refactor: 重构 Reader 内部工具函数到独立模块
- 新增 scripts/readers/_utils.py 作为 Reader 内部共享工具模块 - 将 parse_with_markitdown 等函数从 core/markdown.py 迁移到 _utils.py - 函数重命名：parse_with_xxx → parse_via_xxx，_unstructured_elements_to_markdown → convert_unstructured_to_markdown - 更新 17 个 Reader 实现文件的 import 路径 - 从 core/__init__.py 移除已迁移函数的导出 - 新增测试文件 tests/test_readers/test_utils.py - 新增 spec 文档 openspec/specs/reader-internal-utils/spec.md 这次重构明确了模块边界：core/ 提供公共 API，readers/_utils.py 提供 Reader 内部工具
This commit is contained in:
@@ -8,18 +8,12 @@ from .exceptions import (
|
||||
DownloadError,
|
||||
)
|
||||
from .markdown import (
|
||||
parse_with_markitdown,
|
||||
parse_with_docling,
|
||||
build_markdown_table,
|
||||
flush_list_stack,
|
||||
safe_open_zip,
|
||||
normalize_markdown_whitespace,
|
||||
remove_markdown_images,
|
||||
get_heading_level,
|
||||
extract_titles,
|
||||
extract_title_content,
|
||||
search_markdown,
|
||||
_unstructured_elements_to_markdown,
|
||||
)
|
||||
from .parser import parse_input, process_content, output_result
|
||||
|
||||
@@ -29,18 +23,12 @@ __all__ = [
|
||||
"ReaderNotFoundError",
|
||||
"ParseError",
|
||||
"DownloadError",
|
||||
"parse_with_markitdown",
|
||||
"parse_with_docling",
|
||||
"build_markdown_table",
|
||||
"flush_list_stack",
|
||||
"safe_open_zip",
|
||||
"normalize_markdown_whitespace",
|
||||
"remove_markdown_images",
|
||||
"get_heading_level",
|
||||
"extract_titles",
|
||||
"extract_title_content",
|
||||
"search_markdown",
|
||||
"_unstructured_elements_to_markdown",
|
||||
"parse_input",
|
||||
"process_content",
|
||||
"output_result",
|
||||
|
||||
@@ -1,94 +1,11 @@
|
||||
"""Markdown 后处理模块，包含所有格式共享的工具函数。"""
|
||||
"""Markdown 后处理模块，包含 Markdown 格式化的工具函数。"""
|
||||
|
||||
import re
|
||||
import zipfile
|
||||
from pathlib import Path
|
||||
from typing import List, Optional, Tuple
|
||||
from typing import List, Optional
|
||||
|
||||
IMAGE_PATTERN = re.compile(r"!\[[^\]]*\]\([^)]+\)")
|
||||
_CONSECUTIVE_BLANK_LINES = re.compile(r"\n{3,}")
|
||||
|
||||
# unstructured 噪声匹配: pptx 中的 RGB 颜色值（如 "R:255 G:128 B:0"）
|
||||
_RGB_PATTERN = re.compile(r"^R:\d+\s+G:\d+\s+B:\d+$")
|
||||
# unstructured 噪声匹配: 破折号页码（如 "— 3 —"）
|
||||
_PAGE_NUMBER_PATTERN = re.compile(r"^—\s*\d+\s*—$")
|
||||
|
||||
|
||||
def parse_with_markitdown(
|
||||
file_path: str,
|
||||
) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 MarkItDown 库解析文件"""
|
||||
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_with_docling(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 docling 库解析文件"""
|
||||
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 build_markdown_table(rows_data: List[List[str]]) -> str:
|
||||
"""将二维列表转换为 Markdown 表格格式"""
|
||||
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"
|
||||
|
||||
|
||||
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"""
|
||||
for item in list_stack:
|
||||
if item:
|
||||
target.append(item + "\n")
|
||||
list_stack.clear()
|
||||
|
||||
|
||||
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"""
|
||||
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):
|
||||
return None
|
||||
|
||||
|
||||
def normalize_markdown_whitespace(content: str) -> str:
|
||||
"""规范化 Markdown 空白字符，保留单行空行"""
|
||||
@@ -235,56 +152,3 @@ def search_markdown(
|
||||
results.append("\n".join(result_lines))
|
||||
|
||||
return "\n---\n".join(results)
|
||||
|
||||
|
||||
def _unstructured_elements_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"""
|
||||
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 _RGB_PATTERN.match(text) or _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)
|
||||
|
||||
Reference in New Issue
Block a user