Skip to content

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He

fix(tools): 修复PPT备注匹配与PNG状态污染问题,优化项目名解析

hugohe33217ed305363
diff --git a/tools/project_manager.py b/tools/project_manager.py
index 304cb0d8..63543f72 100644
--- a/tools/project_manager.py
+++ b/tools/project_manager.py
@@ -10,19 +10,16 @@ PPT Master - 项目管理工具
python3 tools/project_manager.py info <project_path>
"""
-import os
import sys
-import json
-import re
from pathlib import Path
-from datetime import datetime
from typing import Dict, List, Optional, Tuple
# 导入公共工具模块(必须成功)
try:
from project_utils import (
CANVAS_FORMATS,
- get_project_info,
+ normalize_canvas_format,
+ get_project_info as get_project_info_common,
validate_project_structure,
validate_svg_viewbox
)
@@ -37,7 +34,8 @@ except ImportError:
try:
from project_utils import (
CANVAS_FORMATS,
- get_project_info,
+ normalize_canvas_format,
+ get_project_info as get_project_info_common,
validate_project_structure,
validate_svg_viewbox
)
@@ -79,9 +77,18 @@ class ProjectManager:
else:
base_path = self.base_dir
+ normalized_format = normalize_canvas_format(canvas_format)
+ if normalized_format not in self.CANVAS_FORMATS:
+ available = ', '.join(sorted(self.CANVAS_FORMATS.keys()))
+ raise ValueError(
+ f"不支持的画布格式: {canvas_format} "
+ f"(可用: {available}; 常用别名: xhs -> xiaohongshu)"
+ )
+
# 创建项目目录名: {project_name}_{format}_{YYYYMMDD}
+ from datetime import datetime
date_str = datetime.now().strftime('%Y%m%d')
- project_dir_name = f"{project_name}_{canvas_format}_{date_str}"
+ project_dir_name = f"{project_name}_{normalized_format}_{date_str}"
project_path = base_path / project_dir_name
if project_path.exists():
@@ -94,10 +101,24 @@ class ProjectManager:
(project_path / 'images').mkdir(exist_ok=True) # 图片资源
(project_path / 'notes').mkdir(exist_ok=True) # 演讲备注
(project_path / 'templates').mkdir(exist_ok=True) # 项目页面模板(可选)
+ readme_path = project_path / 'README.md'
+ readme_path.write_text(
+ (
+ f"# {project_name}\n\n"
+ f"- 画布格式: {normalized_format}\n"
+ f"- 创建日期: {date_str}\n\n"
+ "## 目录\n\n"
+ "- `svg_output/`: 原始 SVG 输出\n"
+ "- `svg_final/`: 后处理后的 SVG\n"
+ "- `images/`: 图片资源\n"
+ "- `notes/`: 演讲备注\n"
+ "- `templates/`: 项目模板\n"
+ ),
+ encoding='utf-8'
+ )
# 获取画布格式信息
- canvas_info = self.CANVAS_FORMATS.get(
- canvas_format, self.CANVAS_FORMATS['ppt169'])
+ canvas_info = self.CANVAS_FORMATS[normalized_format]
# 提示用户下一步操作 (不再自动创建空的设计规范文件)
print(f"项目目录已创建: {project_path}")
@@ -114,81 +135,19 @@ class ProjectManager:
Returns:
(是否有效, 错误列表, 警告列表)
"""
- project_path = Path(project_path)
- errors = []
- warnings = []
-
- # 检查目录是否存在
- if not project_path.exists():
- errors.append(f"项目目录不存在: {project_path}")
- return False, errors, warnings
-
- if not project_path.is_dir():
- errors.append(f"不是有效的目录: {project_path}")
- return False, errors, warnings
-
- # 检查设计规范文件(核心必需文件)
- spec_files = ['设计规范与内容大纲.md', 'design_specification.md', '设计规范.md']
- has_spec = any((project_path / f).exists() for f in spec_files)
- if not has_spec:
- errors.append("缺少设计规范文件(建议文件名: 设计规范与内容大纲.md)")
-
- # 检查 svg_output 目录
- svg_output = project_path / 'svg_output'
- if not svg_output.exists():
- errors.append("缺少 svg_output 目录")
- else:
- # 检查 SVG 文件
- svg_files = list(svg_output.glob('*.svg'))
- if len(svg_files) == 0:
- warnings.append("svg_output 目录为空")
- else:
- # 验证 SVG 文件命名(支持两种格式)
- # 格式1: slide_01_name.svg(英文项目)
- # 格式2: 01_封面.svg 或 P01_封面.svg(中文项目)
- for svg_file in svg_files:
