hos-m2f 0.5.3__py3-none-any.whl → 0.5.5__py3-none-any.whl

hos_m2f/converters/pdf_to_md.py

@@ -0,0 +1,120 @@
+"""PDF到Markdown格式转换器"""
+
+from typing import Any, Optional, Dict
+from hos_m2f.converters.base_converter import BaseConverter
+
+# 延迟导入PyPDF2
+pypdf2_available = False
+PdfReader = None
+
+
+def _check_pypdf2():
+    """检查PyPDF2是否可用"""
+    global pypdf2_available, PdfReader
+    if not pypdf2_available:
+        try:
+            from PyPDF2 import PdfReader
+            pypdf2_available = True
+        except ImportError as e:
+            print(f"Warning: PyPDF2 not available: {e}")
+            print("PDF to Markdown conversion is disabled.")
+
+
+class PDFToMDConverter(BaseConverter):
+    """PDF到Markdown格式转换器"""
+    
+    def convert(self, input_content: bytes, options: Optional[Dict[str, Any]] = None) -> bytes:
+        """将PDF转换为Markdown
+        
+        Args:
+            input_content: PDF文件的二进制数据
+            options: 转换选项
+            
+        Returns:
+            bytes: Markdown文件的二进制数据
+        """
+        # 检查PyPDF2是否可用
+        _check_pypdf2()
+        if not pypdf2_available:
+            raise ImportError("PyPDF2 is not available. PDF to Markdown conversion is disabled.")
+        
+        if options is None:
+            options = {}
+        
+        # 解析PDF内容
+        markdown_content = self._parse_pdf(input_content, options)
+        
+        return markdown_content.encode('utf-8')
+    
+    def _parse_pdf(self, pdf_content: bytes, options: Dict[str, Any]) -> str:
+        """解析PDF内容并转换为Markdown"""
+        import io
+        
+        # 创建PDF阅读器
+        pdf_reader = PdfReader(io.BytesIO(pdf_content))
+        
+        # 提取文本
+        text_content = []
+        for page_num in range(len(pdf_reader.pages)):
+            page = pdf_reader.pages[page_num]
+            text = page.extract_text()
+            if text:
+                text_content.append(text)
+        
+        # 合并文本
+        full_text = '\n\n'.join(text_content)
+        
+        # 转换为Markdown
+        markdown_content = self._text_to_markdown(full_text, options)
+        
+        return markdown_content
+    
+    def _text_to_markdown(self, text: str, options: Dict[str, Any]) -> str:
+        """将纯文本转换为Markdown"""
+        import re
+        
+        # 分割行
+        lines = text.split('\n')
+        
+        # 处理标题
+        markdown_lines = []
+        for line in lines:
+            line = line.strip()
+            if not line:
+                markdown_lines.append('')
+                continue
+            
+            # 简单的标题识别
+            # 假设以数字开头的行可能是标题
+            if re.match(r'^\d+\.', line):
+                # 检查数字级别
+                match = re.match(r'^(\d+)\.', line)
+                if match:
+                    level = len(match.group(1).split('.'))
+                    if level <= 6:
+                        markdown_lines.append(f'{'#' * level} {line}')
+                        continue
+            
+            # 检查是否是大写标题
+            if line.isupper() and len(line) < 50:
+                markdown_lines.append(f'## {line}')
+                continue
+            
+            # 普通行
+            markdown_lines.append(line)
+        
+        # 合并行
+        markdown_content = '\n'.join(markdown_lines)
+        
+        # 处理列表
+        markdown_content = re.sub(r'^\s*\-\s(.*)$', r'* \1', markdown_content, flags=re.MULTILINE)
+        markdown_content = re.sub(r'^\s*\*\s(.*)$', r'* \1', markdown_content, flags=re.MULTILINE)
+        
+        # 处理粗体
+        markdown_content = re.sub(r'\b([A-Z]{3,})\b', r'**\1**', markdown_content)
+        
+        return markdown_content
+    
+    def get_supported_formats(self) -> tuple:
+        """获取支持的格式"""
+        return ('pdf', 'md')

