fix: code spelling

Enable codespell and fix found typos.

Author: nijel

.pre-commit-config.yaml

@@ -62,6 +62,12 @@ repos:
   hooks:
   - id: reuse
 
+- repo: https://github.com/codespell-project/codespell
+  rev: v2.4.1
+  hooks:
+  - id: codespell
+    additional_dependencies:
+    - tomli
 - repo: https://github.com/rhysd/actionlint
   rev: v1.7.7
   hooks:

pyproject.toml

@@ -95,6 +95,10 @@ ignore-bad-ideas = [
   "modules/gettext/gettext-tools/tests/*.mo"
 ]
 
+[tool.codespell]
+builtin = "clear,rare,informal,usage"
+skip = '*.po,*.pot,*.csv,weblate_language_data/aliases.py,weblate_language_data/population.py,weblate_language_data/plurals.py,weblate_language_data/language_codes.py,weblate_language_data/languages.py,weblate_language_data/check_languages.py,weblate_language_data/plural_tags.py,PLURALS_DIFF.md,weblate_language_data/case_insensitive.py,weblate_language_data/country_codes.py'
+
 [tool.isort]
 profile = "black"
 

scripts/export-cldr-orientation

@@ -35,7 +35,7 @@ for layout_file in LAYOUTDIR.glob("*/layout.json"):
         if character_order == "right-to-left":
             RTL_CODES.add(code)
         elif character_order != "left-to-right":
-            print(f"Uknown order for {code}: {character_order})")
+            print(f"Unknown order for {code}: {character_order})")
 
 with open("rtl.csv", "w") as handle:
     handle.write("code,\n")

scripts/export-iso-aliases

@@ -71,7 +71,7 @@ with open(ALIASES) as handle:
             continue
         replacement = alias["_replacement"]
         if code in LANGUAGE_CODES:
-            print(f"Exising language {code}: {alias}")
+            print(f"Existing language {code}: {alias}")
             continue
         if replacement not in LANGUAGE_CODES:
             print(f"Missing target {code}: {alias}")

scripts/generate-language-data

@@ -150,7 +150,7 @@ with open("rtl.csv") as csvfile:
     RTLS = list(reader)
     RTL_CODES = {lang[0] for lang in RTLS}
 
-# Read case insentive
+# Read case-insensitive
 with open("case-insensitive.csv") as csvfile:
     reader = csv.reader(csvfile, delimiter=",")
     next(reader)
@@ -201,7 +201,7 @@ with open("weblate_language_data/aliases.py", "w") as output:
     output.write("}\n")
 with open("weblate_language_data/countries.py", "w") as output:
     output.write(HEADER)
-    output.write("# List of defaul languages, omitting country code should be okay\n")
+    output.write("# List of default languages, omitting country code should be okay\n")
     output.write("DEFAULT_LANGS: tuple[str, ...] = (\n")
     for row in DEFAULT_COUNTRIES:
         output.write(f'    "{escape(row[0])}",\n')
@@ -216,13 +216,13 @@ with open("weblate_language_data/rtl.py", "w") as output:
 
 with open("weblate_language_data/case_insensitive.py", "w") as output:
     output.write(HEADER)
-    output.write("# List of case-insentive languages\n")
+    output.write("# List of case-insensitive languages\n")
     output.write("CASE_INSENSITIVE_LANGS: set[str] = {\n")
     for code in sorted(CASE_INSENSITIVE_CODES):
         output.write(f'    "{code}",\n')
     output.write("}\n")
 
-# Generate same check blacklist
+# Generate same check exception list
 words = set()
 
 
@@ -310,10 +310,10 @@ words.difference_update(
     },
 )
 
-# Write same check blacklist
+# Write same check exclude list
 with open("weblate_language_data/check_languages.py", "w") as output:
     output.write(HEADER)
-    output.write("# Language names to ignore in same check\n")
+    output.write("# Language names to ignore in the same check\n")
     output.write("LANGUAGES: set[str] = {\n")
     for word in sorted(words):
         if len(word) <= 2:  # noqa: PLR2004

scripts/lint

@@ -39,7 +39,7 @@ if missing:
 
 overlap = set(languages.keys()) & set(aliases.keys())
 if overlap:
-    raise ValueError(f"Overlaping languages and aliases: {overlap}")
+    raise ValueError(f"Overlapping languages and aliases: {overlap}")
 
 missing = set(cldr.keys()) - set(languages.keys())
 # Remove aliases (these use lower case)

weblate_language_data/case_insensitive.py

@@ -12,7 +12,7 @@
 """
 # pylint: disable=line-too-long,too-many-lines
 
-# List of case-insentive languages
+# List of case-insensitive languages
 CASE_INSENSITIVE_LANGS: set[str] = {
     "aeb",
     "am",

weblate_language_data/check_languages.py

@@ -12,7 +12,7 @@
 """
 # pylint: disable=line-too-long,too-many-lines
 
-# Language names to ignore in same check
+# Language names to ignore in the same check
 LANGUAGES: set[str] = {
     "aak",
     "aakkâr",

weblate_language_data/countries.py

@@ -12,7 +12,7 @@
 """
 # pylint: disable=line-too-long,too-many-lines
 
-# List of defaul languages, omitting country code should be okay
+# List of default languages, omitting country code should be okay
 DEFAULT_LANGS: tuple[str, ...] = (
     "af_za",
     "am_et",