Setup tools and fix linter issues

.flake8

@@ -0,0 +1,6 @@
+[flake8]
+# E303 - too many blank lines
+# E203 - whitespace before semicolon
+ignore = E303, E203
+exclude = __init__.py
+max-line-length = 120

.vscode/launch.json

@@ -17,6 +17,13 @@
       "request": "launch",
       "script": "${workspaceFolder}/scripts/RunLint.ps1",
       "args": []
+    },
+    {
+      "name": "Setup",
+      "type": "PowerShell",
+      "request": "launch",
+      "script": "${workspaceFolder}/scripts/Setup.ps1",
+      "args": []
     }
   ]
 }

.vscode/settings.json

@@ -3,38 +3,58 @@
     ".mypy_cache/": true,
     ".pytest_cache/": true
   },
-  "python.testing.unittestArgs": ["-v", "-s", "./tests", "-p", "test*.py"],
+  "python.testing.unittestArgs": ["-v", "-s", "./tests", "-p", "t_*.py"],
   "python.testing.pytestEnabled": false,
   "python.testing.unittestEnabled": true,
-  "eslint.workingDirectories": [
-    {
-      "mode": "auto"
-    }
-  ],
   "python.analysis.typeCheckingMode": "off",
-  "python.analysis.ignore": ["**/tests/**", "**/node_modules/**", "**/venv/**"],
+  "python.analysis.ignore": ["**/tests/**", "**/venv/**"],
   "cSpell.words": [
+    "ablt",
+    "accs",
+    "actv",
     "ADJF",
     "ADJS",
     "ADVB",
+    "Anph",
+    "cctext",
+    "datv",
+    "femn",
+    "Fixd",
+    "Geox",
+    "grammeme",
     "Grammemes",
     "GRND",
+    "Impe",
+    "impr",
+    "inan",
+    "indc",
     "INFN",
+    "intg",
     "INTJ",
+    "loct",
+    "moprho",
     "multiword",
+    "nomn",
     "NPRO",
     "NUMR",
     "Opencorpora",
+    "Pltm",
     "PNCT",
     "PRCL",
+    "Prnt",
     "PRTF",
     "PRTS",
+    "pssv",
     "pymorphy",
     "razdel",
     "rumodel",
+    "ruparser",
+    "Sgtm",
     "tagset",
-    "unknwn"
+    "termform",
+    "unknwn",
+    "круть",
+    "фторметил"
   ],
-  "cSpell.language": "en,ru",
-  "cSpell.ignorePaths": ["node_modules/**", "*.json"]
+  "cSpell.language": "en,ru"
 }

TODO.txt

@@ -0,0 +1 @@
+- implement Part of speech transition for VERB <-> NOUN

cctext/__init__.py

@@ -1,16 +1,51 @@
 ''' Concept core text processing library. '''
 # pylint: skip-file
-from .syntax import RuSyntax, Capitalization
-from .rumodel import Morphology, SemanticRole, WordTag, morpho, split_grams, combine_grams
-from .ruparser import PhraseParser, WordToken, Collation
-from .reference import EntityReference, ReferenceType, SyntacticReference, parse_reference
-from .context import TermForm, Entity, TermContext
-from .resolver import Reference, Position, Resolver, ResolvedReference, resolve_entity, resolve_syntactic, extract_entities
-
-from .conceptapi import (
-    parse, normalize,
-    generate_lexeme, inflect, inflect_context, inflect_substitute, inflect_dependant,
-    match_all_morpho, find_substr
+from .syntax import (
+    RuSyntax,
+    Capitalization
+)
+from .rumodel import (
+    Morphology,
+    SemanticRole,
+    WordTag,
+    morpho,
+    split_grams,
+    combine_grams
+)
+from .ruparser import (
+    PhraseParser,
+    WordToken,
+    Collation
+)
+from .reference import (
+    EntityReference,
+    ReferenceType,
+    SyntacticReference,
+    parse_reference
+)
+from .context import (
+    TermForm,
+    Entity,
+    TermContext
+)
+from .resolver import (
+    Reference,
+    Position,
+    Resolver,
+    ResolvedReference,
+    resolve_entity,
+    resolve_syntactic,
+    extract_entities
 )
 
-# TODO: implement Part of speech transition for VERB <-> NOUN
+from .api import (
+    parse,
+    normalize,
+    generate_lexeme,
+    inflect,
+    inflect_context,
+    inflect_substitute,
+    inflect_dependant,
+    match_all_morpho,
+    find_substr
+)

cctext/api.py

@@ -1,5 +1,5 @@
 '''
-Concept API Python functions.
+Core API Python procedures.
 
 ::guarantee:: doesn't raise exceptions and returns workable outputs
 '''
@@ -21,11 +21,6 @@ def parse(text: str, require_grams: str = '') -> str:
     return result if result != 'UNKN' else ''
 
 
-# def parse_variants(text: str, require_grams: str = '') -> list[tuple[str, str]]:
-#     ''' Get all variants of a parse.
-#     ::returns:: string of comma separated grammar tags or empty string '''
-
-
 def generate_lexeme(text_normal: str) -> list[tuple[str, str]]:
     ''' Get all inflected forms belonging to same Lexeme. '''
     model = parser.parse(text_normal)

cctext/context.py

@@ -17,8 +17,8 @@ class TermForm(TypedDict):
 def _match_grams(query: Iterable[str], test: Iterable[str]) -> bool:
     ''' Check if grams from test fit query. '''
     for gram in test:
-        if not gram in query:
-            if not gram in WordTag.PARTS_OF_SPEECH:
+        if gram not in query:
+            if gram not in WordTag.PARTS_OF_SPEECH:
                 return False
             for pos in WordTag.PARTS_OF_SPEECH:
                 if pos in query:
@@ -35,7 +35,7 @@ def _search_form(query: Iterable[str], data: Iterable[TermForm]) -> Optional[str
 
 class Entity:
     ''' Represents text entity. '''
-    def __init__(self, alias: str, nominal: str, manual_forms: Optional[Iterable[TermForm]]=None):
+    def __init__(self, alias: str, nominal: str, manual_forms: Optional[Iterable[TermForm]] = None):
         if manual_forms is None:
             self.manual = []
         else:

cctext/resolver.py

@@ -5,7 +5,7 @@ from dataclasses import dataclass
 
 from .rumodel import split_grams
 
-from .conceptapi import inflect_dependant
+from .api import inflect_dependant
 from .context import TermContext
 from .reference import EntityReference, SyntacticReference, parse_reference, Reference
 

cctext/ruparser.py

@@ -1,4 +1,4 @@
-''' Parsing russian language using pymorphy3 library. '''
+''' Parsing russian language based on pymorphy3 library. '''
 from __future__ import annotations
 from typing import Optional
 

cctext/syntax.py

@@ -1,4 +1,4 @@
-''' Russian language syntax incapsulation. '''
+''' Russian language syntax. '''
 from __future__ import annotations
 from enum import Enum, unique
 

requirements.txt

@@ -1,3 +1,2 @@
 pymorphy3
-pymorphy3-dicts-ru
 razdel

scripts/Setup.ps1

@@ -0,0 +1,11 @@
+Set-Location $PSScriptRoot\..
+
+$python = '.\venv\Scripts\python.exe'
+$env = '.\venv'
+if (Test-Path -Path $python -PathType Leaf) {
+    Remove-Item $env -Recurse -Force
+}
+
+& 'python' -m venv .\venv
+& $python -m pip install --upgrade pip
+& $python -m pip install -r requirements-build.txt

scripts/Test.ps1

@@ -1,10 +0,0 @@
-# Run lint
-function RunLinters() {
-  $pylint = "$PSScriptRoot\..\venv\Scripts\pylint.exe"
-  $mypy = "$PSScriptRoot\..\venv\Scripts\mypy.exe"
-
-  & $pylint cctext
-  & $mypy cctext
-}
-
-RunLinters

tests/__init__.py

@@ -2,7 +2,7 @@
 from .t_reference import *
 from .t_ruparser import *
 from .t_syntax import *
-from .t_conceptapi import *
+from .t_api import *
 from .t_rumodel import *
 from .t_context import *
 from .t_resolver import *

tests/t_api.py

@@ -1,4 +1,4 @@
-''' Unit tests: conceptapi. '''
+''' Unit tests: api. '''
 import unittest
 
 import cctext as cc
@@ -9,18 +9,21 @@ class TestConceptAPI(unittest.TestCase):
     def _assert_tags(self, actual: str, expected: str):
         self.assertEqual(set(cc.split_grams(actual)), set(cc.split_grams(expected)))
 
+
     def test_parse(self):
         ''' Test parsing. '''
         self._assert_tags(cc.parse(''), '')
         self._assert_tags(cc.parse('1'), 'NUMB,intg')
         self._assert_tags(cc.parse('слон', require_grams='masc'), 'NOUN,anim,masc,sing,nomn')
 
+
     def test_normalize_word(self):
         ''' Test normalize for single word. '''
         self.assertEqual(cc.normalize(''), '')
         self.assertEqual(cc.normalize('первого'), 'первый')
         self.assertEqual(cc.normalize('диких людей'), 'дикий человек')
 
+
     def test_generate_lexeme(self):
         ''' Test all lexical forms. '''
         self.assertEqual(cc.generate_lexeme(''), [])
@@ -35,6 +38,7 @@ class TestConceptAPI(unittest.TestCase):
         self.assertEqual(forms[0][0], 'молодой человек')
         self._assert_tags(forms[0][1], 'nomn,masc,sing,anim,NOUN')
 
+
     def test_inflect(self):
         ''' Test inflection. '''
         self.assertEqual(cc.inflect('', ''), '')
@@ -44,16 +48,19 @@ class TestConceptAPI(unittest.TestCase):
         self.assertEqual(cc.inflect('слона', 'nomn, plur'), 'слоны')
         self.assertEqual(cc.inflect('шкала оценок', 'loct,plur'), 'шкалах оценок')
 
+
     def test_find_substr(self):
         '''Test substring search'''
         self.assertEqual(cc.find_substr('', ''), (0, 0))
         self.assertEqual(cc.find_substr('сложного красивого слона', 'красивые слоном'), (9, 24))
 
+
     def test_inflect_context(self):
-        '''Test contex inflection'''
+        '''Test context inflection'''
         self.assertEqual(cc.inflect_context('', '', ''), '')
         self.assertEqual(cc.inflect_context('красивый', '', 'чашка'), 'красивая')
 
+
     def test_inflect_substitute(self):
         '''Test substitute inflection'''
         self.assertEqual(cc.inflect_substitute('', ''), '')
@@ -61,6 +68,7 @@ class TestConceptAPI(unittest.TestCase):
         self.assertEqual(cc.inflect_substitute('слон', ''), 'слон')
         self.assertEqual(cc.inflect_substitute('красивый бантик', 'кошкой'), 'красивым бантиком')
 
+
     def test_inflect_dependant(self):
         ''' Test coordination inflection. '''
         self.assertEqual(cc.inflect_dependant('', ''), '')
@@ -69,6 +77,7 @@ class TestConceptAPI(unittest.TestCase):
         self.assertEqual(cc.inflect_dependant('общий', 'мать'), 'общая')
         self.assertEqual(cc.inflect_dependant('синий', 'слонов'), 'синих')
 
+
     def test_match_all_morpho(self):
         ''' Test extracting matching morpho. '''
         self.assertEqual(cc.match_all_morpho('', ''), [])

tests/t_context.py

@@ -1,7 +1,8 @@
 ''' Unit tests: context. '''
 import unittest
 
-from cctext.context import Entity, TermContext
+from cctext.context import Entity
+
 
 class TestEntity(unittest.TestCase):
     '''Test Entity termform access.'''
@@ -9,24 +10,27 @@ class TestEntity(unittest.TestCase):
         self.alias = 'X1'
         self.nominal = 'человек'
         self.text1 = 'test1'
-        self.form1 = ['sing','datv']
+        self.form1 = ['sing', 'datv']
         self.entity = Entity(self.alias, self.nominal, [{'text': self.text1, 'grams': self.form1}])
 
+
     def test_attributes(self):
         self.assertEqual(self.entity.alias, self.alias)
         self.assertEqual(self.entity.get_nominal(), self.nominal)
         self.assertEqual(self.entity.manual, [{'text': self.text1, 'grams': self.form1}])
 
+
     def test_get_form(self):
         self.assertEqual(self.entity.get_form([]), self.nominal)
         self.assertEqual(self.entity.get_form(self.form1), self.text1)
         self.assertEqual(self.entity.get_form(['invalid tags']), '!Неизвестная граммема: invalid tags!')
         self.assertEqual(self.entity.get_form(['plur']), 'люди')
 
+
     def test_set_nominal(self):
-        new_nomial = 'TEST'
+        new_nominal = 'TEST'
         self.assertEqual(self.entity.get_form(['plur']), 'люди')
-        self.entity.set_nominal(new_nomial)
-        self.assertEqual(self.entity.get_nominal(), new_nomial)
-        self.assertEqual(self.entity.get_form(['plur']), new_nomial)
+        self.entity.set_nominal(new_nominal)
+        self.assertEqual(self.entity.get_nominal(), new_nominal)
+        self.assertEqual(self.entity.get_form(['plur']), new_nominal)
         self.assertEqual(self.entity.manual, [])

tests/t_reference.py

@@ -3,21 +3,25 @@ import unittest
 
 from cctext import EntityReference, ReferenceType, SyntacticReference, parse_reference
 
+
 class TestReferences(unittest.TestCase):
     ''' Test class for references. '''
 
+
     def test_EntityReference(self):
-        ''' Testing EntityRefence basics. '''
+        ''' Testing EntityReference basics. '''
         ref = EntityReference('X1', 'sing,nomn')
         self.assertEqual(ref.get_type(), ReferenceType.entity)
         self.assertEqual(ref.to_text(), '@{X1|sing,nomn}')
 
+
     def test_SyntacticReference(self):
         ''' Testing SyntacticReference basics. '''
         ref = SyntacticReference(-1, 'черный')
         self.assertEqual(ref.get_type(), ReferenceType.syntactic)
         self.assertEqual(ref.to_text(), '@{-1|черный}')
 
+
     def test_parse_reference_invalid(self):
         ''' Testing parsing reference invalid input. '''
         self.assertIsNone(parse_reference(''))
@@ -31,6 +35,7 @@ class TestReferences(unittest.TestCase):
         self.assertIsNone(parse_reference('@{1| }'))
         self.assertIsNone(parse_reference('@{0|черный}'))
 
+
     def test_parse_reference(self):
         ''' Testing parsing reference text. '''
         ref = parse_reference('@{1| черный }')

tests/t_resolver.py

@@ -28,24 +28,52 @@ class TestResolver(unittest.TestCase):
         self.context['X2'] = Entity('X2', '')
         self.resolver = Resolver(self.context)
 
+
     def test_resolve_entity(self):
-        self.assertEqual(resolve_entity(EntityReference('X1', ''), self.context), 'человек')
-        self.assertEqual(resolve_entity(EntityReference('X1', 'plur'), self.context), 'люди')
-        self.assertEqual(resolve_entity(EntityReference('X2', ''), self.context), '!Отсутствует термин: X2!')
-        self.assertEqual(resolve_entity(EntityReference('X1', 'invalid'), self.context), '!Неизвестная граммема: invalid!')
-        self.assertEqual(resolve_entity(EntityReference('X123', 'plur'), self.context), '!Неизвестная сущность: X123!')
+        ref = EntityReference('X1', '')
+        self.assertEqual(resolve_entity(ref, self.context), 'человек')
+
+        ref = EntityReference('X1', 'plur')
+        self.assertEqual(resolve_entity(ref, self.context), 'люди')
+
+        ref = EntityReference('X2', '')
+        self.assertEqual(resolve_entity(ref, self.context), '!Отсутствует термин: X2!')
+
+        ref = EntityReference('X1', 'invalid')
+        self.assertEqual(resolve_entity(ref, self.context), '!Неизвестная граммема: invalid!')
+
+        ref = EntityReference('X123', 'plur')
+        self.assertEqual(resolve_entity(ref, self.context), '!Неизвестная сущность: X123!')
+
 