{hos_m2f-0.5.3.dist-info → hos_m2f-0.5.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hos-m2f
-Version: 0.5.3
+Version: 0.5.5
 Summary: HOS-M2F: Markdown to Industry Standard Format Compiler Engine
 Author: HOS Team
 Author-email: team@hos-m2f.com

hos_m2f-0.5.5.dist-info/RECORD

@@ -0,0 +1,26 @@
+hos_m2f/__init__.py,sha256=v4k4TbKzPb3nbzgKJHaID3QTSpmTvAsGVHZ-poa870I,178
+hos_m2f/cli/__init__.py,sha256=9Ljh6fmOOFYD39fnew21icQYnIW7sElBo2qWCUNV9KM,57
+hos_m2f/cli/cli.py,sha256=0bWtYmOoNE8h_rrBlwS-4yJwIRnRTtuBx3DWnMkZ4Qo,11920
+hos_m2f/converters/__init__.py,sha256=d88A1sTrQsoMzrTipg7jKTWfI83GJzlRFVFNibajeag,971
+hos_m2f/converters/base_converter.py,sha256=4xqcAFMT82va6VesgM_HybUPIpP77x0DrQSYzb1jf28,696
+hos_m2f/converters/docx_to_md.py,sha256=_HBp3TOD9ZkTFhHR_f3ObLlpDcv0tnSPjPfeGxuvhjM,3064
+hos_m2f/converters/epub_to_md.py,sha256=cFfHmK4IrJKwzEWVE3ue7Jw8tBfWu1q7wG9o7oMf4Pw,4612
+hos_m2f/converters/html_to_md.py,sha256=26GqdynSxKKO2NTxPKgfFs9bTuisLaEIJdBhz4CJ5Eg,4487
+hos_m2f/converters/json_to_md.py,sha256=jeLBQ3jTkgA5a2Kr2gsOPjZB-D4PZxumciFHbyPKNmc,3670
+hos_m2f/converters/md_to_docx.py,sha256=GFAAQppSiCff7pkDAPEmvuoj_f4DMzNWHsbv-9cbqmU,12248
+hos_m2f/converters/md_to_epub.py,sha256=wNoniOSgIz7qiuIagJzqsF6f4pu_HLUigq-w0a_HoFg,2572
+hos_m2f/converters/md_to_html.py,sha256=Pn5K6_QiCdasK1M3hdyr4jlTzzu3OpQLJ-wznGiomPo,2502
+hos_m2f/converters/md_to_json.py,sha256=4VzUQFQ8nStmqm7td6MOFKji25hSiydMZhVJcsRHdYU,11246
+hos_m2f/converters/md_to_latex.py,sha256=7Fra7f984XLLWJTSbjPJP3ljSUldvpc2sqF2QyyPUJg,2348
+hos_m2f/converters/md_to_xml.py,sha256=ARuf4rEX4Of-VdGJI45lAejJV8OmtlHQMK8rltzg6B0,14217
+hos_m2f/converters/pdf_to_md.py,sha256=CgKrvv3CWc6H94nNrDO5nLIegttDzokDpoP2E2oSmEs,3851
+hos_m2f/converters/xml_to_md.py,sha256=zOkaEaSZdvyHag05kIHiWF4VyGMMjfmWmBllBpzwJ4E,4051
+tests/__init__.py,sha256=q1Fh8atmZO-c9dA8JDMvlWaIZxlwABwe_HgNgFNDKJc,16
+tests/test_converters.py,sha256=0sAG1fLR0UjJIWzlKWBR2QU7yl8a8LP8NwwSaU1TI5E,5150
+tests/test_latex.py,sha256=-KCCYKRDu6RoI3gOt0HTtExsW2IJ6KoNfIWeocbdFyY,6619
+tests/test_modes.py,sha256=FFZN1cp4sUJUR5fjbZXo2z-Z4Q5akCRBmSIiR7MCdVA,5887
+hos_m2f-0.5.5.dist-info/METADATA,sha256=qzJMupv3Rq2KQqfw2sJb025gy5nSzJOq6kjuyvqCeXc,1764
+hos_m2f-0.5.5.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+hos_m2f-0.5.5.dist-info/entry_points.txt,sha256=1opnVMOGIufdlQMvWG_e-oTUS0Yca5ysnFKhmYvBmTM,76
+hos_m2f-0.5.5.dist-info/top_level.txt,sha256=EOB5321A6FNFviV_29qnjHtmLG-F6peX7v5s9Rw96V0,14
+hos_m2f-0.5.5.dist-info/RECORD,,

