lyxy-document/tests/test_core/test_markdown_extra.py

"""测试 markdown 模块的高级功能（extract_title_content, search_markdown）。"""

import pytest

from core.markdown import extract_title_content, search_markdown


class TestExtractTitleContent:
    """测试 extract_title_content 函数。"""

    def test_extract_simple_title(self):
        """测试提取简单标题。"""
        markdown = """# 目标标题

这是标题下的内容。
第二段内容。"""

        result = extract_title_content(markdown, "目标标题")

        assert result is not None
        assert "# 目标标题" in result
        assert "这是标题下的内容" in result

    def test_extract_with_subtitles(self):
        """测试提取包含子标题的内容。"""
        markdown = """# 目标标题

这是标题下的内容。

## 子标题

子标题下的内容。

### 孙子标题

更深层的内容。"""

        result = extract_title_content(markdown, "目标标题")

        assert result is not None
        assert "# 目标标题" in result
        assert "## 子标题" in result
        assert "### 孙子标题" in result

    def test_extract_stop_at_sibling_title(self):
        """测试在同级标题处停止。"""
        markdown = """# 目标标题

目标内容。

# 另一个标题

另一个内容。"""

        result = extract_title_content(markdown, "目标标题")

        assert result is not None
        assert "# 目标标题" in result
        assert "目标内容" in result
        assert "# 另一个标题" not in result

    def test_extract_with_parent_titles(self):
        """测试包含父级标题。"""
        markdown = """# 父级标题

父级内容。

## 目标标题

目标内容。

### 子标题

子内容。"""

        result = extract_title_content(markdown, "目标标题")

        assert result is not None
        assert "# 父级标题" in result
        assert "## 目标标题" in result
        assert "### 子标题" in result

    def test_extract_multiple_matches(self):
        """测试多个匹配标题的情况。"""
        markdown = """# 第一章

## 目标标题

第一章的目标内容。

# 第二章

## 目标标题

第二章的目标内容。"""

        result = extract_title_content(markdown, "目标标题")

        assert result is not None
        assert "第一章的目标内容" in result
        assert "第二章的目标内容" in result
        assert "---" in result

    def test_title_not_found(self):
        """测试标题不存在的情况。"""
        markdown = "# 其他标题\n内容"

        result = extract_title_content(markdown, "不存在的标题")

        assert result is None

    def test_deep_nested_title(self):
        """测试深层嵌套标题。"""
        markdown = """# H1

## H2

### H3

#### 目标标题

目标内容。"""

        result = extract_title_content(markdown, "目标标题")

        assert result is not None
        assert "# H1" in result
        assert "## H2" in result
        assert "### H3" in result
        assert "#### 目标标题" in result


class TestSearchMarkdown:
    """测试 search_markdown 函数。"""

    def test_search_simple_pattern(self):
        """测试简单搜索模式。"""
        content = """第一行
第二行
包含关键词的行
第四行"""

        result = search_markdown(content, "关键词", context_lines=0)

        assert result is not None
        assert "关键词" in result

    def test_search_with_context(self):
        """测试带上下文的搜索。"""
        content = """行1
行2
关键词行
行4
行5"""

        result = search_markdown(content, "关键词", context_lines=1)

        assert result is not None
        assert "关键词" in result
        assert "行2" in result or "行4" in result

    def test_search_no_match(self):
        """测试无匹配的情况。"""
        content = "普通内容"

        result = search_markdown(content, "不存在的内容", context_lines=0)

        assert result is None

    def test_search_empty_content(self):
        """测试空内容。"""
        result = search_markdown("", "关键词", context_lines=0)

        assert result is None

    def test_search_invalid_regex(self):
        """测试无效正则表达式。"""
        content = "内容"

        result = search_markdown(content, "[invalid", context_lines=0)

        assert result is None

    def test_search_negative_context(self):
        """测试负的上下文行数。"""
        content = "内容"

        with pytest.raises(ValueError):
            search_markdown(content, "内容", context_lines=-1)

    def test_search_multiple_matches_merged(self):
        """测试多个匹配合并。"""
        content = """行1
行2
匹配1
行4
行5
匹配2
行7
行8"""

        result = search_markdown(content, "匹配", context_lines=1)

        assert result is not None
        assert "匹配1" in result
        assert "匹配2" in result

    def test_search_ignore_blank_lines_in_context(self):
        """测试上下文计算忽略空行。"""
        content = """行1

行2
关键词

行4
行5"""

        result = search_markdown(content, "关键词", context_lines=1)

        assert result is not None
        assert "关键词" in result

    def test_search_with_regex(self):
        """测试使用正则表达式搜索。"""
        content = """apple
banana
cherry
date"""

        result = search_markdown(content, "^b", context_lines=0)

        assert result is not None
        assert "banana" in result