diff options
| author | Jesse Wolfe <jes5199@gmail.com> | 2010-11-22 15:17:51 -0800 |
|---|---|---|
| committer | Matt Robinson <matt@puppetlabs.com> | 2010-12-02 11:14:10 -0800 |
| commit | c908fdb520e0fc203d49e0c14c4c7cbc193ab262 (patch) | |
| tree | 13df704e2f289e38ebc4a228fac033a9b089011b | |
| parent | 616986da3751012cf526ad75fd250abc93e6c52a (diff) | |
| download | puppet-c908fdb520e0fc203d49e0c14c4c7cbc193ab262.tar.gz puppet-c908fdb520e0fc203d49e0c14c4c7cbc193ab262.tar.xz puppet-c908fdb520e0fc203d49e0c14c4c7cbc193ab262.zip | |
(#5261) Fix #5261 Don't escape Unicode characters in PSON
This patch removes the escaping of valid UTF-8 sequences as "\uXXXX".
This code was unreliable, as it relied on Iconv's ability to convert
those codepoints between UTF-8 and UTF-16, but some versions of Iconv
barf on some valid codepoints.
Invalid UTF-8 sequences are still passed through unchanged. We believe
that this is fine; if you are concerned about complience with the JSON
standard, what we are doing is equivalent to:
* interpreting binary files as Latin-1 encoded character sequences
* JSON-encoding those characters according to RFC 4627
* outputting the JSON as Latin-1
This allows all raw binary files to be transmitted losslessly.
Paired-With: Paul Berry <paul@puppetlabs.com>
| -rw-r--r-- | lib/puppet/external/pson/pure/generator.rb | 23 | ||||
| -rwxr-xr-x | spec/unit/util/pson_spec.rb | 15 |
2 files changed, 16 insertions, 22 deletions
diff --git a/lib/puppet/external/pson/pure/generator.rb b/lib/puppet/external/pson/pure/generator.rb index 4180be57d..89a0c62e0 100644 --- a/lib/puppet/external/pson/pure/generator.rb +++ b/lib/puppet/external/pson/pure/generator.rb @@ -44,34 +44,13 @@ module PSON string << '' # XXX workaround: avoid buffer sharing string.force_encoding(Encoding::ASCII_8BIT) string.gsub!(/["\\\x0-\x1f]/) { MAP[$MATCH] } - string.gsub!(/( - (?: - [\xc2-\xdf][\x80-\xbf] | - [\xe0-\xef][\x80-\xbf]{2} | - [\xf0-\xf4][\x80-\xbf]{3} - )+ | - [\x80-\xc1\xf5-\xff] # invalid - )/nx) { |c| - c.size == 1 and raise GeneratorError, "invalid utf8 byte: '#{c}'" - s = PSON::UTF8toUTF16.iconv(c).unpack('H*')[0] - s.gsub!(/.{4}/n, '\\\\u\&') - } - string.force_encoding(Encoding::UTF_8) string rescue Iconv::Failure => e raise GeneratorError, "Caught #{e.class}: #{e}" end else def utf8_to_pson(string) # :nodoc: - string. - gsub(/["\\\x0-\x1f]/n) { MAP[$MATCH] }. - gsub(/((?: - [\xc2-\xdf][\x80-\xbf] | - [\xe0-\xef][\x80-\xbf]{2} | - [\xf0-\xf4][\x80-\xbf]{3} - )+)/nx) { |c| - PSON::UTF8toUTF16.iconv(c).unpack('H*')[0].gsub(/.{4}/n, '\\\\u\&') - } + string.gsub(/["\\\x0-\x1f]/n) { MAP[$MATCH] } end end module_function :utf8_to_pson diff --git a/spec/unit/util/pson_spec.rb b/spec/unit/util/pson_spec.rb index d02d28517..474ddafa4 100755 --- a/spec/unit/util/pson_spec.rb +++ b/spec/unit/util/pson_spec.rb @@ -35,4 +35,19 @@ describe Puppet::Util::Pson do bin_string = (1..20000).collect { |i| ((17*i+13*i*i) % 255).chr }.join PSON.parse(%Q{{ "type": "foo", "data": #{bin_string.to_pson} }})["data"].should == bin_string end + + it "should be able to handle UTF8 that isn't a real unicode character" do + s = ["\355\274\267"] + PSON.parse( [s].to_pson ).should == [s] + end + + it "should be able to handle UTF8 for \\xFF" do + s = ["\xc3\xbf"] + PSON.parse( [s].to_pson ).should == [s] + end + + it "should be able to handle invalid UTF8 bytes" do + s = ["\xc3\xc3"] + PSON.parse( [s].to_pson ).should == [s] + end end |
