Merge pull request #93 from IU-Libraries-Joint-Development/HPT-989_oc…

…r_jp2

HPT-989 Add OCR generation to JP2 derivatives creation code

.install_tesseract

@@ -0,0 +1,33 @@
+wget "https://github.com/uclouvain/openjpeg/archive/version.2.1.zip"
+unzip version.2.1.zip
+cd openjpeg-version.2.1
+mkdir build
+cd build
+cmake ..
+make
+sudo make install
+sudo make clean
+cd ..
+cd ..
+wget "http://www.leptonica.com/source/leptonica-1.73.tar.gz"
+tar xzf leptonica-1.73.tar.gz
+cd leptonica-1.73
+sed -i 's/#define  HAVE_LIBJP2K     0/#define  HAVE_LIBJP2K     1/g' ./src/environ.h
+sed -i 's/-ltiff -ljpeg -lpng -lz -lm/-ltiff -ljpeg -lpng -lz -lm -lopenjp2/g' ./prog/makefile.static
+./configure
+make
+sudo make install
+cd ..
+wget "https://github.com/tesseract-ocr/tesseract/archive/3.04.00.zip"
+unzip 3.04.00.zip
+cd tesseract-3.04.00
+./autogen.sh
+./configure
+make
+sudo make install
+sudo ldconfig
+cd ..
+git clone https://github.com/tesseract-ocr/tessdata.git
+sudo cp tessdata/eng.* /usr/local/share/tessdata/
+sudo cp tessdata/ita* /usr/local/share/tessdata
+tesseract -v

app/models/file_set.rb

@@ -47,6 +47,7 @@ def create_derivatives(filename)
       dst = derivative_path('intermediate_file')
       FileUtils.mkdir_p(File.dirname(dst))
       FileUtils.cp(filename, dst)
+      RunOCRJob.perform_later(id) if Plum.config[:store_original_files]
     end
     super
   end

circle.yml

@@ -11,7 +11,8 @@ dependencies:
     - kakadu
   pre:
     - npm install -g eslint
-    - sudo apt-get install libmagickwand-dev imagemagick redis-server tesseract-ocr tesseract-ocr-ita tesseract-ocr-eng sqlite3 libsqlite3-dev
+    - sudo apt-get install libmagickwand-dev imagemagick redis-server sqlite3 libsqlite3-dev
+    - bash ./.install_tesseract
   post:
     - sudo sh bin/ci_kakadu_install.sh
     - bundle exec rake rubocop

spec/fixtures/contentdm_xml/Irish_People_Short.yml

@@ -0,0 +1,79 @@
+---
+:resource: MultiVolumeWork
+:attributes:
+  :default:
+    state: final_review
+    viewing_direction: left-to-right
+    rights_statement: http://rightsstatements.org/vocab/NKC/1.0/
+    visibility: open
+  :local:
+    source_metadata_identifier: Irish People <br> http://indiamond6.ulib.iupui.edu/cdm/search/collection/IP
+    viewing_direction: left-to-right
+:source_metadata: 
+:thumbnail_path: http://indiamond6.ulib.iupui.edu:2012/cgi-bin/thumbnail.exe?CISOROOT=/IP&CISOPTR=5044
+:collections: []
+:volumes:
+- :title:
+  - 1974-11-16 Irish People
+  :structure:
+    :nodes:
+    - :label: page1
+      :proxy: page1
+    - :label: page2
+      :proxy: page2
+    - :label: page3
+      :proxy: page3
+  :files:
+  - :id: page1
+    :mime_type: image/jp2
+    :attributes:
+      :title:
+      - page1
+    :thumbnail: http://indiamond6.ulib.iupui.edu:2012/cgi-bin/thumbnail.exe?CISOROOT=/IP&CISOPTR=5044
+    :path: http://indiamond6.ulib.iupui.edu:2012/cgi-bin/showfile.exe?CISOROOT=/IP&CISOPTR=5044
+    :file_opts: {}
+  - :id: page2
+    :mime_type: image/jp2
+    :attributes:
+      :title:
+      - page2
+    :thumbnail: http://indiamond6.ulib.iupui.edu:2012/cgi-bin/thumbnail.exe?CISOROOT=/IP&CISOPTR=5045
+    :path: http://indiamond6.ulib.iupui.edu:2012/cgi-bin/showfile.exe?CISOROOT=/IP&CISOPTR=5045
+    :file_opts: {}
+  - :id: page3
+    :mime_type: image/jp2
+    :attributes:
+      :title:
+      - page3
+    :thumbnail: http://indiamond6.ulib.iupui.edu:2012/cgi-bin/thumbnail.exe?CISOROOT=/IP&CISOPTR=5046
+    :path: http://indiamond6.ulib.iupui.edu:2012/cgi-bin/showfile.exe?CISOROOT=/IP&CISOPTR=5046
+    :file_opts: {}
+- :title:
+  - 1982-03-27 Irish People
+  :structure:
+    :nodes:
+    - :label: page1
+      :proxy: page1
+    - :label: page2
+      :proxy: page2
+  :files:
+  - :id: page1
+    :mime_type: image/jp2
+    :attributes:
+      :title:
+      - page1
+    :thumbnail: http://indiamond6.ulib.iupui.edu:2012/cgi-bin/thumbnail.exe?CISOROOT=/IP&CISOPTR=8153
+    :path: http://indiamond6.ulib.iupui.edu:2012/cgi-bin/showfile.exe?CISOROOT=/IP&CISOPTR=8153
+    :file_opts: {}
+  - :id: page2
+    :mime_type: image/jp2
+    :attributes:
+      :title:
+      - page2
+    :thumbnail: http://indiamond6.ulib.iupui.edu:2012/cgi-bin/thumbnail.exe?CISOROOT=/IP&CISOPTR=8154
+    :path: http://indiamond6.ulib.iupui.edu:2012/cgi-bin/showfile.exe?CISOROOT=/IP&CISOPTR=8154
+    :file_opts: {}
+:sources:
+- :title:
+  - Contentdm XML
+  :file: spec/fixtures/contentdm_xml/Irish_People_Short.xml