magic-pdf 0.10.0__py3-none-any.whl → 0.10.2__py3-none-any.whl

{magic_pdf-0.10.0.dist-info → magic_pdf-0.10.2.dist-info}/RECORD

@@ -1,8 +1,7 @@
 magic_pdf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/pdf_parse_by_ocr.py,sha256=WTaLVSU2wRpgtldasnqbrw1B0OvVi8VvcB_t-dAIfmw,880
 magic_pdf/pdf_parse_by_txt.py,sha256=dh3ZM6BVrFzwbH4137BPUdKhgacGlpS2N4mn74_-UaA,762
-magic_pdf/pdf_parse_union_core.py,sha256=w90lFIMOYUMAq4iv8bpsbBtLXFphPV4HyYeqbOTYQUI,12420
-magic_pdf/pdf_parse_union_core_v2.py,sha256=EqEi9AahBBh2JbXoY8uOCmClvi9W_H_26U4jK8RwPwU,31308
+magic_pdf/pdf_parse_union_core_v2.py,sha256=-4yJwcSMcGwQKJhmK_MbBMa-fexzkqeD1CQHWpzGC3I,29920
 magic_pdf/user_api.py,sha256=Sh6U7iD5VsH7Qkav_0o5GTx-Rlj7vhmhHQHZSBKR5T8,4006
 magic_pdf/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/config/constants.py,sha256=gqhUEtso7rCop-k-VvEPAMW_6pA6Tv2Y9smrr_0Iajo,1173
@@ -20,7 +19,7 @@ magic_pdf/data/schemas.py,sha256=oIUTBzK8Wq8Wuy8A_uilWAbVhucRvOs9_f3lSKYgcmQ,664
 magic_pdf/data/utils.py,sha256=dJZiqygwNier0UG5tbt5jAPjgwcnfsAN6-m-G1kVPLQ,917
 magic_pdf/data/data_reader_writer/__init__.py,sha256=QtevUaeSivv9dQKi3Tomfn4Z0E4To0cB8qXTnglxaHc,705
 magic_pdf/data/data_reader_writer/base.py,sha256=gUrHCMTHYBrWpqgHdIc-hN7HHwUC2ApK_VXrDUrnfdg,1320
-magic_pdf/data/data_reader_writer/filebase.py,sha256=21RYy4m9MqJGqwd2HWICQJHM-PZXp7UYETCQQK390Kk,1988
+magic_pdf/data/data_reader_writer/filebase.py,sha256=iVjBT1M_89F5HB2uMsBzLfCNhsTVnmurJk4VUuAA2tw,2111
 magic_pdf/data/data_reader_writer/multi_bucket_s3.py,sha256=_HA8NJO1Be7KwozlwOJ90o8Ik2vfjlvlDPXppESeIfk,5885
 magic_pdf/data/data_reader_writer/s3.py,sha256=9Oy1cNuXMwG1e8PgZ7AR-pn_MqHAhkgAGnyEZCYoYAA,2408
 magic_pdf/data/io/__init__.py,sha256=WKaIlu8i5AWYxFCGNJcorAfMnlUQDOF8CX07Ycfnu2c,294
@@ -28,48 +27,36 @@ magic_pdf/data/io/base.py,sha256=SqNQqe30ZvoVvg7GVv-hLMCjN6yBgDyQQWeLgGsTfhQ,111
 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/mkcontent.py,sha256=bMQK7uiay76YaWA92VIK57YajINV20SnOs65wOEXyKE,18667
 magic_pdf/dict2md/ocr_mkcontent.py,sha256=ohjhEFS9YFrzTCC9c9yrvi4QuZe9iZm1qlkQWB6xxIw,13038
 magic_pdf/filter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/filter/pdf_classify_by_type.py,sha256=spmDO-f2ihAl1d6-EP-j271Yi50oyu6mw4X2kRd_m0s,42320
-magic_pdf/filter/pdf_meta_scan.py,sha256=h4D4O0OeAlEy2A8mJ6E0aQ8wIizIfsIxEagbjaomnAo,17823
+magic_pdf/filter/pdf_meta_scan.py,sha256=3I-t3PSrQUZ3PZAPl_NGoEhxLmIUE9Fpc0jueEXP7Xw,17381
 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/layout/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/layout/bbox_sort.py,sha256=PzzaBf6MC_AZ-ZWGU0Kg-KIsw874l_gML73mM3hE4Ps,30807
-magic_pdf/layout/layout_det_utils.py,sha256=NCYBTvsrULE3Cue53aMD1MfXTmOL9Xy0nivl6ku2cls,9137
-magic_pdf/layout/layout_sort.py,sha256=jtacQVcxnuYAksvEqtS0DH-v6U8qyjX-jmyZgDJ-egA,37005
-magic_pdf/layout/layout_spiler_recog.py,sha256=QjBSgB-a7J2yjUR1eaCs9ZD7URtiRnV6W934hpAeuC4,3067
-magic_pdf/layout/mcol_sort.py,sha256=ADnLisBJBHXDKYChcf2lzTb_TC_vZ4q89_CSN8mwEJc,11331
