Avoided the need to install Tesseract

Core/build.xml

@@ -39,6 +39,11 @@
         <copy todir="${basedir}/release/Volatility" >
             <fileset dir="${thirdparty.dir}/Volatility"/>
         </copy>
+        
+        <!--Copy Tesseract OCR to release-->
+        <copy todir="${basedir}/release/Tesseract-OCR" >
+            <fileset dir="${thirdparty.dir}/Tesseract-OCR"/>
+        </copy>
             
         <!--Copy other jars-->
         <copy file="${thirdparty.dir}/rejistry/Rejistry-1.0-SNAPSHOT.jar" todir="${ext.dir}" />

thirdparty/Tesseract-OCR/doc/AUTHORS

@@ -0,0 +1,42 @@
+Ray Smith (lead developer) <theraysmith@gmail.com>
+Ahmad Abdulkader
+Rika Antonova
+Nicholas Beato
+Jeff Breidenbach
+Samuel Charron
+Phil Cheatle
+Simon Crouch
+David Eger
+Sheelagh Huddleston
+Dan Johnson
+Rajesh Katikam
+Thomas Kielbus
+Dar-Shyang Lee
+Zongyi (Joe) Liu
+Robert Moss
+Chris Newton
+Michael Reimer
+Marius Renn
+Raquel Romano
+Christy Russon
+Shobhit Saxena
+Mark Seaman
+Faisal Shafait
+Hiroshi Takenaka
+Ranjith Unnikrishnan
+Joern Wanke
+Ping Ping Xiu
+Andrew Ziem
+Oscar Zuniga
+
+Community Contributors:
+Zdenko Podobný (Maintainer)
+Jim Regan (Maintainer)
+James R Barlow
+Amit Dovev
+Martin Ettl
+Tom Morris
+Tobias Müller
+Egor Pugin
+Sundar M. Vaidya
+Stefan Weil

thirdparty/Tesseract-OCR/doc/COPYING

@@ -0,0 +1,21 @@
+This package contains the Tesseract Open Source OCR Engine.
+Originally 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:
+================================
+
+Tesseract uses Leptonica library (http://leptonica.com/) which essentially
+uses a BSD 2-clause license. (http://leptonica.com/about-the-license.html)

thirdparty/Tesseract-OCR/doc/README

@@ -0,0 +1,43 @@
+How to run UNLV tests.
+
+The scripts in this directory make it possible to duplicate the tests
+published in the Fourth Annual Test of OCR Accuracy.
+See http://www.isri.unlv.edu/downloads/AT-1995.pdf
+but first you have to get the tools and data from UNLV:
+
+Step 1: to download the images goto
+http://www.isri.unlv.edu/ISRI/OCRtk
+and get 3b.tgz, Bb.tgz, Mb.tgz and Nb.tgz.
+
+Step 2: extract the files. It doesn't really matter where
+in your filesystem you put them, but they must go under a common
+root so you have directories 3, B, M and N in, for example,
+/users/me/ISRI-OCRtk.
+
+Step 3: Reorg the files
+The lack of tif extensions on the images is inconvenient, so there
+is a script to reorganize the data to match the rest of the test
+scripts.
+cd to /users/me/ISRI-OCRtk or wherever 3, B, M and N ended up and run
+/blah/blah/tesseract-ocr/testing/reorgdata.sh 3B
+This makes directories doe3.3B, bus.3B, mag.3B and news.3B.
+You can now get rid of 3, B, M, and N unless you want to get some of the
+other scanning resolutions out of them.
+
+Step 4: Download the ISRI toolkit from:
+http://www.isri.unlv.edu/downloads/ftk-1.0.tgz
+
+Step 5: If they work for you, use the binaries directly from the bin
+directory and put them in tesseract-ocr/testing/unlv
+otherwise build the tools for yourself and put them there.
+
+Step 6: cd back to your main tesseract-ocr dir and Build tesseract.
+
+Step 7: run testing/runalltests.sh with the root data dir and testname:
+testing/runalltests.sh /users/me/ISRI-OCRtk tess2.0
+and go to the gym, have lunch etc.
+
+Step 8: There should be a file
+testing/reports/tess2.0.summary that contains the final summarized accuracy
+report and comparison with the 1995 results.
+

thirdparty/Tesseract-OCR/tessdata/ara.cube.fold

@@ -0,0 +1 @@
+.٠

thirdparty/Tesseract-OCR/tessdata/ara.cube.lm

@@ -0,0 +1,7 @@
+LeadPunc="({[`'«
+TrailPunc=}:;-]!?`,.)"'»،؛؟
+NumLeadPunc=#({[@$
+NumTrailPunc=}):;].,%،؛٪
+Operators=*+-/.:,()[]،؛
+Digits=٠١٢٣٤٥٦٧٨٩0123456789
+Alphas=ءآأؤإئابةتثجحخدذرزسشصضطظعغفقكلمنهوىي

thirdparty/Tesseract-OCR/tessdata/ara.cube.params

@@ -0,0 +1,14 @@
+RecoWgt=0.8354
+SizeWgt=0.05
+OODWgt=0.0331
+NumWgt=-0.0626
+CharBigramsWgt=-0.0643
+MaxSegPerChar=10
+BeamWidth=12
+ConvGridSize=48
+HistWindWid=0
+WordUnigramsWgt=0.0100
+MaxWordAspectRatio=5.0
+MinSpaceHeightRatio=0.15
+MaxSpaceHeightRatio=0.4
+MinConCompSize=5

thirdparty/Tesseract-OCR/tessdata/configs/ambigs.train

@@ -0,0 +1,7 @@
+tessedit_ambigs_training	1
+load_freq_dawg	0
+load_punc_dawg	0
+load_system_dawg	0
+load_number_dawg	0
+ambigs_debug_level	3
+load_fixed_length_dawgs	0

thirdparty/Tesseract-OCR/tessdata/configs/api_config

@@ -0,0 +1 @@
+tessedit_zero_rejection T

thirdparty/Tesseract-OCR/tessdata/configs/bigram

@@ -0,0 +1,5 @@
+load_bigram_dawg	True
+tessedit_enable_bigram_correction	True
+tessedit_bigram_debug	3
+save_raw_choices	True
+save_alt_choices	True

thirdparty/Tesseract-OCR/tessdata/configs/box.train

@@ -0,0 +1,14 @@
+disable_character_fragments T
+file_type                   .bl
+textord_fast_pitch_test	T
+tessedit_single_match	0
+tessedit_zero_rejection T
+tessedit_minimal_rejection F
+tessedit_write_rep_codes F
+il1_adaption_test 1
+edges_children_fix F
+edges_childarea 0.65
+edges_boxarea 0.9
+tessedit_resegment_from_boxes T
+tessedit_train_from_boxes T
+textord_no_rejects T

thirdparty/Tesseract-OCR/tessdata/configs/box.train.stderr

@@ -0,0 +1,15 @@
+file_type .bl
+#tessedit_use_nn F
+textord_fast_pitch_test T
+tessedit_single_match 0
+tessedit_zero_rejection T
+tessedit_minimal_rejection F
+tessedit_write_rep_codes F
+il1_adaption_test 1
+edges_children_fix F
+edges_childarea 0.65
+edges_boxarea 0.9
+tessedit_resegment_from_boxes T
+tessedit_train_from_boxes T
+#textord_repeat_extraction F
+textord_no_rejects T

thirdparty/Tesseract-OCR/tessdata/configs/digits

@@ -0,0 +1 @@
+tessedit_char_whitelist 0123456789-.

thirdparty/Tesseract-OCR/tessdata/configs/hocr

@@ -0,0 +1,3 @@
+tessedit_create_hocr 1
+tessedit_pageseg_mode 1
+hocr_font_info 0

thirdparty/Tesseract-OCR/tessdata/configs/inter

@@ -0,0 +1,2 @@
+interactive_display_mode				T
+tessedit_display_outwords		T

thirdparty/Tesseract-OCR/tessdata/configs/kannada

@@ -0,0 +1,4 @@
+textord_skewsmooth_offset 8
+textord_skewsmooth_offset2 8
+textord_merge_desc 0.5
+textord_no_rejects 1

thirdparty/Tesseract-OCR/tessdata/configs/linebox

@@ -0,0 +1,2 @@
+tessedit_resegment_from_line_boxes 1
+tessedit_make_boxes_from_boxes 1

thirdparty/Tesseract-OCR/tessdata/configs/logfile

@@ -0,0 +1 @@
+debug_file tesseract.log

thirdparty/Tesseract-OCR/tessdata/configs/makebox

@@ -0,0 +1 @@
+tessedit_create_boxfile 1

thirdparty/Tesseract-OCR/tessdata/configs/pdf

@@ -0,0 +1,2 @@
+tessedit_create_pdf 1
+tessedit_pageseg_mode 1

thirdparty/Tesseract-OCR/tessdata/configs/quiet

@@ -0,0 +1 @@
+debug_file /dev/null

thirdparty/Tesseract-OCR/tessdata/configs/rebox

@@ -0,0 +1,2 @@
+tessedit_resegment_from_boxes 1
+tessedit_make_boxes_from_boxes 1

thirdparty/Tesseract-OCR/tessdata/configs/strokewidth

@@ -0,0 +1,12 @@
+textord_show_blobs 0
+textord_debug_tabfind 3
+textord_tabfind_show_partitions 1
+textord_tabfind_show_initial_partitions 1
+textord_tabfind_show_columns 1
+textord_tabfind_show_blocks 1
+textord_tabfind_show_initialtabs 1
+textord_tabfind_show_finaltabs 1
+textord_tabfind_show_strokewidths 1
+textord_tabfind_show_vlines 0
+textord_tabfind_show_images 1
+tessedit_dump_pageseg_images 0

thirdparty/Tesseract-OCR/tessdata/configs/tsv

@@ -0,0 +1,2 @@
+tessedit_create_tsv 1
+tessedit_pageseg_mode 1

thirdparty/Tesseract-OCR/tessdata/configs/txt

@@ -0,0 +1,3 @@
+# This config file should be used with other cofig files which creates renderers.
+# usage example: tesseract eurotext.tif eurotext txt hocr pdf
+tessedit_create_txt 1

thirdparty/Tesseract-OCR/tessdata/configs/unlv

@@ -0,0 +1,2 @@
+tessedit_write_unlv 1
+tessedit_pageseg_mode 6

thirdparty/Tesseract-OCR/tessdata/eng.cube.fold

@@ -0,0 +1,12 @@
+0oO
+lI1
+cC
+kK
+pP
+sS
+uU
+vV
+wW
+xX
+yY
+zZ

thirdparty/Tesseract-OCR/tessdata/eng.cube.lm

@@ -0,0 +1,7 @@
+LeadPunc="({[`'
+TrailPunc=}:;-]!?`,.)"'
+NumLeadPunc=#({[@$
+NumTrailPunc=}):;].,%
+Operators=*+-/.:,()[]
+Digits=0123456789
+Alphas=abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ

thirdparty/Tesseract-OCR/tessdata/eng.cube.params

@@ -0,0 +1,14 @@
+RecoWgt=1.0
+SizeWgt=0.2435
+OODWgt=0.0214
+NumWgt=0.036
+CharBigramsWgt=0.1567
+MaxSegPerChar=8
+BeamWidth=10
+ConvGridSize=48
+WordUnigramsWgt=0.01
+MaxWordAspectRatio=20.0000
+MinSpaceHeightRatio=0.5000
+MaxSpaceHeightRatio=0.6000
+HistWindWid=2
+MinConCompSize=0

thirdparty/Tesseract-OCR/tessdata/eng.user-patterns

@@ -0,0 +1,2 @@
+1-\d\d\d-GOOG-411
+www.\n\\\*.com

thirdparty/Tesseract-OCR/tessdata/eng.user-words

@@ -0,0 +1,5 @@
+the
+quick
+brown
+fox
+jumped

thirdparty/Tesseract-OCR/tessdata/tessconfigs/batch

@@ -0,0 +1,2 @@
+# No content needed as all defaults are correct.
+

thirdparty/Tesseract-OCR/tessdata/tessconfigs/batch.nochop

@@ -0,0 +1,2 @@
+chop_enable 0
+wordrec_enable_assoc 0

thirdparty/Tesseract-OCR/tessdata/tessconfigs/matdemo

@@ -0,0 +1,7 @@
+#################################################
+# Adaptive Matcher Using PreAdapted Templates
+#################################################
+
+classify_enable_adaptive_debugger   1
+matcher_debug_flags         6
+matcher_debug_level       1

thirdparty/Tesseract-OCR/tessdata/tessconfigs/msdemo

@@ -0,0 +1,13 @@
+#################################################
+# Adaptive Matcher Using PreAdapted Templates
+#################################################
+
+classify_enable_adaptive_debugger	1
+matcher_debug_flags         6
+matcher_debug_level       1
+
+wordrec_display_splits          0
+wordrec_display_all_words       1
+wordrec_display_all_blobs       1
+wordrec_display_segmentations   2
+classify_debug_level		1

thirdparty/Tesseract-OCR/tessdata/tessconfigs/nobatch

@@ -0,0 +1 @@
+

thirdparty/Tesseract-OCR/tessdata/tessconfigs/segdemo

@@ -0,0 +1,10 @@
+#################################################
+# Adaptive Matcher Using PreAdapted Templates
+#################################################
+
+wordrec_display_splits          0
+wordrec_display_all_words       1
+wordrec_display_all_blobs       1
+wordrec_display_segmentations   2
+classify_debug_level		1
+stopper_debug_level 1