feat: 添加 skill 打包脚本 build.py

新增 build.py 实现 skill 自动化打包：
- 一键完成 skill/SKILL.md 和 scripts/ 打包到 build/
- 时间戳版本号格式 YYYYMMDD_HHMMSS
- 仅复制 .py 文件，避免创建空目录
- 添加 skill-packaging spec 文档

build.py

@@ -0,0 +1,134 @@
+#!/usr/bin/env python3
+"""
+Skill 打包构建脚本
+将 skill/SKILL.md 和 scripts/ 目录打包到 build/ 目录
+"""
+
+import os
+import shutil
+from datetime import datetime
+
+
+def generate_timestamp() -> str:
+    """
+    生成 YYYYMMDD_HHMMSS 格式的时间戳
+
+    Returns:
+        时间戳字符串
+    """
+    return datetime.now().strftime("%Y%m%d_%H%M%S")
+
+
+def clean_and_create_build_dir(build_dir: str) -> None:
+    """
+    删除旧 build 目录并创建新的空目录
+
+    Args:
+        build_dir: 构建目录路径
+    """
+    if os.path.exists(build_dir):
+        print(f"清理旧构建目录: {build_dir}")
+        shutil.rmtree(build_dir)
+    os.makedirs(build_dir)
+    print(f"创建构建目录: {build_dir}")
+
+
+def copy_skill_md(source_path: str, target_dir: str) -> None:
+    """
+    复制 skill/SKILL.md 到 build/SKILL.md
+
+    Args:
+        source_path: 源 SKILL.md 路径
+        target_dir: 目标目录
+    """
+    target_path = os.path.join(target_dir, "SKILL.md")
+    shutil.copy2(source_path, target_path)
+    print(f"复制: {source_path} -> {target_path}")
+
+
+def copy_scripts_dir(source_dir: str, target_dir: str) -> int:
+    """
+    递归复制 scripts/ 目录，仅复制 .py 文件
+
+    Args:
+        source_dir: 源目录
+        target_dir: 目标目录
+
+    Returns:
+        复制的文件数量
+    """
+    file_count = 0
+
+    for root, dirs, files in os.walk(source_dir):
+        # 计算相对路径
+        rel_path = os.path.relpath(root, source_dir)
+        # 处理相对路径为 "." 的情况
+        if rel_path == ".":
+            target_root = target_dir
+        else:
+            target_root = os.path.join(target_dir, rel_path)
+
+        # 检查此目录下是否有 .py 文件需要复制
+        has_py_files = any(file.endswith(".py") for file in files)
+
+        # 只有当有 .py 文件需要复制时才创建目录并复制
+        if has_py_files:
+            if not os.path.exists(target_root):
+                os.makedirs(target_root)
+
+            # 只复制 .py 文件
+            for file in files:
+                if file.endswith(".py"):
+                    source_file = os.path.join(root, file)
+                    target_file = os.path.join(target_root, file)
+                    shutil.copy2(source_file, target_file)
+                    file_count += 1
+                    print(f"复制: {source_file} -> {target_file}")
+
+    return file_count
+
+
+def main() -> None:
+    """
+    主函数：执行完整的打包流程
+    """
+    print("=" * 60)
+    print("Skill 打包构建")
+    print("=" * 60)
+
+    # 路径配置
+    project_root = os.path.dirname(os.path.abspath(__file__))
+    skill_md_path = os.path.join(project_root, "skill", "SKILL.md")
+    scripts_source_dir = os.path.join(project_root, "scripts")
+    build_dir = os.path.join(project_root, "build")
+    scripts_target_dir = os.path.join(build_dir, "scripts")
+
+    # 生成时间戳
+    version = generate_timestamp()
+    print(f"版本号: {version}")
+    print()
+
+    # 清理并创建 build 目录
+    clean_and_create_build_dir(build_dir)
+    print()
+
+    # 复制 SKILL.md
+    copy_skill_md(skill_md_path, build_dir)
+    print()
+
+    # 复制 scripts 目录
+    print("复制 scripts/ 目录（仅 .py 文件）:")
+    file_count = copy_scripts_dir(scripts_source_dir, scripts_target_dir)
+    print()
+
+    # 完成信息
+    print("=" * 60)
+    print("构建完成!")
+    print(f"版本号: {version}")
+    print(f"复制文件数: {file_count}")
+    print(f"输出目录: {build_dir}")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()

