GHA CI: Switch to pre-commit framework for checking file health

Now users are able to run the same checks on their local development
environment.
https://pre-commit.com/

.github/workflows/check_translation_tag.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python3
+
+# A pre-commit hook for detecting problematic <translation> tags
+# Copyright (C) 2021  Mike Tzou (Chocobo1)
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 2
+# of the License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+#
+# In addition, as a special exception, the copyright holders give permission to
+# link this program with the OpenSSL project's "OpenSSL" library (or with
+# modified versions of it that use the same license as the "OpenSSL" library),
+# and distribute the linked executables. You must obey the GNU General Public
+# License in all respects for all of the code used other than "OpenSSL".  If you
+# modify file(s), you may extend this exception to your version of the file(s),
+# but you are not obligated to do so. If you do not wish to do so, delete this
+# exception statement from your version.
+
+from typing import Optional, Sequence
+import argparse
+import re
+
+def main(argv: Optional[Sequence[str]] = None) -> int:
+    parser = argparse.ArgumentParser()
+    parser.add_argument('filenames', nargs='*', help='Filenames to check')
+    args = parser.parse_args(argv)
+
+    error_msg = ""
+    regex = re.compile(r"\s*</translation>")
+
+    for filename in args.filenames:
+        line_counter = 1
+        error_buffer = ""
+
+        with open(filename) as file:
+            try:
+                for line in file:
+                    if (match := regex.match(line)) is not None:
+                        error_buffer += str(f"Defect file: \"{filename}\"\n"
+                              f"Line: {line_counter}\n"
+                              f"Column span: {match.span()}\n"
+                              f"Part: \"{match.group()}\"\n\n")
+                    line_counter += 1
+
+            except UnicodeDecodeError as error:
+                # not a text file, skip
+                continue
+
+        error_msg += error_buffer
+
+    if len(error_msg) > 0:
+        print(error_msg)
+        return 1
+
+    return 0
+
+if __name__ == '__main__':
+    exit(main())

.github/workflows/ci_file_health.yaml

@@ -11,10 +11,7 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Install tools
-        run: |
+        uses: actions/setup-python@v2
-          sudo apt update
-          sudo apt install zsh
 
       - name: Check files
-        run: |
+        uses: pre-commit/action@v2.0.3
-          ./.github/workflows/file_health.sh

