Full-stack Amazon AI Transcreation Platform with: - FastAPI backend (async, PostgreSQL, Redis, Celery) with 11 DB tables - JWT auth (SSO-ready abstract provider pattern) - 6-agent pipeline orchestrator with deterministic modules - Next.js 14 frontend with Amazon branding (Ember fonts, orange/dark theme) - Job wizard, monitoring HUD, output review, admin screens - 154 TM/reference files imported, 12 locales configured - Docker Compose for all services Agents 2-5 (TM retrieval, ranker, transcreator, compliance) are stubs pending Phase 3 LLM integration. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
177 lines
5 KiB
Python
177 lines
5 KiB
Python
"""Reference file loader.
|
|
|
|
Loads various reference files used in the transcreation pipeline:
|
|
- Glossary (JSON): locale-specific term glossary
|
|
- Blacklist (JSON): forbidden terms and roots
|
|
- Date/Percentage formats (JSON): approved format patterns
|
|
- Locale Considerations (JSON): locale-specific rules and notes
|
|
- TOV (Tone of Voice) files (JSON): global and supplementary voice profiles
|
|
"""
|
|
|
|
import json
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
|
|
class RefFileLoadError(Exception):
|
|
"""Raised when a reference file cannot be loaded or parsed."""
|
|
pass
|
|
|
|
|
|
def load_json_file(file_path: str) -> Any:
|
|
"""Load and parse a JSON file.
|
|
|
|
Args:
|
|
file_path: Absolute path to the JSON file.
|
|
|
|
Returns:
|
|
Parsed JSON data.
|
|
|
|
Raises:
|
|
RefFileLoadError: If file cannot be read or parsed.
|
|
"""
|
|
path = Path(file_path)
|
|
if not path.exists():
|
|
raise RefFileLoadError(f"Reference file not found: {file_path}")
|
|
|
|
try:
|
|
with open(path, "r", encoding="utf-8") as f:
|
|
return json.load(f)
|
|
except json.JSONDecodeError as exc:
|
|
raise RefFileLoadError(f"Invalid JSON in reference file: {exc}")
|
|
except UnicodeDecodeError as exc:
|
|
raise RefFileLoadError(f"Encoding error reading reference file: {exc}")
|
|
|
|
|
|
def load_glossary(file_path: str) -> list[dict[str, str]]:
|
|
"""Load a glossary file.
|
|
|
|
Expected format: list of dicts with keys like:
|
|
{"en": "source term", "tx": "translated term", "context": "usage notes"}
|
|
|
|
Args:
|
|
file_path: Path to glossary JSON file.
|
|
|
|
Returns:
|
|
List of glossary entry dicts.
|
|
"""
|
|
data = load_json_file(file_path)
|
|
if not isinstance(data, list):
|
|
raise RefFileLoadError("Glossary file must contain a JSON array")
|
|
return data
|
|
|
|
|
|
def load_blacklist(file_path: str) -> list[dict[str, str]]:
|
|
"""Load a blacklist file.
|
|
|
|
Expected format: list of dicts with keys:
|
|
{"term": "forbidden term", "root": "optional root", "reason": "why forbidden"}
|
|
|
|
Args:
|
|
file_path: Path to blacklist JSON file.
|
|
|
|
Returns:
|
|
List of blacklist entry dicts.
|
|
"""
|
|
data = load_json_file(file_path)
|
|
if not isinstance(data, list):
|
|
raise RefFileLoadError("Blacklist file must contain a JSON array")
|
|
return data
|
|
|
|
|
|
def load_date_pct_formats(file_path: str) -> dict[str, list[dict[str, str]]]:
|
|
"""Load date/percentage format rules.
|
|
|
|
Expected format:
|
|
{
|
|
"date_formats": [{"pattern": "...", "example": "...", "description": "..."}],
|
|
"percentage_formats": [{"pattern": "...", "example": "...", "description": "..."}]
|
|
}
|
|
|
|
Args:
|
|
file_path: Path to date/pct formats JSON file.
|
|
|
|
Returns:
|
|
Dict with "date_formats" and "percentage_formats" keys.
|
|
"""
|
|
data = load_json_file(file_path)
|
|
if not isinstance(data, dict):
|
|
raise RefFileLoadError("Date/pct format file must contain a JSON object")
|
|
return {
|
|
"date_formats": data.get("date_formats", []),
|
|
"percentage_formats": data.get("percentage_formats", []),
|
|
}
|
|
|
|
|
|
def load_locale_considerations(file_path: str) -> dict[str, Any]:
|
|
"""Load locale-specific considerations.
|
|
|
|
Expected format: JSON object with locale-specific rules, cultural notes, etc.
|
|
|
|
Args:
|
|
file_path: Path to locale considerations JSON file.
|
|
|
|
Returns:
|
|
Dict of locale considerations.
|
|
"""
|
|
data = load_json_file(file_path)
|
|
if not isinstance(data, dict):
|
|
raise RefFileLoadError(
|
|
"Locale considerations file must contain a JSON object"
|
|
)
|
|
return data
|
|
|
|
|
|
def load_tov(file_path: str) -> dict[str, Any]:
|
|
"""Load a Tone of Voice file (global or supplement).
|
|
|
|
Expected format: JSON object with voice profile data.
|
|
|
|
Args:
|
|
file_path: Path to TOV JSON file.
|
|
|
|
Returns:
|
|
Dict of TOV profile data.
|
|
"""
|
|
data = load_json_file(file_path)
|
|
if not isinstance(data, dict):
|
|
raise RefFileLoadError("TOV file must contain a JSON object")
|
|
return data
|
|
|
|
|
|
def load_all_reference_files(
|
|
file_manifest: dict[str, str | None],
|
|
) -> dict[str, Any]:
|
|
"""Load all reference files from a file manifest.
|
|
|
|
Args:
|
|
file_manifest: Dict mapping file types to file paths.
|
|
Keys: glossary_file, blacklist_file, tov_global_file,
|
|
tov_supplement_file, locale_considerations_file,
|
|
date_pct_formats_file
|
|
|
|
Returns:
|
|
Dict mapping file types to loaded data.
|
|
"""
|
|
result: dict[str, Any] = {}
|
|
|
|
loaders = {
|
|
"glossary_file": load_glossary,
|
|
"blacklist_file": load_blacklist,
|
|
"date_pct_formats_file": load_date_pct_formats,
|
|
"locale_considerations_file": load_locale_considerations,
|
|
"tov_global_file": load_tov,
|
|
"tov_supplement_file": load_tov,
|
|
}
|
|
|
|
for key, loader in loaders.items():
|
|
path = file_manifest.get(key)
|
|
if path:
|
|
try:
|
|
result[key] = loader(path)
|
|
except RefFileLoadError:
|
|
result[key] = None
|
|
else:
|
|
result[key] = None
|
|
|
|
return result
|