magic-pdf 1.2.1__py3-none-any.whl → 1.3.0__py3-none-any.whl

magic_pdf-1.3.0.dist-info/RECORD

@@ -0,0 +1,202 @@
+magic_pdf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/pdf_parse_union_core_v2.py,sha256=qRLsYctJxthgo2zv56WDV8dU8dmaykRdsHOFiBcDoKM,40385
+magic_pdf/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/config/constants.py,sha256=fXGzANULnJWLPxwYp3BEFWx-rnorzpySMx63ffyEyq4,1272
+magic_pdf/config/drop_reason.py,sha256=CqjMzBE96Qo8OeFvhhhItY8WhyqsKhE3DmyJLoQZNCc,2248
+magic_pdf/config/drop_tag.py,sha256=CjveyzhAsHm_bfXB7ZZNKruw1NR-WdKD8Hz6OhQdG0A,680
+magic_pdf/config/enums.py,sha256=CImYuw4sbKpq9zrj6zrrEvtdoGkjxDt8S8ByNVDpypU,89
+magic_pdf/config/exceptions.py,sha256=2tsJxYUebVeimyYBGQkc9Nd1kIakTmWmz3SDcfJWy54,784
+magic_pdf/config/make_content_config.py,sha256=J2eJIhVHBPGwX18zVQomQUOxs8LcfeGLxLgdBEeRvLg,248
+magic_pdf/config/model_block_type.py,sha256=y5ie2ZLvo-h8OdVk8HOEha6qK0OJFtLmtOhYjrV680g,166
+magic_pdf/config/ocr_content_type.py,sha256=e_7RBTdShaWvWhMO2SFou7GM521elMH_Jtn5usbHWdY,890
+magic_pdf/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/data/batch_build_dataset.py,sha256=rS4f50hBc7IvSqa_Gd84E_tSYpQ66BMaeZkCPd5Ajxw,4601
+magic_pdf/data/dataset.py,sha256=pSz2Ukj9-bEKyg06Wsl9jBhCWeX_0moBtaKujQuYwqI,11830
+magic_pdf/data/read_api.py,sha256=_faBnYE3iU_EiQLNFjVM6a8IQtOGAcSQNYBZsTSN1d8,5225
+magic_pdf/data/schemas.py,sha256=oIUTBzK8Wq8Wuy8A_uilWAbVhucRvOs9_f3lSKYgcmQ,664
+magic_pdf/data/utils.py,sha256=dNWIJECPXaakKocI4z5Tq6vhDDSnR-bVWQV7DO2w_A8,5335
+magic_pdf/data/data_reader_writer/__init__.py,sha256=QtevUaeSivv9dQKi3Tomfn4Z0E4To0cB8qXTnglxaHc,705
+magic_pdf/data/data_reader_writer/base.py,sha256=nqmAcdHOXMOJO6RAT3ILligDFaw8Op0STyCw5yOzAbI,1706
+magic_pdf/data/data_reader_writer/filebase.py,sha256=VbNAxLyo0Io0j7iprJERt_TqxzHAtA7cUyPIaJstToU,2146
+magic_pdf/data/data_reader_writer/multi_bucket_s3.py,sha256=4pEJ8PPd3nX7sccHobCs0mbDM8BiqDP_sAEz7CIvpNI,5938
+magic_pdf/data/data_reader_writer/s3.py,sha256=9Oy1cNuXMwG1e8PgZ7AR-pn_MqHAhkgAGnyEZCYoYAA,2408
+magic_pdf/data/io/__init__.py,sha256=WKaIlu8i5AWYxFCGNJcorAfMnlUQDOF8CX07Ycfnu2c,294
+magic_pdf/data/io/base.py,sha256=SqNQqe30ZvoVvg7GVv-hLMCjN6yBgDyQQWeLgGsTfhQ,1118
+magic_pdf/data/io/http.py,sha256=XlKB0DNf4a_uUnfgcclvaaOtmE7lmddx0DnK8A-emAM,958
+magic_pdf/data/io/s3.py,sha256=hyA7sbNriQy64xd_uyJ7acN_oneQ1Pdmoc7_xcvkue8,3606
+magic_pdf/dict2md/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/dict2md/ocr_mkcontent.py,sha256=U4DqKfD4dJ2S5Z8NEAGhuLYkEOIeC-BWuArMbwi7BJs,13784
+magic_pdf/filter/__init__.py,sha256=_7lSez_myu4b6cdzPpQ-NfREuqeBSq_QdyBPKVLyq2U,1505
+magic_pdf/filter/pdf_classify_by_type.py,sha256=YNYXamxYgEiSujwilCNHOtrwpgJGDiQ597qJfardDVc,42354
+magic_pdf/filter/pdf_meta_scan.py,sha256=eOuM0-JgaXvHolSgepGoNDJDmv_uITWLQpH_0MfnVQw,17478
+magic_pdf/integrations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/integrations/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/integrations/rag/api.py,sha256=t38wvIBzLje4_JzTP3dewMLqV-tQJ-A3B92Sj2oyrfs,2507
+magic_pdf/integrations/rag/type.py,sha256=Z_1g_ZIOCsb7-FmZBudReIXj8nzGrgj_BygCalhJdmk,3193
+magic_pdf/integrations/rag/utils.py,sha256=DCb-UhC8TElb6Eq7_6NmmETreKEk5DVE18hNL8sTEBk,11762
+magic_pdf/libs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/libs/boxbase.py,sha256=DKZXhwpJd-HE2_Du7NmkeeYW5gG-iwX3GeSWL7rYGv0,16956
+magic_pdf/libs/clean_memory.py,sha256=OsQexCjmBO2i-Hv-0uYQfn72dbUWR8sTW81nG2zlNQQ,479
+magic_pdf/libs/commons.py,sha256=xD0fGA16KNB5rhbl4zRrOqdrNHYwaRablT_s9W2ZTbw,1174
+magic_pdf/libs/config_reader.py,sha256=9GXK7jtDyA_jxXKWZAQ69rB02v5UW4mOmo1IaOYOkW0,4374
+magic_pdf/libs/convert_utils.py,sha256=Ov-lsfCLBPz_15iSJXIslBNmrSf_E_1g_XDWJy8NgO8,143
+magic_pdf/libs/coordinate_transform.py,sha256=Bbop2cP2uz2ZG0U0gwd7J6EKkgABq5Rv03qf2LMPw80,429
+magic_pdf/libs/draw_bbox.py,sha256=hpUmpPiQVu7UgWQa3M49dS22G6A9gcG2jpq4dQjTjzA,18331
+magic_pdf/libs/hash_utils.py,sha256=VEKK9WfFoZgrPfi8kfITjLpr8Ahufs8tXh9R1Y5lAL8,404
+magic_pdf/libs/json_compressor.py,sha256=6-KCu0lb5ksmyqWtQGb4QqmP-FjRb5dP7P-Hevcn68g,875
+magic_pdf/libs/language.py,sha256=7RT3mxSa7jdpoC5ySd7ZddHA7TO7UsnmDOWiYZAxuyg,1433
+magic_pdf/libs/local_math.py,sha256=tqljQOgqh3fZc146HYhO88JXJaiXMVwArBkk_CSGICc,177
+magic_pdf/libs/markdown_utils.py,sha256=86v2BmsSV4NkoRZrH4uQD1youJhYFF3vIKr_vDeg3z0,270
+magic_pdf/libs/path_utils.py,sha256=Hykw_l5CU736b2egHV9P7B-qh3QNKO4nZSGCbsi0Z8E,1043
+magic_pdf/libs/pdf_check.py,sha256=7GWWvDR6g_rj_fE6XJlbTq5AFVX11ngRIzT0N18F214,3396
+magic_pdf/libs/pdf_image_tools.py,sha256=_au7plmKKctpPKozBumSKgP8689q4vH1mU8VMLO0IbM,2260
+magic_pdf/libs/performance_stats.py,sha256=DW-c6nUTUnWKGTONRKfpucsYZm1ake016F9K7jJwbik,2136
+magic_pdf/libs/safe_filename.py,sha256=ckwcM_eqoysTb5id8czp-tXq2G9da0-l3pshZDCHQtE,236
+magic_pdf/libs/version.py,sha256=F5mW07pSyGrqDNY2Ehr-UpDzpBtN-FsYU0QGZWf6PJE,22
+magic_pdf/model/__init__.py,sha256=sa-dO2k-TLy25I2gRrzjm_cQeYfzMf-pLwBJHkIxGo0,51
+magic_pdf/model/batch_analyze.py,sha256=iE8WzD13edqyPcqarKJfgUxPxudXGNRck_FDtsPGYdg,11212
+magic_pdf/model/doc_analyze_by_custom_model.py,sha256=cnfjCv9fTGYOgjyRBVQWHc57qbbK7PsoLKFLEQhIcho,10057
+magic_pdf/model/magic_model.py,sha256=yZKWo_wRck_-YLyFGRiUHGar8sV1Y6458BFLbyBAt74,30682
+magic_pdf/model/model_list.py,sha256=aqfEJlEfbib3D3ISrxc0Coh6SbffYh8Yq2FlQN35_zA,213
+magic_pdf/model/pdf_extract_kit.py,sha256=C3sKqRkoD20Ldmo-cqGn1zRldEL-l5NYqcFvd05_fGU,10845
+magic_pdf/model/pp_structure_v2.py,sha256=NcqFWL4nUtjl82MFak8HX_8V3i4Aw_fK4dATrIp5uGs,3840
+magic_pdf/model/sub_modules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/model_init.py,sha256=e2t95kxiuU47luOHByDokbQ2uob6oQhEA4b6UGVfMjY,8303
+magic_pdf/model/sub_modules/model_utils.py,sha256=f8ceLYSHsNkTaAVUokYhAgsaW7hpQa8KwLseMXuKTF4,2638
+magic_pdf/model/sub_modules/language_detection/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
+magic_pdf/model/sub_modules/language_detection/utils.py,sha256=Q__v6DdNJztt8GhVSuSB0txahVq-aj8RLhWn2VScx4w,3047
+magic_pdf/model/sub_modules/language_detection/yolov11/YOLOv11.py,sha256=7T8eFl8zlZe6F0j0jSB3jrwOapDft320JQ1fuWxpvAY,5230
+magic_pdf/model/sub_modules/language_detection/yolov11/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
+magic_pdf/model/sub_modules/layout/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/layout/doclayout_yolo/DocLayoutYOLO.py,sha256=c-OmqY9DOgkIWqiDrNGe0-E5RS6-diwnPPsN5pbPw-s,2346
+magic_pdf/model/sub_modules/layout/doclayout_yolo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/layout/layoutlmv3/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/layout/layoutlmv3/backbone.py,sha256=1cvSCczgvwOLdvzWyqttoYPMHsXmnzI3w9abJ1bAXoM,7106
+magic_pdf/model/sub_modules/layout/layoutlmv3/beit.py,sha256=e-INve6bpEx_0FM5wYbQcEcelc79tzDlCljTVHaGt1w,30450
+magic_pdf/model/sub_modules/layout/layoutlmv3/deit.py,sha256=Qyn5UWutZ-0GJczexCh-oMMSXtav_g3ovumMFJp8Om4,17000
+magic_pdf/model/sub_modules/layout/layoutlmv3/model_init.py,sha256=PhWqqRwgSSmXTaUlLIjGqnBUNjzxwYDKgMzKjnxNy1k,4528
+magic_pdf/model/sub_modules/layout/layoutlmv3/rcnn_vl.py,sha256=nI4G6AeLRmjavNhs5S2USKh0ozn-ftMuW0F0m_eVy3c,6649
+magic_pdf/model/sub_modules/layout/layoutlmv3/visualizer.py,sha256=H6UYeCCbaN2gbDjGthTkKkPoyWxfE3azRjsR7fVBwnw,49797
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/__init__.py,sha256=C4N9gXJr7is7uznvQefQ7dOhlzEhdp86Lgh-7p0Y-08,186
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/data/__init__.py,sha256=W7V62JOh12NdMZj2H1sde3Il0AqW2VKplmHEsLle6tg,76
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/data/cord.py,sha256=jR_lRZxy8SeEvTK3FdlXmQHF0kefJf7ZqwM_8pvyI5E,8153
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/data/data_collator.py,sha256=M2TE47BprHSuQJYcoMeWOSpqkr_nh8VK6t2l26XWmxg,6279
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/data/funsd.py,sha256=Ez9tMeruHncJlkKQ7iRGBB9Pk1uWtgxlGeqs-sOmIG0,5214
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/data/image_utils.py,sha256=vuNOMzYw_h7jmaD2XUqkGlrjDEPB7XUts16GRICBmG4,10334
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/data/xfund.py,sha256=6jLKyc_4VhbHY4YEzBXm5RkPdsd9ldnUGXFZBLiJ-_s,8270
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/models/__init__.py,sha256=d5bm3Rx-jTrgfJDWrzD7t5R5CdHfug9dCNvUEneIYW4,190
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/models/layoutlmv3/__init__.py,sha256=a04w_C0B4P9jF-3I_tXCj3fLmfFQR5XSKGbhgGm--pM,1216
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/models/layoutlmv3/configuration_layoutlmv3.py,sha256=CJBcAmmLeRFVMN1YjWefoUW7hk0KXek0Eb_tergKl4Y,2150
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/models/layoutlmv3/modeling_layoutlmv3.py,sha256=mdo8tO-DrJcv0Lbk9Pp98n3NQXYOnFFyXQWjU7t35kA,54633
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3.py,sha256=diKlrfxYjKAmYrUgjYdx-FXLh-swShC3tl-EBX1b3oI,1197
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3_fast.py,sha256=0lxiG69_fGpSSBYA9CBLnDa_qqa1rInZ0pJpqBwZ0Yw,1372
+magic_pdf/model/sub_modules/mfd/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/mfd/yolov8/YOLOv8.py,sha256=Wm6jh70l_q_P_LQxa_pmLbg9OnHZyEKF1Dfln7Y2c8w,1114
+magic_pdf/model/sub_modules/mfd/yolov8/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/mfr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/mfr/unimernet/Unimernet.py,sha256=hq48TP1Ac8Y4FlK7GamnU-WZTQfdZotxBKuFhOIjrcM,5349
+magic_pdf/model/sub_modules/mfr/unimernet/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/__init__.py,sha256=kHcISG8GS4TWJW34SCJCei1jxo6HxvO00aC0dqyNFgI,413
+magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/modeling_unimernet.py,sha256=F_rwlFytWOwOntNhhZoUqFAyXgzvq_HVjKyBizwlnjo,7913
+magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/unimer_mbart/__init__.py,sha256=9T2rBpyGX5YFQYj89-mWujRokOuz4xgNreBuegcg1_c,228
+magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/unimer_mbart/configuration_unimer_mbart.py,sha256=hwRar3pqN_cVs3TRTNSuhB4wacBncfJ-qvaTajRb0xc,7934
+magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/unimer_mbart/modeling_unimer_mbart.py,sha256=Y5nwqDRzSb8zAbY1U0HGJGVtFggJW1zATP8RdnasNcA,113605
+magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/unimer_mbart/tokenization_unimer_mbart.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/unimer_swin/__init__.py,sha256=8_1DKwDCDUBkeHYiJJ6MZnodZBsatHbqhygh11s9eEA,267
+magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/unimer_swin/configuration_unimer_swin.py,sha256=OX3eRUKBnKCXtxJOG3sdNoB1IV-Z7efgWU-gaclYOGA,5780
+magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/unimer_swin/image_processing_unimer_swin.py,sha256=tlcCxOJVRus_35lCz4faMVZ8ulAjGxK5Yu9Y_IeHsDY,4406
+magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/unimer_swin/modeling_unimer_swin.py,sha256=Q_fdmFHUBtEoAfWp9aowdwTCE2MIFMOPbYjoSyXK2iU,48929
+magic_pdf/model/sub_modules/ocr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/ocr_utils.py,sha256=3qxu0lAjqzZQ2Ci-C_wz_YSakyq_5-KnckA3-5bICTM,12589
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorch_paddle.py,sha256=FaPo02L1IJKybGYfydsohOiHstJIL8d5UKzGck2tYvk,7283
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/base_ocr_v20.py,sha256=5bI7MAu65r-vn28krwdJ6pjZMkEvWjspE7EQaTsRERw,1319
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/data/__init__.py,sha256=YYu3c-W4fgEErxxDM98uQ3oWwPEh-6w75LY4zcj4VtM,199
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/data/imaug/__init__.py,sha256=c4H0gXPRweQ0wMFnkrCLTR6MrtG-e4kUinxwq2G1V9U,1480
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/data/imaug/operators.py,sha256=uwS8t-6hVIBag3jJd3yiBM4DW_dEiynp22_WFmVppjA,14205
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/common.py,sha256=3r2jTvPYQS4IgTvIqR4l6bBVwR7jn-87rSmpv3tlqxI,2294
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/architectures/__init__.py,sha256=DCA9FS4mE5oCHDlBhUrkYLdxFeQIbhPj4P8oJ_gRZD8,832
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/architectures/base_model.py,sha256=RhV2Dm-os08kCFylT57zRu72Hq_RJdFy3xQe1MPaCuU,3588
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/__init__.py,sha256=TOLvLNeJhnAOus0D5jAq2TM67vLrtbzYlThTOhc-idc,1960
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/det_mobilenet_v3.py,sha256=r0gWnA1Xmt0Zw4FQLx7kf-WWwZd_26PfNzhM05drcuE,8334
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/rec_hgnet.py,sha256=UsIbzqN_koyGoSh1TA9r27SggpHbeKS3HmmS-A2Aw04,8341
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/rec_lcnetv3.py,sha256=3PNQG9B1cHe1hAg0NhcFR8p87rZnmH0jTBcfid-ZnKQ,15995
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/rec_mobilenet_v3.py,sha256=mJmE6xGpjHZH2Vaw16LlIlqRFFm9R9yRsSJEa3Yn3nw,4822
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/rec_mv1_enhance.py,sha256=K4p9KFYNmltV3y3QsxHIASNxoqlGtxgAoCxeFofyCmw,6726
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/backbones/rec_svtrnet.py,sha256=AIaUZ3IWBkRz2pWmanBjS0QdJcYnimMSV4MWofNpQcg,20222
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/heads/__init__.py,sha256=7vl3hyn6Ug_DNtqdfUL1Hz9scA_ptch2FCDzNddpQgU,1282
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/heads/cls_head.py,sha256=puIy5GlUtAKer6eS4HWKu07PzRd-HlDAqIz5WqjBHaA,596
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/heads/det_db_head.py,sha256=-k8bpuGQw_xIVDsumrfimOxg0O-oP2MOAyDJTjU70Ro,3633
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/heads/rec_ctc_head.py,sha256=ywyk5RJgUITdXvrUZk2yBSWKsaZIqnTofdFbuQUtwjU,1311
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/heads/rec_multi_head.py,sha256=K40SMA8tAVWu-3fwgfh3jGWeVFAdVnMyHjeZeI9OO7Q,2016
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/necks/__init__.py,sha256=634L1y-QWv5P8opNiSmKvQEx3Uskc20RG8DYiCdbl8U,1030
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/necks/db_fpn.py,sha256=TLF2pSyvRC0oPzL0eVyNlg3W6Zvfr4J8fD1nziVB7uI,14146
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/necks/intracl.py,sha256=w2QdwdI9BpiW92VS4mqL31sVERIbY53TfbD5Q6okiaY,3410
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/necks/rnn.py,sha256=olZwnKQexVlMx0gJi0FVYAm38TxNn5BM6F-OrdHKEgk,7019
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/postprocess/__init__.py,sha256=iC1Ol6CTxRWZBUyQ_5IVMR6kIurv9WJPOWWo7NAuZBA,1183
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/postprocess/cls_postprocess.py,sha256=1VVWXT_b1vhGb7PGvqyfUQ3Ip7LupH62vPva98GtjTA,685
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/postprocess/db_postprocess.py,sha256=EAc-cmhXtxLfFA6h5C871hIcDfXsjPDISiVCKwxh-qM,6339
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/postprocess/rec_postprocess.py,sha256=HiHNr4bhW5U1j4pYoyi8fPOaFsn8TUc4nSB6q8chfV4,26899
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/arch_config.yaml,sha256=eEzg5D5L3MHFL4H02gZnxdDiqtSCUzZDnt5pqDAmgCI,6980
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/models_config.yml,sha256=GOtAGMAretviqDXak409PPav7qHYMDBwSs9wxlSANRA,1388
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/arabic_dict.txt,sha256=xbaXD14RWk0Vpc7fAHpephuszp1j-Qi3IWC4VrFKu70,407
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/chinese_cht_dict.txt,sha256=gyVR_uHy-8l1CHctgevcjboSwA3pejXHHJ3fQ92sGoM,33443
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/cyrillic_dict.txt,sha256=NpqCxsjEeXhKXXJkSLg7Hq-1_vCkEppeqjkpYl3c0TI,410
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/devanagari_dict.txt,sha256=tfG-bYu_8aGfuWxdTKlqQjOAI0u30s4OB7WDittNGOo,508
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/en_dict.txt,sha256=VmLfnS0D8OjKDTsGSdasurkEtqFLPTUhRjxxw3xmjOM,190
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/japan_dict.txt,sha256=Hc_LQe7JBXapRbMITyKt4RztUG4k8Uh5JFsHFpjzCOg,17332
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/ka_dict.txt,sha256=-tP3ZZQyde7CE0pvvJtSeFQmZBEE1OfbOhWdxz80Hd4,452
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/korean_dict.txt,sha256=qh_ciuj3zUCg7E7bRy6wQh4RQn5sz-6ZFUQHQsGLCiA,14480
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/latin_dict.txt,sha256=jm1ONil4jDXDH35TAofWFHtUm7eiZb1nCLsoETRCniw,468
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/ppocr_keys_v1.txt,sha256=KLI2KtSrLcOHaapy_rU146nds_0qdYWgWSDmOTsdx_c,26249
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/ta_dict.txt,sha256=6T5pSBSv2f8ekYtvS7Qmf7TGWpNE7l10ZPkTW5DAonA,352
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/dict/te_dict.txt,sha256=7plGpg13AZd0dOiYg2lKTKIOqjhoojM0v3lA3NAI8Pk,429
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/tools/__init__.py,sha256=xEqR65Z8YOzOLorLjK0LCHos2zX-tCuxSrxndjU00hE,49
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/tools/infer/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/tools/infer/predict_cls.py,sha256=8RmKl1vejnZl65caHZNV2ta6hMsg5B_LE-FuqCO8T8A,4225
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/tools/infer/predict_det.py,sha256=cRBKE0blzryj3Ar6yM0FKKgxmZdgMc44NDNl1S2wiRs,9136
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/tools/infer/predict_rec.py,sha256=_fLTWjEmDZwXC-zzPT37PHO-nNlEvafemo2CyPJS7_w,19216
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/tools/infer/predict_system.py,sha256=hkegkn6hq2v2zqHVAP615-k-fkTS8swRYSbZeoqmSI8,3822
+magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/tools/infer/pytorchocr_utility.py,sha256=i1PFN-_kefJUUZ4Vk7igs1TU8gfErTDlDXY6-8Uaurw,9323
+magic_pdf/model/sub_modules/reading_oreder/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/reading_oreder/layoutreader/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/reading_oreder/layoutreader/helpers.py,sha256=IVUFcNMDF3-kio-BIxjppHnWS3eHPqvvNihIw2fbIFM,4372
+magic_pdf/model/sub_modules/reading_oreder/layoutreader/xycut.py,sha256=ezNSq_Y4UXiztB58hbXJsjTJlOBqWIjuW5A2uLSaZSo,7349
+magic_pdf/model/sub_modules/table/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/table/table_utils.py,sha256=B9BC4f5EEjlt2ldYxrIC8Wic2Tz3t3gTJeEyK3ggrOU,282
+magic_pdf/model/sub_modules/table/rapidtable/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/table/rapidtable/rapid_table.py,sha256=Vh1rWxj6t9PrXw7yhTNdJvTHy2wSVITTbGG2fD0dOZg,2515
+magic_pdf/operators/__init__.py,sha256=liU2-WYUvsQ1G4PYBppyvokS9z5IjrnlVMtoBAC1REI,2630
+magic_pdf/operators/models.py,sha256=mRqbCVrxxaUVDpEBAsXaK7EL1M-goICkE1W0FYgewio,5305
+magic_pdf/operators/pipes.py,sha256=XgBgisKQd_ruW-3Tw4v5LhqloZUHgn2aFcpi_q8LbCs,6767
+magic_pdf/post_proc/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
+magic_pdf/post_proc/llm_aided.py,sha256=yzhu2cCpUZjdwf3v0swYDgSs9VWIfMAoXepYIP1EMZs,6367
+magic_pdf/post_proc/para_split_v3.py,sha256=SPN_VVGvFX5KpFMGw9OzgoE-kTZq-FF036i0cIImGH8,16975
+magic_pdf/pre_proc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/pre_proc/construct_page_dict.py,sha256=OFmq5XRKi6fYIo-lmGlL-NB16Sf0egzsfEx-fT2uYrc,660
+magic_pdf/pre_proc/cut_image.py,sha256=NDzbxwD7z7Tb4uAxL4KR6LzURFdN1Tzr4nPvj-VmEqc,1225
+magic_pdf/pre_proc/ocr_detect_all_bboxes.py,sha256=nt88ttXCEI_1ihAF7HU15SQjwM69V-iJmk-L_nyzA6o,9328
+magic_pdf/pre_proc/ocr_dict_merge.py,sha256=PscKGF0uJIjMxZRM69FLUs1SZO_wOswDQQV1f0M2xAo,5627
+magic_pdf/pre_proc/ocr_span_list_modify.py,sha256=bs5RLvk4kIyx9_Hqq0FU3AGPPxE8Sxs97Uwlf1sBryM,4725
+magic_pdf/pre_proc/remove_bbox_overlap.py,sha256=mcdxAh4P56NZ3Ij8h3vW8qC_SrszfXflVWuWUuUiTNg,3089
+magic_pdf/resources/fasttext-langdetect/lid.176.ftz,sha256=jzRyz-hzintgmejpmcPL-uDc0VaWqsfXc4qAOdtgPoM,938013
+magic_pdf/resources/model_config/model_configs.yaml,sha256=SoyoDmXYQX4ltKclG6ZcpdSA8dX5auSgILBvaA0wPkg,325
+magic_pdf/resources/yolov11-langdetect/yolo_v11_ft.pt,sha256=dV4lcudF8wimEbAooYbvISvFhrXjp9i0rMRqv9VW6hY,3204667
+magic_pdf/spark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/spark/spark_api.py,sha256=BYO6zlRW0cEnIUB3ZzNQTu_LsPHEVitqiUN7gy3x_wo,1124
+magic_pdf/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/tools/cli.py,sha256=_oa-M5Hcopa5RZudVzrEip2W8pa9422Lmat7tMBJO5M,5171
+magic_pdf/tools/cli_dev.py,sha256=3RbubfTIagWoFYdu8wSDanr-BJDjFGeDet55jTy7He0,3948
+magic_pdf/tools/common.py,sha256=LoUz6Y36_U2odZqzBNKXngFNa6plf01U7_5jlDAFXaQ,12313
+magic_pdf/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/utils/annotations.py,sha256=82ou3uELNbQWa9hOFFkVt0gsIskAKf5msCv5J2IJ5V0,211
+magic_pdf/utils/office_to_pdf.py,sha256=7aj-Ls2v8saD-Rgu_t3FIc-J3Ka9wnmiEH5zY-H1Vxs,729
+magic_pdf-1.3.0.dist-info/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
+magic_pdf-1.3.0.dist-info/METADATA,sha256=Z4WBVqCxPlHu7TC2pLGhrCfVpp0Im11NBZNowFQsMyM,41909
+magic_pdf-1.3.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+magic_pdf-1.3.0.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
+magic_pdf-1.3.0.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
+magic_pdf-1.3.0.dist-info/RECORD,,

magic_pdf/model/sub_modules/ocr/paddleocr/ppocr_273_mod.py

@@ -1,204 +0,0 @@
-import copy
-import platform
-import time
-import cv2
-import numpy as np
-import torch
-
-from paddleocr import PaddleOCR
-from ppocr.utils.logging import get_logger
-from ppocr.utils.utility import alpha_to_color, binarize_img
-from tools.infer.predict_system import sorted_boxes
-from tools.infer.utility import get_rotate_crop_image, get_minarea_rect_crop
-
-from magic_pdf.model.sub_modules.ocr.paddleocr.ocr_utils import update_det_boxes, merge_det_boxes, check_img, \
-    ONNXModelSingleton
-
-logger = get_logger()
-
-
-class ModifiedPaddleOCR(PaddleOCR):
-    def __init__(self, *args, **kwargs):
-
-        super().__init__(*args, **kwargs)
-        self.lang = kwargs.get('lang', 'ch')
-        # 在cpu架构为arm且不支持cuda时调用onnx、
-        if not torch.cuda.is_available() and platform.machine() in ['arm64', 'aarch64']:
-            self.use_onnx = True
-            onnx_model_manager = ONNXModelSingleton()
-            self.additional_ocr = onnx_model_manager.get_onnx_model(**kwargs)
-        else:
-            self.use_onnx = False
-
-    def ocr(self,
-            img,
-            det=True,
-            rec=True,
-            cls=True,
-            bin=False,
-            inv=False,
-            alpha_color=(255, 255, 255),
-            mfd_res=None,
-            ):
-        """
-        OCR with PaddleOCR
-        args：
-            img: img for OCR, support ndarray, img_path and list or ndarray
-            det: use text detection or not. If False, only rec will be exec. Default is True
-            rec: use text recognition or not. If False, only det will be exec. Default is True
-            cls: use angle classifier or not. Default is True. If True, the text with rotation of 180 degrees can be recognized. If no text is rotated by 180 degrees, use cls=False to get better performance. Text with rotation of 90 or 270 degrees can be recognized even if cls=False.
-            bin: binarize image to black and white. Default is False.
-            inv: invert image colors. Default is False.
-            alpha_color: set RGB color Tuple for transparent parts replacement. Default is pure white.
-        """
-        assert isinstance(img, (np.ndarray, list, str, bytes))
-        if isinstance(img, list) and det == True:
-            logger.error('When input a list of images, det must be false')
-            exit(0)
