feat: 添加自启动机制，移除 --advice 参数
- 创建 bootstrap.py 承载实际 CLI 逻辑 - 重写 lyxy_document_reader.py 为轻量入口，自动检测依赖并启动 - 使用 subprocess.run() 实现跨平台兼容的自启动 - 移除 --advice 参数及相关测试 - 更新文档和规范，简化使用方式
This commit is contained in:
111
scripts/bootstrap.py
Normal file
111
scripts/bootstrap.py
Normal file
@@ -0,0 +1,111 @@
|
||||
#!/usr/bin/env python3
|
||||
"""文档解析器实际执行模块，承载业务逻辑。"""
|
||||
|
||||
import argparse
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
import warnings
|
||||
from pathlib import Path
|
||||
|
||||
# 将 scripts/ 目录添加到 sys.path，支持从任意位置执行脚本
|
||||
scripts_dir = Path(__file__).resolve().parent
|
||||
if str(scripts_dir) not in sys.path:
|
||||
sys.path.append(str(scripts_dir))
|
||||
|
||||
# 抑制第三方库的进度条和日志，仅保留解析结果输出
|
||||
os.environ["HF_HUB_DISABLE_PROGRESS_BARS"] = "1"
|
||||
os.environ["HF_HUB_DISABLE_TELEMETRY"] = "1"
|
||||
os.environ["TQDM_DISABLE"] = "1"
|
||||
warnings.filterwarnings("ignore")
|
||||
|
||||
# 配置日志系统，只输出 ERROR 级别
|
||||
logging.basicConfig(level=logging.ERROR, format='%(levelname)s: %(message)s')
|
||||
|
||||
# 设置第三方库日志等级
|
||||
logging.getLogger('docling').setLevel(logging.ERROR)
|
||||
logging.getLogger('unstructured').setLevel(logging.ERROR)
|
||||
|
||||
from core import (
|
||||
FileDetectionError,
|
||||
ReaderNotFoundError,
|
||||
output_result,
|
||||
parse_input,
|
||||
process_content,
|
||||
)
|
||||
from readers import READERS
|
||||
|
||||
|
||||
def run_normal(args) -> None:
|
||||
"""正常执行模式：解析文件并输出结果"""
|
||||
# 实例化所有 readers
|
||||
readers = [ReaderCls() for ReaderCls in READERS]
|
||||
|
||||
try:
|
||||
content, failures = parse_input(args.input_path, readers)
|
||||
except FileDetectionError as e:
|
||||
print(f"错误: {e}")
|
||||
sys.exit(1)
|
||||
except ReaderNotFoundError as e:
|
||||
print(f"错误: {e}")
|
||||
sys.exit(1)
|
||||
|
||||
if content is None:
|
||||
print("所有解析方法均失败:")
|
||||
for failure in failures:
|
||||
print(failure)
|
||||
sys.exit(1)
|
||||
|
||||
# 处理内容
|
||||
content = process_content(content)
|
||||
|
||||
# 输出结果
|
||||
output_result(content, args)
|
||||
|
||||
|
||||
def main() -> None:
|
||||
"""主函数：解析命令行参数并执行"""
|
||||
parser = argparse.ArgumentParser(
|
||||
description="将 DOCX、XLS、XLSX、PPTX、PDF、HTML 文件或 URL 解析为 Markdown"
|
||||
)
|
||||
|
||||
parser.add_argument("input_path", help="DOCX、XLS、XLSX、PPTX、PDF、HTML 文件或 URL")
|
||||
|
||||
parser.add_argument(
|
||||
"-n",
|
||||
"--context",
|
||||
type=int,
|
||||
default=2,
|
||||
help="与 -s 配合使用，指定每个检索结果包含的前后行数（不包含空行）",
|
||||
)
|
||||
|
||||
group = parser.add_mutually_exclusive_group()
|
||||
group.add_argument(
|
||||
"-c", "--count", action="store_true", help="返回解析后的 markdown 文档的总字数"
|
||||
)
|
||||
group.add_argument(
|
||||
"-l", "--lines", action="store_true", help="返回解析后的 markdown 文档的总行数"
|
||||
)
|
||||
group.add_argument(
|
||||
"-t",
|
||||
"--titles",
|
||||
action="store_true",
|
||||
help="返回解析后的 markdown 文档的标题行（1-6级）",
|
||||
)
|
||||
group.add_argument(
|
||||
"-tc",
|
||||
"--title-content",
|
||||
help="指定标题名称，输出该标题及其下级内容（不包含#号）",
|
||||
)
|
||||
group.add_argument(
|
||||
"-s",
|
||||
"--search",
|
||||
help="使用正则表达式搜索文档，返回所有匹配结果（用---分隔）",
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
run_normal(args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,56 +1,31 @@
|
||||
#!/usr/bin/env python3
|
||||
"""文档解析器命令行交互模块，提供命令行接口。支持 DOCX、XLS、XLSX、PPTX、PDF、HTML 和 URL。"""
|
||||
"""文档解析器入口 - 环境检测和自启动"""
|
||||
|
||||
import argparse
|
||||
import logging
|
||||
import os
|
||||
import shutil
|
||||
import subprocess
|
||||
import sys
|
||||
import warnings
|
||||
from pathlib import Path
|
||||
|
||||
# 将 scripts/ 目录添加到 sys.path，支持从任意位置执行脚本
|
||||
# 将 scripts/ 目录添加到 sys.path
|
||||
scripts_dir = Path(__file__).resolve().parent
|
||||
if str(scripts_dir) not in sys.path:
|
||||
sys.path.append(str(scripts_dir))
|
||||
|
||||
# 抑制第三方库的进度条和日志，仅保留解析结果输出
|
||||
# 抑制第三方库日志
|
||||
os.environ["HF_HUB_DISABLE_PROGRESS_BARS"] = "1"
|
||||
