entangledstate-isbn 1.4.0 → 1.4.1

data/src/gocr-0.48/CREDITS

@@ -0,0 +1,17 @@
+Thanks:
+  ...to everyone who contributed to gocr. If you feel that your
+  name should be in this list, write mail to the author. These
+  are in no particular order:
+
+    G.Kugler for sending me first example files and testing. (MayMM)
+    Klaas Freitag for the libPgm2asc-patch <freitag@suse.de>
+    Ryan Dibble for the otsu.c file <dibbler@umich.edu>
+    Tim Waugh for the man page <twaugh@redhat.com>
+    David Pinson for the tkispell-patch <dpinson@materials.unsw.EDU.AU>
+    Martin Goldhahn for some patches <Martin.Goldhahn@Webcenter.no> 
+    Eberhard Burkard for the gocr.tcl patch <E.Burkard@web.de>
+    James R. Van Zandt for lot of tips <jrv@vanzandt.mv.com>
+    ...
+ 
+  ... and everyone else who submitted bug-reports,
+  feature-requests, patches and lots of example files.

data/src/gocr-0.48/HISTORY

@@ -0,0 +1,243 @@
+History: (Changes,ChangeLog)
+ 0.48 Jul09
+       fix buffer overflow introduced in 0.46 for filenames
+       add codabar barcode
+       fix bug, removing melted serifs
+       add patch by Chris Lee, i25 barcode recognition + modifications
+       fix some false positive numbers "34" (video, gas meter)
+       fix problems with 2zZ4 for 10x10 screen font
+       better debug output for :;,.
+       remove examples, doc and libs part from configure (see below)
+       remove doc and examples from the (make install) part to reduce
+         dependencies (gs and transfig is not needed for rpm/ebuild)
+         gocr only may depend from netpbm, but can live without too
+         this will help to install gocr on "exotic" (nonlinux) platforms
+       fix gentoo app-text/gocr Bug 243250 src/Makefile: $(CC) $(LDFLAGS) ...
+
+ 0.47  fix database recognition for certainty 100 (-a 100)
+       insert spaces with certainty 100 (old: 99) to let -a 100 work
+       new option -u string for unrecognized chars
+       fix: No contrast in image causes division by zero
+       reduced false positive recognition of scanned "a496" (Gutenberg Project)
+       "d as a" patch ID: 1556112
+       add "Windows Pipe Fix", but I hate extra code for bad environments
+       improve 7x10, sample 0811qemu1.png (ToDo: not finished)
+       change black:white from >4:1 to >3.5:1 as criteria of inversion
+       reintroduce static library libPgm2asc.a (make libs) for OSRA project
+       add dynamic library (make libs), unused but may help other projects
+      
+ 0.46  improved context correction (especially helvetica "Il")
+       improved recognition of tiny chars "$1", fat "s", "rw" ","
+       fix blank spaces problem in filenames
+         (http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=316511)
+         !!! please check on other platforms and report to me !!!
