1
0
mirror of https://github.com/Stirling-Tools/Stirling-PDF.git synced 2024-11-11 02:10:11 +01:00

Extends the checking of message*.properties (#1781)

This commit is contained in:
Ludy 2024-08-31 15:54:11 +02:00 committed by GitHub
parent 09e963b160
commit a14b78ff91
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 305 additions and 67 deletions

View File

@ -1,5 +1,124 @@
"""
Author: Ludy87
Description: This script processes .properties files for localization checks. It compares translation files in a branch with
a reference file to ensure consistency. The script performs two main checks:
1. Verifies that the number of lines (including comments and empty lines) in the translation files matches the reference file.
2. Ensures that all keys in the translation files are present in the reference file and vice versa.
The script also provides functionality to update the translation files to match the reference file by adding missing keys and
adjusting the format.
Usage:
python script_name.py --reference-file <path_to_reference_file> --branch <branch_name> [--files <list_of_changed_files>]
"""
import copy
import glob
import os import os
import argparse import argparse
import re
def parse_properties_file(file_path):
"""Parses a .properties file and returns a list of objects (including comments, empty lines, and line numbers)."""
properties_list = []
with open(file_path, "r", encoding="utf-8") as file:
for line_number, line in enumerate(file, start=1):
stripped_line = line.strip()
# Empty lines
if not stripped_line:
properties_list.append(
{"line_number": line_number, "type": "empty", "content": ""}
)
continue
# Comments
if stripped_line.startswith("#"):
properties_list.append(
{
"line_number": line_number,
"type": "comment",
"content": stripped_line,
}
)
continue
# Key-value pairs
match = re.match(r"^([^=]+)=(.*)$", line)
if match:
key, value = match.groups()
properties_list.append(
{
"line_number": line_number,
"type": "entry",
"key": key.strip(),
"value": value.strip(),
}
)
return properties_list
def write_json_file(file_path, updated_properties):
updated_lines = {entry["line_number"]: entry for entry in updated_properties}
# Sort by line numbers and retain comments and empty lines
all_lines = sorted(set(updated_lines.keys()))
original_format = []
for line in all_lines:
if line in updated_lines:
entry = updated_lines[line]
else:
entry = None
ref_entry = updated_lines[line]
if ref_entry["type"] in ["comment", "empty"]:
original_format.append(ref_entry)
elif entry is None:
# Add missing entries from the reference file
original_format.append(ref_entry)
elif entry["type"] == "entry":
# Replace entries with those from the current JSON
original_format.append(entry)
# Write back in the original format
with open(file_path, "w", encoding="utf-8") as file:
for entry in original_format:
if entry["type"] == "comment":
file.write(f"{entry['content']}\n")
elif entry["type"] == "empty":
file.write(f"{entry['content']}\n")
elif entry["type"] == "entry":
file.write(f"{entry['key']}={entry['value']}\n")
def update_missing_keys(reference_file, file_list, branch=""):
reference_properties = parse_properties_file(reference_file)
for file_path in file_list:
basename_current_file = os.path.basename(branch + file_path)
if (
basename_current_file == os.path.basename(reference_file)
or not file_path.endswith(".properties")
or not basename_current_file.startswith("messages_")
):
continue
current_properties = parse_properties_file(branch + file_path)
updated_properties = []
for ref_entry in reference_properties:
ref_entry_copy = copy.deepcopy(ref_entry)
for current_entry in current_properties:
if current_entry["type"] == "entry":
if ref_entry_copy["type"] != "entry":
continue
if ref_entry_copy["key"] == current_entry["key"]:
ref_entry_copy["value"] = current_entry["value"]
updated_properties.append(ref_entry_copy)
write_json_file(branch + file_path, updated_properties)
def check_for_missing_keys(reference_file, file_list, branch):
update_missing_keys(reference_file, file_list, branch + "/")
def read_properties(file_path): def read_properties(file_path):
@ -7,86 +126,96 @@ def read_properties(file_path):
return file.read().splitlines() return file.read().splitlines()
def check_difference(reference_file, file_list, branch): def check_for_differences(reference_file, file_list, branch):
reference_branch = reference_file.split("/")[0] reference_branch = reference_file.split("/")[0]
basename_reference_file = os.path.basename(reference_file) basename_reference_file = os.path.basename(reference_file)
report = [] report = []
report.append( report.append(
f"#### Checking with the file `{basename_reference_file}` from the `{reference_branch}` - Checking the `{branch}`" f"### 📋 Checking with the file `{basename_reference_file}` from the `{reference_branch}` - Checking the `{branch}`"
) )
reference_list = read_properties(reference_file) reference_lines = read_properties(reference_file)
is_diff = False has_differences = False
only_reference_file = True
for file_path in file_list: for file_path in file_list:
basename_current_file = os.path.basename(branch + "/" + file_path) basename_current_file = os.path.basename(branch + "/" + file_path)
if ( if (
branch + "/" + file_path == reference_file basename_current_file == basename_reference_file
or not file_path.endswith(".properties") or not file_path.endswith(".properties")
or not basename_current_file.startswith("messages_") or not basename_current_file.startswith("messages_")
): ):
