diff --git a/file-receive-system/db.py b/file-receive-system/db.py new file mode 100644 index 0000000..5f8a1f3 --- /dev/null +++ b/file-receive-system/db.py @@ -0,0 +1,4 @@ +from flask_sqlalchemy import SQLAlchemy + +# 创建数据库实例，独立于应用 +db = SQLAlchemy() diff --git a/md2txt/txt2md2docx.py b/md2txt/txt2md2docx.py new file mode 100644 index 0000000..7a3e79c --- /dev/null +++ b/md2txt/txt2md2docx.py @@ -0,0 +1,1006 @@ +import os +import sys +import glob +from PIL import Image +from docx import Document +from docx.shared import Inches, Pt +from docx.enum.text import WD_ALIGN_PARAGRAPH +import PySimpleGUI as sg + + +# 配置设置 +class Config: + def __init__(self): + # 文件处理配置 + self.txt_encoding = "utf-8" + self.match_pattern = "exact" # exact: 完全匹配, prefix: 前缀匹配, contains: 包含 + self.output_location = "txt_folder" # txt_folder or custom + # 图片处理配置 + self.image_sort_by = "name" # name or time + self.image_resize = "none" # none or width + self.image_width = 6 # 英寸 + self.image_alignment = "center" # left, center, right + self.image_strategy = "cycle" # cycle, truncate, repeat_last + # 文档格式配置 + self.line_spacing = 1.5 + self.title_levels = 6 # 支持的最大标题层级 + # 输出配置 + self.output_subfolder = "converted_docs" # 输出子文件夹名称 + + +# 全局配置实例 +config = Config() + + +# 文件处理模块 - 增强文件夹和匹配处理 +class FileHandler: + @staticmethod + def scan_txt_files(folder_path): + """扫描文件夹中的所有TXT文件""" + if not os.path.isdir(folder_path): + raise Exception(f"TXT文件夹不存在: {folder_path}") + + txt_files = [] + # 递归扫描所有TXT文件 + for root, dirs, files in os.walk(folder_path): + for file in files: + if file.lower().endswith(".txt"): + txt_path = os.path.join(root, file) + # 获取文件名（不含扩展名） + file_name = os.path.splitext(file)[0] + txt_files.append({ + "path": txt_path, + "name": file_name, + "relative_path": os.path.relpath(txt_path, folder_path), + "folder": root # 存储文件所在的文件夹 + }) + + if not txt_files: + raise Exception(f"在 {folder_path} 中未找到任何TXT文件") + + return sorted(txt_files, key=lambda x: x["relative_path"]) + + @staticmethod + def find_matching_image_folders(txt_files, images_root): + """根据TXT文件名匹配图片文件夹""" + if not os.path.isdir(images_root): + raise Exception(f"图片根文件夹不存在: {images_root}") + + # 获取所有图片文件夹 + all_image_folders = [] + for root, dirs, _ in os.walk(images_root): + for dir in dirs: + folder_path = os.path.join(root, dir) + all_image_folders.append({ + "path": folder_path, + "name": dir, + "relative_path": os.path.relpath(folder_path, images_root) + }) + + # 为每个TXT文件匹配图片文件夹 + matched_pairs = [] + for txt in txt_files: + matches = [] + txt_name = txt["name"].lower() + + for img_folder in all_image_folders: + folder_name = img_folder["name"].lower() + + # 根据匹配模式查找匹配项 + if config.match_pattern == "exact" and txt_name == folder_name: + matches.append(img_folder) + elif config.match_pattern == "prefix" and folder_name.startswith(txt_name): + matches.append(img_folder) + elif config.match_pattern == "contains" and txt_name in folder_name: + matches.append(img_folder) + + # 优先选择相对路径最短的匹配项 + if matches: + matches.sort(key=lambda x: len(x["relative_path"])) + matched_pairs.append({ + "txt": txt, + "image_folder": matches[0], + "all_matches": matches + }) + else: + matched_pairs.append({ + "txt": txt, + "image_folder": None, + "all_matches": [] + }) + + return matched_pairs + + @staticmethod + def get_image_files(folder_path): + """获取文件夹中的所有图片文件""" + if not folder_path or not