test: 添加全面的测试套件，覆盖所有 Reader 实现

- 测试数量从 83 个增加到 193 个 (+132%)
- 代码覆盖率从 48% 提升到 69% (+44%)
- 为每种文档格式的所有 Reader 实现创建独立测试
- 添加跨 Reader 的一致性验证测试
- 新增 4 个测试规范 (cli-testing, exception-testing, reader-testing, test-fixtures)
- 更新 README 测试统计信息

测试覆盖:
- DOCX: python-docx, markitdown, docling, native-xml, pypandoc, unstructured
- PDF: pypdf, markitdown, docling, docling-ocr, unstructured, unstructured-ocr
- HTML: html2text, markitdown, trafilatura, domscribe
- PPTX: python-pptx, markitdown, docling, native-xml, unstructured
- XLSX: pandas, markitdown, docling, native-xml, unstructured
- CLI: 所有命令行选项和错误处理

所有 193 个测试通过。

scripts/__init__.py

@@ -0,0 +1 @@
+"""lyxy-document 核心模块。"""

scripts/core/parser.py

@@ -50,13 +50,13 @@ def output_result(
     elif args.lines:
         print(len(content.split("\n")))
     elif args.titles:
-        from core.markdown import extract_titles
+        from scripts.core.markdown import extract_titles
 
         titles = extract_titles(content)
         for title in titles:
             print(title)
     elif args.title_content:
-        from core.markdown import extract_title_content
+        from scripts.core.markdown import extract_title_content
 
         title_content = extract_title_content(content, args.title_content)
         if title_content is None:
@@ -64,7 +64,7 @@ def output_result(
             sys.exit(1)
         print(title_content, end="")
     elif args.search:
-        from core.markdown import search_markdown
+        from scripts.core.markdown import search_markdown
 
         search_result = search_markdown(content, args.search, args.context)
         if search_result is None:

scripts/readers/docx/__init__.py

@@ -32,7 +32,7 @@ class DocxReader(BaseReader):
         return [".docx"]
 
     def supports(self, file_path: str) -> bool:
-        return file_path.endswith('.docx')
+        return file_path.lower().endswith('.docx')
 
     def parse(self, file_path: str) -> Tuple[Optional[str], List[str]]:
         failures = []

scripts/readers/html/__init__.py

@@ -31,7 +31,7 @@ class HtmlReader(BaseReader):
         return [".html", ".htm"]
 
     def supports(self, file_path: str) -> bool:
-        return is_url(file_path) or file_path.endswith(('.html', '.htm'))
+        return is_url(file_path) or file_path.lower().endswith(('.html', '.htm'))
 
     def download_and_parse(self, url: str) -> Tuple[Optional[str], List[str]]:
         """下载 URL 并解析"""
@@ -74,6 +74,10 @@ class HtmlReader(BaseReader):
         if is_url(file_path):
             return self.download_and_parse(file_path)
 
+        # 检查文件是否存在
+        if not os.path.exists(file_path):
+            return None, ["文件不存在"]
+
         # 读取本地 HTML 文件，使用编码检测
         html_content, error = encoding_detection.read_text_file(file_path)
         if error:

scripts/readers/pdf/__init__.py

@@ -32,7 +32,7 @@ class PdfReader(BaseReader):
         return [".pdf"]
 
     def supports(self, file_path: str) -> bool:
-        return file_path.endswith('.pdf')
+        return file_path.lower().endswith('.pdf')
 
     def parse(self, file_path: str) -> Tuple[Optional[str], List[str]]:
         failures = []

scripts/readers/pptx/__init__.py

@@ -30,7 +30,7 @@ class PptxReader(BaseReader):
         return [".pptx"]
 
     def supports(self, file_path: str) -> bool:
-        return file_path.endswith('.pptx')
+        return file_path.lower().endswith('.pptx')
 
     def parse(self, file_path: str) -> Tuple[Optional[str], List[str]]:
         failures = []

scripts/readers/xlsx/__init__.py

@@ -30,7 +30,7 @@ class XlsxReader(BaseReader):
         return [".xlsx"]
 
     def supports(self, file_path: str) -> bool:
-        return file_path.endswith('.xlsx')
+        return file_path.lower().endswith('.xlsx')
 
     def parse(self, file_path: str) -> Tuple[Optional[str], List[str]]:
         failures = []