# report.append(f"File '{basename_current_file}' is ignored.")
continue continue
report.append(f"Checking the language file `{basename_current_file}`...") only_reference_file = False
current_list = read_properties(branch + "/" + file_path) report.append(f"#### 🗂️ **Checking File:** `{basename_current_file}`...")
reference_list_len = len(reference_list) current_lines = read_properties(branch + "/" + file_path)
current_list_len = len(current_list) reference_line_count = len(reference_lines)
current_line_count = len(current_lines)
if reference_list_len != current_list_len: if reference_line_count != current_line_count:
report.append("") report.append("")
report.append("- ❌ Test 1 failed! Difference in the file!") report.append("- **Test 1 Status:** ❌ Failed")
is_diff = True has_differences = True
if reference_list_len > current_list_len: if reference_line_count > current_line_count:
report.append( report.append(
f" - Missing lines! Either comments, empty lines, or translation strings are missing! {reference_list_len}:{current_list_len}" f" - **Issue:** Missing lines! Comments, empty lines, or translation strings are missing. Details: {reference_line_count} (reference) vs {current_line_count} (current)."
) )
elif reference_list_len < current_list_len: elif reference_line_count < current_line_count:
report.append( report.append(
f" - Too many lines! Check your translation files! {reference_list_len}:{current_list_len}" f" - **Issue:** Too many lines! Check your translation files! Details: {reference_line_count} (reference) vs {current_line_count} (current)."
) )
else: else:
report.append("- ✅ Test 1 passed") report.append("- **Test 1 Status:** ✅ Passed")
if 1 == 1:
# Check for missing or extra keys
current_keys = [] current_keys = []
reference_keys = [] reference_keys = []
for item in current_list: for line in current_lines:
if not item.startswith("#") and item != "" and "=" in item: if not line.startswith("#") and line != "" and "=" in line:
key, _ = item.split("=", 1) key, _ = line.split("=", 1)
current_keys.append(key) current_keys.append(key)
for item in reference_list: for line in reference_lines:
if not item.startswith("#") and item != "" and "=" in item: if not line.startswith("#") and line != "" and "=" in line:
key, _ = item.split("=", 1) key, _ = line.split("=", 1)
reference_keys.append(key) reference_keys.append(key)
current_set = set(current_keys) current_keys_set = set(current_keys)
reference_set = set(reference_keys) reference_keys_set = set(reference_keys)
set_test1 = current_set.difference(reference_set) missing_keys = current_keys_set.difference(reference_keys_set)
set_test2 = reference_set.difference(current_set) extra_keys = reference_keys_set.difference(current_keys_set)
set_test1_list = list(set_test1) missing_keys_list = list(missing_keys)
set_test2_list = list(set_test2) extra_keys_list = list(extra_keys)
if len(set_test1_list) > 0 or len(set_test2_list) > 0: if missing_keys_list or extra_keys_list:
is_diff = True has_differences = True
set_test1_list = "`, `".join(set_test1_list) missing_keys_str = "`, `".join(missing_keys_list)
set_test2_list = "`, `".join(set_test2_list) extra_keys_str = "`, `".join(extra_keys_list)
report.append("- ❌ Test 2 failed") report.append("- **Test 2 Status:** ❌ Failed")
if len(set_test1_list) > 0: if missing_keys_list:
report.append( report.append(
f" - There are keys in ***{basename_current_file}*** `{set_test1_list}` that are not present in ***{basename_reference_file}***!" f" - **Issue:** There are keys in ***{basename_current_file}*** `{missing_keys_str}` that are not present in ***{basename_reference_file}***!"
) )
if len(set_test2_list) > 0: if extra_keys_list:
report.append( report.append(
f" - There are keys in ***{basename_reference_file}*** `{set_test2_list}` that are not present in ***{basename_current_file}***!" f" - **Issue:** There are keys in ***{basename_reference_file}*** `{extra_keys_str}` that are not present in ***{basename_current_file}***!"
) )
else: else:
report.append("- ✅ Test 2 passed") report.append("- **Test 2 Status:** ✅ Passed")
if has_differences:
report.append("") report.append("")
report.append(f"#### 🚧 ***{basename_current_file}*** will be corrected...")
report.append("") report.append("")
if is_diff: report.append("---")
report.append("## ❌ Check fail") report.append("")
update_file_list = glob.glob(branch + "/src/**/messages_*.properties", recursive=True)
update_missing_keys(reference_file, update_file_list)
if has_differences:
report.append("## ❌ Overall Check Status: **_Failed_**")
else: else:
report.append("## ✅ Check success") report.append("## ✅ Overall Check Status: **_Success_**")
if not only_reference_file:
print("\n".join(report)) print("\n".join(report))
@ -106,10 +235,16 @@ if __name__ == "__main__":
parser.add_argument( parser.add_argument(
"--files", "--files",
nargs="+", nargs="+",
required=True, required=False,
help="List of changed files, separated by spaces.", help="List of changed files, separated by spaces.",
) )
args = parser.parse_args() args = parser.parse_args()
file_list = args.files file_list = args.files
check_difference(args.reference_file, file_list, args.branch) if file_list is None:
file_list = glob.glob(
os.getcwd() + "/src/**/messages_*.properties", recursive=True
)
update_missing_keys(args.reference_file, file_list)
else:
check_for_differences(args.reference_file, file_list, args.branch)

View File

@ -1,15 +1,22 @@
name: Check Properties Files in PR name: Check Properties Files
on: on:
pull_request_target: pull_request_target:
types: [opened, synchronize, reopened] types: [opened, synchronize, reopened]
paths: paths:
- "src/main/resources/messages_*.properties" - "src/main/resources/messages_*.properties"
push:
paths:
- "src/main/resources/messages_en_GB.properties"
permissions:
contents: write
pull-requests: write
jobs: jobs:
check-files: check-files:
if: github.event_name == 'pull_request_target'
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
- name: Checkout PR branch - name: Checkout PR branch
uses: actions/checkout@v4 uses: actions/checkout@v4
@ -59,6 +66,7 @@ jobs:
else else
echo "REFERENCE_FILE=main-branch/src/main/resources/messages_en_GB.properties" >> $GITHUB_ENV echo "REFERENCE_FILE=main-branch/src/main/resources/messages_en_GB.properties" >> $GITHUB_ENV
fi fi
echo "REFERENCE_FILE=${{ env.REFERENCE_FILE }}"
- name: Show REFERENCE_FILE - name: Show REFERENCE_FILE
run: echo "Reference file is set to ${{ env.REFERENCE_FILE }}" run: echo "Reference file is set to ${{ env.REFERENCE_FILE }}"
@ -71,26 +79,121 @@ jobs:
- name: Capture output - name: Capture output
id: capture-output id: capture-output
run: | run: |
if [ -f failure.txt ]; then if [ -f failure.txt ] && [ -s failure.txt ]; then
echo "Test failed, capturing output..." echo "Test failed, capturing output..."
# Use the cat command to avoid issues with special characters in environment variables
ERROR_OUTPUT=$(cat failure.txt) ERROR_OUTPUT=$(cat failure.txt)
echo "ERROR_OUTPUT<<EOF" >> $GITHUB_ENV echo "ERROR_OUTPUT<<EOF" >> $GITHUB_ENV
echo "$ERROR_OUTPUT" >> $GITHUB_ENV echo "$ERROR_OUTPUT" >> $GITHUB_ENV
echo "EOF" >> $GITHUB_ENV echo "EOF" >> $GITHUB_ENV
echo $ERROR_OUTPUT echo $ERROR_OUTPUT
else
echo "No errors found."
echo "ERROR_OUTPUT=" >> $GITHUB_ENV
fi fi
- name: Post comment on PR - name: Post comment on PR
if: env.ERROR_OUTPUT != ''
uses: actions/github-script@v7 uses: actions/github-script@v7
with: with:
script: | script: |
const { GITHUB_REPOSITORY, ERROR_OUTPUT } = process.env; const { GITHUB_REPOSITORY, ERROR_OUTPUT } = process.env;
const [repoOwner, repoName] = GITHUB_REPOSITORY.split('/'); const [repoOwner, repoName] = GITHUB_REPOSITORY.split('/');
const prNumber = context.issue.number; // Pull request number from context const prNumber = context.issue.number;
// Find existing comment
const comments = await github.rest.issues.listComments({
owner: repoOwner,
repo: repoName,
issue_number: prNumber
});
const comment = comments.data.find(c => c.body.includes("## 🚀 Translation Verification Summary"));
// Only allow the action user to update comments
const expectedActor = "github-actions[bot]";
if (comment && comment.user.login === expectedActor) {
// Update existing comment
await github.rest.issues.updateComment({
owner: repoOwner,
repo: repoName,
comment_id: comment.id,
body: `## 🚀 Translation Verification Summary\n\n\n${ERROR_OUTPUT}\n`
});
console.log("Updated existing comment.");
} else if (!comment) {
// Create new comment if no existing comment is found
await github.rest.issues.createComment({ await github.rest.issues.createComment({
owner: repoOwner, owner: repoOwner,
repo: repoName, repo: repoName,
issue_number: prNumber, issue_number: prNumber,
body: `## Translation Verification Summary\n\n\n${ERROR_OUTPUT}\n` body: `## 🚀 Translation Verification Summary\n\n\n${ERROR_OUTPUT}\n`
}); });
console.log("Created new comment.");
} else {
console.log("Comment update attempt denied. Actor does not match.");
}
- name: Set up git config
run: |
git config --global user.name "github-actions[bot]"
git config --global user.email "github-actions[bot]@users.noreply.github.com"
- name: Add translation keys
run: |
cd ${{ env.BRANCH_PATH }}
git add src/main/resources/messages_*.properties
git diff --staged --quiet || echo "CHANGES_DETECTED=true" >> $GITHUB_ENV
git commit -m "Update translation files" || echo "No changes to commit"
- name: Push
if: env.CHANGES_DETECTED == 'true'
run: |
cd pr-branch
git push origin ${{ github.head_ref }} || echo "Push failed: possibly no changes to push"
update-translations-main:
if: github.event_name == 'push'
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: "3.x"
- name: Run Python script to check files
id: run-check
run: |
python .github/scripts/check_language_properties.py --reference-file src/main/resources/messages_en_GB.properties --branch main
- name: Set up git config
run: |
git config --global user.name "github-actions[bot]"
git config --global user.email "github-actions[bot]@users.noreply.github.com"
- name: Add translation keys
run: |
git add src/main/resources/messages_*.properties
git diff --staged --quiet || echo "CHANGES_DETECTED=true" >> $GITHUB_ENV
- name: Create Pull Request
id: cpr
if: env.CHANGES_DETECTED == 'true'
uses: peter-evans/create-pull-request@v6
with:
token: ${{ secrets.GITHUB_TOKEN }}
commit-message: "Update translation files"
committer: GitHub Action <action@github.com>
author: GitHub Action <action@github.com>
signoff: true
branch: update_translation_files
title: "Update translation files"
body: |
Auto-generated by [create-pull-request][1]
[1]: https://github.com/peter-evans/create-pull-request
labels: Translation
draft: false
delete-branch: true