hos-m2f 0.5.1__py3-none-any.whl → 0.5.2__py3-none-any.whl

hos_m2f/converters/md_to_xml.py

@@ -0,0 +1,362 @@
+"""Markdown到XML格式转换器"""
+
+from typing import Any, Optional, Dict
+from hos_m2f.converters.base_converter import BaseConverter
+import mistune
+
+
+class MDToXMLConverter(BaseConverter):
+    """Markdown到XML格式转换器"""
+    
+    def convert(self, input_content: str, options: Optional[Dict[str, Any]] = None) -> bytes:
+        """将Markdown转换为XML
+        
+        Args:
+            input_content: Markdown内容
+            options: 转换选项
+            
+        Returns:
+            bytes: XML文件的二进制数据
+        """
+        if options is None:
+            options = {}
+        
+        # 解析Markdown
+        structure = self._parse_markdown(input_content)
+        
+        # 转换为XML
+        xml_content = self._structure_to_xml(structure)
+        
+        # 生成完整的XML文档
+        full_xml = f'''
+        <?xml version="1.0" encoding="UTF-8"?>
+        <document>
+            {xml_content}
+        </document>
+        '''
+        
+        return full_xml.encode('utf-8')
+    
+    def _parse_markdown(self, content: str) -> Dict[str, Any]:
+        """解析Markdown内容为结构化数据
+        
+        Args:
+            content: Markdown内容
+            
+        Returns:
+            Dict[str, Any]: 结构化数据
+        """
+        lines = content.split('\n')
+        structure = {
+            'type': 'document',
+            'children': [],
+            'metadata': {}
+        }
+        
+        current_heading = None
+        current_level = 0
+        current_paragraph = []
+        current_list = None
+        current_list_items = []
+        list_level = 0
+        
+        # 解析YAML头
+        if lines and lines[0] == '---':
+            metadata = []
+            for i, line in enumerate(lines[1:]):
+                if line == '---':
+                    break
+                metadata.append(line)
+            
+            # 解析YAML元数据
+            if metadata:
+                import yaml
+                try:
+                    metadata_content = '\n'.join(metadata)
+                    structure['metadata'] = yaml.safe_load(metadata_content)
+                except Exception:
+                    pass
+            
+            # 跳过YAML头
+            lines = lines[i+2:]
+        
+        # 解析内容
+        for line in lines:
+            line = line.rstrip()
+            
+            # 处理标题
+            if line.startswith('#'):
+                # 保存当前段落
+                if current_paragraph:
+                    structure['children'].append({
+                        'type': 'paragraph',
+                        'content': '\n'.join(current_paragraph)
+                    })
+                    current_paragraph = []
+                
+                # 保存当前列表
+                if current_list is not None:
+                    structure['children'].append({
+                        'type': 'list',
+                        'ordered': current_list,
+                        'items': current_list_items
+                    })
+                    current_list = None
+                    current_list_items = []
+                
+                # 解析标题
+                level = len(line.split(' ')[0])
+                title = line[level:].strip()
+                structure['children'].append({
+                    'type': 'heading',
+                    'level': level,
+                    'content': title
+                })
+                current_heading = title
+                current_level = level
+            
+            # 处理有序列表
+            elif line.startswith('1. ') or line.startswith('\t1. ') or line.startswith('  1. '):
+                # 保存当前段落
+                if current_paragraph:
+                    structure['children'].append({
+                        'type': 'paragraph',
+                        'content': '\n'.join(current_paragraph)
+                    })
+                    current_paragraph = []
+                
+                # 开始新列表
+                if current_list is None:
+                    current_list = True
+                elif current_list != True:
+                    structure['children'].append({
+                        'type': 'list',
+                        'ordered': current_list,
+                        'items': current_list_items
+                    })
+                    current_list = True
+                    current_list_items = []
+                
+                # 解析列表项
+                content = line.lstrip('1234567890. \t')
+                current_list_items.append({
+                    'type': 'list_item',
+                    'content': content
+                })
+            
+            # 处理无序列表
+            elif line.startswith('- ') or line.startswith('* ') or line.startswith('+ ') or \
+                 line.startswith('\t- ') or line.startswith('\t* ') or line.startswith('\t+ ') or \
+                 line.startswith('  - ') or line.startswith('  * ') or line.startswith('  + '):
+                # 保存当前段落
+                if current_paragraph:
+                    structure['children'].append({
+                        'type': 'paragraph',
+                        'content': '\n'.join(current_paragraph)
+                    })
+                    current_paragraph = []
+                
+                # 开始新列表
+                if current_list is None:
+                    current_list = False
+                elif current_list != False:
+                    structure['children'].append({
+                        'type': 'list',
+                        'ordered': current_list,
+                        'items': current_list_items
+                    })
+                    current_list = False
+                    current_list_items = []
+                
+                # 解析列表项
+                content = line.lstrip('-*+ \t')
+                current_list_items.append({
+                    'type': 'list_item',
+                    'content': content
+                })
+            
+            # 处理代码块
+            elif line.startswith('```'):
+                # 保存当前段落
+                if current_paragraph:
+                    structure['children'].append({
+                        'type': 'paragraph',
+                        'content': '\n'.join(current_paragraph)
+                    })
+                    current_paragraph = []
+                
+                # 保存当前列表
+                if current_list is not None:
+                    structure['children'].append({
