isbn 1.4.1

data/src/gocr-0.48/include/.cvsignore

@@ -0,0 +1,2 @@
+.cvsignore
+config.h

data/src/gocr-0.48/include/config.h

@@ -0,0 +1,36 @@
+/* include/config.h.in.  Generated automatically from configure.in by autoheader.  */
+
+/* Define to empty if the keyword does not work.  */
+#undef const
+
+/* Define if the setvbuf function takes the buffering type as its second
+   argument and the buffer pointer as the third, as on System V
+   before release 3.  */
+#undef SETVBUF_REVERSED
+
+/* Define if you have the ANSI C header files.  */
+#undef STDC_HEADERS
+
+/* Define if you have the gettimeofday function.  */
+#undef HAVE_GETTIMEOFDAY
+
+/* Define if you have the popen function.  */
+#undef HAVE_POPEN
+
+/* Define if you have the wcschr function.  */
+#undef HAVE_WCSCHR
+
+/* Define if you have the wcsdup function.  */
+#undef HAVE_WCSDUP
+
+/* Define if you have the <pam.h> header file.  */
+#undef HAVE_PAM_H
+
+/* Define if you have the <pnm.h> header file.  */
+#undef HAVE_PNM_H
+
+/* Define if you have the <unistd.h> header file.  */
+#undef HAVE_UNISTD_H
+
+/* Define if you have the <wchar.h> header file.  */
+#undef HAVE_WCHAR_H

data/src/gocr-0.48/include/config.h.in

@@ -0,0 +1,36 @@
+/* include/config.h.in.  Generated automatically from configure.in by autoheader.  */
+
+/* Define to empty if the keyword does not work.  */
+#undef const
+
+/* Define if the setvbuf function takes the buffering type as its second
+   argument and the buffer pointer as the third, as on System V
+   before release 3.  */
+#undef SETVBUF_REVERSED
+
+/* Define if you have the ANSI C header files.  */
+#undef STDC_HEADERS
+
+/* Define if you have the gettimeofday function.  */
+#undef HAVE_GETTIMEOFDAY
+
+/* Define if you have the popen function.  */
+#undef HAVE_POPEN
+
+/* Define if you have the wcschr function.  */
+#undef HAVE_WCSCHR
+
+/* Define if you have the wcsdup function.  */
+#undef HAVE_WCSDUP
+
+/* Define if you have the <pam.h> header file.  */
+#undef HAVE_PAM_H
+
+/* Define if you have the <pnm.h> header file.  */
+#undef HAVE_PNM_H
+
+/* Define if you have the <unistd.h> header file.  */
+#undef HAVE_UNISTD_H
+
+/* Define if you have the <wchar.h> header file.  */
+#undef HAVE_WCHAR_H

data/src/gocr-0.48/include/version.h

@@ -0,0 +1,2 @@
+#define version_string "0.48"
+#define release_string "20090802"

data/src/gocr-0.48/install-sh

@@ -0,0 +1,3 @@
+# this is not the final version!
+
+cp ./bin/gocr /usr/local/bin/gocr

data/src/gocr-0.48/make.bat

@@ -0,0 +1,57 @@
+@rem why does DJGPP not work with dosemu?
+@echo " --- compiling GOCR under DOS --- "
+@GOTO DOS
+# unix-shell does not know GOTO
+# changes: .tcl cat=?, xli=?
+#          progress before Stop/button, gocrexe.zip-package
+exit
+:DOS
+if "%1" == "compile" GOTO compile
+@echo "I love this environment. --- Kick me!"
+@rem %0 works only with real-dos, not with DOSEMU
+@if "%0" == "" GOTO compile
+@command.com /E:8000 /c %0 compile
+@GOTO END
+exit
+:compile
+@echo off
+SET ROOT=D:\TMP2\CDROM\DOS\DJGPP
+SET TEMP=%ROOT%\tmp
+SET TMP=%TEMP%
+SET BINPATH=%ROOT%\BIN\
+PATH %BINPATH%;%PATH%
+SET DJGPP=%ROOT%\DJGPP.ENV
+SET OPT=-O2 -pedantic -Iinclude -Wall
+SET OPT=-O2 -DHAVE_CONFIG_H
+SET C_INCLUDE_PATH=SRC;INCLUDE;%C_INCLUDE_PATH%
+REM mkdir tmp
+@echo on
+REM make makefile.dos
+REM exit
+gcc %OPT% -o a1.o -c src\box.c
+gcc %OPT% -o a2.o -c src\database.c
+gcc %OPT% -o a3.o -c src\detect.c
+gcc %OPT% -o a4.o -c src\gocr.c
+gcc %OPT% -o a5.o -c src\lines.c
+gcc %OPT% -o a6.o -c src\list.c
+gcc %OPT% -o a7.o -c src\ocr0.c
+gcc %OPT% -o a8.o -c src\ocr0n.c
+gcc %OPT% -o a9.o -c src\ocr1.c
+gcc %OPT% -o aa.o -c src\otsu.c
+gcc %OPT% -o ab.o -c src\output.c
+gcc %OPT% -o ac.o -c src\pcx.c
+gcc %OPT% -o ad.o -c src\pgm2asc.c
+gcc %OPT% -o ae.o -c src\pixel.c
+gcc %OPT% -o af.o -c src\pnm.c
+gcc %OPT% -o ag.o -c src\remove.c
+gcc %OPT% -o ah.o -c src\unicode.c
+gcc %OPT% -o ai.o -c src\barcode.c
+gcc %OPT% -o aj.o -c src\job.c
+gcc %OPT% -o ak.o -c src\progress.c
+REM having only 128 byte for command line is terrible (concatenate?)
+gcc -o gocr.exe a1.o a2.o a3.o a4.o a5.o a6.o a7.o a8.o a9.o aa.o ab.o ac.o ad.o ae.o af.o ag.o ah.o ai.o aj.o ak.o
+@if exist gocr.exe del *.o
+@if exist gocr.exe strip gocr.exe
+rem pkzip gocrexe gocr.exe gocr.tcl README 
+@GOTO END
+:END

data/src/gocr-0.48/man/.cvsignore

@@ -0,0 +1,2 @@
+.cvsignore
+Makefile

data/src/gocr-0.48/man/Makefile

@@ -0,0 +1,29 @@
+#
+# Makefile for ./man path, used by configure
+#
+
+PROGRAM = gocr
+
+mandir = ${prefix}/man
+
+INSTALL=/usr/bin/install -c
+DESTDIR=/usr/local
+
+default: all
+
+all:
+
+# PHONY = don't look at file clean, -rm = start rm and ignore errors
+.PHONY : clean proper install uninstall
+install: all
+	$(INSTALL) -d $(DESTDIR)$(mandir)/man1
+	$(INSTALL) ../man/man1/$(PROGRAM).1 $(DESTDIR)$(mandir)/man1
+
+uninstall:
+	-rm -f $(DESTDIR)$(mandir)/man1/$(PROGRAM).1
+
+clean:
+	-rm -f *.o *~
+
+proper: clean
+	

data/src/gocr-0.48/man/Makefile.in

@@ -0,0 +1,29 @@
+#
+# Makefile for ./man path, used by configure
+#
+
+PROGRAM = gocr
+
+mandir = @mandir@
+
+INSTALL=@INSTALL@
+DESTDIR=@prefix@
+
+default: all
+
+all:
+
+# PHONY = don't look at file clean, -rm = start rm and ignore errors
+.PHONY : clean proper install uninstall
+install: all
+	$(INSTALL) -d $(DESTDIR)$(mandir)/man1
+	$(INSTALL) ../man/man1/$(PROGRAM).1 $(DESTDIR)$(mandir)/man1
+
+uninstall:
+	-rm -f $(DESTDIR)$(mandir)/man1/$(PROGRAM).1
+
+clean:
+	-rm -f *.o *~
+
+proper: clean
+	

data/src/gocr-0.48/man/man1/gocr.1

@@ -0,0 +1,166 @@
+.\"             -*-Nroff-*-
+.\" Copyright 2000 Red Hat, Inc.
+.TH GOCR 1 "29 Mar 2009" "Linux" "User's Manual"
+.SH NAME
+gocr \- command line text recognition tool
+.SH SYNOPSIS
+.B gocr
+[\fIOPTION\fR] [\fB-i\fR] \fIpnm-file\fR
+.fi
+.SH DESCRIPTION
+gocr is an optical character recognition program that can be used from
+the command line.  It takes input in PNM, PGM, PBM, PPM, or PCX
+format, and writes recognized text to \fBstdout\fR.  If the \fIpnm
+file\fR is a single dash, PNM data is read from \fBstdin\fR.
+If gzip, bzip2 and netpbm-progs are installed and your system
+supports popen(3) also pnm.gz, pnm.bz2, png, jpg, jpeg, tiff,
+gif, bmp, ps (only single pages) and eps are supported as input files
+(not as input stream), where pnm can be replaced
+by one of ppm, pgm and pbm.
+.SH OPTIONS
+.TP
+\fB\-h\fR
+show usage information
+.TP
+\fB\-i\fR \fIfile\fR
+read input from \fIfile\fR (or \fBstdin\fR if \fIfile\fR is a single
+dash)
+.TP
+\fB\-o\fR \fIfile\fR
+send output to \fIfile\fR instead of \fBstdout\fR
+.TP
+\fB\-e\fR \fIfile\fR
+send errors to \fIfile\fR instead of \fBstderr\fR or to \fBstdout\fR
+if \fIfile\fR is a dash
+.TP
+\fB\-x\fR \fIfile\fR
+progress output to \fIfile\fR
+(\fIfile\fR can be a file name, a fifo name or a file descriptor 1...255),
+this is useful for GUI developpers to show the OCR progress, the file
+descriptor argument is only available, if compiled with __USE_POSIX defined
+.TP
+\fB\-p\fR \fIpath\fR
+database path, a final slash must be included, default is ./db/,
+this path will be populated with images of learned characters
+.TP
+\fB\-f\fR \fIformat\fR
+output \fIformat\fR of the recognized text 
+(ISO8859_1 TeX HTML XML UTF8 ASCII), XML will also output position and
+probability data 
+.TP
+\fB\-l\fR \fIlevel\fR
+set grey level to \fIlevel\fR (0<160<=255, default:
+0 for autodetect), darker pixels belong to characters, brighter pixels
+are interpreted as background of the input image
+.TP
+\fB\-d\fR \fIsize\fR
+set dust size in pixels (clusters smaller than this are removed),
+0 means no clusters are removed, the default is -1 for auto detection
+.TP
+\fB\-s\fR \fInum\fR
+set spacewidth between words in units of dots (default: 0 for autodetect),
+wider widths are interpreted as word spaces, smaller as character spaces
+.TP
+\fB\-v\fR \fIverbosity\fR
+be verbose to stderr; \fIverbosity\fR is a bitfield
+.TP
+\fB\-c \fIstring\fR
+only verbose output of characters from \fIstring\fR to stderr,
+more output is generated for all characters within the string,
+the underscore stands for unknown chars, this function is usefull
+to limit debug information to the necessary one 
+.TP
+\fB\-C \fIstring\fR
+only recognise characters from \fIstring\fR, this is a filter function
+in cases where the interest is only to a part of the character alphabet,
+you can use 0-9 or a-z to specify ranges, use -- to detect the minus sign
+.TP
+\fB\-a\fR \fIcertainty\fR
+set value for certainty of recognition (0..100; default: 95),
+characters with a higher certainty are accepted, characters with a lower
+certainty are treated as unknown (not recognized); set higher values, if
+you want to have only more certain recognized characters
+.TP
+\fB\-u \fIstring\fR
+output this string for every unrecognized character (default is "_")
+.TP
+\fB\-m\fR \fImode\fR
+set oprational mode; mode is a bitfield (default: 0)
+.TP
+\fB\-n\fR \fIbool\fR
+if \fIbool\fR is non-zero, only recognise numbers
+(this is now obsolete, use -C "0123456789")
+.PP
+The verbosity is specified as a bitfield:
+.TP 10
+.B 1
+print more info
+.TP
+.B 2
+list shapes of boxes (see -c) to stderr
+.TP
+.B 4
+list pattern of boxes (see -c) to stderr
+.TP
+.B 8
+print pattern after recognition for debugging
+.TP
+.B 16
+print debug information about recognition of lines to stderr
+.TP
+.B 32
+create outXX.png with boxes and lines marked on each general OCR-step
+.PP
+The operation modes are:
+.TP 10
+.B 2
+use database to recognize characters which are not recognized by
+other algorithms, (early development)
+.TP
+.B 4
+switching on layout analysis or zoning (development)
+.TP
+.B 8
+don't compare unrecognized characters to recognized one
+.TP
+.B 16
+don't try to divide overlapping characters to two or three single characters 
+.TP
+.B 32
+don't do context correction
+.TP
+.B 64
+character packing, before recognition starts, similar characters
+are searched and only one of this characters will be send to the
+recognition engine (development)
+.TP
+.B 130
+extend database, prompts user for unidentified characters
+and extends the database with users answer (128+2, early development)
+.TP
+.B 256
+switch off the recognition engine (makes sense together with -m 2)
+.SH
+.SH AUTHOR
+Joerg Schulenburg (see http://jocr.sourceforge.net/ for EMAIL)
+.br
+First version of man page by Tim Waugh <twaugh@redhat.com>
+.SH VERSION INFORMATION
+This man page documents \fBgocr\fR, version 0.41.
+.SH REPORTING BUGS
+Report bugs to Joerg Schulenburg
+.SH SEE ALSO
+More details can be found at /usr/share/doc/gocr-\fBX.XX\fR/gocr.html.
+Also read /usr/share/doc/gocr-\fBX.XX\fR/README to learn, how to improve
+results.
+.SH EXAMPLES
+.TP
+.B gocr -v 33 text1.pbm
+output verbose information, out30.png is created to see details of
+recognition process
+.TP
+.B gocr -v 7 -c _YV text1.pbm
+verbose output for unknown chars and chars Y and V
+.TP
+.B djpeg -pnm -gray text.jpg | gocr -
+convert a jpeg file to pnm format and input via pipe

data/src/gocr-0.48/src/.cvsignore

@@ -0,0 +1,4 @@
+.cvsignore
+Makefile
+gocr
+*.o

data/src/gocr-0.48/src/Makefile

@@ -0,0 +1,132 @@
+#
+# Makefile for ./src path, used by configure
+#
+
+EXEEXT = 
+PROGRAM = gocr$(EXEEXT)
+# lib removed for simplification (v0.46)
+# but Igor from OSRA an optical chemical structure recognition software 
+#  wants it (v0.47 Mar09)
+PGMASCLIB = Pgm2asc
+#LIBPGMASCLIB = lib$(PGMASCLIB).a
+# ToDo: need a better pgm2asc.h for lib users 
+#INCLUDEFILES = gocr.h
+# avoid german compiler messages
+LANG=C
+
+LIBOBJS=pgm2asc.o \
+	box.o \
+	database.o \
+	detect.o \
+	barcode.o \
+	lines.o \
+	list.o \
+	ocr0.o \
+	ocr0n.o \
+	ocr1.o \
+	otsu.o \
+	output.o \
+	pixel.o \
+	unicode.o \
+	remove.o \
+	pnm.o \
+	pcx.o \
+	progress.o \
+	job.o
+
+# these two lines are for cross-compiling, not tested
+#srcdir = .
+#VPATH = .
+bindir = ${exec_prefix}/bin
+#  lib removed for simplification
+#libdir = ${exec_prefix}/lib
+#includedir = ${prefix}/include
+
+CC=gcc
+# lib removed for simplification
+# ar,ranlib detection removed from configure (simplicity)
+#  but needed by some developpers (linux only) for for (make libs)
+# RANLIB = @RANLIB@
+# AR = @AR@
+RANLIB = ranlib
+AR = ar
+INSTALL=/usr/bin/install -c
+# shell is needed for OS/2 to let if test -r $(PROGRAM) ... work
+SHELL=/bin/sh
+
+DEFS=-DHAVE_CONFIG_H
+CPPFLAGS=-Wall -g -fexceptions -DDO_DEBUG=1 
+# to see the config.h
+CFLAGS=-g -O2 $(CPPFLAGS) -I../include $(DEFS)
+LDFLAGS=-lm 
+LIBS=-lnetpbm 
+DESTDIR=/usr/local
+
+.SUFFIXES: .s .o .c .h
+# do not look for files if help (etc) is given
+.PHONY : doc clean install libs default
+
+.c.o: gocr.h pgm2asc.h ../include/config.h
+	$(CC) $(CFLAGS) -c -o $*.o $<
+
+default: all
+
+# all: $(PROGRAM) lib$(PGMASCLIB).a
+all: $(PROGRAM)
+
+gocr.o: gocr.h Makefile ../include/version.h
+
+.c.h:
+
+#$(PROGRAM): lib$(PGMASCLIB).a gocr.o
+$(PROGRAM): $(LIBOBJS) gocr.o
+	# make it conform to ld --as-needed
+	#$(CC) -o $@ $(LDFLAGS) gocr.o ./lib$(PGMASCLIB).a $(LIBS)
+	$(CC) -o $@ $(LDFLAGS) gocr.o $(LIBOBJS) $(LIBS)
+	if test -r $(PROGRAM); then cp $@ ../bin; fi
+
+libs: lib$(PGMASCLIB).a lib$(PGMASCLIB).0.48.so
+
+lib$(PGMASCLIB).0.48.so: $(LIBOBJS)
+	$(CC) -fPIC -shared -Wl,-h$@ -o $@ $(LIBOBJS)
+	-ln -s $@ lib$(PGMASCLIB).so
+
+lib$(PGMASCLIB).a: $(LIBOBJS)
+	#	-rm -f $@
+	$(AR) cru $@ $(LIBOBJS)
+	$(RANLIB) $@
+
+$(LIBOBJS): Makefile
+
+# PHONY = don't look at file clean, -rm = start rm and ignore errors
+.PHONY : clean proper install uninstall
+install: all
+	#$(INSTALL) -d $(DESTDIR)$(bindir) $(DESTDIR)$(libdir) $(DESTDIR)$(includedir)
+	$(INSTALL) -d $(DESTDIR)$(bindir)
+	$(INSTALL) ../bin/$(PROGRAM) $(DESTDIR)$(bindir)
+	$(INSTALL) ../bin/gocr.tcl   $(DESTDIR)$(bindir)  # better X11/bin?
+	if test -f lib$(PGMASCLIB).a; then\
+	 $(INSTALL) lib$(PGMASCLIB).a $(DESTDIR)$(libdir);\
+	 $(INSTALL) lib$(PGMASCLIB).0.48.so $(DESTDIR)$(libdir);\
+	 $(INSTALL) lib$(PGMASCLIB).so $(DESTDIR)$(libdir);\
+	fi
+	# ToDo: not sure that the link will be installed correctly
+	#$(INSTALL) $(INCLUDEFILES) $(DESTDIR)$(includedir)
+
+# directories are not removed
+uninstall:
+	-rm -f $(DESTDIR)$(bindir)/$(PROGRAM)
+	-rm -f $(DESTDIR)$(bindir)/gocr.tcl
+	-rm -f $(DESTDIR)$(libdir)/lib$(PGMASCLIB).a
+	-rm -f $(DESTDIR)$(libdir)/lib$(PGMASCLIB).0.48.so
+	-rm -f $(DESTDIR)$(libdir)/lib$(PGMASCLIB).so
+	# ToDo: set to old version.so ?
+	#for X in $(INCLUDEFILES); do rm -f $(DESTDIR)$(includedir)/$$X; done
+
+clean:
+	-rm -f *.o *~
+
+proper: clean
+	-rm -f gocr libPgm2asc.*
+	-rm -f gocr
+