-        if cls == True and self.use_angle_cls == False:
-            pass
-            # logger.warning(
-            #     'Since the angle classifier is not initialized, it will not be used during the forward process'
-            # )
-
-        img = check_img(img)
-        # for infer pdf file
-        if isinstance(img, list):
-            if self.page_num > len(img) or self.page_num == 0:
-                self.page_num = len(img)
-            imgs = img[:self.page_num]
-        else:
-            imgs = [img]
-
-        def preprocess_image(_image):
-            _image = alpha_to_color(_image, alpha_color)
-            if inv:
-                _image = cv2.bitwise_not(_image)
-            if bin:
-                _image = binarize_img(_image)
-            return _image
-
-        if det and rec:
-            ocr_res = []
-            for img in imgs:
-                img = preprocess_image(img)
-                dt_boxes, rec_res, _ = self.__call__(img, cls, mfd_res=mfd_res)
-                if not dt_boxes and not rec_res:
-                    ocr_res.append(None)
-                    continue
-                tmp_res = [[box.tolist(), res]
-                           for box, res in zip(dt_boxes, rec_res)]
-                ocr_res.append(tmp_res)
-            return ocr_res
-        elif det and not rec:
-            ocr_res = []
-            for img in imgs:
-                img = preprocess_image(img)
-                if self.lang in ['ch'] and self.use_onnx:
-                    dt_boxes, elapse = self.additional_ocr.text_detector(img)
-                else:
-                    dt_boxes, elapse = self.text_detector(img)
-                if dt_boxes is None:
-                    ocr_res.append(None)
-                    continue
-                dt_boxes = sorted_boxes(dt_boxes)
-                # merge_det_boxes 和 update_det_boxes 都会把poly转成bbox再转回poly，因此需要过滤所有倾斜程度较大的文本框
-                dt_boxes = merge_det_boxes(dt_boxes)
-                if mfd_res:
-                    bef = time.time()
-                    dt_boxes = update_det_boxes(dt_boxes, mfd_res)
-                    aft = time.time()
-                    logger.debug("split text box by formula, new dt_boxes num : {}, elapsed : {}".format(
-                        len(dt_boxes), aft - bef))
-                tmp_res = [box.tolist() for box in dt_boxes]
-                ocr_res.append(tmp_res)
-            return ocr_res
-        else:
-            ocr_res = []
-            cls_res = []
-            for img in imgs:
-                if not isinstance(img, list):
-                    img = preprocess_image(img)
-                    img = [img]
-                if self.use_angle_cls and cls:
-                    img, cls_res_tmp, elapse = self.text_classifier(img)
-                    if not rec:
-                        cls_res.append(cls_res_tmp)
-                if self.lang in ['ch'] and self.use_onnx:
-                    rec_res, elapse = self.additional_ocr.text_recognizer(img)
-                else:
-                    rec_res, elapse = self.text_recognizer(img)
-                ocr_res.append(rec_res)
-            if not rec:
-                return cls_res
-            return ocr_res
-
-    def __call__(self, img, cls=True, mfd_res=None):
-        time_dict = {'det': 0, 'rec': 0, 'cls': 0, 'all': 0}
-
-        if img is None:
-            logger.debug("no valid image provided")
-            return None, None, time_dict
-
-        start = time.time()
-        ori_im = img.copy()
-        if self.lang in ['ch'] and self.use_onnx:
-            dt_boxes, elapse = self.additional_ocr.text_detector(img)
-        else:
-            dt_boxes, elapse = self.text_detector(img)
-        time_dict['det'] = elapse
-
-        if dt_boxes is None:
-            logger.debug("no dt_boxes found, elapsed : {}".format(elapse))
-            end = time.time()
-            time_dict['all'] = end - start
-            return None, None, time_dict
-        else:
-            logger.debug("dt_boxes num : {}, elapsed : {}".format(
-                len(dt_boxes), elapse))
-        img_crop_list = []
-
-        dt_boxes = sorted_boxes(dt_boxes)
-
-        # merge_det_boxes 和 update_det_boxes 都会把poly转成bbox再转回poly，因此需要过滤所有倾斜程度较大的文本框
-        dt_boxes = merge_det_boxes(dt_boxes)
-
-        if mfd_res:
-            bef = time.time()
-            dt_boxes = update_det_boxes(dt_boxes, mfd_res)
-            aft = time.time()
-            logger.debug("split text box by formula, new dt_boxes num : {}, elapsed : {}".format(
-                len(dt_boxes), aft - bef))
-
-        for bno in range(len(dt_boxes)):
