ol-openedx-course-translations 0.1.0__py3-none-any.whl → 0.3.5__py3-none-any.whl

ol_openedx_course_translations/settings/lms.py

@@ -0,0 +1,38 @@
+# noqa: INP001
+
+"""Settings to provide to edX"""
+
+from ol_openedx_course_translations.settings.common import apply_common_settings
+
+
+def plugin_settings(settings):
+    """
+    Populate lms settings
+    """
+    apply_common_settings(settings)
+    settings.MIDDLEWARE.extend(
+        ["ol_openedx_course_translations.middleware.CourseLanguageCookieMiddleware"]
+    )
+    VIDEO_TRANSCRIPT_LANGUAGE_FILTERS = {
+        "org.openedx.learning.xblock.render.started.v1": {
+            "pipeline": [
+                "ol_openedx_course_translations.filters.AddDestLangForVideoBlock"
+            ],
+            "fail_silently": False,
+        }
+    }
+    existing_filters = getattr(settings, "OPEN_EDX_FILTERS_CONFIG", {})
+
+    # Merge pipeline lists instead of overwriting
+    for filter_name, config in VIDEO_TRANSCRIPT_LANGUAGE_FILTERS.items():
+        if filter_name not in existing_filters:
+            existing_filters[filter_name] = config
+        else:
+            existing_filters[filter_name]["pipeline"].extend(config.get("pipeline", []))
+            # do not override fail_silently
+            if "fail_silently" in config:
+                existing_filters[filter_name].setdefault(
+                    "fail_silently", config["fail_silently"]
+                )
+
+    settings.OPEN_EDX_FILTERS_CONFIG = existing_filters

ol_openedx_course_translations/tasks.py

@@ -0,0 +1,222 @@
+"""Celery tasks for course content translation."""
+
+import json
+import logging
+from pathlib import Path
+
+from celery import shared_task
+
+from ol_openedx_course_translations.providers.deepl_provider import DeepLProvider
+from ol_openedx_course_translations.utils.course_translations import (
+    get_srt_output_filename,
+    get_translation_provider,
+    translate_policy_fields,
+    translate_xml_display_name,
+    update_video_xml_complete,
+)
+
+logger = logging.getLogger(__name__)
+
+
+@shared_task(bind=True, name="translate_file_task")
+def translate_file_task(  # noqa: PLR0913
+    _self,
+    file_path_str: str,
+    source_language: str,
+    target_language: str,
+    content_provider_name: str,
+    content_model: str | None,
+    srt_provider_name: str,
+    srt_model: str | None,
+    glossary_directory: str | None = None,
+):
+    """
+    Translate a single file asynchronously.
+
+    Handles translation of various file types including SRT subtitles,
+    XML, and HTML files. Uses appropriate translation provider based on file type.
+
+    Args:
+        _self: Celery task instance (bound)
+        file_path_str: Path to the file to translate
+        source_language: Source language code
+        target_language: Target language code
+        content_provider_name: Provider name for content translation
+        content_model: Model name for content provider (optional)
+        srt_provider_name: Provider name for SRT translation
+        srt_model: Model name for SRT provider (optional)
+        glossary_directory: Path to glossary directory (optional)
+
+    Returns:
+        Dict with status, file path, and optional error or output information
+    """
+    try:
+        file_path = Path(file_path_str)
+
+        # Handle SRT files
+        if file_path.suffix == ".srt":
+            provider = get_translation_provider(srt_provider_name, srt_model)
+
+            source_lang_pattern = f"-{source_language.lower()}.srt"
+            if not file_path.name.lower().endswith(source_lang_pattern):
+                return {
+                    "status": "skipped",
+                    "file": file_path_str,
+                    "reason": "Not source language SRT",
+                }
+
+            output_filename = get_srt_output_filename(file_path.name, target_language)
+            output_file_path = file_path.parent / output_filename
+
+            provider.translate_document(
+                file_path,
+                output_file_path,
+                source_language,
+                target_language,
+                glossary_directory,
+            )
+
+            return {
+                "status": "success",
+                "file": file_path_str,
+                "output": str(output_file_path),
+            }
+
+        # Handle other files
+        file_content = file_path.read_text(encoding="utf-8")
+
+        tag_handling_mode = None
+        if file_path.suffix in [".xml", ".html"]:
+            tag_handling_mode = file_path.suffix.lstrip(".")
