use black

Author: filyp

.flake8

@@ -23,11 +23,11 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install flake8 pytest
+        pip install black pytest
         if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-    - name: Lint with flake8
+    - name: Autoformat with black
       run: |
-        flake8
+        black .
     - name: Test with pytest
       run: |
         pytest -s

.github/workflows/python-app.yml

@@ -20,20 +20,15 @@ repos:
       - id: check-merge-conflict
       - id: check-yaml
       - id: debug-statements
-      - id: end-of-file-fixer
-      - id: mixed-line-ending
-        files: \.(py|md)$
-        args: [--fix=lf]
       - id: requirements-txt-fixer
-      - id: trailing-whitespace
 
   - repo: https://github.com/asottile/pyupgrade
     rev: v2.7.2
     hooks:
       - id: pyupgrade
         args: [--py36-plus]
 
-  - repo: https://gitlab.com/pycqa/flake8
-    rev: 3.8.4
-    hooks:
-      - id: flake8
+# -   repo: https://github.com/ambv/black
+#     rev: stable
+#     hooks:
+#     - id: black

.pre-commit-config.yaml

@@ -1,10 +1,12 @@
 # All contributions
-Keep the code clean with `flake8`. Use `pre-commit` to ensure the checks are executed automatically upon commit. To set up `pre-commit`:
+Use `pre-commit` to ensure the checks are executed automatically upon commit. To set up `pre-commit`:
 ```
 pip install pre-commit
 pre-commit install
 ```
 
