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。

tests/test_readers/test_pptx/test_consistency.py

@@ -0,0 +1,42 @@
+"""测试所有 PPTX Readers 的一致性。"""
+
+import pytest
+from scripts.readers.pptx import (
+    docling,
+    markitdown,
+    native_xml,
+    python_pptx,
+    unstructured,
+)
+
+
+class TestPptxReadersConsistency:
+    """验证所有 PPTX Readers 解析同一文件时核心文字内容一致。"""
+
+    def test_all_readers_parse_same_content(self, temp_pptx):
+        """测试所有 Readers 解析同一文件时核心内容一致。"""
+        file_path = temp_pptx(slides=[
+            ("测试标题", "这是测试幻灯片内容。"),
+            ("第二页", "第二页的内容。")
+        ])
+
+        parsers = [
+            ("docling", docling.parse),
+            ("markitdown", markitdown.parse),
+            ("native_xml", native_xml.parse),
+            ("python_pptx", python_pptx.parse),
+            ("unstructured", unstructured.parse),
+        ]
+
+        successful_results = []
+        for name, parser in parsers:
+            content, error = parser(file_path)
+            if content is not None and content.strip():
+                successful_results.append((name, content))
+
+        assert len(successful_results) > 0, "没有任何 reader 成功解析文件"
+
+        core_texts = ["测试标题", "幻灯片", "内容", "第二页"]
+        for name, content in successful_results:
+            assert any(text in content for text in core_texts), \
+                f"{name} 解析结果不包含核心内容"

tests/test_readers/test_pptx/test_docling_pptx.py

@@ -0,0 +1,44 @@
+"""测试 Docling PPTX Reader 的解析功能。"""
+
+import pytest
+from scripts.readers.pptx import docling
+
+
+class TestDoclingPptxReaderParse:
+    """测试 Docling PPTX Reader 的 parse 方法。"""
+
+    def test_normal_file(self, temp_pptx):
+        """测试正常 PPTX 文件解析。"""
+        file_path = temp_pptx(slides=[("标题幻灯片", "幻灯片内容"), ("第二页", "第二页内容")])
+        content, error = docling.parse(file_path)
+        if content is not None:
+            assert "标题" in content or "幻灯片" in content or "内容" in content
+
+    def test_file_not_exists(self, tmp_path):
+        """测试文件不存在的情况。"""
+        non_existent_file = str(tmp_path / "non_existent.pptx")
+        content, error = docling.parse(non_existent_file)
+        assert content is None
+        assert error is not None
+
+    def test_empty_file(self, temp_pptx):
+        """测试空 PPTX 文件。"""
+        file_path = temp_pptx()
+        content, error = docling.parse(file_path)
+        assert content is None or content.strip() == ""
+
+    def test_corrupted_file(self, temp_pptx, tmp_path):
+        """测试损坏的 PPTX 文件。"""
+        file_path = temp_pptx(slides=[("测试", "内容")])
+        with open(file_path, "wb") as f:
+            f.write(b"corrupted content")
+        content, error = docling.parse(file_path)
+        assert content is None
+        assert error is not None
+
+    def test_special_chars(self, temp_pptx):
+        """测试特殊字符处理。"""
+        file_path = temp_pptx(slides=[("中文标题 😀", "特殊符号 ©®")])
+        content, error = docling.parse(file_path)
+        if content is not None:
+            assert "中文" in content or "标题" in content

tests/test_readers/test_pptx/test_markitdown_pptx.py

@@ -0,0 +1,44 @@
+"""测试 MarkItDown PPTX Reader 的解析功能。"""
+
+import pytest
+from scripts.readers.pptx import markitdown
+
+
+class TestMarkitdownPptxReaderParse:
+    """测试 MarkItDown PPTX Reader 的 parse 方法。"""
+
+    def test_normal_file(self, temp_pptx):
+        """测试正常 PPTX 文件解析。"""
+        file_path = temp_pptx(slides=[("标题幻灯片", "幻灯片内容"), ("第二页", "第二页内容")])
+        content, error = markitdown.parse(file_path)
+        if content is not None:
+            assert "标题" in content or "幻灯片" in content or "内容" in content
+
+    def test_file_not_exists(self, tmp_path):
+        """测试文件不存在的情况。"""
+        non_existent_file = str(tmp_path / "non_existent.pptx")
+        content, error = markitdown.parse(non_existent_file)
+        assert content is None
+        assert error is not None
+
+    def test_empty_file(self, temp_pptx):
+        """测试空 PPTX 文件。"""
+        file_path = temp_pptx()
+        content, error = markitdown.parse(file_path)
+        assert content is None or content.strip() == ""
+
+    def test_corrupted_file(self, temp_pptx, tmp_path):
+        """测试损坏的 PPTX 文件。"""
+        file_path = temp_pptx(slides=[("测试", "内容")])
+        with open(file_path, "wb") as f:
+            f.write(b"corrupted content")
+        content, error = markitdown.parse(file_path)
+        # MarkItDown 可能会尝试解析任何内容
+        assert content is not None or error is not None
+
+    def test_special_chars(self, temp_pptx):
+        """测试特殊字符处理。"""
+        file_path = temp_pptx(slides=[("中文标题 😀", "特殊符号 ©®")])
+        content, error = markitdown.parse(file_path)
+        if content is not None:
+            assert "中文" in content or "标题" in content

tests/test_readers/test_pptx/test_native_xml_pptx.py

@@ -0,0 +1,44 @@
+"""测试 Native XML PPTX Reader 的解析功能。"""
+
+import pytest
+from scripts.readers.pptx import native_xml
+
+
+class TestNativeXmlPptxReaderParse:
+    """测试 Native XML PPTX Reader 的 parse 方法。"""
+
+    def test_normal_file(self, temp_pptx):
+        """测试正常 PPTX 文件解析。"""
+        file_path = temp_pptx(slides=[("标题幻灯片", "幻灯片内容"), ("第二页", "第二页内容")])
+        content, error = native_xml.parse(file_path)
+        if content is not None:
+            assert "标题" in content or "幻灯片" in content or "内容" in content
+
+    def test_file_not_exists(self, tmp_path):
+        """测试文件不存在的情况。"""
+        non_existent_file = str(tmp_path / "non_existent.pptx")
+        content, error = native_xml.parse(non_existent_file)
+        assert content is None
+        assert error is not None
+
+    def test_empty_file(self, temp_pptx):
+        """测试空 PPTX 文件。"""
+        file_path = temp_pptx()
+        content, error = native_xml.parse(file_path)
+        assert content is None or content.strip() == ""
+
+    def test_corrupted_file(self, temp_pptx, tmp_path):
+        """测试损坏的 PPTX 文件。"""
+        file_path = temp_pptx(slides=[("测试", "内容")])
+        with open(file_path, "wb") as f:
+            f.write(b"corrupted content")
+        content, error = native_xml.parse(file_path)
+        assert content is None
+        assert error is not None
+
+    def test_special_chars(self, temp_pptx):
+        """测试特殊字符处理。"""
+        file_path = temp_pptx(slides=[("中文标题 😀", "特殊符号 ©®")])
+        content, error = native_xml.parse(file_path)
+        if content is not None:
+            assert "中文" in content or "标题" in content

