feat: 统一文档解析器项目 - 迁移 lyxy-reader-office 和 lyxy-reader-html

## 功能特性

- 建立统一的项目结构,包含 core/、readers/、utils/、tests/ 模块
- 迁移 lyxy-reader-office 的所有解析器(docx、xlsx、pptx、pdf)
- 迁移 lyxy-reader-html 的所有解析器(html、url 下载)
- 统一 CLI 入口为 lyxy_document_reader.py
- 统一 Markdown 后处理逻辑
- 按文件类型组织 readers,每个解析器独立文件
- 依赖分组按文件类型细分(docx、xlsx、pptx、pdf、html、http)
- PDF OCR 解析器优先,无参数控制
- 使用 logging 模块替代简单 print
- 设计完整的单元测试结构
- 重写项目文档

## 新增目录/文件

- core/ - 核心模块(异常体系、Markdown 工具、解析调度器)
- readers/ - 格式阅读器(base.py + docx/xlsx/pptx/pdf/html)
- utils/ - 工具函数(文件类型检测)
- tests/ - 测试(conftest.py + test_core/ + test_readers/ + test_utils/)
- lyxy_document_reader.py - 统一 CLI 入口

## 依赖分组

- docx - DOCX 文档解析支持
- xlsx - XLSX 文档解析支持
- pptx - PPTX 文档解析支持
- pdf - PDF 文档解析支持(含 OCR)
- html - HTML/URL 解析支持
- http - HTTP/URL 下载支持
- office - Office 格式组合(docx/xlsx/pptx/pdf)
- web - Web 格式组合(html/http)
- full - 完整功能
- dev - 开发依赖
This commit is contained in:
2026-03-08 13:46:37 +08:00
parent eb8973495e
commit 833018d451
66 changed files with 4054 additions and 0 deletions

47
readers/pdf/__init__.py Normal file
View File

@@ -0,0 +1,47 @@
"""PDF 文件阅读器支持多种解析方法OCR 优先)。"""
from typing import List, Optional, Tuple
from readers.base import BaseReader
from utils import is_valid_pdf
from . import docling_ocr
from . import unstructured_ocr
from . import docling
from . import unstructured
from . import markitdown
from . import pypdf
PARSERS = [
("docling OCR", docling_ocr.parse),
("unstructured OCR", unstructured_ocr.parse),
("docling", docling.parse),
("unstructured", unstructured.parse),
("MarkItDown", markitdown.parse),
("pypdf", pypdf.parse),
]
class PdfReader(BaseReader):
"""PDF 文件阅读器"""
@property
def supported_extensions(self) -> List[str]:
return [".pdf"]
def supports(self, file_path: str) -> bool:
return is_valid_pdf(file_path)
def parse(self, file_path: str) -> Tuple[Optional[str], List[str]]:
failures = []
content = None
for parser_name, parser_func in PARSERS:
content, error = parser_func(file_path)
if content is not None:
return content, failures
else:
failures.append(f"- {parser_name}: {error}")
return None, failures

29
readers/pdf/docling.py Normal file
View File

@@ -0,0 +1,29 @@
"""使用 docling 库解析 PDF 文件(不启用 OCR"""
from typing import Optional, Tuple
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 docling 库解析 PDF 文件(不启用 OCR"""
try:
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
except ImportError:
return None, "docling 库未安装"
try:
converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_options=PdfPipelineOptions(do_ocr=False)
)
}
)
result = converter.convert(file_path)
markdown_content = result.document.export_to_markdown()
if not markdown_content.strip():
return None, "文档为空"
return markdown_content, None
except Exception as e:
return None, f"docling 解析失败: {str(e)}"

View File

@@ -0,0 +1,21 @@
"""使用 docling 库解析 PDF 文件(启用 OCR"""
from typing import Optional, Tuple
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 docling 库解析 PDF 文件(启用 OCR"""
try:
from docling.document_converter import DocumentConverter
except ImportError:
return None, "docling 库未安装"
try:
converter = DocumentConverter()
result = converter.convert(file_path)
markdown_content = result.document.export_to_markdown()
if not markdown_content.strip():
return None, "文档为空"
return markdown_content, None
except Exception as e:
return None, f"docling OCR 解析失败: {str(e)}"

10
readers/pdf/markitdown.py Normal file
View File

@@ -0,0 +1,10 @@
"""使用 MarkItDown 库解析 PDF 文件"""
from typing import Optional, Tuple
from core import parse_with_markitdown
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 MarkItDown 库解析 PDF 文件"""
return parse_with_markitdown(file_path)

28
readers/pdf/pypdf.py Normal file
View File

@@ -0,0 +1,28 @@
"""使用 pypdf 库解析 PDF 文件"""
from typing import Optional, Tuple
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 pypdf 库解析 PDF 文件"""
try:
from pypdf import PdfReader
except ImportError:
return None, "pypdf 库未安装"
try:
reader = PdfReader(file_path)
md_content = []
for page in reader.pages:
text = page.extract_text(extraction_mode="plain")
if text and text.strip():
md_content.append(text.strip())
md_content.append("")
content = "\n".join(md_content).strip()
if not content:
return None, "文档为空"
return content, None
except Exception as e:
return None, f"pypdf 解析失败: {str(e)}"

View File

@@ -0,0 +1,28 @@
"""使用 unstructured 库解析 PDF 文件fast 策略)"""
from typing import Optional, Tuple
from core import _unstructured_elements_to_markdown
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 unstructured 库解析 PDF 文件fast 策略)"""
try:
from unstructured.partition.pdf import partition_pdf
except ImportError:
return None, "unstructured 库未安装"
try:
elements = partition_pdf(
filename=file_path,
infer_table_structure=True,
strategy="fast",
languages=["chi_sim"],
)
# fast 策略不做版面分析Title 类型标注不可靠
content = _unstructured_elements_to_markdown(elements, trust_titles=False)
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)}"

View File

@@ -0,0 +1,34 @@
"""使用 unstructured 库解析 PDF 文件hi_res 策略 + PaddleOCR"""
from typing import Optional, Tuple
from core import _unstructured_elements_to_markdown
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 unstructured 库解析 PDF 文件hi_res 策略 + PaddleOCR"""
try:
from unstructured.partition.pdf import partition_pdf
except ImportError:
return None, "unstructured 库未安装"
try:
from unstructured.partition.utils.constants import OCR_AGENT_PADDLE
except ImportError:
return None, "unstructured-paddleocr 库未安装"
try:
elements = partition_pdf(
filename=file_path,
infer_table_structure=True,
strategy="hi_res",
languages=["chi_sim"],
ocr_agent=OCR_AGENT_PADDLE,
table_ocr_agent=OCR_AGENT_PADDLE,
)
content = _unstructured_elements_to_markdown(elements, trust_titles=True)
if not content.strip():
return None, "文档为空"
return content, None
except Exception as e:
return None, f"unstructured OCR 解析失败: {str(e)}"