- if not re.match(r'^(slide_\d+_\w+|P?\d+_.+)\.svg$', svg_file.name):
- warnings.append(
- f"SVG 文件命名不规范: {svg_file.name} (建议: 01_名称.svg 或 slide_01_name.svg)")
-
- # 检查 viewBox
- self._validate_svg_viewbox(svg_files, warnings)
-
- # 检查项目命名格式(支持所有画布格式)
- dir_name = project_path.name
- canvas_formats = '|'.join(self.CANVAS_FORMATS.keys())
- pattern = rf'^.+_({canvas_formats})_\d{{8}}$'
- if not re.match(pattern, dir_name, re.IGNORECASE):
- warnings.append(
- f"项目目录命名不规范: {dir_name} (建议: name_format_YYYYMMDD)")
-
- is_valid = len(errors) == 0
- return is_valid, errors, warnings
+ project_path_obj = Path(project_path)
+ is_valid, errors, warnings = validate_project_structure(str(project_path_obj))
+
+ if project_path_obj.exists() and project_path_obj.is_dir():
+ info = get_project_info_common(str(project_path_obj))
+ if info.get('svg_files'):
+ svg_files = [project_path_obj / 'svg_output' / f for f in info['svg_files']]
+ expected_format = info.get('format')
+ if expected_format == 'unknown':
+ expected_format = None
+ warnings.extend(validate_svg_viewbox(svg_files, expected_format))
- def _validate_svg_viewbox(self, svg_files: List[Path], warnings: List[str]):
- """验证 SVG 文件的 viewBox 设置
-
- Args:
- svg_files: SVG 文件列表
- warnings: 警告列表(会被修改)
- """
- viewbox_pattern = re.compile(r'viewBox="([^"]+)"')
- viewboxes = set()
-
- for svg_file in svg_files[:5]: # 只检查前5个文件
- try:
- with open(svg_file, 'r', encoding='utf-8') as f:
- content = f.read(1000) # 只读取前1000字符
- match = viewbox_pattern.search(content)
- if match:
- viewboxes.add(match.group(1))
- else:
- warnings.append(f"{svg_file.name}: 未找到 viewBox 属性")
- except Exception as e:
- warnings.append(f"{svg_file.name}: 读取失败 - {e}")
-
- if len(viewboxes) > 1:
- warnings.append(f"检测到多个不同的 viewBox 设置: {viewboxes}")
+ return is_valid, errors, warnings
def get_project_info(self, project_path: str) -> Dict:
"""获取项目信息
@@ -199,50 +158,17 @@ class ProjectManager:
Returns:
项目信息字典
"""
- project_path = Path(project_path)
- info = {
- 'name': project_path.name,
- 'path': str(project_path),
- 'exists': project_path.exists(),
- 'svg_count': 0,
- 'has_spec': False,
- 'canvas_format': 'unknown',
- 'create_date': 'unknown'
+ shared = get_project_info_common(project_path)
+ return {
+ 'name': shared.get('name', Path(project_path).name),
+ 'path': shared.get('path', str(project_path)),
+ 'exists': shared.get('exists', False),
+ 'svg_count': shared.get('svg_count', 0),
+ 'has_spec': shared.get('has_spec', False),
+ 'canvas_format': shared.get('format_name', '未知格式'),
+ 'create_date': shared.get('date_formatted', '未知日期')
}
- if not project_path.exists():
- return info
-
- # 统计 SVG 文件
- svg_output = project_path / 'svg_output'
- if svg_output.exists():
- info['svg_count'] = len(list(svg_output.glob('*.svg')))
-
- # 检查设计规范
- spec_files = ['设计规范与内容大纲.md', 'design_specification.md', '设计规范.md']
- info['has_spec'] = any((project_path / f).exists() for f in spec_files)
-
- # 从目录名提取信息
- dir_name = project_path.name
-
- # 提取画布格式
- for fmt in self.CANVAS_FORMATS.keys():
- if fmt in dir_name.lower():
- info['canvas_format'] = self.CANVAS_FORMATS[fmt]['name']
- break
-
- # 提取日期
- date_match = re.search(r'_(\d{8})$', dir_name)
- if date_match:
- date_str = date_match.group(1)
- try:
- date_obj = datetime.strptime(date_str, '%Y%m%d')
- info['create_date'] = date_obj.strftime('%Y-%m-%d')
- except ValueError:
- pass
-
- return info
-
def main():
"""主函数"""
