pdfinfo 1.0.0 → 1.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c353a570a0806dfe590c8f5f2f13397a065030b0
-  data.tar.gz: 9e09d7118c9006868b586ddce96738ea88a51af1
+  metadata.gz: 8de9b34e6b07e216baf33dd87f483e41edf284c1
+  data.tar.gz: 20f286868afbde83b138c3a780d626f7b15e2c8b
 SHA512:
-  metadata.gz: 777a7cd47cea0d6ebc9d077d5dd3c32f7e89e28de7d11b321d686b1491a04d5c47e5488c14816dd631513d979cb429076c1cb99506a2e356352e6922af5e3ff2
-  data.tar.gz: 13b389f1cdbf9fafab32c811b80faefc7003315e3cb13f5faeb2463decc1bcd4350faf80647afbc2c31698a361d53d73f0d865aca4d0c14d776998586124692d
+  metadata.gz: 1649532afbe24edf37248f94afe1c57724f0ac4f4a1aa187cff31bb4ce73b7d2ffea93f1360e4c1112fca35b328d445f1e6ac4017c6310bc3b1acb92d22cf08d
+  data.tar.gz: 3d667764447ec721ac6444b83fd4632340a0201f72b5f2dde5441520f4e77753cd5fcc2327f6ab6f6ff81699eb453cec2c083a3e07189ba4fcb99ac0104e2516

data/README.md

@@ -1,11 +1,12 @@
 # Pdfinfo
 
-Simple ruby wrapper around the pdfinfo command
-NOTE: This gem is only intended to provide quick access to the metadata returned by the pdfinfo command without flags
+Simple ruby wrapper around the pdfinfo command.
+This gem was written and tested around xpdf version 3.04. 
+
 
 ## Depdendecies
 
-usage of this gem assumes that you have xpdf installed.  The fastest way to install xpdf:
+usage of this gem assumes that you have xpdf installed (which gives us access to the pdfinfo command).  The fastest way to install xpdf:
 
     $ brew install xpdf
     
@@ -13,7 +14,7 @@ usage of this gem assumes that you have xpdf installed.  The fastest way to inst
 
 Add this line to your application's Gemfile:
 
-    gem 'pdfinfo'
+    gem 'pdfinfo', '~> 1.0.0'
 
 And then execute:
 
@@ -27,6 +28,8 @@ Or install it yourself as:
 
 
 ```ruby
+pdfinfo = Pdfinfo.new("path/to/file.pdf")
+
 pdfinfo.title         #=> "Title" # or nil
 pdfinfo.subject       #=> "Subject" # or nil
 pdfinfo.keywords      #=> ["Keyword1", "Keyword2"] # or nil

data/lib/pdfinfo.rb

@@ -1,4 +1,5 @@
 require 'open3'
+require 'shellwords'
 
 class Pdfinfo
   DIMENSIONS_REGEXP = /([\d\.]+) x ([\d\.]+)/
@@ -20,14 +21,13 @@ class Pdfinfo
 
   def self.exec(file_path, opts = {})
     flags = []
-    if opts[:owner_password]
-      flags << ['-opw', opts[:owner_password]]
-    elsif opts[:user_password]
-      flags << ['-upw', opts[:user_password]]
-    end
+    flags.concat(['-enc', opts.fetch(:encoding, 'UTF-8')])
+    flags.concat(['-opw', opts[:owner_password]]) if opts[:owner_password]
+    flags.concat(['-upw', opts[:user_password]]) if opts[:user_password]
 
-    stdout, stderr, status = Open3.capture2e("#{pdfinfo_command} #{flags.join(" ")} #{file_path}")
-    stdout.chomp
+    command = Shellwords.join([pdfinfo_command, *flags, file_path])
+    stdout, status = Open3.capture2(command)
+    stdout.encode('UTF-8', invalid: :replace, replace: '')
   end
 
   def self.pdfinfo_command
@@ -41,17 +41,20 @@ class Pdfinfo
   def initialize(source_path, opts = {})
     info_hash = parse_shell_response(Pdfinfo.exec(source_path, opts))
 
-    @title          = info_hash['Title'].empty? ? nil : info_hash['Title']
-    @subject        = info_hash['Subject'].empty? ? nil : info_hash['Subject']
-    @keywords       = info_hash['Keywords'].empty? ? [] : info_hash['Keywords'].split(/\s/)
-    @author         = info_hash['Author'].empty? ? nil : info_hash['Author']
-    @creator        = info_hash['Creator'].empty? ? nil : info_hash['Creator']
-    @producer       = info_hash['Producer'].empty? ? nil : info_hash['Producer']
-    @creation_date  = info_hash['CreationDate'].empty? ? nil : Time.parse(info_hash['CreationDate'])
+    @title          = presence(info_hash['Title'])
+    @subject        = presence(info_hash['Subject'])
+    @author         = presence(info_hash['Author'])
+    @creator        = presence(info_hash['Creator'])
+    @producer       = presence(info_hash['Producer'])
     @tagged         = !!(info_hash['Tagged'] =~ /yes/)
-    @form           = info_hash['Form']
-    @page_count     = info_hash['Pages'].to_i
     @encrypted      = !!(info_hash['Encrypted'] =~ /yes/)
+    @page_count     = info_hash['Pages'].to_i
+    @file_size      = info_hash['File size'].to_i
+    @form           = info_hash['Form']
+    @pdf_version    = info_hash['PDF version']
+
+    @keywords       = (info_hash['Keywords'] || "").split(/\s/)
+    @creation_date  = presence(info_hash['CreationDate']) ? Time.parse(info_hash['CreationDate']) : nil
 
     raw_usage_rights = Hash[info_hash['Encrypted'].scan(/(\w+):(\w+)/)]
     booleanize_usage_right = lambda {|val| !(raw_usage_rights[val] == 'no') }
@@ -64,8 +67,6 @@ class Pdfinfo
     end
 
     @width, @height = extract_page_dimensions(info_hash['Page size'])
-    @file_size      = info_hash['File size'].to_i
-    @pdf_version    = info_hash['PDF version']
   end
 
   def tagged?
@@ -94,6 +95,9 @@ class Pdfinfo
   end
 
   private
+  def presence(val)
+    (val.nil? || val.empty?) ? nil : val
+  end
   def parse_shell_response(response_str)
     Hash[response_str.split(/\n/).map {|kv| kv.split(/:/, 2).map(&:strip) }]
   end

data/lib/pdfinfo/version.rb

@@ -1,3 +1,3 @@
 class Pdfinfo
-  VERSION = '1.0.0'
+  VERSION = '1.0.3'
 end

data/spec/pdfinfo_spec.rb

@@ -12,13 +12,15 @@ RSpec.describe Pdfinfo do
     response.sub(/(?<=#{key}:)(.+)$/, new_value)
   end
 
-  specify "mock responses match" do
-    expect(`pdfinfo -upw foo #{fixture_path('pdfs/encrypted.pdf')}`.chomp).to eq(encrypted_response)
-    expect(`pdfinfo #{fixture_path('pdfs/test.pdf')}`.chomp).to eq(unencrypted_response)
+  before(:each) do |ex|
+    unless ex.metadata[:skip_mock_response]
+      allow(Open3).to receive(:capture2).and_return([mock_response, nil])
+    end
   end
 
-  before(:each) do
-    allow(Open3).to receive(:capture2e).and_return([mock_response, nil, nil])
+  specify "mock responses match", :skip_mock_response do
+    expect(`pdfinfo -upw foo #{fixture_path('pdfs/encrypted.pdf')}`.chomp).to eq(encrypted_response)
+    expect(`pdfinfo #{fixture_path('pdfs/test.pdf')}`.chomp).to eq(unencrypted_response)
   end
 
   describe '.pdfinfo_command' do
@@ -36,23 +38,30 @@ RSpec.describe Pdfinfo do
   describe '.exec' do
     context 'with no options given' do
       it 'runs the pdfinfo command without flags' do
-        expect(Open3).to receive(:capture2e).with("pdfinfo  path/to/file.pdf")
+        expect(Open3).to receive(:capture2).with("pdfinfo -enc UTF-8 path/to/file.pdf")
         Pdfinfo.new("path/to/file.pdf")
       end
     end
 
     context "passing in :user_password" do
       it 'runs the pdfinfo command passing the user password flag' do
-        expect(Open3).to receive(:capture2e).with("pdfinfo -upw foo path/to/file.pdf")
+        expect(Open3).to receive(:capture2).with("pdfinfo -enc UTF-8 -upw foo path/to/file.pdf")
         Pdfinfo.new("path/to/file.pdf", user_password: 'foo')
       end
     end
     context 'passing in :owner_password' do
       it 'runs the pdfinfo command passing the user password flag' do
-        expect(Open3).to receive(:capture2e).with("pdfinfo -opw bar path/to/file.pdf")
+        expect(Open3).to receive(:capture2).with("pdfinfo -enc UTF-8 -opw bar path/to/file.pdf")
         Pdfinfo.new("path/to/file.pdf", owner_password: 'bar')
       end
     end
+
+    context "when passed a path with spaces" do
+      it 'should escape the file path' do
+        expect(Open3).to receive(:capture2).with("pdfinfo -enc UTF-8 path/to/file\\ with\\ spaces.pdf")
+        Pdfinfo.new("path/to/file with spaces.pdf")
+      end
+    end
   end
 
   describe '#title' do
@@ -75,12 +84,18 @@ RSpec.describe Pdfinfo do
         expect(pdfinfo.subject).to eq('Pdfinfo Subject')
       end
     end
-    context 'when title is not present' do
+    context 'when subject value is not present' do
       let(:mock_response) { modified_response(unencrypted_response, 'Subject', '') }
       it 'returns nil' do
         expect(pdfinfo.subject).to be_nil
       end
     end
+    context 'when subject key is not present' do
+      let(:mock_response) { unencrypted_response.sub(/^Subject.*\n/, '') }
+      it 'returns nil' do
+        expect(pdfinfo.subject).to be_nil
+      end
+    end
   end
 
   describe '#keywords' do
@@ -89,12 +104,18 @@ RSpec.describe Pdfinfo do
         expect(pdfinfo.keywords).to eq(['Keyword1', 'Keyword2'])
       end
     end
-    context 'when keywords is not present' do
+    context 'when keywords value is not present' do
       let(:mock_response) { modified_response(unencrypted_response, 'Keywords', '') }
       it 'returns an empty array' do
         expect(pdfinfo.keywords).to eq([])
       end
     end
+    context 'when keywords key is not present' do
+      let(:mock_response) { unencrypted_response.sub(/^Keywords.*\n/, '') }
+      it 'returns an empty array' do
+        expect(pdfinfo.keywords).to eq([])
+      end
+    end
   end
 
   describe '#author' do
@@ -120,12 +141,18 @@ RSpec.describe Pdfinfo do
         expect(pdfinfo.creation_date).to eq(Time.parse("2014-10-26 18:23:25 -0700"))
       end
     end
-    context 'when creation date is not present' do
+    context 'when creation date value is not present' do
       let(:mock_response) { modified_response(unencrypted_response, 'CreationDate', '') }
       it 'returns nil' do
         expect(pdfinfo.creation_date).to be_nil
       end
     end
+    context 'when creation date key is not present' do
+      let(:mock_response) { unencrypted_response.sub(/^CreationDate.*\n/, '') }
+      it 'returns nil' do
+        expect(pdfinfo.creation_date).to be_nil
+      end
+    end
   end
 
   describe '#creator' do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pdfinfo
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.3
 platform: ruby
 authors:
 - Ryan Venegas