 magic_pdf/libs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/libs/boxbase.py,sha256=ELMHWolgWROxOAQDgwmL7VS5kveZp4ifvEzRmPul2Ws,16925
-magic_pdf/libs/calc_span_stats.py,sha256=5vnU27DcbkFDRSAoLqAmX0KQ3I9ehWkEgh_t9hxg_zI,10147
 magic_pdf/libs/clean_memory.py,sha256=BIOmEWuwR7c_p4OwTSW2muE3PRaGhmOplS-wTXt_EXk,211
-magic_pdf/libs/commons.py,sha256=6Zu9-OyamyCNDY7qj0SxR-rux-ggj9im3CVPtC4ubB8,7108
+magic_pdf/libs/commons.py,sha256=xD0fGA16KNB5rhbl4zRrOqdrNHYwaRablT_s9W2ZTbw,1174
 magic_pdf/libs/config_reader.py,sha256=vDsxw2xbW7Gb1mKqERTSlttbXFNtVU0BDdae2dG7wEI,4068
 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/detect_language_from_model.py,sha256=Uln8F9qs8EJOw4EgI7KRlaU3lD_mK8KMTlADLFtz8fk,816
-magic_pdf/libs/draw_bbox.py,sha256=NhAfqib5HYuGjjrAG_SvJR-yOHZTy6tzDxLXdxKlULQ,17676
+magic_pdf/libs/draw_bbox.py,sha256=2IXr4TUxm0-pXYIPkNaELWo9pOysZC6etpqzTE5eg-w,17588
 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=Hj5-lrGoNExxdHLbkcNG-c27U4AjJ9AZPdZblaNSehU,1099
 magic_pdf/libs/local_math.py,sha256=tqljQOgqh3fZc146HYhO88JXJaiXMVwArBkk_CSGICc,177
-magic_pdf/libs/markdown_utils.py,sha256=cLxLXjRhrNp_wCHvtglrGA_FVdrvfd1KULeTtj1p18w,944
-magic_pdf/libs/nlp_utils.py,sha256=-X9W3-Ns5ZdDYFvyyEq6i6P2b5hCATaFEZeOjwNOH9M,6901
+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=MAe8wzwT0qvPf_I72wEZG7k1g4haNHS7oUtLqkB5rlE,2145
-magic_pdf/libs/pdf_image_tools.py,sha256=sh8hgBQu_83R71qBLodOFdByBUuQujsOMfgpSD9mrhE,1981
+magic_pdf/libs/pdf_image_tools.py,sha256=kjzSEbm7K0yiHv8kJ4VbZ9HHktM8qvAv3LhxRyDZEQk,1987
 magic_pdf/libs/safe_filename.py,sha256=ckwcM_eqoysTb5id8czp-tXq2G9da0-l3pshZDCHQtE,236
-magic_pdf/libs/textbase.py,sha256=SC1Frhz3Fb7V7n2SFRBsl7Bmg0JZdlvZskq0lfW1vIk,732
-magic_pdf/libs/version.py,sha256=v4zmKjsKOPZbp6BrWoz7iK4ST0sdZdUh9bQSJmluZ5o,23
-magic_pdf/libs/vis_utils.py,sha256=hTOTEakKV0pGMbk0tbRkVI_tku7A3dGc96ynObZ4kwI,10207
+magic_pdf/libs/version.py,sha256=A_AARqtxTOj_AQTpjpgOxNx-UOBio5wYFfZ2mrdMKfs,23
 magic_pdf/model/__init__.py,sha256=1QcfMKET0xQhSaZMjNQHi_TjzSSDR6PI5mjkmaXHPe8,52
-magic_pdf/model/doc_analyze_by_custom_model.py,sha256=HOT6chGx2VPyH6O9WB0c6xGPeDs9m_6oZn3iOa745yw,7125
-magic_pdf/model/magic_model.py,sha256=8nJLzNCa0Ag4JhMAQbjj5qrkj617qKPCXVJAiT9DnaA,43472
+magic_pdf/model/doc_analyze_by_custom_model.py,sha256=YZwlhIgidy1_MUyTM_MRSLfKR_rpi508Bra6Vpj8PJ4,7125
+magic_pdf/model/magic_model.py,sha256=ppMkMqtP7sKncHTZ2SbXuPOoR988iRPexBEMA6QeiIc,42208
 magic_pdf/model/model_list.py,sha256=tJ9jtMB93HGx8Rmt8wmQSDFXZBUIPQrwaaYsep4luTM,183
 magic_pdf/model/pdf_extract_kit.py,sha256=ceYWlSU1BhakfsHPVM9SrUx35EvCBa20uJmgDO5PAtE,10933
 magic_pdf/model/pp_structure_v2.py,sha256=BKPN7W4BjG0eWPAPjPEac1RMnb5eIzmAz4E4Rq-9b1U,3019
@@ -107,8 +94,8 @@ magic_pdf/model/sub_modules/mfr/unimernet/Unimernet.py,sha256=jeJkqID6L1ZivPMdK1
 magic_pdf/model/sub_modules/mfr/unimernet/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/model/sub_modules/ocr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/model/sub_modules/ocr/paddleocr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/model/sub_modules/ocr/paddleocr/ocr_utils.py,sha256=UP7fADPGoxAMj2SUKmeW-fe_AcAQxlT9Mfy4WF6vHmU,9796