     def test_resolve_syntactic(self):
         ref = ResolvedReference(ref=EntityReference('X1', 'sing,datv'), resolved='человеку')
         refs_list = [ref, ref, ref, ref]
-        self.assertEqual(resolve_syntactic(SyntacticReference(text='умный', referral_offset=-1), 0, refs_list), '!Некорректное смещение: -1!')
-        self.assertEqual(resolve_syntactic(SyntacticReference(text='умный', referral_offset=1), 3, refs_list), '!Некорректное смещение: 1!')
-        self.assertEqual(resolve_syntactic(SyntacticReference(text='умный', referral_offset=1), 0, refs_list), 'умному')
-        self.assertEqual(resolve_syntactic(SyntacticReference(text='умный', referral_offset=2), 0, refs_list), 'умному')
-        self.assertEqual(resolve_syntactic(SyntacticReference(text='умный', referral_offset=3), 0, refs_list), 'умному')
-        self.assertEqual(resolve_syntactic(SyntacticReference(text='умный', referral_offset=-1), 3, refs_list), 'умному')
-        self.assertEqual(resolve_syntactic(SyntacticReference(text='умный', referral_offset=-2), 3, refs_list), 'умному')
-        self.assertEqual(resolve_syntactic(SyntacticReference(text='умный', referral_offset=-3), 3, refs_list), 'умному')
+
+        ref = SyntacticReference(text='умный', referral_offset=-1)
+        self.assertEqual(resolve_syntactic(ref, 0, refs_list), '!Некорректное смещение: -1!')
+
+        ref = SyntacticReference(text='умный', referral_offset=1)
+        self.assertEqual(resolve_syntactic(ref, 3, refs_list), '!Некорректное смещение: 1!')
+
+        ref = SyntacticReference(text='умный', referral_offset=1)
+        self.assertEqual(resolve_syntactic(ref, 0, refs_list), 'умному')
+
+        ref = SyntacticReference(text='умный', referral_offset=2)
+        self.assertEqual(resolve_syntactic(ref, 0, refs_list), 'умному')
+
+        ref = SyntacticReference(text='умный', referral_offset=3)
+        self.assertEqual(resolve_syntactic(ref, 0, refs_list), 'умному')
+
+        ref = SyntacticReference(text='умный', referral_offset=-1)
+        self.assertEqual(resolve_syntactic(ref, 3, refs_list), 'умному')
+
+        ref = SyntacticReference(text='умный', referral_offset=-2)
+        self.assertEqual(resolve_syntactic(ref, 3, refs_list), 'умному')
+
+        ref = SyntacticReference(text='умный', referral_offset=-3)
+        self.assertEqual(resolve_syntactic(ref, 3, refs_list), 'умному')
+
 
     def test_resolve_invalid(self):
         self.assertEqual(self.resolver.resolve(''), '')
@@ -57,27 +85,33 @@ class TestResolver(unittest.TestCase):
         self.assertEqual(self.resolver.resolve('simple @{unparsable ref} text'), 'simple @{unparsable ref} text')
         self.assertEqual(len(self.resolver.refs), 0)
 
+
     def test_resolve_single(self):
-        self.assertEqual(self.resolver.resolve('просто @{-1|умный} текст'), 'просто !Некорректное смещение: -1! текст')
+        resolved = self.resolver.resolve('просто @{-1|умный} текст')
+        self.assertEqual(resolved, 'просто !Некорректное смещение: -1! текст')
         self.assertEqual(len(self.resolver.refs), 1)
         self.assertEqual(self.resolver.refs[0].pos_input, Position(7, 18))
         self.assertEqual(self.resolver.refs[0].pos_output, Position(7, 34))
 
-        self.assertEqual(self.resolver.resolve('просто @{X123|sing,nomn} текст'), 'просто !Неизвестная сущность: X123! текст')
+        resolved = self.resolver.resolve('просто @{X123|sing,nomn} текст')
+        self.assertEqual(resolved, 'просто !Неизвестная сущность: X123! текст')
         self.assertEqual(len(self.resolver.refs), 1)
         self.assertEqual(self.resolver.refs[0].pos_input, Position(7, 24))
         self.assertEqual(self.resolver.refs[0].pos_output, Position(7, 35))
 
