sanscript 0.3.2 → 0.3.3
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/.travis.yml +6 -0
- data/lib/sanscript/detect.rb +37 -2
- data/lib/sanscript/transliterate.rb +1 -0
- data/lib/sanscript/version.rb +1 -1
- data/sanscript.gemspec +2 -0
- metadata +5 -5
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: d1e473866926c96b58966e9a570d1310ae9d8eff
|
4
|
+
data.tar.gz: b6f0165d110775e8f4adb49de170634638afb372
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6abff0d8586ff49952c7a308d4ddaf142fcc0ae4be41a739ed287a5705b2bca2cf104ef965c37cdc39dd6b0ce34155d2509722275494a87125e8c5b65403f062
|
7
|
+
data.tar.gz: d66c8bfd4cd7faddf4e544e5287e7c83a8c7d855741aac71f2153f457e4e275a47981cff9559009d7d7ce7cc0b7c3faf20c684d11cf1561f09c6924b500f4e73
|
data/.travis.yml
CHANGED
data/lib/sanscript/detect.rb
CHANGED
@@ -44,14 +44,17 @@ module Sanscript
|
|
44
44
|
# Match on characters available in Harvard-Kyoto
|
45
45
|
RE_HARVARD_KYOTO = /[aAiIuUeoRMHkgGcjJTDNtdnpbmyrlvzSsh]/
|
46
46
|
|
47
|
+
# Match ##...## or {#...#} control blocks.
|
48
|
+
RE_CONTROL_BLOCK = /(?<!\\)##.*?(?<!\\)##|(?<!\\)\{#.*?(?<!\\)#\}/
|
49
|
+
|
47
50
|
private_constant :RE_BRAHMIC_RANGE, :RE_BRAHMIC_SCRIPTS, :RE_IAST_OR_KOLKATA_ONLY,
|
48
51
|
:RE_KOLKATA_ONLY, :RE_ITRANS_ONLY, :RE_SLP1_ONLY, :RE_VELTHUIS_ONLY,
|
49
|
-
:RE_ITRANS_OR_VELTHUIS_ONLY, :RE_HARVARD_KYOTO
|
52
|
+
:RE_ITRANS_OR_VELTHUIS_ONLY, :RE_HARVARD_KYOTO, :RE_CONTROL_BLOCK
|
50
53
|
|
51
54
|
module_function
|
52
55
|
|
53
56
|
def detect_script(text)
|
54
|
-
text = text.to_str.gsub(
|
57
|
+
text = text.to_str.gsub(RE_CONTROL_BLOCK, "")
|
55
58
|
|
56
59
|
# Brahmic schemes are all within a specific range of code points.
|
57
60
|
if RE_BRAHMIC_RANGE === text
|
@@ -78,5 +81,37 @@ module Sanscript
|
|
78
81
|
:unknown
|
79
82
|
end
|
80
83
|
end
|
84
|
+
|
85
|
+
# If Ruby 2.4's Regexp#match? method is found, use it for performance
|
86
|
+
if Regexp.method_defined?(:match?)
|
87
|
+
def detect_script(text)
|
88
|
+
text = text.to_str.gsub(RE_CONTROL_BLOCK, "")
|
89
|
+
|
90
|
+
# Brahmic schemes are all within a specific range of code points.
|
91
|
+
if RE_BRAHMIC_RANGE.match?(text)
|
92
|
+
RE_BRAHMIC_SCRIPTS.each do |script, regex|
|
93
|
+
return script if regex.match?(text)
|
94
|
+
end
|
95
|
+
end
|
96
|
+
|
97
|
+
# Romanizations
|
98
|
+
if RE_IAST_OR_KOLKATA_ONLY.match?(text)
|
99
|
+
return :kolkata if RE_KOLKATA_ONLY.match?(text)
|
100
|
+
:iast
|
101
|
+
elsif RE_ITRANS_ONLY.match?(text)
|
102
|
+
:itrans
|
103
|
+
elsif RE_SLP1_ONLY.match?(text)
|
104
|
+
:slp1
|
105
|
+
elsif RE_VELTHUIS_ONLY.match?(text)
|
106
|
+
:velthuis
|
107
|
+
elsif RE_ITRANS_OR_VELTHUIS_ONLY.match?(text)
|
108
|
+
:itrans
|
109
|
+
elsif RE_HARVARD_KYOTO.match?(text)
|
110
|
+
:hk
|
111
|
+
else
|
112
|
+
:unknown
|
113
|
+
end
|
114
|
+
end
|
115
|
+
end
|
81
116
|
end
|
82
117
|
end
|
@@ -148,6 +148,7 @@ module Sanscript
|
|
148
148
|
def transliterate(data, from, to, options = {})
|
149
149
|
from = from.to_sym
|
150
150
|
to = to.to_sym
|
151
|
+
return data if from == to
|
151
152
|
raise "Scheme not known ':#{from}'" unless @schemes.key?(from)
|
152
153
|
raise "Scheme not known ':#{to}'" unless @schemes.key?(to)
|
153
154
|
|
data/lib/sanscript/version.rb
CHANGED
data/sanscript.gemspec
CHANGED
@@ -19,6 +19,8 @@ Gem::Specification.new do |spec|
|
|
19
19
|
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
20
20
|
spec.require_paths = ["lib"]
|
21
21
|
|
22
|
+
spec.required_ruby_version = "~> 2.2"
|
23
|
+
|
22
24
|
spec.add_development_dependency "bundler", "~> 1.12"
|
23
25
|
spec.add_development_dependency "rake", "~> 11.2"
|
24
26
|
spec.add_development_dependency "rspec", "~> 3.5"
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: sanscript
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.3.
|
4
|
+
version: 0.3.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Tim Bellefleur
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2016-07-
|
11
|
+
date: 2016-07-21 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -145,9 +145,9 @@ require_paths:
|
|
145
145
|
- lib
|
146
146
|
required_ruby_version: !ruby/object:Gem::Requirement
|
147
147
|
requirements:
|
148
|
-
- - "
|
148
|
+
- - "~>"
|
149
149
|
- !ruby/object:Gem::Version
|
150
|
-
version: '
|
150
|
+
version: '2.2'
|
151
151
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
152
152
|
requirements:
|
153
153
|
- - ">="
|
@@ -155,7 +155,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
155
155
|
version: '0'
|
156
156
|
requirements: []
|
157
157
|
rubyforge_project:
|
158
|
-
rubygems_version: 2.6.
|
158
|
+
rubygems_version: 2.6.4
|
159
159
|
signing_key:
|
160
160
|
specification_version: 4
|
161
161
|
summary: Ruby port and extension of Sanscript.js transliterator by learnsanskrit.org
|