-magic_pdf/model/sub_modules/ocr/paddleocr/ppocr_273_mod.py,sha256=a6xkQHqLMUL4NCaORp8oo4Tfa8GB8PN9MVvG7Pj6jIE,7316
+magic_pdf/model/sub_modules/ocr/paddleocr/ocr_utils.py,sha256=bya-KGr5OPCmE8KC8K5Pp6OlGigCmUmB9xpm59nExaM,9056
+magic_pdf/model/sub_modules/ocr/paddleocr/ppocr_273_mod.py,sha256=Deoth86bltlLz1Y-1jpyhLCwCaRfq-KKI0tiFyKKqA8,7268
 magic_pdf/model/sub_modules/ocr/paddleocr/ppocr_291_mod.py,sha256=VouMTvi6M5TV6pQdlpusgfyZapxiZ_Wi7Ff53eMC3rE,8996
 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
@@ -123,64 +110,26 @@ magic_pdf/model/sub_modules/table/structeqtable/struct_eqtable.py,sha256=SrNPm-u
 magic_pdf/model/sub_modules/table/tablemaster/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/model/sub_modules/table/tablemaster/tablemaster_paddle.py,sha256=AdH3UGu4BEoII0uFjPKUf61W7HmG4fDlWgR1xxMeFlE,2775
 magic_pdf/para/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/para/block_continuation_processor.py,sha256=IkReB5hirjm0OAirNzQQpnWe2f2bdP3Hug3Ef8qTRDA,22749
-magic_pdf/para/block_termination_processor.py,sha256=YU3ZYqJy9e3OQmOuQYZrR6AUpmAlQ0mhj0PgZZPZ_fM,17957
-magic_pdf/para/commons.py,sha256=VdJ8SY9qJTtcRyx8HH-PFeZSJwL4Tsf50197RD_-dwc,5414
-magic_pdf/para/denoise.py,sha256=J7dM2KNnbdzAd2A3agB04U6L1GL9RrhAs-MLrq-_Ftg,10443
-magic_pdf/para/draw.py,sha256=KyWc03do_WuBKQ028HYzepYwbIkel9ID0uqRhuPVOHc,5643
-magic_pdf/para/exceptions.py,sha256=kpjGxrSZ-drNmoKlmuQ0asTjI8cKKKWsdDDBoDHQP9M,4978
-magic_pdf/para/layout_match_processor.py,sha256=yr4FEO7GJ502udShqGRqIJQ_FQxoa0aG_mhmWd8nLwI,1554
-magic_pdf/para/para_split.py,sha256=z7nYeg86BjZOAdJNMwYKSu51W9evurtl3cy1ZUcQLlw,33222
-magic_pdf/para/para_split_v2.py,sha256=vJJqqMMKbv8D702nODThL-5hjkgZ7Vl2BTmEIdwmmDw,39051
-magic_pdf/para/para_split_v3.py,sha256=atfELVRx-90paAS3nZptgP0qG8UpTTaj3LG_2x3NAlQ,15977
-magic_pdf/para/raw_processor.py,sha256=mHxD9FrdOSXH7NqM41s55URyCyuyACvm9kKtowkIb3k,6317
-magic_pdf/para/stats.py,sha256=-6Pf9Y8jkP1uJOYWiHUjw9Lb-Fb9GY7MHr_ok7x2GX0,9731
-magic_pdf/para/title_processor.py,sha256=pYZv9vEkIjAtCz8jIUtl9AVUy_ib5SdAZmMVoZtsMRI,38593
+magic_pdf/para/para_split_v3.py,sha256=x6nfjyt38W-wdxXjo6Chd18eiqLzmhbTNyGHhBQcEHs,16459
 magic_pdf/pipe/AbsPipe.py,sha256=jPtAa0pz_vPddya3ZpUk6UrGqp8PcBdLONO1spzavQo,4371
 magic_pdf/pipe/OCRPipe.py,sha256=nuN-zpUzu--gyrC0_vsvvilAyK7Mp3Tom_UOnsur1ps,2158
 magic_pdf/pipe/TXTPipe.py,sha256=5OFo2e8U5Y24wJrFDEJghBDpklnKFEnzKTYVnnhQssE,2159
 magic_pdf/pipe/UNIPipe.py,sha256=ik0xXPdsHo7Un0gFpLC5ul04BP3Omd2mp5gqem40deE,4807
 magic_pdf/pipe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/post_proc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/post_proc/detect_para.py,sha256=5LX86ueHQGOV9CNimAxqZH4R3KTi78leum1de_Na0pw,126181
-magic_pdf/post_proc/pdf_post_filter.py,sha256=3EJDovQPckPKJaBY1wvAty-LGKyRG63WICY_bA_Kfbs,2501
-magic_pdf/post_proc/remove_footnote.py,sha256=701P7xRu6gzLaEHfb2xkYpLZI4CwK2FAo7Ggho4bOTI,7596
 magic_pdf/pre_proc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/pre_proc/citationmarker_remove.py,sha256=IitOERaK9fGaktsYMyiaaL_71uMIrlG5ZdmpZaR6dsA,6640
