lib: Move everything into a PdfExtract module.

Rakefile

@@ -0,0 +1,22 @@
+require 'rubygems'
+
+spec = Gem::Specification.new do |s|
+  s.platform = Gem::Platform::RUBY
+  s.summary = 'PDF text, region, section and section header extraction tool and library.'
+  s.name = 'pdf-extract'
+  s.version = '0.0.1'
+  s.require_path = 'lib'
+  s.files = ['lib/**/*.rb', 'bin/*', '[A-Z]*', 'test/**/*'].to_a
+  s.author = 'Karl Jonathan Ward'
+  s.required_ruby_version = '>= 1.9.1'
+
+  s.add_dependency 'pdf-reader', '>= 0.9.2'
+  s.add_dependency 'nokogiri', '>= 1.4.4'
+
+  s.executables << 'pdf-extract'
+end
+
+Rake::GemPackageTask.new spec do |pkg|
+  pkg.need_zip = true
+  pkg.need_tar = true
+end

TODO.md

@@ -12,8 +12,8 @@
 
 ## Small tasks, 10 minutes or so
 
-* Improve inclusion of spatial object modules. Shouldn't need to call,
-  for example, include_text_runs.
+* DONE Improve inclusion of spatial object modules. Shouldn't need to 
+  call, for example, include_text_runs.
 * Pass set of previously constructed spatial objects to sptials calls,
   via a new method in parser - parser.previous :text_runs { ... }.
   Spatial objects such as margins depend on the positions of text

pdfextract → bindir/pdf-extract

@@ -17,7 +17,7 @@ command :text do |c|
 
   c.action do |args, options|
     args.each do |filename|
-      xml = convert filename, :to => :xml do |pdf| pdf.text_runs end
+      xml = PdfExtract::view filename, :as => :xml do |pdf| pdf.text_runs end
       say xml
     end
   end
@@ -30,7 +30,7 @@ command :mask do |c|
 
   c.action do |args, options|
     args.each do |filename|
-      image = view filename do |pdf|
+      image = PdfExtract::view filename, :as => :png do |pdf|
         pdf.text_runs
         pdf.regions
         pdf.sections
@@ -46,7 +46,7 @@ command :sections do |c|
 
   c.action do |args, options|
     args.each do |filename|
-      xml = convert filename, :to => :xml do |pdf| pdf.sections end
+      xml = PdfExtract::view filename, :as => :xml do |pdf| pdf.sections end
       say xml
     end
   end