egg/OCR
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: consolidate env config and add deployment files

Browse Source 
- Add debug_font_path, demo_docs_dir, e2e_api_base_url to config.py
- Fix hardcoded paths in pp_structure_debug.py, create_demo_images.py
- Fix hardcoded paths in test files
- Update .env.example with new configuration options
- Update .gitignore to exclude AI development files (.claude/, openspec/, AGENTS.md, CLAUDE.md)
- Add production startup script (start-prod.sh)
- Add README.md with project documentation
- Add 1panel Docker deployment files (docker-compose.yml, Dockerfiles, nginx.conf)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
egg
2025-12-14 15:02:16 +08:00
parent 858d93155f
commit 86a6633000
31 changed files with 1177 additions and 252 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
backend/app/core/config.py
View File

@@ -7,21 +7,43 @@ from typing import List, Optional
from pydantic_settings import BaseSettings
from pydantic import Field, model_validator
from pathlib import Path
import platform
from shutil import which
# Anchor all default paths to the backend directory to avoid scattering runtime folders
BACKEND_ROOT = Path(__file__).resolve().parent.parent.parent
PROJECT_ROOT = BACKEND_ROOT.parent
def _default_pandoc_path() -> str:
return which("pandoc") or "/usr/bin/pandoc"
def _default_font_dir() -> str:
candidates = []
system = platform.system()
if system == "Darwin":
candidates.extend(["/System/Library/Fonts", "/Library/Fonts"])
elif system == "Windows":
candidates.append(r"C:\Windows\Fonts")
else:
candidates.extend(["/usr/share/fonts", "/usr/local/share/fonts"])
for path in candidates:
if Path(path).exists():
return path
return candidates[0] if candidates else ""
class Settings(BaseSettings):
"""Application settings loaded from environment variables"""
# ===== Database Configuration =====
mysql_host: str = Field(default="mysql.theaken.com")
mysql_port: int = Field(default=33306)
mysql_user: str = Field(default="A060")
mysql_host: str = Field(default="localhost")
mysql_port: int = Field(default=3306)
mysql_user: str = Field(default="")
mysql_password: str = Field(default="")
mysql_database: str = Field(default="db_A060")
mysql_database: str = Field(default="")
@property
def database_url(self) -> str:
@@ -32,14 +54,16 @@ class Settings(BaseSettings):
)
# ===== Application Configuration =====
backend_host: str = Field(default="0.0.0.0")
backend_port: int = Field(default=8000)
frontend_host: str = Field(default="0.0.0.0")
frontend_port: int = Field(default=5173)
secret_key: str = Field(default="your-secret-key-change-this")
algorithm: str = Field(default="HS256")
access_token_expire_minutes: int = Field(default=1440) # 24 hours
# ===== External Authentication Configuration =====
external_auth_api_url: str = Field(default="https://pj-auth-api.vercel.app")
external_auth_api_url: str = Field(default="https://your-auth-api.example.com")
external_auth_endpoint: str = Field(default="/api/auth/login")
external_auth_timeout: int = Field(default=30)
token_refresh_buffer: int = Field(default=300) # Refresh tokens 5 minutes before expiry
@@ -441,8 +465,8 @@ class Settings(BaseSettings):
result_dir: str = Field(default=str(BACKEND_ROOT / "storage" / "results"))
# ===== PDF Generation Configuration =====
pandoc_path: str = Field(default="/opt/homebrew/bin/pandoc")
font_dir: str = Field(default="/System/Library/Fonts")
pandoc_path: str = Field(default_factory=_default_pandoc_path)
font_dir: str = Field(default_factory=_default_font_dir)
pdf_page_size: str = Field(default="A4")
pdf_margin_top: int = Field(default=20)
pdf_margin_bottom: int = Field(default=20)
@@ -456,7 +480,7 @@ class Settings(BaseSettings):
# ===== Translation Configuration (DIFY API) =====
enable_translation: bool = Field(default=True)
dify_base_url: str = Field(default="https://dify.theaken.com/v1")
dify_base_url: str = Field(default="https://your-dify-instance.example.com/v1")
dify_api_key: str = Field(default="") # Required: set in .env.local
dify_timeout: float = Field(default=120.0) # seconds
dify_max_retries: int = Field(default=3)
@@ -487,6 +511,23 @@ class Settings(BaseSettings):
log_level: str = Field(default="INFO")
log_file: str = Field(default=str(BACKEND_ROOT / "logs" / "app.log"))
# ===== Development & Testing Configuration =====
# Debug font path for visualization scripts (pp_structure_debug, create_demo_images)
debug_font_path: str = Field(
default="/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf",
description="Font path for debug visualization scripts"
)
# Demo documents directory for testing
demo_docs_dir: str = Field(
default=str(PROJECT_ROOT / "demo_docs"),
description="Directory containing demo documents for testing"
)
# E2E test API base URL
e2e_api_base_url: str = Field(
default="http://localhost:8000/api/v2",
description="Base URL for E2E tests"
)
@model_validator(mode="after")
def _normalize_paths(self):
"""Resolve all runtime paths to backend-rooted absolutes"""