+
+        provider = get_translation_provider(content_provider_name, content_model)
+        translated_content = provider.translate_text(
+            file_content,
+            target_language.lower(),
+            tag_handling=tag_handling_mode,
+            glossary_directory=glossary_directory,
+        )
+
+        # Handle XML display_name translation only for DeepL provider
+        # LLM providers translate display_name as part of the XML translation
+        if file_path.suffix == ".xml" and isinstance(provider, DeepLProvider):
+            translated_content = translate_xml_display_name(
+                translated_content, target_language, provider, glossary_directory
+            )
+
+        # Update video XML if needed (use complete version)
+        if file_path.suffix == ".xml" and file_path.parent.name == "video":
+            translated_content = update_video_xml_complete(
+                translated_content, target_language
+            )
+
+        file_path.write_text(translated_content, encoding="utf-8")
+    except Exception as e:
+        logger.exception("Failed to translate file %s", file_path_str)
+        return {"status": "error", "file": file_path_str, "error": str(e)}
+    else:
+        return {"status": "success", "file": file_path_str}
+
+
+@shared_task(bind=True, name="translate_grading_policy_task")
+def translate_grading_policy_task(
+    _self,
+    policy_file_path_str: str,
+    target_language: str,
+    content_provider_name: str,
+    content_model: str | None,
+    glossary_directory: str | None = None,
+):
+    """
+    Translate grading_policy.json file.
+
+    Translates the short_label fields within the GRADER section of grading policy files.
+
+    Args:
+        _self: Celery task instance (bound)
+        policy_file_path_str: Path to the grading_policy.json file
+        target_language: Target language code
+        content_provider_name: Provider name for content translation
+        content_model: Model name for content provider (optional)
+        glossary_directory: Path to glossary directory (optional)
+
+    Returns:
+        Dict with status, file path, and optional error information
+    """
+    try:
+        policy_file_path = Path(policy_file_path_str)
+        provider = get_translation_provider(content_provider_name, content_model)
+
+        grading_policy_data = json.loads(policy_file_path.read_text(encoding="utf-8"))
+        policy_updated = False
+
+        for grader_item in grading_policy_data.get("GRADER", []):
+            if "short_label" in grader_item:
+                translated_label = provider.translate_text(
+                    grader_item["short_label"],
+                    target_language.lower(),
+                    glossary_directory=glossary_directory,
+                )
+                grader_item["short_label"] = translated_label
+                policy_updated = True
+
+        if policy_updated:
+            policy_file_path.write_text(
+                json.dumps(grading_policy_data, ensure_ascii=False, indent=4),
+                encoding="utf-8",
+            )
+    except Exception as e:
+        logger.exception("Failed to translate grading policy %s", policy_file_path_str)
+        return {"status": "error", "file": policy_file_path_str, "error": str(e)}
+    else:
+        return {"status": "success", "file": policy_file_path_str}
+
+
+@shared_task(bind=True, name="translate_policy_json_task")
+def translate_policy_json_task(
+    _self,
+    policy_file_path_str: str,
+    target_language: str,
+    content_provider_name: str,
+    content_model: str | None,
+    glossary_directory: str | None = None,
+):
+    """
+    Translate policy.json file.
+
+    Translates various policy fields including display names, discussion topics,
+    learning info, tabs, and XML attributes.
