pdfbeads 1.0.9 → 1.1.1

data/lib/pdfbeads/pdfpage.rb

@@ -8,7 +8,7 @@
 # Unlike other PDF creation tools, this utility attempts to implement
 # the approach typically used for DjVu books. Its key feature is
 # separating scanned text (typically black, but indexed images with
-# a small number of colors are also accepted) from halftone images 
+# a small number of colors are also accepted) from halftone images
 # placed into a background layer.
 #
 # Copyright (C) 2010 Alexey Kryukov (amkryukov@gmail.com).
@@ -30,7 +30,7 @@
 #
 #######################################################################
 
-# Represents a set of page images accompanies with auxiliary files
+# Represents a set of page images accompanied with auxiliary files
 # needed to build a PDF document.
 class PDFBeads::PageDataProvider < Array
 
@@ -96,7 +96,7 @@ class PDFBeads::PageDataProvider < Array
 
       $stderr.puts( "Prepared data for processing #{@name}\n" )
       if insp.nextImage
-        $stderr.puts( "Warning: #{@name} contains multiple images, but only the first one") 
+        $stderr.puts( "Warning: #{@name} contains multiple images, but only the first one")
         $stderr.puts( "\tis going to be used\n" )
       end
       ret
@@ -117,8 +117,8 @@ class PDFBeads::PageDataProvider < Array
         @bg_layer = bgpath unless bgpath.nil?
 
         # If updating auxiliary files is requested and the base image is
-        # either monochrome or indexed with just a few colors (i. e. doesn't
-        # contain any elements which should be encoded to the background layer),
+        # either bitonal or indexed with just a few colors (i. e. doesn't
+        # contain any elements which should be placed to the background layer),
         # then the *.color.* image (if present) takes priority over any existing
         # *.bg.* and *.fg.* images. So we should regenerate them.
         if bgpath.nil? or ( force and not @s_type.eql? 'c' )
@@ -139,7 +139,7 @@ class PDFBeads::PageDataProvider < Array
         @fg_layer = fgpath unless fgpath.nil?
       end
 
-      if $has_hpricot
+      if $has_nokogiri and not @pageargs[:pages_per_dict].nil?
         @hocr_path = Dir.entries('.').detect do |f|
           /\A#{@basename}.(HOCR|HTML?)/i.match(f)
         end
@@ -353,7 +353,7 @@ class PDFBeads::PageDataProvider < Array
         # to achieve the desired color diffusion. The idea is inspired by
         # Anthony Thyssen's http://www.imagemagick.org/Usage/scripts/hole_fill_shepards
         # script, which is intended just for this purpose (i. e. removing undesired
-        # areas from the image). However our approach is a bit cruder (but still
+        # areas from the image). However our approach is a bit more crude (but still
         # effective).
         fg.resize!( width=imw/100,height=imh/100,filter=GaussianFilter )
         fg.resize!( width=imw,height=imh,filter=GaussianFilter )
@@ -471,7 +471,7 @@ class PDFBeads::PageDataProvider < Array
       end
 
       if pidx == per_dict or i == length - 1
-        # The jbig2 encoder processes a bunch of files at once, producing 
+        # The jbig2 encoder processes a bunch of files at once, producing
         # pages which depend from a shared dictionary. Thus we can skip this
         # stage only if both the dictionary and each of the individual pages
         # are already found on the disk

data/lib/pdfbeads/pdftoc.rb

@@ -8,7 +8,7 @@
 # Unlike other PDF creation tools, this utility attempts to implement
 # the approach typically used for DjVu books. Its key feature is
 # separating scanned text (typically black, but indexed images with
-# a small number of colors are also accepted) from halftone images 
+# a small number of colors are also accepted) from halftone images
 # placed into a background layer.
 #
 # Copyright (C) 2010 Alexey Kryukov (amkryukov@gmail.com).
@@ -38,7 +38,7 @@
 # <indent>"Title" "Page Number" [0|-|1|+]
 #
 # The indent is used to determine the level of this outline item: it may
-# consist either of spaces or of tabs, but it is not allowed to 
+# consist either of spaces or of tabs, but it is not allowed to
 # mix both characters in the same file. The title and page number are
 # separated with an arbitrary number of whitespace characters and are
 # normally enclosed into double quotes. The third, optional argument
@@ -101,7 +101,11 @@ class PDFBeads::PDFBuilder::PDFTOC < Array
           title = parts[0].gsub(/\A"/m,"").gsub(/"\Z/m, "")
           ref   = parts[1].gsub(/\A"/m,"").gsub(/"\Z/m, "")
           begin
-            title = Iconv.iconv( "utf-16be", "utf-8", title ).first
+            if title.respond_to? :encode
+              title.encode!( "utf-16be", "utf-8" )
+            else
+              title = Iconv.iconv( "utf-16be", "utf-8", title ).first
+            end
           rescue
             $stderr.puts("Error: TOC should be specified in utf-8")
             return

metadata

@@ -1,35 +1,75 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: pdfbeads
-version: !ruby/object:Gem::Version 
-  hash: 5
-  prerelease: 
-  segments: 
-  - 1
-  - 0
-  - 9
-  version: 1.0.9
+version: !ruby/object:Gem::Version
+  version: 1.1.1
 platform: ruby
-authors: 
+authors:
 - Alexey Kryukov
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2012-04-21 00:00:00 +04:00
-default_executable: pdfbeads
-dependencies: []
-
-description: "    PDFBeads is a small utility written in Ruby which takes scanned\n    page images and converts them into a single PDF file. Unlike other\n    PDF creation tools, PDFBeads attempts to implement the approach\n    typically used for DjVu books. Its key feature is separating scanned\n    text (typically black, but indexed images with a small number of\n    colors are also accepted) from halftone pictures. Each type of\n    graphical data is encoded into its own layer with a specific\n    compression method and resolution.\n"
+date: 2014-01-30 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rmagick
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 2.13.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 2.13.0
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 1.5.10
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 1.5.10
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+description: |2
+      PDFBeads is a small utility written in Ruby which takes scanned
+      page images and converts them into a single PDF file. Unlike other
+      PDF creation tools, PDFBeads attempts to implement the approach
+      typically used for DjVu books. Its key feature is separating scanned
+      text (typically black, but indexed images with a small number of
+      colors are also accepted) from halftone pictures. Each type of
+      graphical data is encoded into its own layer with a specific
+      compression method and resolution.
 email: amkryukov@gmail.com
-executables: 
+executables:
 - pdfbeads
 extensions: []
-
-extra_rdoc_files: 
+extra_rdoc_files:
 - README
 - COPYING
 - ChangeLog
-files: 
+files:
 - lib/pdfbeads/pdfbuilder.rb
 - lib/pdfbeads/pdfpage.rb
 - lib/pdfbeads/pdftoc.rb
@@ -40,43 +80,35 @@ files:
 - lib/imageinspector.rb
 - bin/pdfbeads
 - doc/pdfbeads.ru.html
+- doc/pdfbeads.en.html
 - README
 - COPYING
 - ChangeLog
-has_rdoc: true
 homepage: http://pdfbeads.rubyforge.org
-licenses: []
-
+licenses:
+- GPL
+metadata: {}
 post_install_message: 
 rdoc_options: []
-
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
-      version: "0"
-requirements: 
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements:
 - RMagick, v2.13.0 or greater
-- Hpricot, v0.8.3 or greater
+- nokogiri, v1.5.10 or greater
+- PDF::Reader, v1.0.0 or greater
 rubyforge_project: PDFBeads
-rubygems_version: 1.5.0
+rubygems_version: 2.0.3
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: PDFBeads -- convert scanned images to a single PDF file.
 test_files: []
-