sanscript 0.8.1 → 0.9.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.gitignore +1 -0
- data/.rubocop.yml +14 -2
- data/.travis.yml +3 -3
- data/Cargo.toml +4 -4
- data/Gemfile +1 -0
- data/Rakefile +1 -0
- data/lib/sanscript.rb +1 -0
- data/lib/sanscript/benchmark.rb +31 -62
- data/lib/sanscript/detect.rb +3 -0
- data/lib/sanscript/detect/constants.rb +5 -15
- data/lib/sanscript/detect/ruby24.rb +2 -5
- data/lib/sanscript/detect/ruby2x.rb +2 -5
- data/lib/sanscript/rust.rb +3 -0
- data/lib/sanscript/transliterate.rb +6 -6
- data/lib/sanscript/version.rb +2 -1
- data/sanscript.gemspec +8 -7
- data/src/detect/mod.rs +27 -33
- data/src/lib.rs +30 -0
- metadata +31 -31
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: ef6e9b7e12549b07177b807613493b8bbf5df8dab1d762d6f2cbb5db65c3a710
|
4
|
+
data.tar.gz: 9e02c19c6189ca48c95a74b6448cb5f0a2be25fa5fabea8a39082a52d4a8bb41
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 11f53ad681749ca4aed397e3401f40c9f97ef1e3f654d3f23c9dde407636739817d6af962f9ed09d18a4375021822e5fbbb99b38790b011986e362e2c4758a8f
|
7
|
+
data.tar.gz: 1296c18342ff547c831549e3b17412541a7afe18c471e6f0e1867b1f0bb0c24bc3c00e52a5e0d69241936f3ebb576504dcc5cfea4f8fcfc1f1a4484576578fc2
|
data/.gitignore
CHANGED
data/.rubocop.yml
CHANGED
@@ -1,6 +1,5 @@
|
|
1
|
-
require: rubocop-rspec
|
2
1
|
AllCops:
|
3
|
-
TargetRubyVersion: 2.
|
2
|
+
TargetRubyVersion: 2.2
|
4
3
|
|
5
4
|
# Metrics
|
6
5
|
Metrics/AbcSize:
|
@@ -17,6 +16,10 @@ Metrics/BlockNesting:
|
|
17
16
|
Enabled: true
|
18
17
|
Max: 4
|
19
18
|
|
19
|
+
Metrics/BlockLength:
|
20
|
+
Exclude:
|
21
|
+
- spec/**/*.rb
|
22
|
+
|
20
23
|
Metrics/ClassLength:
|
21
24
|
Description: 'Avoid classes longer than 250 lines of code.'
|
22
25
|
Enabled: true
|
@@ -96,3 +99,12 @@ Style/TrailingCommaInLiteral:
|
|
96
99
|
Style/TrivialAccessors:
|
97
100
|
ExactNameMatch: true
|
98
101
|
AllowPredicates: true
|
102
|
+
|
103
|
+
# RSpec
|
104
|
+
require: rubocop-rspec
|
105
|
+
|
106
|
+
RSpec/ContextWording:
|
107
|
+
Enabled: false
|
108
|
+
|
109
|
+
RSpec/NestedGroups:
|
110
|
+
Max: 3
|
data/.travis.yml
CHANGED
data/Cargo.toml
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
[package]
|
2
2
|
name = "rusty_sanscript"
|
3
|
-
version = "0.4.
|
3
|
+
version = "0.4.1"
|
4
4
|
authors = ["Tim Bellefleur <nomoon@phoebus.ca>"]
|
5
5
|
publish = false
|
6
6
|
|
7
7
|
[dependencies]
|
8
|
-
lazy_static = "^0.2.
|
9
|
-
ruby-sys = "^0.
|
10
|
-
regex = "^0.
|
8
|
+
lazy_static = "^0.2.10"
|
9
|
+
ruby-sys = "^0.3.0"
|
10
|
+
regex = "^0.2.2"
|
11
11
|
|
12
12
|
[lib]
|
13
13
|
crate-type = ["cdylib"]
|
data/Gemfile
CHANGED
data/Rakefile
CHANGED
data/lib/sanscript.rb
CHANGED
data/lib/sanscript/benchmark.rb
CHANGED
@@ -5,7 +5,7 @@ module Sanscript
|
|
5
5
|
require "benchmark/ips"
|
6
6
|
rescue LoadError
|
7
7
|
#:nocov:
|
8
|
-
module ::Benchmark
|
8
|
+
module ::Benchmark # rubocop:disable Style/ClassAndModuleChildren
|
9
9
|
def self.ips(*)
|
10
10
|
raise NotImplementedError, "You must install the `benchmark-ips` gem first."
