combine_pdf 0.2.34 → 0.2.35

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 978b43d9e325d4e5eba06ceebb396565c0413bc1
-  data.tar.gz: b3f85e2ff8d5fa57643f4aa516c620a0b9dadafc
+  metadata.gz: 9fcaee4b0d0bc2b6991c41c570b300120038e6bd
+  data.tar.gz: 9045bd35b291cd33fb9d8f5a1e5611e64c4b81bb
 SHA512:
-  metadata.gz: f0b111a144fe3b0c8ea54bb7a138d1d97e3d0f59af48e296e6286ea40dfb575c7f1573061e526f278c84765c75c6d56c1ee8d96dccb7c93c2972e296c568fd24
-  data.tar.gz: 0bfbf5060a5f5210fd2349acf898b2feced9e2610cf9c734cb9a20c5c969dfbd361f81ac769e48e4274b23c7217e4476d651daf608ce8a25c139288deecbab03
+  metadata.gz: a82447b8e8caf898149b868818aa5c61f99f30f974297d8ed19e2afdb3ebb2f48f86f03909cbd03a698b23288455ec2743ab6a3fec73a489e73e3c47a6b46769
+  data.tar.gz: f1d0d133c2a84c82cfe7920b626ae56cf8a58e40a73da5ca5bff5fb5c9c07574e404fe5ebcb913fcc14464ca9029cba971c7f581a60af891d0cb555e0be9abb0

data/CHANGELOG.md

@@ -2,6 +2,21 @@
 
 ***
 
+Change log v.0.2.35 (Release Candidate)
+
+**Update**: Updated / upgraded our RC4 and AES PDF encryption support (for non-password protected PDFs). Credit to Gyuchang Jun (@gyuchang) for his work on providing CombinePDF with this extra encryption support. I have no idea what magic he used to make this happen, but it's beautiful!
+
+**Release**: This gem had been using a development versioning scheme for far too long. The API is stable enough to switch to a production versioning scheme. This version is expected to be the last 0.x version. Assuming this version will be stable enough, it is expected to be re-released as v.1.0.
+
+
+***
+
+Change log v.0.2.34
+
+**Fix**: issue #44 for wkhtmltopdf compatibility and PDF v.1.2 use of named destinations. Credit to Devin Wadsworth (@daymun) for exposing the issue.
+
+***
+
 Change log v.0.2.33
 
 **Update**: Fix #97 to allow javascript support for interactive objects. Credit to @joshirashmics for exposing the issue.

data/lib/combine_pdf/decrypt.rb

@@ -31,8 +31,7 @@ module CombinePDF
                       0x64, 0x00, 0x4E, 0x56, 0xFF, 0xFA, 0x01, 0x08,
                       0x2E, 0x2E, 0x00, 0xB6, 0xD0, 0x68, 0x3E, 0x80,
                       0x2F, 0x0C, 0xA9, 0xFE, 0x64, 0x53, 0x69, 0x7A]
-      @key_crypt_first_iv_store = nil
-      @encryption_iv = nil
+
       change_references_to_actual_values @encryption_dictionary
     end
 
@@ -45,20 +44,24 @@ module CombinePDF
         # raise_encrypted_error
         _perform_decrypt_proc_ @objects, method(:decrypt_RC4)
       when 4
-        # raise unsupported error for now
-        raise_encrypted_error
         # make sure CF is a Hash (as required by the PDF standard for this type of encryption).
         raise_encrypted_error unless actual_object(@encryption_dictionary[:CF]).is_a?(Hash)
 
-        # do nothing if there is no data to decrypt except embeded files...?
-        return true unless (actual_object(@encryption_dictionary[:CF]).values.select { |v| !v[:AuthEvent] || v[:AuthEvent] == :DocOpen }).empty?
-
-      # attempt to decrypt all strings?
-      # attempt to decrypy all streams
-      # attempt to decrypt all embeded files?
+        # support trivial case for now
+        # - same filter for streams (Stmf) and strings(Strf)
+        # - AND :CFM == :V2 (use algorithm 1)
+        raise_encrypted_error unless (@encryption_dictionary[:StmF] == @encryption_dictionary[:StrF])
 
