diff --git a/tessdata_fast-4.0.0-part1.tar.gz b/tessdata_fast-4.0.0-part1.tar.gz new file mode 100644 index 0000000..858cdde Binary files /dev/null and b/tessdata_fast-4.0.0-part1.tar.gz differ diff --git a/tessdata_fast-4.0.0-part2.tar.gz b/tessdata_fast-4.0.0-part2.tar.gz new file mode 100644 index 0000000..3452ab1 Binary files /dev/null and b/tessdata_fast-4.0.0-part2.tar.gz differ diff --git a/tessdata_fast-script-part1.tar.gz b/tessdata_fast-script-part1.tar.gz new file mode 100644 index 0000000..b5ea96a Binary files /dev/null and b/tessdata_fast-script-part1.tar.gz differ diff --git a/tessdata_fast-script-part2.tar.gz b/tessdata_fast-script-part2.tar.gz new file mode 100644 index 0000000..b1563b0 Binary files /dev/null and b/tessdata_fast-script-part2.tar.gz differ diff --git a/tesseract-tessdata.spec b/tesseract-tessdata.spec new file mode 100644 index 0000000..1b85bf7 --- /dev/null +++ b/tesseract-tessdata.spec @@ -0,0 +1,252 @@ +Name: tesseract-tessdata +Version: 4.0.0 +Release: 1 +Summary: Trained models for the Tesseract Open Source OCR Engine +BuildArch: noarch +License: Apache 2.0 +URL: https://github.com/tesseract-ocr/tessdata_fast +# Source 0, 1, 2, 3 is from https://github.com/tesseract-ocr/tessdata_fast/archive/%{version}/tessdata_fast-%{version}.tar.gz +# we split it to 4 parts beacuse the size of tarball is over 100mb. +Source0: tessdata_fast-4.0.0-part1.tar.gz +Source1: tessdata_fast-4.0.0-part2.tar.gz +Source2: tessdata_fast-script-part1.tar.gz +Source3: tessdata_fast-script-part2.tar.gz + +%description +This package contains fast integer versions of trained models for the Tesseract +Open Source OCR Engine. +These models only work with the LSTM OCR engine of Tesseract 4. + +%package doc +Summary: Documentation for %{name} +%description doc +The %{name}-doc package contains the documentation for %{name}. + +%package -n tesseract-osd +Summary: Orientation & Script Detection Data for tesseract +BuildArch: noarch +Requires: tesseract %{name}-doc = %{version}-%{release} +%description -n tesseract-osd +Orientation & Script Detection data for the Tesseract Open Source OCR Engine. +%define lang_subpkg(l:m:n:) \ +%define macrolang %{-m:%{-m*}}%{!-m:%{error:3 letter Language code not defined}} \ +%define langcode %{-l:%{-l*}}%{!-l:%{error:Language code not defined}} \ +%define langname %{-n:%{-n*}}%{!-n:%{error:Language name not defined}} \ +\ +%package -n tesseract-langpack-%{macrolang}\ +Summary: %{langname} language data for %{name}\ +BuildArch: noarch\ +Requires: tesseract\ %{name}-doc = %{version}-%{release}\ +%{-l:Provides: %{name}-langpack-%{langcode} = %{version}-%{release}\ +Supplements: (tesseract and langpacks-%{langcode})}\ +\ +%description -n tesseract-langpack-%{macrolang}\ +This package contains the fast integer version of the %{langname} language \ +trained models for the Tesseract Open Source OCR Engine.\ +\ +%files -n tesseract-langpack-%{macrolang}\ +%{_datadir}/tesseract/tessdata/%{macrolang}.* +%define script_subpkg(s:n:) \ +%define scriptname %{-s:%{-s*}}%{!-s:%{error:Script name defined}} \ +%define filename %{-n:%{-n*}}%{!-n:%{error:Package name not defined}} \ +%define pkgname %(echo %filename | tr '[:upper:]' '[:lower:]') \ +\ +%package -n tesseract-script-%{pkgname}\ +Summary: %{scriptname} script data for %{name}\ +BuildArch: noarch\ +Requires: tesseract\ %{name}-doc = %{version}-%{release}\ +\ +%description -n tesseract-script-%{pkgname}\ +This package contains the fast integer version of the %{scriptname} script \ +trained models for the Tesseract Open Source OCR Engine.\ +\ +%files -n tesseract-script-%{pkgname}\ +%dir %{_datadir}/tesseract/tessdata/script/\ +%{_datadir}/tesseract/tessdata/script/%{filename}.