+         there are still problems with special chars (double quodes, backslash)
+         better use this way: djpeg -gray -pnm strangefilename.jpg | gocr -
+       fix possible problem with database and UTF8 input 
+       fix hidden bug in pitch/spacing initialization
+       reactivate code for output of glued chars and strings 
+       fix wrong close() call
+       remove creation of pgm2asc.a for simplicity (see SF-patch 1827477)
+       
+ 0.45  minor corrections for c and k
+       minus sign is filtered by option -C "--" now, ("\-" was parsed badly)
+       clean up old unused code for simplicity (api, frontend)
+       fix problem with low height barcodes and barcode removing
+       fix problem with readpgm (for multiple images) and database
+       PACKAGE_VERSION defined by configure.in AC_INIT + gocr.spec
+
+ 0.44  add volume to boxes (negative means white areas inside black areas)
+       Fix overflow in despeckling routine (verbose mode, dust removing)
+       reactivate composed chars, fix merge_boxes
+       fix problems with uncertain line detection and not recognized "7"
+       option -a has an effect now for the output
+       adaptions to MICR E13-B font (see GnuMICR), ToDo: 4 extra-chars
+       fix num_boxes in merge_boxes (affects line detection)
+       reduce 2 prompts to one per char in database mode, ^A for skip all
+       fix problem with smaller headlines
+       fix problems with tall font (4)
+       fix includes for non-linux-platforms
+
+ 0.43  fix problem with dark frame around image
+       support multiple images, ex: giftopnm -image=all a.gif | gocr -
+       invert if obviously white on black (black_mass>=4*white_mass)
+       improve thresholding for discrete histograms
+         (note: this can particularly lead to bad results, will be fixed later)
+       speedup for big boxes (especially dark background)
+       fix memory leak (setas(same string) + detect_barcode)
+       fix uninitialized variables after insert spaces (num_frames)
+       fix frame_vector for single pixels (twice + ERROR idx out of range)
+
+ 0.42  further parts of recognition engine relaced by vector version
+       changed colored debug output for out??.png
+       division of glued chars replaced (slower but more accurate)
+       fix framing of small font
+       fix problem with uninitialized pnm_readpaminit call (CPS 21Nov06)
+       better progress output (see progress.[ch]), new image debug output
+       switch to the new improved rotation detection
+
+ 0.41  (buggy if --with-netpbm=no, apply the pgm-patch!)
+       otsu.c concentrates now only on high contrast regions
+       fix pnm reads for 2 byte pixels (--with-libpbm=no) 
+       update man-page (mail me your suggestions)
+       fix g++ warnings, float-OPs replaced by int-OPs
+       spacing reviewed; make distance() more sensitive
+       xml-objects (barcode, melted chars) now also handled with weights
+       fix division by zero bug for vertical positioned characters
+       default output is UTF8 now, UTF-encoding bug fixed
+       added certainty option 
+       added uninstall to Makefile
+       debug image format changed to png (using pipe) or ppm (fall-back)
+       much better word spacing (line-by-line based)
+       better DOT_ABOVE recognition
+       fix output of char groups or strings stored in database, utf8 input
+       fix buffer overflow in barcode decode39
+       fix lost comma on end of line
+       internal vector format added for future use (faster, scalable, rotable)
+       line detection extended
+       internal list management rewritten to fix memory leaks and segfaults
+
+ 0.40  update PNM file reader to maxval > 255
+       (make rpm) updated
+       barcode-patch UPC_addon by Michael van Rooyen
+       CAPITAL_LETTER_A_WITH_OGONEK added
+       no "(PICTURE)" output for UTF8+ASCII (better for Mobile OCR project)
+       smooth_borders() bug fixed and reworked
+       5x7 and prop10 font adaptions
+       objects now detected by flood-fill algorithm (better?)
+       XML-output changed
+       changed auto dust detection (not final)
+
+ 0.39  XML output added (subject of change, suggestions are welcome)
+       netpbm-link-error fixed in gocr.c and configure.in:
+         gocr.c: <config.h> changed to "config.h"
+       configure-option --with-netpbm=PATH and --without-netpbm added
+       update configure.in according to autoconf 2.57  
+       wchar_h miss-configuration fixed in pgm2asc.c
+       fix compiler warnings
+       char filter accepts abbreviations now, like "0-9A-F" (but slow)
+       update READMEde.txt
+       output barcode tags (also improved recognition)
+       fix pnm.c for files like example.eps.pbm
+       fix detect.c for barcodes
+       fix ocr0n.c 0<->8g
+
+ 0.38  move UTF/HTML/TeX decoding to getTextLine, return (char *) now
+       out_format HTML step towards detailed XML output
+       correct line detection for footnotes (detect.c)
+       "y" now seen as vowel (pgm2asc.c), I<vowel> susbtituted by l<vowel>
+       &eacute;-detection, &aacute;-output fixed
+       default dust_size is -1 now (auto detection = mean_size/10)
+       char filter added
+        ex: -C 0123456789ABCDEF    - recognize only hexcodes
+       man page updated (hopefully correct syntax)
+       database bug fixed (small fonts, example by Chris)
+       several bugs fixed by W. Webber (thanks)
+       speed improved by 3rd-pass matrix filter in pixel() (pixel.c) (code from W. Webber)
+       bug in remove_dust (remove.c) fixed
+       for fonts bigger than 20x40 smooth_borders() changed (b/w-scans)
+       bug in O0-detection fixed
+
+ 0.37   best-fit generates probability, not perfect but better results
+        bug in line detection removed (happens for lot of small boxes)
+        progress output (option -x <fileID|fname>)
+        counting versions number as floating point now
+        MACRON and DOT_ABOVE (not complete) defined (latin2)
+        adaptions for 5x7 and 6x12 screen font
+	doc/ocr.tex changed to doc/gocr.html (now independent of LaTeX)
+        symbols {} added
+        OCR-B font tested succesfull
+        better headline/picture distinction
+        bug removed (struct box.modifier is wchar_t now)
+
+        known bugs: to much newlines
+
+ 0.3.6
+        CARON and Omega defined,
+        output of not defined chars (HTML="&#xxx;", TeX="\symbol{xxx}")
+        system dependend bug: isupper(>255) SIGSEGV fixed
+        better line detection for lines with lowercase chars only
+        lot of possible SIGSEGV in list_del() fixed
+        barcode recognition (UPC,code128)
+        .ps .eps via pstopnm supported
+        -m 256 switches off the main ocr engine (usefull together with -m 2 for identical chars)
+        strings added to database ("ff","ft","special-symbol")
+        gocr.tcl adapted to gocr v0.3
+        internal detection probability introduced
+
+ 0.3.5
+        minor and major fixes (string\0 bugs)
+        memory leak fixes by Duncan Edwards
+        layout analysis or zoning (-m 4) improved, 
+        now it detects pictures and columns much better
+        the behavior of setting threshold (-l) is slightly changed
+        wcsdup defined for non-gnu-systems (BSD), further Problems?
+        better context correction for 10 (IO,lO)
+        Fixes for S.Koledin examples "GlS"
+        Euro-currency-sign detection added
+        better pitch estimation for proportional font (needs to be improved)
+        make install DESTDIR= instead configure --prefix= (better?)
+        use wchar_t by default, more simple code and -f works with nonLinuxOS
+        line detection more robust against vertical glued chars (js)
+        -f UTF8 added (usefull for xterm -u8), should be default?
+        handle vertical glued boxes (ex: g over T)
+ 0.3.4
+        some BSD adaptions (no WCHAR?), tell me if there are still problems
+        use unicode in database (4-8 hex digits)
+        new option: -p database_path/
+        TILDE fixed, #, &AElig;, &Aring;, etc. added (swedish,norwegian)
+        layout analysis improved
+ 0.3.3
+        database (-m 2) bug fixed and interactive mode (-m 130) added
+          its not finished, but you can test it
+          result should be ok for machine generated images (no scans)           
+        engine improved a bit
+ 0.3.2
+        ocr-engine improved for screen fonts (thanks for examples)
+        option -f [HTML,TeX,...] added
+ 0.3.1
+        make install updated
+ 0.3.0  some parts of the code reviewed (most work done by Bruno Barberi Gnecco)
+        tkispell patch from David Pinson (exec bug fixed)
+	gnome frontend added (Dany De Bontrider)
+        acute, grave, circumflex ... detection
+        C++ parts rewritten into C, and much more (see REVIEW)
+ 0.2.7  lib-patch from Klaas Freitag inserted, engine improved
+        option -n 1 detect only numbers, get threshold value by otsu.cc
+        xxx.pnm.bz2 can be used on linux systems bzip2 installed
+ 0.2.6  pipes used on POSIX2-systems for easier use of jpg,gif,tiff,pnm.gz-files
+        example: gocr text.jpg; gocr text.pnm.gz
+        verbose output on stderr, text output on stdout,
+        redirection of output possible (-e, -o, example: -e /dev/stdout)
+        engine upgraded a bit  (thx for the new sample files)
+        gocr.tcl upgraded (save options, save text)
+        DOS/WIN95-EXE created, download GOCREXE.ZIP (v0.2.5)
+ 0.2.5  program convert renamed to jconv
+        you can choose stdin as input now, for using conversion tools
+	example: djpeg -pnm -gray text.jpg | gocr -i -
+        option "--help" added, some bugs removed
+	amiga.h added for SAS/C under AmigaOS (suggested by Uffe Holst)
+	line detection changed (faster?)
+	importing gocr in your C++ application is easier now (see fkt pgm2asc)
+	argument can be given instead of option -i (this is more natural)
+	some reorganization of code (not finished)
+	2000 downloads counted !!! Jun2000
+        SourceForge.net used for gocr (project: jocr, other gocr exist there)
+        bugs in dust removing, line detection and zoning fixed (rewritten)
+        first version of tcl/tk-GUI, test it!
+        rekursive function frame_nn() replaced by labyrint-algorithm (no extensiv stack used)
+        gluing of broken chars added, removing glued serifs (on small fonts)
+        new bugs added :;
+ 0.2.4a2 some details are added (better dust removing and char division)
+ 0.2.4  three char division (connected chars), dust removing
+ 0.2.3	add layout analysis (very slowly, try -m 4), engine modified
+        better distance function, engine updated, database added for testing
+	1000 downloads counted !!! May2000
+ 0.2.2	gocr_0_2.tgz expands into gocr_0_2 directory (thanks to zz99zz)
+	engine upgraded a bit, some bugs fixed (umlaut, thin lines)
+	short documentation added (ocr.tex)
+	colored output (out30.bmp) for test/development-mode
+	bug: read ASC-PBM and PCX (1 bit) fixed
+ 0.2.1	first official release on freshmeat.net March 2000
+ 0.2	line scanning added
+ 0.1	project started (not documented), autumn 1998 - summer 1999

data/src/gocr-0.48/INSTALL

@@ -0,0 +1,83 @@
+			  INSTALLING gOCR
+
+
+INSTALLING BINARIES
+-------------------
+Be sure that you have all the libraries needed. To install a binary package,
+do the following:
+
+1. Unpack the archive if you have not done so already:
+
+	tar -xzf gocr[version].tar.gz
+
+on older tar versions, the above line might not work. If so, try the following:
+
+	gzip -cd gocr[version].tgz | tar -xf -
+
+This creates the directory ./gocr[version] containing the source from
+the main archive.
+
+2. Change to gocr directory and run make (use GNU Make).
+
+	cd gocr[version]; make install
+
+That's it.
+
+INSTALLING FROM SOURCE 
+----------------------
+
+Requirements
+------------
+You'll need a compiler; we recommend gcc, but the code should compile in any
+good one. gcc is available at http://gcc.gnu.org. I had some problems with gcc
+2.95.1 (it consumed a LOT of memory while compiling ocr0.c). 2.95.2 seems to
+be better.
+
+gOCR provides some simple functions to read/write pnm archives. Though not 
+needed, we strongly suggest, however, that you install the NetPBM package. Its
+official URL is: http://download.sourceforge.net/netpbm/.
+
+Installing this package will add support to many different image formats. 
+If you have a NetPBM version older than August 2000, we suggest that you
+download a more recent one, to take advantage of the new PAM functions.
+
+To create some of the examples provided, you'll need transfig.
+This is completely optional.
+
+Procedure
+---------
+1. Unpack the archive if you have not done so already:
+
+	tar -xzf gocr[version].tar.gz
+
+on older tar versions, the above line might not work. If so, try the following:
+
+	gzip -cd gocr[version].tgz | tar -xf -
+
+This creates the directory ./gocr[version] containing the source from
+the main archive.
+
+2. Change to gocr directory and run configure.
+
+	cd gocr[version]; ./configure
+
+For a list of options, try ./configure --help.
+If something goes wrong, try to run autoconf.
+
+3. Run make (GNU Make). This can take a while.
+
+	make
+
+4. gOCR comes with some examples, which are generated from xfig-files.
+   If you have transfig installed, you can make them:
+
+	make examples
+
+5. Install the binaries. You may need to do this as root.
+
+	make install
+
+6. Run gocr, or the frontend you chose.
+
+	gocr -h			Shows help
+	gocr.tcl		Runs Tcl GUI

data/src/gocr-0.48/Makefile

@@ -0,0 +1,193 @@
+#
+#  type "make help" for help
+#
+# TODO: examples
+#       add rpm to dist package, man page
+#
+# Changes:
+# - be sure that configure is called after untgz, tar original file attributes
+# - suggestion of Marcel Pol 6Dec2001:
+#      make install DESTDIR=$RPM_BUILD_ROOT
+#
+
+prefix = /usr/local
+#bindir = $(prefix)/bin
+bindir = /usr/local${exec_prefix}/bin
+
+SHELL = /bin/sh
+# this does not work on SuSE 6.0, why? (autoconf 2.12 do not set /bin/sh ?)
+#SHELL = bash #
+INSTALL = /usr/bin/install -c
+CC = gcc
+CFLAGS = -g -O2
+# following DEFs are not used, but I play with it for training
+CPPFLAGS = -Wall -g -fexceptions -DDO_DEBUG=1 
+DEFS = -DHAVE_CONFIG_H
+includedir = ${prefix}/include
+#
+# -pedantic -ansi -Wall
+LDFLAGS = -lm 
+LIBS = -lnetpbm 
+
+# RANLIB = @RANLIB@
+# AR = @AR@
+
+
+# files for devel.tgz
+FILES = \
+ AUTHORS Makefile Makefile.in bin/ doc/ include/ examples/ man/ src/\
+ BUGS README make.bat CREDITS READMEde.txt REMARK.txt\
+ HISTORY REVIEW configure gpl.html INSTALL TODO configure.in\
+ install-sh gocr.spec .cvsignore
+
+# files for distribution
+AFILES = $(FILES) lib/
+
+DIRS = doc/ include/ man/ examples/ bin/ src/ lib/
+
+# export all make-variables to submakes - said to be not working on IRIS
+
+# default rule
+default: all
+
+.PHONY : src doc examples help clean proper distclean dist tgz rpm libs
+
+# example file generation takes lot of memory and time, do it explicitely
+# by make examples
+all:	src Makefile
+	@echo " --- for help do: make help ---"
+	@echo " --- for documentation do: make doc ---"
+	@echo " --- for examples do: make examples ---"
+
+include/config.h: include/config.h.in configure
+	./configure
+
+configure: configure.in
+	autoconf
+
+Makefile: Makefile.in configure
+	./configure
+
+src/Makefile: src/Makefile.in configure
+	./configure
+
+src:	src/Makefile
+	$(MAKE) -C src all
+
+libs:	src/Makefile
+	$(MAKE) -C src libs
+
+man:
+	$(MAKE) -C man all
+
+doc:
+	$(MAKE) -C doc all
+
+examples:
+	$(MAKE) -C examples all
+
+help:
+	@printf "make            - compile all\n"
+	@printf "make libs       - compile libraries libPgm2asc.{a,so}\n"
+	@printf "make src        - build lib and gocr\n"
+	@printf "make man        - build manual\n"
+	@printf "make doc        - make documentation\n"
+	@printf "make examples   - create examples ./examples/\n"
+	@printf "make clean      - erase temporary files\n"
+	@printf "make proper     - erase all created files\n"
+	@printf "make install    - Really? Its development version!\n"
+	@printf "make uninstall  - remove installed files from the system\n"
+
+
+# you can override this variable by: make install DESTDIR=yourpath
+DESTDIR=/usr/local
+.PHONY : install uninstall test examples
+install:
+	$(MAKE) -C src install
+	$(MAKE) -C man install
+	# following steps are not needed for end users, but cost dependencies
+	# therefore removed in 0.48
+	# $(MAKE) -C doc install
+	# $(MAKE) -C examples install
+	# $(MAKE) -C frontend install
+
+uninstall:
+	$(MAKE) -C src uninstall
+	$(MAKE) -C man uninstall
+	# $(MAKE) -C doc uninstall
+	# $(MAKE) -C examples uninstall
+	# $(MAKE) -C frontend uninstall
+
+# generate version file before packaging (most up to date)
+#  release is the date of the last modified src file (for bug reports)
+#  to distinguish different developper versions of same version number
+include/version.h: src/*.[ch] Makefile
+	echo "#define version_string \"0.48\"" > $@
+	echo "#define release_string \"`date +%Y%m%d`\"" >> $@
+
+dist: include/version.h
+	echo gocr-0.48 > .fname
+	-rm -rf `cat .fname`
+	mkdir `cat .fname`
+	# create subdirs, because cp -r bin/gocr.tcl jocr => jocr/gocr.tcl
+	(cd `cat .fname`; mkdir $(DIRS))
+	cp -r -p -d $(AFILES) `cat .fname`
+	$(MAKE) -C `cat .fname` proper
+	# for Win, DOS and Mac no configure available, reset config.h
+	cp `cat .fname`/include/config.h.in `cat .fname`/include/config.h
+	touch `cat .fname`/configure   # Makefile will be updated
+	tar chzf ../`cat .fname`.tar.gz `cat .fname`
+	-gpg -ab --default-key 0x53BDFBE3 ../`cat .fname`.tar.gz # .asc
+	ls -l ../`cat .fname`.tar.gz{,.asc}
+	-rm -rf `cat .fname` .fname
+
+
+# the tgz-option is only for the author, to carry the sources home
+tgz: include/version.h
+	mkdir jocr		# causes an error if exist
+	# create subdirs, because cp -r bin/gocr.tcl jocr => jocr/gocr.tcl
+	(cd jocr; mkdir $(DIRS))
+	-cp -rup -d $(FILES) CVS jocr
+	$(MAKE) -C jocr proper
+	if test -d jocr/src/api; then echo "--- rm -r jocr/src/api ---"; fi
+	-rm -rf jocr/src/api
+	# -rm -rf jocr/CVS jocr/*/CVS jocr/*/*/CVS # CVS tree
+	-rm -rf jocr/Makefile jocr/src/Makefile jocr/include/config.h
+	tar chzf ../jocr.tgz jocr
+	-gpg -ab --default-key 0x53BDFBE3 ../jocr.tgz # .asc
+	-cp ../jocr.tgz ../jocr.tgz.`date +%y%m%d` # backup, remove later
+	ls -l ../jocr.tgz{,.asc}
+	-rm -rf jocr
+
+# the rpm option is for the author, to create simple rpm packages
+TRPM = $(HOME)/tmp_gocr_build
+# only gocr?
+#VERSION=$(shell sed -e '/version_string/!d' -e 's/[^0-9.]*\([0-9.]*\).*/\1/' -e q src/gocr.c)
+rpm:
+	echo "%_topdir $(TRPM)" > ~/.rpmmacros
+	mkdir -p $(TRPM)/{SOURCES,SPECS,BUILD,RPMS,SRPMS}
+	sed "s/version.*[0-9]\.[0-9]*/version 0.48/"\
+	 gocr.spec >$(TRPM)/SPECS/gocr.spec
+	cp ../gocr-0.48.tar.gz $(TRPM)/SOURCES
+	#rpmbuild -ba --nobuild gocr.spec  # bin+src-rpm
+	(cd $(TRPM)/SPECS; rpmbuild -bb gocr.spec)
+	rpm -qil -p $(TRPM)/RPMS/i?86/gocr-0.48-*.i?86.rpm
+
+# PHONY = don't look at file clean, -rm = start rm and ignore errors
+.PHONY : clean proper
+clean:
+	-rm -f config.cache config.status config.log
+	-rm -f *.aux *.log *.dvi *.ps *.lj *~ gocr.ini out.txt
+	-rm -f convert.cc convert convert.o	# remove v0.2.4 rests
+	$(MAKE) -C src clean
+	$(MAKE) -C doc clean
+	$(MAKE) -C examples/ clean
+
+
+distclean: proper
+
+proper: clean
+	$(MAKE) -C src/ proper
+	$(MAKE) -C doc proper
+	$(MAKE) -C examples/ proper
+	-rm -f gocr bin/gocr libPgm2asc.* out??.bmp