podoff 0.0.1 → 0.9.0

data/CHANGELOG.txt

@@ -0,0 +1,13 @@
+
+= podoff CHANGELOG.txt
+
+
+== podoff 0.9.0  released 2015-10-21
+
+- beta release
+
+
+== podoff 0.0.1  released 2015-10-20
+
+- initial, empty, release
+

data/README.md

@@ -1,6 +1,19 @@
 
 # podoff
 
+A Ruby tool to deface PDF documents.
+
+If you're looking for serious libraries, look at
+
+* https://github.com/payrollhero/pdf_tempura
+* https://github.com/prawnpdf/prawn-templates
+
+
+## disclaimer
+
+The author of this tool/library have no link whatsoever with the authors of the sample PDF documents found under `pdfs/`. Those documents have been selected because they are representative of the PDF forms podoff is meant to ~~deface~~fill.
+
+
 ## LICENSE
 
 MIT, see [LICENSE.txt](LICENSE.txt)

data/lib/podoff.rb

@@ -26,6 +26,251 @@
 
 module Podoff
 
-  VERSION = '0.0.1'
+  VERSION = '0.9.0'
+
+  def self.load(path)
+
+    Podoff::Document.new(
+      File.open(path, 'r:iso8859-1') { |f| f.read })
+  end
+
+  class Document
+
+    attr_reader :header
+    attr_reader :objs
+    attr_reader :footer
+
+    def initialize(s)
+
+      fail ArgumentError.new('not a PDF file') \
+        unless s.match(/\A%PDF-\d+\.\d+\n/)
+
+      @header = []
+      #
+      @objs = {}
+      cur = nil
+      #
+      @footer = nil
+
+      s.split("\n").each do |l|
+
+        if @footer
+          @footer << l
+        elsif m = /^(\d+ \d+) obj\b/.match(l)
+          cur = (@objs[m[1]] = Obj.new(self, m[1]))
+          cur << l
+        elsif m = /^xref\b/.match(l)
+          @footer = []
+          @footer << l
+        elsif cur
+          cur << l
+        else
+          @header << l
+        end
+      end
+    end
+
+    def fonts; @objs.values.select(&:is_font?); end
+    def pages; @objs.values.select(&:is_page?); end
+
+    def page(i)
+
+      i < 1 ? nil : @objs.values.find { |o| o.page_number == i }
+    end
+
+    def dup
+
+      d0 = self
+
+      d = d0.class.allocate
+
+      d.instance_eval do
+        @header = d0.header.dup
+        @footer = d0.footer.dup
+        @objs = d0.objs.values.inject({}) { |h, v| h[v.ref] = v.dup(d); h }
+      end
+
+      d
+    end
+
+    def write(path)
+
+      File.open(path, 'wb') do |f|
+
+        @header.each { |l| f.print(l); f.print("\n") }
+
+        @objs.values.each do |o|
+          o.lines.each { |l| f.print(l); f.print("\n") }
+        end
+
+        @footer.each { |l| f.print(l); f.print("\n") }
+      end
+    end
+  end
+
+  class Obj
+
+    attr_reader :document
+    attr_reader :ref
+    attr_reader :lines
+
+    def initialize(doc, ref)
+
+      @document = doc
+      @ref = ref
+      @lines = []
+    end
+
+    def <<(l)
+
+      @lines << l
+    end
+
+    def lookup(k)
+
+      @lines.each do |l|
+
+        m = l.match(/^\/#{k} (.*)$/)
+        return m[1] if m
+      end
+
+      nil
+    end
+
+    def index(o, start=0)
+
+      @lines[start..-1].each_with_index do |l, i|
+
+        if o.is_a?(String)
+          return start + i if l == o
+        else
+          return start + i if l.match(o)
+        end
+      end
+
+      nil
+    end
+
+    def type
+
+      t = lookup('Type')
+      t ? t[1..-1] : nil
+    end
+
+    def page_number
+
+      r = lookup('pdftk_PageNum')
+      r ? r.to_i : nil
+    end
+
+    def is_page?
+
+      page_number != nil
+    end
+
+    def is_font?
+
+      type() == 'Font'
+    end
+
+    def parent
+
+      # /Parent 2 0 R
+
+      r = lookup('Parent')
+
+      r ? r[0..-2].strip : nil
+    end
+
+    def kids
+
+      # /Kids [1 0 R 16 0 R 33 0 R]
+
+      r = lookup('Kids')
+      (r || '').split(/[\[\]R]/).collect(&:strip).reject(&:empty?)
+    end
+
+    def contents
+
+      r = lookup('Contents')
+      r ? r[0..-2].strip : nil
+    end
+
+    def font_names
+
+      @lines.inject(nil) do |names, l|
+
+        if names
+          return names if l == '>>'
+          if m = l.match(/\/([^ ]+) /); names << m[1]; end
+        elsif l.match(/\/Font\s*$/)
+          names = []
+        end
+
+        names
+      end
+
+      []
+    end
+
+    def dup(new_doc)
+
+      o0 = self
+      o = o0.class.new(new_doc, @ref)
+      o.instance_eval { @lines = o0.lines.dup }
+
+      o
+    end
+
+    def find(opts={}, &block)
+
+      return self if block.call(self)
+
+      [ *kids, contents ].compact.each do |k|
+        o = @document.objs[k]
+        return o if o && block.call(o)
+      end
+
+      nil
+    end
+
+    def crop_box
+
+      r = lookup('CropBox') || lookup('MediaBox')
+
+      r ? r.strip[1..-2].split(' ').collect(&:strip).collect(&:to_f) : nil
+    end
+
+    def crop_dims
+
+      x, y, w, h = crop_box
+
+      x ? [ w - x, h - y ] : nil
+    end
+
+    def prepend_text(x, y, text, opts={})
+
+      o = find { |o| o.index('BT') }
+      fail ArgumentError.new('found no BT in the tree') unless o
+
+      font = opts[:font] || o.font_names.first || 'TT0'
+      size = opts[:size] || 10
+      comm = opts[:comment]
+
+      i = o.index('BT')
+      bt = []
+      bt << 'BT'
+      bt << "#{x} #{y} Td"
+      bt << "/#{font} #{size} Tf"
+      bt << "(#{text})Tj"
+      bt << 'ET'
+      bt << " % #{comm}" if comm
+      bt = bt.join(' ')
+
+      o.lines.insert(i, bt)
+
+      o
+    end
+  end
 end
 

data/spec/core_spec.rb

@@ -0,0 +1,30 @@
+
+#
+# specifying podoff
+#
+# Tue Oct 20 13:11:38 JST 2015
+#
+
+require 'spec_helper'
+
+
+describe Podoff do
+
+  describe '.load' do
+
+    it 'loads a PDF document' do
+
+      d = Podoff.load('pdfs/udocument0.pdf')
+
+      expect(d.class).to eq(Podoff::Document)
+    end
+
+    it 'rejects items that are not PDF documents' do
+
+      expect {
+        Podoff.load('spec/spec_helper.rb')
+      }.to raise_error(ArgumentError, 'not a PDF file')
+    end
+  end
+end
+

data/spec/document_spec.rb

@@ -0,0 +1,95 @@
+
+#
+# specifying podoff
+#
+# Tue Oct 20 13:30:16 JST 2015
+#
+
+require 'spec_helper'
+
+
+describe Podoff::Document do
+
+  before :all do
+
+    @d = Podoff.load('pdfs/udocument0.pdf')
+  end
+
+  describe '#objs' do
+
+    it 'returns a hash of PDF "obj"' do
+
+      expect(@d.objs.class).to eq(Hash)
+      expect(@d.objs.values.first.class).to eq(Podoff::Obj)
+      expect(@d.objs.size).to eq(273)
+    end
+  end
+
+  describe '#pages' do
+
+    it 'returns the pages' do
+
+      expect(@d.pages.size).to eq(3)
+      expect(@d.pages.first.class).to eq(Podoff::Obj)
+    end
+  end
+
+  describe '#page' do
+
+    it 'returns a page given an index (starts at 1)' do
+
+      p = @d.page(1)
+
+      expect(p.class).to eq(Podoff::Obj)
+      expect(p.type).to eq('Page')
+    end
+
+    it 'returns nil if the page doesn\'t exist' do
+
+      expect(@d.page(0)).to eq(nil)
+      expect(@d.page(9)).to eq(nil)
+    end
+  end
+
+  describe '#fonts' do
+
+    it 'returns the font obj' do
+
+      expect(@d.fonts.size).to eq(35)
+      expect(@d.fonts.first.class).to eq(Podoff::Obj)
+    end
+  end
+
+  describe '#write' do
+
+    it 'writes the document to a given path' do
+
+      @d.write('tmp/out.pdf')
+
+      s = File.open('tmp/out.pdf', 'r:iso8859-1') { |f| f.read }
+      lines = s.split("\n")
+
+      expect(lines.first).to match(/^%PDF-1.7$/)
+      expect(lines.last).to match(/^%%EOF$/)
+    end
+  end
+
+  describe '#dup' do
+
+    it 'produces a shallow copy of the document' do
+
+      d = @d.dup
+
+      expect(d.class
+        ).to eq(Podoff::Document)
+      expect(d.objs.hash
+        ).not_to eq(@d.objs.hash)
+      expect(d.objs.values.first.hash
+        ).not_to eq(@d.objs.values.first.hash)
+
+      expect(d.objs.values.first.document).to eq(d)
+      expect(@d.objs.values.first.document).to eq(@d)
+    end
+  end
+end
+

data/spec/obj_spec.rb

@@ -0,0 +1,183 @@
+
+#
+# specifying podoff
+#
+# Tue Oct 20 15:08:59 JST 2015
+#
+
+require 'spec_helper'
+
+
+describe Podoff::Obj do
+
+  before :all do
+
+    @d = Podoff.load('pdfs/udocument0.pdf')
+  end
+
+  describe '#document' do
+
+    it 'points to the Podoff::Document owning this Obj' do
+
+      expect(@d.objs.values.first.document).to eq(@d)
+    end
+  end
+
+  describe '#type' do
+
+    it 'returns the type of the obj' do
+
+      expect(@d.objs['23 0'].type).to eq('Font')
+    end
+
+    it 'returns nil if there is no type' do
+
+      expect(@d.objs['17 0'].type).to eq(nil)
+    end
+  end
+
+  describe '#parent' do
+
+    it 'returns the parent ref if any' do
+
+      expect(@d.objs.values.first.parent).to eq('2 0')
+    end
+
+    it 'returns nil if there is no parent' do
+
+      expect(@d.objs['2 0'].parent).to eq(nil)
+    end
+  end
+
+  describe '#kids' do
+
+    it 'returns a list of refs' do
+
+      expect(@d.objs['2 0'].kids).to eq([ '1 0', '16 0', '33 0' ])
+    end
+
+    it 'returns an empty list if there are no kids' do
+
+      expect(@d.objs['224 0'].kids).to eq([])
+    end
+  end
+
+  describe '#contents' do
+
+    it 'returns the Contents reference' do
+
+      expect(@d.objs['1 0'].contents).to eq('3 0')
+    end
+
+    it 'returns nil if none' do
+
+      expect(@d.objs['224 0'].contents).to eq(nil)
+    end
+  end
+
+  describe '#font_names' do
+
+    it 'returns a list of font names visible in this obj' do
+
+      expect(
+        @d.objs.values.first.font_names
+      ).to eq(%w[
+        C2_0 TT2 TT1 TT0 C2_2 C2_1 Helv
+      ])
+    end
+  end
+
+  describe '#index' do
+
+    it 'returns the for a given line' do
+
+      o = @d.objs['3 0']
+
+      expect(o.index('stream')).to eq(4)
+      expect(o.index('BT')).to eq(14)
+    end
+
+    it 'returns nil when it doesn\'t find' do
+
+      o = @d.objs['3 0']
+
+      expect(o.index('nada')).to eq(nil)
+    end
+
+    it 'accepts regexes' do
+
+      o = @d.objs['1 0']
+
+      i = o.index(/^\/B.+Box /)
+
+      expect(i).to eq(40)
+      expect(o.lines[i]).to eq('/BleedBox [0.0 0.0 612.0 792.0]')
+    end
+
+    it 'accepts a start index' do
+
+      o = @d.objs['1 0']
+
+      i = o.index(/^\/.+Box /, 3)
+
+      expect(i).to eq(5)
+      expect(o.lines[i]).to eq('/TrimBox [0.0 0.0 612.0 792.0]')
+    end
+  end
+
+  describe '#find' do
+
+    it 'returns the first sub obj that matches the given block' do
+
+      o = @d.objs['1 0']
+
+      o1 = o.find { |o| o.index('stream') }
+
+      expect(o1).not_to eq(nil)
+      expect(o1.lines.first).to eq('3 0 obj ')
+    end
+
+    it 'accept a :skip_root option'
+  end
+
+  describe '#gather' do
+
+    it 'returns a list of sub obj that match the given block'
+    it 'accept a :skip_root option'
+  end
+
+  describe '#crop_box' do
+
+    it 'returns the [ x, y, w, h ] box for the obj' do
+
+      o = @d.objs['1 0']
+
+      expect(o.crop_box).to eq([ 0.0, 0.0, 612.0, 792.0 ])
+    end
+
+    it 'defaults to the MediaBox' do
+
+      o = @d.objs['16 0']
+
+      expect(o.crop_box).to eq([ 0.0, 0.0, 612.0, 792.0 ])
+    end
+  end
+
+  describe '#crop_dims' do
+
+    it 'returns [ w, h ]' do
+
+      o = @d.objs['1 0']
+
+      expect(o.crop_dims).to eq([ 612.0, 792.0 ])
+    end
+
+    it 'defaults to the MediaBox' do
+
+      o = @d.objs['16 0']
+
+      expect(o.crop_dims).to eq([ 612.0, 792.0 ])
+    end
+  end
+end
+

data/spec/spec_helper.rb

@@ -0,0 +1,11 @@
+
+#
+# Specifying podoff
+#
+# Tue Oct 20 13:10:29 JST 2015
+#
+
+require 'pp'
+
+require 'podoff'
+

data/spec/update_spec.rb

@@ -0,0 +1,36 @@
+
+#
+# specifying podoff
+#
+# Tue Oct 20 17:25:49 JST 2015
+#
+
+require 'spec_helper'
+
+
+describe Podoff do
+
+  before :all do
+
+    @d = Podoff.load('pdfs/udocument0.pdf')
+  end
+
+  describe 'Obj.prepend_text' do
+
+    it 'adds text at the beginning of an obj' do
+
+      d = @d.dup
+
+      p1 = d.page(1)
+      p1.prepend_text(0, 500, 'hello world! xxx', size: 35, font: 'Helv')
+      #p1.prepend_text(0, 450, '"stuff NADA"', size: 35, font: 'Helv')
+
+      d.write('tmp/out.pdf')
+
+      s = `grep -a "hello world!" tmp/out.pdf`.strip
+
+      expect(s).to eq('BT 0 500 Td /Helv 35 Tf (hello world! xxx)Tj ET')
+    end
+  end
+end
+

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: podoff
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.9.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-10-19 00:00:00.000000000 Z
+date: 2015-10-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -52,7 +52,13 @@ extra_rdoc_files: []
 files:
 - Rakefile
 - lib/podoff.rb
+- spec/core_spec.rb
+- spec/document_spec.rb
+- spec/obj_spec.rb
+- spec/spec_helper.rb
+- spec/update_spec.rb
 - podoff.gemspec
+- CHANGELOG.txt
 - LICENSE.txt
 - README.md
 homepage: http://github.com/jmettraux/podoff