entangledstate-isbn 1.4.0 → 1.4.1

data/src/gocr-0.48/Makefile.in

@@ -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 = @prefix@
+#bindir = $(prefix)/bin
+bindir = @prefix@@bindir@
+
+SHELL = @SHELL@
+# this does not work on SuSE 6.0, why? (autoconf 2.12 do not set @SHELL@ ?)
+#SHELL = bash #
+INSTALL = @INSTALL@
+CC = @CC@
+CFLAGS = @CFLAGS@
+# following DEFs are not used, but I play with it for training
+CPPFLAGS = @CPPFLAGS@
+DEFS = @DEFS@
+includedir = @includedir@
+#
+# -pedantic -ansi -Wall
+LDFLAGS = @LDFLAGS@
+LIBS = @LIBS@
+
+# RANLIB = @RANLIB@
+# AR = @AR@
+@SET_MAKE@
+
+# 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=@prefix@
+.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 \"@PACKAGE_VERSION@\"" > $@
+	echo "#define release_string \"`date +%Y%m%d`\"" >> $@
+
+dist: include/version.h
+	echo gocr-@PACKAGE_VERSION@ > .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 $(TRPM)/{SOURCES,SPECS,BUILD,RPMS,SRPMS}
+	sed "s/version.*[0-9]\.[0-9]*/version @PACKAGE_VERSION@/"\
+	 gocr.spec >$(TRPM)/SPECS/gocr.spec
+	cp ../gocr-@PACKAGE_VERSION@.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-@PACKAGE_VERSION@-*.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

data/src/gocr-0.48/README

@@ -0,0 +1,165 @@
+			 GOCR (JOCR at SF.net)
+
+GOCR is an optical character recognition program, released under the
+GNU General Public License. It reads images in many formats  and outputs
+a text file. Possible image formats are pnm, pbm, pgm, ppm, some pcx and
+tga image files. Other formats like pnm.gz, pnm.bz2, png, jpg, tiff, gif,
+bmp will be automatically converted using the netpbm-progs, gzip and bzip2
+via unix pipe.
+A simple graphical frontend written in tcl/tk and some
+sample files are included.
+Gocr is also able to recognize and translate barcodes.
+You do not have to train the program or store large font bases.
+Simply call gocr from the command line and get your results.
+
+To see installation instructions, see the INSTALL file.
+
+How to start? (QUICK START)
+---------------------------
+Some examples of how you can use gocr:
+
+  gocr -h       			# help
+  gocr file.pbm				# minimum options
+  gocr -v 1 file.pbm >out.txt 2>out.log # generate text- and log file
+  djpeg -pnm -gray text.jpg | gocr -	# using JPEG-files
+  gzip -cd text.pbm.gz | gocr -		# using gzipped PBM-files
+  giftopnm text.gif | gocr -		# using GIF-files
+  gocr -v 1 -v 32 -m 4 file.pbm   	# zoning and out30.bmp output
+  xli -geometry 400x400 out30.bmp # see details using xli (recommanded viewer)
+  wish gocr.tcl			  # X11-tcl/tk-frontend (development version)
+  # see manual pages for more details
+
+
+How to get image files?
+-----------------------
+Scan text pages and save it as PGM/PBM/PNM file. Use a program such as
+The GIMP or Sane. You can also use netpbm-progs to convert several image 
+formats into PGM/PBM/PNM. The tool djpeg can be used to convert jpeg into pgm.
+If you have a POSIX compatible system like linux and PNM-tools, gzip and bzip2
+are installed, you are lucky and gocr will do conversion 
+from [.pnm.gz, .pnm.bz2, .jpg, .jpeg, .bmp, .tiff, .png, .ps, .eps]
+to [.pgm] for you. This list can easily be extended editing src/pnm.c.
+
+Gocr also comes with some examples, try: make examples.
+
+Memory limitations
+------------------
+WARNING!!!
+
+If you use a 300dpi scan of A4 letter, the image is about 2500x3500 pixels and
+gocr requires 8.75MB for storing the picture into the memory. Not only that,
+but gocr may create a 2nd copy, using a total of 17MB. This is independent
+of using b/w or gray-scale images. Be sure that you have enough RAM installed
+in your machine! Alternatively you can cut the picture into small pieces.
+You can use the pnmcut, from the netpbm package to cut the file. Example:
+
+pnmcut -left 0 -right 2500 -top 0 -height 1000 bigfile.pnm > smallfile.pnm
+
+And then use gocr in the cropped image as usual. Take care: if you chopp the
+characters, gocr won't be able to understand that line.
+
+Future versions will take care of this issue automatically.
+
+Limitations
+-----------
+gocr is still in its early stages. Your images should fit in these requirements
+if you want a good output:
+
+- good scans (all chars well seperated, one column, no tables etc, 12pt 300dpi)
+  should work well
+- fonts 20-60 pixels ( 5pt * 1in/72pt * 300 dpi = 20 dots )
+- output of image file for controlling detection
+
+And note that speed is very slow (this will be changed when recognition works 
+well)
+  12pt 300dpi 1700x950 16lines 700chars 22x28 P90=40s..90s v0.2.3 (gcc -O0)
+
+You can try to optimize the results:
+- make good scans/treat image
+- try to change the critical gray level (option -l <n>)
+- control the result on out10.png, out30.png (option -v 32)
+  example: ./gocr -v 32 -m 4 -m 256 -m 56 ~/aac.jpg # only check layout
+- enlarge option -d <n> for high resolution images which are noisy
+- try different combinations for option -m <n>
+- for thousends of documents with same font
+  you can use/create a database (-m 2/-m 130)
+- use options -d 0 -m 8 on screen shots (font8x12)
+- use filter option -C to through out wrong recognized chars (ex: gothic)
+
+What does >> NOT << work at the moment:
+- complex layouts (try option -m 4)
+- bad scans, noisy/snowy images, FAX-quality images
+- serif fonts, italic fonts, slanted fonts
+- handwritten texts (this is valid for the next ten years I guess)
+   the exisctence of autotrace can shorten this 
+- rotated images (but slightly rotated images should be no problem)
+- small fonts (fax like) or mix of different font size
+- colored images (use gray or black/white)
+- Chinese, Arabian, Egyptian, Cyrillic or Klingon fonts
+
+How it works or how it should work?
+- put the entire file into RAM (300dpi grayscale recommended)
+- remove dust and snow
+- detect small angle (lines which are not horizontal)
+- detect text boxes (option -m 4)
+- detect text-lines
+- detect characters
+- first step recognition (every character has its own empirical procedure)
+  - no neural network or similar general algorithms
+- analyze not detected chars by comparison with detected ones
+- try to divide overlapping chars
+- testwise: compare all letters (like compression of pictures)
+- for more details look to the gocr.html documentation
+
+Why the result of the new version are worse compared to the old version?
+- the algorithms of gocr are sometimes evolutionary, a fine tuned old
+  algorithm will be replased by a completly new algorithm which is more
+  general but a bit worse for your problem.
+  Please send your sample and give the new algo the chance to become
+  better as the old one.
+
+Security
+--------
+Because gocr only reads and writes files it is quite sure, except the
+popen-function which allows you to call gocr with non-pnm-image formats
+directly. The popen function can be misused to start other probably 
+dangerous programs.
+If you care about conversion to pnm format, you can safely disable
+popen-function by removing "#define HAVE_POPEN 1" from config.h before
+compiling the gocr package.
+
+
+How can you help gocr?
+----------------------
+- Send comments, ideas and patches (diff -ru gocr_original/ gocr_changed/).
+- If you have a lot of money, spend a bit (paypal). Ok, paypal has changed,
+  so please forget about it. Also the importand problem is now the missing
+  spare time for coding.
+- I always need example files (.pbm.gz or jpeg <100kB) for testing
+  the behavior of the ocr engine under different conditions, 
+  because scanning does take a lot of time which I do not have.
+  But do not send files which are not convertable by commercial ocr programs
+  or which are protected from copying and electronic processing by copyright.
+  That will help, to get the world's best OCR open source program. :) Thanks!
+- Please dont send captchas.
+- Send me your results (errors,num_chars,dpi) and if possible results
+  and name of professional OCR programs for statistics.
+- Read OCR literature, extract the essentials and send a short report
+  to me ;).
+- If you have a good idea, how to manage some OCR-tasks, tell me!
+- Tell your friends about gocr. Tell me about your success. Be happy.
+
+
+After all, is it gocr or jocr?
+------------------------------
+The original name of this project is gocr, from GNU Optical Character
+Recognition. Another project is using the same name, however; so the
+name was changed to jocr. If you have a good idea for a name, please
+send it.
+
+
+Latest news
+------------
+  http://jocr.sourceforge.net
+
+Authors: (see AUTHORS)