-            tmp_box = copy.deepcopy(dt_boxes[bno])
-            if self.args.det_box_type == "quad":
-                img_crop = get_rotate_crop_image(ori_im, tmp_box)
-            else:
-                img_crop = get_minarea_rect_crop(ori_im, tmp_box)
-            img_crop_list.append(img_crop)
-        if self.use_angle_cls and cls:
-            img_crop_list, angle_list, elapse = self.text_classifier(
-                img_crop_list)
-            time_dict['cls'] = elapse
-            logger.debug("cls num  : {}, elapsed : {}".format(
-                len(img_crop_list), elapse))
-        if self.lang in ['ch'] and self.use_onnx:
-            rec_res, elapse = self.additional_ocr.text_recognizer(img_crop_list)
-        else:
-            rec_res, elapse = self.text_recognizer(img_crop_list)
-        time_dict['rec'] = elapse
-        logger.debug("rec_res num  : {}, elapsed : {}".format(
-            len(rec_res), elapse))
-        if self.args.save_crop_res:
-            self.draw_crop_rec_res(self.args.crop_res_save_dir, img_crop_list,
-                                   rec_res)
-        filter_boxes, filter_rec_res = [], []
-        for box, rec_result in zip(dt_boxes, rec_res):
-            text, score = rec_result
-            if score >= self.drop_score:
-                filter_boxes.append(box)
-                filter_rec_res.append(rec_result)
-        end = time.time()
-        time_dict['all'] = end - start
-        return filter_boxes, filter_rec_res, time_dict

magic_pdf/model/sub_modules/ocr/paddleocr/ppocr_291_mod.py

@@ -1,213 +0,0 @@
-import copy
-import time
-
-
-import cv2
-import numpy as np
-from paddleocr import PaddleOCR
-from paddleocr.paddleocr import check_img, logger
-from paddleocr.ppocr.utils.utility import alpha_to_color, binarize_img
-from paddleocr.tools.infer.predict_system import sorted_boxes
-from paddleocr.tools.infer.utility import slice_generator, merge_fragmented, get_rotate_crop_image, \
-    get_minarea_rect_crop
-
-from magic_pdf.model.sub_modules.ocr.paddleocr.ocr_utils import update_det_boxes
-
-
-class ModifiedPaddleOCR(PaddleOCR):
-
-    def ocr(
-        self,
-        img,
-        det=True,
-        rec=True,
-        cls=True,
-        bin=False,
-        inv=False,
-        alpha_color=(255, 255, 255),
-        slice={},
-        mfd_res=None,
-    ):
-        """
-        OCR with PaddleOCR
-
-        Args:
-            img: Image for OCR. It can be an ndarray, img_path, or a list of ndarrays.
-            det: Use text detection or not. If False, only text recognition will be executed. Default is True.
-            rec: Use text recognition or not. If False, only text detection will be executed. Default is True.
-            cls: Use angle classifier or not. Default is True. If True, the text with a rotation of 180 degrees can be recognized. If no text is rotated by 180 degrees, use cls=False to get better performance.
-            bin: Binarize image to black and white. Default is False.
-            inv: Invert image colors. Default is False.
-            alpha_color: Set RGB color Tuple for transparent parts replacement. Default is pure white.
-            slice: Use sliding window inference for large images. Both det and rec must be True. Requires int values for slice["horizontal_stride"], slice["vertical_stride"], slice["merge_x_thres"], slice["merge_y_thres"] (See doc/doc_en/slice_en.md). Default is {}.
-
-        Returns:
-            If both det and rec are True, returns a list of OCR results for each image. Each OCR result is a list of bounding boxes and recognized text for each detected text region.
-            If det is True and rec is False, returns a list of detected bounding boxes for each image.
-            If det is False and rec is True, returns a list of recognized text for each image.
-            If both det and rec are False, returns a list of angle classification results for each image.
-
-        Raises:
-            AssertionError: If the input image is not of type ndarray, list, str, or bytes.
-            SystemExit: If det is True and the input is a list of images.
-
-        Note:
-            - If the angle classifier is not initialized (use_angle_cls=False), it will not be used during the forward process.
-            - For PDF files, if the input is a list of images and the page_num is specified, only the first page_num images will be processed.
-            - The preprocess_image function is used to preprocess the input image by applying alpha color replacement, inversion, and binarization if specified.
