feat: 添加 doc/xls/ppt 旧格式文档支持
- 新增 DocReader,支持 markitdown 和 pypandoc-binary 解析器 - 新增 XlsReader,支持 unstructured、markitdown 和 pandas+xlrd 解析器 - 新增 PptReader,支持 markitdown 解析器 - 添加 olefile 依赖用于验证 OLE2 格式 - 更新 config.py 添加 doc/xls/ppt 依赖配置 - 更新 --advice 支持 doc/xls/ppt 格式 - 添加相应的测试用例 - 同步 specs 到主目录
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
# lyxy-document
|
||||
|
||||
统一文档解析工具 - 将 DOCX、XLSX、PPTX、PDF、HTML/URL 转换为 Markdown
|
||||
统一文档解析工具 - 将 DOC、DOCX、XLS、XLSX、PPT、PPTX、PDF、HTML/URL 转换为 Markdown
|
||||
|
||||
## 项目概述
|
||||
|
||||
@@ -25,8 +25,11 @@ scripts/
|
||||
│ └── exceptions.py # 异常定义
|
||||
├── readers/ # 格式阅读器
|
||||
│ ├── base.py # Reader 基类
|
||||
│ ├── doc/ # DOC 解析器(旧格式)
|
||||
│ ├── docx/ # DOCX 解析器
|
||||
│ ├── xls/ # XLS 解析器(旧格式)
|
||||
│ ├── xlsx/ # XLSX 解析器
|
||||
│ ├── ppt/ # PPT 解析器(旧格式)
|
||||
│ ├── pptx/ # PPTX 解析器
|
||||
│ ├── pdf/ # PDF 解析器
|
||||
│ └── html/ # HTML/URL 解析器
|
||||
|
||||
53
openspec/specs/doc-reader/spec.md
Normal file
53
openspec/specs/doc-reader/spec.md
Normal file
@@ -0,0 +1,53 @@
|
||||
## Purpose
|
||||
|
||||
DOC 文档解析能力,支持解析 Microsoft Word 97-2003 旧格式文档。
|
||||
|
||||
## Requirements
|
||||
|
||||
### Requirement: DOC 文档解析
|
||||
系统 SHALL 支持解析 .doc 格式文档,按优先级尝试多个解析器。
|
||||
|
||||
#### Scenario: 按优先级尝试解析器
|
||||
- **WHEN** 解析 DOC 文档
|
||||
- **THEN** 系统按 markitdown → pypandoc-binary 的顺序尝试
|
||||
|
||||
#### Scenario: 成功解析
|
||||
- **WHEN** 任一解析器成功
|
||||
- **THEN** 系统返回解析结果
|
||||
|
||||
#### Scenario: 所有解析器失败
|
||||
- **WHEN** 所有解析器均失败
|
||||
- **THEN** 系统返回失败列表并退出非零状态码
|
||||
|
||||
### Requirement: markitdown 解析器
|
||||
系统 SHALL 支持使用 markitdown 库解析 DOC。
|
||||
|
||||
#### Scenario: markitdown 解析成功
|
||||
- **WHEN** markitdown 库可用且文档有效
|
||||
- **THEN** 系统返回 Markdown 内容
|
||||
|
||||
#### Scenario: markitdown 库未安装
|
||||
- **WHEN** markitdown 库未安装
|
||||
- **THEN** 系统尝试下一个解析器
|
||||
|
||||
### Requirement: pypandoc-binary 解析器
|
||||
系统 SHALL 支持使用 pypandoc-binary 库解析 DOC。
|
||||
|
||||
#### Scenario: pypandoc 解析成功
|
||||
- **WHEN** pypandoc-binary 库可用且文档有效
|
||||
- **THEN** 系统返回 Markdown 内容
|
||||
|
||||
#### Scenario: pypandoc-binary 库未安装
|
||||
- **WHEN** pypandoc-binary 库未安装
|
||||
- **THEN** 系统尝试下一个解析器
|
||||
|
||||
### Requirement: 每个解析器独立文件
|
||||
系统 SHALL 将每个解析器实现为独立的单文件模块。
|
||||
|
||||
#### Scenario: markitdown 解析器在独立文件
|
||||
- **WHEN** 使用 markitdown 解析器
|
||||
- **THEN** 从 readers/doc/markitdown.py 导入
|
||||
|
||||
#### Scenario: pypandoc 解析器在独立文件
|
||||
- **WHEN** 使用 pypandoc 解析器
|
||||
- **THEN** 从 readers/doc/pypandoc.py 导入
|
||||
38
openspec/specs/ppt-reader/spec.md
Normal file
38
openspec/specs/ppt-reader/spec.md
Normal file
@@ -0,0 +1,38 @@
|
||||
## Purpose
|
||||
|
||||
PPT 文档解析能力,支持解析 Microsoft PowerPoint 97-2003 旧格式文档。
|
||||
|
||||
## Requirements
|
||||
|
||||
### Requirement: PPT 文档解析
|
||||
系统 SHALL 支持解析 .ppt 格式文档,按优先级尝试多个解析器。
|
||||
|
||||
#### Scenario: 按优先级尝试解析器
|
||||
- **WHEN** 解析 PPT 文档
|
||||
- **THEN** 系统按 markitdown 的顺序尝试
|
||||
|
||||
#### Scenario: 成功解析
|
||||
- **WHEN** 任一解析器成功
|
||||
- **THEN** 系统返回解析结果
|
||||
|
||||
#### Scenario: 所有解析器失败
|
||||
- **WHEN** 所有解析器均失败
|
||||
- **THEN** 系统返回失败列表并退出非零状态码
|
||||
|
||||
### Requirement: markitdown 解析器
|
||||
系统 SHALL 支持使用 markitdown 库解析 PPT。
|
||||
|
||||
#### Scenario: markitdown 解析成功
|
||||
- **WHEN** markitdown 库可用且文档有效
|
||||
- **THEN** 系统返回 Markdown 内容
|
||||
|
||||
#### Scenario: markitdown 库未安装
|
||||
- **WHEN** markitdown 库未安装
|
||||
- **THEN** 系统返回失败信息
|
||||
|
||||
### Requirement: 每个解析器独立文件
|
||||
系统 SHALL 将每个解析器实现为独立的单文件模块。
|
||||
|
||||
#### Scenario: markitdown 解析器在独立文件
|
||||
- **WHEN** 使用 markitdown 解析器
|
||||
- **THEN** 从 readers/ppt/markitdown.py 导入
|
||||
68
openspec/specs/xls-reader/spec.md
Normal file
68
openspec/specs/xls-reader/spec.md
Normal file
@@ -0,0 +1,68 @@
|
||||
## Purpose
|
||||
|
||||
XLS 文档解析能力,支持解析 Microsoft Excel 97-2003 旧格式文档。
|
||||
|
||||
## Requirements
|
||||
|
||||
### Requirement: XLS 文档解析
|
||||
系统 SHALL 支持解析 .xls 格式文档,按优先级尝试多个解析器。
|
||||
|
||||
#### Scenario: 按优先级尝试解析器
|
||||
- **WHEN** 解析 XLS 文档
|
||||
- **THEN** 系统按 unstructured → markitdown → pandas+xlrd 的顺序尝试
|
||||
|
||||
#### Scenario: 成功解析
|
||||
- **WHEN** 任一解析器成功
|
||||
- **THEN** 系统返回解析结果
|
||||
|
||||
#### Scenario: 所有解析器失败
|
||||
- **WHEN** 所有解析器均失败
|
||||
- **THEN** 系统返回失败列表并退出非零状态码
|
||||
|
||||
### Requirement: unstructured 解析器
|
||||
系统 SHALL 支持使用 unstructured 库解析 XLS。
|
||||
|
||||
#### Scenario: unstructured 解析成功
|
||||
- **WHEN** unstructured 库可用且文档有效
|
||||
- **THEN** 系统返回 Markdown 内容
|
||||
|
||||
#### Scenario: unstructured 库未安装
|
||||
- **WHEN** unstructured 库未安装
|
||||
- **THEN** 系统尝试下一个解析器
|
||||
|
||||
### Requirement: markitdown 解析器
|
||||
系统 SHALL 支持使用 markitdown 库解析 XLS。
|
||||
|
||||
#### Scenario: markitdown 解析成功
|
||||
- **WHEN** markitdown 库可用且文档有效
|
||||
- **THEN** 系统返回 Markdown 内容
|
||||
|
||||
#### Scenario: markitdown 库未安装
|
||||
- **WHEN** markitdown 库未安装
|
||||
- **THEN** 系统尝试下一个解析器
|
||||
|
||||
### Requirement: pandas+xlrd 解析器
|
||||
系统 SHALL 支持使用 pandas + xlrd 库解析 XLS。
|
||||
|
||||
#### Scenario: pandas+xlrd 解析成功
|
||||
- **WHEN** pandas 和 xlrd 库可用且文档有效
|
||||
- **THEN** 系统返回 Markdown 格式的表格内容,包含所有工作表
|
||||
|
||||
#### Scenario: pandas 或 xlrd 库未安装
|
||||
- **WHEN** pandas 或 xlrd 库未安装
|
||||
- **THEN** 系统尝试下一个解析器
|
||||
|
||||
### Requirement: 每个解析器独立文件
|
||||
系统 SHALL 将每个解析器实现为独立的单文件模块。