+                        'type': 'list',
+                        'ordered': current_list,
+                        'items': current_list_items
+                    })
+                    current_list = None
+                    current_list_items = []
+                
+                # 解析代码块
+                code_lines = []
+                language = line[3:].strip()
+                
+                # 读取代码内容
+                for i, code_line in enumerate(lines[lines.index(line)+1:]):
+                    if code_line.startswith('```'):
+                        break
+                    code_lines.append(code_line)
+                
+                structure['children'].append({
+                    'type': 'code_block',
+                    'language': language,
+                    'content': '\n'.join(code_lines)
+                })
+                
+                # 跳过已处理的代码行
+                lines = lines[:lines.index(line)] + lines[lines.index(line)+i+2:]
+            
+            # 处理表格
+            elif line.startswith('|') and '|' in line[1:]:
+                # 保存当前段落
+                if current_paragraph:
+                    structure['children'].append({
+                        'type': 'paragraph',
+                        'content': '\n'.join(current_paragraph)
+                    })
+                    current_paragraph = []
+                
+                # 保存当前列表
+                if current_list is not None:
+                    structure['children'].append({
+                        'type': 'list',
+                        'ordered': current_list,
+                        'items': current_list_items
+                    })
+                    current_list = None
+                    current_list_items = []
+                
+                # 解析表格
+                table_lines = [line]
+                
+                # 读取表格内容
+                for i, table_line in enumerate(lines[lines.index(line)+1:]):
+                    if table_line.startswith('|'):
+                        table_lines.append(table_line)
+                    else:
+                        break
+                
+                # 解析表格结构
+                if len(table_lines) >= 2:
+                    headers = [h.strip() for h in table_lines[0].split('|') if h.strip()]
+                    rows = []
+                    
+                    # 跳过分隔线
+                    for table_line in table_lines[2:]:
+                        cells = [c.strip() for c in table_line.split('|') if c.strip()]
+                        if cells:
+                            rows.append(dict(zip(headers, cells)))
+                    
+                    structure['children'].append({
+                        'type': 'table',
+                        'headers': headers,
+                        'rows': rows
+                    })
+                
+                # 跳过已处理的表格行
+                lines = lines[:lines.index(line)] + lines[lines.index(line)+i+1:]
+            
+            # 处理段落
+            else:
+                if line or current_paragraph:
+                    current_paragraph.append(line)
+        
+        # 保存最后一个段落
+        if current_paragraph:
+            structure['children'].append({
+                'type': 'paragraph',
+                'content': '\n'.join(current_paragraph)
+            })
+        
+        # 保存最后一个列表
+        if current_list is not None:
+            structure['children'].append({
+                'type': 'list',
+                'ordered': current_list,
+                'items': current_list_items
+            })
+        
+        return structure
+    
+    def _structure_to_xml(self, structure: Dict[str, Any]) -> str:
+        """将结构化数据转换为XML
+        
+        Args:
+            structure: 结构化数据
+            
+        Returns:
+            str: XML字符串
+        """
+        xml_parts = []
+        
+        # 处理元数据
+        if structure.get('metadata'):
+            xml_parts.append('<metadata>')
+            for key, value in structure['metadata'].items():
+                xml_parts.append(f'<{key}>{self._escape_xml(str(value))}</{key}>')
+            xml_parts.append('</metadata>')
+        
+        # 处理子元素
+        for child in structure.get('children', []):
+            if child['type'] == 'heading':
+                xml_parts.append(f'<heading level="{child["level"]}">{self._escape_xml(child["content"])}</heading>')
+            elif child['type'] == 'paragraph':
+                xml_parts.append(f'<paragraph>{self._escape_xml(child["content"])}</paragraph>')
+            elif child['type'] == 'list':
+                list_type = 'ordered' if child['ordered'] else 'unordered'
+                xml_parts.append(f'<list type="{list_type}">')
+                for item in child['items']:
+                    xml_parts.append(f'<list_item>{self._escape_xml(item["content"])}</list_item>')
+                xml_parts.append('</list>')
+            elif child['type'] == 'code_block':
+                xml_parts.append(f'<code_block language="{child.get("language", "")}">{self._escape_xml(child["content"])}</code_block>')
+            elif child['type'] == 'table':
+                xml_parts.append('<table>')
+                xml_parts.append('<headers>')
+                for header in child['headers']:
+                    xml_parts.append(f'<header>{self._escape_xml(header)}</header>')
+                xml_parts.append('</headers>')
+                xml_parts.append('<rows>')
+                for row in child['rows']:
+                    xml_parts.append('<row>')
+                    for key, value in row.items():
+                        xml_parts.append(f'<cell column="{self._escape_xml(key)}">{self._escape_xml(value)}</cell>')
+                    xml_parts.append('</row>')
+                xml_parts.append('</rows>')
+                xml_parts.append('</table>')
+        
+        return '\n'.join(xml_parts)
+    
+    def _escape_xml(self, text: str) -> str:
+        """转义XML特殊字符
+        
+        Args:
+            text: 原始文本
+            
+        Returns:
+            str: 转义后的文本
+        """
+        escape_map = {
+            '&': '&amp;',
+            '<': '&lt;',
+            '>': '&gt;',
+            '"': '&quot;',
+            "'": '&apos;'
+        }
+        
+        for char, replacement in escape_map.items():
+            text = text.replace(char, replacement)
+        
+        return text
+    
+    def get_supported_formats(self) -> tuple:
+        """获取支持的格式"""
+        return ('markdown', 'xml')

hos_m2f/converters/xml_to_md.py

@@ -0,0 +1,109 @@
+"""XML到Markdown格式转换器"""
+
+from typing import Any, Optional, Dict
+from hos_m2f.converters.base_converter import BaseConverter
+import xml.etree.ElementTree as ET
+
+
+class XMLToMDConverter(BaseConverter):
+    """XML到Markdown格式转换器"""
+    
+    def convert(self, input_content: bytes, options: Optional[Dict[str, Any]] = None) -> bytes:
+        """将XML转换为Markdown
+        
+        Args:
+            input_content: XML文件的二进制数据
+            options: 转换选项
+            
+        Returns:
+            bytes: Markdown文件的二进制数据
+        """
+        if options is None:
+            options = {}
+        
+        # 解析XML
+        root = ET.fromstring(input_content)
+        
+        # 转换为Markdown
+        md_content = self._xml_to_md(root)
+        
+        return md_content.encode('utf-8')
+    
+    def _xml_to_md(self, element: ET.Element, indent: int = 0) -> str:
+        """将XML元素转换为Markdown
+        
+        Args:
+            element: XML元素
+            indent: 缩进级别
+            
+        Returns:
+            str: Markdown字符串
+        """
+        md_parts = []
+        prefix = '  ' * indent
+        
+        # 处理元素内容
+        if element.text and element.text.strip():
+            # 处理标题
+            if element.tag in ['heading', 'title', 'Header', 'Title']:
+                md_parts.append('#' * (indent + 1) + ' ' + element.text.strip())
+            # 处理段落
+            elif element.tag in ['paragraph', 'p', 'Paragraph']:
+                md_parts.append(element.text.strip())
+            # 处理列表项
+            elif element.tag in ['list_item', 'item', 'ListItem']:
+                md_parts.append(f'{prefix}- {element.text.strip()}')
+            # 处理代码块
+            elif element.tag in ['code_block', 'code', 'Code']:
+                language = element.get('language', '')
+                md_parts.append(f'```{language}' if language else '```')
+                md_parts.append(element.text.strip())
+                md_parts.append('```')
+            # 处理普通文本
+            else:
+                md_parts.append(f'{prefix}{element.tag}: {element.text.strip()}')
+        
+        # 处理子元素
+        for child in element:
+            # 处理列表
+            if child.tag in ['list', 'List']:
+                list_type = child.get('type', 'unordered')
+                md_parts.append(f'{prefix}{child.tag}:')
+                for item in child:
+                    if item.tag in ['list_item', 'item', 'ListItem']:
+                        item_text = item.text.strip() if item.text else ''
+                        md_parts.append(f'{prefix}- {item_text}')
+            # 处理表格
+            elif child.tag in ['table', 'Table']:
+                # 提取表头
+                headers = []
+                for header in child.findall('.//header'):
+                    headers.append(header.text.strip() if header.text else '')
+                
+                if headers:
+                    # 生成表格
+                    md_parts.append('| ' + ' | '.join(headers) + ' |')
+                    md_parts.append('| ' + ' | '.join(['---'] * len(headers)) + ' |')
+                    
+                    # 提取表格数据
+                    for row in child.findall('.//row'):
+                        cells = []
+                        for cell in row:
+                            cells.append(cell.text.strip() if cell.text else '')
+                        if cells:
+                            md_parts.append('| ' + ' | '.join(cells) + ' |')
+            # 处理其他子元素
+            else:
+                child_md = self._xml_to_md(child, indent + 1)
+                if child_md:
+                    md_parts.append(child_md)
+        
+        # 添加空行
+        if md_parts:
+            md_parts.append('')
+        
+        return '\n'.join(md_parts)
+    
+    def get_supported_formats(self) -> tuple:
+        """获取支持的格式"""
+        return ('xml', 'markdown')