os.environ["HF_HUB_DISABLE_TELEMETRY"] = "1"
|
||||
os.environ["TQDM_DISABLE"] = "1"
|
||||
warnings.filterwarnings("ignore")
|
||||
|
||||
# 配置日志系统，只输出 ERROR 级别
|
||||
logging.basicConfig(level=logging.ERROR, format='%(levelname)s: %(message)s')
|
||||
|
||||
# 设置第三方库日志等级
|
||||
logging.getLogger('docling').setLevel(logging.ERROR)
|
||||
logging.getLogger('unstructured').setLevel(logging.ERROR)
|
||||
|
||||
from core import (
|
||||
FileDetectionError,
|
||||
ReaderNotFoundError,
|
||||
output_result,
|
||||
parse_input,
|
||||
process_content,
|
||||
generate_advice,
|
||||
)
|
||||
from readers import READERS
|
||||
|
||||
|
||||
def main() -> None:
|
||||
def main():
|
||||
"""主函数：环境检测和决策"""
|
||||
# 解析命令行参数（轻量，仅识别必要参数）
|
||||
parser = argparse.ArgumentParser(
|
||||
description="将 DOCX、XLS、XLSX、PPTX、PDF、HTML 文件或 URL 解析为 Markdown"
|
||||
)
|
||||
|
||||
parser.add_argument("input_path", help="DOCX、XLS、XLSX、PPTX、PDF、HTML 文件或 URL")
|
||||
|
||||
parser.add_argument(
|
||||
"-a",
|
||||
"--advice",
|
||||
action="store_true",
|
||||
help="仅显示执行建议，不实际解析文件",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"-n",
|
||||
"--context",
|
||||
@@ -58,7 +33,6 @@ def main() -> None:
|
||||
default=2,
|
||||
help="与 -s 配合使用，指定每个检索结果包含的前后行数（不包含空行）",
|
||||
)
|
||||
|
||||
group = parser.add_mutually_exclusive_group()
|
||||
group.add_argument(
|
||||
"-c", "--count", action="store_true", help="返回解析后的 markdown 文档的总字数"
|
||||
@@ -85,39 +59,64 @@ def main() -> None:
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
# 实例化所有 readers
|
||||
readers = [ReaderCls() for ReaderCls in READERS]
|
||||
# 检测 uv 是否可用
|
||||
uv_path = shutil.which("uv")
|
||||
|
||||
# --advice 模式：仅显示建议，不解析
|
||||
if args.advice:
|
||||
advice = generate_advice(args.input_path, readers, "scripts/lyxy_document_reader.py")
|
||||
if advice:
|
||||
print(advice)
|
||||
else:
|
||||
print(f"错误: 无法识别文件类型: {args.input_path}")
|
||||
sys.exit(1)
|
||||
if not uv_path:
|
||||
# uv 不可用，降级为直接执行 bootstrap.py
|
||||
import bootstrap
|
||||
bootstrap.run_normal(args)
|
||||
return
|
||||
|
||||
try:
|
||||
content, failures = parse_input(args.input_path, readers)
|
||||
except FileDetectionError as e:
|
||||
print(f"错误: {e}")
|
||||
sys.exit(1)
|
||||
except ReaderNotFoundError as e:
|
||||
print(f"错误: {e}")
|
||||
sys.exit(1)
|
||||
# uv 可用，需要自启动
|
||||
# 导入依赖检测模块
|
||||
from config import DEPENDENCIES
|
||||
from core.advice_generator import (
|
||||
detect_file_type_light,
|
||||
get_platform,
|
||||
get_dependencies,
|
||||
)
|
||||
from readers import READERS
|
||||
|
||||
if content is None:
|
||||
print("所有解析方法均失败:")
|
||||
for failure in failures:
|
||||
print(failure)
|
||||
sys.exit(1)
|
||||
# 检测文件类型
|
||||
readers = [ReaderCls() for ReaderCls in READERS]
|
||||
reader_cls = detect_file_type_light(args.input_path, readers)
|
||||
|
||||
# 处理内容
|
||||
content = process_content(content)
|
||||
if not reader_cls:
|
||||
# 无法识别文件类型，降级执行让它报错
|
||||
import bootstrap
|
||||
bootstrap.run_normal(args)
|
||||
return
|
||||
|
||||
# 输出结果
|
||||
output_result(content, args)
|
||||
# 获取平台和依赖配置
|
||||
platform_id = get_platform()
|
||||
python_version, dependencies = get_dependencies(reader_cls, platform_id)
|
||||
|
||||
# 生成 uv 命令参数列表
|
||||
uv_args = ["uv", "run"]
|
||||
|
||||
if python_version:
|
||||
uv_args.extend(["--python", python_version])
|
||||
|
||||
# 始终添加 pyarmor 依赖（混淆后脚本需要）
|
||||
uv_args.extend(["--with", "pyarmor"])
|
||||
|
||||
for dep in dependencies:
|
||||
uv_args.extend(["--with", dep])
|
||||
|
||||
# 目标脚本是 bootstrap.py
|
||||
uv_args.append("scripts/bootstrap.py")
|
||||
|
||||
# 添加所有命令行参数
|
||||
uv_args.extend(sys.argv[1:])
|
||||
|
||||
# 设置环境变量
|
||||
env = os.environ.copy()
|
||||
env["PYTHONPATH"] = "."
|
||||
|
||||
# 自启动：使用 subprocess 替代 execvpe（Windows 兼容）
|
||||
result = subprocess.run(uv_args, env=env)
|
||||
sys.exit(result.returncode)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Reference in New Issue
Block a user