {POS: DET, "PronType": "Tot", "Style": "Arch"}, + "INTJ_Style=Vrnc": {POS: INTJ, "Style": "Vrnc"}, + "NOUN_Abbr=Yes|Animacy=Nhum|Case=Dat|Definite=Ind|Number=Plur": { + POS: NOUN, + "Abbr": "Yes", + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Ind", + "Number": "Plur", + }, + "NOUN_Abbr=Yes|Animacy=Nhum|Case=Nom|Definite=Ind|Number=Sing": { + POS: NOUN, + "Abbr": "Yes", + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Ind", + "Number": "Sing", + }, + "NOUN_Animacy=Hum|Case=Abl|Definite=Ind|Number=Plur": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Abl", + "Definite": "Ind", + "Number": "Plur", + }, + "NOUN_Animacy=Hum|Case=Abl|Definite=Ind|Number=Plur|Style=Slng": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Abl", + "Definite": "Ind", + "Number": "Plur", + "Style": "Slng", + }, + "NOUN_Animacy=Hum|Case=Abl|Definite=Ind|Number=Sing": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Abl", + "Definite": "Ind", + "Number": "Sing", + }, + "NOUN_Animacy=Hum|Case=Dat|Definite=Def|Number=Plur": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Dat", + "Definite": "Def", + "Number": "Plur", + }, + "NOUN_Animacy=Hum|Case=Dat|Definite=Def|Number=Sing": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Dat", + "Definite": "Def", + "Number": "Sing", + }, + "NOUN_Animacy=Hum|Case=Dat|Definite=Def|Number=Sing|Style=Slng": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Dat", + "Definite": "Def", + "Number": "Sing", + "Style": "Slng", + }, + "NOUN_Animacy=Hum|Case=Dat|Definite=Ind|Number=Assoc": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Dat", + "Definite": "Ind", + "Number": "Assoc", + }, + "NOUN_Animacy=Hum|Case=Dat|Definite=Ind|Number=Plur": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Dat", + "Definite": "Ind", + "Number": "Plur", + }, + "NOUN_Animacy=Hum|Case=Dat|Definite=Ind|Number=Plur|Style=Coll": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Dat", + "Definite": "Ind", + "Number": "Plur", + "Style": "Coll", + }, + "NOUN_Animacy=Hum|Case=Dat|Definite=Ind|Number=Plur|Style=Slng": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Dat", + "Definite": "Ind", + "Number": "Plur", + "Style": "Slng", + }, + "NOUN_Animacy=Hum|Case=Dat|Definite=Ind|Number=Sing": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Dat", + "Definite": "Ind", + "Number": "Sing", + }, + "NOUN_Animacy=Hum|Case=Dat|Definite=Ind|Number=Sing|Style=Arch": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Dat", + "Definite": "Ind", + "Number": "Sing", + "Style": "Arch", + }, + "NOUN_Animacy=Hum|Case=Dat|Number=Sing|Number=Sing|Person=1": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Dat", + "Number": "Sing", + "Number": "Sing", + "Person": "1", + }, + "NOUN_Animacy=Hum|Case=Dat|Number=Sing|Number=Sing|Person=1|Style=Coll": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Dat", + "Number": "Sing", + "Number": "Sing", + "Person": "1", + "Style": "Coll", + }, + "NOUN_Animacy=Hum|Case=Ins|Definite=Ind|Number=Sing": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Ins", + "Definite": "Ind", + "Number": "Sing", + }, + "NOUN_Animacy=Hum|Case=Nom|Definite=Def|Number=Plur": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Def", + "Number": "Plur", + }, + "NOUN_Animacy=Hum|Case=Nom|Definite=Def|Number=Plur|Style=Slng": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Def", + "Number": "Plur", + "Style": "Slng", + }, + "NOUN_Animacy=Hum|Case=Nom|Definite=Def|Number=Sing": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Def", + "Number": "Sing", + }, + "NOUN_Animacy=Hum|Case=Nom|Definite=Def|Number=Sing|Style=Coll": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Def", + "Number": "Sing", + "Style": "Coll", + }, + "NOUN_Animacy=Hum|Case=Nom|Definite=Ind|Number=Assoc": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Ind", + "Number": "Assoc", + }, + "NOUN_Animacy=Hum|Case=Nom|Definite=Ind|Number=Plur": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Ind", + "Number": "Plur", + }, + "NOUN_Animacy=Hum|Case=Nom|Definite=Ind|Number=Plur|Style=Coll": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Ind", + "Number": "Plur", + "Style": "Coll", + }, + "NOUN_Animacy=Hum|Case=Nom|Definite=Ind|Number=Plur|Style=Slng": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Ind", + "Number": "Plur", + "Style": "Slng", + }, + "NOUN_Animacy=Hum|Case=Nom|Definite=Ind|Number=Plur|Typo=Yes": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Ind", + "Number": "Plur", + "Typo": "Yes", + }, + "NOUN_Animacy=Hum|Case=Nom|Definite=Ind|Number=Sing": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Ind", + "Number": "Sing", + }, + "NOUN_Animacy=Hum|Case=Nom|Definite=Ind|Number=Sing|Style=Coll": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Ind", + "Number": "Sing", + "Style": "Coll", + }, + "NOUN_Animacy=Hum|Case=Nom|Number=Sing|Number=Sing|Person=1": { + POS: NOUN, + "Animacy": "Hum", + "Case": "Nom", + "Number": "Sing", + "Number": "Sing", + "Person": "1", + }, + "NOUN_Animacy=Nhum|Case=Abl|Definite=Ind|Number=Coll": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Abl", + "Definite": "Ind", + "Number": "Coll", + }, + "NOUN_Animacy=Nhum|Case=Abl|Definite=Ind|Number=Plur": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Abl", + "Definite": "Ind", + "Number": "Plur", + }, + "NOUN_Animacy=Nhum|Case=Abl|Definite=Ind|Number=Sing": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Abl", + "Definite": "Ind", + "Number": "Sing", + }, + "NOUN_Animacy=Nhum|Case=Abl|Definite=Ind|Number=Sing|Style=Arch": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Abl", + "Definite": "Ind", + "Number": "Sing", + "Style": "Arch", + }, + "NOUN_Animacy=Nhum|Case=Abl|Number=Sing|Number=Sing|Person=2": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Abl", + "Number": "Sing", + "Number": "Sing", + "Person": "2", + }, + "NOUN_Animacy=Nhum|Case=Dat|Definite=Def|Number=Coll": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Def", + "Number": "Coll", + }, + "NOUN_Animacy=Nhum|Case=Dat|Definite=Def|Number=Plur": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Def", + "Number": "Plur", + }, + "NOUN_Animacy=Nhum|Case=Dat|Definite=Def|Number=Sing|NumForm=Digit": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Def", + "Number": "Sing", + "NumForm": "Digit", + }, + "NOUN_Animacy=Nhum|Case=Dat|Definite=Def|Number=Sing|NumForm=Word": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Def", + "Number": "Sing", + "NumForm": "Word", + }, + "NOUN_Animacy=Nhum|Case=Dat|Definite=Def|Number=Sing": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Def", + "Number": "Sing", + }, + "NOUN_Animacy=Nhum|Case=Dat|Definite=Def|Number=Sing|Style=Rare": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Def", + "Number": "Sing", + "Style": "Rare", + }, + "NOUN_Animacy=Nhum|Case=Dat|Definite=Def|Number=Sing|Style=Vrnc": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Def", + "Number": "Sing", + "Style": "Vrnc", + }, + "NOUN_Animacy=Nhum|Case=Dat|Definite=Ind|Number=Coll": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Ind", + "Number": "Coll", + }, + "NOUN_Animacy=Nhum|Case=Dat|Definite=Ind|Number=Plur": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Ind", + "Number": "Plur", + }, + "NOUN_Animacy=Nhum|Case=Dat|Definite=Ind|Number=Sing|NumForm=Digit": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Ind", + "Number": "Sing", + "NumForm": "Digit", + }, + "NOUN_Animacy=Nhum|Case=Dat|Definite=Ind|Number=Sing": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Ind", + "Number": "Sing", + }, + "NOUN_Animacy=Nhum|Case=Dat|Definite=Ind|Number=Sing|Style=Coll": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Ind", + "Number": "Sing", + "Style": "Coll", + }, + "NOUN_Animacy=Nhum|Case=Dat|Definite=Ind|Number=Sing|Style=Vrnc": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Ind", + "Number": "Sing", + "Style": "Vrnc", + }, + "NOUN_Animacy=Nhum|Case=Dat|Number=Coll|Number=Sing|Person=1": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Number": "Coll", + "Number": "Sing", + "Person": "1", + }, + "NOUN_Animacy=Nhum|Case=Dat|Number=Sing|Number=Sing|Person=1": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Number": "Sing", + "Number": "Sing", + "Person": "1", + }, + "NOUN_Animacy=Nhum|Case=Dat|Number=Sing|Number=Sing|Person=2": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Dat", + "Number": "Sing", + "Number": "Sing", + "Person": "2", + }, + "NOUN_Animacy=Nhum|Case=Gen|Definite=Ind|Number=Sing|Style=Arch": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Gen", + "Definite": "Ind", + "Number": "Sing", + "Style": "Arch", + }, + "NOUN_Animacy=Nhum|Case=Ins|Definite=Ind|Number=Coll": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Ins", + "Definite": "Ind", + "Number": "Coll", + }, + "NOUN_Animacy=Nhum|Case=Ins|Definite=Ind|Number=Plur": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Ins", + "Definite": "Ind", + "Number": "Plur", + }, + "NOUN_Animacy=Nhum|Case=Ins|Definite=Ind|Number=Sing": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Ins", + "Definite": "Ind", + "Number": "Sing", + }, + "NOUN_Animacy=Nhum|Case=Ins|Definite=Ind|Number=Sing|Style=Coll": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Ins", + "Definite": "Ind", + "Number": "Sing", + "Style": "Coll", + }, + "NOUN_Animacy=Nhum|Case=Ins|Number=Sing|Number=Sing|Person=1": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Ins", + "Number": "Sing", + "Number": "Sing", + "Person": "1", + }, + "NOUN_Animacy=Nhum|Case=Loc|Definite=Ind|Number=Plur": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Loc", + "Definite": "Ind", + "Number": "Plur", + }, + "NOUN_Animacy=Nhum|Case=Loc|Definite=Ind|Number=Sing": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Loc", + "Definite": "Ind", + "Number": "Sing", + }, + "NOUN_Animacy=Nhum|Case=Loc|Number=Sing|Number=Sing|Person=2": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Loc", + "Number": "Sing", + "Number": "Sing", + "Person": "2", + }, + "NOUN_Animacy=Nhum|Case=Nom|Definite=Def|Number=Coll": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Def", + "Number": "Coll", + }, + "NOUN_Animacy=Nhum|Case=Nom|Definite=Def|Number=Plur|Number=Sing|Poss=Yes": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Def", + "Number": "Plur", + "Number": "Sing", + "Poss": "Yes", + }, + "NOUN_Animacy=Nhum|Case=Nom|Definite=Def|Number=Plur": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Def", + "Number": "Plur", + }, + "NOUN_Animacy=Nhum|Case=Nom|Definite=Def|Number=Sing|NumForm=Digit": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Def", + "Number": "Sing", + "NumForm": "Digit", + }, + "NOUN_Animacy=Nhum|Case=Nom|Definite=Def|Number=Sing": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Def", + "Number": "Sing", + }, + "NOUN_Animacy=Nhum|Case=Nom|Definite=Ind|Number=Coll": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Ind", + "Number": "Coll", + }, + "NOUN_Animacy=Nhum|Case=Nom|Definite=Ind|Number=Coll|Typo=Yes": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Ind", + "Number": "Coll", + "Typo": "Yes", + }, + "NOUN_Animacy=Nhum|Case=Nom|Definite=Ind|Number=Plur": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Ind", + "Number": "Plur", + }, + "NOUN_Animacy=Nhum|Case=Nom|Definite=Ind|Number=Sing": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Ind", + "Number": "Sing", + }, + "NOUN_Animacy=Nhum|Case=Nom|Definite=Ind": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Ind", + }, + "NOUN_Animacy=Nhum|Case=Nom|Number=Plur|Number=Sing|Person=2": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Nom", + "Number": "Plur", + "Number": "Sing", + "Person": "2", + }, + "NOUN_Animacy=Nhum|Case=Nom|Number=Sing|Number=Sing|Person=1": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Nom", + "Number": "Sing", + "Number": "Sing", + "Person": "1", + }, + "NOUN_Animacy=Nhum|Case=Nom|Number=Sing|Number=Sing|Person=2": { + POS: NOUN, + "Animacy": "Nhum", + "Case": "Nom", + "Number": "Sing", + "Number": "Sing", + "Person": "2", + }, + "NUM_NumForm=Digit|NumType=Card": {POS: NUM, "NumForm": "Digit", "NumType": "Card"}, + "NUM_NumForm=Digit|NumType=Frac|Typo=Yes": { + POS: NUM, + "NumForm": "Digit", + "NumType": "Frac", + "Typo": "Yes", + }, + "NUM_NumForm=Digit|NumType=Range": { + POS: NUM, + "NumForm": "Digit", + "NumType": "Range", + }, + "NUM_NumForm=Word|NumType=Card": {POS: NUM, "NumForm": "Word", "NumType": "Card"}, + "NUM_NumForm=Word|NumType=Dist": {POS: NUM, "NumForm": "Word", "NumType": "Dist"}, + "NUM_NumForm=Word|NumType=Range": {POS: NUM, "NumForm": "Word", "NumType": "Range"}, + "PART_Polarity=Neg": {POS: PART, "Polarity": "Neg"}, + "PRON_Case=Abl|Definite=Ind|Number=Sing|Person=3|PronType=Prs": { + POS: PRON, + "Case": "Abl", + "Definite": "Ind", + "Number": "Sing", + "Person": "3", + "PronType": "Prs", + }, + "PRON_Case=Abl|Number=Plur|Person=3|PronType=Prs": { + POS: PRON, + "Case": "Abl", + "Number": "Plur", + "Person": "3", + "PronType": "Prs", + }, + "PRON_Case=Abl|Number=Sing|Person=2|Polite=Infm|PronType=Prs": { + POS: PRON, + "Case": "Abl", + "Number": "Sing", + "Person": "2", + "Polite": "Infm", + "PronType": "Prs", + }, + "PRON_Case=Dat|Definite=Def|Distance=Dist|Number=Sing|PronType=Dem": { + POS: PRON, + "Case": "Dat", + "Definite": "Def", + "Distance": "Dist", + "Number": "Sing", + "PronType": "Dem", + }, + "PRON_Case=Dat|Definite=Def|Number=Sing|Person=3|PronType=Prs": { + POS: PRON, + "Case": "Dat", + "Definite": "Def", + "Number": "Sing", + "Person": "3", + "PronType": "Prs", + }, + "PRON_Case=Dat|Definite=Ind|Number=Sing|PronType=Int": { + POS: PRON, + "Case": "Dat", + "Definite": "Ind", + "Number": "Sing", + "PronType": "Int", + }, + "PRON_Case=Dat|Distance=Dist|Number=Sing|PronType=Dem": { + POS: PRON, + "Case": "Dat", + "Distance": "Dist", + "Number": "Sing", + "PronType": "Dem", + }, + "PRON_Case=Dat|Distance=Med|Number=Plur|PronType=Dem": { + POS: PRON, + "Case": "Dat", + "Distance": "Med", + "Number": "Plur", + "PronType": "Dem", + }, + "PRON_Case=Dat|Number=Plur|Person=1|PronType=Prs": { + POS: PRON, + "Case": "Dat", + "Number": "Plur", + "Person": "1", + "PronType": "Prs", + }, + "PRON_Case=Dat|Number=Plur|Person=2|Polite=Infm|PronType=Prs": { + POS: PRON, + "Case": "Dat", + "Number": "Plur", + "Person": "2", + "Polite": "Infm", + "PronType": "Prs", + }, + "PRON_Case=Dat|Number=Plur|Person=3|PronType=Emp|Reflex=Yes": { + POS: PRON, + "Case": "Dat", + "Number": "Plur", + "Person": "3", + "PronType": "Emp", + "Reflex": "Yes", + }, + "PRON_Case=Dat|Number=Plur|Person=3|PronType=Prs": { + POS: PRON, + "Case": "Dat", + "Number": "Plur", + "Person": "3", + "PronType": "Prs", + }, + "PRON_Case=Dat|Number=Plur|PronType=Rcp": { + POS: PRON, + "Case": "Dat", + "Number": "Plur", + "PronType": "Rcp", + }, + "PRON_Case=Dat|Number=Sing|Person=1|PronType=Prs": { + POS: PRON, + "Case": "Dat", + "Number": "Sing", + "Person": "1", + "PronType": "Prs", + }, + "PRON_Case=Dat|Number=Sing|Person=2|Polite=Infm|PronType=Prs": { + POS: PRON, + "Case": "Dat", + "Number": "Sing", + "Person": "2", + "Polite": "Infm", + "PronType": "Prs", + }, + "PRON_Case=Dat|Number=Sing|Person=3|PronType=Emp": { + POS: PRON, + "Case": "Dat", + "Number": "Sing", + "Person": "3", + "PronType": "Emp", + }, + "PRON_Case=Dat|Number=Sing|Person=3|PronType=Emp|Reflex=Yes": { + POS: PRON, + "Case": "Dat", + "Number": "Sing", + "Person": "3", + "PronType": "Emp", + "Reflex": "Yes", + }, + "PRON_Case=Dat|Number=Sing|PronType=Int": { + POS: PRON, + "Case": "Dat", + "Number": "Sing", + "PronType": "Int", + }, + "PRON_Case=Dat|Number=Sing|PronType=Rel": { + POS: PRON, + "Case": "Dat", + "Number": "Sing", + "PronType": "Rel", + }, + "PRON_Case=Dat|PronType=Tot": {POS: PRON, "Case": "Dat", "PronType": "Tot"}, + "PRON_Case=Gen|Distance=Med|Number=Sing|PronType=Dem": { + POS: PRON, + "Case": "Gen", + "Distance": "Med", + "Number": "Sing", + "PronType": "Dem", + }, + "PRON_Case=Gen|Number=Plur|Person=1|PronType=Prs": { + POS: PRON, + "Case": "Gen", + "Number": "Plur", + "Person": "1", + "PronType": "Prs", + }, + "PRON_Case=Gen|Number=Sing|Person=2|PronType=Prs": { + POS: PRON, + "Case": "Gen", + "Number": "Sing", + "Person": "2", + "PronType": "Prs", + }, + "PRON_Case=Gen|Number=Sing|Person=3|PronType=Prs": { + POS: PRON, + "Case": "Gen", + "Number": "Sing", + "Person": "3", + "PronType": "Prs", + }, + "PRON_Case=Gen|PronType=Tot": {POS: PRON, "Case": "Gen", "PronType": "Tot"}, + "PRON_Case=Ins|Definite=Ind|Number=Sing|PronType=Rel": { + POS: PRON, + "Case": "Ins", + "Definite": "Ind", + "Number": "Sing", + "PronType": "Rel", + }, + "PRON_Case=Ins|Distance=Med|Number=Sing|PronType=Dem": { + POS: PRON, + "Case": "Ins", + "Distance": "Med", + "Number": "Sing", + "PronType": "Dem", + }, + "PRON_Case=Loc|Definite=Ind|Number=Sing|PronType=Rel": { + POS: PRON, + "Case": "Loc", + "Definite": "Ind", + "Number": "Sing", + "PronType": "Rel", + }, + "PRON_Case=Loc|Distance=Med|Number=Sing|PronType=Dem": { + POS: PRON, + "Case": "Loc", + "Distance": "Med", + "Number": "Sing", + "PronType": "Dem", + }, + "PRON_Case=Nom|Definite=Def|Distance=Dist|Number=Plur|PronType=Dem": { + POS: PRON, + "Case": "Nom", + "Definite": "Def", + "Distance": "Dist", + "Number": "Plur", + "PronType": "Dem", + }, + "PRON_Case=Nom|Definite=Def|Distance=Med|Number=Sing|PronType=Dem|Style=Coll": { + POS: PRON, + "Case": "Nom", + "Definite": "Def", + "Distance": "Med", + "Number": "Sing", + "PronType": "Dem", + "Style": "Coll", + }, + "PRON_Case=Nom|Definite=Def|Number=Sing|PronType=Int": { + POS: PRON, + "Case": "Nom", + "Definite": "Def", + "Number": "Sing", + "PronType": "Int", + }, + "PRON_Case=Nom|Definite=Def|Number=Sing|PronType=Rel": { + POS: PRON, + "Case": "Nom", + "Definite": "Def", + "Number": "Sing", + "PronType": "Rel", + }, + "PRON_Case=Nom|Definite=Ind|Number=Sing|PronType=Int": { + POS: PRON, + "Case": "Nom", + "Definite": "Ind", + "Number": "Sing", + "PronType": "Int", + }, + "PRON_Case=Nom|Definite=Ind|Number=Sing|PronType=Neg": { + POS: PRON, + "Case": "Nom", + "Definite": "Ind", + "Number": "Sing", + "PronType": "Neg", + }, + "PRON_Case=Nom|Definite=Ind|Number=Sing|PronType=Rel": { + POS: PRON, + "Case": "Nom", + "Definite": "Ind", + "Number": "Sing", + "PronType": "Rel", + }, + "PRON_Case=Nom|Distance=Dist|Number=Plur|Person=1|PronType=Dem": { + POS: PRON, + "Case": "Nom", + "Distance": "Dist", + "Number": "Plur", + "Person": "1", + "PronType": "Dem", + }, + "PRON_Case=Nom|Distance=Med|Number=Plur|PronType=Dem": { + POS: PRON, + "Case": "Nom", + "Distance": "Med", + "Number": "Plur", + "PronType": "Dem", + }, + "PRON_Case=Nom|Distance=Med|Number=Sing|PronType=Dem": { + POS: PRON, + "Case": "Nom", + "Distance": "Med", + "Number": "Sing", + "PronType": "Dem", + }, + "PRON_Case=Nom|Distance=Prox|Number=Sing|PronType=Dem": { + POS: PRON, + "Case": "Nom", + "Distance": "Prox", + "Number": "Sing", + "PronType": "Dem", + }, + "PRON_Case=Nom|Number=Plur|Person=1|PronType=Prs": { + POS: PRON, + "Case": "Nom", + "Number": "Plur", + "Person": "1", + "PronType": "Prs", + }, + "PRON_Case=Nom|Number=Plur|Person=3|PronType=Emp": { + POS: PRON, + "Case": "Nom", + "Number": "Plur", + "Person": "3", + "PronType": "Emp", + }, + "PRON_Case=Nom|Number=Plur|Person=3|PronType=Prs": { + POS: PRON, + "Case": "Nom", + "Number": "Plur", + "Person": "3", + "PronType": "Prs", + }, + "PRON_Case=Nom|Number=Plur|PronType=Rel": { + POS: PRON, + "Case": "Nom", + "Number": "Plur", + "PronType": "Rel", + }, + "PRON_Case=Nom|Number=Sing|Number=Plur|Person=3|Person=1|PronType=Emp": { + POS: PRON, + "Case": "Nom", + "Number": "Sing", + "Number": "Plur", + "Person": "3", + "Person": "1", + "PronType": "Emp", + }, + "PRON_Case=Nom|Number=Sing|Person=1|PronType=Int": { + POS: PRON, + "Case": "Nom", + "Number": "Sing", + "Person": "1", + "PronType": "Int", + }, + "PRON_Case=Nom|Number=Sing|Person=1|PronType=Prs": { + POS: PRON, + "Case": "Nom", + "Number": "Sing", + "Person": "1", + "PronType": "Prs", + }, + "PRON_Case=Nom|Number=Sing|Person=2|Polite=Infm|PronType=Prs": { + POS: PRON, + "Case": "Nom", + "Number": "Sing", + "Person": "2", + "Polite": "Infm", + "PronType": "Prs", + }, + "PRON_Case=Nom|Number=Sing|Person=3|PronType=Emp": { + POS: PRON, + "Case": "Nom", + "Number": "Sing", + "Person": "3", + "PronType": "Emp", + }, + "PRON_Case=Nom|Number=Sing|Person=3|PronType=Prs": { + POS: PRON, + "Case": "Nom", + "Number": "Sing", + "Person": "3", + "PronType": "Prs", + }, + "PRON_Case=Nom|Number=Sing|PronType=Int": { + POS: PRON, + "Case": "Nom", + "Number": "Sing", + "PronType": "Int", + }, + "PRON_Case=Nom|Number=Sing|PronType=Rel": { + POS: PRON, + "Case": "Nom", + "Number": "Sing", + "PronType": "Rel", + }, + "PRON_Case=Nom|Person=1|PronType=Tot": { + POS: PRON, + "Case": "Nom", + "Person": "1", + "PronType": "Tot", + }, + "PRON_Case=Nom|PronType=Ind": {POS: PRON, "Case": "Nom", "PronType": "Ind"}, + "PRON_Case=Nom|PronType=Tot": {POS: PRON, "Case": "Nom", "PronType": "Tot"}, + "PRON_Distance=Dist|Number=Sing|PronType=Dem": { + POS: PRON, + "Distance": "Dist", + "Number": "Sing", + "PronType": "Dem", + }, + "PRON_Distance=Med|PronType=Dem|Style=Coll": { + POS: PRON, + "Distance": "Med", + "PronType": "Dem", + "Style": "Coll", + }, + "PRON_Distance=Prox|PronType=Dem|Style=Coll": { + POS: PRON, + "Distance": "Prox", + "PronType": "Dem", + "Style": "Coll", + }, + "PRON_Number=Plur|PronType=Rel": {POS: PRON, "Number": "Plur", "PronType": "Rel"}, + "PROPN_Abbr=Yes|Animacy=Hum|Case=Nom|Definite=Ind|NameType=Giv|Number=Sing": { + POS: PROPN, + "Abbr": "Yes", + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Ind", + "NameType": "Giv", + "Number": "Sing", + }, + "PROPN_Abbr=Yes|Animacy=Nhum|Case=Nom|Definite=Ind|NameType=Com|Number=Sing": { + POS: PROPN, + "Abbr": "Yes", + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Ind", + "NameType": "Com", + "Number": "Sing", + }, + "PROPN_Animacy=Hum|Case=Dat|Definite=Def|NameType=Sur|Number=Sing": { + POS: PROPN, + "Animacy": "Hum", + "Case": "Dat", + "Definite": "Def", + "NameType": "Sur", + "Number": "Sing", + }, + "PROPN_Animacy=Hum|Case=Dat|Definite=Ind|NameType=Prs|Number=Sing": { + POS: PROPN, + "Animacy": "Hum", + "Case": "Dat", + "Definite": "Ind", + "NameType": "Prs", + "Number": "Sing", + }, + "PROPN_Animacy=Hum|Case=Dat|Definite=Ind|NameType=Sur|Number=Sing": { + POS: PROPN, + "Animacy": "Hum", + "Case": "Dat", + "Definite": "Ind", + "NameType": "Sur", + "Number": "Sing", + }, + "PROPN_Animacy=Hum|Case=Nom|Definite=Def|NameType=Giv|Number=Sing": { + POS: PROPN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Def", + "NameType": "Giv", + "Number": "Sing", + }, + "PROPN_Animacy=Hum|Case=Nom|Definite=Def|NameType=Sur|Number=Sing": { + POS: PROPN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Def", + "NameType": "Sur", + "Number": "Sing", + }, + "PROPN_Animacy=Hum|Case=Nom|Definite=Ind|NameType=Giv|Number=Sing": { + POS: PROPN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Ind", + "NameType": "Giv", + "Number": "Sing", + }, + "PROPN_Animacy=Hum|Case=Nom|Definite=Ind|NameType=Sur|Number=Sing": { + POS: PROPN, + "Animacy": "Hum", + "Case": "Nom", + "Definite": "Ind", + "NameType": "Sur", + "Number": "Sing", + }, + "PROPN_Animacy=Nhum|Case=Abl|Definite=Ind|NameType=Geo|Number=Coll": { + POS: PROPN, + "Animacy": "Nhum", + "Case": "Abl", + "Definite": "Ind", + "NameType": "Geo", + "Number": "Coll", + }, + "PROPN_Animacy=Nhum|Case=Abl|Definite=Ind|NameType=Geo|Number=Sing": { + POS: PROPN, + "Animacy": "Nhum", + "Case": "Abl", + "Definite": "Ind", + "NameType": "Geo", + "Number": "Sing", + }, + "PROPN_Animacy=Nhum|Case=Abl|Definite=Ind|Number=Plur": { + POS: PROPN, + "Animacy": "Nhum", + "Case": "Abl", + "Definite": "Ind", + "Number": "Plur", + }, + "PROPN_Animacy=Nhum|Case=Dat|Definite=Ind|NameType=Geo|Number=Sing": { + POS: PROPN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Ind", + "NameType": "Geo", + "Number": "Sing", + }, + "PROPN_Animacy=Nhum|Case=Dat|Definite=Ind|NameType=Geo|Number=Sing|Style=Coll": { + POS: PROPN, + "Animacy": "Nhum", + "Case": "Dat", + "Definite": "Ind", + "NameType": "Geo", + "Number": "Sing", + "Style": "Coll", + }, + "PROPN_Animacy=Nhum|Case=Loc|Definite=Ind|NameType=Geo|Number=Sing": { + POS: PROPN, + "Animacy": "Nhum", + "Case": "Loc", + "Definite": "Ind", + "NameType": "Geo", + "Number": "Sing", + }, + "PROPN_Animacy=Nhum|Case=Nom|Definite=Def|NameType=Geo|Number=Sing": { + POS: PROPN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Def", + "NameType": "Geo", + "Number": "Sing", + }, + "PROPN_Animacy=Nhum|Case=Nom|Definite=Def|NameType=Pro|Number=Sing|Style=Coll": { + POS: PROPN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Def", + "NameType": "Pro", + "Number": "Sing", + "Style": "Coll", + }, + "PROPN_Animacy=Nhum|Case=Nom|Definite=Ind|NameType=Geo|Number=Coll": { + POS: PROPN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Ind", + "NameType": "Geo", + "Number": "Coll", + }, + "PROPN_Animacy=Nhum|Case=Nom|Definite=Ind|NameType=Geo|Number=Sing": { + POS: PROPN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Ind", + "NameType": "Geo", + "Number": "Sing", + }, + "PROPN_Animacy=Nhum|Case=Nom|Definite=Ind|NameType=Geo|Number=Sing|Style=Vrnc": { + POS: PROPN, + "Animacy": "Nhum", + "Case": "Nom", + "Definite": "Ind", + "NameType": "Geo", + "Number": "Sing", + "Style": "Vrnc", + }, + "SCONJ_Style=Coll": {POS: SCONJ, "Style": "Coll"}, + "VERB_Aspect=Dur|Polarity=Neg|Subcat=Intr|VerbForm=Part|Voice=Pass": { + POS: VERB, + "Aspect": "Dur", + "Polarity": "Neg", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Pass", + }, + "VERB_Aspect=Dur|Polarity=Pos|Subcat=Intr|VerbForm=Part|Voice=Mid": { + POS: VERB, + "Aspect": "Dur", + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Mid", + }, + "VERB_Aspect=Dur|Polarity=Pos|Subcat=Intr|VerbForm=Part|Voice=Pass": { + POS: VERB, + "Aspect": "Dur", + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Pass", + }, + "VERB_Aspect=Dur|Polarity=Pos|Subcat=Tran|VerbForm=Part|Voice=Act": { + POS: VERB, + "Aspect": "Dur", + "Polarity": "Pos", + "Subcat": "Tran", + "VerbForm": "Part", + "Voice": "Act", + }, + "VERB_Aspect=Dur|Polarity=Pos|Subcat=Tran|VerbForm=Part|Voice=Mid": { + POS: VERB, + "Aspect": "Dur", + "Polarity": "Pos", + "Subcat": "Tran", + "VerbForm": "Part", + "Voice": "Mid", + }, + "VERB_Aspect=Imp|Mood=Ind|Number=Plur|Person=1|Polarity=Neg|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Plur", + "Person": "1", + "Polarity": "Neg", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Imp|Mood=Ind|Number=Plur|Person=1|Polarity=Pos|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Plur", + "Person": "1", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Polarity=Neg|Subcat=Intr|Tense=Pres|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Plur", + "Person": "3", + "Polarity": "Neg", + "Subcat": "Intr", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Imp|Mood=Ind|Number=Plur|Person=3|Polarity=Pos|Subcat=Intr|Tense=Pres|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Plur", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Intr", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Imp|Mood=Ind|Number=Sing|Person=1|Polarity=Pos|Subcat=Tran|Tense=Imp|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "1", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Imp", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Imp|Mood=Ind|Number=Sing|Person=2|Polarity=Neg|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "2", + "Polarity": "Neg", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Polarity=Neg|Subcat=Intr|Tense=Pres|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Neg", + "Subcat": "Intr", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Polarity=Neg|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Neg", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Subcat=Intr|Tense=Pres|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Intr", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Subcat=Tran|Tense=Imp|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Imp", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Imp|Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Imp", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Imp|Style=Coll|Subcat=Intr|VerbForm=Part|Voice=Mid": { + POS: VERB, + "Aspect": "Imp", + "Style": "Coll", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Mid", + }, + "VERB_Aspect=Imp|Style=Vrnc|Subcat=Intr|VerbForm=Part|Voice=Mid": { + POS: VERB, + "Aspect": "Imp", + "Style": "Vrnc", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Mid", + }, + "VERB_Aspect=Imp|Subcat=Intr|VerbForm=Part": { + POS: VERB, + "Aspect": "Imp", + "Subcat": "Intr", + "VerbForm": "Part", + }, + "VERB_Aspect=Imp|Subcat=Intr|VerbForm=Part|Voice=Act": { + POS: VERB, + "Aspect": "Imp", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Act", + }, + "VERB_Aspect=Imp|Subcat=Intr|VerbForm=Part|Voice=Mid": { + POS: VERB, + "Aspect": "Imp", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Mid", + }, + "VERB_Aspect=Imp|Subcat=Intr|VerbForm=Part|Voice=Pass": { + POS: VERB, + "Aspect": "Imp", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Pass", + }, + "VERB_Aspect=Imp|Subcat=Tran|VerbForm=Part|Voice=Act": { + POS: VERB, + "Aspect": "Imp", + "Subcat": "Tran", + "VerbForm": "Part", + "Voice": "Act", + }, + "VERB_Aspect=Imp|Subcat=Tran|VerbForm=Part|Voice=Cau": { + POS: VERB, + "Aspect": "Imp", + "Subcat": "Tran", + "VerbForm": "Part", + "Voice": "Cau", + }, + "VERB_Aspect=Iter|Case=Ins|Definite=Ind|Number=Coll|Polarity=Pos|Subcat=Intr|VerbForm=Gdv|Voice=Mid": { + POS: VERB, + "Aspect": "Iter", + "Case": "Ins", + "Definite": "Ind", + "Number": "Coll", + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Gdv", + "Voice": "Mid", + }, + "VERB_Aspect=Iter|Case=Ins|Definite=Ind|Number=Coll|Polarity=Pos|Subcat=Tran|VerbForm=Gdv|Voice=Act": { + POS: VERB, + "Aspect": "Iter", + "Case": "Ins", + "Definite": "Ind", + "Number": "Coll", + "Polarity": "Pos", + "Subcat": "Tran", + "VerbForm": "Gdv", + "Voice": "Act", + }, + "VERB_Aspect=Iter": {POS: VERB, "Aspect": "Iter"}, + "VERB_Aspect=Perf|Mood=Ind|Number=Plur|Person=3|Polarity=Neg|Subcat=Intr|Tense=Past|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Perf", + "Mood": "Ind", + "Number": "Plur", + "Person": "3", + "Polarity": "Neg", + "Subcat": "Intr", + "Tense": "Past", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Perf|Mood=Ind|Number=Plur|Person=3|Polarity=Pos|Subcat=Intr|Tense=Past|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Perf", + "Mood": "Ind", + "Number": "Plur", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Intr", + "Tense": "Past", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Perf|Mood=Ind|Number=Plur|Person=3|Polarity=Pos|Subcat=Tran|Tense=Past|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Perf", + "Mood": "Ind", + "Number": "Plur", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Past", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Perf|Mood=Ind|Number=Sing|Person=1|Polarity=Neg|Subcat=Intr|Tense=Past|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Perf", + "Mood": "Ind", + "Number": "Sing", + "Person": "1", + "Polarity": "Neg", + "Subcat": "Intr", + "Tense": "Past", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Perf|Mood=Ind|Number=Sing|Person=1|Polarity=Pos|Style=Vrnc|Subcat=Tran|Tense=Past|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Perf", + "Mood": "Ind", + "Number": "Sing", + "Person": "1", + "Polarity": "Pos", + "Style": "Vrnc", + "Subcat": "Tran", + "Tense": "Past", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Perf|Mood=Ind|Number=Sing|Person=1|Polarity=Pos|Subcat=Intr|Tense=Past|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Perf", + "Mood": "Ind", + "Number": "Sing", + "Person": "1", + "Polarity": "Pos", + "Subcat": "Intr", + "Tense": "Past", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Perf|Mood=Ind|Number=Sing|Person=1|Polarity=Pos|Subcat=Tran|Tense=Past|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Perf", + "Mood": "Ind", + "Number": "Sing", + "Person": "1", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Past", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Perf|Mood=Ind|Number=Sing|Person=2|Polarity=Pos|Subcat=Tran|Tense=Past|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Perf", + "Mood": "Ind", + "Number": "Sing", + "Person": "2", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Past", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Perf|Mood=Ind|Number=Sing|Person=3|Polarity=Neg|Style=Vrnc|Subcat=Intr|Tense=Past|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Perf", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Neg", + "Style": "Vrnc", + "Subcat": "Intr", + "Tense": "Past", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Perf|Mood=Ind|Number=Sing|Person=3|Polarity=Neg|Subcat=Tran|Tense=Past|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Perf", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Neg", + "Subcat": "Tran", + "Tense": "Past", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Perf|Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Subcat=Intr|Tense=Past|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Perf", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Intr", + "Tense": "Past", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Perf|Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Subcat=Tran|Tense=Past|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Perf", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Past", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Perf|Mood=Ind|Number=Sing|Person=3|Polarity=Pos|Subcat=Tran|Tense=Past|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Perf", + "Mood": "Ind", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Past", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Perf|Polarity=Neg|Subcat=Intr|VerbForm=Part|Voice=Pass": { + POS: VERB, + "Aspect": "Perf", + "Polarity": "Neg", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Pass", + }, + "VERB_Aspect=Perf|Polarity=Pos|Subcat=Intr|VerbForm=Part|Voice=Mid": { + POS: VERB, + "Aspect": "Perf", + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Mid", + }, + "VERB_Aspect=Perf|Polarity=Pos|Subcat=Intr|VerbForm=Part|Voice=Pass": { + POS: VERB, + "Aspect": "Perf", + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Pass", + }, + "VERB_Aspect=Perf|Polarity=Pos|Subcat=Tran|VerbForm=Part|Voice=Act": { + POS: VERB, + "Aspect": "Perf", + "Polarity": "Pos", + "Subcat": "Tran", + "VerbForm": "Part", + "Voice": "Act", + }, + "VERB_Aspect=Perf|Polarity=Pos|Subcat=Tran|VerbForm=Part|Voice=Pass": { + POS: VERB, + "Aspect": "Perf", + "Polarity": "Pos", + "Subcat": "Tran", + "VerbForm": "Part", + "Voice": "Pass", + }, + "VERB_Aspect=Perf|Polarity=Pos|VerbForm=Part|Voice=Act": { + POS: VERB, + "Aspect": "Perf", + "Polarity": "Pos", + "VerbForm": "Part", + "Voice": "Act", + }, + "VERB_Aspect=Perf|Subcat=Intr|VerbForm=Part|Voice=Mid": { + POS: VERB, + "Aspect": "Perf", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Mid", + }, + "VERB_Aspect=Perf|Subcat=Intr|VerbForm=Part|Voice=Pass": { + POS: VERB, + "Aspect": "Perf", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Pass", + }, + "VERB_Aspect=Perf|Subcat=Tran|VerbForm=Part|Voice=Act": { + POS: VERB, + "Aspect": "Perf", + "Subcat": "Tran", + "VerbForm": "Part", + "Voice": "Act", + }, + "VERB_Aspect=Perf|Subcat=Tran|VerbForm=Part|Voice=Cau": { + POS: VERB, + "Aspect": "Perf", + "Subcat": "Tran", + "VerbForm": "Part", + "Voice": "Cau", + }, + "VERB_Aspect=Prog|Subcat=Intr|VerbForm=Conv|Voice=Mid": { + POS: VERB, + "Aspect": "Prog", + "Subcat": "Intr", + "VerbForm": "Conv", + "Voice": "Mid", + }, + "VERB_Aspect=Prosp|Connegative=Yes|Mood=Cnd|Subcat=Tran|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Connegative": "Yes", + "Mood": "Cnd", + "Subcat": "Tran", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Mood=Cnd|Number=Plur|Person=3|Polarity=Pos|Style=Vrnc|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Cnd", + "Number": "Plur", + "Person": "3", + "Polarity": "Pos", + "Style": "Vrnc", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Mood=Cnd|Number=Plur|Person=3|Polarity=Pos|Subcat=Intr|Tense=Pres|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Cnd", + "Number": "Plur", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Intr", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Prosp|Mood=Cnd|Number=Sing|Person=1|Polarity=Pos|Subcat=Intr|Tense=Pres|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Cnd", + "Number": "Sing", + "Person": "1", + "Polarity": "Pos", + "Subcat": "Intr", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Prosp|Mood=Cnd|Number=Sing|Person=2|Polarity=Pos|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Cnd", + "Number": "Sing", + "Person": "2", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Mood=Cnd|Number=Sing|Person=3|Polarity=Pos|Subcat=Intr|Tense=Pres|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Cnd", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Intr", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Prosp|Mood=Cnd|Number=Sing|Person=3|Polarity=Pos|Subcat=Intr|Tense=Pres|VerbForm=Fin|Voice=Pass": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Cnd", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Intr", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Pass", + }, + "VERB_Aspect=Prosp|Mood=Cnd|Number=Sing|Person=3|Polarity=Pos|Subcat=Tran|Tense=Imp|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Cnd", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Imp", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Mood=Cnd|Number=Sing|Person=3|Polarity=Pos|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Cnd", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Mood=Imp|Number=Sing|Person=2|Subcat=Intr|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Imp", + "Number": "Sing", + "Person": "2", + "Subcat": "Intr", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Prosp|Mood=Imp|Number=Sing|Person=2|Subcat=Tran|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Imp", + "Number": "Sing", + "Person": "2", + "Subcat": "Tran", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Plur|Person=1|Polarity=Pos|Subcat=Intr|Tense=Pres|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Plur", + "Person": "1", + "Polarity": "Pos", + "Subcat": "Intr", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Plur|Person=3|Polarity=Neg|Subcat=Intr|Tense=Pres|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Plur", + "Person": "3", + "Polarity": "Neg", + "Subcat": "Intr", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Plur|Person=3|Polarity=Pos|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Plur", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Sing|Person=1|Polarity=Neg|Subcat=Intr|Tense=Pres|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Sing", + "Person": "1", + "Polarity": "Neg", + "Subcat": "Intr", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Sing|Person=1|Polarity=Neg|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Sing", + "Person": "1", + "Polarity": "Neg", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Sing|Person=1|Polarity=Pos|Subcat=Intr|Tense=Pres|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Sing", + "Person": "1", + "Polarity": "Pos", + "Subcat": "Intr", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Sing|Person=1|Polarity=Pos|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Sing", + "Person": "1", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Sing|Person=2|Polarity=Pos|Subcat=Tran|Tense=Imp|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Sing", + "Person": "2", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Imp", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Sing|Person=2|Polarity=Pos|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Sing", + "Person": "2", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Sing|Person=3|Polarity=Pos|Subcat=Intr|Tense=Imp|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Intr", + "Tense": "Imp", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Sing|Person=3|Polarity=Pos|Subcat=Intr|Tense=Pres|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Intr", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Sing|Person=3|Polarity=Pos|Subcat=Intr|VerbForm=Fin|Voice=Pass": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Fin", + "Voice": "Pass", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Sing|Person=3|Polarity=Pos|Subcat=Tran|Tense=Imp|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Imp", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Mood=Sub|Number=Sing|Person=3|Polarity=Pos|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Number": "Sing", + "Person": "3", + "Polarity": "Pos", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Mood=Sub|Person=1|Polarity=Neg|Subcat=Tran|Tense=Pres|VerbForm=Fin|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Mood": "Sub", + "Person": "1", + "Polarity": "Neg", + "Subcat": "Tran", + "Tense": "Pres", + "VerbForm": "Fin", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Polarity=Pos|Subcat=Intr|VerbForm=Part|Voice=Mid": { + POS: VERB, + "Aspect": "Prosp", + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Mid", + }, + "VERB_Aspect=Prosp|Polarity=Pos|Subcat=Tran|VerbForm=Part|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Polarity": "Pos", + "Subcat": "Tran", + "VerbForm": "Part", + "Voice": "Act", + }, + "VERB_Aspect=Prosp|Subcat=Intr|VerbForm=Part|Voice=Mid": { + POS: VERB, + "Aspect": "Prosp", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Mid", + }, + "VERB_Aspect=Prosp|Subcat=Intr|VerbForm=Part|Voice=Pass": { + POS: VERB, + "Aspect": "Prosp", + "Subcat": "Intr", + "VerbForm": "Part", + "Voice": "Pass", + }, + "VERB_Aspect=Prosp|Subcat=Tran|VerbForm=Part|Voice=Act": { + POS: VERB, + "Aspect": "Prosp", + "Subcat": "Tran", + "VerbForm": "Part", + "Voice": "Act", + }, + "VERB_Case=Abl|Definite=Ind|Number=Coll|Polarity=Pos|Subcat=Intr|VerbForm=Gdv|Voice=Mid": { + POS: VERB, + "Case": "Abl", + "Definite": "Ind", + "Number": "Coll", + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Gdv", + "Voice": "Mid", + }, + "VERB_Case=Abl|Definite=Ind|Number=Coll|Polarity=Pos|Subcat=Intr|VerbForm=Gdv|Voice=Pass": { + POS: VERB, + "Case": "Abl", + "Definite": "Ind", + "Number": "Coll", + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Gdv", + "Voice": "Pass", + }, + "VERB_Case=Abl|Definite=Ind|Number=Coll|Polarity=Pos|Subcat=Tran|VerbForm=Gdv|Voice=Act": { + POS: VERB, + "Case": "Abl", + "Definite": "Ind", + "Number": "Coll", + "Polarity": "Pos", + "Subcat": "Tran", + "VerbForm": "Gdv", + "Voice": "Act", + }, + "VERB_Case=Dat|Definite=Def|Number=Coll|Polarity=Pos|Subcat=Intr|VerbForm=Gdv|Voice=Mid": { + POS: VERB, + "Case": "Dat", + "Definite": "Def", + "Number": "Coll", + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Gdv", + "Voice": "Mid", + }, + "VERB_Case=Dat|Definite=Ind|Number=Coll|Polarity=Neg|Subcat=Intr|VerbForm=Gdv|Voice=Pass": { + POS: VERB, + "Case": "Dat", + "Definite": "Ind", + "Number": "Coll", + "Polarity": "Neg", + "Subcat": "Intr", + "VerbForm": "Gdv", + "Voice": "Pass", + }, + "VERB_Case=Dat|Definite=Ind|Number=Coll|Polarity=Pos|Subcat=Intr|VerbForm=Gdv|Voice=Mid": { + POS: VERB, + "Case": "Dat", + "Definite": "Ind", + "Number": "Coll", + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Gdv", + "Voice": "Mid", + }, + "VERB_Case=Dat|Definite=Ind|Number=Coll|Polarity=Pos|Subcat=Tran|VerbForm=Gdv|Voice=Act": { + POS: VERB, + "Case": "Dat", + "Definite": "Ind", + "Number": "Coll", + "Polarity": "Pos", + "Subcat": "Tran", + "VerbForm": "Gdv", + "Voice": "Act", + }, + "VERB_Case=Ins|Definite=Ind|Number=Coll|Polarity=Pos|Subcat=Intr|VerbForm=Gdv|Voice=Mid": { + POS: VERB, + "Case": "Ins", + "Definite": "Ind", + "Number": "Coll", + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Gdv", + "Voice": "Mid", + }, + "VERB_Case=Ins|Definite=Ind|Number=Coll|Polarity=Pos|Subcat=Tran|VerbForm=Gdv|Voice=Act": { + POS: VERB, + "Case": "Ins", + "Definite": "Ind", + "Number": "Coll", + "Polarity": "Pos", + "Subcat": "Tran", + "VerbForm": "Gdv", + "Voice": "Act", + }, + "VERB_Case=Nom|Definite=Def|Number=Coll|Polarity=Pos|Subcat=Intr|VerbForm=Gdv|Voice=Mid": { + POS: VERB, + "Case": "Nom", + "Definite": "Def", + "Number": "Coll", + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Gdv", + "Voice": "Mid", + }, + "VERB_Case=Nom|Definite=Def|Number=Coll|Polarity=Pos|Subcat=Tran|VerbForm=Gdv|Voice=Act": { + POS: VERB, + "Case": "Nom", + "Definite": "Def", + "Number": "Coll", + "Polarity": "Pos", + "Subcat": "Tran", + "VerbForm": "Gdv", + "Voice": "Act", + }, + "VERB_Mood=Imp|Number=Sing|Person=2|Subcat=Intr|VerbForm=Fin|Voice=Mid": { + POS: VERB, + "Mood": "Imp", + "Number": "Sing", + "Person": "2", + "Subcat": "Intr", + "VerbForm": "Fin", + "Voice": "Mid", + }, + "VERB_Polarity=Neg|Subcat=Intr|VerbForm=Inf|Voice=Mid": { + POS: VERB, + "Polarity": "Neg", + "Subcat": "Intr", + "VerbForm": "Inf", + "Voice": "Mid", + }, + "VERB_Polarity=Pos|Style=Coll|Subcat=Tran|VerbForm=Inf|Voice=Act": { + POS: VERB, + "Polarity": "Pos", + "Style": "Coll", + "Subcat": "Tran", + "VerbForm": "Inf", + "Voice": "Act", + }, + "VERB_Polarity=Pos|Style=Vrnc|Subcat=Tran|VerbForm=Inf|Voice=Act": { + POS: VERB, + "Polarity": "Pos", + "Style": "Vrnc", + "Subcat": "Tran", + "VerbForm": "Inf", + "Voice": "Act", + }, + "VERB_Polarity=Pos|Subcat=Intr|VerbForm=Inf|Voice=Mid": { + POS: VERB, + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Inf", + "Voice": "Mid", + }, + "VERB_Polarity=Pos|Subcat=Intr|VerbForm=Inf|Voice=Pass": { + POS: VERB, + "Polarity": "Pos", + "Subcat": "Intr", + "VerbForm": "Inf", + "Voice": "Pass", + }, + "VERB_Polarity=Pos|Subcat=Tran|Typo=Yes|VerbForm=Inf|Voice=Act": { + POS: VERB, + "Polarity": "Pos", + "Subcat": "Tran", + "Typo": "Yes", + "VerbForm": "Inf", + "Voice": "Act", + }, + "VERB_Polarity=Pos|Subcat=Tran|VerbForm=Inf|Voice=Act": { + POS: VERB, + "Polarity": "Pos", + "Subcat": "Tran", + "VerbForm": "Inf", + "Voice": "Act", + }, + "X_Foreign=Yes": {POS: X, "Foreign": "Yes"}, + "X_Style=Vrnc": {POS: X, "Style": "Vrnc"}, +} diff --git a/spacy/tests/conftest.py b/spacy/tests/conftest.py index fc89c2658..43c3152a0 100644 --- a/spacy/tests/conftest.py +++ b/spacy/tests/conftest.py @@ -234,3 +234,7 @@ def yo_tokenizer(): def zh_tokenizer(): pytest.importorskip("jieba") return get_lang_class("zh").Defaults.create_tokenizer() + +@pytest.fixture(scope="session") +def hy_tokenizer(): + return get_lang_class("hy").Defaults.create_tokenizer() \ No newline at end of file diff --git a/spacy/tests/lang/hy/test_text.py b/spacy/tests/lang/hy/test_text.py new file mode 100644 index 000000000..6b785bdfc --- /dev/null +++ b/spacy/tests/lang/hy/test_text.py @@ -0,0 +1,10 @@ +from __future__ import unicode_literals + +import pytest +from spacy.lang.hy.lex_attrs import like_num + + +@pytest.mark.parametrize("word", ["հիսուն"]) +def test_hy_lex_attrs_capitals(word): + assert like_num(word) + assert like_num(word.upper()) diff --git a/spacy/tests/lang/hy/test_tokenizer.py b/spacy/tests/lang/hy/test_tokenizer.py new file mode 100644 index 000000000..424fb886f --- /dev/null +++ b/spacy/tests/lang/hy/test_tokenizer.py @@ -0,0 +1,47 @@ +from __future__ import unicode_literals + +import pytest + + +# TODO add test cases with valid punctuation signs. + +hy_tokenize_text_test = [ + ( + "Մետաղագիտությունը պայմանականորեն բաժանվում է տեսականի և կիրառականի (տեխնիկական)", + [ + "Մետաղագիտությունը", + "պայմանականորեն", + "բաժանվում", + "է", + "տեսականի", + "և", + "կիրառականի", + "(", + "տեխնիկական", + ")", + ], + ), + ( + "Գետաբերանը գտնվում է Օմոլոնա գետի ձախ ափից 726 կմ հեռավորության վրա", + [ + "Գետաբերանը", + "գտնվում", + "է", + "Օմոլոնա", + "գետի", + "ձախ", + "ափից", + "726", + "կմ", + "հեռավորության", + "վրա", + ], + ), +] + + +@pytest.mark.parametrize("text,expected_tokens", hy_tokenize_text_test) +def test_ga_tokenizer_handles_exception_cases(hy_tokenizer, text, expected_tokens): + tokens = hy_tokenizer(text) + token_list = [token.text for token in tokens if not token.is_space] + assert expected_tokens == token_list