tolq-parsers-xliff 0.1.5 → 0.1.6
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/xliff/parser.rb +44 -13
- data/lib/xliff/unparser.rb +6 -4
- data/lib/xliff/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 31536f271f89a7333c67950065ce2a4347600f0f
|
4
|
+
data.tar.gz: 025b219b7a2232b029f0abcdaa5ec028c9943912
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 9dee89cc6c7de47ba31d6772def5b7af58e0d96c72ac085eff2aef4e029533a945391aef017f1419061a2bd1747d9af8a02115007f5a1f1272d31b37e739b24b
|
7
|
+
data.tar.gz: 19ecc354b22d575eb5cd3012fe45b5303e47202bb14ee45664923dbaec05f0a200a892b11924bcb35555dad1c40cb5501cdd2bd15bcdb30ff435be46147a96a9
|
data/lib/xliff/parser.rb
CHANGED
@@ -1,5 +1,19 @@
|
|
1
1
|
module Tolq::Parsers::Xliff
|
2
|
+
class ParseError < StandardError; end;
|
3
|
+
|
2
4
|
class Parser
|
5
|
+
# Helper method to convert a xliff into an annotated hash. Format is
|
6
|
+
# different from Tolq api
|
7
|
+
#
|
8
|
+
# @param xliff_text [String] String of file
|
9
|
+
# @param parse_opts [Hash] Noop
|
10
|
+
# @return [Hash] Hash representation of xliff
|
11
|
+
def self.to_hash(xliff_text, **parse_opts)
|
12
|
+
xliff = XLIFFer::XLIFF.new(xliff_text)
|
13
|
+
validate_xliff!(xliff)
|
14
|
+
extract_request_data_from_files(xliff.files, text_node: false)
|
15
|
+
end
|
16
|
+
|
3
17
|
|
4
18
|
# Creates a new Xliff parser
|
5
19
|
#
|
@@ -17,34 +31,51 @@ module Tolq::Parsers::Xliff
|
|
17
31
|
# @return [Hash] A hash suitable to be converted to json for the Tolq Api
|
18
32
|
def parse(xliff_text)
|
19
33
|
xliff = XLIFFer::XLIFF.new(xliff_text)
|
20
|
-
|
21
|
-
request_data =
|
34
|
+
self.class.validate_xliff!(xliff)
|
35
|
+
request_data = self.class.extract_request_data_from_files(xliff.files)
|
22
36
|
|
23
37
|
{
|
24
38
|
"request" => request_data,
|
25
|
-
"source_language_code" => @source_language_code || strip_region_language(
|
26
|
-
"target_language_code" => @target_language_code || strip_region_language(
|
39
|
+
"source_language_code" => @source_language_code || strip_region_language(xliff.files.first.source_language),
|
40
|
+
"target_language_code" => @target_language_code || strip_region_language(xliff.files.first.target_language),
|
27
41
|
"quality" => @quality.to_s
|
28
42
|
}
|
29
43
|
end
|
30
44
|
|
31
45
|
private
|
32
46
|
|
33
|
-
def
|
34
|
-
|
35
|
-
|
36
|
-
|
47
|
+
def self.extract_request_data_from_files(xliff_files, text_node: true)
|
48
|
+
acc = {}
|
49
|
+
xliff_files.each.with_index do |file, file_idx|
|
50
|
+
file.strings.each do |string|
|
51
|
+
unless string.source && string.source.strip.length > 0
|
52
|
+
next acc
|
53
|
+
end
|
54
|
+
id = "#{file_idx}-#{string.id}"
|
55
|
+
if text_node
|
56
|
+
acc[id] = {"text" => string.source }
|
57
|
+
else
|
58
|
+
acc[id] = string.source
|
59
|
+
end
|
60
|
+
if string.note.length > 0 && text_node # xliffs so far use this for bogus anyway
|
61
|
+
acc[id].merge!("translator_message" => string.note)
|
62
|
+
end
|
37
63
|
end
|
38
|
-
acc[string.id] = {"text" => string.source }
|
39
|
-
if string.note.length > 0
|
40
|
-
acc[string.id].merge!("translator_message" => string.note)
|
41
|
-
end
|
42
|
-
acc
|
43
64
|
end
|
65
|
+
acc
|
44
66
|
end
|
45
67
|
|
46
68
|
def strip_region_language(language)
|
47
69
|
language[0..1]
|
48
70
|
end
|
71
|
+
|
72
|
+
def self.validate_xliff!(xliff)
|
73
|
+
if xliff.files.map(&:source_language).compact.uniq.length != 1
|
74
|
+
raise ParseError.new("More than one source language, cannot parse file")
|
75
|
+
end
|
76
|
+
if xliff.files.any? { |file| file.strings.map(&:id).any?(&:nil?) }
|
77
|
+
raise ParseError.new("Missing mandatory ID for one or more 'trans-unit'")
|
78
|
+
end
|
79
|
+
end
|
49
80
|
end
|
50
81
|
end
|
data/lib/xliff/unparser.rb
CHANGED
@@ -25,10 +25,12 @@ module Tolq::Parsers::Xliff
|
|
25
25
|
|
26
26
|
def translate_xliff(translations, xliff_text, target_language_code)
|
27
27
|
xliff = XLIFFer::XLIFF.new(xliff_text)
|
28
|
-
xliff.files.
|
29
|
-
|
30
|
-
|
31
|
-
|
28
|
+
xliff.files.each.with_index do |file, file_idx|
|
29
|
+
file.target_language = target_language_code
|
30
|
+
file.strings.each do |string|
|
31
|
+
if translation = translations["#{file_idx}-#{string.id}"]
|
32
|
+
string.target = translation
|
33
|
+
end
|
32
34
|
end
|
33
35
|
end
|
34
36
|
xliff
|
data/lib/xliff/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: tolq-parsers-xliff
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.6
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Timon Vonk
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-02-
|
11
|
+
date: 2017-02-21 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: xliffer
|