2
backend/app/main.py
View File

@@ -530,7 +530,7 @@ if __name__ == "__main__":
uvicorn.run(
"app.main:app",
host="0.0.0.0",
host=settings.backend_host,
port=settings.backend_port,
reload=True,
log_level=settings.log_level.lower(),

32
backend/app/services/memory_manager.py
View File

@@ -1336,31 +1336,31 @@ class PriorityOperationQueue:
# Wait for an item
if not self._queue:
if timeout is not None:
result = self._condition.wait_for(
lambda: len(self._queue) > 0,
timeout=timeout
)
result = self._condition.wait_for(lambda: len(self._queue) > 0, timeout=timeout)
if not result:
return None
else:
return None
# Get highest priority item
neg_priority, _, item_id, data = heapq.heappop(self._queue)
priority = BatchPriority(-neg_priority)
# Keep popping until we find a non-cancelled item (or queue is exhausted)
while self._queue:
neg_priority, _, item_id, data = heapq.heappop(self._queue)
priority = BatchPriority(-neg_priority)
# Skip if cancelled
if item_id in self._cancelled:
self._cancelled.discard(item_id)
self._total_cancelled += 1
if item_id in self._cancelled:
self._cancelled.discard(item_id)
self._total_cancelled += 1
self._condition.notify()
continue
self._total_dequeued += 1
self._condition.notify()
return self.dequeue(timeout=0) # Try next item
logger.debug(f"Dequeued operation {item_id} with priority {priority.name}")
return item_id, data, priority
self._total_dequeued += 1
self._condition.notify()
return None
logger.debug(f"Dequeued operation {item_id} with priority {priority.name}")
return item_id, data, priority
return None
def cancel(self, item_id: str) -> bool:
"""

10
backend/app/services/pp_structure_debug.py
View File

@@ -16,6 +16,7 @@ from datetime import datetime
from PIL import Image, ImageDraw, ImageFont
from app.utils.bbox_utils import normalize_bbox
from app.core.config import BACKEND_ROOT, settings
logger = logging.getLogger(__name__)
@@ -186,12 +187,13 @@ class PPStructureDebug:
# Try to load a font, fall back to default
try:
font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", 14)
small_font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", 10)
font = ImageFont.truetype(settings.debug_font_path, 14)
small_font = ImageFont.truetype(settings.debug_font_path, 10)
except (IOError, OSError):
try:
font = ImageFont.truetype("/home/egg/project/Tool_OCR/backend/fonts/NotoSansSC-Regular.ttf", 14)
small_font = ImageFont.truetype("/home/egg/project/Tool_OCR/backend/fonts/NotoSansSC-Regular.ttf", 10)
noto_font = BACKEND_ROOT / "fonts" / "NotoSansSC-Regular.ttf"
font = ImageFont.truetype(str(noto_font), 14)
small_font = ImageFont.truetype(str(noto_font), 10)
except (IOError, OSError):
font = ImageFont.load_default()
small_font = font