tesseract: added recipe for version 3.02.02

This commit is contained in:
Sergei Reznikov
2015-03-31 15:32:01 +03:00
parent 7e2f14e2c7
commit bd8903b490
3 changed files with 155 additions and 32 deletions

View File

@@ -0,0 +1,40 @@
From 96fec6ffd95b10d352a8df7b57f3e8f36beb5320 Mon Sep 17 00:00:00 2001
From: Sergei Reznikov <diver@gelios.net>
Date: Tue, 31 Mar 2015 14:43:55 +0300
Subject: [PATCH] Backport 16aa99315a3d - make ocrclass.h public header
---
ccutil/Makefile.am | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/ccutil/Makefile.am b/ccutil/Makefile.am
index 5c08f6b..8737dda 100644
--- a/ccutil/Makefile.am
+++ b/ccutil/Makefile.am
@@ -14,13 +14,13 @@ EXTRA_DIST = mfcpch.cpp
include_HEADERS = \
basedir.h errcode.h fileerr.h genericvector.h helpers.h host.h memry.h \
- ndminx.h params.h platform.h serialis.h strngs.h tesscallback.h \
- unichar.h unicharmap.h unicharset.h
+ ndminx.h params.h ocrclass.h platform.h serialis.h strngs.h \
+ tesscallback.h unichar.h unicharmap.h unicharset.h
noinst_HEADERS = \
ambigs.h bits16.h bitvector.h ccutil.h clst.h elst2.h \
elst.h globaloc.h hashfn.h hosthplb.h indexmapbidi.h lsterr.h \
- mfcpch.h notdll.h nwmain.h ocrclass.h qrsequence.h secname.h \
+ mfcpch.h notdll.h nwmain.h qrsequence.h secname.h \
sorthelper.h stderr.h tessdatamanager.h tprintf.h unicity_table.h \
unicodes.h
@@ -51,4 +51,4 @@ if MINGW
AM_CPPFLAGS += -I$(top_srcdir)/vs2008/port -DWINDLLNAME=\"lib@GENERIC_LIBRARY_NAME@\"
noinst_HEADERS += ../vs2008/port/strtok_r.h
libtesseract_ccutil_la_SOURCES += ../vs2008/port/strtok_r.cpp
-endif
\ No newline at end of file
+endif
--
2.2.2

View File

@@ -0,0 +1,115 @@
SUMMARY="An OCR Engine that was developed at HP and now at Google"
DESCRIPTION="
An OCR Engine that was developed at HP Labs between 1985 and 1995... and \
now at Google.
Tesseract is probably the most accurate open source OCR engine available. \
Combined with the Leptonica Image Processing Library it can read a wide \
variety of image formats and convert them to text in over 60 languages. \
It was one of the top 3 engines in the 1995 UNLV Accuracy test. Between \
1995 and 2006 it had little work done on it, but since then it has been \
improved extensively by Google. It is released under the Apache License \
2.0."
HOMEPAGE="http://code.google.com/p/tesseract-ocr"
LICENSE="Apache v2"
COPYRIGHT="1985-1995 HP labs
2012 Google Inc."
SRC_URI="https://tesseract-ocr.googlecode.com/files/tesseract-ocr-3.02.02.tar.gz"
CHECKSUM_SHA256="26cd39cb3f2a6f6f1bf4050d1cc0aae35edee49eb49a92df3cb7f9487caa013d"
REVISION="1"
ARCHITECTURES="x86 x86_64"
if [ $effectiveTargetArchitecture != x86_gcc2 ]; then
# x86_gcc2 is fine as primary target architecture as long as we're building
# for a different secondary architecture.
ARCHITECTURES="$ARCHITECTURES x86_gcc2"
else
ARCHITECTURES="$ARCHITECTURES !x86_gcc2"
fi
SECONDARY_ARCHITECTURES="x86"
PROVIDES="
tesseract$secondaryArchSuffix = $portVersion
lib:libtesseract$secondaryArchSuffix = $portVersion
cmd:ambiguous_words$secondaryArchSuffix = $portVersion
cmd:classifier_tester$secondaryArchSuffix = $portVersion
cmd:cntraining$secondaryArchSuffix = $portVersion
cmd:combine_tessdata$secondaryArchSuffix = $portVersion
cmd:dawg2wordlist$secondaryArchSuffix = $portVersion
cmd:mftraining$secondaryArchSuffix = $portVersion
cmd:shapeclustering$secondaryArchSuffix = $portVersion
cmd:tesseract$secondaryArchSuffix = $portVersion
cmd:unicharset_extractor$secondaryArchSuffix = $portVersion
cmd:wordlist2dawg$secondaryArchSuffix = $portVersion
"
PROVIDES_devel="
tesseract${secondaryArchSuffix}_devel = $portVersion
devel:libtesseract$secondaryArchSuffix = $portVersion
"
REQUIRES_devel="
tesseract$secondaryArchSuffix == $portVersion
"
REQUIRES="
haiku$secondaryArchSuffix
lib:libgcc_s$secondaryArchSuffix
lib:libstdc++$secondaryArchSuffix
lib:liblept$secondaryArchSuffix
lib:libgif$secondaryArchSuffix
lib:libjpeg$secondaryArchSuffix
lib:libpng$secondaryArchSuffix
lib:libwebp$secondaryArchSuffix
lib:libz$secondaryArchSuffix"
BUILD_REQUIRES="
devel:liblept$secondaryArchSuffix
devel:libgif$secondaryArchSuffix
devel:libjpeg$secondaryArchSuffix
devel:libpng$secondaryArchSuffix
devel:libwebp$secondaryArchSuffix
devel:libz$secondaryArchSuffix
"
BUILD_PREREQUIRES="
haiku${secondaryArchSuffix}_devel
cmd:aclocal
cmd:autoconf
cmd:awk
cmd:find
cmd:gcc$secondaryArchSuffix
cmd:libtoolize
cmd:make
"
SOURCE_DIR="tesseract-ocr"
PATCHES="tesseract-3.02.02.patch"
PATCH()
{
sed -i 's,AM_CONFIG_HEADER,AC_CONFIG_HEADERS,g' configure.ac
}
BUILD()
{
autogen.sh
export LIBLEPT_HEADERSDIR=$(finddir B_SYSTEM_HEADERS_DIRECTORY)${secondaryArchSubDir}/leptonica
export TESSDATA_PREFIX=$dataDir/tessdata
runConfigure configure
make
}
INSTALL()
{
make install
prepareInstalledDevelLibs libtesseract
fixPkgconfig
# devel package
packageEntries devel $developDir
}
TEST()
{
make test
make check
}

View File

@@ -1,32 +0,0 @@
DESCRIPTION="An OCR Engine that was developed at HP Labs between 1985 and 1995... now at Google."
HOMEPAGE="http://code.google.com/p/tesseract-ocr"
SRC_URI="svn+http://tesseract-ocr.googlecode.com/svn/trunk"
REVISION="1"
STATUS_HAIKU="broken"
DEPEND=""
#CHECKSUM_MD5="cc812a261088ea0c3d2da735be35d09f"
BUILD()
{
cd tesseract-3.x-svn
./runautoconf
./configure --prefix=`finddir B_COMMON_DIRECTORY`
make
}
INSTALL()
{
cd tesseract-3.x-svn
make install
}
TEST()
{
cd tesseract-ocr-3.x
# make test
# make check
}
LICENSE="Apache v2
GNU GPL v1"
COPYRIGHT="1985-1995 HP labs
2011 Google Inc."