diff --git a/tools/project_utils.py b/tools/project_utils.py
index 41f01ca9..f8cccc24 100644
--- a/tools/project_utils.py
+++ b/tools/project_utils.py
@@ -66,6 +66,22 @@ except ImportError:
}
}
+CANVAS_FORMAT_ALIASES = {
+ 'xhs': 'xiaohongshu',
+ 'wechat_moment': 'moments',
+ 'wechat-moment': 'moments',
+ '朋友圈': 'moments',
+ '小红书': 'xiaohongshu',
+}
+
+
+def normalize_canvas_format(format_key: str) -> str:
+ """标准化画布格式键名(支持常见别名)。"""
+ if not format_key:
+ return ''
+ key = format_key.strip().lower()
+ return CANVAS_FORMAT_ALIASES.get(key, key)
+
def parse_project_name(dir_name: str) -> Dict[str, str]:
"""
@@ -85,12 +101,7 @@ def parse_project_name(dir_name: str) -> Dict[str, str]:
'date_formatted': '未知日期'
}
- # 提取画布格式
- for fmt_key, fmt_info in CANVAS_FORMATS.items():
- if fmt_key in dir_name.lower():
- result['format'] = fmt_key
- result['format_name'] = fmt_info['name']
- break
+ dir_name_lower = dir_name.lower()
# 提取日期 (格式: _YYYYMMDD)
date_match = re.search(r'_(\d{8})$', dir_name)
@@ -103,11 +114,29 @@ def parse_project_name(dir_name: str) -> Dict[str, str]:
except ValueError:
pass
- # 提取项目名称(去除格式和日期后缀)
- name = dir_name
- for fmt_key in CANVAS_FORMATS.keys():
- name = re.sub(f'_{fmt_key}', '', name, flags=re.IGNORECASE)
- name = re.sub(r'_\d{8}$', '', name)
+ # 优先按标准格式解析: name_format_YYYYMMDD
+ full_match = re.match(r'^(?P<name>.+)_(?P<format>[a-z0-9_-]+)_(?P<date>\d{8})$', dir_name_lower)
+ if full_match:
+ raw_format = full_match.group('format')
+ normalized_format = normalize_canvas_format(raw_format)
+ if normalized_format in CANVAS_FORMATS:
+ result['format'] = normalized_format
+ result['format_name'] = CANVAS_FORMATS[normalized_format]['name']
+ result['name'] = dir_name[:len(full_match.group('name'))]
+ return result
+
+ # 兜底:只匹配末尾 `_format`,避免误删项目名内部片段
+ sorted_formats = sorted(CANVAS_FORMATS.keys(), key=len, reverse=True)
+ for fmt_key in sorted_formats:
+ if re.search(rf'_{re.escape(fmt_key)}(?:_\d{{8}})?$', dir_name_lower):
+ result['format'] = fmt_key
+ result['format_name'] = CANVAS_FORMATS[fmt_key]['name']
+ break
+
+ # 提取项目名称(仅移除末尾日期和格式后缀)
+ name = re.sub(r'_\d{8}$', '', dir_name)
+ if result['format'] != 'unknown':
+ name = re.sub(rf'_{re.escape(result["format"])}$', '', name, flags=re.IGNORECASE)
result['name'] = name
return result
diff --git a/tools/svg_quality_checker.py b/tools/svg_quality_checker.py
index c97081c5..2962beb8 100644
--- a/tools/svg_quality_checker.py
+++ b/tools/svg_quality_checker.py
@@ -147,7 +147,7 @@ class SVGQualityChecker:
# 裁剪 / 遮罩
if '<clippath' in content_lower:
result['errors'].append("检测到禁用的 <clipPath> 元素(PPT 不支持 SVG 裁剪路径)")
- if '<mask' in content_lower and '<mask>' not in content_lower: # 排除纯文本 "mask"
+ if '<mask' in content_lower:
result['errors'].append("检测到禁用的 <mask> 元素(PPT 不支持 SVG 遮罩)")
# 样式系统
diff --git a/tools/svg_to_pptx.py b/tools/svg_to_pptx.py
index 423722e2..546d2f22 100644
--- a/tools/svg_to_pptx.py
+++ b/tools/svg_to_pptx.py
@@ -284,7 +284,7 @@ def find_notes_files(project_path: Path, svg_files: List[Path] = None) -> dict:
svg_files: SVG 文件列表(用于按文件名匹配)
Returns:
- 字典,key 为 SVG 文件名(不含扩展名)或幻灯片编号,value 为备注内容
+ 字典,key 为 SVG 文件名(不含扩展名),value 为备注内容
"""
notes_dir = project_path / 'notes'
notes = {}
@@ -293,11 +293,12 @@ def find_notes_files(project_path: Path, svg_files: List[Path] = None) -> dict:
return notes
svg_stems_mapping = {}
-
+ svg_index_mapping = {}
if svg_files:
for i, svg_path in enumerate(svg_files, 1):
svg_stems_mapping[svg_path.stem] = i
