hexapdf 0.15.8 → 0.17.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4953ab56f7c03c62e4f4e2ef1aa51a8a58f98c3d24725eb86dd6bc13419bd2d2
-  data.tar.gz: c4ac38e280f646eecf512481570ddc8670b48c9ac32601f55b24748f4044344b
+  metadata.gz: dd14e53954c77d18ef283523c31784467530575521b283cac8dd2ab377789f3f
+  data.tar.gz: e874c630dfcd1e9bdb29278ddb1ce7c80b8a5d7bbde9e739ebe4ab07ff9e9919
 SHA512:
-  metadata.gz: 529f8f88d9553f300b842838c1f00e8bed3e05adecfe4478f81d41fcb6431fce888f56b76b2747a65a2935cbb76a6792dce2b1f480dcb120634e1932e461c883
-  data.tar.gz: 9e71874d7901145045fab5791ca09b3ec9cc8f9a9243366b0329cb2570c58408d4595ee37e995a22ce2c099127bc6bdc732e5d3562bde834be2fc57aa3f35b8a
+  metadata.gz: ad7641bf6bee9469f6753efb95580f461faacfc1a18d03bf2e787e4bb67779a1bc61f6b31a8f0a878b4a104d889c905a65999229f1a77ef74d9d9c4b4e508112
+  data.tar.gz: 23bb0bcbbf234df4861dbd235d3b3cc47f6f1bc3c6173271d62d2fb6380955f667c48b995a84e677a448b2bf2b3657e585afa66179210023520ccce654e84365

data/lib/hexapdf/cli/batch.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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/command.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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
@@ -354,6 +354,15 @@ module HexaPDF
         end
       end
 
+      # Returns the human readable file size.
+      def human_readable_file_size(size)
+        case size
+        when 0..9999 then "#{size}B"
+        when 10_000..999_999 then "#{(size / 1024.to_f).round(1)}K"
+        else "#{(size.to_f / 1024 / 1024).round(1)}M"
+        end
+      end
+
       private
 
       # Displays the given prompt, reads from the console without echo and returns the read string.

data/lib/hexapdf/cli/files.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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/fonts.rb

@@ -0,0 +1,145 @@
+# -*- encoding: utf-8; frozen_string_literal: true -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2014-2021 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.
+#
+# If the GNU Affero General Public License doesn't fit your need,
+# commercial licenses are available at <https://gettalong.at/hexapdf/>.
+#++
+
+require 'set'
+require 'hexapdf/cli/command'
+
+module HexaPDF
+  module CLI
+
+    # Lists fonts from a PDF file.
+    #
+    # See: HexaPDF::Type::Font
+    class Fonts < Command
+
+      def initialize #:nodoc:
+        super('fonts', takes_commands: false)
+        short_desc("List fonts from a PDF file")
+        long_desc(<<~EOF)
+          Lists the fonts used in the PDF with additional information, sorted by page number.
+        EOF
+        options.on("--password PASSWORD", "-p", String,
+                   "The password for decryption. Use - for reading from standard input.") do |pwd|
+          @password = (pwd == '-' ? read_password : pwd)
+        end
+        options.on("-i", "--pages PAGES", "The subset of pages that should be looked at") do |pages|
+          @pages = pages
+        end
+
+        @password = nil
+        @pages = nil
+      end
+
+      def execute(pdf) #:nodoc:
+        with_document(pdf, password: @password) do |doc|
+          printf("%5s %-40s %-12s %-10s %-3s %-3s %8s %9s\n",
+                 "page", "name", "type", "encoding", "emb", "sub", "size", "oid")
+          puts("-" * 97)
+          each_font(doc) do |pindex, font|
+            font_type = case font[:Subtype]
+                        when :Type1
+                          if font.embedded? && font[:FontDescriptor][:FontFile3]
+                            "Type 1C"
+                          else
+                            "Type 1"
+                          end
+                        when :Type3 then "Type 3"
+                        when :TrueType then "TrueType"
+                        when :Type0
+                          if font.descendant_font[:Subtype] == :CIDFontType0
+                            "CID CFF"
+                          else
+                            "CID TrueType"
+                          end
+                        else
+                          "Unknown"
+                        end
+            encoding = font[:Encoding]
+            encoding = if encoding.kind_of?(Symbol)
+                         encoding.to_s.sub(/Encoding/, '')
+                       elsif encoding.kind_of?(Dictionary) &&
+                           [:Type1, :Type3, :TrueType].include?(font[:Subtype])
+                         "Custom"
+                       else
+                         "Built-in"
+                       end
+            size = human_readable_file_size(font.embedded? ? font.font_file[:Length] : 0)
+            embedded = (font.embedded? ? "yes" : "no")
+            subset = (font[:BaseFont].match?(/\A[A-Z]{6}\+/) ? "yes" : "no")
+            printf("%5s %-40s %-12s %-10s %-3s %-3s %8s %9s\n",
+                   pindex, font[:BaseFont], font_type, encoding,
+                   embedded, subset, size, "#{font.oid},#{font.gen}")
+          end
+        end
+      end
+
+      private
+
+      # Iterates over all fonts by page.
+      def each_font(doc) # :yields: obj, index, page_index
+        if @pages
+          pages = parse_pages_specification(@pages, doc.pages.count).each_with_object({}) do |(i, _), h|
+            h[i] = true
+          end
+        end
+        seen = {}
+
+        doc.pages.each_with_index do |page, pindex|
+          next if pages && !pages[pindex]
+          font_proc = lambda do |_, font|
+            next if seen[font]
+            yield(pindex + 1, font)
+            seen[font] = true
+          end
+          page.resources[:Font]&.each(&font_proc)
+          page.resources[:XObject]&.each do |_, xobj|
+            next unless xobj[:Subtype] == :Form
+            xobj.ressources[:Font]&.each(&font_proc)
+          end
+          page.each_annotation do |annotation|
+            appearance = annotation.appearance
+            next unless appearance
+            appearance.resources[:Font]&.each(&font_proc)
+          end
+
+          seen.clear if pages
+        end
+      end
+
+    end
+
+  end
+end

data/lib/hexapdf/cli/form.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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
@@ -108,12 +108,10 @@ module HexaPDF
                 fill_form(doc)
               end
             end
-            if @flatten
-              unless doc.acro_form.flatten.empty?
-                $stderr.puts "Warning: Not all form fields could be flattened"
-                doc.catalog.delete(:AcroForm)
-                doc.delete(doc.acro_form)
-              end
+            if @flatten && !doc.acro_form.flatten.empty?
+              $stderr.puts "Warning: Not all form fields could be flattened"
+              doc.catalog.delete(:AcroForm)
+              doc.delete(doc.acro_form)
             end
           else
             list_form_fields(doc)
@@ -146,8 +144,8 @@ module HexaPDF
           if command_parser.verbosity_info?
             if field.field_type == :Ch
               puts "    └─ Options: #{field.option_items.map(&:inspect).join(', ')}"
-            elsif concrete_field_type == :radio_button
-              puts "    └─ Options: #{field.radio_button_values.map(&:inspect).join(', ')}"
+            elsif concrete_field_type == :radio_button || concrete_field_type == :check_box
+              puts "    └─ Options: #{([:Off] + field.allowed_values).map(&:to_s).join(', ')}"
             end
           end
         end
@@ -170,11 +168,13 @@ module HexaPDF
           puts "    └─ Current value: #{field.field_value.inspect}"
 
           if field.field_type == :Ch
-            puts "    └─ Possible values: #{field.option_items.map(&:inspect).join(', ')}"
+            puts "    └─ Possible values: #{field.option_items.map(&:to_s).join(', ')}"
           elsif concrete_field_type == :radio_button
-            puts "    └─ Possible values: #{field.radio_button_values.map(&:inspect).join(', ')}"
+            puts "    └─ Possible values: Off, #{field.allowed_values.map(&:to_s).join(', ')}"
           elsif concrete_field_type == :check_box
-            puts "    └─ Possible values: y(es), t(rue); n(o), f(alse)"
+            av = field.allowed_values
+            puts "    └─ Possible values: n(o), f(alse); #{av.size == 1 ? 'y(es), t(rue); ' : ''}" \
+              "#{av.map(&:to_s).join(', ')}"
           end
 
           begin
@@ -220,21 +220,22 @@ module HexaPDF
       # Applies the given value to the field.
       def apply_field_value(field, value)
         case field.concrete_field_type
-        when :single_line_text_field
-          field.field_value = value
-        when :combo_box, :list_box
-          field.field_value = value
-        when :editable_combo_box
+        when :single_line_text_field, :multiline_text_field, :comb_text_field, :combo_box,
+            :list_box, :editable_combo_box
           field.field_value = value
         when :check_box
-          unless value.match?(/y(es)?|t(rue)?|f(alse)?|n(o)/)
-            raise HexaPDF::Error, "Invalid input, use one of the possible values"
-          end
-          field.field_value = value.match?(/y(es)?|t(rue)?/)
+          field.field_value = case value
+                              when /y(es)?|t(rue)?/
+                                true
+                              when /n(o)?|f(alse)?/
+                                false
+                              else
+                                value
+                              end
         when :radio_button
-          field.field_value = value.intern
+          field.field_value = value.to_sym
         else
-          raise "Field type not yet supported"
+          raise "Field type #{field.concrete_field_type} not yet supported"
         end
       end
 
@@ -244,13 +245,13 @@ module HexaPDF
         seen = {}
 
         doc.pages.each_with_index do |page, page_index|
-          page[:Annots]&.each do |annotation|
+          page.each_annotation do |annotation|
             next unless annotation[:Subtype] == :Widget
             field = annotation.form_field
             next if field.concrete_field_type == :push_button
-            unless seen[field]
+            unless seen[field.full_field_name]
               yield(page, page_index, field, annotation)
-              seen[field] = true
+              seen[field.full_field_name] = true
             end
           end
         end

data/lib/hexapdf/cli/image2pdf.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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/images.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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
@@ -197,15 +197,6 @@ module HexaPDF
         end
       end
 
-      # Returns the human readable file size.
-      def human_readable_file_size(size)
-        case size
-        when 0..9999 then "#{size}B"
-        when 10_000..999_999 then "#{(size / 1024.to_f).round(1)}K"
-        else "#{(size.to_f / 1024 / 1024).round(1)}M"
-        end
-      end
-
     end
 
   end

data/lib/hexapdf/cli/info.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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/inspect.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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/merge.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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/modify.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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/optimize.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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/split.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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/watermark.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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
@@ -47,6 +47,7 @@ require 'hexapdf/cli/split'
 require 'hexapdf/cli/watermark'
 require 'hexapdf/cli/image2pdf'
 require 'hexapdf/cli/form'
+require 'hexapdf/cli/fonts'
 require 'hexapdf/version'
 require 'hexapdf/document'
 
@@ -101,6 +102,7 @@ module HexaPDF
         add_command(HexaPDF::CLI::Watermark.new)
         add_command(HexaPDF::CLI::Image2PDF.new)
         add_command(HexaPDF::CLI::Form.new)
+        add_command(HexaPDF::CLI::Fonts.new)
         add_command(CmdParse::HelpCommand.new)
         version_command = CmdParse::VersionCommand.new(add_switches: false)
         add_command(version_command)

data/lib/hexapdf/composer.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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/configuration.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2020 Thomas Leitner
+# Copyright (C) 2014-2021 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
@@ -203,6 +203,12 @@ module HexaPDF
   #
   #    In nearly all cases this option should not be changed from its default setting!
   #
+  # document.on_invalid_string::
+  #    A callable object that takes the invalid UTF-16BE encoded string and returns a valid UTF-8
+  #    encoded string.
+  #
+  #    The default is to remove all invalid characters.
+  #
   # encryption.aes::
   #    The class that should be used for AES encryption. If the value is a String, it should
   #    contain the name of a constant to such a class.
@@ -245,7 +251,7 @@ module HexaPDF
   #    Defines a mapping from font names and variants to font files.
   #
   #    The value needs to be a hash of the form:
-  #      {"font_name": {variant: file_name, variant2: file_name2, ...}, ...}
+  #      {"font_name" => {variant: file_name, variant2: file_name2, ...}, ...}
   #
   #    Once a font is registered in this way, the font name together with a variant name can be used
   #    with the HexaPDF::Document::Fonts#add method to load the font.
@@ -380,6 +386,9 @@ module HexaPDF
                       end,
                       'acro_form.text_field.default_width' => 100,
                       'document.auto_decrypt' => true,
+                      'document.on_invalid_string' => proc do |str|
+                        str.encode(Encoding::UTF_8, invalid: :replace, replace: '')
+                      end,
                       'encryption.aes' => 'HexaPDF::Encryption::FastAES',
                       'encryption.arc4' => 'HexaPDF::Encryption::FastARC4',
                       'encryption.filter_map' => {