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:
207
scripts/readers/_utils.py
Normal file
207
scripts/readers/_utils.py
Normal file
@@ -0,0 +1,207 @@
|
||||
"""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 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)}"
|
||||
|
||||
|
||||
# ============================================================================
|
||||
# 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)
|
||||
@@ -2,9 +2,9 @@
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from scripts.core import parse_with_docling
|
||||
from scripts.readers._utils import parse_via_docling
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 docling 库解析 DOCX 文件"""
|
||||
return parse_with_docling(file_path)
|
||||
return parse_via_docling(file_path)
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from scripts.core import parse_with_markitdown
|
||||
from scripts.readers._utils import parse_via_markitdown
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 MarkItDown 库解析 DOCX 文件"""
|
||||
return parse_with_markitdown(file_path)
|
||||
return parse_via_markitdown(file_path)
|
||||
|
||||
@@ -4,7 +4,7 @@ import xml.etree.ElementTree as ET
|
||||
import zipfile
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
from scripts.core import build_markdown_table, safe_open_zip
|
||||
from scripts.readers._utils import build_markdown_table, safe_open_zip
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
from typing import Any, List, Optional, Tuple
|
||||
|
||||
from scripts.core import build_markdown_table
|
||||
from scripts.readers._utils import build_markdown_table
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from scripts.core import _unstructured_elements_to_markdown
|
||||
from scripts.readers._utils import convert_unstructured_to_markdown
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
@@ -14,7 +14,7 @@ def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
|
||||
try:
|
||||
elements = partition_docx(filename=file_path, infer_table_structure=True)
|
||||
content = _unstructured_elements_to_markdown(elements)
|
||||
content = convert_unstructured_to_markdown(elements)
|
||||
if not content.strip():
|
||||
return None, "文档为空"
|
||||
return content, None
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from scripts.core import parse_with_markitdown
|
||||
from scripts.readers._utils import parse_via_markitdown
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 MarkItDown 库解析 PDF 文件"""
|
||||
return parse_with_markitdown(file_path)
|
||||
return parse_via_markitdown(file_path)
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from scripts.core import _unstructured_elements_to_markdown
|
||||
from scripts.readers._utils import convert_unstructured_to_markdown
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
@@ -20,7 +20,7 @@ def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
languages=["chi_sim"],
|
||||
)
|
||||
# fast 策略不做版面分析，Title 类型标注不可靠
|
||||
content = _unstructured_elements_to_markdown(elements, trust_titles=False)
|
||||
content = convert_unstructured_to_markdown(elements, trust_titles=False)
|
||||
if not content.strip():
|
||||
return None, "文档为空"
|
||||
return content, None
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from scripts.core import _unstructured_elements_to_markdown
|
||||
from scripts.readers._utils import convert_unstructured_to_markdown
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
@@ -26,7 +26,7 @@ def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
ocr_agent=OCR_AGENT_PADDLE,
|
||||
table_ocr_agent=OCR_AGENT_PADDLE,
|
||||
)
|
||||
content = _unstructured_elements_to_markdown(elements, trust_titles=True)
|
||||
content = convert_unstructured_to_markdown(elements, trust_titles=True)
|
||||
if not content.strip():
|
||||
return None, "文档为空"
|
||||
return content, None
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from scripts.core import parse_with_docling
|
||||
from scripts.readers._utils import parse_via_docling
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 docling 库解析 PPTX 文件"""
|
||||
return parse_with_docling(file_path)
|
||||
return parse_via_docling(file_path)
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from scripts.core import parse_with_markitdown
|
||||
from scripts.readers._utils import parse_via_markitdown
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 MarkItDown 库解析 PPTX 文件"""
|
||||
return parse_with_markitdown(file_path)
|
||||
return parse_via_markitdown(file_path)
|
||||
|
||||
@@ -5,7 +5,7 @@ import xml.etree.ElementTree as ET
|
||||
import zipfile
|
||||
from typing import Any, List, Optional, Tuple
|
||||
|
||||
from scripts.core import build_markdown_table, flush_list_stack
|
||||
from scripts.readers._utils import build_markdown_table, flush_list_stack
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
from typing import Any, List, Optional, Tuple
|
||||
|
||||
from scripts.core import build_markdown_table, flush_list_stack
|
||||
from scripts.readers._utils import build_markdown_table, flush_list_stack
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from scripts.core import _unstructured_elements_to_markdown
|
||||
from scripts.readers._utils import convert_unstructured_to_markdown
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
@@ -16,7 +16,7 @@ def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
elements = partition_pptx(
|
||||
filename=file_path, infer_table_structure=True, include_metadata=True
|
||||
)
|
||||
content = _unstructured_elements_to_markdown(elements)
|
||||
content = convert_unstructured_to_markdown(elements)
|
||||
if not content.strip():
|
||||
return None, "文档为空"
|
||||
return content, None
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from scripts.core import parse_with_docling
|
||||
from scripts.readers._utils import parse_via_docling
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 docling 库解析 XLSX 文件"""
|
||||
return parse_with_docling(file_path)
|
||||
return parse_via_docling(file_path)
|
||||
|
||||
@@ -2,9 +2,9 @@
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from scripts.core import parse_with_markitdown
|
||||
from scripts.readers._utils import parse_via_markitdown
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 MarkItDown 库解析 XLSX 文件"""
|
||||
return parse_with_markitdown(file_path)
|
||||
return parse_via_markitdown(file_path)
|
||||
|
||||
@@ -4,7 +4,7 @@ import xml.etree.ElementTree as ET
|
||||
import zipfile
|
||||
from typing import List, Optional, Tuple
|
||||
|
||||
from scripts.core import build_markdown_table, safe_open_zip
|
||||
from scripts.readers._utils import build_markdown_table, safe_open_zip
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from scripts.core import _unstructured_elements_to_markdown
|
||||
from scripts.readers._utils import convert_unstructured_to_markdown
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
@@ -14,7 +14,7 @@ def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
|
||||
try:
|
||||
elements = partition_xlsx(filename=file_path, infer_table_structure=True)
|
||||
content = _unstructured_elements_to_markdown(elements)
|
||||
content = convert_unstructured_to_markdown(elements)
|
||||
if not content.strip():
|
||||
return None, "文档为空"
|
||||
return content, None
|
||||
|
||||
Reference in New Issue
Block a user