+Code style: `black`
+
 # When changing autocorrection logic
 Run this command before and after changes, and paste the output in the comments:
 ```

CONTRIBUTING.md

@@ -3,6 +3,7 @@
 [![Downloads](https://pepy.tech/badge/autocorrect?label=PyPI%20downloads)](https://pepy.tech/project/autocorrect)
 [![Average time to resolve an issue](http://isitmaintained.com/badge/resolution/fsondej/autocorrect.svg)](http://isitmaintained.com/project/fsondej/autocorrect "Average time to resolve an issue")
 [![Percentage of issues still open](http://isitmaintained.com/badge/open/fsondej/autocorrect.svg)](http://isitmaintained.com/project/fsondej/autocorrect "Percentage of issues still open")
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
 Spelling corrector in python. Currently supports English, Polish, Turkish, Russian, Ukrainian, Czech, Portuguese and Spanish, but you can easily add new languages.
 

README.md

@@ -10,42 +10,44 @@
 from autocorrect.constants import word_regexes, urls
 from autocorrect.typos import Word
 
-
 PATH = os.path.abspath(os.path.dirname(__file__))
 
 
 # credit: https://stackoverflow.com/questions/43370284
 class ProgressBar:
     def __init__(self):
         self.old_percent = 0
-        print('_' * 50)
+        print("_" * 50)
 
     def download_progress_hook(self, count, blockSize, totalSize):
         percent = int(count * blockSize * 100 / totalSize)
         if percent >= 2 + self.old_percent:
             self.old_percent = percent
             # print(percent, '%')
-            print('>', end='')
+            print(">", end="")
             sys.stdout.flush()
         if percent == 100:
-            print('\ndone!')
+            print("\ndone!")
 
 
-def load_from_tar(lang, file_name='word_count.json'):
+def load_from_tar(lang, file_name="word_count.json"):
     archive_name = os.path.join(PATH, f"data/{lang}.tar.gz")
 
     if lang not in word_regexes:
-        supported_langs = ', '.join(word_regexes.keys())
+        supported_langs = ", ".join(word_regexes.keys())
         raise NotImplementedError(
-            textwrap.dedent(f"""
+            textwrap.dedent(
+                f"""
             language '{lang}' not supported
             supported languages: {supported_langs}
             you can easily add new languages by following instructions at
             https://github.com/fsondej/autocorrect/tree/master#adding-new-languages
-            """))
+            """
+            )
+        )
 
     if not os.path.isfile(archive_name):
-        print('dictionary for this language not found, downloading...')
+        print("dictionary for this language not found, downloading...")
         for url in urls[lang]:
             progress = ProgressBar()
             try:
@@ -57,50 +59,49 @@ def load_from_tar(lang, file_name='word_count.json'):
                 error_message = str(ex)
         if error_message is not None:
             raise ConnectionError(
-                error_message +
-                '\nFix your network connection, or manually download \n{}'
-                '\nand put it in \nPATH_TO_REPO/autocorrect/data/'.format(url))
+                error_message
+                + "\nFix your network connection, or manually download \n{}"
+                "\nand put it in \nPATH_TO_REPO/autocorrect/data/".format(url)
+            )
 
-    with closing(tarfile.open(archive_name, 'r:gz')) as tarf:
+    with closing(tarfile.open(archive_name, "r:gz")) as tarf:
         with closing(tarf.extractfile(file_name)) as file:
             return json.load(file)
 
 
 class Speller:
-    def __init__(self, lang='en', threshold=0, nlp_data=None, fast=False):
+    def __init__(self, lang="en", threshold=0, nlp_data=None, fast=False):
         self.lang = lang
         self.threshold = threshold
         self.nlp_data = load_from_tar(lang) if nlp_data is None else nlp_data
         self.fast = fast
 
         if threshold > 0:
             # print(f'Original number of words: {len(self.nlp_data)}')
-            self.nlp_data = {k: v for k, v in self.nlp_data.items()
-                             if v >= threshold}
+            self.nlp_data = {k: v for k, v in self.nlp_data.items() if v >= threshold}
             # print(f'After applying threshold: {len(self.nlp_data)}')
 
     def existing(self, words):
         """{'the', 'teh'} => {'the'}"""
-        return {word for word in words
-                if word in self.nlp_data}
+        return {word for word in words if word in self.nlp_data}
 
     def get_candidates(self, word):
         w = Word(word, self.lang)
         if self.fast:
-            candidates = (self.existing([word]) or
-                          self.existing(w.typos()) or
-                          [word])
+            candidates = self.existing([word]) or self.existing(w.typos()) or [word]
         else:
-            candidates = (self.existing([word]) or
-                          self.existing(w.typos()) or
-                          self.existing(w.double_typos()) or
-                          [word])
+            candidates = (
+                self.existing([word])
+                or self.existing(w.typos())
+                or self.existing(w.double_typos())
+                or [word]
+            )
         return [(self.nlp_data.get(c, 0), c) for c in candidates]
 
     def autocorrect_word(self, word):
         """most likely correction for everything up to a double typo"""
-        if word == '':
-            return ''
+        if word == "":
+            return ""
 
         candidates = self.get_candidates(word)
 
@@ -116,9 +117,11 @@ def autocorrect_word(self, word):
         return best_word
 
     def autocorrect_sentence(self, sentence):
-        return re.sub(word_regexes[self.lang],
-                      lambda match: self.autocorrect_word(match.group(0)),
-                      sentence)
+        return re.sub(
+            word_regexes[self.lang],
+            lambda match: self.autocorrect_word(match.group(0)),
+            sentence,
+        )
 
     __call__ = autocorrect_sentence
 
@@ -129,8 +132,10 @@ def __init__(self):
         self.speller = None
 
     def __call__(self, sentence):
-        print('autocorrect.spell is deprecated, \
-            use autocorrect.Speller instead')
+        print(
+            "autocorrect.spell is deprecated, \
+            use autocorrect.Speller instead"
+        )
         if self.speller is None:
             self.speller = Speller()
         return self.speller(sentence)

autocorrect/__init__.py

@@ -1,52 +1,55 @@
 word_regexes = {
-    'en': r'[A-Za-z]+',
-    'pl': r'[A-Za-zęĘóÓąĄśŚłŁżŻźŹćĆńŃ]+',
-    'ru': r'[АаБбВвГгДдЕеЁёЖжЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЪъЫыЬьЭэЮюЯя]+',
-    'uk': r'[АаБбВвГ㥴ДдЕеЄєЖжЗзИиІіЇїЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЬЮюЯя]+',
-    'tr': r'[a-zA-ZçÇğĞüÜöÖşŞıİ]+',
-    'es': r'[A-Za-zÁáÉéÍíÓóÚúÜüÑñ]+',
-    'pt': r'[a-zA-ZãáàâçéêíõóôúüÃÁÀÂÇÉÊÍÕÓÔÚÜ]+',
-    'cs': r'[AÁBCČDĎEÉĚFGH(Ch)IÍJKLMNŇOÓPQRŘSŠTŤUÚŮVWXYÝZŽaábcčdďeéěfgh(ch)iíjklmnňoópqrřsštťuúůvwxyýzž]+',
+    "en": r"[A-Za-z]+",
+    "pl": r"[A-Za-zęĘóÓąĄśŚłŁżŻźŹćĆńŃ]+",
+    "ru": r"[АаБбВвГгДдЕеЁёЖжЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЪъЫыЬьЭэЮюЯя]+",
+    "uk": r"[АаБбВвГ㥴ДдЕеЄєЖжЗзИиІіЇїЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЬЮюЯя]+",
+    "tr": r"[a-zA-ZçÇğĞüÜöÖşŞıİ]+",
+    "es": r"[A-Za-zÁáÉéÍíÓóÚúÜüÑñ]+",
+    "pt": r"[a-zA-ZãáàâçéêíõóôúüÃÁÀÂÇÉÊÍÕÓÔÚÜ]+",
+    "cs": r"[AÁBCČDĎEÉĚFGH(Ch)IÍJKLMNŇOÓPQRŘSŠTŤUÚŮVWXYÝZŽaábcčdďeéěfgh(ch)iíjklmnňoópqrřsštťuúůvwxyýzž]+",
 }
 
-
 alphabets = {
-    'en': 'abcdefghijklmnopqrstuvwxyz',
-    'pl': 'abcdefghijklmnopqrstuvwxyzęóąśłżźćń',
-    'ru': 'шиюынжсяплзухтвкйеобмцьёгдщэарчфъ',
-    'uk': 'фагксщроємшплуьцнжхїйювязтибґідеч',
-    'tr': 'abcçdefgğhıijklmnoöprsştuüvyzqwxÇĞİÜÖ',
-    'es': 'abcdefghijklmnopqrstuvwxyzáéíóúüñ',
-    'pt': 'abcdefghijklmnopqrstuvwxyzãáàâçéêíõóôúü',
-    'cs': 'aábcčdďeéěfgh(ch)iíjklmnňoópqrřsštťuúůvwxyýzž',
+    "en": "abcdefghijklmnopqrstuvwxyz",
+    "pl": "abcdefghijklmnopqrstuvwxyzęóąśłżźćń",
+    "ru": "шиюынжсяплзухтвкйеобмцьёгдщэарчфъ",
+    "uk": "фагксщроємшплуьцнжхїйювязтибґідеч",
+    "tr": "abcçdefgğhıijklmnoöprsştuüvyzqwxÇĞİÜÖ",
+    "es": "abcdefghijklmnopqrstuvwxyzáéíóúüñ",
+    "pt": "abcdefghijklmnopqrstuvwxyzãáàâçéêíõóôúü",
+    "cs": "aábcčdďeéěfgh(ch)iíjklmnňoópqrřsštťuúůvwxyýzž",
 }
 
 urls = {
-    'en': [
-        'https://dl.dropboxusercontent.com/s/grxjmtw4db814g1/en.tar.gz?dl=0'],
-    'pl': [
-        'https://dl.dropboxusercontent.com/s/40orabi1l3dfqpp/pl.tar.gz?dl=0'],
-    'ru': [
-        'https://dl.dropboxusercontent.com/s/mpas7xqn8yl3wej/ru.tar.gz?dl=0',
-        'https://dl.dropboxusercontent.com/s/6tzfxy34xx34mm7/ru.tar.gz?dl=0',
-        'https://siasky.net/AABaSQMcxgHp7LJ-YHs1IWqn4uxa8q17fGET-IaNbGgSnQ'],
-    'uk': [
-        'https://dl.dropboxusercontent.com/s/s64ot0l4lj3a0ec/uk.tar.gz?dl=0',
-        'https://dl.dropboxusercontent.com/s/b76p4sc1lld96lw/uk.tar.gz?dl=0',
-        'https://siasky.net/AADdpauxvMwjieU3n5qaMbjAeCYR9T-vK6L1OEXRTOgr6g'],
-    'tr': [
-        'https://dl.dropboxusercontent.com/s/mj2d3t158ucwhwx/tr.tar.gz?dl=0',