|
11
11
|
end
|
@@ -15,32 +15,32 @@ module Sanscript
|
|
15
15
|
|
16
16
|
# Benchmark/testing module.
|
17
17
|
module Benchmark
|
18
|
+
TEST_STRINGS = {
|
19
|
+
brahmic: {
|
20
|
+
devanagari: "नानाशास्त्रसुभाषितामृतरसैः श्रोत्रोत्सवं कुर्वतां येषां यान्ति दिनानि पण्डितजनव्यायामखिन्नात्मनाम् तेषां जन्म च जीवितं च सुकृतं तैर् एव भूर् भूषिता शेषैह् किं पशुवद् विवेकरहितैर् भूभारभूतैर् नरः",
|
21
|
+
malayalam: "നാനാശാസ്ത്രസുഭാഷിതാമൃതരസൈഃ ശ്രോത്രോത്സവം കുര്വതാം യേഷാം യാന്തി ദിനാനി പണ്ഡിതജനവ്യായാമഖിന്നാത്മനാമ് തേഷാം ജന്മ ച ജീവിതം ച സുകൃതം തൈര് ഏവ ഭൂര് ഭൂഷിതാ ശേഷൈഹ് കിം പശുവദ് വിവേകരഹിതൈര് ഭൂഭാരഭൂതൈര് നരഃ",
|
22
|
+
}.freeze,
|
23
|
+
roman: {
|
24
|
+
iast: "nānāśāstrasubhāṣitāmṛtarasaiḥ śrotrotsavaṃ kurvatāṃ yeṣāṃ yānti dināni paṇḍitajanavyāyāmakhinnātmanām teṣāṃ janma ca jīvitaṃ ca sukṛtaṃ tair eva bhūr bhūṣitā śeṣaih kiṃ paśuvad vivekarahitair bhūbhārabhūtair naraḥ",
|
25
|
+
slp1: "nAnASAstrasuBAzitAmftarasEH SrotrotsavaM kurvatAM yezAM yAnti dinAni paRqitajanavyAyAmaKinnAtmanAm tezAM janma ca jIvitaM ca sukftaM tEr eva BUr BUzitA SezEh kiM paSuvad vivekarahitEr BUBAraBUtEr naraH",
|
26
|
+
hk: "nAnAzAstrasubhASitAmRtarasaiH zrotrotsavaM kurvatAM yeSAM yAnti dinAni paNDitajanavyAyAmakhinnAtmanAm teSAM janma ca jIvitaM ca sukRtaM tair eva bhUr bhUSitA zeSaih kiM pazuvad vivekarahitair bhUbhArabhUtair naraH",
|
27
|
+
}.freeze,
|
28
|
+
}.freeze
|
29
|
+
|
30
|
+
TEST_STRINGS_FLAT = TEST_STRINGS.reduce({}) { |a, (_, v)| a.merge(v) }.freeze
|
31
|
+
|
32
|
+
private_constant :TEST_STRINGS, :TEST_STRINGS_FLAT
|
33
|
+
|
18
34
|
module_function
|
19
35
|
|
20
36
|
# Runs benchmark-ips test on detection methods.
|
21
37
|
def detect!(time = 2, warmup = 1)
|
22
|
-
deva_string = "नानाशास्त्रसुभाषितामृतरसैः श्रोत्रोत्सवं कुर्वतां येषां यान्ति दिनानि पण्डितजनव्यायामखिन्नात्मनाम् तेषां जन्म च जीवितं च सुकृतं तैर् एव भूर् भूषिता शेषैह् किं पशुवद् विवेकरहितैर् भूभारभूतैर् नरः"
|
23
|
-
malayalam_string = "നാനാശാസ്ത്രസുഭാഷിതാമൃതരസൈഃ ശ്രോത്രോത്സവം കുര്വതാം യേഷാം യാന്തി ദിനാനി പണ്ഡിതജനവ്യായാമഖിന്നാത്മനാമ് തേഷാം ജന്മ ച ജീവിതം ച സുകൃതം തൈര് ഏവ ഭൂര് ഭൂഷിതാ ശേഷൈഹ് കിം പശുവദ് വിവേകരഹിതൈര് ഭൂഭാരഭൂതൈര് നരഃ"
|
24
|
-
iast_string = "nānāśāstrasubhāṣitāmṛtarasaiḥ śrotrotsavaṃ kurvatāṃ yeṣāṃ yānti dināni paṇḍitajanavyāyāmakhinnātmanām teṣāṃ janma ca jīvitaṃ ca sukṛtaṃ tair eva bhūr bhūṣitā śeṣaih kiṃ paśuvad vivekarahitair bhūbhārabhūtair naraḥ"
|
25
|
-
slp1_string = "nAnASAstrasuBAzitAmftarasEH SrotrotsavaM kurvatAM yezAM yAnti dinAni paRqitajanavyAyAmaKinnAtmanAm tezAM janma ca jIvitaM ca sukftaM tEr eva BUr BUzitA SezEh kiM paSuvad vivekarahitEr BUBAraBUtEr naraH"
|
26
|
-
hk_string = "nAnAzAstrasubhASitAmRtarasaiH zrotrotsavaM kurvatAM yeSAM yAnti dinAni paNDitajanavyAyAmakhinnAtmanAm teSAM janma ca jIvitaM ca sukRtaM tair eva bhUr bhUSitA zeSaih kiM pazuvad vivekarahitair bhUbhArabhUtair naraH"
|
27
|
-
|
28
38
|
::Benchmark.ips do |x|
|
29
39
|
x.config(time: time, warmup: warmup)
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
Sanscript::Detect.detect_scheme(malayalam_string)
|
35
|
-
end
|
36
|
-
x.report("Detect IAST") do
|
37
|
-
Sanscript::Detect.detect_scheme(iast_string)
|
38
|
-
end
|
39
|
-
x.report("Detect SLP1") do
|
40
|
-
Sanscript::Detect.detect_scheme(slp1_string)
|
41
|
-
end
|
42
|
-
x.report("Detect HK") do
|
43
|
-
Sanscript::Detect.detect_scheme(hk_string)
|
40
|
+
TEST_STRINGS_FLAT.each do |scheme, string|
|
41
|
+
x.report("Detect #{scheme}") do
|
42
|
+
Sanscript::Detect.detect_scheme(string)
|
43
|
+
end
|
44
44
|
end
|
45
45
|
x.compare!
|
46
46
|
end
|
@@ -49,39 +49,13 @@ module Sanscript
|
|
49
49
|
|
50
50
|
# Runs benchmark-ips test on roman-source transliteration methods.
|
51
51
|
def transliterate_roman!(time = 2, warmup = 1)
|
52
|
-
iast_string = "nānāśāstrasubhāṣitāmṛtarasaiḥ śrotrotsavaṃ kurvatāṃ yeṣāṃ yānti dināni paṇḍitajanavyāyāmakhinnātmanām teṣāṃ janma ca jīvitaṃ ca sukṛtaṃ tair eva bhūr bhūṣitā śeṣaih kiṃ paśuvad vivekarahitair bhūbhārabhūtair naraḥ"
|
53
|
-
slp1_string = "nAnASAstrasuBAzitAmftarasEH SrotrotsavaM kurvatAM yezAM yAnti dinAni paRqitajanavyAyAmaKinnAtmanAm tezAM janma ca jIvitaM ca sukftaM tEr eva BUr BUzitA SezEh kiM paSuvad vivekarahitEr BUBAraBUtEr naraH"
|
54
|
-
hk_string = "nAnAzAstrasubhASitAmRtarasaiH zrotrotsavaM kurvatAM yeSAM yAnti dinAni paNDitajanavyAyAmakhinnAtmanAm teSAM janma ca jIvitaM ca sukRtaM tair eva bhUr bhUSitA zeSaih kiM pazuvad vivekarahitair bhUbhArabhUtair naraH"
|
55
|
-
|
56
52
|
::Benchmark.ips do |x|
|
57
53
|
x.config(time: time, warmup: warmup)
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
Sanscript.transliterate(iast_string, :iast, :slp1)
|
64
|
-
end
|
65
|
-
x.report("IAST==>SLP1") do
|
66
|
-
Sanscript.transliterate(iast_string, :iast, :hk)
|
67
|
-
end
|
68
|
-
x.report("SLP1==>Devanagari") do
|
69
|
-
Sanscript.transliterate(slp1_string, :slp1, :devanagari)
|
70
|
-
end
|
71
|
-
x.report("SLP1==>IAST") do
|
72
|
-
Sanscript.transliterate(slp1_string, :slp1, :iast)
|
73
|
-
end
|
74
|
-
x.report("SLP1==>HK") do
|
75
|
-
Sanscript.transliterate(slp1_string, :slp1, :hk)
|
76
|
-
end
|
77
|
-
x.report("HK==>Devanagari") do
|
78
|
-
Sanscript.transliterate(hk_string, :hk, :devanagari)
|
79
|
-
end
|
80
|
-
x.report("HK==>IAST") do
|
81
|
-
Sanscript.transliterate(hk_string, :hk, :iast)
|
82
|
-
end
|
83
|
-
x.report("HK==>SLP1") do
|
84
|
-
Sanscript.transliterate(hk_string, :hk, :slp1)
|
54
|
+
TEST_STRINGS[:roman].to_a.product(TEST_STRINGS_FLAT.keys).each do |(ak, av), bk|
|
55
|
+
next if ak == bk
|
56
|
+
x.report("#{ak} => #{bk}") do
|
57
|
+
Sanscript.transliterate(av, ak, bk)
|
58
|
+
end
|
85
59
|
end
|
86
60
|
x.compare!
|
87
61
|
end
|
@@ -90,18 +64,13 @@ module Sanscript
|
|
90
64
|
|
91
65
|
# Runs benchmark-ips test on brahmic-source transliteration methods.
|
92
66
|
def transliterate_brahmic!(time = 2, warmup = 1)
|
93
|
-
deva_string = "नानाशास्त्रसुभाषितामृतरसैः श्रोत्रोत्सवं कुर्वतां येषां यान्ति दिनानि पण्डितजनव्यायामखिन्नात्मनाम् तेषां जन्म च जीवितं च सुकृतं तैर् एव भूर् भूषिता शेषैह् किं पशुवद् विवेकरहितैर् भूभारभूतैर् नरः"
|
94
|
-
|
95
67
|
::Benchmark.ips do |x|
|
96
68
|
x.config(time: time, warmup: warmup)
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
|
101
|
-
|
102
|
-
end
|
103
|
-
x.report("Devanagari==>HK") do
|
104
|
-
Sanscript.transliterate(deva_string, :devanagari, :hk)
|
69
|
+
TEST_STRINGS[:brahmic].to_a.product(TEST_STRINGS_FLAT.keys).each do |(ak, av), bk|
|
70
|
+
next if ak == bk
|
71
|
+
x.report("#{ak} => #{bk}") do
|
72
|
+
Sanscript.transliterate(av, ak, bk)
|
73
|
+
end
|
105
74
|
end
|
106
75
|
x.compare!
|
107
76
|
end
|
data/lib/sanscript/detect.rb
CHANGED
@@ -1,4 +1,5 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
|
+
|
2
3
|
require "sanscript/detect/constants"
|
3
4
|
|
4
5
|
module Sanscript
|
@@ -6,11 +7,13 @@ module Sanscript
|
|
6
7
|
# Developed from code available @ https://github.com/sanskrit/detect.js
|
7
8
|
module Detect
|
8
9
|
if Regexp.method_defined?(:match?)
