lanyuanxiaoyao
e0c6ed1638
- 提取 LibreOffice 解析逻辑为公共工具函数 _utils.parse_via_libreoffice() - 新增 DocReader 独立 Reader，支持 .doc 格式 - 新增 is_valid_doc() 文件验证函数（复用 OLE2 检测） - 新增 doc 格式依赖配置（独立配置） - 新增完整的测试套件，使用静态测试文件 - 更新 README.md 和 SKILL.md，添加 .doc 格式支持说明 - 新增 openspec/specs/doc-reader/spec.md 规范文档 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
280 lines
8.4 KiB
Python
280 lines
8.4 KiB
Python
"""Reader 内部共享工具模块。
|
|
|
|
此模块包含各 reader 实现共享的内部工具函数，仅供 readers 包内部使用。
|
|
"""
|
|
|
|
import re
|
|
import subprocess
|
|
import tempfile
|
|
import shutil
|
|
import zipfile
|
|
from pathlib import Path
|
|
from typing import List, Optional, Tuple
|
|
|
|
|
|
# ============================================================================
|
|
# 通用解析器包装函数
|
|
# ============================================================================
|
|
|
|
def parse_via_markitdown(
|
|
file_path: str,
|
|
) -> Tuple[Optional[str], Optional[str]]:
|
|
"""使用 MarkItDown 库解析文件。
|
|
|
|
Args:
|
|
file_path: 文件路径
|
|
|
|
Returns:
|
|
(markdown_content, error_message): 成功时 (content, None)，失败时 (None, error)
|
|
"""
|
|
try:
|
|
from markitdown import MarkItDown
|
|
|
|
md = MarkItDown()
|
|
result = md.convert(file_path)
|
|
if not result.text_content.strip():
|
|
return None, "文档为空"
|
|
return result.text_content, None
|
|
except ImportError:
|
|
return None, "MarkItDown 库未安装"
|
|
except Exception as e:
|
|
return None, f"MarkItDown 解析失败: {str(e)}"
|
|
|
|
|
|
def parse_via_docling(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
|
"""使用 docling 库解析文件。
|
|
|
|
Args:
|
|
file_path: 文件路径
|
|
|
|
Returns:
|
|
(markdown_content, error_message): 成功时 (content, None)，失败时 (None, error)
|
|
"""
|
|
try:
|
|
from docling.document_converter import DocumentConverter
|
|
except ImportError:
|
|
return None, "docling 库未安装"
|
|
|
|
try:
|
|
converter = DocumentConverter()
|
|
result = converter.convert(file_path)
|
|
markdown_content = result.document.export_to_markdown()
|
|
if not markdown_content.strip():
|
|
return None, "文档为空"
|
|
return markdown_content, None
|
|
except Exception as e:
|
|
return None, f"docling 解析失败: {str(e)}"
|
|
|
|
|
|
def parse_via_libreoffice(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
|
"""使用 LibreOffice soffice 命令行转换文件为 Markdown。
|
|
|
|
支持 .doc/.docx/.odt 等 LibreOffice 可处理的格式。
|
|
|
|
Args:
|
|
file_path: 文件路径
|
|
|
|
Returns:
|
|
(markdown_content, error_message): 成功时 (content, None)，失败时 (None, error)
|
|
"""
|
|
# 检测 soffice 是否在 PATH 中
|
|
soffice_path = shutil.which("soffice")
|
|
if not soffice_path:
|
|
return None, "LibreOffice 未安装"
|
|
|
|
# 创建临时输出目录
|
|
with tempfile.TemporaryDirectory() as temp_dir:
|
|
temp_path = Path(temp_dir)
|
|
input_path = Path(file_path)
|
|
expected_output = temp_path / (input_path.stem + ".md")
|
|
|
|
# 构建命令
|
|
cmd = [
|
|
soffice_path,
|
|
"--headless",
|
|
"--convert-to", "md",
|
|
"--outdir", str(temp_path),
|
|
str(input_path)
|
|
]
|
|
|
|
# 执行命令，超时 60 秒
|
|
try:
|
|
result = subprocess.run(
|
|
cmd,
|
|
capture_output=True,
|
|
text=True,
|
|
timeout=60
|
|
)
|
|
except subprocess.TimeoutExpired:
|
|
return None, "LibreOffice 转换超时 (60秒)"
|
|
|
|
# 检查返回码
|
|
if result.returncode != 0:
|
|
return None, f"LibreOffice 转换失败 (code: {result.returncode})"
|
|
|
|
# 检查输出文件是否存在
|
|
output_file = None
|
|
if expected_output.exists():
|
|
output_file = expected_output
|
|
else:
|
|
# Fallback: 遍历目录找任意 .md 文件
|
|
md_files = list(temp_path.glob("*.md"))
|
|
if md_files:
|
|
output_file = md_files[0]
|
|
|
|
if not output_file:
|
|
return None, "LibreOffice 未生成输出文件"
|
|
|
|
# 读取输出内容
|
|
content = output_file.read_text(encoding="utf-8", errors="replace")
|
|
content = content.strip()
|
|
|
|
if not content:
|
|
return None, "LibreOffice 输出为空"
|
|
|
|
return content, None
|
|
|
|
|
|
# ============================================================================
|
|