os.path.isdir(folder_path): + return [] + + # 仅保留常见图片格式 + image_extensions = ['*.jpg', '*.jpeg', '*.png', '*.bmp', '*.gif'] + image_files = [] + + for ext in image_extensions: + image_files.extend(glob.glob(os.path.join(folder_path, ext))) + + # 根据配置排序 + if config.image_sort_by == "name": + image_files.sort() + elif config.image_sort_by == "time": + image_files.sort(key=lambda x: os.path.getmtime(x)) + + return image_files + + @staticmethod + def read_markdown_txt(file_path): + """读取含Markdown内容的TXT文件""" + if not os.path.exists(file_path): + raise Exception(f"TXT文件不存在: {file_path}") + + # 尝试多种编码读取TXT文件 + encodings = [config.txt_encoding, "gbk", "utf-16", "iso-8859-1"] + for encoding in encodings: + try: + with open(file_path, 'r', encoding=encoding) as f: + content = f.read() + content = content.replace("\r\n", "\n").replace("\r", "\n") + return content + except UnicodeDecodeError: + continue + + raise Exception(f"无法解析TXT文件（编码问题）: {file_path}") + + @staticmethod + def prepare_output_path(txt_info, images_root, output_root): + """准备输出文件路径""" + # 根据配置决定输出位置 + if config.output_location == "txt_folder": + # 输出到TXT文件所在的文件夹 + base_folder = txt_info["folder"] + else: + # 输出到指定的根文件夹 + base_folder = output_root + + # 创建输出子文件夹 + output_folder = os.path.join(base_folder, config.output_subfolder) + os.makedirs(output_folder, exist_ok=True) + + # 生成输出文件名 + txt_name = txt_info["name"] + output_path = os.path.join(output_folder, f"{txt_name}.docx") + + # 处理文件名冲突 + counter = 1 + while os.path.exists(output_path): + output_path = os.path.join(output_folder, f"{txt_name}_{counter}.docx") + counter += 1 + + return output_path + + +# Markdown解析模块 +class MarkdownParser: + @staticmethod + def parse(txt_content): + """解析TXT中的Markdown内容""" + headings = [] + current_heading = None + current_paragraphs = [] + in_code_block = False + + lines = txt_content.split('\n') + for line in lines: + line = line.rstrip('\r') + + # 处理代码块 + if line.startswith('```'): + in_code_block = not in_code_block + continue + + if in_code_block: + continue + + # 识别标题 + if line.lstrip().startswith('#'): + level = 0 + stripped_line = line.lstrip() + while level < len(stripped_line) and stripped_line[level] == '#' and level < config.title_levels: + level += 1 + + if level > 0 and (len(stripped_line) <= level or stripped_line[level] in (' ', '\t')): + if current_heading: + current_heading['paragraphs'] = current_paragraphs + headings.append(current_heading) + + heading_text = stripped_line[level:].lstrip() + current_heading = { + 'level': level, + 'content': heading_text, + 'paragraphs': [] + } + current_paragraphs = [] + continue + + # 处理无标题内容 + if current_heading is None: + current_heading = { + 'level': 0, + 'content': '前置内容', + 'paragraphs': [] + } + + # 处理段落 + if line.strip() == '': + if current_paragraphs and current_paragraphs[-1]['content'].strip() != '': + current_paragraphs.append({ + 'type': 'empty', + 'content': '', + 'is_first': False, + 'formatting': {} + }) + else: + para_type = 'text' + if line.startswith(('- ', '* ')): + para_type = 'unordered_list' + elif line.lstrip()[0].isdigit() and line.lstrip()[1:3] in ('. ', ') '): + para_type = 'ordered_list' + elif line.startswith('> '): + para_type = 'quote' + + is_first = len(current_paragraphs) == 0 and not any(p['type'] == 'text' for p in current_paragraphs) + formatting = MarkdownParser.extract_formatting(line) + + current_paragraphs.append({ + 'type': para_type, + 'content': line, + 'is_first': is_first, + 'formatting': formatting + }) + + if current_heading: + current_heading['paragraphs'] = current_paragraphs + headings.append(current_heading) + + return headings + + @staticmethod + def extract_formatting(text): + """提取文本格式""" + formatting = { + 'bold': [], + 'italic': [], + 'code': [] + } + + # 提取粗体 + start = 0 + while start < len(text): + pos = text.find('**', start) + if pos == -1: + break + end = text.find('**', pos + 2) + if end == -1: + break + formatting['bold'].append((pos, end + 2)) + start = end + 2 + + # 提取斜体 + start = 0 + while start < len(text): + pos = text.find('*', start) + if pos == -1: + break + if pos > 0 and text[pos - 1] == '*': + start = pos + 1 + continue + end = text.find('*', pos + 1) + if end == -1: + break + formatting['italic'].append((pos, end + 1)) + start = end + 1 + + # 提取代码 + start = 0 + while start < len(text): + pos = text.find('`', start) + if pos == -1: + break + end = text.find('`', pos + 1) + if end == -1: + break + formatting['code'].append((pos, end + 1)) + start = end + 1 + + return formatting + + +# 图片处理模块 +class ImageProcessor: + @staticmethod + def process_image(image_path): + """处理图片""" + try: + with Image.open(image_path) as img: + # 处理图片方向 + if hasattr(img, '_getexif'): + exif = img._getexif() + if exif: + orientation_tag = 274 + if orientation_tag in exif: + orientation = exif[orientation_tag] + if orientation == 3: + img = img.rotate(180, expand=True) + elif orientation == 6: + img = img.rotate(270, expand=True) + elif orientation == 8: + img = img.rotate(90, expand=True) + + # 调整大小 + if config.image_resize == "width" and config.image_width > 0: + target_width_px = config.image_width * 96 + width, height = img.size + + if width > target_width_px: + ratio = target_width_px / width + new_height = int(height * ratio) + img = img.resize((int(target_width_px), new_height), Image.LANCZOS) + + return img, config.image_width + else: + width_in = img.width / 96 + return img, width_in + except Exception as e: + raise Exception(f"处理图片失败 {image_path}: {str(e)}") + + @staticmethod + def get_image_alignment(): + """获取图片对齐方式""" + if config.image_alignment == "left": + return WD_ALIGN_PARAGRAPH.LEFT + elif config.image_alignment == "right": + return WD_ALIGN_PARAGRAPH.RIGHT + else: + return WD_ALIGN_PARAGRAPH.CENTER + + +# DOCX生成模块 +class DocxGenerator: + @staticmethod + def generate(headings, image_files, output_path, progress_callback=None): + """生成DOCX文档""" + doc = Document() + total_headings = len(headings) + image_index = 0 + image_count = len(image_files) + + for i, heading in enumerate(headings): + if progress_callback: + progress = int((i / total_headings) * 100) + progress_callback(progress, f"处理标题: {heading['content'][:30]}...") + + # 添加标题 + if heading['level'] > 0 and heading['level'] <= config.title_levels: + doc.add_heading(heading['content'], level=heading['level']) + else: + para = doc.add_paragraph(heading['content']) + run = para.runs[0] + run.font.size = Pt(14) + run.font.bold = True + para.space_after = Pt(12) + + # 处理段落 + paragraphs = heading['paragraphs'] + if not paragraphs: + continue + + # 处理第一段 + first_para = paragraphs[0] + DocxGenerator.add_formatted_paragraph(doc, first_para) + + # 插入图片 + if image_count > 0 and image_index < image_count: + try: + img, width = ImageProcessor.process_image(image_files[image_index]) + + temp_img_path = None + if config.image_resize == "width": + temp_dir = os.path.dirname(output_path) + os.makedirs(temp_dir, exist_ok=True) + temp_img_path = os.path.join(temp_dir, f"temp_img_{image_index}.png") + img.save(temp_img_path) + img_path = temp_img_path + else: + img_path = image_files[image_index] + + para = doc.add_picture(img_path, width=Inches(width)) + para.alignment = ImageProcessor.get_image_alignment() + + if temp_img_path and os.path.exists(temp_img_path): + os.remove(temp_img_path) + + image_index += 1 + + if image_index >= image_count: + if config.image_strategy == "cycle": + image_index = 0 + elif config.image_strategy == "truncate": + image_index = image_count + + except Exception as e: + doc.add_paragraph(f"[图片插入失败: {str(e)}]") + + # 添加剩余段落 + for para in paragraphs[1:]: + DocxGenerator.add_formatted_paragraph(doc, para) + + try: + doc.save(output_path) + if progress_callback: + progress_callback(100, "转换完成!") + return True + except Exception as e: + raise Exception(f"保存DOCX失败: {str(e)}") + + @staticmethod + def add_formatted_paragraph(doc, paragraph_data): + """添加带格式的段落""" + content = paragraph_data['content'] + para_type = paragraph_data['type'] + formatting = paragraph_data['formatting'] + + if para_type == 'unordered_list': + para = doc.add_paragraph(style='List Bullet') + text = content[2:].strip() + elif para_type == 'ordered_list': + para = doc.add_paragraph(style='List Number') + if '.' in content[:5]: + text = content.split('.', 1)[1].strip() + elif ')' in content[:5]: + text = content.split(')', 1)[1].strip() + else: + text = content.strip() + elif para_type == 'quote': + para = doc.add_paragraph(style='Intense Quote') + text = content[2:].strip() + elif para_type == 'empty': + doc.add_paragraph() + return + else: + para = doc.add_paragraph() + text = content.strip() + + DocxGenerator.apply_formatting(para, text, formatting) + + if config.line_spacing > 0: + para.paragraph_format.line_spacing = config.line_spacing + + @staticmethod + def apply_formatting(paragraph, text, formatting): + """应用文本格式""" + format_positions = [] + for pos in formatting['bold']: + format_positions.append((pos[0], pos[1], 'bold')) + for pos in formatting['italic']: + format_positions.append((pos[0], pos[1], 'italic')) + for pos in formatting['code']: + format_positions.append((pos[0], pos[1], 'code')) + + format_positions.sort(key=lambda x: x[0]) + + current_pos = 0 + for start, end, fmt_type in format_positions: + if start > current_pos: + paragraph.add_run(text[current_pos:start]) + + run = paragraph.add_run(text[start:end]) + + if fmt_type == 'bold': + run.text = run.text[2:-2] + run.bold = True + elif fmt_type == 'italic': + run.text = run.text[1:-1] + run.italic = True + elif fmt_type == 'code': + run.text = run.text[1:-1] + run.font.name = 'Courier New' + run.font.size = Pt(10) + + current_pos = end + + if current_pos < len(text): + paragraph.add_run(text[current_pos:]) + + +# 批量处理模块 +class BatchProcessor: + @staticmethod + def process_batch(matched_pairs, output_root, progress_callback=None): + """批量处理匹配的文件对""" + total = len(matched_pairs) + success_count = 0 + failed_items = [] + + for i, pair in enumerate(matched_pairs): + try: + # 更新整体进度 + if progress_callback: + overall_progress = int((i / total) * 100) + progress_callback(overall_progress, + f"处理 {i + 1}/{total}: {pair['txt']['name']}") + + # 准备输出路径 + output_path = FileHandler.prepare_output_path( + pair['txt'], + pair['image_folder']['path'] if pair['image_folder'] else "", + output_root + ) + + # 读取TXT内容 + txt_content = FileHandler.read_markdown_txt(pair['txt']['path']) + + # 解析内容 + headings = MarkdownParser.parse(txt_content) + + if not headings: + raise Exception("未解析到有效内容") + + # 获取图片文件 + image_files = [] + if pair['image_folder']: + image_files = FileHandler.get_image_files(pair['image_folder']['path']) + + # 生成DOCX + def update_file_progress(progress, text): + if progress_callback: + # 计算整体进度中的子进度 + sub_progress = int((i + progress / 100) / total * 100) + progress_callback(sub_progress, f"{pair['txt']['name']}: {text}") + + DocxGenerator.generate(headings, image_files, output_path, update_file_progress) + success_count += 1 + + except Exception as e: + failed_items.append({ + "name": pair['txt']['name'], + "error": str(e) + }) + + # 确定主要输出文件夹用于结果显示 + if matched_pairs and success_count > 0: + sample_output = FileHandler.prepare_output_path(matched_pairs[0]['txt'], "", output_root) + main_output_folder = os.path.dirname(sample_output) + else: + main_output_folder = "" + + return { + "total": total, + "success": success_count, + "failed": len(failed_items), + "failed_items": failed_items, + "main_output_folder": main_output_folder + } + + +# 配置窗口 +def show_config_window(): + """显示配置窗口""" + layout = [ + [sg.Text('文件匹配设置', font=('bold', 12))], + [sg.Text('TXT编码:'), + sg.Combo(['utf-8', 'gbk', 'utf-16'], + default_value=config.txt_encoding, key='txt_encoding')], + [sg.Text('匹配模式:'), + sg.Radio('完全匹配（文件名与文件夹名相同）', 'match', + default=config.match_pattern == "exact", key='match_exact'), + sg.Radio('前缀匹配', 'match', + default=config.match_pattern == "prefix", key='match_prefix'), + sg.Radio('包含匹配', 'match', + default=config.match_pattern == "contains", key='match_contains')], + [sg.HSeparator()], + [sg.Text('输出位置设置', font=('bold', 12))], + [sg.Radio('输出到TXT文件所在文件夹', 'output_loc', + default=config.output_location == "txt_folder", key='output_txt_folder'), + sg.Radio('输出到指定文件夹', 'output_loc', + default=config.output_location == "custom", key='output_custom')], + [sg.Text('输出子文件夹名称:'), + sg.InputText(config.output_subfolder, key='output_subfolder')], + [sg.HSeparator()], + [sg.Text('图片处理设置', font=('bold', 12))], + [sg.Text('图片排序方式:'), + sg.Radio('按名称', 'sort', default=config.image_sort_by == "name", key='sort_name'), + sg.Radio('按修改时间', 'sort', default=config.image_sort_by == "time", key='sort_time')], + [sg.Text('图片尺寸调整:'), + sg.Radio('不调整', 'resize', default=config.image_resize == "none", key='resize_none'), + sg.Radio('按宽度:', 'resize', default=config.image_resize == "width", key='resize_width'), + sg.InputText(str(config.image_width), size=(5, 1), key='image_width'), + sg.Text('英寸')], + [sg.Text('图片对齐方式:'), + sg.Radio('左对齐', 'align', default=config.image_alignment == "left", key='align_left'), + sg.Radio('居中', 'align', default=config.image_alignment == "center", key='align_center'), + sg.Radio('右对齐', 'align', default=config.image_alignment == "right", key='align_right')], + [sg.HSeparator()], + [sg.Text('图片不足时策略', font=('bold', 12))], + [sg.Radio('循环使用', 'strategy', default=config.image_strategy == "cycle", key='strategy_cycle'), + sg.Radio('忽略多余标题', 'strategy', default=config.image_strategy == "truncate", key='strategy_truncate'), + sg.Radio('重复最后一张', 'strategy', default=config.image_strategy == "repeat_last", key='strategy_repeat')], + [sg.HSeparator()], + [sg.Button('确定'), sg.Button('取消')] + ] + + window = sg.Window('转换设置', layout, modal=True, resizable=True) + + while True: + event, values = window.read() + if event in (sg.WIN_CLOSED, '取消'): + break + if event == '确定': + # 保存配置 + config.txt_encoding = values['txt_encoding'] + + if values['match_exact']: + config.match_pattern = "exact" + elif values['match_prefix']: + config.match_pattern = "prefix" + else: + config.match_pattern = "contains" + + # 保存输出位置设置 + config.output_location = "txt_folder" if values['output_txt_folder'] else "custom" + + if values['output_subfolder'].strip(): + config.output_subfolder = values['output_subfolder'].strip() + + config.image_sort_by = "name" if values['sort_name'] else "time" + config.image_resize = "none" if values['resize_none'] else "width" + + try: + config.image_width = float(values['image_width']) + except: + pass + + if values['align_left']: + config.image_alignment = "left" + elif values['align_right']: + config.image_alignment = "right" + else: + config.image_alignment = "center" + + if values['strategy_cycle']: + config.image_strategy = "cycle" + elif values['strategy_truncate']: + config.image_strategy = "truncate" + else: + config.image_strategy = "repeat_last" + + break + + window.close() + + +# 匹配编辑窗口 +def show_matching_editor(matched_pairs, images_root): + """显示匹配编辑窗口，允许手动调整匹配关系""" + # 获取所有可用的图片文件夹 + all_image_folders = [] + if os.path.isdir(images_root): + for root, dirs, _ in os.walk(images_root): + for dir in dirs: + folder_path = os.path.join(root, dir) + rel_path = os.path.relpath(folder_path, images_root) + all_image_folders.append((folder_path, rel_path)) + + # 创建表格数据 + table_data = [] + for i, pair in enumerate(matched_pairs): + txt_name = pair['txt']['name'] + img_folder = pair['image_folder']['relative_path'] if pair['image_folder'] else "无匹配" + table_data.append([i, txt_name, img_folder]) + + # 窗口布局 + layout = [ + [sg.Text('文件匹配编辑', font=('bold', 14))], + [sg.Text('选择要修改的项目，然后从右侧选择图片文件夹')], + [ + sg.Table( + values=table_data, + headings=['序号', 'TXT文件名', '匹配的图片文件夹'], + key='-TABLE-', + select_mode=sg.TABLE_SELECT_MODE_BROWSE, + enable_events=True, + justification='left', + size=(None, 15) + ), + sg.VSeparator(), + sg.Listbox( + values=[f[1] for f in all_image_folders], + key='-FOLDERS-', + size=(40, 15), + enable_events=True + ) + ], + [sg.Button('设置选中项'), sg.Button('清除选中项'), sg.Button('应用所有')] + ] + + window = sg.Window('匹配编辑', layout, resizable=True) + selected_row = None + + while True: + event, values = window.read() + + if event in (sg.WIN_CLOSED, '应用所有'): + break + + # 表格选中事件 + if event == '-TABLE-': + if values['-TABLE-']: + selected_row = values['-TABLE-'][0] + + # 设置选中项 + if event == '设置选中项' and selected_row is not None and values['-FOLDERS-']: + folder_idx = [i for i, f in enumerate(all_image_folders) if f[1] == values['-FOLDERS-'][0]][0] + folder_path, folder_rel = all_image_folders[folder_idx] + + # 更新匹配数据 + matched_pairs[selected_row]['image_folder'] = { + "path": folder_path, + "name": os.path.basename(folder_path), + "relative_path": folder_rel + } + + # 更新表格 + table_data[selected_row][2] = folder_rel + window['-TABLE-'].update(values=table_data) + + # 清除选中项 + if event == '清除选中项' and selected_row is not None: + matched_pairs[selected_row]['image_folder'] = None + table_data[selected_row][2] = "无匹配" + window['-TABLE-'].update(values=table_data) + + window.close() + return matched_pairs + + +# 帮助窗口 +def show_help_window(): + """显示帮助窗口""" + help_text = """ +批量Markdown TXT转DOCX工具使用说明: + +1. 选择包含Markdown内容的TXT文件所在文件夹 +2. 选择图片文件夹的根目录（程序会自动查找子文件夹） +3. 选择输出文件的保存根目录（当选择"输出到指定文件夹"时有效） +4. 点击"扫描文件"按钮，程序会自动匹配TXT文件和图片文件夹 +5. 查看匹配结果，可点击"编辑匹配"调整匹配关系 +6. 点击"开始批量转换"生成DOCX文件 + +输出路径选择: +- 输出到TXT文件所在文件夹: 每个DOCX文件会保存在对应TXT文件所在文件夹的子目录中 +- 输出到指定文件夹: 所有DOCX文件会保存在您指定的文件夹的子目录中 + +匹配规则: +- 完全匹配: TXT文件名（不含扩展名）与图片文件夹名完全相同 +- 前缀匹配: 图片文件夹名以前缀形式包含TXT文件名 +- 包含匹配: 图片文件夹名中包含TXT文件名 + +转换规则: +- 每个小标题的第一段后会插入一张图片 +- 支持Markdown格式: 标题、列表、粗体、斜体、代码等 +""" + sg.popup_scrolled('使用帮助', help_text, size=(60, 20)) + + +# 结果窗口 +def show_results_window(results): + """显示批量处理结果窗口""" + if results['failed'] == 0: + message = f"全部成功！\n共处理 {results['total']} 个文件，全部转换成功。" + if results['main_output_folder']: + message += f"\n主要输出文件夹: {results['main_output_folder']}" + sg.popup('处理完成', message) + else: + failed_text = "\n".join([f"- {item['name']}: {item['error']}" for item in results['failed_items']]) + message = (f"处理完成！\n共处理 {results['total']} 个文件，" + f"{results['success']} 个成功，{results['failed']} 个失败。\n\n" + f"失败项:\n{failed_text}") + if results['main_output_folder']: + message += f"\n主要输出文件夹: {results['main_output_folder']}" + sg.popup_scrolled('处理完成', message, size=(60, 20)) + + # 询问是否打开输出文件夹 + if results['main_output_folder'] and os.path.exists(results['main_output_folder']): + if sg.popup_yes_no('是否打开主要输出文件夹?') == 'Yes': + if sys.platform.startswith('win'): + os.startfile(results['main_output_folder']) + elif sys.platform.startswith('darwin'): + os.system(f'open "{results["main_output_folder"]}"') + else: + os.system(f'xdg-open "{results["main_output_folder"]}"') + + +# 主界面 +def main_window(): + """主界面""" + sg.theme('BlueMono') + + # 初始化变量 + matched_pairs = [] + + layout = [ + [sg.Text('批量Markdown TXT转DOCX工具', font=('bold', 16))], + [sg.Text('（按文件名匹配TXT文件和图片文件夹）', text_color='gray')], + [sg.HSeparator()], + [sg.Text('TXT文件文件夹:', size=(15, 1)), + sg.InputText(key='txt_folder', enable_events=True), + sg.FolderBrowse('浏览')], + [sg.Text('图片根文件夹:', size=(15, 1)), + sg.InputText(key='images_root', enable_events=True), + sg.FolderBrowse('浏览')], + [sg.Text('输出根文件夹:', size=(15, 1)), + sg.InputText(key='output_root', enable_events=True), + sg.FolderBrowse('浏览'), + sg.Text('(当选择"输出到指定文件夹"时有效)', text_color='gray')], + [sg.Button('扫描文件', size=(12, 1)), + sg.Button('编辑匹配', size=(12, 1), disabled=True), + sg.Button('转换设置', size=(12, 1)), + sg.Button('帮助', size=(8, 1))], + [sg.HSeparator()], + [sg.Text('匹配结果预览:', font=('bold', 10))], + [sg.Table( + values=[], + headings=['TXT文件名', '相对路径', '匹配的图片文件夹'], + key='-PREVIEW_TABLE-', + auto_size_columns=False, + col_widths=[20, 30, 30], + justification='left', + size=(None, 10) + )], + [sg.ProgressBar(100, orientation='h', size=(80, 20), key='progress_bar', visible=False)], + [sg.Text('状态: 就绪', key='status_text', size=(80, 1))], + [sg.Button('开始批量转换', size=(15, 1), disabled=True), sg.Button('退出')] + ] + + # 创建窗口时不使用finalized参数 + window = sg.Window('批量Markdown TXT转DOCX工具', layout, resizable=True) + progress_bar = window['progress_bar'] + status_text = window['status_text'] + preview_table = window['-PREVIEW_TABLE-'] + output_root_input = window['output_root'] + + def update_output_root_state(): + """根据配置更新输出根文件夹输入框的状态""" + if config.output_location == "custom": + output_root_input.update(disabled=False) + output_root_input.Widget.configure(foreground='black') + else: + output_root_input.update(disabled=True) + output_root_input.Widget.configure(foreground='gray') + + # 先进行一次窗口读取来完成初始化，然后再更新元素状态 + # 发送一个虚拟事件来触发首次更新 + window.read(timeout=1) + update_output_root_state() + + while True: + event, values = window.read() + + if event in (sg.WIN_CLOSED, '退出'): + break + + if event == '转换设置': + # 保存当前输出根目录 + current_output_root = values['output_root'] + # 显示配置窗口 + show_config_window() + # 更新输出根目录输入框状态 + update_output_root_state() + # 恢复输出根目录值 + window['output_root'].update(current_output_root) + + if event == '帮助': + show_help_window() + + if event == '扫描文件': + txt_folder = values['txt_folder'] + images_root = values['images_root'] + + if not txt_folder: + sg.popup_error('请选择TXT文件所在的文件夹') + continue + + if not images_root: + sg.popup_error('请选择图片根文件夹') + continue + + try: + status_text.update('正在扫描TXT文件...') + window.refresh() + txt_files = FileHandler.scan_txt_files(txt_folder) + + status_text.update('正在匹配图片文件夹...') + window.refresh() + matched_pairs = FileHandler.find_matching_image_folders(txt_files, images_root) + + # 更新预览表格 + table_data = [] + for pair in matched_pairs: + img_folder = pair['image_folder']['relative_path'] if pair['image_folder'] else "无匹配" + table_data.append([ + pair['txt']['name'], + pair['txt']['relative_path'], + img_folder + ]) + + preview_table.update(values=table_data) + status_text.update(f'扫描完成: 找到 {len(matched_pairs)} 个TXT文件') + + # 启用相关按钮 + window['编辑匹配'].update(disabled=False) + window['开始批量转换'].update(disabled=False) + + except Exception as e: + sg.popup_error(f'扫描失败: {str(e)}') + status_text.update('状态: 扫描失败') + + if event == '编辑匹配' and matched_pairs: + images_root = values['images_root'] + if not images_root: + sg.popup_error('请选择图片根文件夹') + continue + + # 打开匹配编辑窗口 + matched_pairs = show_matching_editor(matched_pairs, images_root) + + # 更新预览表格 + table_data = [] + for pair in matched_pairs: + img_folder = pair['image_folder']['relative_path'] if pair['image_folder'] else "无匹配" + table_data.append([ + pair['txt']['name'], + pair['txt']['relative_path'], + img_folder + ]) + + preview_table.update(values=table_data) + + if event == '开始批量转换' and matched_pairs: + # 检查输出路径（当选择输出到指定文件夹时） + if config.output_location == "custom" and not values['output_root']: + sg.popup_error('请选择输出根文件夹（在"转换设置"中选择了"输出到指定文件夹"）') + continue + + try: + # 显示进度条 + progress_bar.update(0, visible=True) + status_text.update('开始批量转换...') + window.refresh() + + # 执行批量处理 + def update_batch_progress(progress, text): + progress_bar.update(progress) + status_text.update(f'状态: {text}') + window.refresh() + + results = BatchProcessor.process_batch(matched_pairs, values['output_root'], update_batch_progress) + + # 显示结果 + show_results_window(results) + status_text.update('状态: 批量转换完成') + + except Exception as e: + sg.popup_error(f'批量处理失败: {str(e)}') + status_text.update('状态: 批量转换失败') + + # 自动填充输出文件夹（如果未设置） + if (event == 'txt_folder' or event == 'images_root') and values[event] and not values['output_root']: + # 使用TXT文件夹作为默认输出文件夹 + default_output = values['txt_folder'] if values['txt_folder'] else values['images_root'] + window['output_root'].update(default_output) + + window.close() + + +# 程序入口 +if __name__ == '__main__': + main_window()