pylint!

Author: eschluntz

.pylintrc

@@ -337,7 +337,7 @@ indent-after-paren=4
 indent-string='    '
 
 # Maximum number of characters on a single line.
-max-line-length=100
+max-line-length=120
 
 # Maximum number of lines in a module.
 max-module-lines=1000
@@ -429,7 +429,15 @@ disable=raw-checker-failed,
         useless-suppression,
         deprecated-pragma,
         use-symbolic-message-instead,
-        missing-function-docstring
+        missing-function-docstring,
+        fixme,
+        no-else-return,
+        invalid-name,
+        redefined-outer-name,
+        too-many-locals,  # TODO: remove these next 3 after refactoring match_abbrevs_to_phrases
+        too-many-branches,
+        too-many-nested-blocks
+
 
 
 # Enable the message, report, category or checker with the given id(s). You can

find_suggested_phrases.py

@@ -1,4 +1,10 @@
-import json
+#!/usr/bin/env python
+
+"""
+Script to turn a corpus of text into a list of suggested phrases
+and abbreviations.
+"""
+
 import os
 from typing import List, Dict, Optional, Set, Tuple
 from collections import Counter, namedtuple
@@ -67,14 +73,8 @@ def try_plural_of_word(word : str) -> str:
         return word[:-1] + "ies"
     if word[-1] == "f":
         return word[:-1] + "ves"
-    if word[-1] == "o":
-        return word + "es"
-    if word[-1] == "h":
-        return word + "es"
-    if word[-1] == "x":
+    if word[-1] in "ohxz":
         return word + "es"
-    if word[-1] == "z":
-        return word[:-1] + "zes"
     return word + "s"
 
 
@@ -219,7 +219,7 @@ def load_corpus() -> List[str]:
     all_lines = []
     for filename in os.listdir(corpus_path):
         if filename.endswith(".txt"):
-            with open(corpus_path + filename, 'r') as f:
+            with open(corpus_path + filename, 'r', encoding="utf8") as f:
                 all_lines.extend(f.readlines())
     return all_lines
 
@@ -267,7 +267,7 @@ def fix_grammer(text: str) -> str:
 
 def save_shortcuts(shortcuts: Dict[str, str]) -> None:
     """Save the shortcuts to a yaml file"""
-    with open("output/suggested_shortcuts.yaml", 'w') as f:
+    with open("output/suggested_shortcuts.yaml", 'w', encoding="utf8") as f:
         yaml.dump(shortcuts, f, default_flow_style=False)
 
 

generate_autokeys.py

@@ -1,6 +1,13 @@
+#!/usr/bin/env python
+
+"""
+Script to turn the json file of shortcuts.yaml into config files for Autokey
+"""
+
+
 import json
-import yaml
 import os
+import yaml
 
 
 def make_safe_filename_from_string(s : str) -> str:
@@ -21,10 +28,10 @@ def create_autokey_config_for_abbrev(phrase : str, abbrev : str) -> None:
 
     file_extensions = ["py"]  # add . as a word character for any of these abbrevs.
     if abbrev in file_extensions:
-        extra_word_chars = "\."
+        extra_word_chars = r"\."
     else:
         extra_word_chars = ""
-    words_regex = "[\\w\\t'{}\-&\+]".format(extra_word_chars)  # what should not trigger a substitution
+    words_regex = rf"[\w\t'{extra_word_chars}\-&\+]"  # what should not trigger a substitution
 
     result_path = "output/autokey_phrases/"
 
@@ -39,10 +46,10 @@ def create_autokey_config_for_abbrev(phrase : str, abbrev : str) -> None:
 
     abbrevs = [a.strip() for a in abbrev.split(",")]
 
-    with open(result_path + f"{name}.txt", 'w') as f:
+    with open(result_path + f"{name}.txt", 'w', encoding="utf8") as f:
         f.write(phrase)
 
-    with open(result_path + f".{name}.json", 'w') as f:
+    with open(result_path + f".{name}.json", 'w', encoding="utf8") as f:
         config = {
             "usageCount": 0,
             "omitTrigger": False,
@@ -76,7 +83,9 @@ def create_autokey_config_for_abbrev(phrase : str, abbrev : str) -> None:
 
 
 if __name__ == "__main__":
-    shortcuts = yaml.load(open("output/shortcuts.yaml", 'r'), Loader=yaml.FullLoader)
 
-    for phrase, abbrev in shortcuts.items():
-        create_autokey_config_for_abbrev(phrase, abbrev)
+    with open("output/shortcuts.yaml", 'r', encoding="utf8") as file:
+        shortcuts = yaml.load(file, Loader=yaml.FullLoader)
+
+        for phrase, abbrev in shortcuts.items():
+            create_autokey_config_for_abbrev(phrase, abbrev)

parse_slack.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+
 """
 Parses a slack export folder, cleans up the slack messages found for your user
 and then exports them into a file in corpus.
@@ -14,12 +16,12 @@
 def extract_slack_msgs(export_root_path : str, username : str) -> List[str]:
     """extract all text from the users messages as a list of strings"""
     file_strs : List[str] = []
-    for (dirpath, dirnames, filenames) in os.walk(export_root_path):
+    for (dirpath, _, filenames) in os.walk(export_root_path):
         file_strs += [os.path.join(dirpath, file) for file in filenames]
 
     msgs : List[str] = []
     for file_str in file_strs:
-        with open(file_str) as file:
+        with open(file_str, encoding="utf8") as file:
             channel = json.load(file)
 
         for msg in channel:
@@ -55,6 +57,6 @@ def clean_slack_msg(text: str) -> str:
     texts = [clean_slack_msg(m) for m in msgs]
 
     # write each msg as a line to a file
-    with open("data/corpus/slack_msgs.txt", 'w') as f:
+    with open("data/corpus/slack_msgs.txt", 'w', encoding="utf8") as f:
         for text in texts:
             f.write(text + "\n")

preset_abbrevs.py

@@ -1,7 +1,12 @@
+#!/usr/bin/env python
+
+"""
+Abbrevs you definitely want in your set.
+you can set None if you want to pick one automatically
+you're responsible for creating any plurals here
+"""
+
 
-# Abbrevs you definitely want in your set.
-# you can set None if you want to pick one automatically
-# you're responsible for creating any plurals here
 PRESET_ABBREVS = {
     "right now": "rn",
     "ansible": "ans",

run_tests.sh

@@ -4,8 +4,8 @@
 # exit when any command fails
 set -e
 
-# linter
-# pylint $(git ls-files '*.py')
-
 # tests
-pytest --cov
+pytest --cov
+
+# linter
+pylint $(git ls-files '*.py')

test_compress.py

@@ -1,7 +1,13 @@
+#!/usr/bin/env python
 
+"""
+Tests for the compress repo. This is best executed from `run_tests.sh`
+in order to keep parity with what's running in CI.
+"""
+import json
 from typing import Counter
-from preset_abbrevs import BLACKLIST, PRESET_ABBREVS
-from parse_slack import extract_slack_msgs, clean_slack_msg
+import os
+
 from find_suggested_phrases import (
     get_plural,
     get_possible_abbrevs,
@@ -13,8 +19,9 @@
     fix_grammer,
 )
 from generate_autokeys import create_autokey_config_for_abbrev
-import os
-import json
+from parse_slack import extract_slack_msgs, clean_slack_msg
+from preset_abbrevs import BLACKLIST, PRESET_ABBREVS
+
 
 
 def test_presets():
@@ -194,15 +201,15 @@ def test_autokey_configs():
     main_path = result_path + "testbecause.txt"
     config_path = result_path + ".testbecause.json"
 
-    with open(main_path, 'r') as f:
+    with open(main_path, 'r', encoding="utf8") as f:
         out = f.readline()
         assert out == "test_because"
 
-    with open(config_path, 'r') as f:
+    with open(config_path, 'r', encoding="utf8") as f:
         out = json.load(f)
         expected = {'usageCount': 0, 'omitTrigger': False,
             'prompt': False, 'description': 'test_because', 'abbreviation':
-            {'wordChars': "[\\w\\t'\-&\+]", 'abbreviations': ['bc'], 'immediate': False,
+            {'wordChars': r"[\w\t'\-&\+]", 'abbreviations': ['bc'], 'immediate': False,
             'ignoreCase': True, 'backspace': True, 'triggerInside': False},
             'hotkey': {'hotKey': None, 'modifiers': []}, 'modes': [1],
             'showInTrayMenu': False, 'matchCase': True, 'filter':
@@ -216,15 +223,15 @@ def test_autokey_configs():
     main_path = result_path + "testi.txt"
     config_path = result_path + ".testi.json"
 
-    with open(main_path, 'r') as f:
+    with open(main_path, 'r', encoding="utf8") as f:
         out = f.readline()
         assert out == "test_i"
 
-    with open(config_path, 'r') as f:
+    with open(config_path, 'r', encoding="utf8") as f:
         out = json.load(f)
         expected = {'usageCount': 0, 'omitTrigger': False,
             'prompt': False, 'description': 'test_i', 'abbreviation':
-            {'wordChars': "[\\w\\t'\-&\+]", 'abbreviations': ['i'], 'immediate': False,
+            {'wordChars': r"[\w\t'\-&\+]", 'abbreviations': ['i'], 'immediate': False,
             'ignoreCase': True, 'backspace': True, 'triggerInside': False},
             'hotkey': {'hotKey': None, 'modifiers': []}, 'modes': [1],
             'showInTrayMenu': False, 'matchCase': True, 'filter':