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

refactor: 移除 doc 和 ppt reader 支持

Browse Source 
移除对旧版 .doc 和 .ppt 格式的支持，以简化项目架构和减少维护负担。

变更内容：
- 删除 scripts/readers/doc/ 目录
- 删除 scripts/readers/ppt/ 目录
- 从 readers/__init__.py 中移除 DocReader 和 PptReader
- 从 utils/file_detection.py 中移除 is_valid_doc 和 is_valid_ppt
- 从 config.py 中移除 doc 和 ppt 依赖配置
- 从 advice_generator.py 中移除相关映射
- 更新 CLI 帮助文档
- 更新 README.md 文档
- 删除相关测试用例
- 删除相关规范文档
This commit is contained in:
兰缘小妖
2026-03-11 00:55:15 +08:00
parent fad0edc46a
commit 65c746c639
22 changed files with 9 additions and 564 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
scripts/config.py
View File

@@ -98,16 +98,6 @@ DEPENDENCIES = {
]
}
},
"doc": {
"default": {
"python": None,
"dependencies": [
"markitdown[docx]",
"pypandoc-binary",
"olefile"
]
}
},
"xls": {
"default": {
"python": None,
@@ -120,14 +110,5 @@ DEPENDENCIES = {
"olefile"
]
}
},
"ppt": {
"default": {
"python": None,
"dependencies": [
"markitdown[pptx]",
"olefile"
]
}
}
}

4
scripts/core/advice_generator.py
View File

@@ -12,9 +12,7 @@ from readers import (
XlsxReader,
PptxReader,
HtmlReader,
DocReader,
XlsReader,
PptReader,
)
@@ -25,9 +23,7 @@ _READER_KEY_MAP: Dict[Type[BaseReader], str] = {
XlsxReader: "xlsx",
PptxReader: "pptx",
HtmlReader: "html",
DocReader: "doc",
XlsReader: "xls",
PptReader: "ppt",
}

6
scripts/lyxy_document_reader.py
View File

@@ -1,5 +1,5 @@
#!/usr/bin/env python3
"""文档解析器命令行交互模块，提供命令行接口。支持 DOC、DOCX、XLS、XLSX、PPT、PPTX、PDF、HTML 和 URL。"""
"""文档解析器命令行交互模块，提供命令行接口。支持 DOCX、XLS、XLSX、PPTX、PDF、HTML 和 URL。"""
import argparse
import logging
@@ -39,10 +39,10 @@ from readers import READERS
def main() -> None:
parser = argparse.ArgumentParser(
description="将 DOC、DOCX、XLS、XLSX、PPT、PPTX、PDF、HTML 文件或 URL 解析为 Markdown"
description="将 DOCX、XLS、XLSX、PPTX、PDF、HTML 文件或 URL 解析为 Markdown"
)
parser.add_argument("input_path", help="DOC、DOCX、XLS、XLSX、PPT、PPTX、PDF、HTML 文件或 URL")
parser.add_argument("input_path", help="DOCX、XLS、XLSX、PPTX、PDF、HTML 文件或 URL")
parser.add_argument(
"-a",

6
scripts/readers/__init__.py
View File

@@ -6,9 +6,7 @@ from .xlsx import XlsxReader
from .pptx import PptxReader
from .pdf import PdfReader
from .html import HtmlReader
from .doc import DocReader
from .xls import XlsReader
from .ppt import PptReader
READERS = [
DocxReader,
@@ -16,9 +14,7 @@ READERS = [
PptxReader,
PdfReader,
HtmlReader,
DocReader,
XlsReader,
PptReader,
]
__all__ = [
@@ -28,8 +24,6 @@ __all__ = [
"PptxReader",
"PdfReader",
"HtmlReader",
"DocReader",
"XlsReader",
"PptReader",
"READERS",
]