|
||||
|
||||
#### Scenario: unstructured 解析器在独立文件
|
||||
- **WHEN** 使用 unstructured 解析器
|
||||
- **THEN** 从 readers/xls/unstructured.py 导入
|
||||
|
||||
#### Scenario: markitdown 解析器在独立文件
|
||||
- **WHEN** 使用 markitdown 解析器
|
||||
- **THEN** 从 readers/xls/markitdown.py 导入
|
||||
|
||||
#### Scenario: pandas 解析器在独立文件
|
||||
- **WHEN** 使用 pandas 解析器
|
||||
- **THEN** 从 readers/xls/pandas.py 导入
|
||||
@@ -97,5 +97,37 @@ DEPENDENCIES = {
|
||||
"selenium"
|
||||
]
|
||||
}
|
||||
},
|
||||
"doc": {
|
||||
"default": {
|
||||
"python": None,
|
||||
"dependencies": [
|
||||
"markitdown[docx]",
|
||||
"pypandoc-binary",
|
||||
"olefile"
|
||||
]
|
||||
}
|
||||
},
|
||||
"xls": {
|
||||
"default": {
|
||||
"python": None,
|
||||
"dependencies": [
|
||||
"unstructured[xlsx]",
|
||||
"markitdown[xls]",
|
||||
"pandas",
|
||||
"tabulate",
|
||||
"xlrd",
|
||||
"olefile"
|
||||
]
|
||||
}
|
||||
},
|
||||
"ppt": {
|
||||
"default": {
|
||||
"python": None,
|
||||
"dependencies": [
|
||||
"markitdown[pptx]",
|
||||
"olefile"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -12,6 +12,9 @@ from readers import (
|
||||
XlsxReader,
|
||||
PptxReader,
|
||||
HtmlReader,
|
||||
DocReader,
|
||||
XlsReader,
|
||||
PptReader,
|
||||
)
|
||||
|
||||
|
||||
@@ -22,6 +25,9 @@ _READER_KEY_MAP: Dict[Type[BaseReader], str] = {
|
||||
XlsxReader: "xlsx",
|
||||
PptxReader: "pptx",
|
||||
HtmlReader: "html",
|
||||
DocReader: "doc",
|
||||
XlsReader: "xls",
|
||||
PptReader: "ppt",
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -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 DOCX、PPTX、XLSX、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 DOC、DOCX、XLS、XLSX、PPT、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 DOCX、PPTX、XLSX、PDF、HTML 文件或 URL 解析为 Markdown"
|
||||
description="将 DOC、DOCX、XLS、XLSX、PPT、PPTX、PDF、HTML 文件或 URL 解析为 Markdown"
|
||||
)
|
||||
|
||||
parser.add_argument("input_path", help="DOCX、PPTX、XLSX、PDF、HTML 文件或 URL")
|
||||
parser.add_argument("input_path", help="DOC、DOCX、XLS、XLSX、PPT、PPTX、PDF、HTML 文件或 URL")
|
||||
|
||||
parser.add_argument(
|
||||
"-a",
|
||||
|
||||
@@ -6,6 +6,9 @@ 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,
|
||||
@@ -13,6 +16,9 @@ READERS = [
|
||||
PptxReader,
|
||||
PdfReader,
|
||||
HtmlReader,
|
||||
DocReader,
|
||||
XlsReader,
|
||||
PptReader,
|
||||
]
|
||||
|
||||
__all__ = [
|
||||
@@ -22,5 +28,8 @@ __all__ = [
|
||||
"PptxReader",
|
||||
"PdfReader",
|
||||
"HtmlReader",
|
||||
"DocReader",
|
||||
"XlsReader",
|
||||
"PptReader",
|
||||
"READERS",
|
||||
]
|
||||
|
||||
48
scripts/readers/doc/__init__.py
Normal file
48
scripts/readers/doc/__init__.py
Normal file
@@ -0,0 +1,48 @@
