pdf-forms 1.1.1 → 1.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 7082ff050aa4f56aa3bfede64817eda71a98d5f7
-  data.tar.gz: 54078c07d1d53e29858c56daf19ae3ce446ebcd3
+SHA256:
+  metadata.gz: 6f7ed295a6b7127c97a398655de313fcce3950b3ea32b62b31ecafb72993315e
+  data.tar.gz: 432d25045b4cc7383aa2500cc66da6f7ca058be803965be1fab3dd202be1eff8
 SHA512:
-  metadata.gz: ac501b1ee613c1f21a526bceb24331535eafb017e71d8935cb6a175f29d0123d64ad5b4aa4a5ba5770315e4b00e10dd806946695bbdadc306af0083bb620afe6
-  data.tar.gz: 0d366788a6163b62f6c5e1b9e9d7a27ffc46898efb93067acc5f5b1fee675452395e5ad0671b6218344cd318dbf3a2b428fcb4479c9fb2377e9db5c2030bc261
+  metadata.gz: 439a63e18b1ee43256ca559f6fcd7a34faa9ac2db6ccb807ec91c2378c16bc5db840bb772d6ba59690cd856cb82e98bc814cdade458800dcb6744c3ace4aaaee
+  data.tar.gz: e6e7e593801b25ad4912e8d3eaf647d27f6ca1aad08ca8a170cee702c9d5781a3353f3fcc7af56f9f94c28a8bcb9b98c6320d9452f05e3c5fea17d86bbd51904

data/README.md

@@ -15,6 +15,31 @@ http://www.pdflabs.com/tools/pdftk-server/ and install it, or run
 After that, add `pdf-forms` to your Gemfile or manually install the gem. Nothing
 unusual here.
 
+### Using the Java port of PDFTK
+
+The PDFTK package was dropped from most (all?) current versions of major Linux distributions.
+As contributed in [this issue](https://github.com/jkraemer/pdf-forms/issues/75#issuecomment-698436643), you can use the [Java version of PDFTK](https://gitlab.com/pdftk-java/pdftk)
+with this gem, as well. Just create a small shell script:
+
+~~~shell
+#!/bin/sh
+MYSELF=`which "$0" 2>/dev/null`
+[ $? -gt 0 -a -f "$0" ] && MYSELF="./$0"
+java=java
+if test -n "$JAVA_HOME"; then
+    java="$JAVA_HOME/bin/java"
+fi
+exec "$java" $java_args -jar $MYSELF "$@"
+exit 1
+~~~
+
+Next, concatenate the wrapper script and the Jar file, and you end up with an executable that 
+can be used with pdf-forms:
+
+~~~
+cat stub.sh pdftk-all.jar > pdftk.run && chmod +x pdftk.run
+~~~
+
 
 ## Usage
 
@@ -40,6 +65,9 @@ require 'pdf_forms'
 # add :data_format => 'XFdf' option to generate XFDF instead of FDF when
 # filling a form (XFDF is supposed to have better support for non-western
 # encodings)
+# add :data_format => 'FdfHex' option to generate FDF with values passed in
+# UTF16 hexadecimal format (Hexadecimal format has also proven more reliable
+# for passing latin accented characters to pdftk)
 # add :utf8_fields => true in order to get UTF8 encoded field metadata (this
 # will use dump_data_fields_utf8 instead of dump_data_fields in the call to
 # pdftk)
@@ -51,7 +79,8 @@ pdftk.get_field_names 'path/to/form.pdf'
 # take form.pdf, set the 'foo' field to 'bar' and save the document to myform.pdf
 pdftk.fill_form '/path/to/form.pdf', 'myform.pdf', :foo => 'bar'
 
-# optionally, add the :flatten option to prevent editing of a filled out form
+# optionally, add the :flatten option to prevent editing of a filled out form.
+# Other supported options are :drop_xfa and :drop_xmp.
 pdftk.fill_form '/path/to/form.pdf', 'myform.pdf', {:foo => 'bar'}, :flatten => true
 
 # to enable PDF encryption, pass encrypt: true. By default, a random 'owner
@@ -66,6 +95,21 @@ Any options shown above can also be set when initializing the PdfForms
 instance. In this case, options given to `fill_form` will override the global
 options.
 