tests/test_readers/test_pptx/test_python_pptx.py

@@ -0,0 +1,121 @@
+"""测试 PPTX Reader 的解析功能。"""
+
+import pytest
+import os
+from scripts.readers.pptx import PptxReader
+
+
+class TestPythonPptxReaderParse:
+    """测试 PPTX Reader 的 parse 方法。"""
+
+    def test_normal_file(self, temp_pptx):
+        """测试正常 PPTX 文件解析。"""
+        # 创建包含多个幻灯片的测试文件
+        file_path = temp_pptx(slides=[
+            ("主标题", "这是第一张幻灯片的内容。"),
+            ("子标题", "这是第二张幻灯片的内容。"),
+        ])
+
+        reader = PptxReader()
+        content, failures = reader.parse(file_path)
+
+        # 验证解析成功
+        assert content is not None, f"解析失败: {failures}"
+        assert len(failures) == 0 or all("成功" in f or not f for f in failures)
+
+        # 验证关键内容存在
+        assert "主标题" in content
+        assert "子标题" in content
+        assert "第一张幻灯片" in content or "第二张幻灯片" in content
+
+    def test_file_not_exists(self, tmp_path):
+        """测试文件不存在的情况。"""
+        non_existent_file = str(tmp_path / "non_existent.pptx")
+
+        reader = PptxReader()
+        content, failures = reader.parse(non_existent_file)
+
+        # 验证返回 None 和错误信息
+        assert content is None
+        assert len(failures) > 0
+        assert any("不存在" in f or "找不到" in f for f in failures)
+
+    def test_empty_file(self, temp_pptx):
+        """测试空 PPTX 文件。"""
+        # 创建没有任何内容的文件
+        file_path = temp_pptx()
+
+        reader = PptxReader()
+        content, failures = reader.parse(file_path)
+
+        # 空文件应该返回 None 或空字符串
+        assert content is None or content.strip() == ""
+
+    def test_corrupted_file(self, temp_pptx, tmp_path):
+        """测试损坏的 PPTX 文件。"""
+        # 先创建正常文件
+        file_path = temp_pptx(slides=[("测试", "测试内容")])
+
+        # 破坏文件内容 - 完全覆盖文件
+        with open(file_path, "wb") as f:
+            f.write(b"corrupted content that is not a valid pptx file")
+
+        reader = PptxReader()
+        content, failures = reader.parse(file_path)
+
+        # 验证返回 None 和错误信息
+        assert content is None
+        assert len(failures) > 0
+
+    def test_special_chars(self, temp_pptx):
+        """测试特殊字符处理。"""
+        special_slides = [
+            ("中文标题", "中文测试内容"),
+            ("Emoji测试", "😀🎉🚀"),
+            ("特殊符号", "©®™°±"),
+            ("混合内容", "Hello你好🎉World世界"),
+        ]
+
+        file_path = temp_pptx(slides=special_slides)
+
+        reader = PptxReader()
+        content, failures = reader.parse(file_path)
+
+        assert content is not None, f"解析失败: {failures}"
+
+        # 验证各种特殊字符都被正确处理
+        assert "中文" in content
+        assert "😀" in content or "🎉" in content  # 至少包含一个 emoji
+        assert "©" in content or "®" in content  # 至少包含一个特殊符号
+        assert "Hello" in content or "World" in content
+
+
+class TestPythonPptxReaderSupports:
+    """测试 PPTX Reader 的 supports 方法。"""
+
+    def test_supports_pptx_extension(self):
+        """测试识别 .pptx 扩展名。"""
+        reader = PptxReader()
+        assert reader.supports("test.pptx") is True
+
+    def test_supports_uppercase_extension(self):
+        """测试识别大写扩展名。"""
+        reader = PptxReader()
+        assert reader.supports("TEST.PPTX") is True
+
+    def test_rejects_unsupported_format(self):
+        """测试拒绝不支持的格式。"""
+        reader = PptxReader()
+        assert reader.supports("test.pdf") is False
+        assert reader.supports("test.txt") is False
+
+    def test_supports_path_with_spaces(self):
+        """测试包含空格的路径。"""
+        reader = PptxReader()
+        assert reader.supports("path with spaces/test.pptx") is True
+
+    def test_supports_absolute_path(self):
+        """测试绝对路径。"""
+        reader = PptxReader()
+        assert reader.supports("/absolute/path/test.pptx") is True
+        assert reader.supports("C:\\Windows\\path\\test.pptx") is True

tests/test_readers/test_pptx/test_unstructured_pptx.py

@@ -0,0 +1,44 @@
+"""测试 Unstructured PPTX Reader 的解析功能。"""
+
+import pytest
+from scripts.readers.pptx import unstructured
+
+
+class TestUnstructuredPptxReaderParse:
+    """测试 Unstructured PPTX Reader 的 parse 方法。"""
+
+    def test_normal_file(self, temp_pptx):
+        """测试正常 PPTX 文件解析。"""
+        file_path = temp_pptx(slides=[("标题幻灯片", "幻灯片内容"), ("第二页", "第二页内容")])
+        content, error = unstructured.parse(file_path)
+        if content is not None:
+            assert "标题" in content or "幻灯片" in content or "内容" in content
+
+    def test_file_not_exists(self, tmp_path):
+        """测试文件不存在的情况。"""
+        non_existent_file = str(tmp_path / "non_existent.pptx")
+        content, error = unstructured.parse(non_existent_file)
+        assert content is None
+        assert error is not None
+
+    def test_empty_file(self, temp_pptx):
+        """测试空 PPTX 文件。"""
+        file_path = temp_pptx()
+        content, error = unstructured.parse(file_path)
+        assert content is None or content.strip() == ""
+
+    def test_corrupted_file(self, temp_pptx, tmp_path):
+        """测试损坏的 PPTX 文件。"""
+        file_path = temp_pptx(slides=[("测试", "内容")])
+        with open(file_path, "wb") as f:
+            f.write(b"corrupted content")
+        content, error = unstructured.parse(file_path)
+        assert content is None
+        assert error is not None
+
+    def test_special_chars(self, temp_pptx):
+        """测试特殊字符处理。"""
+        file_path = temp_pptx(slides=[("中文标题 😀", "特殊符号 ©®")])
+        content, error = unstructured.parse(file_path)
+        if content is not None:
+            assert "中文" in content or "标题" in content