|
||||
"""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
Normal file
10
scripts/readers/doc/markitdown.py
Normal file
@@ -0,0 +1,10 @@
|
||||
"""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
Normal file
29
scripts/readers/doc/pypandoc.py
Normal file
@@ -0,0 +1,29 @@
|
||||
"""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
Normal file
46
scripts/readers/ppt/__init__.py
Normal file
@@ -0,0 +1,46 @@
|
||||
"""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
Normal file
10
scripts/readers/ppt/markitdown.py
Normal file
@@ -0,0 +1,10 @@
|
||||
"""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)
|
||||
50
scripts/readers/xls/__init__.py
Normal file
50
scripts/readers/xls/__init__.py
Normal file
@@ -0,0 +1,50 @@
|
||||
"""XLS 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_xls
|
||||
|
||||
from . import unstructured
|
||||
from . import markitdown
|
||||
from . import pandas
|
||||
|
||||
|
||||
PARSERS = [
|
||||
("unstructured", unstructured.parse),
|
||||
("MarkItDown", markitdown.parse),
|
||||
("pandas+xlrd", pandas.parse),
|
||||
]
|
||||
|
||||
|
||||
class XlsReader(BaseReader):
|
||||
"""XLS 文件阅读器"""
|
||||
|
||||
def supports(self, file_path: str) -> bool:
|
||||
return file_path.lower().endswith('.xls')
|
||||
|
||||
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_xls(file_path):
|
||||
return None, ["不是有效的 XLS 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/xls/markitdown.py
Normal file
10
scripts/readers/xls/markitdown.py
Normal file
@@ -0,0 +1,10 @@
|
||||
"""使用 MarkItDown 库解析 XLS 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 XLS 文件"""
|
||||
return parse_via_markitdown(file_path)
|
||||
41
scripts/readers/xls/pandas.py
Normal file
41
scripts/readers/xls/pandas.py
Normal file
@@ -0,0 +1,41 @@
|
||||
"""使用 pandas+xlrd 库解析 XLS 文件"""
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 pandas+xlrd 库解析 XLS 文件"""
|
||||
try:
|
||||
import pandas as pd
|
||||
from tabulate import tabulate
|
||||
except ImportError as e:
|
||||
if "pandas" in str(e):
|
||||
missing_lib = "pandas"
|
||||
elif "xlrd" in str(e):
|
||||
missing_lib = "xlrd"
|
||||
else:
|
||||
missing_lib = "tabulate"
|
||||
return None, f"{missing_lib} 库未安装"
|
||||
|
||||
try:
|
||||
sheets = pd.read_excel(file_path, sheet_name=None, engine="xlrd")
|
||||
|
||||
markdown_parts = []
|
||||
for sheet_name, df in sheets.items():
|
||||
if len(df) == 0:
|
||||
markdown_parts.append(f"## {sheet_name}\n\n*工作表为空*")
|
||||
continue
|
||||
|
||||
table_md = tabulate(
|
||||
df, headers="keys", tablefmt="pipe", showindex=True, missingval=""
|
||||
)
|
||||
markdown_parts.append(f"## {sheet_name}\n\n{table_md}")
|
||||