-        'https://dl.dropboxusercontent.com/s/1wy01nq5fpq8iay/tr.tar.gz?dl=0',
-        'https://siasky.net/AABWRhJ-7NVoo2vaTgSs6HNhwGmFgCgYzg0q_0d-eqgCeA'],
-    'es': [
-        'https://dl.dropboxusercontent.com/s/jh0212sou1qbs7t/es.tar.gz?dl=0',
-        'https://dl.dropboxusercontent.com/s/k6g5vj3x0rx7mjz/es.tar.gz?dl=0',
-        'https://siasky.net/_ArsYbh-vpFWosvzEuQQZnPrOt2XggjDQfkvDwTFu5MQoA'],
-    'cs': [
-        'https://dl.dropboxusercontent.com/s/8ptuuh8kcr3kufy/cs.tar.gz?dl=0',
-        'https://dl.dropboxusercontent.com/s/369wplqb0w2ax21/cs.tar.gz?dl=0',
-        'https://siasky.net/AAC6lW1ShlSRUeiFnr4_2bmw6sznlZsWvmhDhyQy_-g2wA'],
-    'pt': [
-        'https://dl.dropboxusercontent.com/s/6xnko882tsjgeaw/pt.tar.gz?dl=0',
-        'https://siasky.net/PAOmY66v3ggXpqNtbHQU_hb7ARNOL_Lv3LcTwFMMWmdzVw'],
+    "en": ["https://dl.dropboxusercontent.com/s/grxjmtw4db814g1/en.tar.gz?dl=0"],
+    "pl": ["https://dl.dropboxusercontent.com/s/40orabi1l3dfqpp/pl.tar.gz?dl=0"],
+    "ru": [
+        "https://dl.dropboxusercontent.com/s/mpas7xqn8yl3wej/ru.tar.gz?dl=0",
+        "https://dl.dropboxusercontent.com/s/6tzfxy34xx34mm7/ru.tar.gz?dl=0",
+        "https://siasky.net/AABaSQMcxgHp7LJ-YHs1IWqn4uxa8q17fGET-IaNbGgSnQ",
+    ],
+    "uk": [
+        "https://dl.dropboxusercontent.com/s/s64ot0l4lj3a0ec/uk.tar.gz?dl=0",
+        "https://dl.dropboxusercontent.com/s/b76p4sc1lld96lw/uk.tar.gz?dl=0",
+        "https://siasky.net/AADdpauxvMwjieU3n5qaMbjAeCYR9T-vK6L1OEXRTOgr6g",
+    ],
+    "tr": [
+        "https://dl.dropboxusercontent.com/s/mj2d3t158ucwhwx/tr.tar.gz?dl=0",
+        "https://dl.dropboxusercontent.com/s/1wy01nq5fpq8iay/tr.tar.gz?dl=0",
+        "https://siasky.net/AABWRhJ-7NVoo2vaTgSs6HNhwGmFgCgYzg0q_0d-eqgCeA",
+    ],
+    "es": [
+        "https://dl.dropboxusercontent.com/s/jh0212sou1qbs7t/es.tar.gz?dl=0",
+        "https://dl.dropboxusercontent.com/s/k6g5vj3x0rx7mjz/es.tar.gz?dl=0",
+        "https://siasky.net/_ArsYbh-vpFWosvzEuQQZnPrOt2XggjDQfkvDwTFu5MQoA",
+    ],
+    "cs": [
+        "https://dl.dropboxusercontent.com/s/8ptuuh8kcr3kufy/cs.tar.gz?dl=0",
+        "https://dl.dropboxusercontent.com/s/369wplqb0w2ax21/cs.tar.gz?dl=0",
+        "https://siasky.net/AAC6lW1ShlSRUeiFnr4_2bmw6sznlZsWvmhDhyQy_-g2wA",
+    ],
+    "pt": [
+        "https://dl.dropboxusercontent.com/s/6xnko882tsjgeaw/pt.tar.gz?dl=0",
+        "https://siasky.net/PAOmY66v3ggXpqNtbHQU_hb7ARNOL_Lv3LcTwFMMWmdzVw",
+    ],
 }

autocorrect/constants.py

@@ -21,9 +21,10 @@
 
 class Word:
     """container for word-based methods"""
-    __slots__ = ['slices', 'word', 'alphabet']  # optimization
 
-    def __init__(self, word, lang='en'):
+    __slots__ = ["slices", "word", "alphabet"]  # optimization
+
+    def __init__(self, word, lang="en"):
         """
         Generate slices to assist with typo
         definitions.
@@ -33,41 +34,38 @@ def __init__(self, word, lang='en'):
 
         """
         slice_range = range(len(word) + 1)
-        self.slices = tuple((word[:i], word[i:])
-                            for i in slice_range)
+        self.slices = tuple((word[:i], word[i:]) for i in slice_range)
         self.word = word
         self.alphabet = alphabets[lang]
 
     def _deletes(self):
         """th"""
         for a, b in self.slices[:-1]:
-            yield ''.join((a, b[1:]))
+            yield "".join((a, b[1:]))
 
     def _transposes(self):
         """teh"""
         for a, b in self.slices[:-2]:
-            yield ''.join((a, b[1], b[0], b[2:]))
+            yield "".join((a, b[1], b[0], b[2:]))
 
     def _replaces(self):
         """tge"""
         for a, b in self.slices[:-1]:
             for c in self.alphabet:
-                yield ''.join((a, c, b[1:]))
+                yield "".join((a, c, b[1:]))
 
     def _inserts(self):
         """thwe"""
         for a, b in self.slices:
             for c in self.alphabet:
-                yield ''.join((a, c, b))
+                yield "".join((a, c, b))
 
     def typos(self):
         """letter combinations one typo away from word"""
-        return chain(self._deletes(),
-                     self._transposes(),
-                     self._replaces(),
-                     self._inserts())
+        return chain(
+            self._deletes(), self._transposes(), self._replaces(), self._inserts()
+        )
 
     def double_typos(self):
         """letter combinations two typos away from word"""
-        return chain.from_iterable(
-            Word(e1).typos() for e1 in self.typos())
+        return chain.from_iterable(Word(e1).typos() for e1 in self.typos())