pyxllib 0.3.96__py3-none-any.whl → 0.3.200__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- pyxllib/__init__.py +21 -21
- pyxllib/algo/__init__.py +8 -8
- pyxllib/algo/disjoint.py +54 -54
- pyxllib/algo/geo.py +541 -529
- pyxllib/algo/intervals.py +964 -964
- pyxllib/algo/matcher.py +389 -311
- pyxllib/algo/newbie.py +166 -166
- pyxllib/algo/pupil.py +629 -461
- pyxllib/algo/shapelylib.py +67 -67
- pyxllib/algo/specialist.py +241 -240
- pyxllib/algo/stat.py +494 -458
- pyxllib/algo/treelib.py +149 -149
- pyxllib/algo/unitlib.py +66 -66
- {pyxlpr → pyxllib/autogui}/__init__.py +5 -5
- pyxllib/autogui/activewin.py +246 -0
- pyxllib/autogui/all.py +9 -0
- pyxllib/{ext/autogui → autogui}/autogui.py +852 -823
- pyxllib/autogui/uiautolib.py +362 -0
- pyxllib/{ext/autogui → autogui}/virtualkey.py +102 -102
- pyxllib/autogui/wechat.py +827 -0
- pyxllib/autogui/wechat_msg.py +421 -0
- pyxllib/autogui/wxautolib.py +84 -0
- pyxllib/cv/__init__.py +5 -5
- pyxllib/cv/expert.py +267 -267
- pyxllib/cv/imfile.py +159 -159
- pyxllib/cv/imhash.py +39 -39
- pyxllib/cv/pupil.py +9 -9
- pyxllib/cv/rgbfmt.py +1525 -1525
- pyxllib/cv/slidercaptcha.py +137 -0
- pyxllib/cv/trackbartools.py +251 -251
- pyxllib/cv/xlcvlib.py +1040 -1040
- pyxllib/cv/xlpillib.py +423 -423
- pyxllib/data/echarts.py +240 -129
- pyxllib/data/jsonlib.py +89 -0
- pyxllib/data/oss.py +72 -72
- pyxllib/data/pglib.py +1127 -643
- pyxllib/data/sqlite.py +568 -341
- pyxllib/data/sqllib.py +297 -297
- pyxllib/ext/JLineViewer.py +505 -492
- pyxllib/ext/__init__.py +6 -6
- pyxllib/ext/demolib.py +246 -246
- pyxllib/ext/drissionlib.py +277 -0
- pyxllib/ext/kq5034lib.py +12 -1606
- pyxllib/ext/old.py +663 -663
- pyxllib/ext/qt.py +449 -449
- pyxllib/ext/robustprocfile.py +497 -0
- pyxllib/ext/seleniumlib.py +76 -76
- pyxllib/ext/tk.py +173 -173
- pyxllib/ext/unixlib.py +827 -826
- pyxllib/ext/utools.py +351 -338
- pyxllib/ext/webhook.py +124 -101
- pyxllib/ext/win32lib.py +40 -40
- pyxllib/ext/wjxlib.py +88 -0
- pyxllib/ext/wpsapi.py +124 -0
- pyxllib/ext/xlwork.py +9 -0
- pyxllib/ext/yuquelib.py +1105 -173
- pyxllib/file/__init__.py +17 -17
- pyxllib/file/docxlib.py +761 -761
- pyxllib/file/gitlib.py +309 -309
- pyxllib/file/libreoffice.py +165 -0
- pyxllib/file/movielib.py +148 -139
- pyxllib/file/newbie.py +10 -10
- pyxllib/file/onenotelib.py +1469 -1469
- pyxllib/file/packlib/__init__.py +330 -293
- pyxllib/file/packlib/zipfile.py +2441 -2441
- pyxllib/file/pdflib.py +426 -426
- pyxllib/file/pupil.py +185 -185
- pyxllib/file/specialist/__init__.py +685 -685
- pyxllib/file/specialist/dirlib.py +799 -799
- pyxllib/file/specialist/download.py +193 -186
- pyxllib/file/specialist/filelib.py +2829 -2618
- pyxllib/file/xlsxlib.py +3131 -2976
- pyxllib/file/xlsyncfile.py +341 -0
- pyxllib/prog/__init__.py +5 -5
- pyxllib/prog/cachetools.py +64 -0
- pyxllib/prog/deprecatedlib.py +233 -233
- pyxllib/prog/filelock.py +42 -0
- pyxllib/prog/ipyexec.py +253 -253
- pyxllib/prog/multiprogs.py +940 -0
- pyxllib/prog/newbie.py +451 -444
- pyxllib/prog/pupil.py +1197 -1128
- pyxllib/prog/sitepackages.py +33 -33
- pyxllib/prog/specialist/__init__.py +391 -217
- pyxllib/prog/specialist/bc.py +203 -200
- pyxllib/prog/specialist/browser.py +497 -488
- pyxllib/prog/specialist/common.py +347 -347
- pyxllib/prog/specialist/datetime.py +199 -131
- pyxllib/prog/specialist/tictoc.py +240 -241
- pyxllib/prog/specialist/xllog.py +180 -180
- pyxllib/prog/xlosenv.py +108 -101
- pyxllib/stdlib/__init__.py +17 -17
- pyxllib/stdlib/tablepyxl/__init__.py +10 -10
- pyxllib/stdlib/tablepyxl/style.py +303 -303
- pyxllib/stdlib/tablepyxl/tablepyxl.py +130 -130
- pyxllib/text/__init__.py +8 -8
- pyxllib/text/ahocorasick.py +39 -39
- pyxllib/text/airscript.js +744 -0
- pyxllib/text/charclasslib.py +121 -109
- pyxllib/text/jiebalib.py +267 -264
- pyxllib/text/jinjalib.py +32 -0
- pyxllib/text/jsa_ai_prompt.md +271 -0
- pyxllib/text/jscode.py +922 -767
- pyxllib/text/latex/__init__.py +158 -158
- pyxllib/text/levenshtein.py +303 -303
- pyxllib/text/nestenv.py +1215 -1215
- pyxllib/text/newbie.py +300 -288
- pyxllib/text/pupil/__init__.py +8 -8
- pyxllib/text/pupil/common.py +1121 -1095
- pyxllib/text/pupil/xlalign.py +326 -326
- pyxllib/text/pycode.py +47 -47
- pyxllib/text/specialist/__init__.py +8 -8
- pyxllib/text/specialist/common.py +112 -112
- pyxllib/text/specialist/ptag.py +186 -186
- pyxllib/text/spellchecker.py +172 -172
- pyxllib/text/templates/echart_base.html +11 -0
- pyxllib/text/templates/highlight_code.html +17 -0
- pyxllib/text/templates/latex_editor.html +103 -0
- pyxllib/text/vbacode.py +17 -17
- pyxllib/text/xmllib.py +747 -685
- pyxllib/xl.py +42 -38
- pyxllib/xlcv.py +17 -17
- pyxllib-0.3.200.dist-info/METADATA +48 -0
- pyxllib-0.3.200.dist-info/RECORD +126 -0
- {pyxllib-0.3.96.dist-info → pyxllib-0.3.200.dist-info}/WHEEL +1 -2
- {pyxllib-0.3.96.dist-info → pyxllib-0.3.200.dist-info/licenses}/LICENSE +190 -190
- pyxllib/ext/autogui/__init__.py +0 -8
- pyxllib-0.3.96.dist-info/METADATA +0 -51
- pyxllib-0.3.96.dist-info/RECORD +0 -333
- pyxllib-0.3.96.dist-info/top_level.txt +0 -2
- pyxlpr/ai/__init__.py +0 -5
- pyxlpr/ai/clientlib.py +0 -1281
- pyxlpr/ai/specialist.py +0 -286
- pyxlpr/ai/torch_app.py +0 -172
- pyxlpr/ai/xlpaddle.py +0 -655
- pyxlpr/ai/xltorch.py +0 -705
- pyxlpr/data/__init__.py +0 -11
- pyxlpr/data/coco.py +0 -1325
- pyxlpr/data/datacls.py +0 -365
- pyxlpr/data/datasets.py +0 -200
- pyxlpr/data/gptlib.py +0 -1291
- pyxlpr/data/icdar/__init__.py +0 -96
- pyxlpr/data/icdar/deteval.py +0 -377
- pyxlpr/data/icdar/icdar2013.py +0 -341
- pyxlpr/data/icdar/iou.py +0 -340
- pyxlpr/data/icdar/rrc_evaluation_funcs_1_1.py +0 -463
- pyxlpr/data/imtextline.py +0 -473
- pyxlpr/data/labelme.py +0 -866
- pyxlpr/data/removeline.py +0 -179
- pyxlpr/data/specialist.py +0 -57
- pyxlpr/eval/__init__.py +0 -85
- pyxlpr/paddleocr.py +0 -776
- pyxlpr/ppocr/__init__.py +0 -15
- pyxlpr/ppocr/configs/rec/multi_language/generate_multi_language_configs.py +0 -226
- pyxlpr/ppocr/data/__init__.py +0 -135
- pyxlpr/ppocr/data/imaug/ColorJitter.py +0 -26
- pyxlpr/ppocr/data/imaug/__init__.py +0 -67
- pyxlpr/ppocr/data/imaug/copy_paste.py +0 -170
- pyxlpr/ppocr/data/imaug/east_process.py +0 -437
- pyxlpr/ppocr/data/imaug/gen_table_mask.py +0 -244
- pyxlpr/ppocr/data/imaug/iaa_augment.py +0 -114
- pyxlpr/ppocr/data/imaug/label_ops.py +0 -789
- pyxlpr/ppocr/data/imaug/make_border_map.py +0 -184
- pyxlpr/ppocr/data/imaug/make_pse_gt.py +0 -106
- pyxlpr/ppocr/data/imaug/make_shrink_map.py +0 -126
- pyxlpr/ppocr/data/imaug/operators.py +0 -433
- pyxlpr/ppocr/data/imaug/pg_process.py +0 -906
- pyxlpr/ppocr/data/imaug/randaugment.py +0 -143
- pyxlpr/ppocr/data/imaug/random_crop_data.py +0 -239
- pyxlpr/ppocr/data/imaug/rec_img_aug.py +0 -533
- pyxlpr/ppocr/data/imaug/sast_process.py +0 -777