-      else
-        raise_encrypted_error
+        cfilter = actual_object(@encryption_dictionary[:CF])[@encryption_dictionary[:StrF]]
+        raise_encrypted_error unless cfilter
+        raise_encrypted_error unless (cfilter[:AuthEvent] == :DocOpen)
+        if (cfilter[:CFM] == :V2)
+          _perform_decrypt_proc_ @objects, method(:decrypt_RC4)
+        elsif (cfilter[:CFM] == :AESV2)
+          _perform_decrypt_proc_ @objects, method(:decrypt_AES)
+        else
+          raise_encrypted_error
+        end
       end
       # rebuild stream lengths?
       @objects
@@ -85,11 +88,9 @@ module CombinePDF
       # # 4(a) (Security handlers of revision 4 or greater)
       # # if document metadata is not being encrypted, add 4 bytes with the value 0xFFFFFFFF.
       if actual_object(@encryption_dictionary[:R]) >= 4
-        key << if actual_object(@encryption_dictionary)[:EncryptMetadata] == false
-                 "\xFF\xFF\xFF\xFF"
-               else # default is true and nil != false
-                 "\x00\x00\x00\x00"
-               end
+        if actual_object(@encryption_dictionary)[:EncryptMetadata] == false
+          key << "\xFF\xFF\xFF\xFF".force_encoding(Encoding::ASCII_8BIT)
+        end
       end
       # 5) pass everything as a MD5 hash
       key = Digest::MD5.digest(key)
@@ -132,22 +133,24 @@ module CombinePDF
     end
 
     def decrypt_AES(encrypted, encrypted_id, encrypted_generation, _encrypted_filter)
-      ## extract encryption_iv if it wasn't extracted yet
-      unless @encryption_iv
-        @encryption_iv = encrypted[0..15].to_i
-        # raise "Tryed decrypting using AES and couldn't extract iv" if @encryption_iv == 0
-        @encryption_iv = 0.chr * 16
-        # encrypted = encrypted[16..-1]
-      end
       ## start decryption using padding strings
       object_key = @key.dup
-      (0..2).each { |e| object_key << (encrypted_id >> e * 8 & 0xFF) }
-      (0..1).each { |e| object_key << (encrypted_generation >> e * 8 & 0xFF) }
-      object_key << 'sAlT'
+      object_key << [encrypted_id].pack('i')[0..2]
+      object_key << [encrypted_generation].pack('i')[0..1]
+      object_key << 'sAlT'.force_encoding(Encoding::ASCII_8BIT)
       key_length = object_key.length < 16 ? object_key.length : 16
-      cipher = OpenSSL::Cipher::Cipher.new("aes-#{object_key.length << 3}-cbc").decrypt
-      cipher.padding = 0
-      (cipher.update(encrypted) + cipher.final).unpack('C*')
+
+      begin
+        cipher = OpenSSL::Cipher.new("aes-#{key_length << 3}-cbc")
+        cipher.decrypt
+        cipher.key = Digest::MD5.digest(object_key)[(0...key_length)]
+        cipher.iv = encrypted[0..15]
+        cipher.padding = 0
+        cipher.update(encrypted[16..-1]) + cipher.final
+      rescue StandardError => e
+        # puts e.class.name
+        encrypted
+      end
     end
 
     protected
@@ -159,14 +162,14 @@ module CombinePDF
         encrypted_id ||= actual_object(object[:indirect_reference_id])
         encrypted_generation ||= actual_object(object[:indirect_generation_number])
         encrypted_filter ||= actual_object(object[:Filter])
-        if object[:raw_stream_content]
+        if object[:raw_stream_content] && !object[:raw_stream_content].empty?
           stream_length = actual_object(object[:Length])
           actual_length = object[:raw_stream_content].bytesize
           # p stream_length
           # p actual_length
           # p object[:Length]
           # p object
-          warn "Stream registeded length was #{object[:Length]} and the actual length was #{actual_length}." if actual_length < stream_length
+          warn "Stream registered length was #{object[:Length]} and the actual length was #{actual_length}." if actual_length < stream_length
           length = [stream_length, actual_length].min
           object[:raw_stream_content] = decrypt_proc.call((object[:raw_stream_content][0...length]), encrypted_id, encrypted_generation, encrypted_filter)
         end

data/lib/combine_pdf/page_methods.rb

@@ -182,6 +182,7 @@ module CombinePDF
     # border_width:: border width in PDF units. defaults to nil (none).
     # box_radius:: border radius in PDF units. defaults to 0 (no corner rounding).
     # opacity:: textbox opacity, a float between 0 (transparent) and 1 (opaque)
+    # ctm:: A PDF complient CTM data array that will manipulate the axis and allow transformations. i.e. `[1,0,0,1,0,0]`
     def textbox(text, properties = {})
       options = {
         x: 0,
@@ -392,6 +393,8 @@ module CombinePDF
     # This method moves the Page[:Rotate] property into the page's data stream, so that
     # "what you see is what you get".
     #
+    # After using thie method, {#orientation} should return the absolute orientation rather than only the data's orientation (unless `:Rotate` is changed).
+    #
     # This is usful in cases where there might be less control over the source PDF files,
     # and the user assums that the PDF page's data is the same as the PDF's pages
     # on screen display (Rotate rotates a page but leaves the data in the original orientation).
@@ -441,7 +444,7 @@ module CombinePDF
       y_ratio = 1.0 * (new_size[3] - new_size[1]) / (c_size[3]) #-c_size[1])
       x_move = new_size[0] - c_size[0]
       y_move = new_size[1] - c_size[1]
-      puts "ctm will be: #{x_ratio.round(4)} 0 0 #{y_ratio.round(4)} #{x_move} #{y_move}"
+      # puts "ctm will be: #{x_ratio.round(4)} 0 0 #{y_ratio.round(4)} #{x_move} #{y_move}"
       self[:MediaBox] = [(c_mediabox[0] + x_move), (c_mediabox[1] + y_move), ((c_mediabox[2] * x_ratio) + x_move), ((c_mediabox[3] * y_ratio) + y_move)]
       self[:CropBox] = [(c_cropbox[0] + x_move), (c_cropbox[1] + y_move), ((c_cropbox[2] * x_ratio) + x_move), ((c_cropbox[3] * y_ratio) + y_move)] if c_cropbox
       x_ratio = y_ratio = [x_ratio, y_ratio].min if conserve_aspect_ratio
@@ -506,7 +509,10 @@ module CombinePDF
       fix_rotation
     end
 
-    # get or set (by clockwise rotation) the page's orientation
+    # get or set (by clockwise rotation) the page's data orientation.
+    #
+    # note that the data's orientation is the way data is oriented on the page.
+    # The display orientati0n (which might different) is controlled by the `:Rotate` property. see {#fix_orientation} for more details.
     #
     # accepts one optional parameter:
     # force:: to get the orientation, pass nil. to set the orientatiom, set fource to either :portrait or :landscape. defaults to nil (get orientation).

data/lib/combine_pdf/version.rb

@@ -1,3 +1,3 @@
 module CombinePDF
-  VERSION = '0.2.34'.freeze
+  VERSION = '0.2.35'.freeze
 end

data/test/automated

@@ -57,16 +57,37 @@ CombinePDF.load("./Ruby/test\ pdfs/Scribus-unknown_err3.pdf").save '08_3-unknown
 
 CombinePDF.load("/Users/2Be/Ruby/test\ pdfs/nil_object.pdf").save('09_nil_in_parsed_array.pdf')
 
+encrypted = [ "./Ruby/test\ pdfs/pdf-reader/encrypted_version4_revision4_128bit_aes_user_pass_apples_enc_metadata.pdf",
+              "./Ruby/test\ pdfs/AESv2\ encrypted.pdf",
+              "./Ruby/test\ pdfs/pdf-reader/encrypted_version2_revision3_128bit_rc4_blank_user_pass.pdf",
+              "./Ruby/test\ pdfs/AES\ enc.pdf",
+              "./Ruby/test\ pdfs/RC4\ enc.pdf"]
+
+encrypted.length.times do |i|
+  fname = File.basename encrypted[i]
+  begin
+    CombinePDF.load(encrypted[i]).save "10_#{i}_#{fname}"
+  rescue => e
+    puts e.class.name, e.message
+    if(i == 0)
+      puts "CombinePDF expected to fail to read AESv2 #{fname}"
+    else
+      puts "ERROR: CombinePDF failed to open #{fname}"
+    end
+  end
+end
+
 require 'prawn'
-IO.binwrite '10_prawn.pdf', (Prawn::Document.new { text 'Hello World!' }).render
+IO.binwrite '11_prawn.pdf', (Prawn::Document.new { text 'Hello World!' }).render
 page = CombinePDF.parse((Prawn::Document.new { text 'Hello World!' }).render)
 pdf = CombinePDF.new
 pdf << page
-pdf.save '10_parsed_from_prawn.pdf'
+pdf.save '11_parsed_from_prawn.pdf'
 pdf = CombinePDF.new
 pdf << page << page
-pdf.save('10_AcrobatReader_is_unique_page.pdf')
+pdf.save('11_AcrobatReader_is_unique_page.pdf')
 
+puts GC.stat.inspect
 # unify = [
 #   "./Ruby/test\ pdfs/AESv2\ encrypted.pdf",
 #   "./Ruby/test\ pdfs/data-in-comment.pdf",

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 0.2.34
+  version: 0.2.35
 platform: ruby
 authors:
 - Boaz Segev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-02-12 00:00:00.000000000 Z
+date: 2017-03-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4