tmx_importer 1.1.0 → 1.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/tmx_importer/version.rb +1 -1
- data/lib/tmx_importer.rb +4 -3
- data/spec/tmx_importer_spec.rb +1 -0
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 3257bc81284bce15ebf42b0e8505f25314473bcc
|
4
|
+
data.tar.gz: 930e6d4e5e16d72f6c46d6d29a0170a37049c460
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 4d3b0951312776fb1046bbbf8fb029b7d4829b9bcac0d4904909eb286d26327de136afa9c623692f0a6468e774628ede5bdd12d1399c1f4139d0a164830dfd18
|
7
|
+
data.tar.gz: 521f1f035a34c5e0c0785901c08b5720b0729ba85104bbedc6ec57676981070ed971935a4b832a8105138de628473fb8f76f0c32895f1c0c2ae13ca6d3a52afe
|
data/lib/tmx_importer/version.rb
CHANGED
data/lib/tmx_importer.rb
CHANGED
@@ -9,8 +9,9 @@ module TmxImporter
|
|
9
9
|
attr_reader :file_path, :encoding
|
10
10
|
def initialize(file_path:, **args)
|
11
11
|
@file_path = file_path
|
12
|
+
@content = File.read(open(@file_path)) if !args[:encoding].eql?('UTF-8')
|
12
13
|
if args[:encoding].nil?
|
13
|
-
@encoding = CharlockHolmes::EncodingDetector.detect(
|
14
|
+
@encoding = CharlockHolmes::EncodingDetector.detect(@content[0..100_000])[:encoding]
|
14
15
|
else
|
15
16
|
@encoding = args[:encoding].upcase
|
16
17
|
end
|
@@ -22,7 +23,7 @@ module TmxImporter
|
|
22
23
|
}
|
23
24
|
raise "Encoding type could not be determined. Please set an encoding of UTF-8, UTF-16LE, or UTF-16BE" if @encoding.nil?
|
24
25
|
raise "Encoding type not supported. Please choose an encoding of UTF-8, UTF-16LE, or UTF-16BE" unless @encoding.eql?('UTF-8') || @encoding.eql?('UTF-16LE') || @encoding.eql?('UTF-16BE')
|
25
|
-
@text = CharlockHolmes::Converter.convert(
|
26
|
+
@text = CharlockHolmes::Converter.convert(@content, @encoding, 'UTF-8') if !@encoding.eql?('UTF-8')
|
26
27
|
end
|
27
28
|
|
28
29
|
def stats
|
@@ -58,7 +59,7 @@ module TmxImporter
|
|
58
59
|
if encoding.eql?('UTF-8')
|
59
60
|
XML::Reader.io(open(file_path), options: XML::Parser::Options::NOERROR, encoding: XML::Encoding::UTF_8)
|
60
61
|
else
|
61
|
-
reader = @text.gsub
|
62
|
+
reader = @text.gsub(/(?<=encoding=").*(?=")/, 'utf-8').gsub(/&#x[0-1]?[0-9a-fA-F];/, ' ').gsub(/[\0-\x1f\x7f\u2028]/, ' ')
|
62
63
|
XML::Reader.string(reader, options: XML::Parser::Options::NOERROR, encoding: XML::Encoding::UTF_8)
|
63
64
|
end
|
64
65
|
end
|
data/spec/tmx_importer_spec.rb
CHANGED