openspec/specs/reader-internal-utils/spec.md

@@ -0,0 +1,95 @@
+## Purpose
+
+提供 Reader 内部共享工具模块，包含解析器包装函数、格式化工具、ZIP 安全处理和 unstructured 库集成。此模块仅供 readers 包内部使用，不作为公共 API。
+
+## Requirements
+
+### Requirement: 解析器包装函数
+系统 SHALL 提供统一的解析器包装函数，封装第三方库的调用细节。
+
+#### Scenario: 使用 MarkItDown 解析
+- **WHEN** 调用 `parse_via_markitdown(file_path)`
+- **THEN** 系统使用 MarkItDown 库解析文件
+- **AND** 成功时返回 `(markdown_content, None)`
+- **AND** 失败时返回 `(None, error_message)`
+
+#### Scenario: 使用 docling 解析
+- **WHEN** 调用 `parse_via_docling(file_path)`
+- **THEN** 系统使用 docling 库解析文件
+- **AND** 成功时返回 `(markdown_content, None)`
+- **AND** 失败时返回 `(None, error_message)`
+
+#### Scenario: 库未安装时返回友好错误
+- **WHEN** 调用解析器包装函数但对应库未安装
+- **THEN** 系统返回 `(None, "<库名> 库未安装")`
+
+### Requirement: Markdown 表格格式化
+系统 SHALL 提供将二维列表格式化为 Markdown 表格的工具函数。
+
+#### Scenario: 格式化标准表格
+- **WHEN** 调用 `build_markdown_table(rows_data)` 且 rows_data 包含表头和数据行
+- **THEN** 系统生成标准 Markdown 表格格式
+- **AND** 第一行前生成分隔行（`| --- | --- |`）
+
+#### Scenario: 空数据返回空字符串
+- **WHEN** 调用 `build_markdown_table([])` 或 `build_markdown_table([[]])`
+- **THEN** 系统返回空字符串
+
+### Requirement: 列表堆栈处理
+系统 SHALL 提供列表堆栈处理工具函数，用于处理嵌套列表的格式化输出。
+
+#### Scenario: 刷新列表堆栈
+- **WHEN** 调用 `flush_list_stack(list_stack, target)`
+- **THEN** 系统将 list_stack 中所有非空项添加到 target 列表
+- **AND** 每个项末尾添加换行符
+- **AND** 清空 list_stack
+
+#### Scenario: 跳过空项
+- **WHEN** list_stack 中包含空字符串
+- **THEN** 系统跳过空项，不添加到 target
+
+### Requirement: ZIP 文件安全打开
+系统 SHALL 提供安全的 ZIP 文件打开函数，防止路径遍历攻击。
+
+#### Scenario: 打开合法文件
+- **WHEN** 调用 `safe_open_zip(zip_file, "valid/file.txt")`
+- **THEN** 系统返回对应的 ZipExtFile 对象
+
+#### Scenario: 拒绝路径遍历攻击
+- **WHEN** 路径包含 ".." 在 Path.parts 中
+- **THEN** 系统返回 None
+
+#### Scenario: 拒绝绝对路径
+- **WHEN** 路径为绝对路径
+- **THEN** 系统返回 None
+
+#### Scenario: 处理路径异常
+- **WHEN** Path() 抛出 ValueError 或 OSError
+- **THEN** 系统捕获异常并返回 None
+
+### Requirement: unstructured 元素转换
+系统 SHALL 提供将 unstructured 库解析的元素转换为 Markdown 的工具函数。
+
+#### Scenario: 转换标准元素
+- **WHEN** 调用 `convert_unstructured_to_markdown(elements, trust_titles=True)`
+- **THEN** 系统跳过 Header、Footer、PageBreak、PageNumber 元素
+- **AND** 跳过 RGB 颜色值和页码噪声
+- **AND** Table 元素转换为 Markdown 表格
+- **AND** Title 元素转换为 # 标题（根据 category_depth 确定级别）
+- **AND** ListItem 元素转换为 - 列表项
+- **AND** Image 元素转换为 ![image](path) 格式
+
+#### Scenario: 库未安装时回退
+- **WHEN** markdownify 或 unstructured 库未安装
+- **THEN** 系统提取所有元素的 text 属性并用双换行连接
+
+### Requirement: 噪声模式匹配
+系统 SHALL 定义 unstructured 库的噪声匹配模式。
+
+#### Scenario: 匹配 RGB 颜色值
+- **WHEN** 文本匹配 `_UNSTRUCTURED_RGB_PATTERN`（如 "R:255 G:128 B:0"）
+- **THEN** 系统将其识别为噪声并过滤
+
+#### Scenario: 匹配页码
+- **WHEN** 文本匹配 `_UNSTRUCTURED_PAGE_NUMBER_PATTERN`（如 "— 3 —"）
+- **THEN** 系统将其识别为噪声并过滤

openspec/specs/skill-packaging/spec.md

@@ -0,0 +1,54 @@
+## Purpose
+
+提供自动化的 skill 打包能力，将 skill/SKILL.md 和 scripts/ 目录打包到 build/ 目录，便于 skill 分发。
+
+## Requirements
+
+### Requirement: build.py 一键打包
+系统 SHALL 提供 build.py 脚本，运行后完成 skill 的完整打包流程。
+
+#### Scenario: 运行 build.py 成功
+- **WHEN** 用户执行 `uv run python build.py`
+- **THEN** 脚本完成所有打包步骤并输出成功信息
+
+### Requirement: 构建目录清理重建
+系统 SHALL 在每次构建前删除整个 build 目录，然后重建空的 build 目录。
+
+#### Scenario: 删除并重建 build 目录
+- **WHEN** 构建开始
+- **THEN** 脚本删除整个 build 目录（如有），然后创建新的空 build 目录
+
+### Requirement: SKILL.md 复制
+系统 SHALL 将 skill/SKILL.md 直接复制到 build/SKILL.md，不保留 skill 这一级目录。
+
+#### Scenario: SKILL.md 成功复制
+- **WHEN** 构建执行
+- **THEN** build/SKILL.md 文件存在且内容与 skill/SKILL.md 一致
+
+### Requirement: scripts 目录复制
+系统 SHALL 将 scripts/ 目录完整复制到 build/scripts/，保持目录结构。
+
+#### Scenario: scripts 目录结构保留
+- **WHEN** 构建执行
+- **THEN** build/scripts/ 下的子目录结构与原 scripts/ 一致
+
+### Requirement: 仅复制 Python 文件
+系统 SHALL 只复制 .py 扩展名的文件，其他文件类型自然被过滤。
+
+#### Scenario: 只保留 py 文件
+- **WHEN** 原目录包含多种文件类型
+- **THEN** build/scripts/ 中只存在 .py 文件
+
+### Requirement: 时间戳版本号
+系统 SHALL 生成 YYYYMMDD_HHMMSS 格式的时间戳作为构建版本标识。
+
+#### Scenario: 时间戳格式正确
+- **WHEN** 构建在 2025年3月9日 14点30分22秒执行
+- **THEN** 生成的版本号为 20250309_143022
+
+### Requirement: 输出构建信息
+系统 SHALL 在构建完成后打印版本号和构建结果信息。
+
+#### Scenario: 显示构建信息
+- **WHEN** 构建成功完成
+- **THEN** 控制台输出版本号和构建文件清单