+
+    Args:
+        _self: Celery task instance (bound)
+        policy_file_path_str: Path to the policy.json file
+        target_language: Target language code
+        content_provider_name: Provider name for content translation
+        content_model: Model name for content provider (optional)
+        glossary_directory: Path to glossary directory (optional)
+
+    Returns:
+        Dict with status, file path, and optional error information
+    """
+    try:
+        policy_file_path = Path(policy_file_path_str)
+        provider = get_translation_provider(content_provider_name, content_model)
+
+        policy_json_data = json.loads(policy_file_path.read_text(encoding="utf-8"))
+        for course_policy_obj in policy_json_data.values():
+            if not isinstance(course_policy_obj, dict):
+                continue
+
+            translate_policy_fields(
+                course_policy_obj, target_language, provider, glossary_directory
+            )
+
+        policy_file_path.write_text(
+            json.dumps(policy_json_data, ensure_ascii=False, indent=4),
+            encoding="utf-8",
+        )
+    except Exception as e:
+        logger.exception("Failed to translate policy.json %s", policy_file_path_str)
+        return {"status": "error", "file": policy_file_path_str, "error": str(e)}
+    else:
+        return {"status": "success", "file": policy_file_path_str}

ol_openedx_course_translations/urls.py

@@ -0,0 +1,16 @@
+"""
+URL configuration for ol_openedx_course_translations app.
+"""
+
+from django.conf import settings
+from django.urls import re_path
+
+from ol_openedx_course_translations.views import CourseLanguageView
+
+urlpatterns = [
+    re_path(
+        rf"api/course-language/{settings.COURSE_KEY_PATTERN}$",
+        CourseLanguageView.as_view(),
+        name="ol_openedx_course_language",
+    ),
+]

ol_openedx_course_translations/utils/command_utils.py

@@ -0,0 +1,197 @@
+"""
+Utility functions for management commands.
+
+This module provides reusable utilities for Django management commands,
+including validation, error handling, git operations, and configuration helpers.
+"""
+
+import os
+import re
+from datetime import UTC, datetime
+from typing import Any
+
+from django.conf import settings
+from django.core.management.base import CommandError
+
+from ol_openedx_course_translations.utils.constants import (
+    PROVIDER_GEMINI,
+    PROVIDER_MISTRAL,
+)
+
+# ============================================================================
+# Validation Utilities
+# ============================================================================
+
+
+def validate_language_code(code: str, field_name: str = "language code") -> None:
+    """Validate language code format (xx or xx_XX)."""
+    if not re.match(r"^[a-z]{2}(_[A-Z]{2})?$", code):
+        msg = (
+            f"Invalid {field_name} format: {code}. "
+            f"Expected format: 'xx' or 'xx_XX' (e.g., 'el', 'es_ES')"
+        )
+        raise CommandError(msg)
+
+
+def validate_branch_name(branch_name: str) -> None:
+    """Validate branch name format to prevent injection."""
+    if not re.match(r"^[a-z0-9/_-]+$", branch_name):
+        msg = f"Invalid branch name format: {branch_name}"
+        raise CommandError(msg)
+
+
+# ============================================================================
+# Git Utilities
+# ============================================================================
+
+
+def sanitize_for_git(text: str) -> str:
+    """Sanitize text for use in git operations."""
+    return re.sub(r"[^\w\s-]", "", text)
+
+
+def create_branch_name(lang_code: str) -> str:
+    """Create a safe branch name from language code."""
+    safe_lang = re.sub(r"[^a-z0-9_-]", "", lang_code.lower())
+    timestamp = datetime.now(tz=UTC).strftime("%Y%m%d-%H%M%S")
+    return f"feature/add-{safe_lang}-translations-{timestamp}"
+
+
+# ============================================================================
+# Configuration Helpers
+# ============================================================================
+
+
+def get_config_value(key: str, options: dict, default: Any = None) -> Any:
+    """Get configuration value from options, settings, or environment."""
