refactor: 移除 doc 和 ppt reader 支持
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:
@@ -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",
|
||||
]
|
||||
|
||||
@@ -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
|
||||
@@ -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)
|
||||
@@ -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
|
||||
@@ -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
|
||||
@@ -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)
|
||||
Reference in New Issue
Block a user