data/src/gocr-0.48/READMEde.txt

@@ -0,0 +1,80 @@
+
+This is the short german version for README.
+Dies ist die deutsche Kurzinformation fuer README.
+
+                      --- GOCR v0.38 ---
+
+Worum gehts?
+- OCR = optical character recognition = Schrifterkennung
+- liest pnm, pbm, pgm, ppm, einige pcx und tga Bilddateien
+   (auf un*x-systemen mit libpnm fast alle Formate)
+- gibt text aus
+- Dieses Programm ist herausgegeben unter GPL (General Public License).
+   Das bedeutet unter anderem:  FREI FUER ALLE BENUTZER.
+
+Wie kompilieren?
+  
+  gzip -cd gocr-0.38.tgz | tar xfv -   # auspacken
+  cd gocr-0.38	  # Ordner wechseln
+  ./configure     # Makefile anpassen
+  make  	  # gcc/g++ sollte installiert sein
+
+
+Wie starten?
+  gocr -h       	# Kurz(!)-Hilfe
+  gocr file.pbm		# minimale Argumente 
+  gocr -v 1 -v 32 -m 4 file.pbm # zusaetzlich debug-Modus und Layout-Analyse
+ Optionen (bitte auch das aktuelle Manual zu gocr (man gocr) ansehen!):
+  [-i] name - Bilddatei (pnm,pgm,pbm,ppm,pcx), - fuer stdin
+  -o name   - Ausgabefile (Umlenkung der Standardausgabe)
+  -e name   - Ausgabefile (Umlenkung der Fehlerausgabe)
+  -x name   - Fortschrittsanzeige (file, fifo oder fd=1..255)
+  -p name   - Verzeichnis der optionalen Datenbasis (z.B.: ./db/)
+  -l num    - Schwellenwert 0<160<=255
+  -d num    - Schmutzgroesse (Entfernen von Schmutz, -1=autodetect)
+  -s num    - Wortabstand in Punkten (0 = autodetect)
+  -v num    - Mehr Infos  [summiert]
+      1      mehr Informationen
+      2      Groesse der Boxen anzeigen (siehe -c)
+      4      Boxen anzeigen (siehe -c)
+      8      Ausgabe der Muster nach Erkennung
+     16      Zeilenerkennung ausgeben
+     32      debug-Ausgaben outXX.pgm
+  -c string - Liste der auszugebenen Zeichen (_ = nicht erkanntes Zeichen)
+  -C string - Zeichenfilter (z.B.: hexdigits: 0-9A-Fx, nur ASCII)
+  -m num    - Arbeitsarten, ~ = abschalten
+      2      Datenbank nutzen (in Entwicklung)
+      4      Layout-Analyse (zum Testen)
+      8      ~ vergleiche nichterkannte Zeichen
+     16      ~ Teile verklebte Zeichen
+     32      ~ Kontextkorrektur
+     64      Zeichen komprimieren
+    130      Datenbank erweitern (unbekannte Zeichen, Interaktiv)
+    256      OCR Engine abschalten, macht nur Sinn mit -m 2
+ Beispiel: gocr -v 6 -v 32 -c _YV text1.pbm
+ - Programm ist noch sehr langsam, bitte Geduld!
+  
+Was geht nicht?
+- vieles ... siehe README
+
+Wie koennen Sie helfen?
+- Schicken Sie Bemerkungen und KLEINE Beispieldaten als .pbm.gz. 
+- Geld oder einen neuen Notebook koennte ich auch brauchen (paypal).
+  Ok, paypal ist nicht mehr was es war, also vergesst es und mangelnde
+  Zeit zum programmieren ist jetzt das groessere Problem.
+- Wie finden Sie das Programm, wie viele Fehler erzeugt es im Vergleich
+  zu anderen OCR-Programmen?
+ (bitte Anzahl Fehler, Zeichen und Programmversion angeben)
+- Gute Ideen nehme ich gern entgegen
+  (d.h. kleine Aenderungen mit grosser Wirkung).
+- Lob und Tadel nehm ich ebenfalls gerne entgegen.
+
+Bugs:
+- Das Programm hat sicher viele Fehler, nur welche? (siehe README)
+
+Letzte Neuerungen:
+  http://jOCR.sourceforge.net
+
+Authoren: (siehe README und AUTHORS)
+
+                      --- HAVE FUN ---

data/src/gocr-0.48/REMARK.txt

@@ -0,0 +1,18 @@
+                                     
+testfile      size   num_c quality  time num_errors
+--------      x    y       -------  p1   p1 p2 p3
+g300a1.pbm  703  580   469 +        2s    4 -   0
+g300a2.pbm  724 1252  1021 +        5s    2 0   0
+g300b1.pbm 1564  277    55 +        4s    0 1   1
+g300b2.pbm  599 1319   860 snowy    9s   76 -  40
+g300b3.pbm  592 1324   934 snowy    7s   36 2  15
+g300c1.pbm  750 2771  2182 +       15s   35 1  14
+liebfrau1  2289 3200  1927 +       19s   13 0   8
+meraji1    1912 1355  1246 thinn   15s   65 4  40
+paraguay1  2617 1375  3280 frame   78s 1000 1  55
+
+p1=gocr0.2.4a3 on P400
+p2=recognita+4.0
+p3=gocr0.2.5
+
+most errors: connected chars, like fi,ff, italic font