+### Field names with HTML entities
+
+In case your form's field names contain HTML entities (like
+`Straße Hausnummer`), make sure you unescape those before using them, i.e.
+`CGI.unescapeHTML(name)`.  Thanks to @phoet for figuring this out in #65.
+
+### Non-ASCII Characters (UTF8 etc) are not displayed in the filled out PDF
+
+First, check if the field value has been stored properly in the output PDF using `pdftk output.pdf dump_data_fields_utf8`.
+
+If it has been stored but is not rendered, your input PDF lacks the proper font for your kind of characters. Re-create it and embed any necessary fonts.
+If the value has not been stored, there is a problem with filling out the form, either on your side, of with this gem.
+
+Also see [UTF-8 chars are not displayed in the filled PDF](https://github.com/jkraemer/pdf-forms/issues/53)
+
 ### Prior Art
 
 The FDF generation part is a straight port of Steffen Schwigon's PDF::FDF::Simple perl module. Didn't port the FDF parsing, though ;-)

data/lib/pdf_forms/fdf.rb

@@ -28,6 +28,7 @@ module PdfForms
       end
     end
 
+    # pp 559 https://www.adobe.com/content/dam/acom/en/devnet/pdf/pdfs/pdf_reference_archives/PDFReference.pdf
     def header
       header = "%FDF-1.2\n\n1 0 obj\n<<\n/FDF << /Fields 2 0 R"
 
@@ -39,13 +40,16 @@ module PdfForms
       header << "/ID[" << options[:id].join << "]" if options[:id]
 
       header << ">>\n>>\nendobj\n2 0 obj\n["
-      return header
+      header
     end
 
+    # pp 561 https://www.adobe.com/content/dam/acom/en/devnet/pdf/pdfs/pdf_reference_archives/PDFReference.pdf
     def field(key, value)
-      "<</T(#{key})/V" +
-        (Array === value ? "[#{value.map{ |v|"(#{quote(v)})" }.join}]" : "(#{quote(value)})") +
-        ">>\n"
+      field = "<<"
+      field << "/T" + "(#{key})"
+      field << "/V" + (Array === value ? "[#{value.map{ |v|"(#{quote(v)})" }.join}]" : "(#{quote(value)})")
+      field << ">>\n"
+      field
     end
 
     def quote(value)

data/lib/pdf_forms/fdf_hex.rb

@@ -0,0 +1,39 @@
+# coding: UTF-8
+
+module PdfForms
+  # Map keys and values to Adobe's FDF format.
+  #
+  # This is a variation of the original Fdf data format, values are encoded in UTF16 hexadesimal
+  # notation to improve compatibility with non ascii charsets.
+  #
+  # Information about hexadesimal FDF values was found here:
+  #
+  # http://stackoverflow.com/questions/6047970/weird-characters-when-filling-pdf-with-pdftk
+  #
+  class FdfHex < Fdf
+    private
+
+    def field(key, value)
+      "<</T(#{key})/V" +
+        (Array === value ? encode_many(value) : encode_value_as_hex(value)) +
+        ">>\n"
+    end
+
+    def encode_many(values)
+      "[#{values.map { |v| encode_value_as_hex(v) }.join}]"
+    end
+
+    def encode_value_as_hex(value)
+      value = value.to_s
+      utf_16 = value.encode('UTF-16BE', :invalid => :replace, :undef => :replace)
+      hex = utf_16.unpack('H*').first
+      hex.force_encoding 'ASCII-8BIT' # jruby
+      '<FEFF' + hex.upcase + '>'
+    end
+
+    # Fdf implementation encodes to ISO-8859-15 which we do not want here.
+    def encode_data(fdf)
+      fdf
+    end
+  end
+end

data/lib/pdf_forms/pdftk_wrapper.rb

@@ -23,6 +23,9 @@ module PdfForms
     #
     # The pdftk binary may also be explecitly specified:
     # PdftkWrapper.new('/usr/bin/pdftk', :flatten => true, :encrypt => true, :encrypt_options => 'allow Printing')
+    #
+    # Besides the options shown above, the drop_xfa or drop_xmp options are
+    # also supported.
     def initialize(*args)
       pdftk, options = normalize_args *args
       @pdftk = Cliver.detect! pdftk
@@ -82,7 +85,7 @@ module PdfForms
     # returns the commands output, check general execution success with
     # $?.success?
     def call_pdftk(*args)
-      SafeShell.execute pdftk, *(args.flatten)
+      SafeShell.execute! pdftk, *(args.flatten)
     end
 
     # concatenate documents, can optionally specify page ranges
@@ -133,11 +136,20 @@ module PdfForms
       local[attrib] || options[attrib]
     end
 
+    ALLOWED_OPTIONS = %i(
+      drop_xmp
+      drop_xfa
+      flatten
+      need_appearances
+    ).freeze
+
     def append_options(args, local_options = {})
       return args if options.empty? && local_options.empty?
       args = args.dup
-      if option_or_global(:flatten, local_options)
-        args << 'flatten'
+      ALLOWED_OPTIONS.each do |option|
+        if option_or_global(option, local_options)
+          args << option.to_s
+        end
       end
       if option_or_global(:encrypt, local_options)
         encrypt_pass = option_or_global(:encrypt_password, local_options)
@@ -160,11 +172,11 @@ module PdfForms
         when String
           pdftk = first_arg
           options = args.shift || {}
-          raise InvalidArgumentError.new("expected hash, got #{options.class.name}") unless Hash === options
+          raise ArgumentError.new("expected hash, got #{options.class.name}") unless Hash === options
         when Hash
           options = first_arg
         else
-          raise InvalidArgumentError.new("expected string or hash, got #{first_arg.class.name}")
+          raise ArgumentError.new("expected string or hash, got #{first_arg.class.name}")
         end
       end
       [pdftk, options]

data/lib/pdf_forms/version.rb

@@ -1,5 +1,5 @@
 # coding: UTF-8
 
 module PdfForms
-  VERSION = '1.1.1'
+  VERSION = '1.4.0'
 end

data/lib/pdf_forms.rb

@@ -5,6 +5,7 @@ require 'pdf_forms/normalize_path'
 require 'pdf_forms/data_format'
 require 'pdf_forms/fdf'
 require 'pdf_forms/xfdf'
+require 'pdf_forms/fdf_hex'
 require 'pdf_forms/pdf'
 require 'pdf_forms/pdftk_wrapper'
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdf-forms
 version: !ruby/object:Gem::Version
-  version: 1.1.1
+  version: 1.4.0
 platform: ruby
 authors:
 - Jens Krämer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-08-30 00:00:00.000000000 Z
+date: 2021-11-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cliver
@@ -50,30 +50,31 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.7'
+        version: '2.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.7'
+        version: '2.1'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '13.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '13.0'
 description: A Ruby frontend to the pdftk binary, including FDF and XFDF creation.
-  Just pass your template and a hash of data to fill in.
+  Also works with the PDFTK Java port. Just pass your template and a hash of data
+  to fill in.
 email:
 - jk@jkraemer.net
 executables: []
@@ -86,6 +87,7 @@ files:
 - lib/pdf_forms.rb
 - lib/pdf_forms/data_format.rb
 - lib/pdf_forms/fdf.rb
+- lib/pdf_forms/fdf_hex.rb
 - lib/pdf_forms/field.rb
 - lib/pdf_forms/normalize_path.rb
 - lib/pdf_forms/pdf.rb
@@ -111,8 +113,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: 1.3.6
 requirements: []
-rubyforge_project: pdf-forms
-rubygems_version: 2.5.1
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: Fill out PDF forms with pdftk (http://www.accesspdf.com/pdftk/).