tesseract_bin 1.0.0

data/test/helper.rb

@@ -0,0 +1,18 @@
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'test/unit'
+require 'shoulda'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'tesseract_bin'
+
+class Test::Unit::TestCase
+end

data/test/test_tesseract_bin.rb

@@ -0,0 +1,7 @@
+require 'helper'
+
+class TestTesseractBin < Test::Unit::TestCase
+  should "probably rename this file and start testing for real" do
+    flunk "hey buddy, you should probably rename this file and start testing for real"
+  end
+end

data/vendor/tesseract-2.04/AUTHORS

@@ -0,0 +1,8 @@
+Ray Smith (lead developer) <theraysmith@users.sourceforge.net>
+Phil Cheatle
+Simon Crouch
+Dan Johnson
+Mark Seaman
+Sheelagh Huddleston
+Chris Newton
+... and several others.

data/vendor/tesseract-2.04/COPYING

@@ -0,0 +1,23 @@
+This package contains the Tesseract Open Source OCR Engine.
+Orignally developed at Hewlett Packard Laboratories Bristol and
+at Hewlett Packard Co, Greeley Colorado, all the code
+in this distribution is now licensed under the Apache License:
+
+** Licensed under the Apache License, Version 2.0 (the "License");
+** you may not use this file except in compliance with the License.
+** You may obtain a copy of the License at
+** http://www.apache.org/licenses/LICENSE-2.0
+** Unless required by applicable law or agreed to in writing, software
+** distributed under the License is distributed on an "AS IS" BASIS,
+** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+** See the License for the specific language governing permissions and
+** limitations under the License.
+
+
+Other Dependencies and Licenses:
+================================
+The Aspirin/MIGRAINES system is no longer used.
+
+Tesseract can also make use of the libtiff library. (www.libtiff.org)
+Without libtiff, Tesseract can only read uncompressed and G3 compressed
+TIFF files.

data/vendor/tesseract-2.04/ChangeLog

@@ -0,0 +1,71 @@
+June  2006 - V1.0 of open source Tesseract checked-in.
+Sep 7 2006 - V1.01.
+          Added mfcpch.cpp and getopt.cpp for VC++.
+          Fixed problem with greyscale images and no libtiff.
+          Stopped debug window from being used for the usage output.
+          Fixed load of inttemp for big-endian architectures.
+          Fixed some Mac compilation issues.
+Oct 4 2006 - V1.02
+          Removed dependency on Aspirin.
+          Fixed a few missing Apache license headers.
+          Removed $log.
+Feb 2 2007 - V1.03
+          Added mftraining and cntraining.
+          Added baseapi with adaptive thresholding for grey and color.
+          Fixed many memory leaks.
+          Fixed several bugs including lack of use of adaptive classifier.
+          Added ifdefs to eliminate graphics code and add embedded platform support.
+          Incorporated several patches, including 64-bit builds, Mac builds.
+          Minor accuracy improvements.
+May 15 2007 - V1.04
+          Added dll exports for Windows.
+          Fixed name collisions with stl etc.
+          Made some preliminary changes ready for unicodeization.
+          Several bug fixes discovered during unicodeization.
+July 02 2007 - V2.00
+          Converted internal character handling to UTF8.
+          Trained with 6 languages.
+          Added unicharset_extractor, wordlist2dawg.
+          Added boxfile creation mode.
+          Added UNLV regression test capability.
+          Fixed problems with copyright and registered symbols.
+          Fixed extern "C" declarations problem.
+August 27 2007 - V2.01
+          Fixed UTF8 input problems with box file reader.
+          Fixed various infinite loops and crashes in dawg code.
+          Removed include of config_auto.h from host.h.
+          Added automatic wctype encoding to unicharset_extractor.
+          Fixed dawg table too full error.
+          Removed svn files from tarball.
+          Added new functions to tessdll.
+          Increased maximum utf8 string in a classification result to 8.
+
+January 23 2008 - V2.02
+          Improvements to clustering, training and classifier.
+          Major internationalization improvements for large-character-set
+          languages, eg Kannada.
+          Removed some compiler warnings.
+          Added multipage tiff support for training and running.
+          Updated graphics output to talk to new java-based viewer.
+          Added ability to save n-best lists.
+          Added leptonica support for more file types.
+          Improved Init/End to make them safe.
+          Reduced memory use of dictionaries.
+          Added some new APIs to TessBaseAPI.
+April 21 2008 - V2.02 (again)
+          Fixed namespace collisions with jpeg library (INT32).
+          Portability fixes for Windows for new code.
+          Updates to autoconf system for new code.
+April 22 2008 - V2.03
+          Fixed crash introduced in 2.02.
+	  Fixed lack of tessembedded.cpp in distribution.
+	  Added test for leptonica header files and conditional test for lib.
+June 30 2009 - V2.04
+	  Integrated bug fixes and patches and misc changes for portability.
+	  Integrated a patch to remove some of the "access" macros.
+	  Removed dependence on lua from the viewer, speeding it up
+	  dramatically.
+	  Fixed the viewer so it compiles and runs properly!
+	  Specifically fixing issues: 1, 63, 67, 71, 76, 81, 82, 106, 111,
+	  112, 128, 129, 130, 133, 135, 142, 143, 145, 147, 153, 154, 160,
+	  165, 170, 175, 177, 187, 192, 195, 199, 201, 205, 209, 108, 169