{hos_m2f-0.5.3.dist-info → hos_m2f-0.5.5.dist-info}/entry_points.txt

@@ -1,2 +1,3 @@
 [console_scripts]
+hos = hos_m2f.cli.cli:main
 hos-m2f = hos_m2f.cli.cli:main

{hos_m2f-0.5.3.dist-info → hos_m2f-0.5.5.dist-info}/top_level.txt

@@ -1 +1,2 @@
 hos_m2f
+tests

tests/__init__.py

@@ -0,0 +1 @@
+"""测试包"""

tests/test_converters.py

@@ -0,0 +1,179 @@
+"""测试转换器模块"""
+
+import unittest
+import os
+import tempfile
+from hos_m2f.converters.md_to_docx import MDToDOCXConverter
+from hos_m2f.converters.md_to_html import MDToHTMLConverter
+from hos_m2f.converters.md_to_json import MDToJSONConverter
+from hos_m2f.converters.md_to_xml import MDToXMLConverter
+from hos_m2f.converters.md_to_epub import MDToEPUBConverter
+
+
+class TestConverters(unittest.TestCase):
+    """测试转换器"""
+    
+    def setUp(self):
+        """设置测试环境"""
+        # 创建测试用的Markdown内容
+        self.test_content = """
+# 测试文档
+
+这是一个测试文档，用于测试各种格式转换器。
+
+## 章节1
+
+这是章节1的内容。
+
+### 子章节1.1
+
+这是子章节1.1的内容。
+
+## 章节2
+
+这是章节2的内容。
+
+### 表格测试
+
+| 列1 | 列2 | 列3 |
+| --- | --- | --- |
+| 行1 | 行1 | 行1 |
+| 行2 | 行2 | 行2 |
+
+### Mermaid图表测试
+
+```mermaid
+graph TD
+    A[开始] --> B[处理]
+    B --> C[结束]
+```
+
+### 链接测试
+
+[百度](https://www.baidu.com)
+
+### 图片测试
+
+![测试图片](https://example.com/test.jpg)
+
+### 格式化测试
+
+*斜体文本*
+
+**粗体文本**
+
+`代码`
+
+```python
+print("Hello, world!")
+```
+        """.strip()
+    
+    def test_md_to_docx(self):
+        """测试Markdown到DOCX转换"""
+        converter = MDToDOCXConverter()
+        result = converter.convert(self.test_content)
+        self.assertIsInstance(result, bytes)
+        self.assertGreater(len(result), 0)
+        
+        # 保存为临时文件，以便手动检查
+        with tempfile.NamedTemporaryFile(suffix=".docx", delete=False) as tmp:
+            tmp.write(result)
+            tmp_path = tmp.name
+        
+        try:
+            # 验证文件存在且大小大于0
+            self.assertTrue(os.path.exists(tmp_path))
+            self.assertGreater(os.path.getsize(tmp_path), 0)
+        finally:
+            # 清理临时文件
+            if os.path.exists(tmp_path):
+                os.unlink(tmp_path)
+    
+    def test_md_to_html(self):
+        """测试Markdown到HTML转换"""
+        converter = MDToHTMLConverter()
+        result = converter.convert(self.test_content)
+        self.assertIsInstance(result, bytes)
+        self.assertGreater(len(result), 0)
+        
+        # 保存为临时文件，以便手动检查
+        with tempfile.NamedTemporaryFile(suffix=".html", delete=False) as tmp:
+            tmp.write(result)
+            tmp_path = tmp.name
+        
+        try:
+            # 验证文件存在且大小大于0
+            self.assertTrue(os.path.exists(tmp_path))
+            self.assertGreater(os.path.getsize(tmp_path), 0)
+        finally:
+            # 清理临时文件
+            if os.path.exists(tmp_path):
+                os.unlink(tmp_path)
+    
+    def test_md_to_json(self):
+        """测试Markdown到JSON转换"""
+        converter = MDToJSONConverter()
+        result = converter.convert(self.test_content)
+        self.assertIsInstance(result, bytes)
+        self.assertGreater(len(result), 0)
+        
+        # 保存为临时文件，以便手动检查
+        with tempfile.NamedTemporaryFile(suffix=".json", delete=False) as tmp:
+            tmp.write(result)
+            tmp_path = tmp.name
+        
+        try:
+            # 验证文件存在且大小大于0
+            self.assertTrue(os.path.exists(tmp_path))
+            self.assertGreater(os.path.getsize(tmp_path), 0)
+        finally:
+            # 清理临时文件
+            if os.path.exists(tmp_path):
+                os.unlink(tmp_path)
+    
+    def test_md_to_xml(self):
+        """测试Markdown到XML转换"""
+        converter = MDToXMLConverter()
+        result = converter.convert(self.test_content)
+        self.assertIsInstance(result, bytes)
+        self.assertGreater(len(result), 0)
+        
+        # 保存为临时文件，以便手动检查
+        with tempfile.NamedTemporaryFile(suffix=".xml", delete=False) as tmp:
+            tmp.write(result)
+            tmp_path = tmp.name
+        
+        try:
+            # 验证文件存在且大小大于0
+            self.assertTrue(os.path.exists(tmp_path))
+            self.assertGreater(os.path.getsize(tmp_path), 0)
+        finally:
+            # 清理临时文件
+            if os.path.exists(tmp_path):
+                os.unlink(tmp_path)
+    
+    def test_md_to_epub(self):
+        """测试Markdown到EPUB转换"""
+        converter = MDToEPUBConverter()
+        result = converter.convert(self.test_content)
+        self.assertIsInstance(result, bytes)
+        self.assertGreater(len(result), 0)
+        
+        # 保存为临时文件，以便手动检查
+        with tempfile.NamedTemporaryFile(suffix=".epub", delete=False) as tmp:
+            tmp.write(result)
+            tmp_path = tmp.name
+        
+        try:
+            # 验证文件存在且大小大于0
+            self.assertTrue(os.path.exists(tmp_path))
+            self.assertGreater(os.path.getsize(tmp_path), 0)
+        finally:
+            # 清理临时文件
+            if os.path.exists(tmp_path):
+                os.unlink(tmp_path)
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/test_latex.py

@@ -0,0 +1,182 @@
+"""测试LaTeX渲染器和转换器"""
+
+import unittest
+import os
+import tempfile
+from hos_m2f.renderers.latex_renderer import LaTeXRenderer
+from hos_m2f.converters.md_to_latex import MDToLaTeXConverter
+
+
+class TestLaTeX(unittest.TestCase):
+    """测试LaTeX渲染器和转换器"""
+    
+    def setUp(self):
+        """设置测试环境"""
+        # 创建测试用的Markdown内容
+        self.test_content = """
+# 测试文档
+
+## 摘要
+
+这是一个测试文档，用于测试LaTeX渲染功能。
+
+## 引言
+
+这是引言章节的内容。
+
+### 背景
+
+这是背景部分的内容。
+
+## 方法
+
+这是方法章节的内容。
+
+### 实验设计
+
+这是实验设计部分的内容。
+
+## 结果
+
+这是结果章节的内容。
+
+### 数据表格
+
+| 列1 | 列2 | 列3 |
+| --- | --- | --- |
+| 行1 | 行1 | 行1 |
+| 行2 | 行2 | 行2 |
+
+### 代码示例
+
+```python
+print("Hello, world!")
+```
+
+## 讨论
+
+这是讨论章节的内容。
+
+## 结论
+
+这是结论章节的内容。
+
+## 参考文献
+
+[1] 参考文献1
+[2] 参考文献2
+        """.strip()
+        
+        # 创建测试用的结构化内容
+        self.structured_content = {
+            "metadata": {
+                "title": "测试文档",
+                "author": "测试作者",
+                "date": "2023-01-01",
+                "abstract": "这是一个测试文档，用于测试LaTeX渲染功能。",
+                "keywords": ["测试", "LaTeX", "渲染"]
+            },
+            "structure": [
+                {"level": 1, "title": "测试文档", "line_number": 1},
+                {"level": 2, "title": "摘要", "line_number": 3},
+                {"level": 2, "title": "引言", "line_number": 7},
+                {"level": 3, "title": "背景", "line_number": 9},
+                {"level": 2, "title": "方法", "line_number": 13},
+                {"level": 3, "title": "实验设计", "line_number": 15},
+                {"level": 2, "title": "结果", "line_number": 19},
+                {"level": 3, "title": "数据表格", "line_number": 21},
+                {"level": 3, "title": "代码示例", "line_number": 29},
+                {"level": 2, "title": "讨论", "line_number": 35},
+                {"level": 2, "title": "结论", "line_number": 39},
+                {"level": 2, "title": "参考文献", "line_number": 43}
+            ],
+            "chapters": [
+                {"title": "测试文档", "content": "", "level": 1, "start_line": 1, "end_line": 1},
+                {"title": "摘要", "content": "这是一个测试文档，用于测试LaTeX渲染功能。", "level": 2, "start_line": 3, "end_line": 5},
+                {"title": "引言", "content": "这是引言章节的内容。", "level": 2, "start_line": 7, "end_line": 8},
+                {"title": "背景", "content": "这是背景部分的内容。", "level": 3, "start_line": 9, "end_line": 11},
+                {"title": "方法", "content": "这是方法章节的内容。", "level": 2, "start_line": 13, "end_line": 14},
+                {"title": "实验设计", "content": "这是实验设计部分的内容。", "level": 3, "start_line": 15, "end_line": 17},
+                {"title": "结果", "content": "这是结果章节的内容。", "level": 2, "start_line": 19, "end_line": 20},
+                {"title": "数据表格", "content": "| 列1 | 列2 | 列3 |\n| --- | --- | --- |\n| 行1 | 行1 | 行1 |\n| 行2 | 行2 | 行2 |", "level": 3, "start_line": 21, "end_line": 28},