{hos_m2f-0.5.1.dist-info → hos_m2f-0.5.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hos-m2f
-Version: 0.5.1
+Version: 0.5.2
 Summary: HOS-M2F: Markdown to Industry Standard Format Compiler Engine
 Author: HOS Team
 Author-email: team@hos-m2f.com

hos_m2f-0.5.2.dist-info/RECORD

@@ -0,0 +1,20 @@
+hos_m2f/__init__.py,sha256=v4k4TbKzPb3nbzgKJHaID3QTSpmTvAsGVHZ-poa870I,178
+hos_m2f/cli/__init__.py,sha256=NqhmK68K2evHjP7qcyT7FUWlDqfb22CUpCOfJhnQzPs,68
+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=5l4Q8F0-9dM0gnpZmC9C-QAKZ58LHZ9CTZ4EK9Yv5UU,5573
+hos_m2f/converters/md_to_epub.py,sha256=HF0YJ3efvuG6ts45N7IaLIH_4O9VrWG5aqczF4mGPk0,2993
+hos_m2f/converters/md_to_html.py,sha256=ss6Uud2mPhoIMctQWKeGpRHa0FtUqB9573ZB6cnKucA,2827
+hos_m2f/converters/md_to_json.py,sha256=XqeIqwrubuLOU4dTmveAMmyuGD-lK57GVHh9nzAdtXo,10295
+hos_m2f/converters/md_to_xml.py,sha256=RXNdPlkXtvQXLXBuv_xNAu5UXHQo7dF31bynBy9yDIs,13266
+hos_m2f/converters/xml_to_md.py,sha256=zOkaEaSZdvyHag05kIHiWF4VyGMMjfmWmBllBpzwJ4E,4051
+hos_m2f-0.5.2.dist-info/METADATA,sha256=vDnHHOcme8BeiVGqIk_AcHNtzOPFuNsL3XImjG2Lg3U,1764
+hos_m2f-0.5.2.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+hos_m2f-0.5.2.dist-info/entry_points.txt,sha256=NeLjg1hvVt_A2sDUVZAYbfkvnZ1nGMcTqRiDoVQzn0w,49
+hos_m2f-0.5.2.dist-info/top_level.txt,sha256=DMIK2jdfJss-FB_GRZ6iw4gahhZUAvSI0fHamOPL9mE,8
+hos_m2f-0.5.2.dist-info/RECORD,,

hos_m2f-0.5.1.dist-info/RECORD

@@ -1,8 +0,0 @@
-hos_m2f/__init__.py,sha256=v4k4TbKzPb3nbzgKJHaID3QTSpmTvAsGVHZ-poa870I,178
-hos_m2f/cli/__init__.py,sha256=NqhmK68K2evHjP7qcyT7FUWlDqfb22CUpCOfJhnQzPs,68
-hos_m2f/cli/cli.py,sha256=61agI2zcmgH5vtBNayueMGD7sVrqhMe5eFpvgd9j7r0,10639
-hos_m2f-0.5.1.dist-info/METADATA,sha256=8cdJz_maLr7TK51prDlcqULg2mCr-XyPYz3ZOlDq8cM,1764
-hos_m2f-0.5.1.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-hos_m2f-0.5.1.dist-info/entry_points.txt,sha256=NeLjg1hvVt_A2sDUVZAYbfkvnZ1nGMcTqRiDoVQzn0w,49
-hos_m2f-0.5.1.dist-info/top_level.txt,sha256=DMIK2jdfJss-FB_GRZ6iw4gahhZUAvSI0fHamOPL9mE,8
-hos_m2f-0.5.1.dist-info/RECORD,,