|
10
|
+
# :nocov:
|
9
11
|
require "sanscript/detect/ruby24"
|
10
12
|
extend Ruby24
|
11
13
|
else
|
12
14
|
require "sanscript/detect/ruby2x"
|
13
15
|
extend Ruby2x
|
16
|
+
# :nocov:
|
14
17
|
end
|
15
18
|
|
16
19
|
# @!method detect_scheme(text)
|
@@ -8,24 +8,14 @@ module Sanscript
|
|
8
8
|
# between Devanagari and Malayalam.
|
9
9
|
RE_BRAHMIC_RANGE = /[\u0900-\u0d7f]/
|
10
10
|
|
11
|
-
#
|
12
|
-
|
13
|
-
devanagari: /\p{Devanagari}/,
|
14
|
-
bengali: /\p{Bengali}/,
|
15
|
-
gurmukhi: /\p{Gurmukhi}/,
|
16
|
-
gujarati: /\p{Gujarati}/,
|
17
|
-
oriya: /\p{Oriya}/,
|
18
|
-
tamil: /\p{Tamil}/,
|
19
|
-
telugu: /\p{Telugu}/,
|
20
|
-
kannada: /\p{Kannada}/,
|
21
|
-
malayalam: /\p{Malayalam}/,
|
22
|
-
}.freeze
|
11
|
+
# The order of individual brahmic scripts in 128 character unicode blocks.
|
12
|
+
BRAHMIC_SCRIPTS_ORDER = %i[devanagari bengali gurmukhi gujarati oriya tamil telugu kannada malayalam].freeze
|
23
13
|
|
24
14
|
# Match on special Roman characters
|
25
|
-
RE_IAST_OR_KOLKATA_ONLY = /[
|
15
|
+
RE_IAST_OR_KOLKATA_ONLY = /[āīūṛṝḷḹēōṃḥṅñṭḍṇśṣḻĀĪŪṚṜḶḸĒŌṂḤṄÑṬḌṆŚṢḺ]|[aiueoAIUEO]\u0304|[rlRL]\u0323\u0304?|[mhtdMHTD]\u0323|[nN][\u0307\u0303\u0323]|[sS][\u0301\u0323]|[lL]\u0331/
|
26
16
|
|
27
17
|
# Match on Kolkata-specific Roman characters
|
28
|
-
RE_KOLKATA_ONLY = /[
|
18
|
+
RE_KOLKATA_ONLY = /[ēōĒŌ]|[eoEO]\u0304/
|
29
19
|
|
30
20
|
# Match on ITRANS-only
|
31
21
|
RE_ITRANS_ONLY = /ee|oo|\^[iI]|RR[iI]|L[iI]|~N|N\^|Ch|chh|JN|sh|Sh|\.a/
|
@@ -45,7 +35,7 @@ module Sanscript
|
|
45
35
|
# Match ##...## or {#...#} control blocks.
|
46
36
|
RE_CONTROL_BLOCK = /(?<!\\)##.*?(?<!\\)##|(?<!\\)\{#.*?(?<!\\)#\}/
|
47
37
|
|
48
|
-
private_constant :RE_BRAHMIC_RANGE, :
|
38
|
+
private_constant :RE_BRAHMIC_RANGE, :BRAHMIC_SCRIPTS_ORDER, :RE_IAST_OR_KOLKATA_ONLY,
|
49
39
|
:RE_KOLKATA_ONLY, :RE_ITRANS_ONLY, :RE_SLP1_ONLY, :RE_VELTHUIS_ONLY,
|
50
40
|
:RE_ITRANS_OR_VELTHUIS_ONLY, :RE_HARVARD_KYOTO, :RE_CONTROL_BLOCK
|
51
41
|
end
|
@@ -14,11 +14,8 @@ module Sanscript
|
|
14
14
|
text = text.to_str.gsub(RE_CONTROL_BLOCK, "")
|
15
15
|
|
16
16
|
# Brahmic schemes are all within a specific range of code points.
|
17
|
-
|
18
|
-
|
19
|
-
return script if regex.match?(text)
|
20
|
-
end
|
21
|
-
end
|
17
|
+
brahmic_char = text[RE_BRAHMIC_RANGE]
|
18
|
+
return BRAHMIC_SCRIPTS_ORDER[(brahmic_char.ord - 0x0900) / 0x80] if brahmic_char
|
22
19
|
|
23
20
|
# Romanizations
|
24
21
|
if RE_IAST_OR_KOLKATA_ONLY.match?(text)
|
@@ -15,11 +15,8 @@ module Sanscript
|
|
15
15
|
# rubocop:disable Style/CaseEquality
|
16
16
|
|
17
17
|
# Brahmic schemes are all within a specific range of code points.
|
18
|
-
|
19
|
-
|
20
|
-
return script if regex === text
|
21
|
-
end
|
22
|
-
end
|
18
|
+
brahmic_char = text[RE_BRAHMIC_RANGE]
|
19
|
+
return BRAHMIC_SCRIPTS_ORDER[(brahmic_char.ord - 0x0900) / 0x80] if brahmic_char
|
23
20
|
|
24
21
|
# Romanizations
|
25
22
|
if RE_IAST_OR_KOLKATA_ONLY === text
|
data/lib/sanscript/rust.rb
CHANGED
@@ -1,10 +1,12 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
|
+
|
2
3
|
module Sanscript
|
3
4
|
module_function
|
4
5
|
|
5
6
|
# Attempts to load Rust native extension.
|
6
7
|
# @return [bool] whether the extension loaded.
|
7
8
|
def rust_load!
|
9
|
+
# :nocov:
|
8
10
|
return RUST_AVAILABLE if defined?(RUST_AVAILABLE)
|
9
11
|
require "thermite/fiddle"
|
10
12
|
Thermite::Fiddle.load_module("init_rusty_sanscript",
|
@@ -13,6 +15,7 @@ module Sanscript
|
|
13
15
|
defined?(Sanscript::Rust) ? true : false
|
14
16
|
rescue Fiddle::DLError
|
15
17
|
false
|
18
|
+
# :nocov:
|
16
19
|
end
|
17
20
|
|
18
21
|
# @return [bool] the enabled status of the Rust extension
|
@@ -128,7 +128,7 @@ module Sanscript
|
|
128
128
|
add_roman_scheme(:itrans_dravidian, itrans_dravidian)
|
129
129
|
|
130
130
|
# ensure deep freeze on alternates
|
131
|
-
@all_alternates.
|
131
|
+
@all_alternates.each_value { |alternates| alternates.deep_freeze } # rubocop:disable Style/SymbolProc
|
132
132
|
end
|
133
133
|
|
134
134
|
# Transliterate from one script to another.
|
@@ -195,14 +195,14 @@ module Sanscript
|
|
195
195
|
token_lengths.push(f.length)
|
196
196
|
token_lengths.concat(alts.map(&:length))
|
197
197
|
|
198
|
-
if group == :vowel_marks || group == :virama
|
198
|
+
if group == :vowel_marks || group == :virama # rubocop:disable MultipleComparison
|
199
199
|
marks[f] = t
|
200
200
|
alts.each { |alt| marks[alt] = t }
|
201
201
|
else
|
202
202
|
letters[f] = t
|
203
203
|
alts.each { |alt| letters[alt] = t }
|
204
204
|
|
205
|
-
if group == :consonants || group == :other
|
205
|
+
if group == :consonants || group == :other # rubocop:disable MultipleComparison
|
206
206
|
consonants[f] = t
|
207
207
|
alts.each { |alt| consonants[alt] = t }
|
208
208
|
end
|
@@ -227,7 +227,7 @@ module Sanscript
|
|
227
227
|
# @param data [String] the string to transliterate
|
228
228
|
# @param map [Hash] map data generated from {#make_map}
|
229
229
|
# @return [String] the transliterated string
|
230
|
-
def transliterate_roman(data, map, options = {})
|
230
|
+
def transliterate_roman(data, map, options = {}) # rubocop:disable MethodLength, CyclomaticComplexity
|
231
231
|
data = data.to_str.chars
|
232
232
|
buf = []
|
233
233
|
token_buffer = []
|
@@ -239,7 +239,7 @@ module Sanscript
|
|
239
239
|
until data.empty? && token_buffer.empty?
|
240
240
|
# Match all token substrings to our map.
|
241
241
|
token = data[0, max_token_length].join("")
|
242
|
-
max_token_length.downto(1) do |j|
|
242
|
+
max_token_length.downto(1) do |j| # rubocop:disable BlockLength
|
243
243
|
token = token[0, j] unless j == max_token_length
|
244
244
|
if j == 2
|
245
245
|
if !control_char && token == "##"
|
@@ -302,7 +302,7 @@ module Sanscript
|
|
302
302
|
# @param data [String] the string to transliterate
|
303
303
|
# @param map [Hash] map data generated from {#make_map}
|
304
304
|
# @return [String] the transliterated string
|
305
|
-
def transliterate_brahmic(data, map)
|
305
|
+
def transliterate_brahmic(data, map) # rubocop:disable MethodLength, CyclomaticComplexity
|
306
306
|
data = data.to_str.chars
|
307
307
|
buf = []
|
308
308
|
had_roman_consonant = false
|
data/lib/sanscript/version.rb
CHANGED
data/sanscript.gemspec
CHANGED
@@ -1,5 +1,6 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
# coding: utf-8
|
3
|
+
|
3
4
|
lib = File.expand_path("../lib", __FILE__)
|
4
5
|
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
5
6
|
require "sanscript/version"
|
@@ -22,16 +23,16 @@ Gem::Specification.new do |spec|
|
|
22
23
|
|
23
24
|
spec.required_ruby_version = "~> 2.2"
|
24
25
|
|
26
|
+
spec.add_development_dependency "benchmark-ips", "~> 2.7"
|
25
27
|
spec.add_development_dependency "bundler", "~> 1.13"
|
26
|
-
spec.add_development_dependency "rake", "~> 12"
|
27
|
-
spec.add_development_dependency "rspec", "~> 3.5"
|
28
28
|
spec.add_development_dependency "coveralls", "~> 0.8"
|
29
|
-
spec.add_development_dependency "rubocop", "~> 0.43"
|
30
|
-
spec.add_development_dependency "rubocop-rspec", "~> 1.7"
|
31
29
|
spec.add_development_dependency "pry", "~> 0.10"
|
32
|
-
spec.add_development_dependency "
|
30
|
+
spec.add_development_dependency "rake", "~> 12"
|
31
|
+
spec.add_development_dependency "rspec", "~> 3.5"
|
32
|
+
spec.add_development_dependency "rubocop", "~> 0.51"
|
33
|
+
spec.add_development_dependency "rubocop-rspec", "~> 1.20"
|
33
34
|
spec.add_development_dependency "yard", "~> 0.9"
|
34
35
|
|
35
|
-
spec.add_runtime_dependency "ragabash", "~> 0.
|
36
|
-
spec.add_runtime_dependency "thermite", "~> 0.
|
36
|
+
spec.add_runtime_dependency "ragabash", "~> 0.3"
|
37
|
+
spec.add_runtime_dependency "thermite", "~> 0.13"
|
37
38
|
end
|
data/src/detect/mod.rs
CHANGED
@@ -14,13 +14,13 @@ lazy_static! {
|
|
14
14
|
|
15
15
|
// Match any character in the block of Brahmic scripts
|
16
16
|
// between Devanagari and Malayalam.
|
17
|
-
static ref RE_BRAHMIC_RANGE: Regex = Regex::new(r"[\x{0900}-\x{
|
17
|
+
static ref RE_BRAHMIC_RANGE: Regex = Regex::new(r"[\x{0900}-\x{0D7F}]").unwrap();
|
18
18
|
|
19
19
|
// Match on special Roman characters
|
20
|
-
static ref RE_IAST_OR_KOLKATA_ONLY: Regex = Regex::new(r"
|
20
|
+
static ref RE_IAST_OR_KOLKATA_ONLY: Regex = Regex::new(r"[āīūṛṝḷḹēōṃḥṅñṭḍṇśṣḻĀĪŪṚṜḶḸĒŌṂḤṄÑṬḌṆŚṢḺ]|[aiueoAIUEO]\x{0304}|[rlRL]\x{0323}\x{0304}?|[mhtdMHTD]\x{0323}|[nN][\x{0307}\x{0303}\x{0323}]|[sS][\x{0301}\x{0323}]|[lL]\x{0331}").unwrap();
|
21
21
|
|
22
22
|
// Match on Kolkata-specific Roman characters
|
23
|
-
static ref RE_KOLKATA_ONLY: Regex = Regex::new(r"
|
23
|
+
static ref RE_KOLKATA_ONLY: Regex = Regex::new(r"[ēōĒŌ]|[eoEO]\x{0304}").unwrap();
|
24
24
|
|
25
25
|
// Match on ITRANS-only
|
26
26
|
static ref RE_ITRANS_ONLY: Regex = Regex::new(r"ee|oo|\^[iI]|RR[iI]|L[iI]|~N|N\^|Ch|chh|JN|sh|Sh|\.a").unwrap();
|
@@ -44,53 +44,47 @@ lazy_static! {
|
|
44
44
|
#[no_mangle]
|
45
45
|
pub extern fn detect_scheme(s: &str) -> usize {
|
46
46
|
// Clean-up string of control characters.
|
47
|
-
let r_str = &
|
48
|
-
|
47
|
+
let r_str = &RE_ESCAPED_CONTROL_CHAR.replace_all(s, "");
|
48
|
+
let r_str = &RE_CONTROL_BLOCK.replace_all(r_str, "");
|
49
49
|
|
50
50
|
// Brahmic schemes are all within a specific range of code points.
|
51
51
|
let brahmic_match = RE_BRAHMIC_RANGE.find(r_str);
|
52
52
|
if brahmic_match != None {
|
53
53
|
let brahmic_match = brahmic_match.unwrap();
|
54
|
-
let brahmic_codepoint = r_str.chars().nth(brahmic_match.
|
54
|
+
let brahmic_codepoint = r_str.chars().nth(brahmic_match.start()).unwrap() as usize;
|
55
55
|
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
return 6; // Tamil
|
68
|
-
} else if brahmic_codepoint < 0x0C80 {
|
69
|
-
return 7; // Telugu
|
70
|
-
} else if brahmic_codepoint < 0x0D00 {
|
71
|
-
return 8; // Kannada
|
72
|
-
} else {
|
73
|
-
return 9; // Malayalam
|
56
|
+
return match brahmic_codepoint {
|
57
|
+
0x0900...0x097F => 1, // Devanagari
|
58
|
+
0x0980...0x09FF => 2, // Bengali
|
59
|
+
0x0A00...0x0A7F => 3, // Gurmukhi
|
60
|
+
0x0A80...0x0AFF => 4, // Gujarati
|
61
|
+
0x0B00...0x0B7F => 5, // Oriya
|
62
|
+
0x0B80...0x0BFF => 6, // Tamil
|
63
|
+
0x0C00...0x0C7F => 7, // Telugu
|
64
|
+
0x0C80...0x0CFF => 8, // Kannada
|
65
|
+
0x0D00...0x0D7F => 9, // Malayalam
|
66
|
+
_ => 0
|
74
67
|
}
|
75
68
|
}
|
76
69
|
|
77
70
|
// Romanizations
|
78
|
-
if RE_IAST_OR_KOLKATA_ONLY.is_match(r_str) {
|
71
|
+
return if RE_IAST_OR_KOLKATA_ONLY.is_match(r_str) {
|
79
72
|
if RE_KOLKATA_ONLY.is_match(r_str) {
|
80
|
-
|
73
|
+
11 // Kolkata
|
81
74
|
} else {
|
82
|
-
|
75
|
+
10 // IAST
|
83
76
|
}
|
84
77
|
} else if RE_ITRANS_ONLY.is_match(r_str) {
|
85
|
-
|
78
|
+
12 // ITRANS
|
86
79
|
} else if RE_SLP1_ONLY.is_match(r_str) {
|
87
|
-
|
80
|
+
13 // SLP1
|
88
81
|
} else if RE_VELTHUIS_ONLY.is_match(r_str) {
|
89
|
-
|
82
|
+
14 // Velthuis
|
90
83
|
} else if RE_ITRANS_OR_VELTHUIS_ONLY.is_match(r_str) {
|
91
|
-
|
84
|
+
12 // ITRANS
|
92
85
|
} else if RE_HARVARD_KYOTO.is_match(r_str) {
|
93
|
-
|
86
|
+
15 // HK
|
87
|
+
} else {
|
88
|
+
0 // Unknown
|
94
89
|
}
|
95
|
-
return 0; // Unknown
|
96
90
|
}
|
data/src/lib.rs
CHANGED
@@ -4,3 +4,33 @@ extern crate regex;
|
|
4
4
|
|
5
5
|
#[macro_use] mod rb;
|
6
6
|
pub mod detect;
|
7
|
+
|
8
|
+
#[cfg(test)]
|
9
|
+
mod tests {
|
10
|
+
use detect::detect_scheme;
|
11
|
+
|
12
|
+
#[test]
|
13
|
+
fn detect_devanagari() {
|
14
|
+
assert_eq!(detect_scheme("नानाशास्त्रसुभाषितामृतरसैः श्रोत्रोत्सवं कुर्वतां येषां यान्ति दिनानि पण्डितजनव्यायामखिन्नात्मनाम् तेषां जन्म च जीवितं च सुकृतं तैर् एव भूर् भूषिता शेषैह् किं पशुवद् विवेकरहितैर् भूभारभूतैर् नरः"), 1);
|
15
|
+
}
|
16
|
+
|
17
|
+
#[test]
|
18
|
+
fn detect_malayalam() {
|
19
|
+
assert_eq!(detect_scheme("നാനാശാസ്ത്രസുഭാഷിതാമൃതരസൈഃ ശ്രോത്രോത്സവം കുര്വതാം യേഷാം യാന്തി ദിനാനി പണ്ഡിതജനവ്യായാമഖിന്നാത്മനാമ് തേഷാം ജന്മ ച ജീവിതം ച സുകൃതം തൈര് ഏവ ഭൂര് ഭൂഷിതാ ശേഷൈഹ് കിം പശുവദ് വിവേകരഹിതൈര് ഭൂഭാരഭൂതൈര് നരഃ"), 9);
|
20
|
+
}
|
21
|
+
|
22
|
+
#[test]
|
23
|
+
fn detect_iast() {
|
24
|
+
assert_eq!(detect_scheme("nānāśāstrasubhāṣitāmṛtarasaiḥ śrotrotsavaṃ kurvatāṃ yeṣāṃ yānti dināni paṇḍitajanavyāyāmakhinnātmanām teṣāṃ janma ca jīvitaṃ ca sukṛtaṃ tair eva bhūr bhūṣitā śeṣaih kiṃ paśuvad vivekarahitair bhūbhārabhūtair naraḥ"), 10);
|
25
|
+
}
|
26
|
+
|
27
|
+
#[test]
|
28
|
+
fn detect_slp1() {
|
29
|
+
assert_eq!(detect_scheme("nAnASAstrasuBAzitAmftarasEH SrotrotsavaM kurvatAM yezAM yAnti dinAni paRqitajanavyAyAmaKinnAtmanAm tezAM janma ca jIvitaM ca sukftaM tEr eva BUr BUzitA SezEh kiM paSuvad vivekarahitEr BUBAraBUtEr naraH"), 13);
|
30
|
+
}
|
31
|
+
|
32
|
+
#[test]
|
33
|
+
fn detect_hk() {
|
34
|
+
assert_eq!(detect_scheme("nAnAzAstrasubhASitAmRtarasaiH zrotrotsavaM kurvatAM yeSAM yAnti dinAni paNDitajanavyAyAmakhinnAtmanAm teSAM janma ca jIvitaM ca sukRtaM tair eva bhUr bhUSitA zeSaih kiM pazuvad vivekarahitair bhUbhArabhUtair naraH"), 15);
|
35
|
+
}
|
36
|
+
}
|
metadata
CHANGED
@@ -1,127 +1,127 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: sanscript
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.9.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Tim Bellefleur
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-
|
11
|
+
date: 2017-11-17 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
|
-
name:
|
14
|
+
name: benchmark-ips
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
17
|
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: '
|
19
|
+
version: '2.7'
|
20
20
|
type: :development
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: '
|
26
|
+
version: '2.7'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
|
-
name:
|
28
|
+
name: bundler
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
31
|
- - "~>"
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: '
|
33
|
+
version: '1.13'
|
34
34
|
type: :development
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
38
|
- - "~>"
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version: '
|
40
|
+
version: '1.13'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
|
-
name:
|
42
|
+
name: coveralls
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
45
|
- - "~>"
|
46
46
|
- !ruby/object:Gem::Version
|
47
|
-
version: '
|
47
|
+
version: '0.8'
|
48
48
|
type: :development
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
52
|
- - "~>"
|
53
53
|
- !ruby/object:Gem::Version
|
54
|
-
version: '
|
54
|
+
version: '0.8'
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
|
-
name:
|
56
|
+
name: pry
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
59
|
- - "~>"
|
60
60
|
- !ruby/object:Gem::Version
|
61
|
-
version: '0.