+                {"title": "代码示例", "content": "```python\nprint(\"Hello, world!\")\n```", "level": 3, "start_line": 29, "end_line": 34},
+                {"title": "讨论", "content": "这是讨论章节的内容。", "level": 2, "start_line": 35, "end_line": 37},
+                {"title": "结论", "content": "这是结论章节的内容。", "level": 2, "start_line": 39, "end_line": 41},
+                {"title": "参考文献", "content": "[1] 参考文献1\n[2] 参考文献2", "level": 2, "start_line": 43, "end_line": 46}
+            ],
+            "references": [
+                {"text": "参考文献1"},
+                {"text": "参考文献2"}
+            ]
+        }
+    
+    def test_latex_renderer(self):
+        """测试LaTeX渲染器"""
+        renderer = LaTeXRenderer()
+        
+        # 测试渲染功能
+        latex_content = renderer.render(self.structured_content)
+        self.assertIsInstance(latex_content, bytes)
+        self.assertGreater(len(latex_content), 0)
+        
+        # 保存为临时文件，以便手动检查
+        with tempfile.NamedTemporaryFile(suffix=".tex", delete=False) as tmp:
+            tmp.write(latex_content)
+            tmp_path = tmp.name
+        
+        try:
+            # 验证文件存在且大小大于0
+            self.assertTrue(os.path.exists(tmp_path))
+            self.assertGreater(os.path.getsize(tmp_path), 0)
+        finally:
+            # 清理临时文件
+            if os.path.exists(tmp_path):
+                os.unlink(tmp_path)
+    
+    def test_md_to_latex_converter(self):
+        """测试Markdown到LaTeX转换器"""
+        converter = MDToLaTeXConverter()
+        
+        # 测试转换功能
+        result = converter.convert(self.test_content)
+        self.assertIsInstance(result, bytes)
+        self.assertGreater(len(result), 0)
+        
+        # 保存为临时文件，以便手动检查
+        with tempfile.NamedTemporaryFile(suffix=".tex", delete=False) as tmp:
+            tmp.write(result)
+            tmp_path = tmp.name
+        
+        try:
+            # 验证文件存在且大小大于0
+            self.assertTrue(os.path.exists(tmp_path))
+            self.assertGreater(os.path.getsize(tmp_path), 0)
+        finally:
+            # 清理临时文件
+            if os.path.exists(tmp_path):
+                os.unlink(tmp_path)
+    
+    def test_latex_with_options(self):
+        """测试带选项的LaTeX渲染"""
+        renderer = LaTeXRenderer()
+        converter = MDToLaTeXConverter()
+        
+        # 测试带选项的渲染
+        options = {
+            "document_class": "article",
+            "document_options": "a4paper, 12pt",
+            "table_of_contents": True
+        }
+        
+        latex_content = renderer.render(self.structured_content, options)
+        self.assertIsInstance(latex_content, bytes)
+        self.assertGreater(len(latex_content), 0)
+        
+        # 测试带选项的转换
+        result = converter.convert(self.test_content, options)
+        self.assertIsInstance(result, bytes)
+        self.assertGreater(len(result), 0)
+
+
+if __name__ == '__main__':
+    unittest.main()