sparkocr.transformers.readers.alab_readers#

Classes#

class AlabReaders#

dataLabeler(spark, jsonPath, imageFolderPath)#

static getPreparedDataItem(item, result, ind)#

static get_words(hocr)#

static isRectangleOverlap(R1, R2)#

jsonReader(spark, json_path='./sparkocr/resources/ocr/data/llmv2_Alab_data/result.json')#

class AlabReadersV1#

dataLabeler(spark, path, doc_type='pdf')#