|
61
|
+
version: '0.10'
|
62
62
|
type: :development
|
63
63
|
prerelease: false
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
66
|
- - "~>"
|
67
67
|
- !ruby/object:Gem::Version
|
68
|
-
version: '0.
|
68
|
+
version: '0.10'
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
|
-
name:
|
70
|
+
name: rake
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
73
|
- - "~>"
|
74
74
|
- !ruby/object:Gem::Version
|
75
|
-
version: '
|
75
|
+
version: '12'
|
76
76
|
type: :development
|
77
77
|
prerelease: false
|
78
78
|
version_requirements: !ruby/object:Gem::Requirement
|
79
79
|
requirements:
|
80
80
|
- - "~>"
|
81
81
|
- !ruby/object:Gem::Version
|
82
|
-
version: '
|
82
|
+
version: '12'
|
83
83
|
- !ruby/object:Gem::Dependency
|
84
|
-
name:
|
84
|
+
name: rspec
|
85
85
|
requirement: !ruby/object:Gem::Requirement
|
86
86
|
requirements:
|
87
87
|
- - "~>"
|
88
88
|
- !ruby/object:Gem::Version
|
89
|
-
version: '
|
89
|
+
version: '3.5'
|
90
90
|
type: :development
|
91
91
|
prerelease: false
|
92
92
|
version_requirements: !ruby/object:Gem::Requirement
|
93
93
|
requirements:
|
94
94
|
- - "~>"
|
95
95
|
- !ruby/object:Gem::Version
|
96
|
-
version: '
|
96
|
+
version: '3.5'
|
97
97
|
- !ruby/object:Gem::Dependency
|
98
|
-
name:
|
98
|
+
name: rubocop
|
99
99
|
requirement: !ruby/object:Gem::Requirement
|
100
100
|
requirements:
|
101
101
|
- - "~>"
|
102
102
|
- !ruby/object:Gem::Version
|
103
|
-
version: '0.
|
103
|
+
version: '0.51'
|
104
104
|
type: :development
|
105
105
|
prerelease: false
|
106
106
|
version_requirements: !ruby/object:Gem::Requirement
|
107
107
|
requirements:
|
108
108
|
- - "~>"
|
109
109
|
- !ruby/object:Gem::Version
|
110
|
-
version: '0.
|
110
|
+
version: '0.51'
|
111
111
|
- !ruby/object:Gem::Dependency
|
112
|
-
name:
|
112
|
+
name: rubocop-rspec
|
113
113
|
requirement: !ruby/object:Gem::Requirement
|
114
114
|
requirements:
|
115
115
|
- - "~>"
|
116
116
|
- !ruby/object:Gem::Version
|
117
|
-
version: '
|
117
|
+
version: '1.20'
|
118
118
|
type: :development
|
119
119
|
prerelease: false
|
120
120
|
version_requirements: !ruby/object:Gem::Requirement
|
121
121
|
requirements:
|
122
122
|
- - "~>"
|
123
123
|
- !ruby/object:Gem::Version
|
124
|
-
version: '
|
124
|
+
version: '1.20'
|
125
125
|
- !ruby/object:Gem::Dependency
|
126
126
|
name: yard
|
127
127
|
requirement: !ruby/object:Gem::Requirement
|
@@ -142,28 +142,28 @@ dependencies:
|
|
142
142
|
requirements:
|
143
143
|
- - "~>"
|
144
144
|
- !ruby/object:Gem::Version
|
145
|
-
version: '0.
|
145
|
+
version: '0.3'
|
146
146
|
type: :runtime
|
147
147
|
prerelease: false
|
148
148
|
version_requirements: !ruby/object:Gem::Requirement
|
149
149
|
requirements:
|
150
150
|
- - "~>"
|
151
151
|
- !ruby/object:Gem::Version
|
152
|
-
version: '0.
|
152
|
+
version: '0.3'
|
153
153
|
- !ruby/object:Gem::Dependency
|
154
154
|
name: thermite
|
155
155
|
requirement: !ruby/object:Gem::Requirement
|
156
156
|
requirements:
|
157
157
|
- - "~>"
|
158
158
|
- !ruby/object:Gem::Version
|
159
|
-
version: '0.
|
159
|
+
version: '0.13'
|
160
160
|
type: :runtime
|
161
161
|
prerelease: false
|
162
162
|
version_requirements: !ruby/object:Gem::Requirement
|
163
163
|
requirements:
|
164
164
|
- - "~>"
|
165
165
|
- !ruby/object:Gem::Version
|
166
|
-
version: '0.
|
166
|
+
version: '0.13'
|
167
167
|
description:
|
168
168
|
email:
|
169
169
|
- nomoon@phoebus.ca
|
@@ -222,7 +222,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
222
222
|
version: '0'
|
223
223
|
requirements: []
|
224
224
|
rubyforge_project:
|
225
|
-
rubygems_version: 2.
|
225
|
+
rubygems_version: 2.7.2
|
226
226
|
signing_key:
|
227
227
|
specification_version: 4
|
228
228
|
summary: Ruby port and extension of Sanscript.js transliterator by learnsanskrit.org
|