purrfectmeow.tc01_spl package

Submodules

purrfectmeow.tc01_spl.base module

class purrfectmeow.tc01_spl.base.Suphalak[source]

Bases: object

tmp_dir = '.cache/tmp'
DEFAULT_LOADER = 'PYMUPDF4LLM'
classmethod reading(file, file_name, loader=None, **kwargs)[source]
Parameters:
  • file (BinaryIO)

  • file_name (str)

  • loader (str | None)

  • kwargs (Any)

Return type:

str

purrfectmeow.tc01_spl.markdown module

class purrfectmeow.tc01_spl.markdown.Markdown[source]

Bases: object

classmethod markitdown_convert(file_path)[source]
Parameters:

file_path (str)

Return type:

str

classmethod docling_convert(file_path)[source]
Parameters:

file_path (str)

Return type:

str

classmethod pymupdf4llm_convert(file_path)[source]
Parameters:

file_path (str)

Return type:

str

purrfectmeow.tc01_spl.ocr module

class purrfectmeow.tc01_spl.ocr.Ocr[source]

Bases: object

classmethod pytesseract_convert(file_path)[source]
Parameters:

file_path (str)

Return type:

str

classmethod easyocr_convert(file_path)[source]
Parameters:

file_path (str)

Return type:

str

classmethod suryaocr_convert(file_path)[source]
Parameters:

file_path (str)

Return type:

str

classmethod doctr_convert(file_path)[source]
Parameters:

file_path (str)

Return type:

str

purrfectmeow.tc01_spl.simple module

class purrfectmeow.tc01_spl.simple.Simple[source]

Bases: object

classmethod encoding_convert(file_path)[source]
Parameters:

file_path (str)

Return type:

str

classmethod pymupdf_convert(file_path)[source]
Parameters:

file_path (str)

Return type:

str

classmethod pandas_convert(file_path)[source]
Parameters:

file_path (str)

Return type:

str

Module contents

class purrfectmeow.tc01_spl.Suphalak[source]

Bases: object

DEFAULT_LOADER = 'PYMUPDF4LLM'
classmethod reading(file, file_name, loader=None, **kwargs)[source]
Parameters:
  • file (BinaryIO)

  • file_name (str)

  • loader (str | None)

  • kwargs (Any)

Return type:

str

tmp_dir = '.cache/tmp'