isbn 2.0.4 → 2.0.5

data/src/gocr-0.48/doc/unicode.txt

@@ -1,57 +0,0 @@
-This file is intended to clarify why and how we are using Unicode in gocr. It's
-probably only interesting if you intend to do something similar in a project of
-yours or to develop gocr.
-
-History
-0.1	initial version
-
----
-Why to use Unicode? While in this early development stage gocr doesn't
-recognize much more than the ASCII characters, we hope that someday it will
-support many different languages with different character sets; that it will
-recognize mathematical expressions, and so on. Even in this early stage, we are
-trying to support other Latin languages --- accented characters. Since once we
-aren't using ASCII characters anymore we are subject to the character set
-loaded in the machine if we use the 0x80-0xFF characters, we had to solve the
-problem.
-
-Against what Andrew Tanenbaum once said, "The good thing about standards is
-that there are so many to choose from", we decided to not invent a new one and
-stick to one of the current; Unicode is the most famous, so we chose it.
-
-To my dismay, Unicode's support, at this time, sucks. There are few libraries
-around to deal with it, contrary to what one would expect. The libraries I
-found, though very good, did not provide the kind of support we needed in gocr:
-to work internally with hundreds of different characters. They were all focused
-in handling external files, user interface --- i18n, in short --- something that
-I'm sure is much more needed and used than what gocr needs.
-
-That's why we wrote our own Unicode code. We implemented only what we needed,
-and in a practical way to the developer --- composing characters, etc. Since no
-one I know will want the output of their scanned and OCR document in Unicode or
-UTF-8 format (though I hope that one format will eventually be used in every OS
-and computer around, and ASCII will go to a museum, and though gocr can output
-in one of these formats too), we had to output in some format more friendly;
-the choices are existing character maps, TeX, SGML and HTML initially, and who
-knows what else later. Once we can recognize the text and keep the formatting,
-these formats will be desired even more.
-
-How to implement it (careful: developer's view)? Fortunatedly, there is partial
-support for it now. The wchar_t type defined in <stddef.h> is a standard (only
-sometimes 16, sometimes 32, perhaps even 64 somewhere). Do we need the libc's
-string functions? If we do, they also exist for wchar_t. Some conversion
-functions were needed: ASCII -> Unicode, Unicode -> everything else. 
-
-The ASCII -> Unicode conversion (done by the compose() function) is written to
-be called by the ocr engine, when it recognizes a character. You can also use
-the Unicode codes #defined in unicode.h, but the compose function allows a 
-simpler use. It's recommended to use the symbols itself for ASCII codes (don't
-need to LATIN_CAPITAL_LETTER_A, use 'A').
-
-The Unicode -> etc conversion (done by decode()) is a bit more difficult
-sometimes, since previous symbols may interact with the current one. For
-example, if you're converting to TeX, two characters that are in math mode will
-call two times math mode; for example, "\( \pi \) \( \iota \)", instead of 
-"\( \pi \iota \)". Possibly a wider conversion function, decode_text(), which
-deals with the entire text at once should be provided; this function will also
-create headers, etc.

data/src/gocr-0.48/examples/.#Makefile.1.22

@@ -1,166 +0,0 @@
-#
-# using convert from ImageMagick instead of my own jconv version v0.2.8
-#   to crop the example images
-#
-# Version: @(#)ImageMagick 4.1.6 99/01/01 cristy@mystic.es.dupont.com
-# Copyright: Copyright 1999 E. I. du Pont de Nemours and Company
-# ... hmm, convert seems to use a lot of memory, pnmcrop works better
-CROPPG = convert -crop 0x0+1+1
-
-.PHONY: all examples fonts install uninstall clean proper proper_old gif jpg png
-
-all: examples
-
-help:
-	echo " make examples       # Fig-examples (very fast)"
-	echo " make examples_tex   # TeX-examples (takes lot of time)"
-	echo " make [proper|clean] # remove non source stuff"
-
-examples: font21.pcx font22.pcx font23.pcx font24.pcx ex.pcx inverse.pcx\
- rotate45.pcx
-	ls -l *.pcx
-
-examples_tex: text.pbm font0.pbm font1.pbm font2.pbm polish.pbm man.pbm
-# what about small.pbm? anyone remember?
-
-.SUFFIXES: .ps .tex .dvi .fig .pcx .png .jpg .gif .pbm .gz
-.tex.dvi:
-	latex $*.tex
-
-.dvi.ps:
-	dvips -E -o $*.ps $*.dvi    # -PAPERSIZE=a4
-
-# default font size is 11*mag
-# fig2dev can create pcx directly, but only unpacked and incompatible to xli
-.fig.pcx:
-	fig2dev -L ppm -m 3 $< | ppmtopcx -packed >$@
-
-.fig.pbm:
-	fig2dev -L ppm -m 3 $< | ppmtopgm | pgmtopbm -threshold >$@
-
-.fig.png:
-	fig2dev -L png -S 4 -m 3 $< >$@
-
-.fig.gif:
-	fig2dev -L gif -S 4 -m 3 $< >$@
-
-.fig.jpg:
-	fig2dev -L jpeg -S 4 -q 25 -m 3 $< >$@
-
-
-# some make versions does not set $< in explicit rules (info autoconf)
-font21.pcx: font2.fig
-	fig2dev -L ppm -m 2 font2.fig | ppmtopcx -packed >$@
-	# fig2dev -L pcx -m 2 font2.fig $@
-
-font22.pcx: font2.fig
-	fig2dev -L ppm -m 3 font2.fig | ppmtopcx -packed >$@
-	# fig2dev -L pcx -m 3 font2.fig $@
-
-font23.jpg: font2.fig
-	fig2dev -L jpeg -m 4 font2.fig $@
-
-font23.pgm: font2.fig
-	fig2dev -L ppm -m 4 font2.fig | ppmtopgm >$@
-
-font23.pbm: font2.fig
-	fig2dev -L ppm -m 4 font2.fig | ppmtopgm | pgmtopbm >$@
-
-font23.gif: font2.fig
-	fig2dev -L gif -m 4 font2.fig $@
-
-font23.pnm: font23.gif
-	giftopnm $< >$@
-
-font23.pcx: font2.fig
-	fig2dev -L ppm -m 4 font2.fig | ppmtopcx -packed >$@
-
-font24.pcx: font2.fig
-	fig2dev -L ppm -m 5 font2.fig | ppmtopcx -packed >$@
-
-font.tex: font1.tex
-	cp font1.tex font.tex
-
-# unfortunatly gs always creates a4 from boxed-ps, therefore we must crop it
-# gs options: pgmraw, pcxmono, laserjet
-font0.pbm: font.ps Makefile
-	gs -dNOPAUSE -q -r600 -sDEVICE=pbmraw \
-	 -sOutputFile=font0.pbm - < font.ps
-#	$(CROPPG) font0.pbm font0.pbm
-	pnmcrop font0.pbm >a.pbm; mv a.pbm font0.pbm
-
-font1.pbm: font.ps Makefile
-	gs -dNOPAUSE -q -r300 -sDEVICE=pbmraw \
-	 -sOutputFile=font1.pbm - < font.ps
-#	$(CROPPG) font1.pbm font1.pbm
-	pnmcrop font1.pbm >a.pbm; mv a.pbm font1.pbm
-
-font2.pbm: font.ps Makefile 
-	gs -dNOPAUSE -q -r150 -sDEVICE=pbmraw \
-	 -sOutputFile=font2.pbm - < font.ps
-#	$(CROPPG) font2.pbm font2.pbm
-	pnmcrop font2.pbm >a.pbm; mv a.pbm font2.pbm
-
-polish.pbm: polish.ps Makefile 
-	gs -dNOPAUSE -q -r200 -sDEVICE=pbmraw \
-	 -sOutputFile=polish.pbm - < polish.ps
-#	$(CROPPG) polish.pbm polish.pbm
-	pnmcrop polish.pbm >a.pbm; mv a.pbm polish.pbm
-
-text.pbm: text.ps Makefile
-	gs -dNOPAUSE -q -r150 -sDEVICE=pbmraw \
-	 -sOutputFile=text.pbm - < text.ps
-#	 $(CROPPG) text.pbm text.pbm
-	pnmcrop text.pbm >a.pbm; mv a.pbm text.pbm
-	
-small.pbm: small.ps Makefile
-	gs -dNOPAUSE -q -r150 -sDEVICE=pbmraw \
-	 -sOutputFile=small.pbm - < small.ps
-#	 $(CROPPG) text.pbm text.pbm
-	pnmcrop small.pbm >a.pbm; mv a.pbm small.pbm
-
-# change this to make a man page to a test.pbm file
-man.pbm: Makefile
-	man -Tdvi man >man.dvi
-	dvips -o man.ps man.dvi
-	gs -dNOPAUSE -q -r300 -sDEVICE=pbmraw \
-	 -sOutputFile=man.pbm - < man.ps
-#	$(CROPPG) man.pbm man.pbm
-	pnmcrop man.pbm >a.pbm; mv a.pbm man.pbm
-	rm -f man.ps man.dvi
-
-fonts: font0.pbm font1.pbm font2.pbm
-
-clean:
-	-rm -f a *.bak *.aux *.log *.dvi man.ps text.ps font.ps polish.ps *~
-
-# two ways to remove examples
-# 1) expand all *.gif *.p?m ... and check if basname.fig exist
-# 2) expand all *.fig and remove basename.{gif,p?m}
-# works only with GnuMake:
-suffix:=%.pbm %.pgm %.ppm %.pcx %.png %.gif %.jpg
-figobj:= $(filter $(suffix),$(wildcard $(patsubst %.fig,%.*,$(wildcard *.fig))))
-# figobj:= $(foreach var,$(wildcard *.p[bgp]m *.pcx *.png *.gif *.jpg),$(if $(wildcard $(basename $(var)).fig),$(var)))
-# shell: 
-proper: clean
-	-rm -f ./font2[1234].{p[bgp]m,pcx,png,gif,jpg}
-	-rm -f $(figobj)
-
-proper_old:
-	# -rm -f ./{ex,inverse,rotate45,font2[1234]}.{p[bgpna]m,pcx,png,gif,jpg}
-	-for xx in *.fig; do\
-	 rm -f ./$$(echo $${xx} | sed 's/.fig$$//'){,1,2,3,4}.{p[bgpn]m,pcx,png,gif,jpg} 2>/dev/null;\
-	done
-
-gif: $(patsubst %.fig,%.gif,$(wildcard *.fig))
-	ls -l *.gif
-
-png: $(patsubst %.fig,%.png,$(wildcard *.fig))
-	ls -l *.png
-
-jpg: $(patsubst %.fig,%.jpg,$(wildcard *.fig))
-	ls -l *.jpg
-
-install:
-
-uninstall:

data/src/gocr-0.48/examples/4x6.txt

@@ -1,2 +0,0 @@
-ABCD abcd EFGHI efghi JKLMN jklmn OPQR opqr
-STUVW stuvw XYZ xyz 12345 67890  !?'&/\=+-*#(){}[]<>

data/src/gocr-0.48/examples/5x7.png.txt

@@ -1,2 +0,0 @@
-ABCD abcd EFGHI efghi JKLMN jklmn OPQR opqr
-STUVW stuvw XYZ xyz 12345 67890  !?'&/\=+-*#(){}[]<>

data/src/gocr-0.48/examples/5x8.png.txt

@@ -1,2 +0,0 @@
-ABCD abcd EFGHI efghi JKLMN jklmn OPQR opqr
-STUVW stuvw XYZ xyz 12345 67890  !?'&/\=+-*#(){}[]<>

data/src/gocr-0.48/examples/Makefile

@@ -1,166 +0,0 @@
-#
-# using convert from ImageMagick instead of my own jconv version v0.2.8
-#   to crop the example images
-#
-# Version: @(#)ImageMagick 4.1.6 99/01/01 cristy@mystic.es.dupont.com
-# Copyright: Copyright 1999 E. I. du Pont de Nemours and Company
-# ... hmm, convert seems to use a lot of memory, pnmcrop works better
-CROPPG = convert -crop 0x0+1+1
-
-.PHONY: all examples fonts install uninstall clean proper proper_old gif jpg png
-
-all: examples
-
-help:
-	echo " make examples       # Fig-examples (very fast)"
-	echo " make examples_tex   # TeX-examples (takes lot of time)"
-	echo " make [proper|clean] # remove non source stuff"
-
-examples: font21.pcx font22.pcx font23.pcx font24.pcx ex.pcx inverse.pcx\
- rotate45.pcx
-	ls -l *.pcx
-
-examples_tex: text.pbm font0.pbm font1.pbm font2.pbm polish.pbm man.pbm
-# what about small.pbm? anyone remember?
-
-.SUFFIXES: .ps .tex .dvi .fig .pcx .png .jpg .gif .pbm .gz
-.tex.dvi:
-	latex $*.tex
-
-.dvi.ps:
-	dvips -E -o $*.ps $*.dvi    # -PAPERSIZE=a4
-
-# default font size is 11*mag
-# fig2dev can create pcx directly, but only unpacked and incompatible to xli
-.fig.pcx:
-	fig2dev -L ppm -m 3 $< | ppmtopcx -packed >$@
-
-.fig.pbm:
-	fig2dev -L ppm -m 3 $< | ppmtopgm | pgmtopbm -threshold >$@
-
-.fig.png:
-	fig2dev -L png -S 4 -m 3 $< >$@
-
-.fig.gif:
-	fig2dev -L gif -S 4 -m 3 $< >$@
-
-.fig.jpg:
-	fig2dev -L jpeg -S 4 -q 25 -m 3 $< >$@
-
-
-# some make versions does not set $< in explicit rules (info autoconf)
-font21.pcx: font2.fig
-	fig2dev -L ppm -m 2 font2.fig | ppmtopcx -packed >$@
-	# fig2dev -L pcx -m 2 font2.fig $@
-
-font22.pcx: font2.fig
-	fig2dev -L ppm -m 3 font2.fig | ppmtopcx -packed >$@
-	# fig2dev -L pcx -m 3 font2.fig $@
-
-font23.jpg: font2.fig
-	fig2dev -L jpeg -m 4 font2.fig $@
-
-font23.pgm: font2.fig
-	fig2dev -L ppm -m 4 font2.fig | ppmtopgm >$@
-
-font23.pbm: font2.fig
-	fig2dev -L ppm -m 4 font2.fig | ppmtopgm | pgmtopbm >$@
-
-font23.gif: font2.fig
-	fig2dev -L gif -m 4 font2.fig $@
-
-font23.pnm: font23.gif
-	giftopnm $< >$@
-
-font23.pcx: font2.fig
-	fig2dev -L ppm -m 4 font2.fig | ppmtopcx -packed >$@
-
-font24.pcx: font2.fig
-	fig2dev -L ppm -m 5 font2.fig | ppmtopcx -packed >$@
-
-font.tex: font1.tex
-	cp font1.tex font.tex
-
-# unfortunatly gs always creates a4 from boxed-ps, therefore we must crop it
-# gs options: pgmraw, pcxmono, laserjet
-font0.pbm: font.ps Makefile
-	gs -dNOPAUSE -q -r600 -sDEVICE=pbmraw \
-	 -sOutputFile=font0.pbm - < font.ps
-#	$(CROPPG) font0.pbm font0.pbm
-	pnmcrop font0.pbm >a.pbm; mv a.pbm font0.pbm
-
-font1.pbm: font.ps Makefile
-	gs -dNOPAUSE -q -r300 -sDEVICE=pbmraw \
-	 -sOutputFile=font1.pbm - < font.ps
-#	$(CROPPG) font1.pbm font1.pbm
-	pnmcrop font1.pbm >a.pbm; mv a.pbm font1.pbm
-
-font2.pbm: font.ps Makefile 
-	gs -dNOPAUSE -q -r150 -sDEVICE=pbmraw \
-	 -sOutputFile=font2.pbm - < font.ps
-#	$(CROPPG) font2.pbm font2.pbm
-	pnmcrop font2.pbm >a.pbm; mv a.pbm font2.pbm
-
-polish.pbm: polish.ps Makefile 
-	gs -dNOPAUSE -q -r200 -sDEVICE=pbmraw \
-	 -sOutputFile=polish.pbm - < polish.ps
-#	$(CROPPG) polish.pbm polish.pbm
-	pnmcrop polish.pbm >a.pbm; mv a.pbm polish.pbm
-
-text.pbm: text.ps Makefile
-	gs -dNOPAUSE -q -r150 -sDEVICE=pbmraw \
-	 -sOutputFile=text.pbm - < text.ps
-#	 $(CROPPG) text.pbm text.pbm
-	pnmcrop text.pbm >a.pbm; mv a.pbm text.pbm
-	
-small.pbm: small.ps Makefile
-	gs -dNOPAUSE -q -r150 -sDEVICE=pbmraw \
-	 -sOutputFile=small.pbm - < small.ps
-#	 $(CROPPG) text.pbm text.pbm
-	pnmcrop small.pbm >a.pbm; mv a.pbm small.pbm
-
-# change this to make a man page to a test.pbm file
-man.pbm: Makefile
-	man -Tdvi man >man.dvi
-	dvips -o man.ps man.dvi
-	gs -dNOPAUSE -q -r300 -sDEVICE=pbmraw \
-	 -sOutputFile=man.pbm - < man.ps
-#	$(CROPPG) man.pbm man.pbm
-	pnmcrop man.pbm >a.pbm; mv a.pbm man.pbm
-	rm -f man.ps man.dvi
-
-fonts: font0.pbm font1.pbm font2.pbm
-
-clean:
-	-rm -f a *.bak *.aux *.log *.dvi man.ps text.ps font.ps polish.ps *~
-
-# two ways to remove examples
-# 1) expand all *.gif *.p?m ... and check if basname.fig exist
-# 2) expand all *.fig and remove basename.{gif,p?m}
-# works only with GnuMake:
-suffix:=%.pbm %.pgm %.ppm %.pcx %.png %.gif %.jpg
-figobj:= $(filter $(suffix),$(wildcard $(patsubst %.fig,%.*,$(wildcard *.fig))))
-# figobj:= $(foreach var,$(wildcard *.p[bgp]m *.pcx *.png *.gif *.jpg),$(if $(wildcard $(basename $(var)).fig),$(var)))
-# shell: 
-proper: clean
-	-rm -f ./font2[1234].{p[bgp]m,pcx,png,gif,jpg}
-	-rm -f $(figobj)
-
-proper_old:
-	# -rm -f ./{ex,inverse,rotate45,font2[1234]}.{p[bgpna]m,pcx,png,gif,jpg}
-	-for xx in *.fig; do\
-	 rm -f ./$$(echo $${xx} | sed 's/.fig$$//'){,1,2,3,4}.{p[bgpn]m,pcx,png,gif,jpg} 2>/dev/null;\
-	done
-
-gif: $(patsubst %.fig,%.gif,$(wildcard *.fig))
-	ls -l *.gif
-
-png: $(patsubst %.fig,%.png,$(wildcard *.fig))
-	ls -l *.png
-
-jpg: $(patsubst %.fig,%.jpg,$(wildcard *.fig))
-	ls -l *.jpg
-
-install:
-
-uninstall:

data/src/gocr-0.48/examples/color.fig

@@ -1,20 +0,0 @@
-#FIG 3.2
-Landscape
-Center
-Metric
-A4      
-100.00
-Single
--2
-1200 2
-2 2 0 1 7 7 60 0 20 0.000 0 0 -1 0 0 5
-	 1125 2880 4365 2880 4365 1485 1125 1485 1125 2880
-2 2 0 1 7 0 70 0 10 0.000 0 0 -1 0 0 5
-	 900 450 4500 450 4500 3150 900 3150 900 450
-2 2 0 1 2 2 55 0 20 0.000 0 0 -1 0 0 5
-	 2475 2700 4185 2700 4185 1935 2475 1935 2475 2700
-4 0 6 50 0 0 20 0.0000 4 270 720 1350 2160 step 2\001
-4 0 0 60 0 16 20 0.0000 4 225 3015 990 360 outer text Helvetica 20\001
-4 0 0 50 0 0 20 0.0000 4 195 3090 1170 1080 Inner-1 Times-Roman 20\001
-4 0 4 50 0 0 20 0.0000 4 195 2685 1305 1800 This is a box in a box.\001
-4 0 1 50 0 0 20 0.0000 4 270 1245 2700 2385 step 3 box\001

data/src/gocr-0.48/examples/ex.fig

@@ -1,16 +0,0 @@
-#FIG 3.2
-Landscape
-Center
-Metric
-A4      
-100.00
-Single
--2
-1200 2
-2 1 0 1 0 7 100 0 -1 0.000 0 0 -1 0 0 2
-	 360 225 585 225
-2 1 0 1 0 7 100 0 -1 0.000 0 0 -1 0 0 2
-	 4500 1305 4680 1305
-4 0 0 100 0 0 12 0.0000 4 225 3750 450 495 Special chars: \340\341\342\343\344\345\346\347 \300 \305 \306 \337 &$#% \370\330\253\273\242\265\001
-4 0 0 100 0 16 12 0.0000 4 225 4245 450 765 Special chars: \340\341\342\343\344\345\346\347 \300 \305 \306 \337 &$#% \370\330\253\273\242\265\001
-4 0 0 100 0 12 12 0.0000 4 210 4515 450 1080 Special chars: \340\341\342\343\344\345\346\347 \300 \305 \306 \337 &$#% \370\330\253\273\242\265\001