scripts/core/__init__.py

@@ -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",

scripts/core/markdown.py

@@ -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"![image]({path})")
-        else:
-            parts.append(text)
-
-    return "\n\n".join(parts)

scripts/readers/_utils.py

@@ -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"![image]({path})")
+        else:
+            parts.append(text)
+
+    return "\n\n".join(parts)

scripts/readers/docx/docling.py

@@ -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)

scripts/readers/docx/markitdown.py

@@ -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)

scripts/readers/docx/native_xml.py

@@ -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]]:

scripts/readers/docx/python_docx.py

@@ -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]]:

scripts/readers/docx/unstructured.py

@@ -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

scripts/readers/html/__init__.py

@@ -9,7 +9,7 @@ from scripts.utils import is_url
 from scripts.utils import encoding_detection
 
 from . import cleaner
-from . import downloader
+from .downloader import download_html
 from . import trafilatura
 from . import domscribe
 from . import markitdown
@@ -37,7 +37,7 @@ class HtmlReader(BaseReader):
         # 步骤 1: 获取 HTML 内容
         if is_url(file_path):
             # URL 路径: 下载 HTML
-            html_content, download_failures = downloader.download_html(file_path)
+            html_content, download_failures = download_html(file_path)
             all_failures.extend(download_failures)
             if html_content is None:
                 return None, all_failures