data/vendor/tesseract-2.04/INSTALL

@@ -0,0 +1,229 @@
+Copyright 1994, 1995, 1996, 1999, 2000, 2001, 2002 Free Software
+Foundation, Inc.
+
+   This file is free documentation; the Free Software Foundation gives
+unlimited permission to copy, distribute and modify it.
+
+Basic Installation
+==================
+
+   These are generic installation instructions.
+
+   The `configure' shell script attempts to guess correct values for
+various system-dependent variables used during compilation.  It uses
+those values to create a `Makefile' in each directory of the package.
+It may also create one or more `.h' files containing system-dependent
+definitions.  Finally, it creates a shell script `config.status' that
+you can run in the future to recreate the current configuration, and a
+file `config.log' containing compiler output (useful mainly for
+debugging `configure').
+
+   It can also use an optional file (typically called `config.cache'
+and enabled with `--cache-file=config.cache' or simply `-C') that saves
+the results of its tests to speed up reconfiguring.  (Caching is
+disabled by default to prevent problems with accidental use of stale
+cache files.)
+
+   If you need to do unusual things to compile the package, please try
+to figure out how `configure' could check whether to do them, and mail
+diffs or instructions to the address given in the `README' so they can
+be considered for the next release.  If you are using the cache, and at
+some point `config.cache' contains results you don't want to keep, you
+may remove or edit it.
+
+   The file `configure.ac' (or `configure.in') is used to create
+`configure' by a program called `autoconf'.  You only need
+`configure.ac' if you want to change it or regenerate `configure' using
+a newer version of `autoconf'.
+
+The simplest way to compile this package is:
+
+  1. `cd' to the directory containing the package's source code and type
+     `./configure' to configure the package for your system.  If you're
+     using `csh' on an old version of System V, you might need to type
+     `sh ./configure' instead to prevent `csh' from trying to execute
+     `configure' itself.
+
+     Running `configure' takes awhile.  While running, it prints some
+     messages telling which features it is checking for.
+
+  2. Type `make' to compile the package.
+
+  3. Optionally, type `make check' to run any self-tests that come with
+     the package.
+
+  4. Type `make install' to install the programs and any data files and
+     documentation.
+
+  5. You can remove the program binaries and object files from the
+     source code directory by typing `make clean'.  To also remove the
+     files that `configure' created (so you can compile the package for
+     a different kind of computer), type `make distclean'.  There is
+     also a `make maintainer-clean' target, but that is intended mainly
+     for the package's developers.  If you use it, you may have to get
+     all sorts of other programs in order to regenerate files that came
+     with the distribution.
+
+Compilers and Options
+=====================
+
+   Some systems require unusual options for compilation or linking that
+the `configure' script does not know about.  Run `./configure --help'
+for details on some of the pertinent environment variables.
+
+   You can give `configure' initial values for configuration parameters
+by setting variables in the command line or in the environment.  Here
+is an example:
+
+     ./configure CC=c89 CFLAGS=-O2 LIBS=-lposix
+
+   *Note Defining Variables::, for more details.
+
+Compiling For Multiple Architectures
+====================================
+
+   You can compile the package for more than one kind of computer at the
+same time, by placing the object files for each architecture in their
+own directory.  To do this, you must use a version of `make' that
+supports the `VPATH' variable, such as GNU `make'.  `cd' to the
+directory where you want the object files and executables to go and run
+the `configure' script.  `configure' automatically checks for the
+source code in the directory that `configure' is in and in `..'.
+
+   If you have to use a `make' that does not support the `VPATH'
+variable, you have to compile the package for one architecture at a
+time in the source code directory.  After you have installed the
+package for one architecture, use `make distclean' before reconfiguring
+for another architecture.
+
+Installation Names
+==================
+
+   By default, `make install' will install the package's files in
+`/usr/local/bin', `/usr/local/man', etc.  You can specify an
+installation prefix other than `/usr/local' by giving `configure' the
+option `--prefix=PATH'.
+
+   You can specify separate installation prefixes for
+architecture-specific files and architecture-independent files.  If you
+give `configure' the option `--exec-prefix=PATH', the package will use
+PATH as the prefix for installing programs and libraries.
+Documentation and other data files will still use the regular prefix.
+
+   In addition, if you use an unusual directory layout you can give
+options like `--bindir=PATH' to specify different values for particular
+kinds of files.  Run `configure --help' for a list of the directories
+you can set and what kinds of files go in them.
+
+   If the package supports it, you can cause programs to be installed
+with an extra prefix or suffix on their names by giving `configure' the
+option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'.
+
+Optional Features
+=================
+
+   Some packages pay attention to `--enable-FEATURE' options to
+`configure', where FEATURE indicates an optional part of the package.
+They may also pay attention to `--with-PACKAGE' options, where PACKAGE
+is something like `gnu-as' or `x' (for the X Window System).  The
+`README' should mention any `--enable-' and `--with-' options that the
+package recognizes.
+
+   For packages that use the X Window System, `configure' can usually
+find the X include and library files automatically, but if it doesn't,
+you can use the `configure' options `--x-includes=DIR' and
+`--x-libraries=DIR' to specify their locations.
+
+Specifying the System Type
+==========================
+
+   There may be some features `configure' cannot figure out
+automatically, but needs to determine by the type of machine the package
+will run on.  Usually, assuming the package is built to be run on the
+_same_ architectures, `configure' can figure that out, but if it prints
+a message saying it cannot guess the machine type, give it the
+`--build=TYPE' option.  TYPE can either be a short name for the system
+type, such as `sun4', or a canonical name which has the form:
+
+     CPU-COMPANY-SYSTEM
+
+where SYSTEM can have one of these forms:
+
+     OS KERNEL-OS
+
+   See the file `config.sub' for the possible values of each field.  If
+`config.sub' isn't included in this package, then this package doesn't
+need to know the machine type.
+
+   If you are _building_ compiler tools for cross-compiling, you should
+use the `--target=TYPE' option to select the type of system they will
+produce code for.
+
+   If you want to _use_ a cross compiler, that generates code for a
+platform different from the build platform, you should specify the
+"host" platform (i.e., that on which the generated programs will
+eventually be run) with `--host=TYPE'.
+
+Sharing Defaults
+================
+
+   If you want to set default values for `configure' scripts to share,
+you can create a site shell script called `config.site' that gives
+default values for variables like `CC', `cache_file', and `prefix'.
+`configure' looks for `PREFIX/share/config.site' if it exists, then
+`PREFIX/etc/config.site' if it exists.  Or, you can set the
+`CONFIG_SITE' environment variable to the location of the site script.
+A warning: not all `configure' scripts look for a site script.
+
+Defining Variables
+==================
+
+   Variables not defined in a site shell script can be set in the
+environment passed to `configure'.  However, some packages may run
+configure again during the build, and the customized values of these
+variables may be lost.  In order to avoid this problem, you should set
+them in the `configure' command line, using `VAR=value'.  For example:
+
+     ./configure CC=/usr/local2/bin/gcc
+
+will cause the specified gcc to be used as the C compiler (unless it is
+overridden in the site shell script).
+
+`configure' Invocation
+======================
+
+   `configure' recognizes the following options to control how it
+operates.
+
+`--help'
+`-h'
+     Print a summary of the options to `configure', and exit.
+
+`--version'
+`-V'
+     Print the version of Autoconf used to generate the `configure'
+     script, and exit.
+
+`--cache-file=FILE'
+     Enable the cache: use and save the results of the tests in FILE,
+     traditionally `config.cache'.  FILE defaults to `/dev/null' to
+     disable caching.
+
+`--config-cache'
+`-C'
+     Alias for `--cache-file=config.cache'.
+
+`--quiet'
+`--silent'
+`-q'
+     Do not print messages saying which checks are being made.  To
+     suppress all normal output, redirect it to `/dev/null' (any error
+     messages will still be shown).
+
+`--srcdir=DIR'
+     Look for the package's source code in directory DIR.  Usually
+     `configure' can determine that directory automatically.
+
+`configure' also accepts some other, not widely useful, options.  Run
+`configure --help' for more details.
+

