lanyuanxiaoyao/lyxy-document
1
0
Fork 0
Code Releases Activity

feat: 新增 PPT 旧格式支持，重构 LibreOffice 转换工具

Browse Source 
- 新增 PPT (旧格式) 解析器
- 重构 _utils.py，提取通用 convert_via_libreoffice 函数
- 更新依赖配置，添加 PPT 相关依赖
- 完善文档，更新 README 和 SKILL.md
- 添加 PPT 文件检测函数
- 新增 PPT 解析器测试用例
This commit is contained in:
兰缘小妖
2026-03-16 22:49:04 +08:00
parent 1306dd5971
commit a490b2642c
14 changed files with 355 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
scripts/config.py
View File

@@ -116,5 +116,30 @@ DEPENDENCIES = {
"python": None,
"dependencies": []
}
},
"ppt": {
"default": {
"python": None,
"dependencies": [
"docling",
"unstructured[pptx]",
"markitdown[pptx]",
"python-pptx",
"markdownify",
"olefile"
]
},
"Darwin-x86_64": {
"python": "3.12",
"dependencies": [
"docling==2.40.0",
"docling-parse==4.0.0",
"numpy<2",
"markitdown[pptx]",
"python-pptx",
"markdownify",
"olefile"
]
}
}
}

3
scripts/readers/__init__.py
View File

@@ -8,6 +8,7 @@ from .pptx import PptxReader
from .pdf import PdfReader
from .html import HtmlReader
from .xls import XlsReader
from .ppt import PptReader
READERS = [
DocxReader,
@@ -17,6 +18,7 @@ READERS = [
PdfReader,
HtmlReader,
XlsReader,
PptReader,
]
__all__ = [
@@ -28,5 +30,6 @@ __all__ = [
"PdfReader",
"HtmlReader",
"XlsReader",
"PptReader",
"READERS",
]

125
scripts/readers/_utils.py
View File

@@ -66,6 +66,75 @@ def parse_via_docling(file_path: str) -> Tuple[Optional[str], Optional[str]]:
return None, f"docling 解析失败: {str(e)}"
def convert_via_libreoffice(
input_path: str,
target_format: str,
output_dir: Path,
output_suffix: Optional[str] = None,
timeout: int = 60
) -> Tuple[Optional[Path], Optional[str]]:
"""使用 LibreOffice soffice 命令行转换文件格式。
Args:
input_path: 输入文件路径
target_format: 目标格式（如 "md", "pptx"）
output_dir: 输出目录（调用者负责生命周期管理）
output_suffix: 可选，输出文件后缀（不指定则使用 target_format）
timeout: 超时时间（秒）
Returns:
(output_path, error_message): 成功时 (Path, None)，失败时 (None, error)
"""
# 检测 soffice 是否在 PATH 中
soffice_path = shutil.which("soffice")
if not soffice_path:
return None, "LibreOffice 未安装"
input_file = Path(input_path)
suffix = output_suffix if output_suffix else target_format
expected_output = output_dir / (input_file.stem + "." + suffix)
# 构建命令
cmd = [
soffice_path,
"--headless",
"--convert-to", target_format,
"--outdir", str(output_dir),
str(input_file)
]
# 执行命令
try:
result = subprocess.run(
cmd,
capture_output=True,
text=True,
timeout=timeout
)
except subprocess.TimeoutExpired:
return None, f"LibreOffice 转换超时 ({timeout}秒)"
# 检查返回码
if result.returncode != 0:
return None, f"LibreOffice 转换失败 (code: {result.returncode})"
# 检查输出文件是否存在
output_file = None
if expected_output.exists():
output_file = expected_output
else:
# Fallback: 遍历目录找任意匹配后缀的文件
pattern = "*." + suffix
files = list(output_dir.glob(pattern))
if files:
output_file = files[0]
if not output_file:
return None, "LibreOffice 未生成输出文件"
return output_file, None
def parse_via_libreoffice(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 LibreOffice soffice 命令行转换文件为 Markdown。
@@ -77,56 +146,18 @@ def parse_via_libreoffice(file_path: str) -> Tuple[Optional[str], Optional[str]]
Returns:
(markdown_content, error_message): 成功时 (content, None)，失败时 (None, error)
"""
# 检测 soffice 是否在 PATH 中
soffice_path = shutil.which("soffice")
if not soffice_path:
return None, "LibreOffice 未安装"
# 创建临时输出目录
with tempfile.TemporaryDirectory() as temp_dir:
temp_path = Path(temp_dir)
input_path = Path(file_path)
expected_output = temp_path / (input_path.stem + ".md")
# 构建命令
cmd = [
soffice_path,
"--headless",
"--convert-to", "md",
"--outdir", str(temp_path),
str(input_path)
]
# 执行命令，超时 60 秒
try:
result = subprocess.run(
cmd,
capture_output=True,
text=True,
timeout=60
)
except subprocess.TimeoutExpired:
return None, "LibreOffice 转换超时 (60秒)"
# 检查返回码
if result.returncode != 0:
return None, f"LibreOffice 转换失败 (code: {result.returncode})"
# 检查输出文件是否存在
output_file = None
if expected_output.exists():
output_file = expected_output
else:
# Fallback: 遍历目录找任意 .md 文件
md_files = list(temp_path.glob("*.md"))
if md_files:
output_file = md_files[0]
if not output_file:
return None, "LibreOffice 未生成输出文件"
output_path, error = convert_via_libreoffice(
input_path=file_path,
target_format="md",
output_dir=Path(temp_dir),
timeout=60
)
if error:
return None, error
# 读取输出内容
content = output_file.read_text(encoding="utf-8", errors="replace")
content = output_path.read_text(encoding="utf-8", errors="replace")
content = content.strip()
if not content:

46
scripts/readers/ppt/__init__.py Normal file
View File

@@ -0,0 +1,46 @@
"""PPT 文件阅读器，使用 LibreOffice 解析。"""
import os
from typing import List, Optional, Tuple
from readers.base import BaseReader
from utils import is_valid_ppt
from . import libreoffice
PARSERS = [
("LibreOffice", libreoffice.parse),
]
class PptReader(BaseReader):
"""PPT 文件阅读器"""
def supports(self, file_path: str) -> bool:
return file_path.lower().endswith('.ppt')
def parse(self, file_path: str) -> Tuple[Optional[str], List[str]]:
failures = []
# 检查文件是否存在
if not os.path.exists(file_path):
return None, ["文件不存在"]
# 验证文件格式
if not is_valid_ppt(file_path):
return None, ["不是有效的 PPT 文件"]
content = None
for parser_name, parser_func in PARSERS:
try:
content, error = parser_func(file_path)
if content is not None:
return content, failures
else:
failures.append(f"- {parser_name}: {error}")
except Exception as e:
failures.append(f"- {parser_name}: [意外异常] {type(e).__name__}: {str(e)}")
return None, failures

37
scripts/readers/ppt/libreoffice.py Normal file
View File

@@ -0,0 +1,37 @@
"""使用 LibreOffice soffice 命令行转换 PPT 为 PPTX 后复用 PptxReader 解析"""
import tempfile
from pathlib import Path
from typing import Optional, Tuple
from readers._utils import convert_via_libreoffice
from readers.pptx import PptxReader
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 LibreOffice soffice 解析 PPT 文件
Args:
file_path: PPT 文件路径
Returns:
(markdown_content, error_message): 成功时 (content, None)，失败时 (None, error)
"""
with tempfile.TemporaryDirectory() as temp_dir:
# 将 PPT 转换为 PPTX
pptx_path, error = convert_via_libreoffice(
input_path=file_path,
target_format="pptx",
output_dir=Path(temp_dir),
timeout=60
)
if error:
return None, error
# 复用 PptxReader 解析转换后的 PPTX
reader = PptxReader()
content, failures = reader.parse(str(pptx_path))
if content is not None:
return content, None
else:
return None, f"转换成功但 PPTX 解析失败: {failures}"

2
scripts/utils/__init__.py
View File

@@ -7,6 +7,7 @@ from .file_detection import (
is_valid_xlsx,
is_valid_pdf,
is_valid_xls,
is_valid_ppt,
is_html_file,
is_url,
)
@@ -18,6 +19,7 @@ __all__ = [
"is_valid_xlsx",
"is_valid_pdf",
"is_valid_xls",
"is_valid_ppt",
"is_html_file",
"is_url",
]

5
scripts/utils/file_detection.py
View File

@@ -58,6 +58,11 @@ def is_valid_doc(file_path: str) -> bool:
return _is_valid_ole(file_path)
def is_valid_ppt(file_path: str) -> bool:
"""验证文件是否为有效的 PPT 格式（OLE2）"""
return _is_valid_ole(file_path)
def is_valid_pdf(file_path: str) -> bool:
"""验证文件是否为有效的 PDF 格式"""
try: