Merge pull request #5 from I-can-read/feature/#4-train-model

Feature/#4 train model

tesseract-4.1.1/.clang-format

@@ -0,0 +1,9 @@
+---
+BasedOnStyle:  Google
+# Only merge empty functions.
+AllowShortFunctionsOnASingleLine: Empty
+# Do not allow short if statements.
+AllowShortIfStatementsOnASingleLine: false
+# Enforce always the same pointer alignment.
+DerivePointerAlignment: false
+IndentPPDirectives: AfterHash

tesseract-4.1.1/.github/ISSUE_TEMPLATE.md

@@ -0,0 +1,23 @@
+Before you submit an issue, please review [the guidelines for this repository](https://github.com/tesseract-ocr/tesseract/blob/master/CONTRIBUTING.md).
+
+Please report an issue only for a BUG, not for asking questions.
+
+Note that it will be much easier for us to fix the issue if a test case that
+reproduces the problem is provided. Ideally this test case should not have any
+external dependencies. Provide a copy of the image or link to files for the test case.
+
+Please delete this text and fill in the template below.
+
+------------------------
+
+### Environment
+
+* **Tesseract Version**: <!-- compulsory. you must provide your version -->
+* **Commit Number**: <!-- optional. if known - specify commit used, if built from source -->
+* **Platform**: <!-- either `uname -a` output, or if Windows, version and 32-bit or 64-bit -->
+
+### Current Behavior:
+
+### Expected Behavior:
+
+### Suggested Fix:

tesseract-4.1.1/.gitignore

@@ -0,0 +1,120 @@
+*~
+# Windows
+*.user.*
+*.idea*
+*.log
+*.tlog
+*.cache
+*.obj
+*.sdf
+*.opensdf
+*.lastbuildstate
+*.unsuccessfulbuild
+*.suo
+*.res
+*.ipch
+*.manifest
+*.user
+
+# Linux
+# ignore local configuration
+config.*
+config/*
+Makefile
+Makefile.in
+*.m4
+
+# ignore help scripts/files
+configure
+libtool
+stamp-h1
+tesseract.pc
+config_auto.h
+/doc/html/*
+/doc/*.1
+/doc/*.5
+/doc/*.html
+/doc/*.xml
+
+# generated version file
+/src/api/tess_version.h
+
+# executables
+/src/api/tesseract
+/src/training/ambiguous_words
+/src/training/classifier_tester
+/src/training/cntraining
+/src/training/combine_tessdata
+/src/training/dawg2wordlist
+/src/training/merge_unicharsets
+/src/training/mftraining
+/src/training/set_unicharset_properties
+/src/training/shapeclustering
+/src/training/text2image
+/src/training/unicharset_extractor
+/src/training/wordlist2dawg
+
+*.patch
+
+# files generated by libtool
+/src/training/combine_lang_model
+/src/training/lstmeval
+/src/training/lstmtraining
+
+# ignore compilation files
+build/*
+/bin
+*/.deps/*
+*/.libs/*
+*/*/.deps/*
+*/*/.libs/*
+*.lo
+*.la
+*.o
+*.Plo
+*.a
+*.class
+*.jar
+__pycache__
+
+# tessdata
+*.traineddata
+
+# OpenCL
+tesseract_opencl_profile_devices.dat
+kernel*.bin
+
+# build dirs
+/build*
+/.cppan
+/cppan
+/*.dll
+/*.lib
+/*.exe
+/*.lnk
+/win*
+.vs*
+.s*
+
+# files generated by "make check"
+/tests/.dirstamp
+/unittest/*.trs
+/unittest/tmp/*
+
+# test programs
+/unittest/*_test
+/unittest/primesbitvector
+/unittest/primesmap
+
+# generated files from unlvtests
+times.txt
+/unlvtests/results*
+
+# snap packaging specific rules
+/parts/
+/stage/
+/prime/
+/snap/.snapcraft/
+
+/*.snap
+/*_source.tar.bz2

tesseract-4.1.1/.gitmodules

@@ -0,0 +1,9 @@
+[submodule "abseil"]
+	path = abseil
+	url = https://github.com/abseil/abseil-cpp.git
+[submodule "googletest"]
+	path = googletest
+	url = https://github.com/google/googletest.git
+[submodule "test"]
+	path = test
+	url = https://github.com/tesseract-ocr/test

tesseract-4.1.1/.lgtm.yml

@@ -0,0 +1,18 @@
+extraction:
+  cpp:
+    prepare:
+      packages:
+        - libpango1.0-dev
+    configure:
+      command:
+        - ./autogen.sh
+        - mkdir _lgtm_build_dir
+        - cd _lgtm_build_dir
+        - ../configure
+    index:
+      build_command:
+        - cd _lgtm_build_dir
+        - make training
+  python:
+    python_setup:
+      version: 3

tesseract-4.1.1/.travis.yml

@@ -0,0 +1,57 @@
+# Travis CI configuration for Tesseract
+
+language: cpp
+
+dist: xenial
+
+env:
+  - LEPT_VER=1.77.0
+
+notifications:
+  email: false
+
+sudo: false
+
+os:
+  - linux
+  - osx
+
+addons:
+  apt:
+    sources:
+    #- ubuntu-toolchain-r-test
+    packages:
+      - libarchive-dev
+      - libpango1.0-dev
+    #- g++-6
+
+#matrix:
+  #include:
+    #- os: osx
+      #install:
+      #script: brew install tesseract --HEAD
+      #cache:
+        #directories:
+          #- $HOME/Library/Caches/Homebrew
+  #allow_failures:
+    #- script: brew install tesseract --HEAD
+
+cache:
+  directories:
+  - leptonica-$LEPT_VER
+
+before_install:
+  - if [[ $TRAVIS_OS_NAME == linux   ]]; then LINUX=true; fi
+  - if [[ $TRAVIS_OS_NAME == osx     ]]; then OSX=true; fi
+
+install:
+  #- if [[ $LINUX && "$CXX" = "g++" ]]; then export CXX="g++-6" CC="gcc-6"; fi
+  - if test ! -d leptonica-$LEPT_VER/src; then curl -Ls https://github.com/DanBloomberg/leptonica/archive/$LEPT_VER.tar.gz | tar -xz; fi
+  - if test ! -d leptonica-$LEPT_VER/usr; then cmake -Hleptonica-$LEPT_VER -Bleptonica-$LEPT_VER/build -DCMAKE_INSTALL_PREFIX=leptonica-$LEPT_VER/usr; fi
+  - if test ! -e leptonica-$LEPT_VER/usr/lib/libleptonica.so; then make -C leptonica-$LEPT_VER/build install; fi
+
+script:
+  - mkdir build
+  - cd build
+  - cmake .. -DLeptonica_DIR=leptonica-$LEPT_VER/build -DCPPAN_BUILD=OFF
+  - make

tesseract-4.1.1/AUTHORS

@@ -0,0 +1,44 @@
+Ray Smith (lead developer) <[email protected]>
+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
+Shree Devi Kumar
+Noah Metzger
+Tom Morris
+Tobias Müller
+Egor Pugin
+Sundar M. Vaidya
+Stefan Weil