treat 2.0.6 → 2.0.7

data/lib/treat/entities/entity/buildable.rb

@@ -47,8 +47,8 @@ module Treat::Entities::Entity::Buildable
     elsif file_or_value.is_a?(Hash)
       from_db(file_or_value)
     elsif self == Treat::Entities::Document ||
-      (fv.index('yml') || fv.index('yaml') ||
-      fv.index('xml') || fv.index('mongo'))
+      (fv.index('.yml') || fv.index('.yaml') ||
+      fv.index('.xml'))
       if fv =~ UriRegexp
         from_url(fv)
       else

data/lib/treat/version.rb

@@ -1,7 +1,7 @@
 module Treat
   
   # The current version of Treat.
-  VERSION = '2.0.6'
+  VERSION = '2.0.7'
   
   # Treat requires Ruby >= 1.9.2
   if RUBY_VERSION < '1.9.2'

data/lib/treat/workers/formatters/readers/image.rb

@@ -7,8 +7,8 @@
 # statistical natural language modeling, and multi-
 # lingual capabilities."
 #
-# Original paper: Google Ocropus Engine: Breuel, 
-# Thomas M. The Ocropus Open Source OCR System. 
+# Original paper: Google Ocropus Engine: Breuel,
+# Thomas M. The Ocropus Open Source OCR System.
 # DFKI and U. Kaiserslautern, Germany.
 class Treat::Workers::Formatters::Readers::Image
 
@@ -18,27 +18,27 @@ class Treat::Workers::Formatters::Readers::Image
   #
   # - (Boolean) :silent => whether to silence Ocropus.
   def self.read(document, options = {})
-    
+
     read = lambda do |doc|
       self.create_temp_dir do |tmp|
-        `ocropus book2pages #{tmp}/out #{doc.file}`
-        `ocropus pages2lines #{tmp}/out`
-        `ocropus lines2fsts #{tmp}/out`
-        `ocropus buildhtml #{tmp}/out > #{tmp}/output.html`
-        doc.set :file,  "#{tmp}/output.html"
+        `ocropus-nlbin -o #{tmp}/out #{doc.file}`
+        `ocropus-gpageseg #{tmp}/out/????.bin.png --minscale 2`
+        `ocropus-rpred #{tmp}/out/????/??????.bin.png`
+        `ocropus-hocr #{tmp}/out/????.bin.png -o #{tmp}/book.html`
+        doc.set :file,  "#{tmp}/book.html"
         doc.set :format, :html
+
         doc = doc.read(:html)
       end
     end
-    
-    Treat.core.verbosity.silence ? silence_stdout { 
+
+    Treat.core.verbosity.silence ? silence_stdout {
     read.call(document) } : read.call(document)
-    
+
     document
-    
   end
-  
-  # Create a dire that gets deleted after execution of the block.
+
+  # Create a dir that gets deleted after execution of the block.
   def self.create_temp_dir(&block)
     if not FileTest.directory?(Treat.paths.tmp)
       FileUtils.mkdir(Treat.paths.tmp)
@@ -50,5 +50,5 @@ class Treat::Workers::Formatters::Readers::Image
   ensure
     FileUtils.rm_rf(dname)
   end
-  
+
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: treat
 version: !ruby/object:Gem::Version
-  version: 2.0.6
+  version: 2.0.7
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-06-27 00:00:00.000000000 Z
+date: 2013-06-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: schiphol