Disable binarization for old ocr service versions. Add new ocr service version (including binarization)

This commit is contained in:
Patrick Jentsch 2022-04-13 16:39:51 +02:00
parent 43ea898394
commit d35ca7c261
3 changed files with 148 additions and 25 deletions

View File

@ -10,6 +10,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Amharic'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/amh.traineddata'
@ -22,6 +23,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
- title: 'Arabic'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ara.traineddata'
@ -34,6 +36,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
# - title: 'Assamese'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/asm.traineddata'
@ -46,6 +49,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Azerbaijani'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/aze.traineddata'
@ -58,6 +62,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Azerbaijani - Cyrillic'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/aze_cyrl.traineddata'
@ -70,6 +75,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Belarusian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/bel.traineddata'
@ -82,6 +88,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Bengali'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ben.traineddata'
@ -94,6 +101,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Tibetan'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/bod.traineddata'
@ -106,6 +114,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Bosnian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/bos.traineddata'
@ -118,6 +127,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Bulgarian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/bul.traineddata'
@ -130,6 +140,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Catalan; Valencian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/cat.traineddata'
@ -142,6 +153,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Cebuano'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ceb.traineddata'
@ -154,6 +166,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Czech'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ces.traineddata'
@ -166,6 +179,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Chinese - Simplified'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/chi_sim.traineddata'
@ -178,6 +192,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
- title: 'Chinese - Traditional'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/chi_tra.traineddata'
@ -190,6 +205,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
# - title: 'Cherokee'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/chr.traineddata'
@ -202,6 +218,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Welsh'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/cym.traineddata'
@ -214,6 +231,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
- title: 'Danish'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/dan.traineddata'
@ -226,6 +244,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
- title: 'German'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/deu.traineddata'
@ -238,6 +257,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
# - title: 'Dzongkha'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/dzo.traineddata'
@ -250,6 +270,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
- title: 'Greek, Modern (1453-)'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ell.traineddata'
@ -262,6 +283,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
- title: 'English'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/eng.traineddata'
@ -274,6 +296,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
- title: 'English, Middle (1100-1500)'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/enm.traineddata'
@ -286,6 +309,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
# - title: 'Esperanto'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/epo.traineddata'
@ -298,6 +322,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Estonian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/est.traineddata'
@ -310,6 +335,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Basque'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/eus.traineddata'
@ -322,6 +348,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Persian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/fas.traineddata'
@ -334,6 +361,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Finnish'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/fin.traineddata'
@ -346,6 +374,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
- title: 'French'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/fra.traineddata'
@ -358,6 +387,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
- title: 'German Fraktur'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/frk.traineddata'
@ -370,6 +400,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
- title: 'French, Middle (ca. 1400-1600)'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/frm.traineddata'
@ -382,6 +413,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
# - title: 'Irish'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/gle.traineddata'
@ -394,6 +426,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Galician'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/glg.traineddata'
@ -406,6 +439,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
- title: 'Greek, Ancient (-1453)'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/grc.traineddata'
@ -418,6 +452,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
# - title: 'Gujarati'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/guj.traineddata'
@ -430,6 +465,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Haitian; Haitian Creole'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/hat.traineddata'
@ -442,6 +478,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Hebrew'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/heb.traineddata'
@ -454,6 +491,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Hindi'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/hin.traineddata'
@ -466,6 +504,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Croatian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/hrv.traineddata'
@ -478,6 +517,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Hungarian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/hun.traineddata'
@ -490,6 +530,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Inuktitut'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/iku.traineddata'
@ -502,6 +543,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Indonesian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ind.traineddata'
@ -514,6 +556,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Icelandic'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/isl.traineddata'
@ -526,6 +569,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
- title: 'Italian'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ita.traineddata'
@ -538,6 +582,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
- title: 'Italian - Old'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ita_old.traineddata'
@ -550,6 +595,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
# - title: 'Javanese'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/jav.traineddata'
@ -562,6 +608,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Japanese'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/jpn.traineddata'
@ -574,6 +621,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Kannada'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kan.traineddata'
@ -586,6 +634,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Georgian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kat.traineddata'
@ -598,6 +647,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Georgian - Old'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kat_old.traineddata'
@ -610,6 +660,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Kazakh'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kaz.traineddata'
@ -622,6 +673,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Central Khmer'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/khm.traineddata'
@ -634,6 +686,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Kirghiz; Kyrgyz'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kir.traineddata'
@ -646,6 +699,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Korean'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kor.traineddata'
@ -658,6 +712,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Kurdish'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/kur.traineddata'
@ -670,6 +725,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Lao'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/lao.traineddata'
@ -682,6 +738,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Latin'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/lat.traineddata'
@ -694,6 +751,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Latvian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/lav.traineddata'
@ -706,6 +764,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Lithuanian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/lit.traineddata'
@ -718,6 +777,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Malayalam'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/mal.traineddata'
@ -730,6 +790,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Marathi'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/mar.traineddata'
@ -742,6 +803,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Macedonian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/mkd.traineddata'
@ -754,6 +816,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Maltese'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/mlt.traineddata'
@ -766,6 +829,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Malay'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/msa.traineddata'
@ -778,6 +842,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Burmese'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/mya.traineddata'
@ -790,6 +855,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Nepali'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/nep.traineddata'
@ -802,6 +868,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Dutch; Flemish'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/nld.traineddata'
@ -814,6 +881,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Norwegian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/nor.traineddata'
@ -826,6 +894,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Oriya'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ori.traineddata'
@ -838,6 +907,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Panjabi; Punjabi'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/pan.traineddata'
@ -850,6 +920,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Polish'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/pol.traineddata'
@ -862,6 +933,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
- title: 'Portuguese'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/por.traineddata'
@ -874,6 +946,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
# - title: 'Pushto; Pashto'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/pus.traineddata'
@ -886,6 +959,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Romanian; Moldavian; Moldovan'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ron.traineddata'
@ -898,6 +972,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
- title: 'Russian'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/rus.traineddata'
@ -910,6 +985,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
# - title: 'Sanskrit'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/san.traineddata'
@ -922,6 +998,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Sinhala; Sinhalese'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/sin.traineddata'
@ -934,6 +1011,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Slovak'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/slk.traineddata'
@ -946,6 +1024,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Slovenian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/slv.traineddata'
@ -958,6 +1037,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
- title: 'Spanish; Castilian'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/spa.traineddata'
@ -970,6 +1050,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
- title: 'Spanish; Castilian - Old'
description: ''
url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/spa_old.traineddata'
@ -982,6 +1063,7 @@
- '0.1.2'
- '0.1.3'
- '0.1.4'
- '0.1.5'
# - title: 'Albanian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/sqi.traineddata'
@ -994,6 +1076,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Serbian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/srp.traineddata'
@ -1006,6 +1089,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Serbian - Latin'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/srp_latn.traineddata'
@ -1018,6 +1102,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Swahili'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/swa.traineddata'
@ -1030,6 +1115,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Swedish'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/swe.traineddata'
@ -1042,6 +1128,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Syriac'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/syr.traineddata'
@ -1054,6 +1141,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Tamil'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tam.traineddata'
@ -1066,6 +1154,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Telugu'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tel.traineddata'
@ -1078,6 +1167,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Tajik'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tgk.traineddata'
@ -1090,6 +1180,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Tagalog'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tgl.traineddata'
@ -1102,6 +1193,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Thai'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tha.traineddata'
@ -1114,6 +1206,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Tigrinya'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tir.traineddata'
@ -1126,6 +1219,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Turkish'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/tur.traineddata'
@ -1138,6 +1232,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Uighur; Uyghur'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/uig.traineddata'
@ -1150,6 +1245,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Ukrainian'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/ukr.traineddata'
@ -1162,6 +1258,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Urdu'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/urd.traineddata'
@ -1174,6 +1271,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Uzbek'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/uzb.traineddata'
@ -1186,6 +1284,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Uzbek - Cyrillic'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/uzb_cyrl.traineddata'
@ -1198,6 +1297,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Vietnamese'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/vie.traineddata'
@ -1210,6 +1310,7 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'
# - title: 'Yiddish'
# description: ''
# url: 'https://github.com/tesseract-ocr/tessdata/raw/4.1.0/yid.traineddata'
@ -1222,3 +1323,4 @@
# - '0.1.2'
# - '0.1.3'
# - '0.1.4'
# - '0.1.5'

View File

@ -46,7 +46,11 @@ class AddTesseractOCRPipelineJobForm(AddJobForm):
def validate_binarization(self, field):
service_info = SERVICES['tesseract-ocr-pipeline']['versions'][self.version.data]
if field.data and 'binarization' not in service_info['methods']:
if field.data:
if(
'methods' not in service_info
or 'binarization' not in service_info['methods']
):
raise ValidationError('Binarization is not available')
def validate_pdf(self, field):
@ -58,8 +62,13 @@ class AddTesseractOCRPipelineJobForm(AddJobForm):
version = kwargs.pop('version', service_manifest['latest_version'])
super().__init__(*args, **kwargs)
service_info = service_manifest['versions'][version]
if 'binarization' not in service_info['methods']:
self.binarization.render_kw = {'disabled': True}
if self.binarization.render_kw is None:
self.binarization.render_kw = {}
self.binarization.render_kw['disabled'] = True
if 'methods' in service_info:
if 'binarization' in service_info['methods']:
if 'disabled' in self.binarization.render_kw:
del self.binarization.render_kw['disabled']
compatible_models = [
x for x in TesseractOCRModel.query.filter_by(shared=True).all()
if version in x.compatible_service_versions
@ -83,7 +92,11 @@ class AddTranskribusHTRPipelineJobForm(AddJobForm):
def validate_binarization(self, field):
service_info = SERVICES['transkribus-htr-pipeline']['versions'][self.version.data]
if field.data and 'binarization' not in service_info['methods']:
if field.data:
if(
'methods' not in service_info
or 'binarization' not in service_info['methods']
):
raise ValidationError('Binarization is not available')
def validate_pdf(self, field):
@ -95,8 +108,13 @@ class AddTranskribusHTRPipelineJobForm(AddJobForm):
version = kwargs.pop('version', service_manifest['latest_version'])
super().__init__(*args, **kwargs)
service_info = service_manifest['versions'][version]
if 'binarization' not in service_info['methods']:
self.binarization.render_kw = {'disabled': True}
if self.binarization.render_kw is None:
self.binarization.render_kw = {}
self.binarization.render_kw['disabled'] = True
if 'methods' in service_info:
if 'binarization' in service_info['methods']:
if 'disabled' in self.binarization.render_kw:
del self.binarization.render_kw['disabled']
self.model.choices = [('', 'Choose your option')]
self.model.choices += [
('37569', 'Tim Model'),
@ -109,15 +127,18 @@ class AddTranskribusHTRPipelineJobForm(AddJobForm):
class AddSpacyNLPPipelineJobForm(AddJobForm):
encoding_detection = BooleanField('Encoding detection')
encoding_detection = BooleanField('Encoding detection', render_kw={'disabled': True})
txt = FileField('File', validators=[FileRequired()])
model = SelectField('Model', validators=[DataRequired()])
def validate_encoding_detection(self, field):
service_manifest = SERVICES['spacy-nlp-pipeline']
service_info = service_manifest['versions'][self.version.data]
if field.data and 'encoding_detection' not in service_info['methods']:
raise ValidationError('Encoding detection is not available!')
service_info = SERVICES['spacy-nlp-pipeline']['versions'][self.version.data]
if field.data:
if(
'methods' not in service_info
or 'encoding_detection' not in service_info['methods']
):
raise ValidationError('Encoding detection is not available')
def validate_txt(form, field):
if field.data.mimetype != 'text/plain':
@ -128,8 +149,13 @@ class AddSpacyNLPPipelineJobForm(AddJobForm):
version = kwargs.pop('version', service_manifest['latest_version'])
super().__init__(*args, **kwargs)
service_info = service_manifest['versions'][version]
if 'encoding_detection' not in service_info['methods']:
self.encoding_detection.render_kw = {'disabled': True}
if self.encoding_detection.render_kw is None:
self.encoding_detection.render_kw = {}
self.encoding_detection.render_kw['disabled'] = True
if 'methods' in service_info:
if 'encoding_detection' in service_info['methods']:
if 'disabled' in self.encoding_detection.render_kw:
del self.encoding_detection.render_kw['disabled']
self.model.choices = [('', 'Choose your option')]
self.model.choices += [(x, y) for x, y in service_info['models'].items()] # noqa
self.model.default = ''

View File

@ -10,33 +10,28 @@ file-setup-pipeline:
tesseract-ocr-pipeline:
name: 'Tesseract OCR Pipeline'
publisher: 'Bielefeld University - CRC 1288 - INF'
latest_version: '0.1.4'
latest_version: '0.1.5'
versions:
0.1.0:
methods:
- 'binarization'
publishing_year: 2022
url: 'https://gitlab.ub.uni-bielefeld.de/sfb1288inf/tesseract-ocr-pipeline/-/releases/v0.1.0'
0.1.1:
methods:
- 'binarization'
publishing_year: 2022
url: 'https://gitlab.ub.uni-bielefeld.de/sfb1288inf/tesseract-ocr-pipeline/-/releases/v0.1.1'
0.1.2:
methods:
- 'binarization'
publishing_year: 2022
url: 'https://gitlab.ub.uni-bielefeld.de/sfb1288inf/tesseract-ocr-pipeline/-/releases/v0.1.2'
0.1.3:
methods:
- 'binarization'
publishing_year: 2022
url: 'https://gitlab.ub.uni-bielefeld.de/sfb1288inf/tesseract-ocr-pipeline/-/releases/v0.1.3'
0.1.4:
publishing_year: 2022
url: 'https://gitlab.ub.uni-bielefeld.de/sfb1288inf/tesseract-ocr-pipeline/-/releases/v0.1.4'
0.1.5:
methods:
- 'binarization'
publishing_year: 2022
url: 'https://gitlab.ub.uni-bielefeld.de/sfb1288inf/tesseract-ocr-pipeline/-/releases/v0.1.4'
url: 'https://gitlab.ub.uni-bielefeld.de/sfb1288inf/tesseract-ocr-pipeline/-/releases/v0.1.5'
transkribus-htr-pipeline:
name: 'Transkribus HTR Pipeline'
publisher: 'Bielefeld University - CRC 1288 - INF'