-        """
-        assert isinstance(img, (np.ndarray, list, str, bytes))
-        if isinstance(img, list) and det == True:
-            logger.error("When input a list of images, det must be false")
-            exit(0)
-        if cls == True and self.use_angle_cls == False:
-            logger.warning(
-                "Since the angle classifier is not initialized, it will not be used during the forward process"
-            )
-
-        img, flag_gif, flag_pdf = check_img(img, alpha_color)
-        # for infer pdf file
-        if isinstance(img, list) and flag_pdf:
-            if self.page_num > len(img) or self.page_num == 0:
-                imgs = img
-            else:
-                imgs = img[: self.page_num]
-        else:
-            imgs = [img]
-
-        def preprocess_image(_image):
-            _image = alpha_to_color(_image, alpha_color)
-            if inv:
-                _image = cv2.bitwise_not(_image)
-            if bin:
-                _image = binarize_img(_image)
-            return _image
-
-        if det and rec:
-            ocr_res = []
-            for img in imgs:
-                img = preprocess_image(img)
-                dt_boxes, rec_res, _ = self.__call__(img, cls, slice, mfd_res=mfd_res)
-                if not dt_boxes and not rec_res:
-                    ocr_res.append(None)
-                    continue
-                tmp_res = [[box.tolist(), res] for box, res in zip(dt_boxes, rec_res)]
-                ocr_res.append(tmp_res)
-            return ocr_res
-        elif det and not rec:
-            ocr_res = []
-            for img in imgs:
-                img = preprocess_image(img)
-                dt_boxes, elapse = self.text_detector(img)
-                if dt_boxes.size == 0:
-                    ocr_res.append(None)
-                    continue
-                tmp_res = [box.tolist() for box in dt_boxes]
-                ocr_res.append(tmp_res)
-            return ocr_res
-        else:
-            ocr_res = []
-            cls_res = []
-            for img in imgs:
-                if not isinstance(img, list):
-                    img = preprocess_image(img)
-                    img = [img]
-                if self.use_angle_cls and cls:
-                    img, cls_res_tmp, elapse = self.text_classifier(img)
-                    if not rec:
-                        cls_res.append(cls_res_tmp)
-                rec_res, elapse = self.text_recognizer(img)
-                ocr_res.append(rec_res)
-            if not rec:
-                return cls_res
-            return ocr_res
-
-    def __call__(self, img, cls=True, slice={}, mfd_res=None):
-        time_dict = {"det": 0, "rec": 0, "cls": 0, "all": 0}
-
-        if img is None:
-            logger.debug("no valid image provided")
-            return None, None, time_dict
-
-        start = time.time()
-        ori_im = img.copy()
-        if slice:
-            slice_gen = slice_generator(
-                img,
-                horizontal_stride=slice["horizontal_stride"],
-                vertical_stride=slice["vertical_stride"],
-            )
-            elapsed = []
-            dt_slice_boxes = []
-            for slice_crop, v_start, h_start in slice_gen:
-                dt_boxes, elapse = self.text_detector(slice_crop, use_slice=True)
-                if dt_boxes.size:
-                    dt_boxes[:, :, 0] += h_start
-                    dt_boxes[:, :, 1] += v_start
-                    dt_slice_boxes.append(dt_boxes)
-                    elapsed.append(elapse)
-            dt_boxes = np.concatenate(dt_slice_boxes)
-
-            dt_boxes = merge_fragmented(
-                boxes=dt_boxes,
-                x_threshold=slice["merge_x_thres"],
-                y_threshold=slice["merge_y_thres"],
-            )
-            elapse = sum(elapsed)
-        else:
-            dt_boxes, elapse = self.text_detector(img)
-
-        time_dict["det"] = elapse
-
-        if dt_boxes is None:
-            logger.debug("no dt_boxes found, elapsed : {}".format(elapse))
-            end = time.time()
-            time_dict["all"] = end - start
-            return None, None, time_dict
-        else:
-            logger.debug(
-                "dt_boxes num : {}, elapsed : {}".format(len(dt_boxes), elapse)
-            )
-        img_crop_list = []
-
-        dt_boxes = sorted_boxes(dt_boxes)
-
-        if mfd_res:
-            bef = time.time()
-            dt_boxes = update_det_boxes(dt_boxes, mfd_res)
-            aft = time.time()
-            logger.debug("split text box by formula, new dt_boxes num : {}, elapsed : {}".format(
-                len(dt_boxes), aft - bef))
-
-        for bno in range(len(dt_boxes)):
-            tmp_box = copy.deepcopy(dt_boxes[bno])
-            if self.args.det_box_type == "quad":
-                img_crop = get_rotate_crop_image(ori_im, tmp_box)
-            else:
-                img_crop = get_minarea_rect_crop(ori_im, tmp_box)
-            img_crop_list.append(img_crop)
-        if self.use_angle_cls and cls:
-            img_crop_list, angle_list, elapse = self.text_classifier(img_crop_list)
-            time_dict["cls"] = elapse
-            logger.debug(
-                "cls num  : {}, elapsed : {}".format(len(img_crop_list), elapse)
-            )
-        if len(img_crop_list) > 1000:
-            logger.debug(
-                f"rec crops num: {len(img_crop_list)}, time and memory cost may be large."
-            )
-
-        rec_res, elapse = self.text_recognizer(img_crop_list)
-        time_dict["rec"] = elapse
-        logger.debug("rec_res num  : {}, elapsed : {}".format(len(rec_res), elapse))
-        if self.args.save_crop_res:
-            self.draw_crop_rec_res(self.args.crop_res_save_dir, img_crop_list, rec_res)
-        filter_boxes, filter_rec_res = [], []
-        for box, rec_result in zip(dt_boxes, rec_res):
-            text, score = rec_result[0], rec_result[1]
-            if score >= self.drop_score:
-                filter_boxes.append(box)
-                filter_rec_res.append(rec_result)
-        end = time.time()
-        time_dict["all"] = end - start
-        return filter_boxes, filter_rec_res, time_dict