+    # Check command-line options first (Django converts --repo-path to repo_path)
+    option_value = options.get(key) or options.get(key.replace("_", "-"))
+    if option_value:
+        return option_value
+
+    # Check settings with TRANSLATIONS_ prefix
+    setting_key = f"TRANSLATIONS_{key.upper().replace('-', '_')}"
+    if hasattr(settings, setting_key):
+        setting_value = getattr(settings, setting_key)
+        # Only use setting if it's not empty
+        if setting_value:
+            return setting_value
+
+    # Check environment variable with TRANSLATIONS_ prefix
+    env_key = setting_key
+    env_value = os.environ.get(env_key)
+    if env_value:
+        return env_value
+
+    # Return default if nothing found
+    return default
+
+
+def get_default_provider() -> str | None:
+    """Get default provider from TRANSLATIONS_PROVIDERS."""
+    providers = getattr(settings, "TRANSLATIONS_PROVIDERS", {})
+    if not isinstance(providers, dict):
+        return None
+    return providers.get("default_provider")
+
+
+def get_default_model_for_provider(provider: str) -> str | None:
+    """Get default model for a provider from TRANSLATIONS_PROVIDERS."""
+    providers = getattr(settings, "TRANSLATIONS_PROVIDERS", {})
+    if not isinstance(providers, dict):
+        return None
+    provider_config = providers.get(provider, {})
+    if not isinstance(provider_config, dict):
+        return None
+    return provider_config.get("default_model")
+
+
+def configure_litellm_for_provider(
+    provider: str, model: str, api_key: str | None, **base_kwargs
+) -> dict[str, Any]:
+    """Configure LiteLLM completion kwargs for a specific provider."""
+    completion_kwargs = dict(base_kwargs)
+    completion_kwargs["model"] = model
+
+    if api_key:
+        completion_kwargs["api_key"] = api_key
+        if provider == PROVIDER_GEMINI:
+            # If no prefix, add gemini/ to force Gemini API usage (not Vertex AI)
+            # If vertex_ai/ or gemini/ prefix already exists, respect it
+            if not model.startswith(("gemini/", "vertex_ai/")):
+                completion_kwargs["model"] = f"gemini/{model}"
+            # Gemini 3 models require temperature = 1.0 to avoid issues:
+            # - Infinite loops in response generation
+            # - Degraded reasoning performance
+            # - Failure on complex tasks
+            # See: https://docs.litellm.ai/docs/providers/gemini
+            if "gemini-3" in model.lower():
+                completion_kwargs["temperature"] = 1.0
+        elif provider == PROVIDER_MISTRAL and not model.startswith("mistral/"):
+            completion_kwargs["model"] = f"mistral/{model}"
+
+    return completion_kwargs
+
+
+# ============================================================================
+# Error Handling Utilities
+# ============================================================================
+
+
+def is_retryable_error(error: Exception) -> bool:
+    """
+    Check if an error is retryable (network issues, rate limits, timeouts).
+
+    Args:
+        error: The exception to check
+
+    Returns:
+        True if the error is retryable, False otherwise
+
+    Examples:
+        >>> is_retryable_error(ConnectionError("Connection timeout"))
+        True
+        >>> is_retryable_error(ValueError("Invalid API key"))
+        False
+    """
+    error_str = str(error).lower()
+
+    # Retryable errors
+    retryable_patterns = [
+        "timeout",
+        "connection",
+        "rate limit",
+        "429",
+        "503",
+        "502",
+        "500",
+        "temporarily unavailable",
+        "service unavailable",
+        "too many requests",
+    ]
+
+    # Non-retryable errors (don't retry these)
+    non_retryable_patterns = [
+        "invalid api key",
+        "authentication",
+        "401",
+        "403",
+        "not found",
+        "404",
+        "bad request",
+        "400",
+        "commanderror",  # Our custom errors that are usually non-retryable
+    ]
+
+    # Check for non-retryable first
+    for pattern in non_retryable_patterns:
+        if pattern in error_str:
+            return False
+
+    # Check for retryable patterns
+    for pattern in retryable_patterns:
+        if pattern in error_str:
+            return True
+
+    # Default: retry unknown errors (could be transient)
+    return True

ol_openedx_course_translations/utils/constants.py

@@ -0,0 +1,218 @@
+"""Constants for translation synchronization."""
