lib/podoff.rb in podoff-1.1.1 vs lib/podoff.rb in podoff-1.2.0

@@ -28,48 +28,55 @@
 require 'stringio'
 
 
 module Podoff
 
-  VERSION = '1.1.1'
+  VERSION = '1.2.0'
 
-  def self.load(path, encoding='iso-8859-1')
+  def self.load(path, encoding)
 
     Podoff::Document.load(path, encoding)
   end
 
-  def self.parse(s)
+  def self.parse(s, encoding)
 
-    Podoff::Document.new(s)
+    Podoff::Document.new(s, encoding)
   end
 
   class Document
 
-    def self.load(path, encoding='iso-8859-1')
+    def self.load(path, encoding)
 
-      Podoff::Document.new(File.open(path, 'r:' + encoding) { |f| f.read })
+      Podoff::Document.new(
+        File.open(path, 'r:' + encoding) { |f| f.read },
+        encoding
+      )
     end
 
     def self.parse(s)
 
       Podoff::Document.new(s)
     end
 
+    attr_reader :encoding
+
     attr_reader :scanner
     attr_reader :version
     attr_reader :xref
     attr_reader :objs
     attr_reader :obj_counters
     attr_reader :root
     #
     attr_reader :additions
 
-    def initialize(s)
+    def initialize(s, encoding)
 
       fail ArgumentError.new('not a PDF file') \
         unless s.match(/\A%PDF-\d+\.\d+\s/)
 
+      @encoding = encoding
+
       @scanner = ::StringScanner.new(s)
       @version = nil
       @xref = nil
       @objs = {}
       @obj_counters = {}
@@ -111,15 +118,10 @@
     def source
 
       @scanner.string
     end
 
-    def extract_ref(s)
-
-      s.gsub(/\s+/, ' ').gsub(/[^0-9 ]+/, '').strip
-    end
-
     def updated?
 
       @additions.any?
     end
 
@@ -127,10 +129,12 @@
 
       o = self
 
       self.class.allocate.instance_eval do
 
+        @encoding = o.encoding
+
         @scanner = ::StringScanner.new(o.source)
         @xref = o.xref
 
         @objs = o.objs.inject({}) { |h, (k, v)| h[k] = v.dup(self); h }
         @obj_counters = o.obj_counters.dup
@@ -144,30 +148,27 @@
       end
     end
 
     def pages
 
-      @objs.values.select { |o| o.type == '/Page' }
+      #@objs.values.select { |o| o.type == '/Page' }
+
+      ps = @objs.values.find { |o| o.type == '/Pages' }
+      return nil unless ps
+
+      extract_refs(ps.attributes[:kids]).collect { |r| @objs[r] }
     end
 
     def page(index)
 
-      return nil if index == 0
-
-      pas = pages
-      return nil if pas.empty?
-
-      return (
-        index > 0 ? pas.at(index - 1) : pas.at(index)
-      ) unless pas.first.attributes[:pagenum]
-
       if index < 0
-        max = pas.inject(0) { |n, pa| [ n, pa.page_number ].max }
-        index = max + 1 + index
+        pages[index]
+      elsif index == 0
+        nil
+      else
+        pages[index - 1]
       end
-
-      pas.find { |pa| pa.page_number == index }
     end
 
     def new_ref
 
       "#{
@@ -222,40 +223,44 @@
       obj = obj.replicate unless obj.replica?
 
       add(obj)
     end
 
-    def write(path)
+    def write(path=:string, encoding=nil)
 
+      encoding ||= @encoding
+
       f =
         case path
           when :string, '-' then StringIO.new
           when String then File.open(path, 'wb')
           else path
         end
+      f.set_encoding(encoding) # internal encoding: nil
+      #f.set_encoding(encoding, encoding)
 
       f.write(source)
 
       if @additions.any?
 
         pointers = {}
 
         @additions.values.each do |o|
           f.write("\n")
-          pointers[o.ref.split(' ').first.to_i] = f.pos + 1
-          f.write(o.to_s)
+          pointers[o.ref.split(' ').first.to_i] = f.pos
+          f.write(o.to_s.force_encoding(encoding))
         end
         f.write("\n\n")
 
-        xref = f.pos + 1
+        xref = f.pos
 
         write_xref(f, pointers)
 
         f.write("trailer\n")
         f.write("<<\n")
         f.write("/Prev #{self.xref}\n")
-        f.write("/Size #{objs.size}\n")
+        f.write("/Size #{objs.size + 1}\n")
         f.write("/Root #{root} R\n")
         f.write(">>\n")
         f.write("startxref #{xref}\n")
         f.write("%%EOF\n")
       end
@@ -263,38 +268,41 @@
       f.close if path.is_a?(String) || path.is_a?(Symbol)
 
       f.is_a?(StringIO) ? f.string : nil
     end
 
-    def rewrite(path=:string)
+    def rewrite(path=:string, encoding=nil)
 
+      encoding ||= @encoding
+
       f =
         case path
           when :string, '-' then StringIO.new
           when String then File.open(path, 'wb')
           else path
         end
+      f.set_encoding(encoding)
 
       v = source.match(/%PDF-\d+\.\d+/)[0]
       f.write(v)
       f.write("\n")
 
       pointers = {}
 
       objs.keys.sort.each do |k|
-        pointers[k.split(' ').first.to_i] = f.pos + 1
-        f.write(objs[k].source)
+        pointers[k.split(' ').first.to_i] = f.pos
+        f.write(objs[k].source.force_encoding(encoding))
         f.write("\n")
       end
 
-      xref = f.pos + 1
+      xref = f.pos
 
       write_xref(f, pointers)
 
       f.write("trailer\n")
       f.write("<<\n")
-      f.write("/Size #{objs.size}\n")
+      f.write("/Size #{objs.size + 1}\n")
       f.write("/Root #{root} R\n")
       f.write(">>\n")
       f.write("startxref #{xref}\n")
       f.write("%%EOF\n")
 
@@ -307,11 +315,11 @@
 
     def write_xref(f, pointers)
 
       f.write("xref\n")
       f.write("0 1\n")
-      f.write("0000000000 65535 f\n")
+      f.write("0000000000 65535 f \n")
 
       pointers
         .keys
         .sort
         .inject([ [] ]) { |ps, k|
@@ -319,27 +327,36 @@
           ps.last << k
           ps
         }
         .each { |part|
           f.write("#{part.first} #{part.size}\n")
-          part.each { |k| f.write(sprintf("%010d 00000 n\n", pointers[k])) }
+          part.each { |k| f.write(sprintf("%010d 00000 n \n", pointers[k])) }
         }
     end
 
     def make_stream(&block)
 
       s = Stream.new
       s.instance_exec(&block) if block
 
       s
     end
+
+    def extract_ref(s)
+
+      s.gsub(/\s+/, ' ').gsub(/[^0-9 ]+/, '').strip
+    end
+
+    def extract_refs(s)
+
+      s.gsub(/\s+/, ' ').scan(/(\d+ \d+) R/).collect(&:first)
+    end
   end
 
   class Obj
 
-    ATTRIBUTES =
-      { type: 'Type', contents: 'Contents', pagenum: 'pdftk_PageNum' }
+    ATTRIBUTES = { type: 'Type', contents: 'Contents', kids: 'Kids' }
 
     def self.extract(doc)
 
       sca = doc.scanner
 
@@ -409,15 +426,9 @@
     end
 
     def type
 
       @attributes && @attributes[:type]
-    end
-
-    def page_number
-
-      r = @attributes && @attributes[:pagenum]
-      r ? r.to_i : nil
     end
 
     def insert_font(nick, obj_or_ref)
 
       fail ArgumentError.new("target '#{ref}' not a replica") \