|
||||
if not markdown_parts:
|
||||
return None, "Excel 文件为空"
|
||||
|
||||
markdown_content = "# Excel数据转换结果\n\n" + "\n\n".join(markdown_parts)
|
||||
|
||||
return markdown_content, None
|
||||
except Exception as e:
|
||||
return None, f"pandas 解析失败: {str(e)}"
|
||||
22
scripts/readers/xls/unstructured.py
Normal file
22
scripts/readers/xls/unstructured.py
Normal file
@@ -0,0 +1,22 @@
|
||||
"""使用 unstructured 库解析 XLS 文件"""
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
from readers._utils import convert_unstructured_to_markdown
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 unstructured 库解析 XLS 文件"""
|
||||
try:
|
||||
from unstructured.partition.xlsx import partition_xlsx
|
||||
except ImportError:
|
||||
return None, "unstructured 库未安装"
|
||||
|
||||
try:
|
||||
elements = partition_xlsx(filename=file_path, infer_table_structure=True)
|
||||
content = convert_unstructured_to_markdown(elements)
|
||||
if not content.strip():
|
||||
return None, "文档为空"
|
||||
return content, None
|
||||
except Exception as e:
|
||||
return None, f"unstructured 解析失败: {str(e)}"
|
||||
@@ -5,6 +5,9 @@ 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,
|
||||
detect_file_type,
|
||||
@@ -15,6 +18,9 @@ __all__ = [
|
||||
"is_valid_pptx",
|
||||
"is_valid_xlsx",
|
||||
"is_valid_pdf",
|
||||
"is_valid_doc",
|
||||
"is_valid_xls",
|
||||
"is_valid_ppt",
|
||||
"is_html_file",
|
||||
"is_url",
|
||||
"detect_file_type",
|
||||
|
||||
@@ -5,6 +5,19 @@ import zipfile
|
||||
from typing import List, Optional
|
||||
|
||||
|
||||
def _is_valid_ole(file_path: str) -> bool:
|
||||
"""验证 OLE2 格式文件(DOC/XLS/PPT)"""
|
||||
try:
|
||||
import olefile
|
||||
except ImportError:
|
||||
# 如果 olefile 未安装,就不做严格验证
|
||||
return True
|
||||
try:
|
||||
return olefile.isOleFile(file_path)
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
def _is_valid_ooxml(file_path: str, required_files: List[str]) -> bool:
|
||||
"""验证 OOXML 格式文件(DOCX/PPTX/XLSX)"""
|
||||
try:
|
||||
@@ -35,6 +48,21 @@ 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:
|
||||
@@ -61,13 +89,18 @@ _FILE_TYPE_VALIDATORS = {
|
||||
".pptx": is_valid_pptx,
|
||||
".xlsx": is_valid_xlsx,
|
||||
".pdf": is_valid_pdf,
|
||||
".doc": is_valid_doc,
|
||||
".xls": is_valid_xls,
|
||||
".ppt": is_valid_ppt,
|
||||
}
|
||||
|
||||
|
||||
def detect_file_type(file_path: str) -> Optional[str]:
|
||||
"""检测文件类型,返回 'docx'、'pptx'、'xlsx' 或 'pdf'"""
|
||||
"""检测文件类型,返回 'docx'、'pptx'、'xlsx'、'pdf'、'doc'、'xls' 或 'ppt'"""
|
||||
ext = os.path.splitext(file_path)[1].lower()
|
||||
validator = _FILE_TYPE_VALIDATORS.get(ext)
|
||||
if validator and validator(file_path):
|
||||
return ext.lstrip(".")
