j= hdZddlZddlmZddlmZeGddZeZdS)a This module contains variables that can permitted to be tweaked by the system environment. For example, model parameters that changes the output of an inference call. Constants do NOT belong in this module. Constants are values that are usually names for common options (e.g., color names) or settings that should not be altered without making a code change (e.g., definition of 1Gb of memory in bytes). Constants should go into `./constants.py` N) dataclass)OCR_AGENT_TESSERACTceZdZdZddededefdZdededefdZdededefdZ e defd Z e defd Z e defd Z e defd Ze defd Ze defdZe defdZdS) ENVConfigz+class for configuring enviorment parametersvar default_valuereturncBtj||S)zhattempt to get the value of var from the os environment; if not present return the default_value)osenvironget)selfrr s m/lsinfo/ai/hellotax_ai/base_platform/venv/lib/python3.11/site-packages/unstructured/partition/utils/config.py _get_stringzENVConfig._get_stringsz~~c=111cR||x}rt|S|SN)rintrrr values r_get_intzENVConfig._get_ints/$$S)) )5 u:: rcR||x}rt|S|Sr)rfloatrs r _get_floatzENVConfig._get_floats/$$S)) )5 << rc.|ddS)zRextra image content to add around an identified element region; measured in pixelsIMAGE_CROP_PADrrrs rrzENVConfig.IMAGE_CROP_PAD!s}}-q111rc.|ddS)zextra image content to add around an identified table region; measured in pixels The padding adds image data around an identified table bounding box for downstream table structure detection model use as input TABLE_IMAGE_CROP_PADrrrs rr!zENVConfig.TABLE_IMAGE_CROP_PAD&s}}3Q777rc.|ddS)z%the quantile to check for text heightTESSERACT_TEXT_HEIGHT_QUANTILEg?)rrs rr#z(ENVConfig.TESSERACT_TEXT_HEIGHT_QUANTILE/s?EEErc.|ddS)zminimum text height acceptable from tesseract OCR results if estimated text height from tesseract OCR results is lower than this value the image is scaled up to be processed again TESSERACT_MIN_TEXT_HEIGHT rrs rr%z#ENVConfig.TESSERACT_MIN_TEXT_HEIGHT4s}}8"===rc.|ddS)zmaximum text height acceptable from tesseract OCR results if estimated text height from tesseract OCR results is higher than this value the image is scaled down to be processed again TESSERACT_MAX_TEXT_HEIGHTdrrs rr(z#ENVConfig.TESSERACT_MAX_TEXT_HEIGHT=s}}8#>>>rc.|ddS)z%optimum text height for tesseract OCRTESSERACT_OPTIMUM_TEXT_HEIGHTrrs rr+z'ENVConfig.TESSERACT_OPTIMUM_TEXT_HEIGHTFs}}3>>>X>?3???X?BsBBBXBB3BBBXBBBrr)r2r dataclassesr&unstructured.partition.utils.constantsrr env_configr5rrr9s !!!!!!FFFFFF ABABABABABABAB ABHY[[ r