- pyxlpr/ppocr/data/imaug/text_image_aug/__init__.py +0 -17
- pyxlpr/ppocr/data/imaug/text_image_aug/augment.py +0 -120
- pyxlpr/ppocr/data/imaug/text_image_aug/warp_mls.py +0 -168
- pyxlpr/ppocr/data/lmdb_dataset.py +0 -115
- pyxlpr/ppocr/data/pgnet_dataset.py +0 -104
- pyxlpr/ppocr/data/pubtab_dataset.py +0 -107
- pyxlpr/ppocr/data/simple_dataset.py +0 -372
- pyxlpr/ppocr/losses/__init__.py +0 -61
- pyxlpr/ppocr/losses/ace_loss.py +0 -52
- pyxlpr/ppocr/losses/basic_loss.py +0 -135
- pyxlpr/ppocr/losses/center_loss.py +0 -88
- pyxlpr/ppocr/losses/cls_loss.py +0 -30
- pyxlpr/ppocr/losses/combined_loss.py +0 -67
- pyxlpr/ppocr/losses/det_basic_loss.py +0 -208
- pyxlpr/ppocr/losses/det_db_loss.py +0 -80
- pyxlpr/ppocr/losses/det_east_loss.py +0 -63
- pyxlpr/ppocr/losses/det_pse_loss.py +0 -149
- pyxlpr/ppocr/losses/det_sast_loss.py +0 -121
- pyxlpr/ppocr/losses/distillation_loss.py +0 -272
- pyxlpr/ppocr/losses/e2e_pg_loss.py +0 -140
- pyxlpr/ppocr/losses/kie_sdmgr_loss.py +0 -113
- pyxlpr/ppocr/losses/rec_aster_loss.py +0 -99
- pyxlpr/ppocr/losses/rec_att_loss.py +0 -39
- pyxlpr/ppocr/losses/rec_ctc_loss.py +0 -44
- pyxlpr/ppocr/losses/rec_enhanced_ctc_loss.py +0 -70
- pyxlpr/ppocr/losses/rec_nrtr_loss.py +0 -30
- pyxlpr/ppocr/losses/rec_sar_loss.py +0 -28
- pyxlpr/ppocr/losses/rec_srn_loss.py +0 -47
- pyxlpr/ppocr/losses/table_att_loss.py +0 -109
- pyxlpr/ppocr/metrics/__init__.py +0 -44
- pyxlpr/ppocr/metrics/cls_metric.py +0 -45
- pyxlpr/ppocr/metrics/det_metric.py +0 -82
- pyxlpr/ppocr/metrics/distillation_metric.py +0 -73
- pyxlpr/ppocr/metrics/e2e_metric.py +0 -86
- pyxlpr/ppocr/metrics/eval_det_iou.py +0 -274
- pyxlpr/ppocr/metrics/kie_metric.py +0 -70
- pyxlpr/ppocr/metrics/rec_metric.py +0 -75
- pyxlpr/ppocr/metrics/table_metric.py +0 -50
- pyxlpr/ppocr/modeling/architectures/__init__.py +0 -32
- pyxlpr/ppocr/modeling/architectures/base_model.py +0 -88
- pyxlpr/ppocr/modeling/architectures/distillation_model.py +0 -60
- pyxlpr/ppocr/modeling/backbones/__init__.py +0 -54
- pyxlpr/ppocr/modeling/backbones/det_mobilenet_v3.py +0 -268
- pyxlpr/ppocr/modeling/backbones/det_resnet_vd.py +0 -246
- pyxlpr/ppocr/modeling/backbones/det_resnet_vd_sast.py +0 -285
- pyxlpr/ppocr/modeling/backbones/e2e_resnet_vd_pg.py +0 -265
- pyxlpr/ppocr/modeling/backbones/kie_unet_sdmgr.py +0 -186
- pyxlpr/ppocr/modeling/backbones/rec_mobilenet_v3.py +0 -138
- pyxlpr/ppocr/modeling/backbones/rec_mv1_enhance.py +0 -258
- pyxlpr/ppocr/modeling/backbones/rec_nrtr_mtb.py +0 -48
- pyxlpr/ppocr/modeling/backbones/rec_resnet_31.py +0 -210
- pyxlpr/ppocr/modeling/backbones/rec_resnet_aster.py +0 -143
- pyxlpr/ppocr/modeling/backbones/rec_resnet_fpn.py +0 -307
- pyxlpr/ppocr/modeling/backbones/rec_resnet_vd.py +0 -286
- pyxlpr/ppocr/modeling/heads/__init__.py +0 -54
- pyxlpr/ppocr/modeling/heads/cls_head.py +0 -52
- pyxlpr/ppocr/modeling/heads/det_db_head.py +0 -118
- pyxlpr/ppocr/modeling/heads/det_east_head.py +0 -121
- pyxlpr/ppocr/modeling/heads/det_pse_head.py +0 -37
- pyxlpr/ppocr/modeling/heads/det_sast_head.py +0 -128
- pyxlpr/ppocr/modeling/heads/e2e_pg_head.py +0 -253
- pyxlpr/ppocr/modeling/heads/kie_sdmgr_head.py +0 -206
- pyxlpr/ppocr/modeling/heads/multiheadAttention.py +0 -163
- pyxlpr/ppocr/modeling/heads/rec_aster_head.py +0 -393
- pyxlpr/ppocr/modeling/heads/rec_att_head.py +0 -202
- pyxlpr/ppocr/modeling/heads/rec_ctc_head.py +0 -88
