sanscript 0.8.1 → 0.9.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: c50d574983e399ea044b60c2d8ece2a624d561ca
-  data.tar.gz: 7b8b068883034401079c3671f6ca60b9f777d5df
+SHA256:
+  metadata.gz: ef6e9b7e12549b07177b807613493b8bbf5df8dab1d762d6f2cbb5db65c3a710
+  data.tar.gz: 9e02c19c6189ca48c95a74b6448cb5f0a2be25fa5fabea8a39082a52d4a8bb41
 SHA512:
-  metadata.gz: 39a77f3cc096bb673ad499539f7e8bae0e6300c5401c091391b3dd1e3305f8d7ec278d5dd16b19cf8a9ac1e4144bd3f606ff07e5d1028f198b499585bab893e9
-  data.tar.gz: 8b9a1fbe21223ca924c62e83c487cd3ea2be68735cee2207b66970644f6a3a8c307173b8287c916286bcddc1e989867abd775b4a43e4a31b14c36bf2882b29d8
+  metadata.gz: 11f53ad681749ca4aed397e3401f40c9f97ef1e3f654d3f23c9dde407636739817d6af962f9ed09d18a4375021822e5fbbb99b38790b011986e362e2c4758a8f
+  data.tar.gz: 1296c18342ff547c831549e3b17412541a7afe18c471e6f0e1867b1f0bb0c24bc3c00e52a5e0d69241936f3ebb576504dcc5cfea4f8fcfc1f1a4484576578fc2

data/.gitignore

@@ -8,6 +8,7 @@
 /spec/reports/
 /tmp/
 /lib/librusty_sanscript.*
+/lib/rusty_sanscript.*
 /target
 mkmf.log
 Cargo.lock

data/.rubocop.yml

@@ -1,6 +1,5 @@
-require: rubocop-rspec
 AllCops:
-  TargetRubyVersion: 2.3
+  TargetRubyVersion: 2.2
 
 # Metrics
 Metrics/AbcSize:
@@ -17,6 +16,10 @@ Metrics/BlockNesting:
   Enabled: true
   Max: 4
 
+Metrics/BlockLength:
+  Exclude:
+    - spec/**/*.rb
+
 Metrics/ClassLength:
   Description: 'Avoid classes longer than 250 lines of code.'
   Enabled: true
@@ -96,3 +99,12 @@ Style/TrailingCommaInLiteral:
 Style/TrivialAccessors:
   ExactNameMatch: true
   AllowPredicates: true
+
+# RSpec
+require: rubocop-rspec
+
+RSpec/ContextWording:
+  Enabled: false
+
+RSpec/NestedGroups:
+  Max: 3

data/.travis.yml

@@ -1,9 +1,9 @@
 sudo: false
 language: ruby
 rvm:
-  - 2.4.0
-  - 2.3.3
-  - 2.2.6
+  - 2.4.2
+  - 2.3.5
+  - 2.2.8
   - ruby-head
 env:
   - RUST=yes

data/Cargo.toml

@@ -1,13 +1,13 @@
 [package]
 name = "rusty_sanscript"
-version = "0.4.0"
+version = "0.4.1"
 authors = ["Tim Bellefleur <nomoon@phoebus.ca>"]
 publish = false
 
 [dependencies]
-lazy_static = "^0.2.2"
-ruby-sys = "^0.2.17"
-regex = "^0.1.80"
+lazy_static = "^0.2.10"
+ruby-sys = "^0.3.0"
+regex = "^0.2.2"
 
 [lib]
 crate-type = ["cdylib"]

data/Gemfile

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+
 source "https://rubygems.org"
 
 # Specify your gem's dependencies in sanscript.gemspec

data/Rakefile

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+
 require "bundler/gem_tasks"
 
 require "thermite/tasks"

data/lib/sanscript.rb

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+
 require "ragabash"
 
 require "sanscript/version"

data/lib/sanscript/benchmark.rb

@@ -5,7 +5,7 @@ module Sanscript
     require "benchmark/ips"
   rescue LoadError
     #:nocov:
-    module ::Benchmark
+    module ::Benchmark # rubocop:disable Style/ClassAndModuleChildren
       def self.ips(*)
         raise NotImplementedError, "You must install the `benchmark-ips` gem first."
       end
@@ -15,32 +15,32 @@ module Sanscript
 
