combine_pdf 1.0.21 → 1.0.23

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6ee7f4bb8ca8b2a51a7f42251d9a3faa6c1d91d19ed3d91db8ce470a1b1995a9
-  data.tar.gz: 5be4868dcb9f1b834fc12e5316d5a46b6fee97104c8509cbcdb13908b499d79f
+  metadata.gz: 94a057a85d5c2709211baa3ed7d7deaf73fe93d6bb39ef76e0441a166fb36926
+  data.tar.gz: c7dc7060c7abd51d84ee871b5f818d6e23a797eb424a8a7a963b0ae7f7324921
 SHA512:
-  metadata.gz: 751d04258815d32076eccc5bb2905cfed641b2942721900dfa5826b0cf902a35bbf60178501a81617ce0979b1be87554666320423c4066b375dced68927e8aea
-  data.tar.gz: 7171c0c987646b6336984fff497fa40f02ae7b6079cd8a29b58cb7659c1b527179b44f0c7210edeb63dcc931c634320ae93d0513579852ee28beca23896a085e
+  metadata.gz: 110074ae751586009d436dd4dc997c7d6bb71480d782270fe67834458cecc7479b58effc8102745a437c718426c97ca78d9ea3d2941355ba1ce8fc6f34ab2b8a
+  data.tar.gz: 4cf409946ba651fd474f7ff8a3dbf56442afd96b35fe73b68013a9a863e01e9d766a516ea4ddd4f5af7f2c47192abc0619321a6bc01c5a4e0dcd0e192701d168

data/.travis.yml

@@ -0,0 +1 @@
+language: ruby

data/CHANGELOG.md

@@ -1,6 +1,14 @@
 # Change Log
 
-***
+#### Change log v.1.0.23 (2023-03-04)
+
+**Feature**: merged PR #177 for the `raise_on_encrypted: true` option support. Credit to @leviwilson and @kimyu92 for the PR.
+
+#### Change log v.1.0.22
+
+**Fix**: fix `fonts` dereferencing issue (#203), credit to @MarcWeber (Marc Weber) for identifying the issue.
+
+**Fix**: fix `metrix` dependency, credit to @casperisfine (Jean byroot Boussier) for PR #195.
 
 #### Change log v.1.0.21
 

data/README.md

@@ -39,7 +39,7 @@ Quick rundown:
 
     Some links will be lost when ripping pages out of PDF files and merging them with another PDF.
 
-* Some encrypted PDF files (usually the ones you can't view without a password) will fail quietly instead of noisily.
+* Some encrypted PDF files (usually the ones you can't view without a password) will fail quietly instead of noisily. If you prefer to choose the noisy route, you can specify the `raise_on_encrypted` option using `CombinePDF.load(pdf_file, raise_on_encrypted: true)` which will raise a `CombinePDF::EncryptionError`.
 
 * Sometimes the CombinePDF will raise an exception even if the PDF could be parsed (i.e., when PDF optional content exists)... I find it better to err on the side of caution, although for optional content PDFs an exception is avoidable using `CombinePDF.load(pdf_file, allow_optional_content: true)`.
 

data/Rakefile

@@ -1,2 +1,9 @@
-require "bundler/gem_tasks"
+require 'bundler/gem_tasks'
+require 'rake/testtask'
+
+task default: 'test'
+
+Rake::TestTask.new do |t|
+  t.test_files = FileList['test/**/*_test.rb']
+end
 

data/combine_pdf.gemspec

@@ -19,8 +19,10 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
 
   spec.add_runtime_dependency 'ruby-rc4', '>= 0.1.5'
+  spec.add_runtime_dependency 'matrix'
 
   # spec.add_development_dependency "bundler", ">= 1.7"
   spec.add_development_dependency "rake", ">= 12.3.3"
   spec.add_development_dependency "minitest"
+  spec.add_development_dependency "minitest-around"
 end

data/lib/combine_pdf/parser.rb

@@ -33,7 +33,7 @@ module CombinePDF
     # they are mainly to used to know if the file is (was) encrypted and to get more details.
     attr_reader :info_object, :root_object, :names_object, :forms_object, :outlines_object, :metadata
 
-    attr_reader :allow_optional_content
+    attr_reader :allow_optional_content, :raise_on_encrypted
     # when creating a parser, it is important to set the data (String) we wish to parse.
     #
     # <b>the data is required and it is not possible to set the data at a later stage</b>
@@ -58,6 +58,7 @@ module CombinePDF
       @version = nil
       @scanner = nil
       @allow_optional_content = options[:allow_optional_content]
+      @raise_on_encrypted = options[:raise_on_encrypted]
     end
 
     # parse the data in the new parser (the data already set through the initialize / new method)
@@ -96,6 +97,7 @@ module CombinePDF
       end
 
       if @root_object[:Encrypt]
+        raise EncryptionError, 'the file is encrypted' if @raise_on_encrypted
         # change_references_to_actual_values @root_object
         warn 'PDF is Encrypted! Attempting to decrypt - not yet fully supported.'
         decryptor = PDFDecrypt.new @parsed, @root_object
@@ -360,8 +362,8 @@ module CombinePDF
           @scanner.pos += 1 if @scanner.peek(1) == "\n".freeze && @scanner.matched[-1] != "\n".freeze
           # advance by the publshed stream length (if any)
           old_pos = @scanner.pos
-          if(out.last.is_a?(Hash) && out.last[:Length].is_a?(Integer) && out.last[:Length].to_i > 2)
-            @scanner.pos += out.last[:Length].to_i - 2
+          if(out.last.is_a?(Hash) && out.last[:Length].is_a?(Integer) && out.last[:Length] > 2)
+            @scanner.pos += out.last[:Length] - 2
           end
 
           # the following was dicarded because some PDF files didn't have an EOL marker as required

data/lib/combine_pdf/pdf_public.rb

@@ -96,6 +96,7 @@ module CombinePDF
       parser ||= PDFParser.new('')
       raise TypeError, "initialization error, expecting CombinePDF::PDFParser or nil, but got #{parser.class.name}" unless parser.is_a? PDFParser
       @objects = parser.parse
+
       # remove any existing id's
       remove_old_ids
       # set data from parser
@@ -257,12 +258,18 @@ module CombinePDF
     def fonts(limit_to_type0 = false)
       fonts_array = []
       pages.each do |pg|
-        if pg[:Resources][:Font]
-          pg[:Resources][:Font].values.each do |f|
-            f = f[:referenced_object] if f[:referenced_object]
-            if (limit_to_type0 || f[:Subtype] == :Type0) && f[:Type] == :Font && !fonts_array.include?(f)
-              fonts_array << f
-            end
+        r = pg[:Resources]
+        next if !r
+        r = r[:referenced_object] if r[:referenced_object]
+        r = r[:Font]
+        next if !r
+        r = r[:referenced_object] if r[:referenced_object]
+        r.values.each do |f|
+          next if f.class != Hash
+          f = f[:referenced_object] if f[:referenced_object]
+          next if f.class != Hash
+          if (limit_to_type0 || f[:Subtype] == :Type0) && f[:Type] == :Font && !fonts_array.include?(f)
+            fonts_array << f
           end
         end
       end

data/lib/combine_pdf/version.rb

@@ -1,3 +1,3 @@
 module CombinePDF
-  VERSION = '1.0.21'.freeze
+  VERSION = '1.0.23'.freeze
 end

data/test/automated

@@ -5,7 +5,7 @@ $VERBOSE = true
 require 'benchmark'
 $LOAD_PATH.unshift File.expand_path(File.join('..', '..', 'lib'), __FILE__)
 require 'combine_pdf'
-require 'bundler/setup'
+# require 'bundler/setup'
 
 # You can add fixtures and/or initialization code here to make experimenting
 # with your gem easier. You can also use a different console, if you like.
@@ -14,54 +14,54 @@ require 'bundler/setup'
 # require "pry"
 # Pry.start
 
-pdf = CombinePDF.load "./Ruby/test\ pdfs/filled_form.pdf"
+pdf = CombinePDF.load "../../test\ pdfs/filled_form.pdf"
 pdf.save '01_check_radio_buttuns.pdf'
-pdf = CombinePDF.load "./Ruby/test\ pdfs/filled_form.pdf"
-pdf << CombinePDF.load("./Ruby/test\ pdfs/empty_form.pdf")
-pdf << CombinePDF.load("./Ruby/test\ pdfs/filled_form.pdf")
+pdf = CombinePDF.load "../../test\ pdfs/filled_form.pdf"
+pdf << CombinePDF.load("../../test\ pdfs/empty_form.pdf")
+pdf << CombinePDF.load("../../test\ pdfs/filled_form.pdf")
 pdf.save '02_check_form_unification_middle_is_empty.pdf'
 
-pdf = CombinePDF.load "./Ruby/test\ pdfs/check_form_data__objstreams_w_versions.pdf"
+pdf = CombinePDF.load "../../test\ pdfs/check_form_data__objstreams_w_versions.pdf"
 pdf.save '02_01_check_form_data_ordering_issue.pdf'
 
 
-pdf = CombinePDF.load './Ruby/test pdfs/share-font-background.pdf'
-pdf2 = CombinePDF.load './Ruby/test pdfs/share-font-foreground.pdf'
+pdf = CombinePDF.load '../../test pdfs/share-font-background.pdf'
+pdf2 = CombinePDF.load '../../test pdfs/share-font-foreground.pdf'
 i = 0
 pdf.pages.each { |pg| pg << pdf2.pages[i] }
 pdf.save '03_check_font_conflict.pdf'
 
-pdf = CombinePDF.load './Ruby/test pdfs/nil_1.pdf'
-pdf2 = CombinePDF.load './Ruby/test pdfs/nil_2.pdf'
+pdf = CombinePDF.load '../../test pdfs/nil_1.pdf'
+pdf2 = CombinePDF.load '../../test pdfs/nil_2.pdf'
 pdf << pdf2
 pdf.save '03_01_nil_value_conflict.pdf'
 
-pdf = CombinePDF.load './Ruby/test pdfs/space_after_streram_keyword.pdf'
+pdf = CombinePDF.load '../../test pdfs/space_after_streram_keyword.pdf'
 pdf.save '03_02_extra_space_after_stream_keyword.pdf'
 
-pdf = CombinePDF.load './Ruby/test pdfs/nested_difference.pdf'
+pdf = CombinePDF.load '../../test pdfs/nested_difference.pdf'
 pdf.save '03_03_nested_difference.pdf'
 
-pdf = CombinePDF.load './Ruby/test pdfs/names_go_haywire_0.pdf'
-pdf << CombinePDF.load('./Ruby/test pdfs/names_go_haywire_1.pdf')
+pdf = CombinePDF.load '../../test pdfs/names_go_haywire_0.pdf'
+pdf << CombinePDF.load('../../test pdfs/names_go_haywire_1.pdf')
 pdf.save '04_check_view_and_names_reference.pdf'
 
-pdf = CombinePDF.load('./Ruby/test pdfs/outlines/self_merge_err.pdf')
+pdf = CombinePDF.load('../../test pdfs/outlines/self_merge_err.pdf')
 pdf.save '05_x1_scribus_test.pdf'
-pdf = CombinePDF.load('./Ruby/test pdfs/outlines/self_merge_err.pdf')
-pdf << CombinePDF.load('./Ruby/test pdfs/outlines/self_merge_err.pdf')
+pdf = CombinePDF.load('../../test pdfs/outlines/self_merge_err.pdf')
+pdf << CombinePDF.load('../../test pdfs/outlines/self_merge_err.pdf')
 pdf.save '05_x2_scribus_test.pdf'
-# pdf = CombinePDF.load "./Ruby/test pdfs/named_dest.pdf";nil
-# pdf.save '05_check_named_dest_links.pdf' # this will take a while
-# pdf = CombinePDF.load "./Ruby/test pdfs/named_dest.pdf";nil
-pdf << CombinePDF.load('./Ruby/test pdfs/named_dest.pdf'); nil
+pdf = CombinePDF.load "../../test pdfs/outlines/named_dest.pdf";nil
+pdf.save '05_check_named_dest_links.pdf' # this will take a while
+pdf = CombinePDF.load "../../test pdfs/outlines/named_dest.pdf";nil
+pdf << CombinePDF.load('../../test pdfs/outlines/named_dest.pdf'); nil
 pdf.save '05_1_timeless_check_named_dest_links.pdf' # never ends... :-(
 
-pdf = CombinePDF.load './Ruby/test pdfs/outline_small.pdf'
-pdf << CombinePDF.load('./Ruby/test pdfs/outline_small.pdf')
+pdf = CombinePDF.load '../../test pdfs/outline_small.pdf'
+pdf << CombinePDF.load('../../test pdfs/outline_small.pdf')
 pdf.save '06_check_links_to_second_copy.pdf'
 
-lists = %w(./Ruby/test\ pdfs/outlines/self_merge_err.pdf ./Ruby/test\ pdfs/outlines/big_toc.pdf ./Ruby/test\ pdfs/outlines/bigger_toc.pdf ./Ruby/test\ pdfs/outlines/named_dest_no_toc.pdf ./Ruby/test\ pdfs/outlines/named_dest_no_toc2.pdf ./Ruby/test\ pdfs/outlines/named_dest.pdf ./Ruby/test\ pdfs/outlines/named_dest2.pdf)
+lists = %w(../../test\ pdfs/outlines/self_merge_err.pdf ../../test\ pdfs/outlines/big_toc.pdf ../../test\ pdfs/outlines/bigger_toc.pdf ../../test\ pdfs/outlines/named_dest_no_toc.pdf ../../test\ pdfs/outlines/named_dest_no_toc2.pdf ../../test\ pdfs/outlines/named_dest.pdf ../../test\ pdfs/outlines/named_dest2.pdf)
 
 i = 0
 lists.each do |n|
@@ -92,19 +92,19 @@ pdf.number_pages(start_at: 1,
 
 pdf.save('07_named destinations_numbered.pdf')
 
-CombinePDF.load("./Ruby/test\ pdfs/Scribus-unknown_err.pdf").save '08_1-unknown-err-empty-str.pdf'
-CombinePDF.load("./Ruby/test\ pdfs/Scribus-unknown_err2.pdf").save '08_2-unknown-err-empty-str.pdf'
-CombinePDF.load("./Ruby/test\ pdfs/Scribus-unknown_err3.pdf").save '08_3-unknown-err-empty-str.pdf'
-CombinePDF.load("./Ruby/test\ pdfs/xref_in_middle.pdf").save '08_4-xref-in-middle.pdf'
-CombinePDF.load("./Ruby/test\ pdfs/xref_split.pdf").save '08_5-xref-fragmented.pdf'
+CombinePDF.load("../../test\ pdfs/Scribus-unknown_err.pdf").save '08_1-unknown-err-empty-str.pdf'
+CombinePDF.load("../../test\ pdfs/Scribus-unknown_err2.pdf").save '08_2-unknown-err-empty-str.pdf'
+CombinePDF.load("../../test\ pdfs/Scribus-unknown_err3.pdf").save '08_3-unknown-err-empty-str.pdf'
+CombinePDF.load("../../test\ pdfs/xref_in_middle.pdf").save '08_4-xref-in-middle.pdf'
+CombinePDF.load("../../test\ pdfs/xref_split.pdf").save '08_5-xref-fragmented.pdf'
 
-CombinePDF.load("/Users/2Be/Ruby/test\ pdfs/nil_object.pdf").save('09_nil_in_parsed_array.pdf')
+CombinePDF.load("../../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 = [ "../../test\ pdfs/pdf-reader/encrypted_version4_revision4_128bit_aes_user_pass_apples_enc_metadata.pdf",
+              "../../test\ pdfs/AESv2\ encrypted.pdf",
+              "../../test\ pdfs/pdf-reader/encrypted_version2_revision3_128bit_rc4_blank_user_pass.pdf",
+              "../../test\ pdfs/AES\ enc.pdf",
+              "../../test\ pdfs/RC4\ enc.pdf"]
 
 encrypted.length.times do |i|
   fname = File.basename encrypted[i]
@@ -132,17 +132,17 @@ 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",
-#   "./Ruby/test\ pdfs/file_name.pdf",
-#   "./Ruby/test\ pdfs/garbage_after_eof.pdf",
-#   "./Ruby/test\ pdfs/Many\ comments.pdf",
-#   "./Ruby/test\ pdfs/nested\ contents\ array.PDF",
-#   "./Ruby/test\ pdfs/nested_resources.pdf",
-#   "./Ruby/test\ pdfs/original-missing-endobje.pdf",
-#   "./Ruby/test\ pdfs/original-multi-issue.pdf",
-#   "./Ruby/test\ pdfs/page_stap_nil_secure.pdf",
-#   "./Ruby/test\ pdfs/referenced\ decryption.pdf",
+#   "../../test\ pdfs/AESv2\ encrypted.pdf",
+#   "../../test\ pdfs/data-in-comment.pdf",
+#   "../../test\ pdfs/file_name.pdf",
+#   "../../test\ pdfs/garbage_after_eof.pdf",
+#   "../../test\ pdfs/Many\ comments.pdf",
+#   "../../test\ pdfs/nested\ contents\ array.PDF",
+#   "../../test\ pdfs/nested_resources.pdf",
+#   "../../test\ pdfs/original-missing-endobje.pdf",
+#   "../../test\ pdfs/original-multi-issue.pdf",
+#   "../../test\ pdfs/page_stap_nil_secure.pdf",
+#   "../../test\ pdfs/referenced\ decryption.pdf",
 #   '',
 #   '',
 #   '',

data/test/combine_pdf/load_test.rb

@@ -0,0 +1,48 @@
+require 'bundler/setup'
+require 'minitest/autorun'
+require 'minitest/around/spec'
+require 'combine_pdf'
+
+describe 'CombinePDF.load' do
+  let(:options) { {} }
+
+  subject { CombinePDF.load "test/fixtures/files/#{file}", options }
+
+  describe 'raise_on_encrypted option' do
+    let(:file) { 'sample_encrypted_pdf.pdf' }
+    let(:options) { { raise_on_encrypted: raise_on_encrypted } }
+
+    describe 'when raise_on_encrypted: true' do
+      let(:raise_on_encrypted) { true }
+
+      describe 'with encrypted file' do
+        it('raises an CombinePDF::EncryptionError') do
+          error = assert_raises(CombinePDF::EncryptionError) { subject }
+          assert_match 'the file is encrypted', error.message
+        end
+      end
+
+      describe 'with unencrypted file' do
+        let(:file) { 'sample_pdf.pdf' }
+
+        it('has a PDF') { assert_instance_of CombinePDF::PDF, subject }
+      end
+    end
+
+    describe 'when raise_on_encrypted: false' do
+      let(:raise_on_encrypted) { false }
+
+      describe 'with encrypted file' do
+        it('does not raise an CombinePDF::EncryptionError') do
+          assert_instance_of CombinePDF::PDF, subject
+        end
+      end
+
+      describe 'with unencrypted file' do
+        let(:file) { 'sample_pdf.pdf' }
+
+        it('has a PDF') { assert_instance_of CombinePDF::PDF, subject }
+      end
+    end
+  end
+end

data/test/combine_pdf/renderer_test.rb

@@ -1,6 +1,4 @@
-require 'bundler/setup'
 require 'minitest/autorun'
-require 'combine_pdf/renderer'
 
 class CombinePDFRendererTest < Minitest::Test
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 1.0.21
+  version: 1.0.23
 platform: ruby
 authors:
 - Boaz Segev
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-12-12 00:00:00.000000000 Z
+date: 2023-04-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
@@ -24,6 +24,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 0.1.5
+- !ruby/object:Gem::Dependency
+  name: matrix
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -52,6 +66,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: minitest-around
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: A nifty gem, in pure Ruby, to parse PDF files and combine (merge) them
   with other PDF files, number the pages, watermark them or stamp them, create tables,
   add basic text objects etc` (all using the PDF file format).
@@ -62,6 +90,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
+- ".travis.yml"
 - CHANGELOG.md
 - Gemfile
 - LICENSE.txt
@@ -82,14 +111,17 @@ files:
 - lib/combine_pdf/renderer.rb
 - lib/combine_pdf/version.rb
 - test/automated
+- test/combine_pdf/load_test.rb
 - test/combine_pdf/renderer_test.rb
 - test/console
+- test/fixtures/files/sample_encrypted_pdf.pdf
+- test/fixtures/files/sample_pdf.pdf
 - test/named_dest
 homepage: https://github.com/boazsegev/combine_pdf
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -104,12 +136,15 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.2
-signing_key: 
+rubygems_version: 3.3.26
+signing_key:
 specification_version: 4
 summary: Combine, stamp and watermark PDF files in pure Ruby.
 test_files:
 - test/automated
+- test/combine_pdf/load_test.rb
 - test/combine_pdf/renderer_test.rb
 - test/console
+- test/fixtures/files/sample_encrypted_pdf.pdf
+- test/fixtures/files/sample_pdf.pdf
 - test/named_dest