diff --git a/.gitignore b/.gitignore index efbe08d..238adc0 100644 --- a/.gitignore +++ b/.gitignore @@ -19,3 +19,4 @@ tesseract-2.00.eng.tar.gz /tesseract-4.1.0.tar.gz /tesseract-4.1.1.tar.gz /tesseract-4.1.3.tar.gz +/tesseract-5.0.0.tar.gz diff --git a/sources b/sources index d567a4f..3608b38 100644 --- a/sources +++ b/sources @@ -1 +1 @@ -SHA512 (tesseract-4.1.3.tar.gz) = 16b3813cb287f0ccf72ab66f36e140cc55f80a0a7b1fad319649110e60e85dea97dd59558644535592df1018f981aae69ca84175d04654d6a96ac46fd2acf748 +SHA512 (tesseract-5.0.0.tar.gz) = 80e0d6e9076eb8d6b0d99942586acbb43aaec7bee7f7b13a500470aa11bf03f1c128434d764abd67839355e3fb80d41d0bcf10400b33e57fa0ae4659adb42af9 diff --git a/tesseract.spec b/tesseract.spec index 0cd9430..740a073 100644 --- a/tesseract.spec +++ b/tesseract.spec @@ -1,7 +1,7 @@ #global pre beta.4 Name: tesseract -Version: 4.1.3 +Version: 5.0.0 Release: 1%{?pre:.%pre}%{?dist} Summary: Raw OCR Engine @@ -9,12 +9,11 @@ License: ASL 2.0 URL: https://github.com/tesseract-ocr/%{name} Source0: https://github.com/tesseract-ocr/tesseract/archive/%{version}%{?pre:-%pre}/%{name}-%{version}%{?pre:-%pre}.tar.gz -# Tweak location of tessdata folder -Patch0: tesseract_datadir.patch +# Expose symbol used when linking dawg2wordlist +Patch0: tesseract_api.patch +BuildRequires: cmake BuildRequires: make -BuildRequires: automake -BuildRequires: autoconf-archive BuildRequires: gcc-c++ BuildRequires: libtool BuildRequires: libtiff-devel @@ -54,21 +53,17 @@ The %{name}-tools package contains tools for training %{name}. %build -autoreconf -ifv -%configure --disable-static - -%make_build -%make_build training +%cmake \ + -DUSE_SYSTEM_ICU=ON \ + -DENABLE_LTO=ON \ + -DTESSDATA_PREFIX=%{_datadir}/%{name} \ + -DCMAKE_INSTALL_LIBDIR=%{_lib} +%cmake_build %install -%make_install -%make_install training-install - -find %{buildroot}%{_libdir} -type f -name '*.la' -delete - -# Create directory for tessdata -mkdir -p %{buildroot}/%{_datadir}/%{name}/tessdata/ +%cmake_install +mkdir -p %{buildroot}%{_datadir}/%{name}/tessdata %files @@ -77,14 +72,12 @@ mkdir -p %{buildroot}/%{_datadir}/%{name}/tessdata/ %{_bindir}/%{name} %dir %{_datadir}/%{name} %dir %{_datadir}/%{name}/tessdata -%{_datadir}/%{name}/tessdata/configs/ -%{_datadir}/%{name}/tessdata/tessconfigs/ -%{_datadir}/%{name}/tessdata/pdf.ttf -%{_libdir}/lib%{name}*.so.4* +%{_libdir}/lib%{name}.so.5* %files devel %{_includedir}/%{name} -%{_libdir}/lib%{name}*.so +%{_libdir}/lib%{name}.so +%{_libdir}/cmake/%{name}/ %{_libdir}/pkgconfig/%{name}.pc %files tools @@ -94,21 +87,21 @@ mkdir -p %{buildroot}/%{_datadir}/%{name}/tessdata/ %{_bindir}/combine_lang_model %{_bindir}/combine_tessdata %{_bindir}/dawg2wordlist -%{_bindir}/language-specific.sh %{_bindir}/lstmeval %{_bindir}/lstmtraining %{_bindir}/merge_unicharsets %{_bindir}/mftraining %{_bindir}/set_unicharset_properties %{_bindir}/shapeclustering -%{_bindir}/tesstrain.sh -%{_bindir}/tesstrain_utils.sh %{_bindir}/text2image %{_bindir}/unicharset_extractor %{_bindir}/wordlist2dawg %changelog +* Fri Dec 10 2021 Sandro Mani - 5.0.0-1 +- Update to 5.0.0 + * Wed Nov 17 2021 Sandro Mani - 4.1.3-1 - Update to 4.1.7 diff --git a/tesseract_api.patch b/tesseract_api.patch new file mode 100644 index 0000000..8d9aae7 --- /dev/null +++ b/tesseract_api.patch @@ -0,0 +1,12 @@ +diff -rupN tesseract-5.0.0/src/lstm/plumbing.h tesseract-5.0.0-new/src/lstm/plumbing.h +--- tesseract-5.0.0/src/lstm/plumbing.h 2021-11-30 18:48:16.000000000 +0100 ++++ tesseract-5.0.0-new/src/lstm/plumbing.h 2021-12-10 21:24:35.113774177 +0100 +@@ -76,7 +76,7 @@ public: + void SetRandomizer(TRand *randomizer) override; + + // Adds the given network to the stack. +- virtual void AddToStack(Network *network); ++ TESS_API virtual void AddToStack(Network *network); + + // Sets needs_to_backprop_ to needs_backprop and returns true if + // needs_backprop || any weights in this network so the next layer forward diff --git a/tesseract_datadir.patch b/tesseract_datadir.patch deleted file mode 100644 index 7e91c6b..0000000 --- a/tesseract_datadir.patch +++ /dev/null @@ -1,50 +0,0 @@ -diff -rupN --no-dereference tesseract-4.1.3/src/ccutil/Makefile.am tesseract-4.1.3-new/src/ccutil/Makefile.am ---- tesseract-4.1.3/src/ccutil/Makefile.am 2021-11-15 09:50:28.000000000 +0100 -+++ tesseract-4.1.3-new/src/ccutil/Makefile.am 2021-11-17 20:49:03.900528627 +0100 -@@ -4,7 +4,7 @@ AM_CPPFLAGS = - AM_CPPFLAGS += -I$(top_builddir)/include - - if !NO_TESSDATA_PREFIX --AM_CXXFLAGS += -DTESSDATA_PREFIX=@datadir@ -+AM_CXXFLAGS += -DTESSDATA_PREFIX=@datadir@/tesseract/ - endif - - if VISIBILITY -diff -rupN --no-dereference tesseract-4.1.3/src/lstm/Makefile.am tesseract-4.1.3-new/src/lstm/Makefile.am ---- tesseract-4.1.3/src/lstm/Makefile.am 2021-11-15 09:50:28.000000000 +0100 -+++ tesseract-4.1.3-new/src/lstm/Makefile.am 2021-11-17 20:49:03.900528627 +0100 -@@ -15,7 +15,7 @@ AM_CPPFLAGS += -I/usr/include/tensorflow - endif - - if !NO_TESSDATA_PREFIX --AM_CXXFLAGS += -DTESSDATA_PREFIX=@datadir@ -+AM_CXXFLAGS += -DTESSDATA_PREFIX=@datadir@/tesseract/ - endif - - if DISABLED_LEGACY_ENGINE -diff -rupN --no-dereference tesseract-4.1.3/tessdata/configs/Makefile.am tesseract-4.1.3-new/tessdata/configs/Makefile.am ---- tesseract-4.1.3/tessdata/configs/Makefile.am 2021-11-15 09:50:28.000000000 +0100 -+++ tesseract-4.1.3-new/tessdata/configs/Makefile.am 2021-11-17 20:49:03.900528627 +0100 -@@ -1,4 +1,4 @@ --datadir = @datadir@/tessdata/configs -+datadir = @datadir@/tesseract/tessdata/configs - data_DATA = inter makebox box.train unlv ambigs.train lstm.train lstmdebug - data_DATA += api_config kannada box.train.stderr quiet logfile digits get.images - data_DATA += lstmbox wordstrbox -diff -rupN --no-dereference tesseract-4.1.3/tessdata/Makefile.am tesseract-4.1.3-new/tessdata/Makefile.am ---- tesseract-4.1.3/tessdata/Makefile.am 2021-11-15 09:50:28.000000000 +0100 -+++ tesseract-4.1.3-new/tessdata/Makefile.am 2021-11-17 20:49:03.901528627 +0100 -@@ -1,4 +1,4 @@ --datadir = @datadir@/tessdata -+datadir = @datadir@/tesseract/tessdata - - data_DATA = pdf.ttf - EXTRA_DIST = $(data_DATA) -diff -rupN --no-dereference tesseract-4.1.3/tessdata/tessconfigs/Makefile.am tesseract-4.1.3-new/tessdata/tessconfigs/Makefile.am ---- tesseract-4.1.3/tessdata/tessconfigs/Makefile.am 2021-11-15 09:50:28.000000000 +0100 -+++ tesseract-4.1.3-new/tessdata/tessconfigs/Makefile.am 2021-11-17 20:49:03.901528627 +0100 -@@ -1,3 +1,3 @@ --datadir = @datadir@/tessdata/tessconfigs -+datadir = @datadir@/tesseract/tessdata/tessconfigs - data_DATA = batch batch.nochop nobatch matdemo segdemo msdemo - EXTRA_DIST = batch batch.nochop nobatch matdemo segdemo msdemo