+
+# LLM Provider names
+PROVIDER_DEEPL = "deepl"
+PROVIDER_GEMINI = "gemini"
+PROVIDER_MISTRAL = "mistral"
+PROVIDER_OPENAI = "openai"
+
+# Learner-facing frontend applications that require translation
+LEARNER_FACING_APPS = [
+    "frontend-app-learning",
+    "frontend-app-learner-dashboard",
+    "frontend-app-learner-record",
+    "frontend-app-account",
+    "frontend-app-profile",
+    "frontend-app-authn",
+    "frontend-app-catalog",
+    "frontend-app-discussions",
+    "frontend-component-header",
+    "frontend-component-footer",
+    "frontend-app-ora",
+    "frontend-platform",
+]
+
+# Plural forms configuration for different languages
+# Based on GNU gettext plural forms specification
+# See: https://www.gnu.org/software/gettext/manual/html_node/Plural-forms.html
+PLURAL_FORMS = {
+    # Languages with no plural forms (nplurals=1)
+    "ja": "nplurals=1; plural=0;",  # Japanese
+    "ko": "nplurals=1; plural=0;",  # Korean
+    "zh": "nplurals=1; plural=0;",  # Chinese (all variants)
+    "th": "nplurals=1; plural=0;",  # Thai
+    "vi": "nplurals=1; plural=0;",  # Vietnamese
+    "id": "nplurals=1; plural=0;",  # Indonesian
+    "ms": "nplurals=1; plural=0;",  # Malay
+    "km": "nplurals=1; plural=0;",  # Khmer
+    "bo": "nplurals=1; plural=0;",  # Tibetan
+    # Languages with 2 plural forms: plural=(n != 1)
+    "en": "nplurals=2; plural=(n != 1);",  # English
+    "es": "nplurals=2; plural=(n != 1);",  # Spanish (all variants)
+    "de": "nplurals=2; plural=(n != 1);",  # German
+    "el": "nplurals=2; plural=(n != 1);",  # Greek
+    "it": "nplurals=2; plural=(n != 1);",  # Italian
+    "pt": "nplurals=2; plural=(n != 1);",  # Portuguese (all variants)
+    "nl": "nplurals=2; plural=(n != 1);",  # Dutch
+    "sv": "nplurals=2; plural=(n != 1);",  # Swedish
+    "da": "nplurals=2; plural=(n != 1);",  # Danish
+    "no": "nplurals=2; plural=(n != 1);",  # Norwegian
+    "nb": "nplurals=2; plural=(n != 1);",  # Norwegian Bokmål
+    "nn": "nplurals=2; plural=(n != 1);",  # Norwegian Nynorsk
+    "fi": "nplurals=2; plural=(n != 1);",  # Finnish
+    "is": "nplurals=2; plural=(n != 1);",  # Icelandic
+    "et": "nplurals=2; plural=(n != 1);",  # Estonian
+    "lv": "nplurals=2; plural=(n != 1);",  # Latvian
+    "he": "nplurals=2; plural=(n != 1);",  # Hebrew
+    "hi": "nplurals=2; plural=(n != 1);",  # Hindi
+    "bn": "nplurals=2; plural=(n != 1);",  # Bengali
+    "gu": "nplurals=2; plural=(n != 1);",  # Gujarati
+    "kn": "nplurals=2; plural=(n != 1);",  # Kannada
+    "ml": "nplurals=2; plural=(n != 1);",  # Malayalam
+    "ta": "nplurals=2; plural=(n != 1);",  # Tamil
+    "te": "nplurals=2; plural=(n != 1);",  # Telugu
+    "or": "nplurals=2; plural=(n != 1);",  # Oriya
+    "si": "nplurals=2; plural=(n != 1);",  # Sinhala