scripts/readers/html/downloader.py

@@ -1,262 +0,0 @@
-"""URL 下载模块，按 pyppeteer → selenium → httpx → urllib 优先级尝试下载。"""
-
-import os
-import asyncio
-import tempfile
-import urllib.request
-import urllib.error
-from typing import Optional, Tuple
-
-
-# 公共配置
-USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36"
-WINDOW_SIZE = "1920,1080"
-LANGUAGE_SETTING = "zh-CN,zh"
-
-# Chrome 浏览器启动参数（pyppeteer 和 selenium 共用）
-CHROME_ARGS = [
-    "--no-sandbox",
-    "--disable-dev-shm-usage",
-    "--disable-gpu",
-    "--disable-software-rasterizer",
-    "--disable-extensions",
-    "--disable-background-networking",
-    "--disable-default-apps",
-    "--disable-sync",
-    "--disable-translate",
-    "--hide-scrollbars",
-    "--metrics-recording-only",
-    "--mute-audio",
-    "--no-first-run",
-    "--safebrowsing-disable-auto-update",
-    "--blink-settings=imagesEnabled=false",
-    "--disable-plugins",
-    "--disable-ipc-flooding-protection",
-    "--disable-renderer-backgrounding",
-    "--disable-background-timer-throttling",
-    "--disable-hang-monitor",
-    "--disable-prompt-on-repost",
-    "--disable-client-side-phishing-detection",
-    "--disable-component-update",
-    "--disable-domain-reliability",
-    "--disable-features=site-per-process",
-    "--disable-features=IsolateOrigins",
-    "--disable-features=VizDisplayCompositor",
-    "--disable-features=WebRTC",
-    f"--window-size={WINDOW_SIZE}",
-    f"--lang={LANGUAGE_SETTING}",
-    f"--user-agent={USER_AGENT}",
-]
-
-# 隐藏自动化特征的脚本（pyppeteer 和 selenium 共用）
-HIDE_AUTOMATION_SCRIPT = """
-    () => {
-        Object.defineProperty(navigator, 'webdriver', { get: () => undefined });
-        Object.defineProperty(navigator, 'plugins', { get: () => [1, 2, 3, 4, 5] });
-        Object.defineProperty(navigator, 'languages', { get: () => ['zh-CN', 'zh'] });
-    }
-"""
-
-# pyppeteer 额外的隐藏自动化脚本（包含 notifications 处理）
-HIDE_AUTOMATION_SCRIPT_PUPPETEER = """
-    () => {
-        Object.defineProperty(navigator, 'webdriver', { get: () => undefined });
-        Object.defineProperty(navigator, 'plugins', { get: () => [1, 2, 3, 4, 5] });
-        Object.defineProperty(navigator, 'languages', { get: () => ['zh-CN', 'zh'] });
-        const originalQuery = window.navigator.permissions.query;
-        window.navigator.permissions.query = (parameters) => (
-            parameters.name === 'notifications' ?
-                Promise.resolve({ state: Notification.permission }) :
-                originalQuery(parameters)
-        );
-    }
-"""
-
-
-def download_with_pyppeteer(url: str) -> Tuple[Optional[str], Optional[str]]:
-    """使用 pyppeteer 下载 URL（支持 JS 渲染）"""
-    try:
-        from pyppeteer import launch
-    except ImportError:
-        return None, "pyppeteer 库未安装"
-
-    async def _download():
-        pyppeteer_temp_dir = os.path.join(tempfile.gettempdir(), "pyppeteer_home")
-        chromium_path = os.environ.get("LYXY_CHROMIUM_BINARY")
-        if not chromium_path:
-            os.environ["PYPPETEER_HOME"] = pyppeteer_temp_dir
-        executable_path = chromium_path if (chromium_path and os.path.exists(chromium_path)) else None
-
-        browser = None
-        try:
-            browser = await launch(
-                headless=True,
-                executablePath=executable_path,
-                args=CHROME_ARGS
-            )
-            page = await browser.newPage()
-
-            await page.evaluateOnNewDocument(HIDE_AUTOMATION_SCRIPT_PUPPETEER)
-
-            await page.setJavaScriptEnabled(True)
-            await page.goto(url, {"waitUntil": "networkidle2", "timeout": 30000})
-            return await page.content()
-        finally:
-            if browser is not None:
-                try:
-                    await browser.close()
-                except Exception:
-                    pass
-
-    try:
-        content = asyncio.run(_download())
-        if not content or not content.strip():
-            return None, "下载内容为空"
-        return content, None
-    except Exception as e:
-        return None, f"pyppeteer 下载失败: {str(e)}"
-
-
-def download_with_selenium(url: str) -> Tuple[Optional[str], Optional[str]]:
-    """使用 selenium 下载 URL（支持 JS 渲染）"""
-    try:
-        from selenium import webdriver
-        from selenium.webdriver.chrome.service import Service
-        from selenium.webdriver.chrome.options import Options
-        from selenium.webdriver.support.ui import WebDriverWait
-    except ImportError:
-        return None, "selenium 库未安装"
-
-    driver_path = os.environ.get("LYXY_CHROMIUM_DRIVER")
-    binary_path = os.environ.get("LYXY_CHROMIUM_BINARY")
-
-    if not driver_path or not os.path.exists(driver_path):
-        return None, "LYXY_CHROMIUM_DRIVER 环境变量未设置或文件不存在"
-    if not binary_path or not os.path.exists(binary_path):
-        return None, "LYXY_CHROMIUM_BINARY 环境变量未设置或文件不存在"
-
-    chrome_options = Options()
-    chrome_options.binary_location = binary_path
-    chrome_options.add_argument("--headless=new")
-    for arg in CHROME_ARGS:
-        chrome_options.add_argument(arg)
-
-    # 隐藏自动化特征
-    chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
-    chrome_options.add_experimental_option("useAutomationExtension", False)
-
-    driver = None
-    try:
-        import time
-        service = Service(driver_path)
-        driver = webdriver.Chrome(service=service, options=chrome_options)
-
-        # 隐藏 webdriver 属性
-        driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
-            "source": HIDE_AUTOMATION_SCRIPT
-        })
-
-        driver.get(url)
-
-        # 等待页面内容稳定
-        WebDriverWait(driver, 30).until(
-            lambda d: d.execute_script("return document.readyState") == "complete"
-        )
-
-        last_len = 0
-        stable_count = 0
-        for _ in range(30):
-            current_len = len(driver.page_source)
-            if current_len == last_len:
-                stable_count += 1
-                if stable_count >= 2:
-                    break
-            else:
-                stable_count = 0
-                last_len = current_len
-            time.sleep(0.5)
-
-        content = driver.page_source
-        if not content or not content.strip():
-            return None, "下载内容为空"
-        return content, None
-    except Exception as e:
-        return None, f"selenium 下载失败: {str(e)}"
-    finally:
-        if driver is not None:
-            try:
-                driver.quit()
-            except Exception:
-                pass
-
-
-def download_with_httpx(url: str) -> Tuple[Optional[str], Optional[str]]:
-    """使用 httpx 下载 URL（轻量级 HTTP 客户端）"""
-    try:
-        import httpx
-    except ImportError:
-        return None, "httpx 库未安装"
-
-    headers = {
-        "User-Agent": USER_AGENT
-    }
-
-    try:
-        with httpx.Client(timeout=30.0) as client:
-            response = client.get(url, headers=headers)
-            if response.status_code == 200:
-                content = response.text
-                if not content or not content.strip():
-                    return None, "下载内容为空"
-                return content, None
-            return None, f"HTTP {response.status_code}"
-    except Exception as e:
-        return None, f"httpx 下载失败: {str(e)}"
-
-
-def download_with_urllib(url: str) -> Tuple[Optional[str], Optional[str]]:
-    """使用 urllib 下载 URL（标准库，兜底方案）"""
-    headers = {
-        "User-Agent": USER_AGENT
-    }
-
-    try:
-        req = urllib.request.Request(url, headers=headers)
-        with urllib.request.urlopen(req, timeout=30) as response:
-            if response.status == 200:
-                content = response.read().decode("utf-8")
-                if not content or not content.strip():
-                    return None, "下载内容为空"
-                return content, None
-            return None, f"HTTP {response.status}"
-    except Exception as e:
-        return None, f"urllib 下载失败: {str(e)}"
-
-
-def download_html(url: str) -> Tuple[Optional[str], list]:
-    """
-    统一的 HTML 下载入口函数，按优先级尝试各下载器。
-
-    返回: (content, failures)
-    - content: 成功时返回 HTML 内容，失败时返回 None
-    - failures: 各下载器的失败原因列表
-    """
-    failures = []
-    content = None
-
-    # 按优先级尝试各下载器
-    downloaders = [
-        ("pyppeteer", download_with_pyppeteer),
-        ("selenium", download_with_selenium),
-        ("httpx", download_with_httpx),
-        ("urllib", download_with_urllib),
-    ]
-
-    for name, func in downloaders:
-        content, error = func(url)
-        if content is not None:
-            return content, failures
-        else:
-            failures.append(f"- {name}: {error}")
-
-    return None, failures

scripts/readers/html/downloader/__init__.py

@@ -0,0 +1,39 @@
+"""HTML 下载器子包，支持多种下载方式按优先级降级"""
+
+from typing import Optional, Tuple, List
+
+from . import pyppeteer
+from . import selenium
+from . import httpx
+from . import urllib
+
+
+DOWNLOADERS = [
+    ("pyppeteer", pyppeteer.download),
+    ("selenium", selenium.download),
+    ("httpx", httpx.download),
+    ("urllib", urllib.download),
+]
+
+
+def download_html(url: str) -> Tuple[Optional[str], List[str]]:
+    """
+    统一的 HTML 下载入口，按优先级尝试各下载器
+
+    Args:
+        url: 目标 URL
+
+    Returns:
+        (content, failures): content 成功时为 HTML 内容，所有失败时为 None
+                            failures 各下载器的失败原因列表
+    """
+    failures: List[str] = []
+
+    for name, func in DOWNLOADERS:
+        content, error = func(url)
+        if content is not None:
+            return content, failures
+        else:
+            failures.append(f"- {name}: {error}")
+
+    return None, failures

scripts/readers/html/downloader/common.py

@@ -0,0 +1,65 @@
+"""下载器公共配置"""
+
+# 公共配置
+USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36"
+WINDOW_SIZE = "1920,1080"
+LANGUAGE_SETTING = "zh-CN,zh"
+
+# Chrome 浏览器启动参数（pyppeteer 和 selenium 共用）
+CHROME_ARGS = [
+    "--no-sandbox",
+    "--disable-dev-shm-usage",
+    "--disable-gpu",
+    "--disable-software-rasterizer",
+    "--disable-extensions",
+    "--disable-background-networking",
+    "--disable-default-apps",
+    "--disable-sync",
+    "--disable-translate",
+    "--hide-scrollbars",
+    "--metrics-recording-only",
+    "--mute-audio",
+    "--no-first-run",
+    "--safebrowsing-disable-auto-update",
+    "--blink-settings=imagesEnabled=false",
+    "--disable-plugins",
+    "--disable-ipc-flooding-protection",
+    "--disable-renderer-backgrounding",
+    "--disable-background-timer-throttling",
+    "--disable-hang-monitor",
+    "--disable-prompt-on-repost",
+    "--disable-client-side-phishing-detection",
+    "--disable-component-update",
+    "--disable-domain-reliability",
+    "--disable-features=site-per-process",
+    "--disable-features=IsolateOrigins",
+    "--disable-features=VizDisplayCompositor",
+    "--disable-features=WebRTC",
+    f"--window-size={WINDOW_SIZE}",
+    f"--lang={LANGUAGE_SETTING}",
+    f"--user-agent={USER_AGENT}",
+]
+
+# 隐藏自动化特征的脚本（pyppeteer 和 selenium 共用）
+HIDE_AUTOMATION_SCRIPT = """
+    () => {
+        Object.defineProperty(navigator, 'webdriver', { get: () => undefined });
+        Object.defineProperty(navigator, 'plugins', { get: () => [1, 2, 3, 4, 5] });
+        Object.defineProperty(navigator, 'languages', { get: () => ['zh-CN', 'zh'] });
+    }
+"""
+
+# pyppeteer 额外的隐藏自动化脚本（包含 notifications 处理）
+HIDE_AUTOMATION_SCRIPT_PUPPETEER = """
+    () => {
+        Object.defineProperty(navigator, 'webdriver', { get: () => undefined });
+        Object.defineProperty(navigator, 'plugins', { get: () => [1, 2, 3, 4, 5] });
+        Object.defineProperty(navigator, 'languages', { get: () => ['zh-CN', 'zh'] });
+        const originalQuery = window.navigator.permissions.query;
+        window.navigator.permissions.query = (parameters) => (
+            parameters.name === 'notifications' ?
+                Promise.resolve({ state: Notification.permission }) :
+                originalQuery(parameters)
+        );
+    }
+"""

scripts/readers/html/downloader/httpx.py

@@ -0,0 +1,38 @@
+"""使用 httpx 下载 URL（轻量级 HTTP 客户端）"""
+
+from typing import Optional, Tuple
+
+from .common import USER_AGENT
+
+
+def download(url: str) -> Tuple[Optional[str], Optional[str]]:
+    """
+    使用 httpx 下载 URL（轻量级 HTTP 客户端）
+
+    Args:
+        url: 目标 URL
+
+    Returns:
+        (content, error): content 成功时为 HTML 内容，失败时为 None
+                         error 成功时为 None，失败时为错误信息
+    """
+    try:
+        import httpx
+    except ImportError:
+        return None, "httpx 库未安装"
+
+    headers = {
+        "User-Agent": USER_AGENT
+    }
+
+    try:
+        with httpx.Client(timeout=30.0) as client:
+            response = client.get(url, headers=headers)
+            if response.status_code == 200:
+                content = response.text
+                if not content or not content.strip():
+                    return None, "下载内容为空"
+                return content, None
+            return None, f"HTTP {response.status_code}"
+    except Exception as e:
+        return None, f"httpx 下载失败: {str(e)}"

scripts/readers/html/downloader/pyppeteer.py

@@ -0,0 +1,65 @@
+"""使用 pyppeteer 下载 URL（支持 JS 渲染）"""
+
+import os
+import asyncio
+import tempfile
+from typing import Optional, Tuple
+
+from .common import (
+    USER_AGENT,
+    CHROME_ARGS,
+    HIDE_AUTOMATION_SCRIPT_PUPPETEER
+)
+
+
+def download(url: str) -> Tuple[Optional[str], Optional[str]]:
+    """
+    使用 pyppeteer 下载 URL（支持 JS 渲染）
+
+    Args:
+        url: 目标 URL
+
+    Returns:
+        (content, error): content 成功时为 HTML 内容，失败时为 None
+                         error 成功时为 None，失败时为错误信息
+    """
+    try:
+        from pyppeteer import launch
+    except ImportError:
+        return None, "pyppeteer 库未安装"
+
+    async def _download():
+        pyppeteer_temp_dir = os.path.join(tempfile.gettempdir(), "pyppeteer_home")
+        chromium_path = os.environ.get("LYXY_CHROMIUM_BINARY")
+        if not chromium_path:
+            os.environ["PYPPETEER_HOME"] = pyppeteer_temp_dir
+        executable_path = chromium_path if (chromium_path and os.path.exists(chromium_path)) else None
+
+        browser = None
+        try:
+            browser = await launch(
+                headless=True,
+                executablePath=executable_path,
+                args=CHROME_ARGS
+            )
+            page = await browser.newPage()
+
+            await page.evaluateOnNewDocument(HIDE_AUTOMATION_SCRIPT_PUPPETEER)
+
+            await page.setJavaScriptEnabled(True)
+            await page.goto(url, {"waitUntil": "networkidle2", "timeout": 30000})
+            return await page.content()
+        finally:
+            if browser is not None:
+                try:
+                    await browser.close()
+                except Exception:
+                    pass
+
+    try:
+        content = asyncio.run(_download())
+        if not content or not content.strip():
+            return None, "下载内容为空"
+        return content, None
+    except Exception as e:
+        return None, f"pyppeteer 下载失败: {str(e)}"

scripts/readers/html/downloader/selenium.py

@@ -0,0 +1,92 @@
+"""使用 selenium 下载 URL（支持 JS 渲染）"""
+
+import os
+from typing import Optional, Tuple
+
+from .common import (
+    USER_AGENT,
+    CHROME_ARGS,
+    HIDE_AUTOMATION_SCRIPT
+)
+
+
+def download(url: str) -> Tuple[Optional[str], Optional[str]]:
+    """
+    使用 selenium 下载 URL（支持 JS 渲染）
+
+    Args:
+        url: 目标 URL
+
+    Returns:
+        (content, error): content 成功时为 HTML 内容，失败时为 None
+                         error 成功时为 None，失败时为错误信息
+    """
+    try:
+        from selenium import webdriver
+        from selenium.webdriver.chrome.service import Service
+        from selenium.webdriver.chrome.options import Options
+        from selenium.webdriver.support.ui import WebDriverWait
+    except ImportError:
+        return None, "selenium 库未安装"
+
+    driver_path = os.environ.get("LYXY_CHROMIUM_DRIVER")
+    binary_path = os.environ.get("LYXY_CHROMIUM_BINARY")
+
+    if not driver_path or not os.path.exists(driver_path):
+        return None, "LYXY_CHROMIUM_DRIVER 环境变量未设置或文件不存在"
+    if not binary_path or not os.path.exists(binary_path):
+        return None, "LYXY_CHROMIUM_BINARY 环境变量未设置或文件不存在"
+
+    chrome_options = Options()
+    chrome_options.binary_location = binary_path
+    chrome_options.add_argument("--headless=new")
+    for arg in CHROME_ARGS:
+        chrome_options.add_argument(arg)
+
+    # 隐藏自动化特征
+    chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    chrome_options.add_experimental_option("useAutomationExtension", False)
+
+    driver = None
+    try:
+        import time
+        service = Service(driver_path)
+        driver = webdriver.Chrome(service=service, options=chrome_options)
+
+        # 隐藏 webdriver 属性
+        driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
+            "source": HIDE_AUTOMATION_SCRIPT
+        })
+
+        driver.get(url)
+
+        # 等待页面内容稳定
+        WebDriverWait(driver, 30).until(
+            lambda d: d.execute_script("return document.readyState") == "complete"
+        )
+
+        last_len = 0
+        stable_count = 0
+        for _ in range(30):
+            current_len = len(driver.page_source)
+            if current_len == last_len:
+                stable_count += 1
+                if stable_count >= 2:
+                    break
+            else:
+                stable_count = 0
+                last_len = current_len
+            time.sleep(0.5)
+
+        content = driver.page_source
+        if not content or not content.strip():
+            return None, "下载内容为空"
+        return content, None
+    except Exception as e:
+        return None, f"selenium 下载失败: {str(e)}"
+    finally:
+        if driver is not None:
+            try:
+                driver.quit()
+            except Exception:
+                pass

scripts/readers/html/downloader/urllib.py

@@ -0,0 +1,35 @@
+"""使用 urllib 下载 URL（标准库，兜底方案）"""
+
+import urllib.request
+import urllib.error
+from typing import Optional, Tuple
+
+from .common import USER_AGENT
+
+
+def download(url: str) -> Tuple[Optional[str], Optional[str]]:
+    """
+    使用 urllib 下载 URL（标准库，兜底方案）
+
+    Args:
+        url: 目标 URL
+
+    Returns:
+        (content, error): content 成功时为 HTML 内容，失败时为 None
+                         error 成功时为 None，失败时为错误信息
+    """
+    headers = {
+        "User-Agent": USER_AGENT
+    }
+
+    try:
+        req = urllib.request.Request(url, headers=headers)
+        with urllib.request.urlopen(req, timeout=30) as response:
+            if response.status == 200:
+                content = response.read().decode("utf-8")
+                if not content or not content.strip():
+                    return None, "下载内容为空"
+                return content, None
+            return None, f"HTTP {response.status}"
+    except Exception as e:
+        return None, f"urllib 下载失败: {str(e)}"

scripts/readers/pdf/markitdown.py

@@ -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)

scripts/readers/pdf/unstructured.py

@@ -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

scripts/readers/pdf/unstructured_ocr.py

@@ -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

scripts/readers/pptx/docling.py

@@ -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)

scripts/readers/pptx/markitdown.py

@@ -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)

scripts/readers/pptx/native_xml.py

@@ -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]]:

scripts/readers/pptx/python_pptx.py

@@ -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]]:

scripts/readers/pptx/unstructured.py

@@ -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

scripts/readers/xlsx/docling.py

@@ -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)

scripts/readers/xlsx/markitdown.py

@@ -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)

scripts/readers/xlsx/native_xml.py

@@ -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]]:

scripts/readers/xlsx/unstructured.py

@@ -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

tests/test_readers/test_utils.py

@@ -0,0 +1,203 @@
+"""测试 Reader 内部工具函数。"""
+
+import zipfile
+import pytest
+from scripts.readers._utils import (
+    parse_via_markitdown,
+    parse_via_docling,
+    build_markdown_table,
+    flush_list_stack,
+    safe_open_zip,
+    convert_unstructured_to_markdown,
+    _UNSTRUCTURED_RGB_PATTERN,
+    _UNSTRUCTURED_PAGE_NUMBER_PATTERN,
+)
+
+
+class TestBuildMarkdownTable:
+    """测试 build_markdown_table 函数。"""
+
+    def test_standard_table(self):
+        """测试标准表格格式化。"""
+        rows_data = [["姓名", "年龄"], ["张三", "25"], ["李四", "30"]]
+        result = build_markdown_table(rows_data)
+
+        assert "| 姓名 | 年龄 |" in result
+        assert "| --- | --- |" in result
+        assert "| 张三 | 25 |" in result
+        assert "| 李四 | 30 |" in result
+
+    def test_empty_table(self):
+        """测试空表格。"""
+        assert build_markdown_table([]) == ""
+        assert build_markdown_table([[]]) == ""
+
+    def test_table_with_empty_cells(self):
+        """测试包含空单元格的表格。"""
+        rows_data = [["A", "B"], ["", "C"], ["D", ""]]
+        result = build_markdown_table(rows_data)
+
+        assert "| A | B |" in result
+        assert "|  | C |" in result
+        assert "| D |  |" in result
+
+
+class TestFlushListStack:
+    """测试 flush_list_stack 函数。"""
+
+    def test_flush_non_empty_items(self):
+        """测试刷新非空堆栈。"""
+        list_stack = ["item1\n", "", "item2\n"]
+        target = []
+
+        flush_list_stack(list_stack, target)
+
+        assert target == ["item1\n\n", "item2\n\n"]
+        assert list_stack == []
+
+    def test_flush_all_empty(self):
+        """测试刷新空堆栈。"""
+        list_stack = ["", "", ""]
+        target = []
+
+        flush_list_stack(list_stack, target)
+
+        assert target == []
+        assert list_stack == []
+
+
+class TestSafeOpenZip:
+    """测试 safe_open_zip 函数。"""
+
+    def test_open_valid_file(self, tmp_path):
+        """测试打开合法文件。"""
+        # 创建测试 ZIP 文件
+        zip_path = tmp_path / "test.zip"
+        with zipfile.ZipFile(zip_path, "w") as zf:
+            zf.writestr("valid.txt", "content")
+
+        with zipfile.ZipFile(zip_path, "r") as zf:
+            result = safe_open_zip(zf, "valid.txt")
+            assert result is not None
+            assert result.read() == b"content"
+
+    def test_reject_path_traversal(self, tmp_path):
+        """测试拒绝路径遍历攻击。"""
+        zip_path = tmp_path / "test.zip"
+        with zipfile.ZipFile(zip_path, "w") as zf:
+            zf.writestr("safe.txt", "content")
+
+        with zipfile.ZipFile(zip_path, "r") as zf:
+            assert safe_open_zip(zf, "../etc/passwd") is None
+            assert safe_open_zip(zf, "sub/../../etc/passwd") is None
+
+    def test_reject_absolute_path(self, tmp_path):
+        """测试拒绝绝对路径。"""
+        zip_path = tmp_path / "test.zip"
+        with zipfile.ZipFile(zip_path, "w") as zf:
+            zf.writestr("safe.txt", "content")
+
+        with zipfile.ZipFile(zip_path, "r") as zf:
+            assert safe_open_zip(zf, "/absolute/path.txt") is None
+            assert safe_open_zip(zf, "C:\\Windows\\System32\\config") is None
+
+    def test_empty_name(self):
+        """测试空文件名。"""
+        import io
+
+        zip_buffer = io.BytesIO()
+        with zipfile.ZipFile(zip_buffer, "w") as zf:
+            zf.writestr("test.txt", "content")
+
+        with zipfile.ZipFile(io.BytesIO(zip_buffer.getvalue()), "r") as zf:
+            assert safe_open_zip(zf, "") is None
+
+
+class TestUnstructuredPatterns:
+    """测试 unstructured 噪声匹配模式。"""
+
+    def test_rgb_pattern(self):
+        """测试 RGB 颜色值模式。"""
+        assert _UNSTRUCTURED_RGB_PATTERN.match("R:255 G:128 B:0")
+        assert _UNSTRUCTURED_RGB_PATTERN.match("R:0 G:0 B:0")
+        assert _UNSTRUCTURED_RGB_PATTERN.match("R:255 G:255 B:255")
+
+    def test_rgb_pattern_invalid(self):
+        """测试无效 RGB 值。"""
+        assert not _UNSTRUCTURED_RGB_PATTERN.match("255 128 0")
+        assert not _UNSTRUCTURED_RGB_PATTERN.match("RGB:255 G:128 B:0")
+
+    def test_page_number_pattern(self):
+        """测试页码模式。"""
+        assert _UNSTRUCTURED_PAGE_NUMBER_PATTERN.match("— 3 —")
+        assert _UNSTRUCTURED_PAGE_NUMBER_PATTERN.match("— 123 —")
+        assert _UNSTRUCTURED_PAGE_NUMBER_PATTERN.match("— 1 —")
+
+    def test_page_number_pattern_invalid(self):
+        """测试无效页码。"""
+        assert not _UNSTRUCTURED_PAGE_NUMBER_PATTERN.match("Page 3")
+        assert not _UNSTRUCTURED_PAGE_NUMBER_PATTERN.match("--- 3 ---")
+
+
+class TestConvertUnstructuredToMarkdown:
+    """测试 convert_unstructured_to_markdown 函数。"""
+
+    def test_skip_rgb_pattern(self):
+        """测试跳过 RGB 噪声。"""
+        try:
+            from unstructured.documents.elements import Text
+        except ImportError:
+            pytest.skip("unstructured 库未安装")
+
+        elements = [Text("R:255 G:128 B:0"), Text("正常文本")]
+        result = convert_unstructured_to_markdown(elements)
+
+        assert "R:255 G:128 B:0" not in result
+        assert "正常文本" in result
+
+    def test_skip_page_number_pattern(self):
+        """测试跳过页码噪声。"""
+        try:
+            from unstructured.documents.elements import Text
+        except ImportError:
+            pytest.skip("unstructured 库未安装")
+
+        elements = [Text("— 3 —"), Text("正常文本")]
+        result = convert_unstructured_to_markdown(elements)
+
+        assert "— 3 —" not in result
+        assert "正常文本" in result
+
+    def test_convert_without_markdownify(self):
+        """测试未安装 markdownify 时的回退行为。"""
+        # 创建简单的 mock 对象
+        class MockElement:
+            def __init__(self, text):
+                self.text = text
+
+        elements = [MockElement("文本1"), MockElement("文本2")]
+        result = convert_unstructured_to_markdown(elements)
+
+        # 应该回退到简单连接文本
+        assert "文本1" in result
+        assert "文本2" in result
+
+
+class TestParseViaMarkitdown:
+    """测试 parse_via_markitdown 函数。"""
+
+    def test_parse_nonexistent_file(self):
+        """测试解析不存在的文件。"""
+        content, error = parse_via_markitdown("/nonexistent/file.txt")
+        assert content is None
+        assert error is not None
+
+
+class TestParseViaDocling:
+    """测试 parse_via_docling 函数。"""
+
+    def test_parse_nonexistent_file(self):
+        """测试解析不存在的文件。"""
+        content, error = parse_via_docling("/nonexistent/file.txt")
+        assert content is None
+        assert error is not None