- pyxlpr/ppocr/modeling/heads/rec_nrtr_head.py +0 -826
- pyxlpr/ppocr/modeling/heads/rec_sar_head.py +0 -402
- pyxlpr/ppocr/modeling/heads/rec_srn_head.py +0 -280
- pyxlpr/ppocr/modeling/heads/self_attention.py +0 -406
- pyxlpr/ppocr/modeling/heads/table_att_head.py +0 -246
- pyxlpr/ppocr/modeling/necks/__init__.py +0 -32
- pyxlpr/ppocr/modeling/necks/db_fpn.py +0 -111
- pyxlpr/ppocr/modeling/necks/east_fpn.py +0 -188
- pyxlpr/ppocr/modeling/necks/fpn.py +0 -138
- pyxlpr/ppocr/modeling/necks/pg_fpn.py +0 -314
- pyxlpr/ppocr/modeling/necks/rnn.py +0 -92
- pyxlpr/ppocr/modeling/necks/sast_fpn.py +0 -284
- pyxlpr/ppocr/modeling/necks/table_fpn.py +0 -110
- pyxlpr/ppocr/modeling/transforms/__init__.py +0 -28
- pyxlpr/ppocr/modeling/transforms/stn.py +0 -135
- pyxlpr/ppocr/modeling/transforms/tps.py +0 -308
- pyxlpr/ppocr/modeling/transforms/tps_spatial_transformer.py +0 -156
- pyxlpr/ppocr/optimizer/__init__.py +0 -61
- pyxlpr/ppocr/optimizer/learning_rate.py +0 -228
- pyxlpr/ppocr/optimizer/lr_scheduler.py +0 -49
- pyxlpr/ppocr/optimizer/optimizer.py +0 -160
- pyxlpr/ppocr/optimizer/regularizer.py +0 -52
- pyxlpr/ppocr/postprocess/__init__.py +0 -55
- pyxlpr/ppocr/postprocess/cls_postprocess.py +0 -33
- pyxlpr/ppocr/postprocess/db_postprocess.py +0 -234
- pyxlpr/ppocr/postprocess/east_postprocess.py +0 -143
- pyxlpr/ppocr/postprocess/locality_aware_nms.py +0 -200
- pyxlpr/ppocr/postprocess/pg_postprocess.py +0 -52
- pyxlpr/ppocr/postprocess/pse_postprocess/__init__.py +0 -15
- pyxlpr/ppocr/postprocess/pse_postprocess/pse/__init__.py +0 -29
- pyxlpr/ppocr/postprocess/pse_postprocess/pse/setup.py +0 -14
- pyxlpr/ppocr/postprocess/pse_postprocess/pse_postprocess.py +0 -118
- pyxlpr/ppocr/postprocess/rec_postprocess.py +0 -654
- pyxlpr/ppocr/postprocess/sast_postprocess.py +0 -355
- pyxlpr/ppocr/tools/__init__.py +0 -14
- pyxlpr/ppocr/tools/eval.py +0 -83
- pyxlpr/ppocr/tools/export_center.py +0 -77
- pyxlpr/ppocr/tools/export_model.py +0 -129
- pyxlpr/ppocr/tools/infer/predict_cls.py +0 -151
- pyxlpr/ppocr/tools/infer/predict_det.py +0 -300
- pyxlpr/ppocr/tools/infer/predict_e2e.py +0 -169
- pyxlpr/ppocr/tools/infer/predict_rec.py +0 -414
- pyxlpr/ppocr/tools/infer/predict_system.py +0 -204
- pyxlpr/ppocr/tools/infer/utility.py +0 -629
- pyxlpr/ppocr/tools/infer_cls.py +0 -83
- pyxlpr/ppocr/tools/infer_det.py +0 -134
- pyxlpr/ppocr/tools/infer_e2e.py +0 -122
- pyxlpr/ppocr/tools/infer_kie.py +0 -153
- pyxlpr/ppocr/tools/infer_rec.py +0 -146
- pyxlpr/ppocr/tools/infer_table.py +0 -107
- pyxlpr/ppocr/tools/program.py +0 -596
- pyxlpr/ppocr/tools/test_hubserving.py +0 -117
- pyxlpr/ppocr/tools/train.py +0 -163
- pyxlpr/ppocr/tools/xlprog.py +0 -748
- pyxlpr/ppocr/utils/EN_symbol_dict.txt +0 -94
- pyxlpr/ppocr/utils/__init__.py +0 -24
- pyxlpr/ppocr/utils/dict/ar_dict.txt +0 -117
- pyxlpr/ppocr/utils/dict/arabic_dict.txt +0 -162
- pyxlpr/ppocr/utils/dict/be_dict.txt +0 -145
- pyxlpr/ppocr/utils/dict/bg_dict.txt +0 -140
- pyxlpr/ppocr/utils/dict/chinese_cht_dict.txt +0 -8421
- pyxlpr/ppocr/utils/dict/cyrillic_dict.txt +0 -163
- pyxlpr/ppocr/utils/dict/devanagari_dict.txt +0 -167
- pyxlpr/ppocr/utils/dict/en_dict.txt +0 -63
- pyxlpr/ppocr/utils/dict/fa_dict.txt +0 -136
- pyxlpr/ppocr/utils/dict/french_dict.txt +0 -136
- pyxlpr/ppocr/utils/dict/german_dict.txt +0 -143
- pyxlpr/ppocr/utils/dict/hi_dict.txt +0 -162
- pyxlpr/ppocr/utils/dict/it_dict.txt +0 -118
- pyxlpr/ppocr/utils/dict/japan_dict.txt +0 -4399
- pyxlpr/ppocr/utils/dict/ka_dict.txt +0 -153
- pyxlpr/ppocr/utils/dict/korean_dict.txt +0 -3688
- pyxlpr/ppocr/utils/dict/latin_dict.txt +0 -185
- pyxlpr/ppocr/utils/dict/mr_dict.txt +0 -153
- pyxlpr/ppocr/utils/dict/ne_dict.txt +0 -153
- pyxlpr/ppocr/utils/dict/oc_dict.txt +0 -96
- pyxlpr/ppocr/utils/dict/pu_dict.txt +0 -130
- pyxlpr/ppocr/utils/dict/rs_dict.txt +0 -91
- pyxlpr/ppocr/utils/dict/rsc_dict.txt +0 -134
- pyxlpr/ppocr/utils/dict/ru_dict.txt +0 -125
- pyxlpr/ppocr/utils/dict/ta_dict.txt +0 -128
- pyxlpr/ppocr/utils/dict/table_dict.txt +0 -277
- pyxlpr/ppocr/utils/dict/table_structure_dict.txt +0 -2759
- pyxlpr/ppocr/utils/dict/te_dict.txt +0 -151
- pyxlpr/ppocr/utils/dict/ug_dict.txt +0 -114
- pyxlpr/ppocr/utils/dict/uk_dict.txt +0 -142
- pyxlpr/ppocr/utils/dict/ur_dict.txt +0 -137
- pyxlpr/ppocr/utils/dict/xi_dict.txt +0 -110
- pyxlpr/ppocr/utils/dict90.txt +0 -90
- pyxlpr/ppocr/utils/e2e_metric/Deteval.py +0 -574
- pyxlpr/ppocr/utils/e2e_metric/polygon_fast.py +0 -83
- pyxlpr/ppocr/utils/e2e_utils/extract_batchsize.py +0 -87
- pyxlpr/ppocr/utils/e2e_utils/extract_textpoint_fast.py +0 -457
- pyxlpr/ppocr/utils/e2e_utils/extract_textpoint_slow.py +0 -592
- pyxlpr/ppocr/utils/e2e_utils/pgnet_pp_utils.py +0 -162
- pyxlpr/ppocr/utils/e2e_utils/visual.py +0 -162
- pyxlpr/ppocr/utils/en_dict.txt +0 -95
- pyxlpr/ppocr/utils/gen_label.py +0 -81
- pyxlpr/ppocr/utils/ic15_dict.txt +0 -36
- pyxlpr/ppocr/utils/iou.py +0 -54
- pyxlpr/ppocr/utils/logging.py +0 -69
- pyxlpr/ppocr/utils/network.py +0 -84
- pyxlpr/ppocr/utils/ppocr_keys_v1.txt +0 -6623
- pyxlpr/ppocr/utils/profiler.py +0 -110
- pyxlpr/ppocr/utils/save_load.py +0 -150
- pyxlpr/ppocr/utils/stats.py +0 -72
- pyxlpr/ppocr/utils/utility.py +0 -80
- pyxlpr/ppstructure/__init__.py +0 -13
- pyxlpr/ppstructure/predict_system.py +0 -187
- pyxlpr/ppstructure/table/__init__.py +0 -13
- pyxlpr/ppstructure/table/eval_table.py +0 -72
- pyxlpr/ppstructure/table/matcher.py +0 -192
- pyxlpr/ppstructure/table/predict_structure.py +0 -136
- pyxlpr/ppstructure/table/predict_table.py +0 -221
- pyxlpr/ppstructure/table/table_metric/__init__.py +0 -16
- pyxlpr/ppstructure/table/table_metric/parallel.py +0 -51
- pyxlpr/ppstructure/table/table_metric/table_metric.py +0 -247
- pyxlpr/ppstructure/table/tablepyxl/__init__.py +0 -13
- pyxlpr/ppstructure/table/tablepyxl/style.py +0 -283
- pyxlpr/ppstructure/table/tablepyxl/tablepyxl.py +0 -118
- pyxlpr/ppstructure/utility.py +0 -71
- pyxlpr/xlai.py +0 -10
pyxllib/text/latex/__init__.py
CHANGED
@@ -1,158 +1,158 @@
|
|
1
|
-
#!/usr/bin/env python3
|
2
|
-
# -*- coding: utf-8 -*-
|
3
|
-
# @Author : 陈坤泽
|
4
|
-
# @Email : 877362867@qq.com
|
5
|
-
# @Date : 2021/10/08 22:26
|
6
|
-
|
7
|
-
import re
|
8
|
-
|
9
|
-
from pyxllib.prog.specialist import browser
|
10
|
-
from pyxllib.text.pupil import grp_bracket, continuous_zero
|
11
|
-
|
12
|
-
|
13
|
-
class TexTabular:
|
14
|
-
@classmethod
|
15
|
-
def parse_multirow(cls, s, brace_text_only=True):
|
16
|
-
r"""
|
17
|
-
|
18
|
-
:param brace_text_only: 只取花括号里面的内容
|
19
|
-
如果为False,会把multirow外部的内容做拼接
|
20
|
-
|
21
|
-
multirow 和 multicolumn 的不同是,第1、2个花括号后面可以有可选参数。
|
22
|
-
第2个花括号如果内容是*,可以省略。
|
23
|
-
两个[]的内容先省略,不做分析处理
|
24
|
-
|
25
|
-
注意:这里会取出前后缀内容!业务需要,防止bug,不过这种概率很小
|
26
|
-
|
27
|
-
>>> TexTabular.parse_multirow(r'\multirow{2}*{特点}')
|
28
|
-
(2, None, '*', None, '特点')
|
29
|
-
>>> TexTabular.parse_multirow(r'\multirow{2}{*}{特点}')
|
30
|
-
(2, None, '*', None, '特点')
|
31
|
-
>>> TexTabular.parse_multirow(r'aa\multirow{2}[bla1]{*}[bla2]{特点}bb', brace_text_only=False)
|
32
|
-
(2, 'bla1', '*', 'bla2', 'aa特点bb')
|
33
|
-
|
34
|
-
TODO multirow第一个数字是可以负值的,代表向上合并单元格数,
|
35
|
-
"""
|
36
|
-
square = r'(?:\[(.*?)\])?' # 可选参数
|
37
|
-
m = re.search(r'\\multirow' + grp_bracket(3, inner=True) + square +
|
38
|
-
r'(?:{(.*?)}|(\*))' + square + grp_bracket(5, inner=True), s)
|
39
|
-
if not m: return None
|
40
|
-
n, bigstructs, width1, width2, fixup, text = m.groups()
|
41
|
-
width = width1 or width2
|
42
|
-
if not brace_text_only: text = s[:m.start()] + text + s[m.end():]
|
43
|
-
# if re.match(r'\d+$', text): text = int(text) # 如果可以,直接识别为数字
|
44
|
-
|
45
|
-
n = int(n)
|
46
|
-
if -1 <= n <= 1:
|
47
|
-
n = 1
|
48
|
-
elif n > 1:
|
49
|
-
pass
|
50
|
-
else:
|
51
|
-
raise ValueError(f'{s} 不支持解析multirow第一个值为负数,向上合并单元格的情况')
|
52
|
-
|
53
|
-
return n, bigstructs, width, fixup, text
|
54
|
-
|
55
|
-
@classmethod
|
56
|
-
def parse_multicolumn(cls, s):
|
57
|
-
r"""找出s中第一次出现的满足模式的multicolumn,返回3个关键值
|
58
|
-
|
59
|
-
:returns:
|
60
|
-
第1个参数是该合并单元格的尺寸,固定格式: (行数, 列数),只有一行是也会写'1'
|
61
|
-
|
62
|
-
>>> TexTabular.parse_multicolumn(r'\multicolumn{2}{|c|}{aa\multirow{3}*{特点}bb}')
|
63
|
-
((3, 2), '|c|', 'aa特点bb')
|
64
|
-
"""
|
65
|
-
# 1 基本的模式匹配抓取
|
66
|
-
m = re.search(r'\\multicolumn' + grp_bracket(3, inner=True) * 2
|
67
|
-
+ grp_bracket(5, inner=True), s) # 最后层多套下,我怕不够用
|
68
|
-
if not m: return None
|
69
|
-
|
70
|
-
# 2 取出参数值
|
71
|
-
m, col_align, text = m.groups()
|
72
|
-
m = int(m)
|
73
|
-
|
74
|
-
# 3 如果有 multirow
|
75
|
-
if 'multirow' in text:
|
76
|
-
n, bigstructs, width, fixup, text = cls.parse_multirow(text, brace_text_only=False)
|
77
|
-
else:
|
78
|
-
n = 1
|
79
|
-
# if isinstance(text, str) and re.match(r'\d+$', text): text = int(text) # 如果可以,直接识别为数字
|
80
|
-
return (n, m), col_align, text
|
81
|
-
|
82
|
-
@classmethod
|
83
|
-
def parse_align(cls, s):
|
84
|
-
r"""解析latex表头的列对齐格式
|
85
|
-
|
86
|
-
latex表头的规则很复杂,这里目前只处理一些较常用的功能点
|
87
|
-
|
88
|
-
:param s: 内容文本
|
89
|
-
:return: 不考虑竖线和一些高级对齐格式,暂时返回一个str
|
90
|
-
长度是表格列数,每个元素是一个字母存储对齐信息(后续可以扩展更细致的对齐格式信息)
|
91
|
-
|
92
|
-
>>> TexTabular.parse_align('{|c|c|c|c|c|c|c|c|c<{}|c|}')
|
93
|
-
'cccccccccc'
|
94
|
-
>>> TexTabular.parse_align('{|c|w{6em}|w{23mm}|w{47mm}|w{22mm}|}')
|
95
|
-
'cwwww'
|
96
|
-
>>> TexTabular.parse_align('cc*{8}{l}')
|
97
|
-
'ccllllllll'
|
98
|
-
>>> TexTabular.parse_align('|c|')
|
99
|
-
'c'
|
100
|
-
>>> TexTabular.parse_align('|c|*{2}{m{38mm}<{\\centering}|}')
|
101
|
-
'cmm'
|
102
|
-
"""
|
103
|
-
# 展开 *{n}{列格式} 模式
|
104
|
-
s = re.sub(r'\*(\d+)', r'*{\1}', s) # 给*数字加上花括号,不然我的匹配会错
|
105
|
-
s = re.sub(r'\*{(\d+)}' + grp_bracket(3, inner=True), lambda m: m.group(2) * int(m.group(1)), s)
|
106
|
-
# 删除其他干扰字符
|
107
|
-
if s[0] == '{' and s[-1] == '}': s = s[1:-1] # 去掉头尾 { }
|
108
|
-
s = re.sub(r'{.*?}', '', s)
|
109
|
-
for char in '|<>!':
|
110
|
-
s = s.replace(char, '')
|
111
|
-
return s
|
112
|
-
|
113
|
-
@classmethod
|
114
|
-
def create_cline(cls, merge_count):
|
115
|
-
r"""
|
116
|
-
:param merge_count: 一个长度等于表格列数的list,第i位的值存储了第i列累计到当前被合并的格子数
|
117
|
-
假设一个3*4的表格,第1、3、4列正常,第2列被合并了
|
118
|
-
那么遍历到第二行时,merge_count为 [0, 2, 0, 0]
|
119
|
-
遍历到第三行时,merge_count 为 [0, 1, 0, 0]
|
120
|
-
:return:
|
121
|
-
|
122
|
-
>>> TexTabular.create_cline([0, 1, 0, 0])
|
123
|
-
'\\cline{1-1} \\cline{3-4}'
|
124
|
-
"""
|
125
|
-
|
126
|
-
s = ''.join([('1' if v else '0') for v in merge_count])
|
127
|
-
if s.count('1') == 0: return '\\hline' # 没有间断,直接用hline命令
|
128
|
-
|
129
|
-
spans = continuous_zero(s) # 注意返回的区间是从0开始编号,左闭右开的
|
130
|
-
li = [f'\\cline{{{span[0] + 1}-{span[1]}}}' for span in spans]
|
131
|
-
return ' '.join(li)
|
132
|
-
|
133
|
-
@classmethod
|
134
|
-
def create_formats(cls, format_count):
|
135
|
-
""" 获得latex表头格式 """
|
136
|
-
|
137
|
-
def count(s):
|
138
|
-
"""列对齐格式统计,返回最终去用的对齐格式"""
|
139
|
-
if not s: return 'l' # 默认左对齐
|
140
|
-
l, c, r = s.count('l'), s.count('c'), s.count('r')
|
141
|
-
if l >= c and l >= r:
|
142
|
-
return 'l'
|
143
|
-
elif c >= l and c >= r:
|
144
|
-
return 'c'
|
145
|
-
else:
|
146
|
-
return 'r'
|
147
|
-
|
148
|
-
formats = [count(x) for x in format_count]
|
149
|
-
return '{|' + '|'.join(formats) + '|}'
|
150
|
-
|
151
|
-
|
152
|
-
def browser_latex(text='请输入...'):
|
153
|
-
from html import escape
|
154
|
-
from pyxllib.text.xmllib import get_jinja_template
|
155
|
-
|
156
|
-
# 致谢:感谢奕本在晓波做的工具基础上,做出的这个简洁版的latex渲染器
|
157
|
-
content = get_jinja_template('latex_editor.html').render(text=escape(text))
|
158
|
-
browser.html(content)
|
1
|
+
#!/usr/bin/env python3
|
2
|
+
# -*- coding: utf-8 -*-
|
3
|
+
# @Author : 陈坤泽
|
4
|
+
# @Email : 877362867@qq.com
|
5
|
+
# @Date : 2021/10/08 22:26
|
6
|
+
|
7
|
+
import re
|
8
|
+
|
9
|
+
from pyxllib.prog.specialist import browser
|
10
|
+
from pyxllib.text.pupil import grp_bracket, continuous_zero
|
11
|
+
|
12
|
+
|
13
|
+
class TexTabular:
|
14
|
+
@classmethod
|
15
|
+
def parse_multirow(cls, s, brace_text_only=True):
|
16
|
+
r"""
|
17
|
+
|
18
|
+
:param brace_text_only: 只取花括号里面的内容
|
19
|
+
如果为False,会把multirow外部的内容做拼接
|
20
|
+
|
21
|
+
multirow 和 multicolumn 的不同是,第1、2个花括号后面可以有可选参数。
|
22
|
+
第2个花括号如果内容是*,可以省略。
|
23
|
+
两个[]的内容先省略,不做分析处理
|
24
|
+
|
25
|
+
注意:这里会取出前后缀内容!业务需要,防止bug,不过这种概率很小
|
26
|
+
|
27
|
+
>>> TexTabular.parse_multirow(r'\multirow{2}*{特点}')
|
28
|
+
(2, None, '*', None, '特点')
|
29
|
+
>>> TexTabular.parse_multirow(r'\multirow{2}{*}{特点}')
|
30
|
+
(2, None, '*', None, '特点')
|
31
|
+
>>> TexTabular.parse_multirow(r'aa\multirow{2}[bla1]{*}[bla2]{特点}bb', brace_text_only=False)
|
32
|
+
(2, 'bla1', '*', 'bla2', 'aa特点bb')
|
33
|
+
|
34
|
+
TODO multirow第一个数字是可以负值的,代表向上合并单元格数,
|
35
|
+
"""
|
36
|
+
square = r'(?:\[(.*?)\])?' # 可选参数
|
37
|
+
m = re.search(r'\\multirow' + grp_bracket(3, inner=True) + square +
|
38
|
+
r'(?:{(.*?)}|(\*))' + square + grp_bracket(5, inner=True), s)
|
39
|
+
if not m: return None
|
40
|
+
n, bigstructs, width1, width2, fixup, text = m.groups()
|
41
|
+
width = width1 or width2
|
42
|
+
if not brace_text_only: text = s[:m.start()] + text + s[m.end():]
|
43
|
+
# if re.match(r'\d+$', text): text = int(text) # 如果可以,直接识别为数字
|
44
|
+
|
45
|
+
n = int(n)
|
46
|
+
if -1 <= n <= 1:
|
47
|
+
n = 1
|
48
|
+
elif n > 1:
|
49
|
+
pass
|
50
|
+
else:
|
51
|
+
raise ValueError(f'{s} 不支持解析multirow第一个值为负数,向上合并单元格的情况')
|
52
|
+
|
53
|
+
return n, bigstructs, width, fixup, text
|
54
|
+
|
55
|
+
@classmethod
|
56
|
+
def parse_multicolumn(cls, s):
|
57
|
+
r"""找出s中第一次出现的满足模式的multicolumn,返回3个关键值
|
58
|
+
|
59
|
+
:returns:
|
60
|
+
第1个参数是该合并单元格的尺寸,固定格式: (行数, 列数),只有一行是也会写'1'
|
61
|
+
|
62
|
+
>>> TexTabular.parse_multicolumn(r'\multicolumn{2}{|c|}{aa\multirow{3}*{特点}bb}')
|
63
|
+
((3, 2), '|c|', 'aa特点bb')
|
64
|
+
"""
|
65
|
+
# 1 基本的模式匹配抓取
|
66
|
+
m = re.search(r'\\multicolumn' + grp_bracket(3, inner=True) * 2
|
67
|
+
+ grp_bracket(5, inner=True), s) # 最后层多套下,我怕不够用
|
68
|
+
if not m: return None
|
69
|
+
|
70
|
+
# 2 取出参数值
|
71
|
+
m, col_align, text = m.groups()
|
72
|
+
m = int(m)
|
73
|
+
|
74
|
+
# 3 如果有 multirow
|
75
|
+
if 'multirow' in text:
|
76
|
+
n, bigstructs, width, fixup, text = cls.parse_multirow(text, brace_text_only=False)
|
77
|
+
else:
|
78
|
+
n = 1
|
79
|
+
# if isinstance(text, str) and re.match(r'\d+$', text): text = int(text) # 如果可以,直接识别为数字
|
80
|
+
return (n, m), col_align, text
|
81
|
+
|
82
|
+
@classmethod
|
83
|
+
def parse_align(cls, s):
|
84
|
+
r"""解析latex表头的列对齐格式
|
85
|
+
|
86
|
+
latex表头的规则很复杂,这里目前只处理一些较常用的功能点
|
87
|
+
|
88
|
+
:param s: 内容文本
|
89
|
+
:return: 不考虑竖线和一些高级对齐格式,暂时返回一个str
|
90
|
+
长度是表格列数,每个元素是一个字母存储对齐信息(后续可以扩展更细致的对齐格式信息)
|
91
|
+
|
92
|
+
>>> TexTabular.parse_align('{|c|c|c|c|c|c|c|c|c<{}|c|}')
|
93
|
+
'cccccccccc'
|
94
|
+
>>> TexTabular.parse_align('{|c|w{6em}|w{23mm}|w{47mm}|w{22mm}|}')
|
95
|
+
'cwwww'
|
96
|
+
>>> TexTabular.parse_align('cc*{8}{l}')
|
97
|
+
'ccllllllll'
|
98
|
+
>>> TexTabular.parse_align('|c|')
|
99
|
+
'c'
|
100
|
+
>>> TexTabular.parse_align('|c|*{2}{m{38mm}<{\\centering}|}')
|
101
|
+
'cmm'
|
102
|
+
"""
|
103
|
+
# 展开 *{n}{列格式} 模式
|
104
|
+
s = re.sub(r'\*(\d+)', r'*{\1}', s) # 给*数字加上花括号,不然我的匹配会错
|
105
|
+
s = re.sub(r'\*{(\d+)}' + grp_bracket(3, inner=True), lambda m: m.group(2) * int(m.group(1)), s)
|
106
|
+
# 删除其他干扰字符
|
107
|
+
if s[0] == '{' and s[-1] == '}': s = s[1:-1] # 去掉头尾 { }
|
108
|
+
s = re.sub(r'{.*?}', '', s)
|
109
|
+
for char in '|<>!':
|
110
|
+
s = s.replace(char, '')
|
111
|
+
return s
|
112
|
+
|
113
|
+
@classmethod
|
114
|
+
def create_cline(cls, merge_count):
|
115
|
+
r"""
|
116
|
+
:param merge_count: 一个长度等于表格列数的list,第i位的值存储了第i列累计到当前被合并的格子数
|
117
|
+
假设一个3*4的表格,第1、3、4列正常,第2列被合并了
|
118
|
+
那么遍历到第二行时,merge_count为 [0, 2, 0, 0]
|
119
|
+
遍历到第三行时,merge_count 为 [0, 1, 0, 0]
|
120
|
+
:return:
|
121
|
+
|
122
|
+
>>> TexTabular.create_cline([0, 1, 0, 0])
|
123
|
+
'\\cline{1-1} \\cline{3-4}'
|
124
|
+
"""
|
125
|
+
|
126
|
+
s = ''.join([('1' if v else '0') for v in merge_count])
|
127
|
+
if s.count('1') == 0: return '\\hline' # 没有间断,直接用hline命令
|
128
|
+
|
129
|
+
spans = continuous_zero(s) # 注意返回的区间是从0开始编号,左闭右开的
|
130
|
+
li = [f'\\cline{{{span[0] + 1}-{span[1]}}}' for span in spans]
|
131
|
+
return ' '.join(li)
|
132
|
+
|
133
|
+
@classmethod
|
134
|
+
def create_formats(cls, format_count):
|
135
|
+
""" 获得latex表头格式 """
|
136
|
+
|
137
|
+
def count(s):
|
138
|
+
"""列对齐格式统计,返回最终去用的对齐格式"""
|
139
|
+
if not s: return 'l' # 默认左对齐
|
140
|
+
l, c, r = s.count('l'), s.count('c'), s.count('r')
|
141
|
+
if l >= c and l >= r:
|
142
|
+
return 'l'
|
143
|
+
elif c >= l and c >= r:
|
144
|
+
return 'c'
|
145
|
+
else:
|
146
|
+
return 'r'
|
147
|
+
|
148
|
+
formats = [count(x) for x in format_count]
|
149
|
+
return '{|' + '|'.join(formats) + '|}'
|
150
|
+
|
151
|
+
|
152
|
+
def browser_latex(text='请输入...'):
|
153
|
+
from html import escape
|
154
|
+
from pyxllib.text.xmllib import get_jinja_template
|
155
|
+
|
156
|
+
# 致谢:感谢奕本在晓波做的工具基础上,做出的这个简洁版的latex渲染器
|
157
|
+
content = get_jinja_template('latex_editor.html').render(text=escape(text))
|
158
|
+
browser.html(content)
|