+    "ne": "nplurals=2; plural=(n != 1);",  # Nepali
+    "mr": "nplurals=2; plural=(n != 1);",  # Marathi
+    "ur": "nplurals=2; plural=(n != 1);",  # Urdu
+    "az": "nplurals=2; plural=(n != 1);",  # Azerbaijani
+    "uz": "nplurals=2; plural=(n != 1);",  # Uzbek
+    "kk": "nplurals=2; plural=(n != 1);",  # Kazakh
+    "mn": "nplurals=2; plural=(n != 1);",  # Mongolian
+    "sq": "nplurals=2; plural=(n != 1);",  # Albanian
+    "eu": "nplurals=2; plural=(n != 1);",  # Basque
+    "ca": "nplurals=2; plural=(n != 1);",  # Catalan
+    "gl": "nplurals=2; plural=(n != 1);",  # Galician
+    "tr": "nplurals=2; plural=(n != 1);",  # Turkish
+    "af": "nplurals=2; plural=(n != 1);",  # Afrikaans
+    "fil": "nplurals=2; plural=(n != 1);",  # Filipino
+    # Languages with 2 plural forms: plural=(n > 1)
+    "fr": "nplurals=2; plural=(n > 1);",  # French
+    "br": "nplurals=2; plural=(n > 1);",  # Breton
+    # Languages with 3 plural forms
+    "pl": (
+        "nplurals=3; plural=(n==1 ? 0 : n%10>=2 && n%10<=4 && "
+        "(n%100<10 || n%100>=20) ? 1 : 2);"
+    ),  # Polish
+    "ru": (
+        "nplurals=3; plural=(n%10==1 && n%100!=11 ? 0 : n%10>=2 && n%10<=4 && "
+        "(n%100<10 || n%100>=20) ? 1 : 2);"
+    ),  # Russian
+    "uk": (
+        "nplurals=3; plural=(n%10==1 && n%100!=11 ? 0 : n%10>=2 && n%10<=4 && "
+        "(n%100<10 || n%100>=20) ? 1 : 2);"
+    ),  # Ukrainian
+    "be": (
+        "nplurals=3; plural=(n%10==1 && n%100!=11 ? 0 : n%10>=2 && n%10<=4 && "
+        "(n%100<10 || n%100>=20) ? 1 : 2);"
+    ),  # Belarusian
+    "sr": (
+        "nplurals=3; plural=(n%10==1 && n%100!=11 ? 0 : n%10>=2 && n%10<=4 && "
+        "(n%100<10 || n%100>=20) ? 1 : 2);"
+    ),  # Serbian
+    "hr": (
+        "nplurals=3; plural=(n%10==1 && n%100!=11 ? 0 : n%10>=2 && n%10<=4 && "
+        "(n%100<10 || n%100>=20) ? 1 : 2);"
+    ),  # Croatian
+    "bs": (
+        "nplurals=3; plural=(n%10==1 && n%100!=11 ? 0 : n%10>=2 && n%10<=4 && "
+        "(n%100<10 || n%100>=20) ? 1 : 2);"
+    ),  # Bosnian
+    "cs": "nplurals=3; plural=(n==1 ? 0 : (n>=2 && n<=4) ? 1 : 2);",  # Czech
+    "sk": "nplurals=3; plural=(n==1 ? 0 : (n>=2 && n<=4) ? 1 : 2);",  # Slovak
+    "lt": (
+        "nplurals=3; plural=(n%10==1 && n%100!=11 ? 0 : n%10>=2 && "
+        "(n%100<10 || n%100>=20) ? 1 : 2);"
+    ),  # Lithuanian
+    "hy": "nplurals=3; plural=(n==1 ? 0 : n>=2 && n<=4 ? 1 : 2);",  # Armenian
+    "ro": (
+        "nplurals=3; plural=(n==1 ? 0 : (n==0 || (n%100 > 0 && n%100 < 20)) ? 1 : 2);"
+    ),  # Romanian
+    # Languages with 4 plural forms
+    "cy": (
+        "nplurals=4; plural=(n==1 ? 0 : n==2 ? 1 : (n==8 || n==11) ? 2 : 3);"
+    ),  # Welsh
+    "ga": "nplurals=4; plural=(n==1 ? 0 : n==2 ? 1 : (n>2 && n<7) ? 2 : 3);",  # Irish
