From 867ece014a79442a4faa3e941ab6e545b0247079 Mon Sep 17 00:00:00 2001
From: Yorgei <reedef@yorgei.dev>
Date: Sat, 30 Aug 2025 20:11:34 +1000
Subject: [PATCH] a

---
 .dockerignore           |  24 ++++++++
 .env                    |  12 ++++
 Dockerfile              |  17 +++++
 README.md               | 103 +++++++++++++++++++++++++++++++
 docker-compose.yml      |  14 +++++
 download_and_compare.py | 133 ++++++++++++++++++++++++++++++++++++++++
 env.example             |  12 ++++
 requirements.txt        |   2 +
 8 files changed, 317 insertions(+)
 create mode 100644 .dockerignore
 create mode 100644 .env
 create mode 100644 Dockerfile
 create mode 100644 README.md
 create mode 100644 docker-compose.yml
 create mode 100644 download_and_compare.py
 create mode 100644 env.example
 create mode 100644 requirements.txt

diff --git a/.dockerignore b/.dockerignore
new file mode 100644
index 0000000..b38e409
--- /dev/null
+++ b/.dockerignore
@@ -0,0 +1,24 @@
+.git
+.env
+*.diff
+*.json
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+env
+pip-log.txt
+pip-delete-this-directory.txt
+.tox
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.log
+.git
+.mypy_cache
+.pytest_cache
+.hypothesis
diff --git a/.env b/.env
new file mode 100644
index 0000000..ddb0ec7
--- /dev/null
+++ b/.env
@@ -0,0 +1,12 @@
+GIT_REPO_URL=https://github.com/yourusername/yourrepo.git
+GIT_USERNAME=yourusername
+GIT_EMAIL=your.email@example.com
+GIT_BRANCH=main
+
+# GitHub Authentication (choose one method):
+# Method 1: Personal Access Token (recommended for HTTPS)
+GITHUB_TOKEN=ghp_your_personal_access_token_here
+
+# Method 2: SSH Key (for SSH URLs)
+# GIT_REPO_URL=git@github.com:yourusername/yourrepo.git
+# SSH_PRIVATE_KEY_PATH=/path/to/your/private/key
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..03f68f5
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,17 @@
+FROM python:3.11-slim
+
+RUN apt-get update && apt-get install -y \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+RUN git config --global user.email "docker@example.com"
+RUN git config --global user.name "Docker Container"
+
+CMD ["python", "download_and_compare.py"]
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..21b3191
--- /dev/null
+++ b/README.md
@@ -0,0 +1,103 @@
+# Language File Download and Compare Docker
+
+This Docker container downloads language JSON files from a specified URL, compares them with existing files, and automatically commits and pushes changes to a Git repository.
+
+## Features
+
+- Downloads language files for multiple languages
+- Compares new files with existing ones
+- Generates diff files for changes
+- Automatically commits and pushes changes to Git
+- Supports 15 languages: en, zh-TW, ja, ko, fr, de, es, it, nl, pl, pt, ru, tr, vi, zh-CN
+
+## Setup
+
+1. Copy `env.example` to `.env` and configure your Git repository:
+   ```bash
+   cp env.example .env
+   ```
+
+2. Edit `.env` with your Git repository details and authentication method:
+
+   **Method 1: Personal Access Token (Recommended)**
+   ```
+   GIT_REPO_URL=https://github.com/yourusername/yourrepo.git
+   GIT_USERNAME=yourusername
+   GIT_EMAIL=your.email@example.com
+   GIT_BRANCH=main
+   GITHUB_TOKEN=ghp_your_personal_access_token_here
+   ```
+
+   **Method 2: SSH Key**
+   ```
+   GIT_REPO_URL=git@github.com:yourusername/yourrepo.git
+   GIT_USERNAME=yourusername
+   GIT_EMAIL=your.email@example.com
+   GIT_BRANCH=main
+   ```
+
+3. Build and run the container:
+   ```bash
+   docker-compose up --build
+   ```
+
+## GitHub Authentication
+
+### Personal Access Token (Recommended)
+1. Go to GitHub → Settings → Developer settings → Personal access tokens
+2. Generate a new token with `repo` scope
+3. Add the token to your `.env` file as `GITHUB_TOKEN`
+4. Use HTTPS URLs: `https://github.com/username/repo.git`
+
+### SSH Key Authentication
+1. Generate SSH key pair: `ssh-keygen -t ed25519 -C "your_email@example.com"`
+2. Add public key to GitHub → Settings → SSH and GPG keys
+3. Use SSH URLs: `git@github.com:username/repo.git`
+4. Mount your private key in docker-compose (see Advanced Configuration)
+
+## Local Testing
+
+For local testing on your machine:
+
+1. Install dependencies:
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+2. Create a `.env` file with your Git configuration (same as above)
+
+3. Run the script locally:
+   ```bash
+   python download_and_compare.py
+   ```
+
+The script will automatically load environment variables from the `.env` file using python-dotenv.