-        self.assertEqual(self.resolver.resolve('@{X1|sing,nomn}'), 'человек')
+        resolved = self.resolver.resolve('@{X1|sing,nomn}')
+        self.assertEqual(resolved, 'человек')
         self.assertEqual(len(self.resolver.refs), 1)
         self.assertEqual(self.resolver.refs[0].pos_input, Position(0, 15))
         self.assertEqual(self.resolver.refs[0].pos_output, Position(0, 7))
 
-        self.assertEqual(self.resolver.resolve('просто @{X1|sing,nomn} текст'), 'просто человек текст')
+        resolved = self.resolver.resolve('просто @{X1|sing,nomn} текст')
+        self.assertEqual(resolved, 'просто человек текст')
         self.assertEqual(len(self.resolver.refs), 1)
         self.assertEqual(self.resolver.refs[0].pos_input, Position(7, 22))
         self.assertEqual(self.resolver.refs[0].pos_output, Position(7, 14))
 
+
     def test_resolve_multiple(self):
         input = '@{X1|sing,datv} @{-1|умный} @{X1|plur} завидуют'
         self.assertEqual(self.resolver.resolve(input), 'человеку умному люди завидуют')
@@ -89,6 +123,7 @@ class TestResolver(unittest.TestCase):
         self.assertEqual(self.resolver.refs[2].pos_input, Position(28, 38))
         self.assertEqual(self.resolver.refs[2].pos_output, Position(16, 20))
 
+
     def test_resolve_manual_forms(self):
         self.context['X1'] = Entity(
             alias='X1',

tests/t_rumodel.py

@@ -10,9 +10,9 @@ class TestTags(unittest.TestCase):
     def test_split_tags(self):
         self.assertEqual(split_grams(''), [])
         self.assertEqual(split_grams('NOUN'), ['NOUN'])
-        self.assertEqual(split_grams('NOUN,plur,sing'), ['NOUN','plur','sing'])
+        self.assertEqual(split_grams('NOUN,plur,sing'), ['NOUN', 'plur', 'sing'])
 
     def test_combine_tags(self):
         self.assertEqual(combine_grams([]), '')
         self.assertEqual(combine_grams(['NOUN']), 'NOUN')
-        self.assertEqual(combine_grams(['NOUN','plur','sing']), 'NOUN,plur,sing')
+        self.assertEqual(combine_grams(['NOUN', 'plur', 'sing']), 'NOUN,plur,sing')

tests/t_ruparser.py

@@ -7,6 +7,7 @@ from cctext import PhraseParser
 parser = PhraseParser()
 
 
+# cSpell:disable
 class TestRuParser(unittest.TestCase):
     ''' Test class for russian parsing. '''
 
@@ -199,7 +200,7 @@ class TestRuParser(unittest.TestCase):
         self._assert_inflect('три', ['loct'], 'трёх')
 
     def test_inflect_adjf(self):
-        ''' Test inflection for single adjectif. '''
+        ''' Test inflection for single adjective. '''
         self._assert_inflect('хороший', ['nomn'], 'хороший')
         self._assert_inflect('хороший', ['gent'], 'хорошего')
         self._assert_inflect('хороший', ['datv'], 'хорошему')
@@ -317,8 +318,8 @@ class TestRuParser(unittest.TestCase):
 
         # self._assert_inflect('реципиенту воздействия', ['nomn'], 'реципиент воздействия')
 
-    def test_inflect_complex_mainword(self):
-        ''' Test inflection of mainword conmprised of multiple words. '''
+    def test_inflect_complex_main(self):
+        ''' Test inflection of main word comprised of multiple words. '''
         # Do not parse complex main words
         self._assert_inflect('слона и кота', ['nomn'], 'слон и кота')
         self._assert_inflect('сказал и поехал', ['INFN'], 'сказать и поехал')
@@ -440,6 +441,7 @@ class TestRuParser(unittest.TestCase):
         self.assertEqual(parser.find_substr('сложного слона', 'слоном'), (9, 14))
         self.assertEqual(parser.find_substr('сложного красивого слона', 'красивые слоном'), (9, 24))
         self.assertEqual(parser.find_substr('человек', 'люди'), (0, 7))
+# cSpell:enable
 
 
 if __name__ == '__main__':