+    "gd": (
+        "nplurals=4; plural=(n==1 || n==11) ? 0 : (n==2 || n==12) ? 1 : "
+        "(n>2 && n<20) ? 2 : 3);"
+    ),  # Scottish Gaelic
+    "mt": (
+        "nplurals=4; plural=(n==1 ? 0 : n==0 || (n%100>=2 && n%100<=10) ? 1 : "
+        "(n%100>=11 && n%100<=19) ? 2 : 3);"
+    ),  # Maltese
+    # Languages with 6 plural forms
+    "ar": (
+        "nplurals=6; plural=(n==0 ? 0 : n==1 ? 1 : n==2 ? 2 : n%100>=3 && "
+        "n%100<=10 ? 3 : n%100>=11 && n%100<=99 ? 4 : 5);"
+    ),  # Arabic
+    # Other languages
+    "fa": "nplurals=2; plural=(n==0 || n==1 ? 0 : 1);",  # Persian/Farsi
+    "hu": "nplurals=2; plural=(n != 1);",  # Hungarian
+    "bg": "nplurals=2; plural=(n != 1);",  # Bulgarian
+    "am": "nplurals=2; plural=(n > 1);",  # Amharic
+}
+
+# Default plural form fallback (English-style)
+# Used when a language code is not found in PLURAL_FORMS
+DEFAULT_PLURAL_FORM = "nplurals=2; plural=(n != 1);"
+
+# Typo patterns to fix in translation files
+TYPO_PATTERNS = [
+    ("Serch", "Search"),
+]
+
+# Backend PO file names
+BACKEND_PO_FILES = ["django.po", "djangojs.po"]
+
+# PO file header metadata
+PO_HEADER_PROJECT_VERSION = "0.1a"
+PO_HEADER_BUGS_EMAIL = "openedx-translation@googlegroups.com"
+PO_HEADER_POT_CREATION_DATE = "2023-06-13 08:00+0000"
+PO_HEADER_MIME_VERSION = "1.0"
+PO_HEADER_CONTENT_TYPE = "text/plain; charset=UTF-8"
+PO_HEADER_CONTENT_TRANSFER_ENCODING = "8bit"
+PO_HEADER_TRANSIFEX_TEAM_BASE_URL = "https://app.transifex.com/open-edx/teams/6205"
+
+# File and directory names
+TRANSLATION_FILE_NAMES = {
+    "transifex_input": "transifex_input.json",
+    "english": "en.json",
+    "messages_dir": "messages",
+    "i18n_dir": "i18n",
+    "locale_dir": "locale",
+    "lc_messages": "LC_MESSAGES",
+    "conf_dir": "conf",
+    "edx_platform": "edx-platform",
+}
+
+# JSON file formatting
+DEFAULT_JSON_INDENT = 2
+
+# Language code to human-readable name mapping
+# Used in PO file headers for Language-Team field
+LANGUAGE_MAPPING = {
+    "ar": "Arabic",
+    "de": "German",
+    "el": "Greek",
+    "es": "Spanish",
+    "fr": "French",
+    "hi": "Hindi",
+    "id": "Indonesian",
+    "ja": "Japanese",
+    "kr": "Korean",
+    "pt": "Portuguese",
+    "ru": "Russian",
+    "sq": "Albanian",
+    "tr": "Turkish",
+    "zh": "Chinese",
+}
+
+# Maximum number of retries for failed translation batches
+MAX_RETRIES = 3
+
+# Glossary parsing constants
+EXPECTED_GLOSSARY_PARTS = 2  # English term and translation separated by "->"
+
+# HTTP Status Codes
+HTTP_OK = 200
+HTTP_CREATED = 201
+HTTP_NOT_FOUND = 404
+HTTP_TOO_MANY_REQUESTS = 429
+HTTP_UNPROCESSABLE_ENTITY = 422
+
+# Error message length limit
+MAX_ERROR_MESSAGE_LENGTH = 200
+
+ENGLISH_LANGUAGE_CODE = "en"