-magic_pdf/pre_proc/construct_page_dict.py,sha256=lp3zBmInlWYYIcGC1-NSqT9s44AjDvlnWxDPeZoBVSY,3043
-magic_pdf/pre_proc/cut_image.py,sha256=TghshkDTgdUbyLSbKZoFI9-n-xaFub02IYPyu0IAnRY,2761
-magic_pdf/pre_proc/detect_equation.py,sha256=9omDHKTI8QO9Qd46eVFHWhZeMmTNx7XDuWRgjXI-KFA,6627
-magic_pdf/pre_proc/detect_footer_by_model.py,sha256=_EghAM_zWBcqVY8XBkbSoprKqKUa0mlN1U8YNWxNNLI,2848
-magic_pdf/pre_proc/detect_footer_header_by_statistics.py,sha256=924soXZ51QVpitPgVgnwbC7BqOZI30j5hGW5zP86y-w,11250
-magic_pdf/pre_proc/detect_footnote.py,sha256=UxFuTCRwXdAv3wKCgRQJJVt12hM9O9oPTwzPAChQXoM,8309
-magic_pdf/pre_proc/detect_header.py,sha256=KOmRehgKMuMqNa_2weXkdNSiRVWMFgLMQE4e1itbY7g,2848
-magic_pdf/pre_proc/detect_images.py,sha256=8DwGGTb5IjxqADZDTc_ngwJrTYXxK2qpRqI2FBoPr00,30432
-magic_pdf/pre_proc/detect_page_number.py,sha256=qvYrBbCtBbREvw-MySL_p7byCRvcm1fkLJ5ZB4TP8OM,2848
-magic_pdf/pre_proc/detect_tables.py,sha256=srJzgLVeVuOsqnESqfdJfVukTF84K8qmI5mgFX_BZGs,2800
-magic_pdf/pre_proc/equations_replace.py,sha256=7mexRPwD9C_UJ-SbvO_-XnpcnN7YtGUUznmPjHbjhnw,20526
-magic_pdf/pre_proc/fix_image.py,sha256=5MOfkXc8abfIp49g-68vll40wwTUZ5tcQ2gtsJuFmvs,11486
-magic_pdf/pre_proc/fix_table.py,sha256=20sqJe27fAXcL7_C0qQ9mpsggmH37WuX-wPYWyRgACA,13227
-magic_pdf/pre_proc/main_text_font.py,sha256=1gkjvPuBdKC4oVFkLvnRm2zghsLtVlfAEMKXouyVonM,1048
-magic_pdf/pre_proc/ocr_detect_all_bboxes.py,sha256=DMc2H2xGqVePBReZu5AQbPdvDw3sxOssmujCLlNW3Vs,14143
-magic_pdf/pre_proc/ocr_detect_layout.py,sha256=DW0_HXzmcbW22cXKIYFsyZNFh8mEjSHXIFVjXndJsvQ,5878
-magic_pdf/pre_proc/ocr_dict_merge.py,sha256=Au8y1NBhbWpq_VuPLg3b9dAMUhyPS71xtTghtd21K5M,14273
-magic_pdf/pre_proc/ocr_span_list_modify.py,sha256=9DxEyy1pH87g4T_JEgI3cTVCL2TVrEBl38wsmqhQM4k,12758
-magic_pdf/pre_proc/pdf_pre_filter.py,sha256=qvNlNyj4Mc3qa73mgfkp0PMR-ucABbx3mMcyVipaEpQ,2776
-magic_pdf/pre_proc/post_layout_split.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=U-ttnl3lAhhmgtkR1GGyPAVm0i0-6VscXf3E2EDy3lE,1187
+magic_pdf/pre_proc/ocr_detect_all_bboxes.py,sha256=xQ1L6pwQjN4xBSKEXslheip1aMFaiB0grqlX3BF-kh0,9282
+magic_pdf/pre_proc/ocr_dict_merge.py,sha256=Ycgz2whzotL7kwl0-mHNV48QOQ2j4tRXqLSQrJRojYg,4847
+magic_pdf/pre_proc/ocr_span_list_modify.py,sha256=a5OmIwtkXkz6fTQg6p8R-f1nA_w0rgMwKFQjfs_HwrE,2864
 magic_pdf/pre_proc/remove_bbox_overlap.py,sha256=8eXNdsz9s06LX0kS0AxYSkaY1tWQQMkJfVtVSdjTQNE,3090
-magic_pdf/pre_proc/remove_colored_strip_bbox.py,sha256=WVKhgeWifRdO-u2ETYffkcMOFVYIbiaZu5pMr1RpEdA,4090
-magic_pdf/pre_proc/remove_footer_header.py,sha256=Igdr4jH7BUGuTcapWPiKEGKxhWH12c3VVmX5xwUVn7w,5680
-magic_pdf/pre_proc/remove_rotate_bbox.py,sha256=di7geS7AFhSaAvkWZHT6J3dlXEq8uu9Z4oBYtolQjl0,8803
-magic_pdf/pre_proc/resolve_bbox_conflict.py,sha256=ABl0vo8kkcCPSTI8dpXQTOH1b9R-lbzsJDDFONU6ELk,7313
-magic_pdf/pre_proc/solve_line_alien.py,sha256=aNoQptPcC38Sm1I2ABhgw8jeH_5kjsRHx3VYlFFtm1g,853
-magic_pdf/pre_proc/statistics.py,sha256=_9jGlXq0iXd03UMxB92ZqCiu7cjNkG5vHvFlTF_9ytA,220
 magic_pdf/resources/fasttext-langdetect/lid.176.ftz,sha256=jzRyz-hzintgmejpmcPL-uDc0VaWqsfXc4qAOdtgPoM,938013
 magic_pdf/resources/model_config/model_configs.yaml,sha256=S2BnVQxPd0xsZswn9WqJKTfnqd7ayY5lRwDVifTEAfw,290
 magic_pdf/resources/model_config/UniMERNet/demo.yaml,sha256=Jdaim2D2lAYrV9rhc1X5Sy2_IacGOrfysJhxEUgSElo,827
 magic_pdf/resources/model_config/layoutlmv3/layoutlmv3_base_inference.yaml,sha256=9aNAEYgpHTAWpcUrDvuPG2y4V-Qw8QdcJefi96y8yDU,6109
 magic_pdf/rw/AbsReaderWriter.py,sha256=2H5SDJfAAOX9kPfel06a8VRCHxD1Y8aPbWEkQDdn9JM,452
 magic_pdf/rw/DiskReaderWriter.py,sha256=7ZAekH8V6xlBo_1WeSZ6sNwAj2WGPtjNl50zq1CoMDY,2614
-magic_pdf/rw/S3ReaderWriter.py,sha256=_DmL45Ubio-_VsKD84KrqOQ-VNDUTzcXSrXfNMb5vww,5310
+magic_pdf/rw/S3ReaderWriter.py,sha256=LmbtA-pZlC745nnSUs67C1iqSrBDS7IzE6QC8YMB644,5293
 magic_pdf/rw/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/spark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/spark/spark_api.py,sha256=BYO6zlRW0cEnIUB3ZzNQTu_LsPHEVitqiUN7gy3x_wo,1124
@@ -190,9 +139,9 @@ magic_pdf/tools/cli_dev.py,sha256=3RbubfTIagWoFYdu8wSDanr-BJDjFGeDet55jTy7He0,39
 magic_pdf/tools/common.py,sha256=ILTv8YjnK-XTVV5nzak3Sm-EJJXjG1hJJghlYKgYVBQ,6809
 magic_pdf/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/utils/annotations.py,sha256=82ou3uELNbQWa9hOFFkVt0gsIskAKf5msCv5J2IJ5V0,211
-magic_pdf-0.10.0.dist-info/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
-magic_pdf-0.10.0.dist-info/METADATA,sha256=U_TtQjdODFjAADoZro_ipfGiasBCVq2_zZlF2DFyNpM,40300
-magic_pdf-0.10.0.dist-info/WHEEL,sha256=bFJAMchF8aTQGUgMZzHJyDDMPTO3ToJ7x23SLJa1SVo,92
-magic_pdf-0.10.0.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
-magic_pdf-0.10.0.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
-magic_pdf-0.10.0.dist-info/RECORD,,
+magic_pdf-0.10.2.dist-info/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
+magic_pdf-0.10.2.dist-info/METADATA,sha256=5pYglDeTXZaIsMRAHSfNl57Yq3gPXdcexNxt1zdvmu4,37030
+magic_pdf-0.10.2.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+magic_pdf-0.10.2.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
+magic_pdf-0.10.2.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
+magic_pdf-0.10.2.dist-info/RECORD,,

{magic_pdf-0.10.0.dist-info → magic_pdf-0.10.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.45.0)
+Generator: bdist_wheel (0.45.1)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

magic_pdf/dict2md/mkcontent.py

@@ -1,438 +0,0 @@
-import math
-
-from loguru import logger
-
-from magic_pdf.config.ocr_content_type import ContentType
-from magic_pdf.libs.boxbase import (find_bottom_nearest_text_bbox,
-                                    find_top_nearest_text_bbox)
-from magic_pdf.libs.commons import join_path
-
-TYPE_INLINE_EQUATION = ContentType.InlineEquation
-TYPE_INTERLINE_EQUATION = ContentType.InterlineEquation
-UNI_FORMAT_TEXT_TYPE = ['text', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6']
-
-
-@DeprecationWarning
-def mk_nlp_markdown_1(para_dict: dict):
-    """对排序后的bboxes拼接内容."""