* + +%lang_subpkg -m afr -l af -n Afrikaans +%lang_subpkg -m amh -l an -n Amharic +%lang_subpkg -m ara -l ar -n Arabic +%lang_subpkg -m asm -l as -n Assamese +%lang_subpkg -m aze -l az -n Azerbaijani +%lang_subpkg -m aze_cyrl -n %{quote:Azerbaijani (Cyrillic)} +%lang_subpkg -m bel -l bel -n Belarusian +%lang_subpkg -m ben -l bn -n Bengali +%lang_subpkg -m bod -l bo -n %{quote:Tibetan (Standard)} +%lang_subpkg -m bos -l bs -n Bosnian +%lang_subpkg -m bre -l br -n Breton +%lang_subpkg -m bul -l bg -n Bulgarian +%lang_subpkg -m cat -l ca -n Catalan +%lang_subpkg -m ceb -n Cebuano +%lang_subpkg -m ces -l cs -n Czech +%lang_subpkg -m chi_sim -l zh_CN -n %{quote:Chinese (Simplified)} +%lang_subpkg -m chi_sim_vert -l zh_CN -n %{quote:Chinese (Simplified, Vertical)} +%lang_subpkg -m chi_tra -l zh_TW -n %{quote:Chinese (Traditional)} +%lang_subpkg -m chi_tra_vert -l zh_TW -n %{quote:Chinese (Traditional, Vertical)} +%lang_subpkg -m chr -n Cherokee +%lang_subpkg -m cos -l co -n Corsican +%lang_subpkg -m cym -l cy -n Welsh +%lang_subpkg -m dan -l da -n Danish +%lang_subpkg -m deu -l de -n German +%lang_subpkg -m div -l dv -n %{quote:Dhivehi; Maldivian} +%lang_subpkg -m dzo -n Dzongkha +%lang_subpkg -m ell -l el -n Greek +%lang_subpkg -m eng -n English +%lang_subpkg -m enm -n %{quote:Middle English (1100-1500)} +%lang_subpkg -m epo -l eo -n Esperanto +%lang_subpkg -m est -l et -n Estonian +%lang_subpkg -m eus -l eu -n Basque +%lang_subpkg -m fao -l fo -n %{quote:Faroese} +%lang_subpkg -m fas -l fa -n %{quote:Persian (Farsi)} +%lang_subpkg -m fil -n %{quote:Filipino; Pilipino} +%lang_subpkg -m fin -l fi -n Finnish +%lang_subpkg -m fra -l fr -n French +%lang_subpkg -m frk -n Fraktur +%lang_subpkg -m frm -n %{quote:Middle French (ca. 1400-1600)} +%lang_subpkg -m fry -l fy -n %{quote:Western Frisian} +%lang_subpkg -m gla -l gd -n %{quote:Gaelic; Scottish Gaelic} +%lang_subpkg -m gle -l ga -n Irish +%lang_subpkg -m glg -l gl -n Galician +%lang_subpkg -m grc -n %{quote:Ancient Greek} +%lang_subpkg -m guj -l gu -n Gujarati +%lang_subpkg -m hat -l ht -n Haitian +%lang_subpkg -m heb -l he -n Hebrew +%lang_subpkg -m hin -l hi -n Hindi +%lang_subpkg -m hrv -l hr -n Croatian +%lang_subpkg -m hun -l hu -n Hungarian +%lang_subpkg -m hye -l hy -n Armenian +%lang_subpkg -m iku -l iu -n Inuktitut +%lang_subpkg -m ind -l id -n Indonesian +%lang_subpkg -m isl -l is -n Icelandic +%lang_subpkg -m ita -l it -n Italian +%lang_subpkg -m ita_old -n %{quote:Italian (Old)} +%lang_subpkg -m jav -l jav -n Javanese +%lang_subpkg -m jpn -l ja -n Japanese +%lang_subpkg -m jpn_vert -l ja -n "Japanese (Vertical)" +%lang_subpkg -m kan -l kn -n Kannada +%lang_subpkg -m kat -l ka -n Georgian +%lang_subpkg -m kat_old -n %{quote:Georgian (Old)} +%lang_subpkg -m kaz -l kk -n Kazakh +%lang_subpkg -m khm -l km -n Khmer +%lang_subpkg -m kir -l ky -n Kyrgyz +%lang_subpkg -m kor -l ko -n Korean +%lang_subpkg -m kor_vert -l ko -n "Korean (Vertical)" +%lang_subpkg -m kmr -l ku -n Kurmanji +%lang_subpkg -m lao -l lo -n Lao +%lang_subpkg -m lat -l lat -n Latin +%lang_subpkg -m lav -l lv -n Latvian +%lang_subpkg -m lit -l lt -n Lithuanian +%lang_subpkg -m ltz -l lb -n Luxembourgish +%lang_subpkg -m mal -l ml -n Malayalam +%lang_subpkg -m mar -l mr -n Marathi +%lang_subpkg -m mkd -l mk -n Macedonian +%lang_subpkg -m mlt -l mt -n Maltese +%lang_subpkg -m mon -l mn -n Mongolian +%lang_subpkg -m mri -l mi -n Maori +%lang_subpkg -m msa -l ms -n Malay +%lang_subpkg -m mya -l my -n Burmese +%lang_subpkg -m nep -l ne -n Nepali +%lang_subpkg -m nld -l nl -n Dutch +%lang_subpkg -m nor -l no -n Norwegian +%lang_subpkg -m oci -l oc -n Occitan +%lang_subpkg -m ori -l or -n Oriya +%lang_subpkg -m pan -l pa -n Panjabi +%lang_subpkg -m pol -l pl -n Polish +%lang_subpkg -m por -l pt -n Portuguese +%lang_subpkg -m pus -l ps -n Pashto +%lang_subpkg -m que -l qu -n Quechuan +%lang_subpkg -m ron -l ro -n Romanian +%lang_subpkg -m rus -l ru -n Russian +%lang_subpkg -m san -l sa -n Sanskrit +%lang_subpkg -m sin -l si -n Sinhala +%lang_subpkg -m slk -l sk -n Slovakian +%lang_subpkg -m slv -l sl -n Slovenian +%lang_subpkg -m snd -l sd -n Sindhi +%lang_subpkg -m spa -l es -n Spanish +%lang_subpkg -m spa_old -n %{quote:Spanish (Old)} +%lang_subpkg -m sqi -l sq -n Albanian +%lang_subpkg -m srp -l sr -n Serbian +%lang_subpkg -m srp_latn -n %{quote:Serbian (Latin)} +%lang_subpkg -m sun -l su -n Sundanese +%lang_subpkg -m swa -l sw -n Swahili +%lang_subpkg -m swe -l sv -n Swedish +%lang_subpkg -m syr -l ar_SY -n Syriac +%lang_subpkg -m tam -l ta -n Tamil +%lang_subpkg -m tat -l tt -n Tatar +%lang_subpkg -m tel -l te -n Telugu +%lang_subpkg -m tgk -l tg -n Tajik +%lang_subpkg -m tha -l th -n Thai +%lang_subpkg -m tir -l ti -n Tigrinya +%lang_subpkg -m ton -l to -n Tongan +%lang_subpkg -m tur -l tr -n Turkish +%lang_subpkg -m uig -l ug -n Uyghur +%lang_subpkg -m ukr -l uk -n Ukrainian +%lang_subpkg -m urd -l ur -n Urdu +%lang_subpkg -m uzb -l uz -n Uzbek +%lang_subpkg -m uzb_cyrl -n %{quote:Uzbek (Cyrillic)} +%lang_subpkg -m vie -l vi -n Vietnamese +%lang_subpkg -m yid -l yi -n Yiddish +%lang_subpkg -m yor -l yo -n Yoruba + +%script_subpkg -n Arabic -s Arabic +%script_subpkg -n Armenian -s Armenian +%script_subpkg -n Bengali -s Bengali +%script_subpkg -n Canadian_Aboriginal -s %{quote:Canadian (Aboriginal)} +%script_subpkg -n Cherokee -s Cherokee +%script_subpkg -n Cyrillic -s Cyrillic +%script_subpkg -n Devanagari -s Devanagari +%script_subpkg -n Ethiopic -s Ethiopic +%script_subpkg -n Fraktur -s Fraktur +%script_subpkg -n Georgian -s Georgian +%script_subpkg -n Greek -s Greek +%script_subpkg -n Gujarati -s Gujarati +%script_subpkg -n Gurmukhi -s Gurmukhi +%script_subpkg -n HanS -s %{quote:Han (Simplified)} +%script_subpkg -n HanS_vert -s %{quote:Han (Simplified, Vertical)} +%script_subpkg -n HanT -s %{quote:Han (Traditional)} +%script_subpkg -n HanT_vert -s %{quote:Han (Traditional, Vertical)} +%script_subpkg -n Hangul -s Hangul +%script_subpkg -n Hangul_vert -s %{quote:Hangul (Vertical)} +%script_subpkg -n Hebrew -s Hebrew +%script_subpkg -n Japanese -s Japanese +%script_subpkg -n Japanese_vert -s %{quote:Japanese (Vertical)} +%script_subpkg -n Kannada -s Kannada +%script_subpkg -n Khmer -s Khmer +%script_subpkg -n Lao -s Lao +%script_subpkg -n Latin -s Latin +%script_subpkg -n Malayalam -s Malayalam +%script_subpkg -n Myanmar -s Myanmar +%script_subpkg -n Oriya -s Oriya +%script_subpkg -n Sinhala -s Sinhala +%script_subpkg -n Syriac -s Syriac +%script_subpkg -n Tamil -s Tamil +%script_subpkg -n Telugu -s Telugu +%script_subpkg -n Thaana -s Thaana +%script_subpkg -n Thai -s Thai +%script_subpkg -n Tibetan -s Tibetan +%script_subpkg -n Vietnamese -s Vietnamese + +%prep +%setup -n tessdata_fast-%{version} -a 2 -a 3 +cd ../ +tar -xf %{SOURCE1} +cd - + +%build + +%install +mkdir -p %{buildroot}/%{_datadir}/tesseract/tessdata/ +cp -a * %{buildroot}/%{_datadir}/tesseract/tessdata/ +rm -f %{buildroot}/%{_datadir}/tesseract/tessdata/COPYING +rm -f %{buildroot}/%{_datadir}/tesseract/tessdata/README.md + +%files doc +%license COPYING +%doc README.md + +%files -n tesseract-osd +%{_datadir}/tesseract/tessdata/osd.traineddata + +%changelog +* Sat Jan 9 2021 chengzihan - 4.0.0-1 +- Package init