hexapdf 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 874a5d2e5a2408ceed91a9bc61df138248fbbcd2
-  data.tar.gz: 894e67110daae93c1479a5ced992a84dabc66cd1
+  metadata.gz: ecec6549dbb8ccc811ea329857ff768bb248d9ca
+  data.tar.gz: 2e04be0ab4a81fc11491314b18ad95411dc2a0cc
 SHA512:
-  metadata.gz: 9d7c18191ea0d64992fc01b05904c3324cc1f32e98fe848bc931970b53f42d9ab6878d4e8c3730a570c607f677dfdaa8a8adebe7ab4c8e279cc13383124dee1b
-  data.tar.gz: 1e080dd694ad58c3256a647a98a9b03c439ae340311b037fad3b1bdbe436ffbed74fec0c00af3df68540ca32aa75336c328a317a74233428dcf16d8920cc8e75
+  metadata.gz: 4a447429d78977fb78336e4f000d4b53d13bb40fd9e27a4d5a02b9a984d6e2fad76dbbe4d8a069236e24d1295b49ec996eb09d416cbe2668018b3331109e4df1
+  data.tar.gz: aba92a4c25811ab09146a3dafb544194c4aa42373098137ffe339061c1b779c5239afd092521cfe683d4bc8b9e11e609e108213e94375894c854278dac98be41

data/CHANGELOG.md

@@ -1,4 +1,36 @@
-## 0.2.0 - unreleased
+## 0.3.0 - 2017-01-25
+
+### Added
+
+* TrueType font subsetting support
+* Image extraction ability to CLI via `hexapdf images` command
+* [HexaPDF::Type::Image#write] for writing an image XObject to an IO stream or
+  file
+* [HexaPDF::Type::Image#info] for getting image properties of an image XObject
+* CLI option `--[no-]force` to force overwriting existing files
+
+### Changed
+
+* Refactor `hexapdf modify` command into three individual commands `modify`,
+  `merge` and `optimize`
+* Rename `hexapdf extract` to `hexapdf files` and the option `--indices` to
+  `--extract`
+* Show PDF trailer by default with `hexapdf inspect`
+* Refactor CLI command classes to use specialized superclass
+  [HexaPDF::CLI::Command]
+* Optimize parsing of PDF files for better performance and memory efficiency
+
+### Fixed
+
+* Writing of hybrid-reference PDF files - they are written as standard PDF files
+  since all current applications should be able to handle PDF 1.5
+* Serialization of self-referential, indirect PDF objects
+* Performance problem for `hexapdf inspect --pages` when inspecting huge files
+* TrueType compound glyph component offset calculation
+* Parsing of TrueType data type 'fixed'
+* Updating a PDF trailer's ID field when it isn't an array
+
+## 0.2.0 - 2016-11-28
 
 ### Added
 

data/CONTRIBUTERS

@@ -1,3 +1,3 @@
   Count Name
 ======= ====
-    647 Thomas Leitner <t_leitner@gmx.at>
+    682 Thomas Leitner <t_leitner@gmx.at>

data/LICENSE

@@ -1,5 +1,5 @@
 HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-Copyright (C) 2016 Thomas Leitner
+Copyright (C) 2014-2017 Thomas Leitner
 
 HexaPDF is free software: you can redistribute it and/or modify it
 under the terms of the GNU Affero General Public License version 3 as

data/Rakefile

@@ -64,7 +64,7 @@ namespace :dev do
     s.require_path = 'lib'
     s.executables = ['hexapdf']
     s.default_executable = 'hexapdf'
-    s.add_dependency('cmdparse', '~> 3.0', '>= 3.0.1')
+    s.add_dependency('cmdparse', '~> 3.0', '>= 3.0.3')
     s.add_development_dependency('kramdown', '~> 1.0', '>= 1.13.0')
 
     s.author = 'Thomas Leitner'

data/VERSION

@@ -1 +1 @@
-0.2.0
+0.3.0

data/lib/hexapdf.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2016 Thomas Leitner
+# Copyright (C) 2014-2017 Thomas Leitner
 #
 # HexaPDF is free software: you can redistribute it and/or modify it
 # under the terms of the GNU Affero General Public License version 3 as

data/lib/hexapdf/cli.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2016 Thomas Leitner
+# Copyright (C) 2014-2017 Thomas Leitner
 #
 # HexaPDF is free software: you can redistribute it and/or modify it
 # under the terms of the GNU Affero General Public License version 3 as
@@ -31,12 +31,14 @@
 # is created or manipulated using HexaPDF.
 #++
 
-require 'io/console'
 require 'cmdparse'
 require 'hexapdf/cli/info'
-require 'hexapdf/cli/extract'
+require 'hexapdf/cli/files'
 require 'hexapdf/cli/inspect'
 require 'hexapdf/cli/modify'
+require 'hexapdf/cli/merge'
+require 'hexapdf/cli/optimize'
+require 'hexapdf/cli/images'
 require 'hexapdf/version'
 require 'hexapdf/document'
 
@@ -50,23 +52,35 @@ module HexaPDF
     def self.run(args = ARGV)
       Application.new.parse(args)
     rescue => e
-      $stderr.puts "An error occurred: #{e.message}"
+      $stderr.puts "Problem encountered: #{e.message}"
       exit(1)
     end
 
     # The CmdParse::CommandParser class that is used for running the CLI application.
     class Application < CmdParse::CommandParser
 
+      # Specifies whether an operation should be forced. For example, if an existing file should be
+      # overwritten.
+      attr_reader :force
+
       def initialize #:nodoc:
         super(handle_exceptions: :no_help)
         main_command.options.program_name = "hexapdf"
         main_command.options.version = HexaPDF::VERSION
         add_command(HexaPDF::CLI::Info.new)
-        add_command(HexaPDF::CLI::Extract.new)
+        add_command(HexaPDF::CLI::Files.new)
+        add_command(HexaPDF::CLI::Images.new)
         add_command(HexaPDF::CLI::Inspect.new)
         add_command(HexaPDF::CLI::Modify.new)
+        add_command(HexaPDF::CLI::Optimize.new)
+        add_command(HexaPDF::CLI::Merge.new)
         add_command(CmdParse::HelpCommand.new)
         add_command(CmdParse::VersionCommand.new)
+
+        @force = false
+        global_options.on("--[no-]force", "Force overwriting existing files. Default: false") do |f|
+          @force = f
+        end
       end
 
       def parse(argv = ARGV) #:nodoc:
@@ -74,53 +88,6 @@ module HexaPDF
         super
       end
 
-      PAGE_NUMBER_SPEC = "([1-9]\\d*|e)".freeze #:nodoc:
-      ROTATE_MAP = {'l' => -90, 'r' => 90, 'd' => 180, 'n' => :none}.freeze #:nodoc:
-
-      # Parses the pages specification string and returns an array of tuples containing a page
-      # number and a rotation value (either -90, 90, 180 or :none).
-      #
-      # The parameter +count+ needs to be the total number of pages in the document.
-      def parse_pages_specification(range, count)
-        range.split(',').each_with_object([]) do |str, arr|
-          case str
-          when /\A#{PAGE_NUMBER_SPEC}(l|r|d|n)?\z/o
-            arr << [($1 == 'e' ? count : str.to_i) - 1, ROTATE_MAP[$2]]
-          when /\A#{PAGE_NUMBER_SPEC}-#{PAGE_NUMBER_SPEC}(?:\/([1-9]\d*))?(l|r|d|n)?\z/
-            start_nr = ($1 == 'e' ? count : $1.to_i) - 1
-            end_nr = ($2 == 'e' ? count : $2.to_i) - 1
-            step = ($3 ? $3.to_i : 1) * (start_nr > end_nr ? -1 : 1)
-            rotation = ROTATE_MAP[$4]
-            start_nr.step(to: end_nr, by: step) {|n| arr << [n, rotation]}
-          else
-            raise OptionParser::InvalidArgument, "invalid page range format: #{str}"
-          end
-        end
-      end
-
-      # Reads a password from the standard input and falls back to the console if needed.
-      #
-      # The optional argument +prompt+ can be used to customize the prompt when reading from the
-      # console.
-      def read_password(prompt = "Password")
-        if $stdin.tty?
-          read_from_console(prompt)
-        else
-          pwd = $stdin.gets
-          pwd = read_from_console(prompt) unless pwd
-          pwd.chomp
-        end
-      end
-
-      private
-
-      # Displays the given prompt, reads from the console without echo and returns the read string.
-      def read_from_console(prompt)
-        IO.console.write("#{prompt}: ")
-        str = IO.console.noecho {|io| io.gets.chomp}
-        puts
-        str
-      end
     end
 
   end

data/lib/hexapdf/cli/command.rb

@@ -0,0 +1,251 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2014-2017 Thomas Leitner
+#
+# HexaPDF is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License version 3 as
+# published by the Free Software Foundation with the addition of the
+# following permission added to Section 15 as permitted in Section 7(a):
+# FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
+# THOMAS LEITNER, THOMAS LEITNER DISCLAIMS THE WARRANTY OF NON
+# INFRINGEMENT OF THIRD PARTY RIGHTS.
+#
+# HexaPDF is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
+# License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with HexaPDF. If not, see <http://www.gnu.org/licenses/>.
+#
+# The interactive user interfaces in modified source and object code
+# versions of HexaPDF must display Appropriate Legal Notices, as required
+# under Section 5 of the GNU Affero General Public License version 3.
+#
+# In accordance with Section 7(b) of the GNU Affero General Public
+# License, a covered work must retain the producer line in every PDF that
+# is created or manipulated using HexaPDF.
+#++
+
+require 'io/console'
+require 'ostruct'
+require 'cmdparse'
+require 'hexapdf/document'
+
+module HexaPDF
+  module CLI
+
+    # Base class for all hexapdf commands. It provides utility methods needed by the individual
+    # commands.
+    class Command < CmdParse::Command
+
+      def initialize(*args, &block) #:nodoc:
+        super
+        @out_options = OpenStruct.new
+        @out_options.compact = true
+        @out_options.compress_pages = false
+        @out_options.object_streams = :preserve
+        @out_options.xref_streams = :preserve
+        @out_options.streams = :preserve
+
+        @out_options.encryption = :preserve
+        @out_options.enc_user_pwd = @out_options.enc_owner_pwd = nil
+        @out_options.enc_key_length = 128
+        @out_options.enc_algorithm = :aes
+        @out_options.enc_force_v4 = false
+        @out_options.enc_permissions = []
+      end
+
+      protected
+
+      # Checks whether the given output file exists and raises an error if it does and
+      # HexaPDF::CLI#force is not set.
+      def maybe_raise_on_existing_file(filename)
+        if !command_parser.force && File.exist?(filename)
+          raise "Output file '#{filename}' already exists, not overwriting. Use --force to " \
+            "force writing"
+        end
+      end
+
+      # Defines the optimization options.
+      #
+      # See: #out_options, #apply_optimization_options
+      def define_optimization_options
+        options.on("--[no-]compact", "Delete unnecessary PDF objects (default: " \
+                   "#{@out_options.compact})") do |c|
+          @out_options.compact = c
+        end
+        options.on("--object-streams MODE", [:generate, :preserve, :delete],
+                   "Handling of object streams (either generate, preserve or delete; " \
+                     "default: #{@out_options.object_streams})") do |os|
+          @out_options.object_streams = os
+        end
+        options.on("--xref-streams MODE", [:generate, :preserve, :delete],
+                   "Handling of cross-reference streams (either generate, preserve or delete; " \
+                     "default: #{@out_options.xref_streams})") do |x|
+          @out_options.xref_streams = x
+        end
+        options.on("--streams MODE", [:compress, :preserve, :uncompress],
+                   "Handling of stream data (either compress, preserve or uncompress; default: " \
+                     "#{@out_options.streams})") do |streams|
+          @out_options.streams = streams
+        end
+        options.on("--[no-]compress-pages", "Recompress page content streams (may take a long " \
+                   "time; default: #{@out_options.compress_pages})") do |c|
+          @out_options.compress_pages = c
+        end
+      end
+
+      # Defines the encryption options.
+      #
+      # See: #out_options, #apply_encryption_options
+      def define_encryption_options
+        options.on("--decrypt", "Remove any encryption") do
+          @out_options.encryption = :remove
+        end
+        options.on("--encrypt", "Encrypt the output file") do
+          @out_options.encryption = :add
+        end
+        options.on("--owner-password PASSWORD", String, "The owner password to be set on the " \
+                   "output file (use - for reading from standard input)") do |pwd|
+          @out_options.encryption = :add
+          @out_options.enc_owner_pwd = (pwd == '-' ? read_password("Owner password") : pwd)
+        end
+        options.on("--user-password PASSWORD", String, "The user password to be set on the " \
+                   "output file (use - for reading from standard input)") do |pwd|
+          @out_options.encryption = :add
+          @out_options.enc_user_pwd = (pwd == '-' ? read_password("User password") : pwd)
+        end
+        options.on("--algorithm ALGORITHM", [:aes, :arc4],
+                   "The encryption algorithm: aes or arc4 (default: " \
+                     "#{@out_options.enc_algorithm})") do |a|
+          @out_options.encryption = :add
+          @out_options.enc_algorithm = a
+        end
+        options.on("--key-length BITS", Integer,
+                   "The encryption key length in bits (default: " \
+                     "#{@out_options.enc_key_length})") do |i|
+          @out_options.encryption = :add
+          @out_options.enc_key_length = i
+        end
+        options.on("--force-V4",
+                   "Force use of encryption version 4 if key length=128 and algorithm=arc4") do
+          @out_options.encryption = :add
+          @out_options.enc_force_v4 = true
+        end
+        syms = HexaPDF::Encryption::StandardSecurityHandler::Permissions::SYMBOL_TO_PERMISSION.keys
+        options.on("--permissions PERMS", Array,
+                   "Comma separated list of permissions to be set on the output file. Possible " \
+                     "values: #{syms.join(', ')}") do |perms|
+          perms.map! do |perm|
+            unless syms.include?(perm.to_sym)
+              raise OptionParser::InvalidArgument, "#{perm} (invalid permission name)"
+            end
+            perm.to_sym
+          end
+          @out_options.encryption = :add
+          @out_options.enc_permissions = perms
+        end
+      end
+
+      # Applies the optimization options to the given HexaPDF::Document instance.
+      #
+      # See: #define_optimization_options
+      def apply_optimization_options(doc)
+        doc.task(:optimize, compact: @out_options.compact,
+                 object_streams: @out_options.object_streams,
+                 xref_streams: @out_options.xref_streams,
+                 compress_pages: @out_options.compress_pages)
+        handle_streams(doc) unless @out_options.streams == :preserve
+      end
+
+      IGNORED_FILTERS = { #:nodoc:
+        CCITTFaxDecode: true, JBIG2Decode: true, DCTDecode: true, JPXDecode: true, Crypt: true
+      }.freeze
+
+      # Applies the chosen stream mode to all streams.
+      def handle_streams(doc)
+        doc.each(current: false) do |obj|
+          next if !obj.respond_to?(:set_filter) || Array(obj[:Filter]).any? {|f| IGNORED_FILTERS[f]}
+          if @out_options.streams == :compress
+            obj.set_filter(:FlateDecode)
+          else
+            obj.set_filter(nil)
+          end
+        end
+      end
+
+      # Applies the encryption related options to the given HexaPDF::Document instance.
+      #
+      # See: #define_encryption_options
+      def apply_encryption_options(doc)
+        if @out_options.encryption == :add
+          doc.encrypt(algorithm: @out_options.enc_algorithm,
+                      key_length: @out_options.enc_key_length,
+                      force_V4: @out_options.enc_force_v4,
+                      permissions: @out_options.enc_permissions,
+                      owner_password: @out_options.enc_owner_pwd,
+                      user_password: @out_options.enc_user_pwd)
+        elsif @out_options.encryption == :remove
+          doc.encrypt(name: nil)
+        end
+      end
+
+      PAGE_NUMBER_SPEC = "([1-9]\\d*|e)".freeze #:nodoc:
+      ROTATE_MAP = {'l' => -90, 'r' => 90, 'd' => 180, 'n' => :none}.freeze #:nodoc:
+
+      # Parses the pages specification string and returns an array of tuples containing a page
+      # number and a rotation value (either -90, 90, 180 or :none).
+      #
+      # The parameter +count+ needs to be the total number of pages in the document.
+      #
+      # For details on the pages specification see the hexapdf(1) manual page.
+      def parse_pages_specification(range, count)
+        range.split(',').each_with_object([]) do |str, arr|
+          case str
+          when /\A#{PAGE_NUMBER_SPEC}(l|r|d|n)?\z/o
+            arr << [($1 == 'e' ? count : str.to_i) - 1, ROTATE_MAP[$2]]
+          when /\A#{PAGE_NUMBER_SPEC}-#{PAGE_NUMBER_SPEC}(?:\/([1-9]\d*))?(l|r|d|n)?\z/
+            start_nr = ($1 == 'e' ? count : $1.to_i) - 1
+            end_nr = ($2 == 'e' ? count : $2.to_i) - 1
+            step = ($3 ? $3.to_i : 1) * (start_nr > end_nr ? -1 : 1)
+            rotation = ROTATE_MAP[$4]
+            start_nr.step(to: end_nr, by: step) {|n| arr << [n, rotation]}
+          else
+            raise OptionParser::InvalidArgument, "invalid page range format: #{str}"
+          end
+        end
+      end
+
+      # Reads a password from the standard input and falls back to the console if needed.
+      #
+      # The optional argument +prompt+ can be used to customize the prompt when reading from the
+      # console.
+      def read_password(prompt = "Password")
+        if $stdin.tty?
+          read_from_console(prompt)
+        else
+          pwd = $stdin.gets
+          pwd = read_from_console(prompt) unless pwd
+          pwd.chomp
+        end
+      end
+
+      private
+
+      # Displays the given prompt, reads from the console without echo and returns the read string.
+      def read_from_console(prompt)
+        IO.console.write("#{prompt}: ")
+        str = IO.console.noecho {|io| io.gets.chomp}
+        puts
+        str
+      end
+
+    end
+
+  end
+end