Files
Stirling-PDF/scripts/translations/validate_json_structure.py
T
0a50e765b7 Restructure/frontend editor (#6404)
## Move editor under `frontend/editor/`

Pure restructure: `frontend/` becomes the workspace, `frontend/editor/`
holds
  the PDF editor. 1775 file renames + 40 wiring edits. No logic changes.

  ### Why

`frontend/` is currently the editor — its `src/`, `public/`,
`src-tauri/`,
  config files all sit at the root. Promoting `frontend/` to a
workspace and putting the editor in a sibling folder leaves room for
future
apps to drop in alongside it, sharing one `package.json` /
`node_modules` /
  lint config / Storybook.

  ### What moves

  frontend/
  ├── editor/                ← NEW: everything editor-specific
  │   ├── src/               ← was frontend/src/
  │   ├── public/            ← was frontend/public/
  │   ├── src-tauri/         ← was frontend/src-tauri/
│ ├── index.html, vite.config.ts, vitest.config.ts, playwright.config.ts
  │   ├── tsconfig*.json, tailwind.config.js, postcss.config.js
  │   ├── scripts/
  │   ├── .env, .env.desktop, .env.saas
  │   └── DeveloperGuide.md
├── package.json, package-lock.json, node_modules/ ← workspace install
  ├── eslint.config.mjs, .prettierrc, .prettierignore ← shared tooling
  ├── .gitignore
  └── README.md

  ### Wiring edits (40 files)

  - `.taskfiles/frontend.yml`, `desktop.yml`, `e2e.yml`
  - `build.gradle`, `app/core/build.gradle`
- `eslint.config.mjs`, `frontend/package.json`, `.gitignore`,
`.prettierignore`
  - `docker/frontend/Dockerfile`
  - 8 `.github/workflows/*.yml`, plus `.github/dependabot.yml`,
    `.github/config/.files.yaml`, `.github/labeler-config-srvaroa.yml`
  - `scripts/translations/**`
- Docs: `AGENTS.md`, `CLAUDE.md`, `ADDING_TOOLS.md`,
`DeveloperGuide.md`,
`WINDOWS_SIGNING.md`, `devGuide/HowToAddNewLanguage.md`,
`frontend/README.md`,
    `frontend/editor/DeveloperGuide.md`

Plus 3 renamed + edited: `editor/vite.config.ts` (env path +
node_modules
  walk-up), `editor/scripts/setup-env.mts` (renamed from `.ts` for
`import.meta.url`), `editor/scripts/build-provisioner.mjs` (resolve
src-tauri
  relative to script).

  ### Verification

  | Check | Result |
  |---|---|
  | `task frontend:typecheck:all` (6 variants) | exit 0 |
  | `task frontend:lint` (eslint + dpdm) | exit 0 |
  | `task frontend:format:check` | exit 0 |
  | `task frontend:test` | 657 tests pass, 50 files |
| `task frontend:build:{core,proprietary,saas,desktop,prototypes}` | all
green |
| `task desktop:build` | full Tauri pipeline →
`Stirling-PDF_2.11.0_x64_en-US.msi` |
  | `playwright test --list --project=stubbed` | 172 tests discovered |

`task desktop:build` exercises the heaviest path — Rust + WiX + MSI
bundle
against the moved `editor/src-tauri/`. If anything in the restructure
was
  wrong it wouldn't have built.

  ### Test plan

  - [ ] `frontend-validation.yml` green
  - [ ] `e2e-stubbed.yml` green
  - [ ] `tauri-build.yml` green on at least one platform
  - [ ] `check_toml.yml` runs on a translation-touching PR

---------

Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]>
2026-05-22 13:40:34 +01:00

222 lines
7.1 KiB
Python

#!/usr/bin/env python3
"""
Validate TOML structure and formatting of translation files.
Checks for:
- Valid TOML syntax
- Consistent key structure with en-GB
- Missing keys
- Extra keys not in en-GB
- Malformed entries
Usage:
python scripts/translations/validate_json_structure.py [--language LANG]
"""
import json
import sys
from pathlib import Path
from typing import Dict, Set
import argparse
import tomllib # Python 3.11+ (stdlib)
def get_all_keys(d: dict, parent_key: str = "", sep: str = ".") -> Set[str]:
"""Get all keys from nested dict as dot-notation paths."""
keys = set()
for k, v in d.items():
new_key = f"{parent_key}{sep}{k}" if parent_key else k
keys.add(new_key)
if isinstance(v, dict):
keys.update(get_all_keys(v, new_key, sep=sep))
return keys
def validate_translation_file(file_path: Path) -> tuple[bool, str]:
"""Validate that a file contains valid TOML."""
try:
with open(file_path, "rb") as f:
tomllib.load(f)
return True, "Valid TOML"
except Exception as e:
return False, f"Error reading file: {str(e)}"
def validate_structure(
en_gb_keys: Set[str], lang_keys: Set[str], lang_code: str
) -> Dict:
"""Compare structure between en-GB and target language."""
missing_keys = en_gb_keys - lang_keys
extra_keys = lang_keys - en_gb_keys
return {
"language": lang_code,
"missing_keys": sorted(missing_keys),
"extra_keys": sorted(extra_keys),
"total_keys": len(lang_keys),
"expected_keys": len(en_gb_keys),
"missing_count": len(missing_keys),
"extra_count": len(extra_keys),
}
def print_validation_result(result: Dict, verbose: bool = False):
"""Print validation results in readable format."""
lang = result["language"]
print(f"\n{'=' * 100}")
print(f"Language: {lang}")
print(f"{'=' * 100}")
print(f" Total keys: {result['total_keys']}")
print(f" Expected keys (en-GB): {result['expected_keys']}")
print(f" Missing keys: {result['missing_count']}")
print(f" Extra keys: {result['extra_count']}")
if result["missing_count"] == 0 and result["extra_count"] == 0:
print(" ✅ Structure matches en-GB perfectly!")
else:
if result["missing_count"] > 0:
print(f"\n ⚠️ Missing {result['missing_count']} key(s):")
if verbose or result["missing_count"] <= 20:
for key in result["missing_keys"][:50]:
print(f" - {key}")
if result["missing_count"] > 50:
print(f" ... and {result['missing_count'] - 50} more")
else:
print(" (use --verbose to see all)")
if result["extra_count"] > 0:
print(f"\n ⚠️ Extra {result['extra_count']} key(s) not in en-GB:")
if verbose or result["extra_count"] <= 20:
for key in result["extra_keys"][:50]:
print(f" - {key}")
if result["extra_count"] > 50:
print(f" ... and {result['extra_count'] - 50} more")
else:
print(" (use --verbose to see all)")
print("-" * 100)
def load_translation_file(file_path: Path) -> dict:
"""Load TOML translation file."""
with open(file_path, "rb") as f:
return tomllib.load(f)
def main():
parser = argparse.ArgumentParser(description="Validate translation TOML structure")
parser.add_argument(
"--language",
help="Specific language code to validate (e.g., es-ES)",
default=None,
)
parser.add_argument(
"--verbose", "-v", action="store_true", help="Show all missing/extra keys"
)
parser.add_argument("--json", action="store_true", help="Output results as JSON")
args = parser.parse_args()
# Define paths
locales_dir = Path("frontend/editor/public/locales")
en_gb_path = locales_dir / "en-GB" / "translation.toml"
if not en_gb_path.exists():
print(f"❌ Error: en-GB translation file not found at {en_gb_path}")
sys.exit(1)
# Validate en-GB itself
is_valid, message = validate_translation_file(en_gb_path)
if not is_valid:
print(f"❌ Error in en-GB file: {message}")
sys.exit(1)
# Load en-GB structure
en_gb = load_translation_file(en_gb_path)
en_gb_keys = get_all_keys(en_gb)
# Get list of languages to validate
if args.language:
languages = [args.language]
else:
# Validate all languages except en-GB
languages = []
for d in locales_dir.iterdir():
if d.is_dir() and d.name != "en-GB":
if (d / "translation.toml").exists():
languages.append(d.name)
results = []
json_errors = []
# Validate each language
for lang_code in sorted(languages):
lang_path = locales_dir / lang_code / "translation.toml"
if not lang_path.exists():
print(f"⚠️ Warning: {lang_code}/translation.toml not found, skipping")
continue
# First check if file is valid
is_valid, message = validate_translation_file(lang_path)
if not is_valid:
json_errors.append(
{"language": lang_code, "file": str(lang_path), "error": message}
)
continue
# Load and compare structure
lang_data = load_translation_file(lang_path)
lang_keys = get_all_keys(lang_data)
result = validate_structure(en_gb_keys, lang_keys, lang_code)
results.append(result)
# Output results
if args.json:
output = {"json_errors": json_errors, "structure_validation": results}
print(json.dumps(output, indent=2, ensure_ascii=False))
else:
# Print syntax errors first
if json_errors:
print("\n❌ Syntax Errors:")
print("=" * 100)
for error in json_errors:
print(f"\nLanguage: {error['language']}")
print(f"File: {error['file']}")
print(f"Error: {error['error']}")
print("\n")
# Print structure validation results
if results:
print("\n📊 Structure Validation Summary:")
print(f" Languages validated: {len(results)}")
perfect = sum(
1 for r in results if r["missing_count"] == 0 and r["extra_count"] == 0
)
print(f" Perfect matches: {perfect}/{len(results)}")
total_missing = sum(r["missing_count"] for r in results)
total_extra = sum(r["extra_count"] for r in results)
print(f" Total missing keys: {total_missing}")
print(f" Total extra keys: {total_extra}")
for result in results:
print_validation_result(result, verbose=args.verbose)
if not json_errors and perfect == len(results):
print("\n✅ All translations have perfect structure!")
# Exit with error code if issues found
has_issues = len(json_errors) > 0 or any(
r["missing_count"] > 0 or r["extra_count"] > 0 for r in results
)
sys.exit(1 if has_issues else 0)
if __name__ == "__main__":
main()