fix filemode;

update autotools and distribution script to repository changes;
ignore doxygen generated files and langauge data files;

.gitignore

@@ -23,6 +23,7 @@ libtool
 stamp-h1
 tesseract.pc
 config_auto.h
+doc/html/*
 api/tesseract
 training/ambiguous_words
 training/classifier_tester
@@ -46,3 +47,7 @@ training/wordlist2dawg
 *.Plo
 *.a
 
+# tessdata
+*.cube.*
+*.tesseract_cube.*
+*.traineddata
\ No newline at end of file

INSTALL.SVN → INSTALL.GIT

 autotools (LINUX/UNIX...)
 ======================
 
-If you have checked out Tesseract from Subversion, you must generate the 
-configure script.
+If you have checked out Tesseract from Subversion, you must generate
+the configure script.
 
 If you have tesseract 3.0x installation in your system, please remove it
 before new build.
 
+Known depencies for training tools (excluding leptonica):
+ * compiler with c++ support
+ * pango-devel
+ * cairo-devel
+ * icu-devel
+
 So, the steps for making Tesseract are:
 
   $ ./autogen.sh
   $ ./configure
   $ make
   $ sudo make install
-  $ sudo make install-langs
   $ make training
   $ sudo make training-install
-  
-'sudo make install-langs' or 'sudo make install LANGS=' will install all
-available language data files in tessdata directory.
-
-If you want to install just few of them than run:
-  $ sudo make install-langs LANGS="eng ara deu"
-It will install only English, Arabic and German language datafiles (if 
-they are present in tessdata directory)
-
-  $ sudo make install LANGS="eng ara deu"
-will install tesseract library, tesseract programs  and English, Arabic 
-and German language datafiles.
+
+You need to install at least English langugage data file to TESSDATA_PREFIX
+directory. All langugage data files can be retrieved from git repository:
+  $ git clone https://code.google.com/p/tesseract-ocr.tessdata/ tessdata
 
 To compile ScrollView.jar you need to download piccolo2d-core-3.0.jar
 and piccolo2d-extras-3.0.jar[1] and place them to tesseract/java.

Makefile.am

@@ -18,7 +18,7 @@ endif
 
 SUBDIRS = ccutil viewer cutil opencl ccstruct dict classify wordrec neural_networks/runtime textord cube ccmain api . tessdata doc
 
-EXTRA_DIST = eurotext.tif phototest.tif ReleaseNotes \
+EXTRA_DIST = ReleaseNotes \
 	aclocal.m4 config configure.ac autogen.sh contrib \
 	tesseract.pc.in $(TRAINING_SUBDIR) java doc testing
 
@@ -34,31 +34,12 @@ dist-hook:
 	rm -rf `find $(distdir) -name .svn`
 	rm -rf `find $(distdir) -name .git`
 	rm -rf `find $(distdir) -name .deps`
-
-# 'make install' will install only libraries and programs (no language 
-#       data files)
-# 'make install LANGS=' will install libraries, programs and  all 
-#       language datafiles in tessdata/
-# 'make install LANGS="eng ara deu"' will install libraries, programs
-#       English, Arabic and German language datafiles if they are present
-#       in tessdata/
-# 'make install-langs LANGS="eng ara deu"' will install only English,
-#	Arabic and German language datafiles if they are present
-#       in tessdata/
-install-data-hook:
-	@if test $${LANGS+defined}; then \
-		if test "$${LANGS}" == ""; then \
-			echo ____All language files will be installed; \
-		else \
-			echo ___Folowing language files will be installed: "$$LANGS"; \
-		fi; \
-		cd "$(top_builddir)/tessdata" && $(MAKE) install-langs LANG="${LANGS}"; \
-	else \
-		echo No language file is installed.; \
-	fi;
-
-install-langs:
-	@cd "$(top_builddir)/tessdata" && $(MAKE) $@
+	rm -rf `find $(distdir) -name .libs`
+	rm -rf `find $(distdir) -name *.o`
+	rm -rf `find $(distdir) -name *.lo`
+	rm -rf `find $(distdir) -name *.la`
+	rm -rf `find $(distdir)/training -executable -type f`
+	rm -rf $(distdir)/doc/html/*
 
 ScrollView.jar:
 	@cd "$(top_builddir)/java" && $(MAKE) $@

makemoredists

-#!/bin/bash
-# Requirement: tesseract directory name should be "tesseract-ocr"
-
-source_dir=${PWD##*/}
-tess_ver=3.02
-src_min_ver=.02
-ver=$source_dir-$tess_ver
-excld="exclude.txt"
-
-cd ..
-echo Output for $source_dir is in `pwd` ...
-
-# create language files packages
-if [ -f $excld ] 
-then
-	echo Removing $excld...
-	rm -f $excld
-fi
-
-for l in $source_dir/tessdata/*.traineddata
-do
-	filename=`basename "$l"`
-	lang=${filename%.*}
-	echo  Creating language package for `basename "$l"`...
-	chmod 644 $source_dir/tessdata/*$lang*
-	tar --group root --owner root -chozf $ver.`basename "$l" .traineddata`.tar.gz $source_dir/tessdata/*$lang*
-	echo $source_dir/tessdata/*$lang* | tr " " "\n" >>$excld
-done
-
-# Windows build relevant files
-name=$ver-win_vs2008
-# Let's be nice and use common windows packager ;-)
-zip -9 -r --exclude=*.svn* --exclude=*strtok_r* $name.zip $source_dir/vs2008/
-
-# create linux source package
-echo Creating linux source package $ver$src_min_ver.tar.gz ...
-tar -chof $ver$src_min_ver.tar --exclude=.svn --exclude=debian --exclude=autom4te.cache --exclude=doc/html --exclude=po/ --exclude=m4/ --exclude=makemoredists --exclude=vs2008 -exclude=INSTALL.SVN -X $excld $source_dir/*
-#workaround to include strtok_r from vs2008 for mingw
-tar -rof $ver$src_min_ver.tar $source_dir/vs2008/port/strtok_r.*
-gzip $ver$src_min_ver.tar
-
-# create doc and package doc
-cd $source_dir
-doxygen doc/Doxyfile
-cd ..
-tar --group root --owner root -chozf $ver-doc-html.tar.gz $source_dir/doc/html/*
-
-rm -f $excld
-cd $source_dir