hexapdf 0.17.0 → 0.17.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 49952c8667073a4bf4c1508684fa03cbffacab9d54b2821f4d69aa83bb8332ec
-  data.tar.gz: db57322db66eb9c35b618fdf23e70119943874c8f4dab9a5fb01d965a90e91bf
+  metadata.gz: dd14e53954c77d18ef283523c31784467530575521b283cac8dd2ab377789f3f
+  data.tar.gz: e874c630dfcd1e9bdb29278ddb1ce7c80b8a5d7bbde9e739ebe4ab07ff9e9919
 SHA512:
-  metadata.gz: cdb87d3a9f26165bfa2a901d4b91fc720e24b4b5839ace8163d18c74f6cab145ac2ab9095dcad8bb30515f8e1a1437eb2d6b3e86609259f059f6c909d24b87ff
-  data.tar.gz: c087e748a9750156bb6ab3fcf3dfe98b11b4daff9161e290d9acb1cb0953494e0778ec4b81486bda680a11eeb21c321e8c2029266716efce9906d9da2cef2d87
+  metadata.gz: ad7641bf6bee9469f6753efb95580f461faacfc1a18d03bf2e787e4bb67779a1bc61f6b31a8f0a878b4a104d889c905a65999229f1a77ef74d9d9c4b4e508112
+  data.tar.gz: 23bb0bcbbf234df4861dbd235d3b3cc47f6f1bc3c6173271d62d2fb6380955f667c48b995a84e677a448b2bf2b3657e585afa66179210023520ccce654e84365

data/lib/hexapdf/configuration.rb

@@ -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.
@@ -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' => {

data/lib/hexapdf/dictionary_fields.rb

@@ -233,11 +233,16 @@ module HexaPDF
 
       # Converts the string into UTF-8 encoding, assuming it is a binary string. Otherwise +nil+ is
       # returned.
-      def self.convert(str, _type, _document)
+      def self.convert(str, _type, document)
         return unless str.kind_of?(String) && str.encoding == Encoding::BINARY
 
         if str.getbyte(0) == 254 && str.getbyte(1) == 255
-          str[2..-1].force_encoding(Encoding::UTF_16BE).encode(Encoding::UTF_8)
+          str = str[2..-1].force_encoding(Encoding::UTF_16BE)
+          if str.valid_encoding?
+            str.encode!(Encoding::UTF_8)
+          else
+            document.configuration['document.on_invalid_string'].call(str)
+          end
         else
           Utils::PDFDocEncoding.convert_to_utf8(str)
         end

data/lib/hexapdf/version.rb

@@ -37,6 +37,6 @@
 module HexaPDF
 
   # The version of HexaPDF.
-  VERSION = '0.17.0'
+  VERSION = '0.17.1'
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: hexapdf
 version: !ruby/object:Gem::Version
-  version: 0.17.0
+  version: 0.17.1
 platform: ruby
 authors:
 - Thomas Leitner
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-10-21 00:00:00.000000000 Z
+date: 2021-10-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cmdparse