48
scripts/readers/doc/__init__.py
View File

@@ -1,48 +0,0 @@
"""DOC 文件阅读器，支持多种解析方法。"""
import os
from typing import List, Optional, Tuple
from readers.base import BaseReader
from utils import is_valid_doc
from . import markitdown
from . import pypandoc
PARSERS = [
("MarkItDown", markitdown.parse),
("pypandoc-binary", pypandoc.parse),
]
class DocReader(BaseReader):
"""DOC 文件阅读器"""
def supports(self, file_path: str) -> bool:
return file_path.lower().endswith('.doc')
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_doc(file_path):
return None, ["不是有效的 DOC 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

10
scripts/readers/doc/markitdown.py
View File

@@ -1,10 +0,0 @@
"""使用 MarkItDown 库解析 DOC 文件"""
from typing import Optional, Tuple
from readers._utils import parse_via_markitdown
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 MarkItDown 库解析 DOC 文件"""
return parse_via_markitdown(file_path)

29
scripts/readers/doc/pypandoc.py
View File

@@ -1,29 +0,0 @@
"""使用 pypandoc-binary 库解析 DOC 文件"""
from typing import Optional, Tuple
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 pypandoc-binary 库解析 DOC 文件"""
try:
import pypandoc
except ImportError:
return None, "pypandoc-binary 库未安装"
try:
content = pypandoc.convert_file(
source_file=file_path,
to="md",
format="doc",
outputfile=None,
extra_args=["--wrap=none"],
)
except OSError as exc:
return None, f"pypandoc-binary 缺少 Pandoc 可执行文件: {exc}"
except RuntimeError as exc:
return None, f"pypandoc-binary 解析失败: {exc}"
content = content.strip()
if not content:
return None, "文档为空"
return content, None

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

@@ -1,46 +0,0 @@
"""PPT 文件阅读器，支持多种解析方法。"""
import os
from typing import List, Optional, Tuple
from readers.base import BaseReader
from utils import is_valid_ppt
from . import markitdown
PARSERS = [
("MarkItDown", markitdown.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

10
scripts/readers/ppt/markitdown.py
View File

@@ -1,10 +0,0 @@
"""使用 MarkItDown 库解析 PPT 文件"""
from typing import Optional, Tuple
from readers._utils import parse_via_markitdown
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 MarkItDown 库解析 PPT 文件"""
return parse_via_markitdown(file_path)

4
scripts/utils/__init__.py
View File

@@ -5,9 +5,7 @@ from .file_detection import (
is_valid_pptx,
is_valid_xlsx,
is_valid_pdf,
is_valid_doc,
is_valid_xls,
is_valid_ppt,
is_html_file,
is_url,
)
@@ -17,9 +15,7 @@ __all__ = [
"is_valid_pptx",
"is_valid_xlsx",
"is_valid_pdf",
"is_valid_doc",
"is_valid_xls",
"is_valid_ppt",
"is_html_file",
"is_url",
]

16
scripts/utils/file_detection.py
View File

@@ -6,7 +6,7 @@ from typing import List, Optional
def _is_valid_ole(file_path: str) -> bool:
"""验证 OLE2 格式文件（DOC/XLS/PPT）"""
"""验证 OLE2 格式文件（XLS）"""
try:
import olefile
except ImportError:
@@ -48,21 +48,11 @@ def is_valid_xlsx(file_path: str) -> bool:
return _is_valid_ooxml(file_path, _XLSX_REQUIRED)
def is_valid_doc(file_path: str) -> bool:
"""验证文件是否为有效的 DOC 格式"""
return _is_valid_ole(file_path)
def is_valid_xls(file_path: str) -> bool:
"""验证文件是否为有效的 XLS 格式"""
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"""
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:
@@ -82,7 +72,3 @@ def is_html_file(file_path: str) -> bool:
def is_url(input_str: str) -> bool:
"""判断输入是否为 URL"""
return input_str.startswith("http://") or input_str.startswith("https://")