pdf-trim_detector 0.1.0

data/CHANGELOG

@@ -0,0 +1,2 @@
+v0.1.0 (12th January 2013)
+* initial release

data/README.markdown

@@ -0,0 +1,28 @@
+= PDF::TrimDetector
+
+Attempts to detect the trim marks on a PDF page and returns a rectangle
+describing the box they indicate. Useful for when you have a PDF with trim
+marks drawn on the page but no matching page box (TrimBox, ArtBox, etc)
+
+== Installation
+
+  gem install pdf-trim_detector
+
+== Usage
+
+    require 'pdf-reader'
+    require 'pdf/trim_detector'
+
+    detector = PDF::TrimDetector.new
+
+    PDF::Reader.open("somefile.pdf") do |pdf|
+      pdf.pages.each do |page|
+        page.walk(detector)
+        puts detector.trim.inspect
+      end
+    end
+
+== Licensing
+
+This library is distributed under the terms of the MIT License. See the included file for
+more detail.

data/lib/pdf/trim_detector.rb

@@ -0,0 +1,162 @@
+# coding: utf-8
+
+require 'forwardable'
+require 'bigdecimal'
+
+module PDF
+
+  # attempts to detect the trim marks on a PDF page and returns a rectangle
+  # describing the box they indicate. Useful for when you have a PDF with trim
+  # marks drawn on the page but no matching page box (TrimBox, ArtBox, etc)
+  #
+  # See the project README for a usage overview.
+  #
+  class TrimDetector
+    extend Forwardable
+
+    ########## BEGIN FORWARDERS ##########
+    # Graphics State Operators
+    def_delegators :@state, :save_graphics_state, :restore_graphics_state
+
+    # Matrix Operators
+    def_delegators :@state, :concatenate_matrix
+
+    def page=(page)
+      @page  = page
+      @state = PDF::Reader::PageState.new(page)
+      @paths = []
+      @trim  = nil
+      @current_paths = []
+    end
+
+    def trim
+      xes = outer_x_candidates
+      yes = outer_y_candidates
+      if xes.size == 2 && yes.size == 2
+        [
+          xes.sort.first,
+          yes.sort.first,
+          xes.sort.last,
+          yes.sort.last,
+        ]
+      end
+    end
+
+    def begin_new_subpath(x, y) # m
+      @current_paths << Path.new
+      x, y = @state.ctm_transform(x, y)
+      @current_paths.last.add_point(x, y)
+    end
+
+    def append_line(x, y) # l
+      if @current_paths.last
+        x, y = @state.ctm_transform(x, y)
+        @current_paths.last.add_point(x, y)
+      end
+    end
+
+    def fill_stroke # B
+      # TODO set the path colour
+      while path = @current_paths.shift
+        @paths << path
+      end
+    end
+
+    def stroke_path # S
+      # TODO set the path colour
+      while path = @current_paths.shift
+        @paths << path
+      end
+    end
+
+    private
+
+    def horizontal_paths
+      @paths.select(&:horizontal?)
+    end
+
+    def vertical_paths
+      @paths.select(&:vertical?)
+    end
+
+    def grouped_vertical_paths
+      vertical_paths.group_by { |path| path.start.x }
+    end
+
+    def grouped_horizontal_paths
+      horizontal_paths.group_by { |path| path.start.y }
+    end
+
+    def x_with_two_paths
+      grouped_vertical_paths.map { |x, paths|
+        paths.size >= 2 ? x : nil
+      }.compact.sort
+    end
+
+    def y_with_two_paths
+      grouped_horizontal_paths.map { |y, paths|
+        paths.size >= 2 ? y : nil
+      }.compact.sort
+    end
+
+    def outer_x_candidates
+      xes = x_with_two_paths
+      if xes.size >= 2
+        [xes.first, xes.last]
+      else
+        xes
+      end
+    end
+
+    def outer_y_candidates
+      yes = y_with_two_paths
+      if yes.size >= 2
+        [yes.first, yes.last]
+      else
+        yes
+      end
+    end
+
+    class Point
+      attr_reader :x, :y
+
+      def initialize(x, y)
+        @x = BigDecimal.new(x.to_s).round(1)
+        @y = BigDecimal.new(y.to_s).round(1)
+      end
+    end
+
+    class Path
+
+      def initialize
+        @points = []
+      end
+
+      def start
+        @points.first
+      end
+
+      def add_point(x, y)
+        @points << Point.new(x, y)
+      end
+
+      def horizontal?
+        @points.size == 2 && y_points.uniq.size == 1
+      end
+
+      def vertical?
+        @points.size == 2 && x_points.uniq.size == 1
+      end
+
+      private
+
+      def x_points
+        @points.map { |point| point.x}
+      end
+
+      def y_points
+        @points.map { |point| point.y}
+      end
+    end
+  end
+end

metadata

@@ -0,0 +1,115 @@
+--- !ruby/object:Gem::Specification
+name: pdf-trim_detector
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+  prerelease: 
+platform: ruby
+authors:
+- James Healy
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-01-12 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.1.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.1.0
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.3'
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Attempt to detect the region of a PDF page indicated by trim marks
+email:
+- james@yob.id.au
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/pdf/trim_detector.rb
+- README.markdown
+- CHANGELOG
+homepage: 
+licenses: []
+post_install_message: 
+rdoc_options:
+- --title
+- PDF::TrimDetector
+- --line-numbers
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: 1.8.7
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: 1.3.2
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.23
+signing_key: 
+specification_version: 3
+summary: Attempt to detect the region of a PDF page indicated by trim marks
+test_files: []