+
+## Usage
+
+The container will:
+1. Download language files from the configured URL
+2. Compare with existing files
+3. Generate diff files for any changes
+4. Commit and push changes to the Git repository
+
+## Files Generated
+
+- `{lang}.json` - Current language files
+- `{lang}.diff` - Diff files showing changes (only when changes detected)
+
+## Environment Variables
+
+- `GIT_REPO_URL` - URL of the Git repository to push to
+- `GIT_USERNAME` - Git username for commits
+- `GIT_EMAIL` - Git email for commits
+- `GIT_BRANCH` - Git branch to use (defaults to 'main')
+
+## Running Manually
+
+To run the script manually outside of Docker:
+```bash
+python download_and_compare.py
+```
+
+The script will automatically load your `.env` file for local testing.
diff --git a/docker-compose.yml b/docker-compose.yml
new file mode 100644
index 0000000..16a4508
--- /dev/null
+++ b/docker-compose.yml
@@ -0,0 +1,14 @@
+version: '3.8'
+
+services:
+  download-compare:
+    build: .
+    environment:
+      - GIT_REPO_URL=${GIT_REPO_URL}
+      - GIT_USERNAME=${GIT_USERNAME}
+      - GIT_EMAIL=${GIT_EMAIL}
+      - GIT_BRANCH=${GIT_BRANCH:-main}
+    volumes:
+      - ./data:/app/data
+      - ./.git:/app/.git
+    working_dir: /app
diff --git a/download_and_compare.py b/download_and_compare.py
new file mode 100644
index 0000000..3a0712c
--- /dev/null
+++ b/download_and_compare.py
@@ -0,0 +1,133 @@
+import requests
+import json
+import os
+import subprocess
+import sys
+from datetime import datetime
+from dotenv import load_dotenv
+
+load_dotenv()
+
+lang_list = ['en','zh-TW','ja', 'ko', 'fr', 'de', 'es', 'it', 'nl', 'pl', 'pt', 'ru', 'tr', 'vi', 'zh-CN']
+
+def run_git_command(command):
+    try:
+        result = subprocess.run(command, shell=True, capture_output=True, text=True, cwd="/app")
+        if result.returncode != 0:
+            print(f"Git command failed: {command}")
+            print(f"Error: {result.stderr}")
+            return False
+        return True
+    except Exception as e:
+        print(f"Error running git command: {e}")
+        return False
+
+def setup_git_repo():
+    git_repo_url = os.environ.get('GIT_REPO_URL')
+    git_username = os.environ.get('GIT_USERNAME')
+    git_email = os.environ.get('GIT_EMAIL')
+    git_branch = os.environ.get('GIT_BRANCH', 'main')
+    github_token = os.environ.get('GITHUB_TOKEN')
+    
+    if not all([git_repo_url, git_username, git_email]):
+        print("Git environment variables not set. Skipping Git operations.")
+        return False
+    
+    if not os.path.exists("/app/.git"):
+        print("Initializing Git repository...")
+        if not run_git_command("git init"):
+            return False
+        
+        if github_token and git_repo_url.startswith('https://'):
+            print("Using GitHub Personal Access Token for authentication...")
+            auth_url = git_repo_url.replace('https://', f'https://{git_username}:{github_token}@')
+            if not run_git_command(f"git remote add origin {auth_url}"):
+                return False
+        else:
+            if not run_git_command(f"git remote add origin {git_repo_url}"):
+                return False
+        
+        if not run_git_command(f"git checkout -b {git_branch}"):
+            return False
+    
+    run_git_command(f"git config user.name '{git_username}'")
+    run_git_command(f"git config user.email '{git_email}'")
+    
+    if github_token:
+        run_git_command("git config credential.helper store")
+    
+    return True
+
+def commit_and_push_changes():
+    if not os.path.exists("/app/.git"):
+        return False
+    
+    try:
+        run_git_command("git add .")
+        run_git_command("git commit -m 'Update language files'")
+        run_git_command("git push origin HEAD")
+        print("Changes committed and pushed to Git repository")
+        return True
+    except Exception as e:
+        print(f"Error pushing to Git: {e}")
+        return False
+
+def download_and_compare_json(lang):
+    url = f"https://highschool.stg.g123-cpp.com/1/g123/i18n/{lang}/texts/source_schooltest_1.json"
+    
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+        new_data = response.json()
+    except requests.RequestException as e:
+        print(f"Error downloading JSON: {e}")
+        return
+    except json.JSONDecodeError as e:
+        print(f"Error parsing JSON: {e}")
+        return
+    
+    old_data = {}
+    if os.path.exists(f"{lang}.json"):
+        try:
+            with open(f"{lang}.json", "r", encoding="utf-8") as f:
+                old_data = json.load(f)
+        except (json.JSONDecodeError, FileNotFoundError):
+            print(f"Warning: Could not read existing {lang}.json, treating as empty")
+    
+    diff_lines = []
+    diff_lines.append(f"--- {lang}.json")
+    diff_lines.append(f"+++ {lang}.json")
+    diff_lines.append("")
+    
+    all_keys = sorted(set(old_data.keys()) | set(new_data.keys()))
+    
+    for key in all_keys:
+        if key not in old_data:
+            diff_lines.append(f"+{key}: {json.dumps(new_data[key], ensure_ascii=False)}")
+        elif key not in new_data:
+            diff_lines.append(f"-{key}: {json.dumps(old_data[key], ensure_ascii=False)}")
+        elif old_data[key] != new_data[key]:
+            diff_lines.append(f"-{key}: {json.dumps(old_data[key], ensure_ascii=False)}")
+            diff_lines.append(f"+{key}: {json.dumps(new_data[key], ensure_ascii=False)}")
+    
+    with open(f"{lang}.json", "w", encoding="utf-8") as f:
+        json.dump(new_data, f, indent=2, ensure_ascii=False)
+    
+    if len(diff_lines) > 3:
+        with open(f"{lang}.diff", "w", encoding="utf-8") as f:
+            f.write("\n".join(diff_lines))
+        print(f"Changes detected: {len(diff_lines) - 3} lines affected")
+        print(f"Diff saved to {lang}.diff")
+    else:
+        print("No changes detected")
+    
+    print(f"New data saved to {lang}.json ({len(new_data)} keys)")
+
+if __name__ == "__main__":
+    git_enabled = setup_git_repo()
+    
+    for lang in lang_list:
+        download_and_compare_json(lang)
+    
+    if git_enabled:
+        commit_and_push_changes()
diff --git a/env.example b/env.example
new file mode 100644
index 0000000..ddb0ec7
--- /dev/null
+++ b/env.example
@@ -0,0 +1,12 @@
+GIT_REPO_URL=https://github.com/yourusername/yourrepo.git
+GIT_USERNAME=yourusername
+GIT_EMAIL=your.email@example.com
+GIT_BRANCH=main
+
+# GitHub Authentication (choose one method):
+# Method 1: Personal Access Token (recommended for HTTPS)
+GITHUB_TOKEN=ghp_your_personal_access_token_here
+
+# Method 2: SSH Key (for SSH URLs)
+# GIT_REPO_URL=git@github.com:yourusername/yourrepo.git
+# SSH_PRIVATE_KEY_PATH=/path/to/your/private/key
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..2b1be2a
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,2 @@
+requests>=2.31.0
+python-dotenv>=1.0.0