.github/workflows/file_health.sh

@@ -1,85 +0,0 @@
-#!/usr/bin/env zsh
-
-set -o nounset
-
-# Assumption: file names don't contain `:` (for the `cut` invocation).
-# Safe to assume, as such a character in a filename would cause trouble on Windows, a platform we support
-
-# any regression turn this non-zero
-regressions=0
-
-# exclusions (these are just grep extended regular expressions to match against paths relative to the root of the repository)
-exclusions_nonutf8='(.*(7z|gif|ic(ns|o)|png|qm|zip))'
-exclusions_bom='src/base/unicodestrings.h'
-exclusions_tw='(*.ts)|src/webui/www/private/scripts/lib/*'
-exclusions_trailing_newline='configure'
-exclusions_no_lf='(*.ts)|(.*svg)|compile_commands.json|src/webui/www/private/scripts/lib/*'
-
-echo -e "\n*** Detect files not encoded in UTF-8 ***\n"
-
-find . -path ./build -prune -false -o -path ./.git -prune -false -o -type f -exec file --mime {} \; | sort \
-    | grep -v -e "charset=us-ascii" -e "charset=utf-8" | cut -d ":" -f 1 \
-    | grep -E -v -e "${exclusions_nonutf8}" \
-    | tee >(echo -e "--> Files not encoded in UTF-8: found" "$(wc -l < /dev/stdin)" "regression(s)\n") \
-    | xargs -I my_input -0 bash -c 'echo "my_input"; test "$(echo -n "my_input" | wc -l)" -eq 0'
-regressions=$((regressions+$?))
-
-echo -e "\n*** Detect files encoded in UTF-8 with BOM ***\n"
-
-grep --exclude-dir={.git,build} -rIl $'\xEF\xBB\xBF' | sort \
-    | grep -E -v -e "${exclusions_bom}" \
-    | tee >(echo -e "--> Files encoded in UTF-8 with BOM: found" "$(wc -l < /dev/stdin)" "regression(s)\n") \
-    | xargs -I my_input -0 bash -c 'echo "my_input"; test "$(echo -n "my_input" | wc -l)" -eq 0'
-regressions=$((regressions+$?))
-
-echo -e "\n*** Detect usage of CR byte ***\n"
-
-grep --exclude-dir={.git,build} -rIlU $'\x0D' | sort \
-    | tee >(echo -e "--> Usage of CR byte: found" "$(wc -l < /dev/stdin)" "regression(s)\n") \
-    | xargs -I my_input -0 bash -c 'echo "my_input"; test "$(echo -n "my_input" | wc -l)" -eq 0'
-regressions=$((regressions+$?))
-
-echo -e "\n*** Detect trailing whitespace in lines ***\n"
-
-grep --exclude-dir={.git,build} -rIl "[[:blank:]]$" | sort \
-    | grep -E -v -e "${exclusions_tw}" \
-    | tee >(echo -e "--> Trailing whitespace in lines: found" "$(wc -l < /dev/stdin)" "regression(s)\n") \
-    | xargs -I my_input -0 bash -c 'echo "my_input"; test "$(echo -n "my_input" | wc -l)" -eq 0';
-regressions=$((regressions+$?))
-
-echo -e "\n*** Detect too many trailing newlines ***\n"
-
-find . -path ./build -prune -false -o -path ./.git -prune -false -o -type f -exec file --mime {} \; | sort \
-    | grep -e "charset=us-ascii" -e "charset=utf-8" | cut -d ":" -f 1 \
-    | grep -E -v -e "${exclusions_trailing_newline}" \
-    | xargs -L1 -I my_input bash -c 'test "$(tail -q -c2 "my_input" | hexdump -C | grep "0a 0a")" && echo "my_input"' \
-    | tee >(echo -e "--> Too many trailing newlines: found" "$(wc -l < /dev/stdin)" "regression(s)\n") \
-    | xargs -I my_input -0 bash -c 'echo "my_input"; test "$(echo -n "my_input" | wc -l)" -eq 0'
-regressions=$((regressions+$?))
-
-echo -e "\n*** Detect no trailing newline ***\n"
-
-find . -path ./build -prune -false -o -path ./.git -prune -false -o -type f -exec file --mime {} \; | sort \
-    | grep -e "charset=us-ascii" -e "charset=utf-8" |  cut -d ":" -f 1 \
-    | grep -E -v -e "${exclusions_no_lf}" \
-    | xargs -L1 -I my_input bash -c 'test "$(tail -q -c1 "my_input" | hexdump -C | grep "0a")" || echo "my_input"' \
-    | tee >(echo -e "--> No trailing newline: found" "$(wc -l < /dev/stdin)" "regression(s)\n") \
-    | xargs -I my_input -0 bash -c 'echo "my_input"; test "$(echo -n "my_input" | wc -l)" -eq 0'
-regressions=$((regressions+$?))
-
-echo -e "\n*** Detect translation closing tag in new line ***\n"
-
-grep --exclude-dir={.git,build} -nri "^</translation>" | sort \
-    | cut -d ":" -f 1,2 \
-    | tee >(echo -e "--> Translation closing tag in new line: found" "$(wc -l < /dev/stdin)" "regression(s)\n") \
-    | xargs -I my_input -0 bash -c 'echo "my_input"; test "$(echo -n "my_input" | wc -l)" -eq 0'
-regressions=$((regressions+$?))
-
-if [ "$regressions" -ne 0 ]; then
-    regressions=1
-    echo "\nFile health regressions found. Please fix them (or add them as exclusions)."
-else
-    echo "All OK, no file health regressions found."
-fi
-
-exit $regressions;

.pre-commit-config.yaml

@@ -0,0 +1,55 @@
+repos:
+  - repo: local
+    hooks:
+      - id: check-translation-tag
+        name: Check newline characters in <translation> tag
+        entry: .github/workflows/check_translation_tag.py
+        language: script
+        types_or:
+          - ts
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks.git
+    rev: v4.0.1
+    hooks:
+    - id: check-json
+      name: Check JSON files
+
+    - id: check-yaml
+      name: Check YAML files
+
+    - id: fix-byte-order-marker
+      name: Check file encoding (UTF-8 without BOM)
+      exclude: |
+        (?x)^(
+          src/base/unicodestrings.h
+        )$
+
+    - id: mixed-line-ending
+      name: Check line ending character (LF)
+      args: ["--fix=lf"]
+      exclude: |
+        (?x)^(
+          compile_commands.json |
+          src/webui/www/private/scripts/lib/.*
+        )$
+
+    - id: end-of-file-fixer
+      name: Check trailing newlines
+      exclude: |
+        (?x)^(
+          compile_commands.json |
+          configure |
+          src/webui/www/private/scripts/lib/.*
+        )$
+      exclude_types:
+        - svg
+        - ts
+
+    - id: trailing-whitespace
+      name: Check trailing whitespaces
+      exclude: |
+        (?x)^(
+          src/webui/www/private/scripts/lib/.*
+        )$
+      exclude_types:
+        - ts