-
+ svg_index_mapping[i] = svg_path.stem
+
# 收集所有 notes 文件信息
for notes_file in notes_dir.glob('*.md'):
try:
@@ -311,11 +312,14 @@ def find_notes_files(project_path: Path, svg_files: List[Path] = None) -> dict:
# 尝试提取序号(向后兼容 slide01.md 格式)
match = re.search(r'slide[_]?(\d+)', stem)
if match:
- notes[int(match.group(1))] = content
+ index = int(match.group(1))
+ mapped_stem = svg_index_mapping.get(index)
+ if mapped_stem:
+ notes[mapped_stem] = content
# 按文件名提取(覆盖向后兼容的格式)
if stem in svg_stems_mapping:
- notes[svg_stems_mapping[stem]] = content
+ notes[stem] = content
except Exception:
pass
@@ -709,7 +713,7 @@ def create_pptx_with_native_svg(
# 处理每个 SVG 文件
success_count = 0
- png_generated = False
+ any_png_generated = False
for i, svg_path in enumerate(svg_files, 1):
slide_num = i
@@ -723,6 +727,7 @@ def create_pptx_with_native_svg(
shutil.copy(svg_path, media_dir / svg_filename)
# 兼容模式:生成 PNG 后备图片
+ slide_has_png = False
if use_compat_mode:
png_path = media_dir / png_filename
png_success = convert_svg_to_png(
@@ -732,7 +737,8 @@ def create_pptx_with_native_svg(
height=pixel_height
)
if png_success:
- png_generated = True
+ slide_has_png = True
+ any_png_generated = True
else:
# PNG 生成失败,降级为纯 SVG
if verbose:
@@ -750,7 +756,7 @@ def create_pptx_with_native_svg(
transition=transition,
transition_duration=transition_duration,
auto_advance=auto_advance,
- use_compat_mode=(use_compat_mode and png_generated)
+ use_compat_mode=(use_compat_mode and slide_has_png)
)
with open(slide_xml_path, 'w', encoding='utf-8') as f:
f.write(slide_xml)
@@ -764,16 +770,17 @@ def create_pptx_with_native_svg(
png_filename=png_filename,
svg_rid=svg_rid,
svg_filename=svg_filename,
- use_compat_mode=(use_compat_mode and png_generated)
+ use_compat_mode=(use_compat_mode and slide_has_png)
)
with open(rels_path, 'w', encoding='utf-8') as f:
f.write(rels_xml)
# 处理备注
+ notes_content = ''
if enable_notes:
# 按文件名匹配(新逻辑)或按序号匹配(向后兼容)
svg_stem = svg_path.stem
- notes_content = notes.get(svg_stem, notes.get(i, '')) if notes else ''
+ notes_content = notes.get(svg_stem, '') if notes else ''
if notes_content:
notes_text = markdown_to_plain_text(notes_content)
else:
@@ -806,8 +813,8 @@ def create_pptx_with_native_svg(
f.write(slide_rels_content)
if verbose:
- mode_str = " (PNG+SVG)" if (use_compat_mode and png_generated) else " (SVG)"
- has_notes = enable_notes and notes and (notes.get(svg_stem) or notes.get(i))
+ mode_str = " (PNG+SVG)" if (use_compat_mode and slide_has_png) else " (SVG)"
+ has_notes = enable_notes and bool(notes_content)
notes_str = " +备注" if has_notes else ""
print(f" [{i}/{len(svg_files)}] {svg_path.name}{mode_str}{notes_str}")
@@ -826,7 +833,7 @@ def create_pptx_with_native_svg(
types_to_add = []
if 'Extension="svg"' not in content_types:
types_to_add.append(' <Default Extension="svg" ContentType="image/svg+xml"/>')
- if png_generated and 'Extension="png"' not in content_types:
+ if any_png_generated and 'Extension="png"' not in content_types:
types_to_add.append(' <Default Extension="png" ContentType="image/png"/>')
if types_to_add:
@@ -857,7 +864,7 @@ def create_pptx_with_native_svg(
print()
print(f"[完成] 已保存: {output_path}")
print(f" 成功: {success_count}, 失败: {len(svg_files) - success_count}")
- if use_compat_mode and png_generated:
+ if use_compat_mode and any_png_generated:
print(f" 模式: Office 兼容模式 (支持所有 Office 版本)")
# 如果使用 svglib,给出升级提示
if PNG_RENDERER == 'svglib' and renderer_hint: