libera 1.0.0 → 1.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: cc099d4ec4b7e794ee9fcd8dbd057a1ccd04467c
-  data.tar.gz: 42e414654cab1579bdaad82e5fe6d70f97b0fd7a
+  metadata.gz: a48b962889918bed974055b7c00258ab1d546826
+  data.tar.gz: f70e99edf393c7fb1f534ce878f1e79279f6ab56
 SHA512:
-  metadata.gz: 5e4e80f572b7e2bc9ac1febedd14693a956d818aa0ec999d486e11f74813df1029a2eaeed846c36d4fb7951d57c2c0981e50b6a9393c1daaa86b3114a504dd3f
-  data.tar.gz: d7bb316456adfd50f29e19c28eee08051c6bc2439ac41b98a6f550ee37031528ad89724225e20f6b5a424ea12c208dd9f0f9ada4ec035aff6e4999dc13c986c4
+  metadata.gz: 00aa349e53c83c32b84c901d48d37ace7472f095fd65c0b63fae43a68c7c700bbc45141e7b3617cc51c54db493a109daf694f15e5ef2b6e2d6e78299fe65ff76
+  data.tar.gz: c336a4d25119edcf30c5eba034b7c875656b1d626445ab354e125e289b1e532ea3e202cefc638c76aac77bcfbcca46a52603d6c571ee1d929eab8716b1dc4734

data/README.md

@@ -6,6 +6,15 @@ It's purpose is to take PDF files as input, and split them apart into individual
 
 ## Installation
 
+There are some programs that are required for Libera to work;
+
+* Tesseract - https://github.com/tesseract-ocr/tesseract
+* ImageMagick - https://www.imagemagick.org
+
+Tesseract 3.03 and ImageMagick 6.7.7-10 were the versions used in the development of this gem.
+
+Both should be available through package managers such as APT, Yum, Homebrew etc.
+
 Add this line to your application's Gemfile:
 
 ```ruby

data/lib/libera/tei.rb

@@ -5,7 +5,7 @@ module Libera
     include OM::XML::Document
     
     set_terminology do |t|
-      t.root(:path => 'tei', :xmlns => 'http://www.tei-c.org/ns/1.0', :namespace_prefix => nil)
+      t.root(:path => 'TEI', :xmlns => 'http://www.tei-c.org/ns/1.0', :namespace_prefix => nil)
       t.text(path: 'text'){
         t.body(path: 'body'){
           t.page_break(path: 'pb')
@@ -14,6 +14,14 @@ module Libera
       }
     end
     
+    define_template :text do |xml|
+      xml.text_
+    end
+    
+    define_template :body do |xml|
+      xml.body
+    end
+    
     define_template :page_break do |xml, img_src|
       xml.pb(:facs => img_src)
     end
@@ -51,7 +59,33 @@ module Libera
       return builder.doc
     end
     
+    def add_text
+      begin
+        self.template_registry.add_child(self.ng_xml.root, :text)
+      rescue NoMethodError
+        raise "Unable to add XML node to base template"
+      end
+    end
+    
+    def add_body
+      begin
+        self.template_registry.add_child(self.find_by_terms(:text => 0), :body)
+      rescue NoMethodError
+        raise "Unable to add XML node to base template"
+      end
+    end
+    
     def add_page_break(page_img)
+      # any text?
+      if self.find_by_terms(:text => 0).blank?
+        self.add_text
+      end
+      
+      # any body?
+      if self.find_by_terms(:text, :body => 0).blank?
+        self.add_body
+      end
+      
       # any anon breaks?
       ab_count = self.find_by_terms(:text, :body, :anon_block).count
       

data/lib/libera/version.rb

@@ -1,3 +1,3 @@
 module Libera
-  VERSION = "1.0.0"
+  VERSION = "1.0.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: libera
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.1
 platform: ruby
 authors:
 - David Cliff
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-06-06 00:00:00.000000000 Z
+date: 2018-06-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler