refactor: 统一代码格式,调整多行代码换行风格
对多个文件进行代码格式化调整,将长行参数拆分为多行书写,提升代码可读性,包括: - 调整函数定义、调用的多行换行格式 - 优化列表、元组、字典的多行排版 - 新增README.md项目说明文档
This commit is contained in:
@@ -102,7 +102,9 @@ def _parse_pdf(content: bytes) -> str:
|
||||
if not settings.pdf_ocr_enabled:
|
||||
return ""
|
||||
|
||||
ocr_text = _ocr_pdf(content, max_pages=settings.pdf_ocr_max_pages, dpi=settings.pdf_ocr_dpi)
|
||||
ocr_text = _ocr_pdf(
|
||||
content, max_pages=settings.pdf_ocr_max_pages, dpi=settings.pdf_ocr_dpi
|
||||
)
|
||||
return ocr_text
|
||||
|
||||
|
||||
@@ -143,7 +145,9 @@ def _ocr_pdf(content: bytes, max_pages: int, dpi: int) -> str:
|
||||
result, _ = _ocr_engine(pil_image)
|
||||
if result:
|
||||
# result: [[box, text, score], ...],按行拼接
|
||||
lines = [item[1] for item in result if item and len(item) >= 2 and item[1]]
|
||||
lines = [
|
||||
item[1] for item in result if item and len(item) >= 2 and item[1]
|
||||
]
|
||||
if lines:
|
||||
page_texts.append("\n".join(lines))
|
||||
pdf.close()
|
||||
|
||||
Reference in New Issue
Block a user