combine_pdf 1.0.22 → 1.0.24

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 96825d0aa74bd673883c4d7dbf3884459ff27c2a3d7bd0c60875e0499c7b9aeb
-  data.tar.gz: 985c39883f343bb5182344ccc31353103fbac89494000362973f08cdd379d2ac
+  metadata.gz: e4c508088d852d177d9e360d9c9b2327d4964e3126ceb61c8e652788bf0e2ffb
+  data.tar.gz: 0451512bbe0f7b61bbb2154fda45542e088bc1cee4bb905654ffde17cc196243
 SHA512:
-  metadata.gz: 8575b612e1eb31775833faba8f310d84680d6ce27512d6a9c182e7598a743956da34e0321f0280d032e3e46b861dd2abdd88b297e65a652ec8e3e416ed9fb0a0
-  data.tar.gz: 2026d924120f1798681842fee7a2eb0de78be6ac493dcbd4ffbb934c1c0135161ccbf29283fb0eec42b4ebab66f84b7fa3ac354a970fad9bc0ad302f64da7c7a
+  metadata.gz: f1eb1830a1cca67729c8b4161df3aabcd23b5cd993d9392051aeb6f93b5ac129dbd4e37c37ff3513cc426fa4bbca6682c9954f18f51f090f9b47da775ce0847f
+  data.tar.gz: ef9a12eb9eb0314973a3e76b6d69cb01bf2c0ee9d05e876824e88b657a771b00839a147d7d98e77f18a1d5f81196c92528958d2ac6b18f3b6cc9423d47d35c53

data/.github/workflows/main.yml

@@ -0,0 +1,28 @@
+name: Main
+on:
+  push:
+
+jobs:
+  tests:
+    name: Tests
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        ruby: ["2.7", "3.0", "3.1", "3.2"]
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Setup Ruby
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: ${{ matrix.ruby }}
+          bundler-cache: true
+
+      - name: Generate lockfile
+        run: bundle lock
+
+      - name: Run tests
+        run: bundle exec rake test

data/.travis.yml

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

data/CHANGELOG.md

@@ -1,6 +1,14 @@
 # Change Log
 
-***
+#### Change log v.1.0.24 (2023-10-19)
+
+**Fix**: possible `nil` in loop. Credit to @jkowens for PR #231 and adding a quick fix using a simple guard.
+
+**Fix**: preserve file creation date metadata where relevant.
+
+#### Change log v.1.0.23 (2023-04-04)
+
+**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
 

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

@@ -7,7 +7,7 @@ Gem::Specification.new do |spec|
   spec.name          = "combine_pdf"
   spec.version       = CombinePDF::VERSION
   spec.authors       = ["Boaz Segev"]
-  spec.email         = ["boaz@2be.co.il"]
+  spec.email         = ["bo@bowild.com"]
   spec.summary       = %q{Combine, stamp and watermark PDF files in pure Ruby.}
   spec.description   = %q{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).}
   spec.homepage      = "https://github.com/boazsegev/combine_pdf"
@@ -24,4 +24,5 @@ Gem::Specification.new do |spec|
   # 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
@@ -321,8 +323,8 @@ module CombinePDF
                 str << 12
               when 48..57 # octal notation for byte?
                 rep -= 48
-                rep = (rep << 3) + (str_bytes.shift-48) if str_bytes[0].between?(48, 57)
-                rep = (rep << 3) + (str_bytes.shift-48) if str_bytes[0].between?(48, 57) && (((rep << 3) + (str_bytes[0] - 48)) <= 255)
+                rep = (rep << 3) + (str_bytes.shift-48) if str_bytes[0]&.between?(48, 57)
+                rep = (rep << 3) + (str_bytes.shift-48) if str_bytes[0]&.between?(48, 57) && (((rep << 3) + (str_bytes[0] - 48)) <= 255)
                 str << rep
               when 10 # new line, ignore
                 str_bytes.shift if str_bytes[0] == 13

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
@@ -174,8 +175,12 @@ module CombinePDF
     def to_pdf(options = {})
       # reset version if not specified
       @version = 1.5 if @version.to_f == 0.0
+
       # set info for merged file
-      @info[:ModDate] = @info[:CreationDate] = Time.now.strftime "D:%Y%m%d%H%M%S%:::z'00"
+      unless(@info[:CreationDate].is_a?(String))
+        @info[:CreationDate] = Time.now unless @info[:CreationDate].is_a?(Time)
+        @info[:CreationDate] = @info[:CreationDate].getgm.strftime("D:%Y%m%d%H%M%S%:::z'00")
+      end
       @info[:Subject] = options[:subject] if options[:subject]
       @info[:Producer] = options[:producer] if options[:producer]
       # rebuild_catalog
@@ -261,10 +266,12 @@ module CombinePDF
         next if !r
         r = r[:referenced_object] if r[:referenced_object]
         r = r[:Font]
-        next if !r        
+        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

data/lib/combine_pdf/version.rb

@@ -1,3 +1,3 @@
 module CombinePDF
-  VERSION = '1.0.22'.freeze
+  VERSION = '1.0.24'.freeze
 end

data/test/automated

@@ -3,9 +3,10 @@
 $VERBOSE = true
 
 require 'benchmark'
-$LOAD_PATH.unshift File.expand_path(File.join('..', '..', 'lib'), __FILE__)
+Dir.chdir File.expand_path(File.join('..', '..', 'lib'), __FILE__)
+$LOAD_PATH.unshift Dir.pwd
 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 +15,54 @@ 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 +93,19 @@ 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 +133,17 @@ 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: 1.0.22
+  version: 1.0.24
 platform: ruby
 authors:
 - Boaz Segev
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-11-27 00:00:00.000000000 Z
+date: 2023-10-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
@@ -66,16 +66,32 @@ 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).
 email:
-- boaz@2be.co.il
+- bo@bowild.com
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/workflows/main.yml"
 - ".gitignore"
+- ".travis.yml"
 - CHANGELOG.md
 - Gemfile
 - LICENSE.txt
@@ -96,8 +112,11 @@ 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:
@@ -118,12 +137,15 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.3
+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