# 格式化工具
|
|
# ============================================================================
|
|
|
|
def build_markdown_table(rows_data: List[List[str]]) -> str:
|
|
"""将二维列表格式化为 Markdown 表格。
|
|
|
|
Args:
|
|
rows_data: 二维列表，第一行为表头
|
|
|
|
Returns:
|
|
Markdown 格式的表格字符串
|
|
"""
|
|
if not rows_data or not rows_data[0]:
|
|
return ""
|
|
|
|
md_lines = []
|
|
for i, row_data in enumerate(rows_data):
|
|
row_text = [cell if cell else "" for cell in row_data]
|
|
md_lines.append("| " + " | ".join(row_text) + " |")
|
|
if i == 0:
|
|
md_lines.append("| " + " | ".join(["---"] * len(row_text)) + " |")
|
|
return "\n".join(md_lines) + "\n\n"
|
|
|
|
|
|
# ============================================================================
|
|
# 列表处理工具
|
|
# ============================================================================
|
|
|
|
def flush_list_stack(list_stack: List[str], target: List[str]) -> None:
|
|
"""将列表堆栈中的非空项添加到目标列表并清空堆栈。
|
|
|
|
用于处理嵌套列表的格式化输出。
|
|
|
|
Args:
|
|
list_stack: 列表堆栈
|
|
target: 目标列表
|
|
"""
|
|
for item in list_stack:
|
|
if item:
|
|
target.append(item + "\n")
|
|
list_stack.clear()
|
|
|
|
|
|
# ============================================================================
|
|
# ZIP 文件安全处理
|
|
# ============================================================================
|
|
|
|
def safe_open_zip(zip_file: zipfile.ZipFile, name: str) -> Optional[zipfile.ZipExtFile]:
|
|
"""安全地从 ZipFile 中打开文件，防止路径遍历攻击。
|
|
|
|
Args:
|
|
zip_file: ZipFile 对象
|
|
name: 文件名
|
|
|
|
Returns:
|
|
ZipExtFile 对象，如果路径不安全则返回 None
|
|
"""
|
|
if not name:
|
|
return None
|
|
|
|
try:
|
|
normalized = Path(name).as_posix()
|
|
# 检查是否包含父目录引用
|
|
if ".." in Path(normalized).parts:
|
|
return None
|
|
# 检查是否为绝对路径
|
|
if Path(normalized).is_absolute():
|
|
return None
|
|
return zip_file.open(name)
|
|
except (ValueError, OSError, KeyError):
|
|
return None
|
|
|
|
|
|
# ============================================================================
|
|
# unstructured 库相关
|
|
# ============================================================================
|
|
|
|
# unstructured 噪声匹配模式
|
|
_UNSTRUCTURED_RGB_PATTERN = re.compile(r"^R:\d+\s+G:\d+\s+B:\d+$")
|
|
_UNSTRUCTURED_PAGE_NUMBER_PATTERN = re.compile(r"^—\s*\d+\s*—$")
|
|
|
|
|
|
def convert_unstructured_to_markdown(
|
|
elements: list, trust_titles: bool = True
|
|
) -> str:
|
|
"""将 unstructured 解析出的元素列表转换为 Markdown 文本。
|
|
|
|
Args:
|
|
elements: unstructured 解析的元素列表
|
|
trust_titles: 是否信任 unstructured 的标题检测
|
|
|
|
Returns:
|
|
Markdown 格式的文本
|
|
"""
|
|
try:
|
|
import markdownify as md_lib
|
|
from unstructured.documents.elements import (
|
|
Footer,
|
|
Header,
|
|
Image,
|
|
ListItem,
|
|
PageBreak,
|
|
PageNumber,
|
|
Table,
|
|
Title,
|
|
)
|
|
except ImportError:
|
|
return "\n\n".join(
|
|
el.text for el in elements if hasattr(el, "text") and el.text and el.text.strip()
|
|
)
|
|
|
|
skip_types = (Header, Footer, PageBreak, PageNumber)
|
|
parts = []
|
|
|
|
for el in elements:
|
|
if isinstance(el, skip_types):
|
|
continue
|
|
text = el.text.strip() if hasattr(el, "text") else str(el).strip()
|
|
if not text or _UNSTRUCTURED_RGB_PATTERN.match(text) or _UNSTRUCTURED_PAGE_NUMBER_PATTERN.match(text):
|
|
continue
|
|
|
|
if isinstance(el, Table):
|
|
html = getattr(el.metadata, "text_as_html", None)
|
|
if html:
|
|
parts.append(md_lib.markdownify(html, strip=["img"]).strip())
|
|
else:
|
|
parts.append(str(el))
|
|
elif isinstance(el, Title) and trust_titles:
|
|
depth = getattr(el.metadata, "category_depth", None) or 1
|
|
depth = min(max(depth, 1), 4)
|
|
parts.append(f"{'#' * depth} {text}")
|
|
elif isinstance(el, ListItem):
|
|
parts.append(f"- {text}")
|
|
elif isinstance(el, Image):
|
|
path = getattr(el.metadata, "image_path", None) or ""
|
|
if path:
|
|
parts.append(f"")
|
|
else:
|
|
parts.append(text)
|
|
|
|
return "\n\n".join(parts)
|