|
||||
return None
|
||||
|
||||
|
||||
|
||||
@@ -38,6 +38,27 @@ class TestCLIAdviceOption:
|
||||
output = stdout + stderr
|
||||
assert "无法识别" in output or "错误" in output
|
||||
|
||||
def test_advice_option_doc(self, cli_runner):
|
||||
"""测试 --advice 选项对 DOC 文件。"""
|
||||
stdout, stderr, exit_code = cli_runner(["test.doc", "--advice"])
|
||||
|
||||
assert exit_code == 0
|
||||
assert "文件类型: DOC" in stdout
|
||||
|
||||
def test_advice_option_xls(self, cli_runner):
|
||||
"""测试 --advice 选项对 XLS 文件。"""
|
||||
stdout, stderr, exit_code = cli_runner(["test.xls", "--advice"])
|
||||
|
||||
assert exit_code == 0
|
||||
assert "文件类型: XLS" in stdout
|
||||
|
||||
def test_advice_option_ppt(self, cli_runner):
|
||||
"""测试 --advice 选项对 PPT 文件。"""
|
||||
stdout, stderr, exit_code = cli_runner(["test.ppt", "--advice"])
|
||||
|
||||
assert exit_code == 0
|
||||
assert "文件类型: PPT" in stdout
|
||||
|
||||
|
||||
class TestCLIDefaultOutput:
|
||||
"""测试 CLI 默认输出功能。"""
|
||||
|
||||
1
tests/test_readers/test_doc/__init__.py
Normal file
1
tests/test_readers/test_doc/__init__.py
Normal file
@@ -0,0 +1 @@
|
||||
"""测试 DocReader 模块。"""
|
||||
21
tests/test_readers/test_doc/test_consistency.py
Normal file
21
tests/test_readers/test_doc/test_consistency.py
Normal file
@@ -0,0 +1,21 @@
|
||||
"""测试所有 DOC Readers 的一致性。"""
|
||||
|
||||
import pytest
|
||||
from readers.doc import markitdown, pypandoc
|
||||
|
||||
|
||||
class TestDocReadersConsistency:
|
||||
"""验证 DOC Readers 模块结构正确。"""
|
||||
|
||||
def test_parsers_importable(self):
|
||||
"""测试所有 parser 模块可以正确导入。"""
|
||||
# 验证模块导入成功
|
||||
assert markitdown is not None
|
||||
assert pypandoc is not None
|
||||
assert hasattr(markitdown, 'parse')
|
||||
assert hasattr(pypandoc, 'parse')
|
||||
|
||||
def test_parser_functions_callable(self):
|
||||
"""测试 parse 函数是可调用的。"""
|
||||
assert callable(markitdown.parse)
|
||||
assert callable(pypandoc.parse)
|
||||
25
tests/test_readers/test_doc/test_markitdown_doc.py
Normal file
25
tests/test_readers/test_doc/test_markitdown_doc.py
Normal file
@@ -0,0 +1,25 @@
|
||||
"""测试 MarkItDown DOC Reader 的解析功能。"""
|
||||
|
||||
import pytest
|
||||
import os
|
||||
from readers.doc import markitdown
|
||||
|
||||
|
||||
class TestMarkitdownDocReaderParse:
|
||||
"""测试 MarkItDown DOC Reader 的 parse 方法。"""
|
||||
|
||||
def test_module_importable(self):
|
||||
"""测试模块可以正确导入。"""
|
||||
assert markitdown is not None
|
||||
assert hasattr(markitdown, 'parse')
|
||||
assert callable(markitdown.parse)
|
||||
|
||||
def test_file_not_exists(self, tmp_path):
|
||||
"""测试文件不存在的情况。"""
|
||||
non_existent_file = str(tmp_path / "non_existent.doc")
|
||||
|
||||
content, error = markitdown.parse(non_existent_file)
|
||||
|
||||
# 验证返回 None 和错误信息
|
||||
assert content is None
|
||||
assert error is not None
|
||||
25
tests/test_readers/test_doc/test_pypandoc_doc.py
Normal file
25
tests/test_readers/test_doc/test_pypandoc_doc.py
Normal file
@@ -0,0 +1,25 @@
|
||||
"""测试 pypandoc DOC Reader 的解析功能。"""
|
||||
|
||||
import pytest
|
||||
import os
|
||||
from readers.doc import pypandoc
|
||||
|
||||
|
||||
class TestPypandocDocReaderParse:
|
||||
"""测试 pypandoc DOC Reader 的 parse 方法。"""
|
||||
|
||||
def test_module_importable(self):
|
||||
"""测试模块可以正确导入。"""
|
||||
assert pypandoc is not None
|
||||
assert hasattr(pypandoc, 'parse')
|
||||
assert callable(pypandoc.parse)
|
||||
|
||||
def test_file_not_exists(self, tmp_path):
|
||||
"""测试文件不存在的情况。"""
|
||||
non_existent_file = str(tmp_path / "non_existent.doc")
|
||||
|
||||
content, error = pypandoc.parse(non_existent_file)
|
||||
|
||||
# 验证返回 None 和错误信息
|
||||
assert content is None
|
||||
assert error is not None
|
||||
1
tests/test_readers/test_ppt/__init__.py
Normal file
1
tests/test_readers/test_ppt/__init__.py
Normal file
@@ -0,0 +1 @@
|
||||
"""测试 PptReader 模块。"""
|
||||
18
tests/test_readers/test_ppt/test_consistency.py
Normal file
18
tests/test_readers/test_ppt/test_consistency.py
Normal file
@@ -0,0 +1,18 @@
|
||||
"""测试所有 PPT Readers 的一致性。"""
|
||||
|
||||
import pytest
|
||||
from readers.ppt import markitdown
|
||||
|
||||
|
||||
class TestPptReadersConsistency:
|
||||
"""验证 PPT Readers 模块结构正确。"""
|
||||
|
||||
def test_parsers_importable(self):
|
||||
"""测试所有 parser 模块可以正确导入。"""
|
||||
# 验证模块导入成功
|
||||
assert markitdown is not None
|
||||
assert hasattr(markitdown, 'parse')
|
||||
|
||||
def test_parser_functions_callable(self):
|
||||
"""测试 parse 函数是可调用的。"""
|
||||
assert callable(markitdown.parse)
|
||||
25
tests/test_readers/test_ppt/test_markitdown_ppt.py
Normal file
25
tests/test_readers/test_ppt/test_markitdown_ppt.py
Normal file
@@ -0,0 +1,25 @@
|
||||
"""测试 MarkItDown PPT Reader 的解析功能。"""
|
||||
|
||||
import pytest
|
||||
import os
|
||||
from readers.ppt import markitdown
|
||||
|
||||
|
||||
class TestMarkitdownPptReaderParse:
|
||||
"""测试 MarkItDown PPT Reader 的 parse 方法。"""
|
||||
|
||||
def test_module_importable(self):
|
||||
"""测试模块可以正确导入。"""
|
||||
assert markitdown is not None
|
||||
assert hasattr(markitdown, 'parse')
|
||||
assert callable(markitdown.parse)
|
||||
|
||||
def test_file_not_exists(self, tmp_path):
|
||||
"""测试文件不存在的情况。"""
|
||||
non_existent_file = str(tmp_path / "non_existent.ppt")
|
||||
|
||||
content, error = markitdown.parse(non_existent_file)
|
||||
|
||||
# 验证返回 None 和错误信息
|
||||
assert content is None
|
||||
assert error is not None
|
||||
1
tests/test_readers/test_xls/__init__.py
Normal file
1
tests/test_readers/test_xls/__init__.py
Normal file
@@ -0,0 +1 @@
|
||||
"""测试 XlsReader 模块。"""
|
||||
24
tests/test_readers/test_xls/test_consistency.py
Normal file
24
tests/test_readers/test_xls/test_consistency.py
Normal file
@@ -0,0 +1,24 @@
|
||||
"""测试所有 XLS Readers 的一致性。"""
|
||||
|
||||
import pytest
|
||||
from readers.xls import unstructured, markitdown, pandas
|
||||
|
||||
|
||||
class TestXlsReadersConsistency:
|
||||
"""验证 XLS Readers 模块结构正确。"""
|
||||
|
||||
def test_parsers_importable(self):
|
||||
"""测试所有 parser 模块可以正确导入。"""
|
||||
# 验证模块导入成功
|
||||
assert unstructured is not None
|
||||
assert markitdown is not None
|
||||