-    content_lst = []
-    for _, page_info in para_dict.items():
-        para_blocks = page_info.get('para_blocks')
-        if not para_blocks:
-            continue
-
-        for block in para_blocks:
-            item = block['paras']
-            for _, p in item.items():
-                para_text = p['para_text']
-                is_title = p['is_para_title']
-                title_level = p['para_title_level']
-                md_title_prefix = '#' * title_level
-                if is_title:
-                    content_lst.append(f'{md_title_prefix} {para_text}')
-                else:
-                    content_lst.append(para_text)
-
-    content_text = '\n\n'.join(content_lst)
-
-    return content_text
-
-
-# 找到目标字符串在段落中的索引
-def __find_index(paragraph, target):
-    index = paragraph.find(target)
-    if index != -1:
-        return index
-    else:
-        return None
-
-
-def __insert_string(paragraph, target, position):
-    new_paragraph = paragraph[:position] + target + paragraph[position:]
-    return new_paragraph
-
-
-def __insert_after(content, image_content, target):
-    """在content中找到target，将image_content插入到target后面."""
-    index = content.find(target)
-    if index != -1:
-        content = (
-            content[: index + len(target)]
-            + '\n\n'
-            + image_content
-            + '\n\n'
-            + content[index + len(target) :]
-        )
-    else:
-        logger.error(
-            f"Can't find the location of image {image_content} in the markdown file, search target is {target}"
-        )
-    return content
-
-
-def __insert_before(content, image_content, target):
-    """在content中找到target，将image_content插入到target前面."""
-    index = content.find(target)
-    if index != -1:
-        content = content[:index] + '\n\n' + image_content + '\n\n' + content[index:]
-    else:
-        logger.error(
-            f"Can't find the location of image {image_content} in the markdown file, search target is {target}"
-        )
-    return content
-
-
-@DeprecationWarning
-def mk_mm_markdown_1(para_dict: dict):
-    """拼装多模态markdown."""
-    content_lst = []
-    for _, page_info in para_dict.items():
-        page_lst = []  # 一个page内的段落列表
-        para_blocks = page_info.get('para_blocks')
-        pymu_raw_blocks = page_info.get('preproc_blocks')
-
-        all_page_images = []
-        all_page_images.extend(page_info.get('images', []))
-        all_page_images.extend(page_info.get('image_backup', []))
-        all_page_images.extend(page_info.get('tables', []))
-        all_page_images.extend(page_info.get('table_backup', []))
-
-        if not para_blocks or not pymu_raw_blocks:  # 只有图片的拼接的场景
-            for img in all_page_images:
-                page_lst.append(f"![]({img['image_path']})")  # TODO 图片顺序
-            page_md = '\n\n'.join(page_lst)
-
-        else:
-            for block in para_blocks:
-                item = block['paras']
-                for _, p in item.items():
-                    para_text = p['para_text']
-                    is_title = p['is_para_title']
-                    title_level = p['para_title_level']
-                    md_title_prefix = '#' * title_level
-                    if is_title:
-                        page_lst.append(f'{md_title_prefix} {para_text}')
-                    else:
-                        page_lst.append(para_text)
-
-            """拼装成一个页面的文本"""
-            page_md = '\n\n'.join(page_lst)
-            """插入图片"""
-            for img in all_page_images:
-                imgbox = img['bbox']
-                img_content = f"![]({img['image_path']})"
-                # 先看在哪个block内
-                for block in pymu_raw_blocks:
-                    bbox = block['bbox']
-                    if (
-                        bbox[0] - 1 <= imgbox[0] < bbox[2] + 1
-                        and bbox[1] - 1 <= imgbox[1] < bbox[3] + 1
-                    ):  # 确定在block内
-                        for l in block['lines']:  # noqa: E741
-                            line_box = l['bbox']
-                            if (
-                                line_box[0] - 1 <= imgbox[0] < line_box[2] + 1
-                                and line_box[1] - 1 <= imgbox[1] < line_box[3] + 1
-                            ):  # 在line内的，插入line前面
-                                line_txt = ''.join([s['text'] for s in l['spans']])
-                                page_md = __insert_before(
-                                    page_md, img_content, line_txt
-                                )
-                                break
-                            break
-                        else:  # 在行与行之间
-                            # 找到图片x0,y0与line的x0,y0最近的line
-                            min_distance = 100000
-                            min_line = None
-                            for l in block['lines']:  # noqa: E741
-                                line_box = l['bbox']
-                                distance = math.sqrt(
-                                    (line_box[0] - imgbox[0]) ** 2
-                                    + (line_box[1] - imgbox[1]) ** 2
-                                )
-                                if distance < min_distance:
-                                    min_distance = distance
-                                    min_line = l
-                            if min_line:
-                                line_txt = ''.join(
-                                    [s['text'] for s in min_line['spans']]
-                                )
-                                img_h = imgbox[3] - imgbox[1]
-                                if min_distance < img_h:  # 文字在图片前面
-                                    page_md = __insert_after(
-                                        page_md, img_content, line_txt
-                                    )
-                                else:
-                                    page_md = __insert_before(
-                                        page_md, img_content, line_txt
-                                    )
-                            else:
-                                logger.error(
-                                    f"Can't find the location of image {img['image_path']} in the markdown file  #1"
-                                )
-                else:  # 应当在两个block之间
-                    # 找到上方最近的block，如果上方没有就找大下方最近的block
-                    top_txt_block = find_top_nearest_text_bbox(pymu_raw_blocks, imgbox)
-                    if top_txt_block:
-                        line_txt = ''.join(
-                            [s['text'] for s in top_txt_block['lines'][-1]['spans']]
-                        )
-                        page_md = __insert_after(page_md, img_content, line_txt)
-                    else:
-                        bottom_txt_block = find_bottom_nearest_text_bbox(
-                            pymu_raw_blocks, imgbox
-                        )
-                        if bottom_txt_block:
-                            line_txt = ''.join(
-                                [
-                                    s['text']
-                                    for s in bottom_txt_block['lines'][0]['spans']
-                                ]
-                            )
-                            page_md = __insert_before(page_md, img_content, line_txt)
-                        else:
-                            logger.error(
-                                f"Can't find the location of image {img['image_path']} in the markdown file  #2"
-                            )
-
-        content_lst.append(page_md)
-
-    """拼装成全部页面的文本"""
-    content_text = '\n\n'.join(content_lst)
-
-    return content_text
-
-
-def __insert_after_para(text, type, element, content_list):
-    """在content_list中找到text，将image_path作为一个新的node插入到text后面."""