data/vendor/tesseract-2.04/Makefile.am

@@ -0,0 +1,20 @@
+# TODO(luc) Add 'doc' to this list when ready
+SUBDIRS = ccstruct ccutil classify cutil dict pageseg image textord viewer wordrec ccmain training tessdata testing dlltest java
+
+EXTRA_DIST = eurotext.tif phototest.tif ReleaseNotes tesseract.spec config \
+      tesseract.dsp tesseract.dsw tesseract.vcproj tesseract.sln \
+      StdAfx.cpp StdAfx.h tessdll.cpp tessdll.h tessdll.dsp tessdll.vcproj
+
+#EXTRA_DIST = doc/html doc/@PACKAGE_NAME@_@PACKAGE_VERSION@.pdf doc/@PACKAGE_NAME@_@PACKAGE_VERSION@.ps.gz
+
+dist-hook:
+# Need to remove CVS directories from directories
+# added using EXTRA_DIST. $(distdir)/tessdata would in
+# theory suffice.
+	rm -rf `find $(distdir) -name CVS`
+	rm -rf `find $(distdir) -name .svn`
+	rm -rf `find $(distdir) -name .deps`
+# Also remove extra files not needed in a distribution
+	rm -rf `find $(distdir) -name configure.ac`
+	rm -rf `find $(distdir) -name acinclude.m4`
+	rm -rf `find $(distdir) -name aclocal.m4`