assert pandas is not None
|
||||
assert hasattr(unstructured, 'parse')
|
||||
assert hasattr(markitdown, 'parse')
|
||||
assert hasattr(pandas, 'parse')
|
||||
|
||||
def test_parser_functions_callable(self):
|
||||
"""测试 parse 函数是可调用的。"""
|
||||
assert callable(unstructured.parse)
|
||||
assert callable(markitdown.parse)
|
||||
assert callable(pandas.parse)
|
||||
25
tests/test_readers/test_xls/test_markitdown_xls.py
Normal file
25
tests/test_readers/test_xls/test_markitdown_xls.py
Normal file
@@ -0,0 +1,25 @@
|
||||
"""测试 MarkItDown XLS Reader 的解析功能。"""
|
||||
|
||||
import pytest
|
||||
import os
|
||||
from readers.xls import markitdown
|
||||
|
||||
|
||||
class TestMarkitdownXlsReaderParse:
|
||||
"""测试 MarkItDown XLS Reader 的 parse 方法。"""
|
||||
|
||||
def test_module_importable(self):
|
||||
"""测试模块可以正确导入。"""
|
||||
assert markitdown is not None
|
||||
assert hasattr(markitdown, 'parse')
|
||||
assert callable(markitdown.parse)
|
||||
|
||||
def test_file_not_exists(self, tmp_path):
|
||||
"""测试文件不存在的情况。"""
|
||||
non_existent_file = str(tmp_path / "non_existent.xls")
|
||||
|
||||
content, error = markitdown.parse(non_existent_file)
|
||||
|
||||
# 验证返回 None 和错误信息
|
||||
assert content is None
|
||||
assert error is not None
|
||||
25
tests/test_readers/test_xls/test_pandas_xls.py
Normal file
25
tests/test_readers/test_xls/test_pandas_xls.py
Normal file
@@ -0,0 +1,25 @@
|
||||
"""测试 pandas XLS Reader 的解析功能。"""
|
||||
|
||||
import pytest
|
||||
import os
|
||||
from readers.xls import pandas
|
||||
|
||||
|
||||
class TestPandasXlsReaderParse:
|
||||
"""测试 pandas XLS Reader 的 parse 方法。"""
|
||||
|
||||
def test_module_importable(self):
|
||||
"""测试模块可以正确导入。"""
|
||||
assert pandas is not None
|
||||
assert hasattr(pandas, 'parse')
|
||||
assert callable(pandas.parse)
|
||||
|
||||
def test_file_not_exists(self, tmp_path):
|
||||
"""测试文件不存在的情况。"""
|
||||
non_existent_file = str(tmp_path / "non_existent.xls")
|
||||
|
||||
content, error = pandas.parse(non_existent_file)
|
||||
|
||||
# 验证返回 None 和错误信息
|
||||
assert content is None
|
||||
assert error is not None
|
||||
25
tests/test_readers/test_xls/test_unstructured_xls.py
Normal file
25
tests/test_readers/test_xls/test_unstructured_xls.py
Normal file
@@ -0,0 +1,25 @@
|
||||
"""测试 unstructured XLS Reader 的解析功能。"""
|
||||
|
||||
import pytest
|
||||
import os
|
||||
from readers.xls import unstructured
|
||||
|
||||
|
||||
class TestUnstructuredXlsReaderParse:
|
||||
"""测试 unstructured XLS Reader 的 parse 方法。"""
|
||||
|
||||
def test_module_importable(self):
|
||||
"""测试模块可以正确导入。"""
|
||||
assert unstructured is not None
|
||||
assert hasattr(unstructured, 'parse')
|
||||
assert callable(unstructured.parse)
|
||||
|
||||
def test_file_not_exists(self, tmp_path):
|
||||
"""测试文件不存在的情况。"""
|
||||
non_existent_file = str(tmp_path / "non_existent.xls")
|
||||
|
||||
content, error = unstructured.parse(non_existent_file)
|
||||
|
||||
# 验证返回 None 和错误信息
|
||||
assert content is None
|
||||
assert error is not None
|
||||
Reference in New Issue
Block a user