-    for i, c in enumerate(content_list):
-        content_type = c.get('type')
-        if content_type in UNI_FORMAT_TEXT_TYPE and text in c.get('text', ''):
-            if type == 'image':
-                content_node = {
-                    'type': 'image',
-                    'img_path': element.get('image_path'),
-                    'img_alt': '',
-                    'img_title': '',
-                    'img_caption': '',
-                }
-            elif type == 'table':
-                content_node = {
-                    'type': 'table',
-                    'img_path': element.get('image_path'),
-                    'table_latex': element.get('text'),
-                    'table_title': '',
-                    'table_caption': '',
-                    'table_quality': element.get('quality'),
-                }
-            content_list.insert(i + 1, content_node)
-            break
-    else:
-        logger.error(
-            f"Can't find the location of image {element.get('image_path')} in the markdown file, search target is {text}"
-        )
-
-
-def __insert_before_para(text, type, element, content_list):
-    """在content_list中找到text，将image_path作为一个新的node插入到text前面."""
-    for i, c in enumerate(content_list):
-        content_type = c.get('type')
-        if content_type in UNI_FORMAT_TEXT_TYPE and text in c.get('text', ''):
-            if type == 'image':
-                content_node = {
-                    'type': 'image',
-                    'img_path': element.get('image_path'),
-                    'img_alt': '',
-                    'img_title': '',
-                    'img_caption': '',
-                }
-            elif type == 'table':
-                content_node = {
-                    'type': 'table',
-                    'img_path': element.get('image_path'),
-                    'table_latex': element.get('text'),
-                    'table_title': '',
-                    'table_caption': '',
-                    'table_quality': element.get('quality'),
-                }
-            content_list.insert(i, content_node)
-            break
-    else:
-        logger.error(
-            f"Can't find the location of image {element.get('image_path')} in the markdown file, search target is {text}"
-        )
-
-
-def mk_universal_format(pdf_info_list: list, img_buket_path):
-    """构造统一格式 https://aicarrier.feishu.cn/wiki/FqmMwcH69iIdCWkkyjvcDwNUnTY."""
-    content_lst = []
-    for page_info in pdf_info_list:
-        page_lst = []  # 一个page内的段落列表
-        para_blocks = page_info.get('para_blocks')
-        pymu_raw_blocks = page_info.get('preproc_blocks')
-
-        all_page_images = []
-        all_page_images.extend(page_info.get('images', []))
-        all_page_images.extend(page_info.get('image_backup', []))
-        # all_page_images.extend(page_info.get("tables",[]))
-        # all_page_images.extend(page_info.get("table_backup",[]) )
-        all_page_tables = []
-        all_page_tables.extend(page_info.get('tables', []))
-
-        if not para_blocks or not pymu_raw_blocks:  # 只有图片的拼接的场景
-            for img in all_page_images:
-                content_node = {
-                    'type': 'image',
-                    'img_path': join_path(img_buket_path, img['image_path']),
-                    'img_alt': '',
-                    'img_title': '',
-                    'img_caption': '',
-                }
-                page_lst.append(content_node)  # TODO 图片顺序
-            for table in all_page_tables:
-                content_node = {
-                    'type': 'table',
-                    'img_path': join_path(img_buket_path, table['image_path']),
-                    'table_latex': table.get('text'),
-                    'table_title': '',
-                    'table_caption': '',
-                    'table_quality': table.get('quality'),
-                }
-                page_lst.append(content_node)  # TODO 图片顺序
-        else:
-            for block in para_blocks:
-                item = block['paras']
-                for _, p in item.items():
-                    font_type = p[
-                        'para_font_type'
-                    ]  # 对于文本来说，要么是普通文本，要么是个行间公式
-                    if font_type == TYPE_INTERLINE_EQUATION:
-                        content_node = {'type': 'equation', 'latex': p['para_text']}
-                        page_lst.append(content_node)
-                    else:
-                        para_text = p['para_text']
-                        is_title = p['is_para_title']
-                        title_level = p['para_title_level']
-
-                        if is_title:
-                            content_node = {
-                                'type': f'h{title_level}',
-                                'text': para_text,
-                            }
-                            page_lst.append(content_node)
-                        else:
-                            content_node = {'type': 'text', 'text': para_text}
-                            page_lst.append(content_node)
-
-        content_lst.extend(page_lst)
-
-        """插入图片"""
-        for img in all_page_images:
-            insert_img_or_table('image', img, pymu_raw_blocks, content_lst)
-
-        """插入表格"""
-        for table in all_page_tables:
-            insert_img_or_table('table', table, pymu_raw_blocks, content_lst)
-    # end for
-    return content_lst
-
-
-def insert_img_or_table(type, element, pymu_raw_blocks, content_lst):
-    element_bbox = element['bbox']
-    # 先看在哪个block内
-    for block in pymu_raw_blocks:
-        bbox = block['bbox']
-        if (
-            bbox[0] - 1 <= element_bbox[0] < bbox[2] + 1
-            and bbox[1] - 1 <= element_bbox[1] < bbox[3] + 1
-        ):  # 确定在这个大的block内，然后进入逐行比较距离
-            for l in block['lines']:  # noqa: E741
-                line_box = l['bbox']
-                if (
-                    line_box[0] - 1 <= element_bbox[0] < line_box[2] + 1
-                    and line_box[1] - 1 <= element_bbox[1] < line_box[3] + 1
-                ):  # 在line内的，插入line前面
-                    line_txt = ''.join([s['text'] for s in l['spans']])
-                    __insert_before_para(line_txt, type, element, content_lst)
-                    break
-                break
-            else:  # 在行与行之间
-                # 找到图片x0,y0与line的x0,y0最近的line
-                min_distance = 100000
-                min_line = None
-                for l in block['lines']:  # noqa: E741
-                    line_box = l['bbox']
-                    distance = math.sqrt(
-                        (line_box[0] - element_bbox[0]) ** 2
-                        + (line_box[1] - element_bbox[1]) ** 2
-                    )
-                    if distance < min_distance:
-                        min_distance = distance
-                        min_line = l
-                if min_line:
-                    line_txt = ''.join([s['text'] for s in min_line['spans']])
-                    img_h = element_bbox[3] - element_bbox[1]
-                    if min_distance < img_h:  # 文字在图片前面
-                        __insert_after_para(line_txt, type, element, content_lst)
-                    else:
-                        __insert_before_para(line_txt, type, element, content_lst)
-                    break
-                else:
-                    logger.error(
-                        f"Can't find the location of image {element.get('image_path')} in the markdown file  #1"
-                    )
-    else:  # 应当在两个block之间
-        # 找到上方最近的block，如果上方没有就找大下方最近的block
-        top_txt_block = find_top_nearest_text_bbox(pymu_raw_blocks, element_bbox)
-        if top_txt_block:
-            line_txt = ''.join([s['text'] for s in top_txt_block['lines'][-1]['spans']])
-            __insert_after_para(line_txt, type, element, content_lst)
-        else:
-            bottom_txt_block = find_bottom_nearest_text_bbox(
-                pymu_raw_blocks, element_bbox
-            )
-            if bottom_txt_block:
-                line_txt = ''.join(
-                    [s['text'] for s in bottom_txt_block['lines'][0]['spans']]
-                )
-                __insert_before_para(line_txt, type, element, content_lst)
-            else:  # TODO ，图片可能独占一列，这种情况上下是没有图片的
-                logger.error(
-                    f"Can't find the location of image {element.get('image_path')} in the markdown file  #2"
-                )
-
-
-def mk_mm_markdown(content_list):
-    """基于同一格式的内容列表，构造markdown，含图片."""
-    content_md = []
-    for c in content_list:
-        content_type = c.get('type')
-        if content_type == 'text':
-            content_md.append(c.get('text'))
-        elif content_type == 'equation':
-            content = c.get('latex')
-            if content.startswith('$$') and content.endswith('$$'):
-                content_md.append(content)
-            else:
-                content_md.append(f"\n$$\n{c.get('latex')}\n$$\n")
-        elif content_type in UNI_FORMAT_TEXT_TYPE:
-            content_md.append(f"{'#'*int(content_type[1])} {c.get('text')}")
-        elif content_type == 'image':
-            content_md.append(f"![]({c.get('img_path')})")
-    return '\n\n'.join(content_md)
-
-
-def mk_nlp_markdown(content_list):
-    """基于同一格式的内容列表，构造markdown，不含图片."""
-    content_md = []
-    for c in content_list:
-        content_type = c.get('type')
-        if content_type == 'text':
-            content_md.append(c.get('text'))
-        elif content_type == 'equation':
-            content_md.append(f"$$\n{c.get('latex')}\n$$")
-        elif content_type == 'table':
-            content_md.append(f"$$$\n{c.get('table_latex')}\n$$$")
-        elif content_type in UNI_FORMAT_TEXT_TYPE:
-            content_md.append(f"{'#'*int(content_type[1])} {c.get('text')}")
-    return '\n\n'.join(content_md)