   # Benchmark/testing module.
   module Benchmark
+    TEST_STRINGS = {
+      brahmic: {
+        devanagari: "नानाशास्त्रसुभाषितामृतरसैः श्रोत्रोत्सवं कुर्वतां येषां यान्ति दिनानि पण्डितजनव्यायामखिन्नात्मनाम् तेषां जन्म च जीवितं च सुकृतं तैर् एव भूर् भूषिता शेषैह् किं पशुवद् विवेकरहितैर् भूभारभूतैर् नरः",
+        malayalam: "നാനാശാസ്ത്രസുഭാഷിതാമൃതരസൈഃ ശ്രോത്രോത്സവം കുര്വതാം യേഷാം യാന്തി ദിനാനി പണ്ഡിതജനവ്യായാമഖിന്നാത്മനാമ് തേഷാം ജന്മ ച ജീവിതം ച സുകൃതം തൈര് ഏവ ഭൂര് ഭൂഷിതാ ശേഷൈഹ് കിം പശുവദ് വിവേകരഹിതൈര് ഭൂഭാരഭൂതൈര് നരഃ",
+      }.freeze,
+      roman: {
+        iast: "nānāśāstrasubhāṣitāmṛtarasaiḥ śrotrotsavaṃ kurvatāṃ yeṣāṃ yānti dināni paṇḍitajanavyāyāmakhinnātmanām teṣāṃ janma ca jīvitaṃ ca sukṛtaṃ tair eva bhūr bhūṣitā śeṣaih kiṃ paśuvad vivekarahitair bhūbhārabhūtair naraḥ",
+        slp1: "nAnASAstrasuBAzitAmftarasEH SrotrotsavaM kurvatAM yezAM yAnti dinAni paRqitajanavyAyAmaKinnAtmanAm tezAM janma ca jIvitaM ca sukftaM tEr eva BUr BUzitA SezEh kiM paSuvad vivekarahitEr BUBAraBUtEr naraH",
+        hk: "nAnAzAstrasubhASitAmRtarasaiH zrotrotsavaM kurvatAM yeSAM yAnti dinAni paNDitajanavyAyAmakhinnAtmanAm teSAM janma ca jIvitaM ca sukRtaM tair eva bhUr bhUSitA zeSaih kiM pazuvad vivekarahitair bhUbhArabhUtair naraH",
+      }.freeze,
+    }.freeze
+
+    TEST_STRINGS_FLAT = TEST_STRINGS.reduce({}) { |a, (_, v)| a.merge(v) }.freeze
+
+    private_constant :TEST_STRINGS, :TEST_STRINGS_FLAT
+
     module_function
 
     # Runs benchmark-ips test on detection methods.
     def detect!(time = 2, warmup = 1)
-      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"
-      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"
-      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"
-      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"
-      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"
-
       ::Benchmark.ips do |x|
         x.config(time: time, warmup: warmup)
-        x.report("Detect Devanagari") do
-          Sanscript::Detect.detect_scheme(deva_string)
-        end
-        x.report("Detect Malayalam") do
-          Sanscript::Detect.detect_scheme(malayalam_string)
-        end
-        x.report("Detect IAST") do
-          Sanscript::Detect.detect_scheme(iast_string)
-        end
-        x.report("Detect SLP1") do
-          Sanscript::Detect.detect_scheme(slp1_string)
-        end
-        x.report("Detect HK") do
-          Sanscript::Detect.detect_scheme(hk_string)
+        TEST_STRINGS_FLAT.each do |scheme, string|
+          x.report("Detect #{scheme}") do
+            Sanscript::Detect.detect_scheme(string)
+          end
         end
         x.compare!
       end
@@ -49,39 +49,13 @@ module Sanscript
 
     # Runs benchmark-ips test on roman-source transliteration methods.
     def transliterate_roman!(time = 2, warmup = 1)
-      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"
-      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"
-      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"
-
       ::Benchmark.ips do |x|
         x.config(time: time, warmup: warmup)
-
-        x.report("IAST==>Devanagari") do
-          Sanscript.transliterate(iast_string, :iast, :devanagari)
-        end
-        x.report("IAST==>SLP1") do
-          Sanscript.transliterate(iast_string, :iast, :slp1)
-        end
-        x.report("IAST==>SLP1") do
-          Sanscript.transliterate(iast_string, :iast, :hk)
-        end
-        x.report("SLP1==>Devanagari") do
-          Sanscript.transliterate(slp1_string, :slp1, :devanagari)
-        end
-        x.report("SLP1==>IAST") do
-          Sanscript.transliterate(slp1_string, :slp1, :iast)
-        end
-        x.report("SLP1==>HK") do
-          Sanscript.transliterate(slp1_string, :slp1, :hk)
-        end
-        x.report("HK==>Devanagari") do
-          Sanscript.transliterate(hk_string, :hk, :devanagari)
-        end
-        x.report("HK==>IAST") do
-          Sanscript.transliterate(hk_string, :hk, :iast)
-        end
-        x.report("HK==>SLP1") do
-          Sanscript.transliterate(hk_string, :hk, :slp1)
+        TEST_STRINGS[:roman].to_a.product(TEST_STRINGS_FLAT.keys).each do |(ak, av), bk|
+          next if ak == bk
+          x.report("#{ak} => #{bk}") do
+            Sanscript.transliterate(av, ak, bk)
+          end
         end
         x.compare!
       end
@@ -90,18 +64,13 @@ module Sanscript
 
     # Runs benchmark-ips test on brahmic-source transliteration methods.
     def transliterate_brahmic!(time = 2, warmup = 1)
-      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"
-
       ::Benchmark.ips do |x|
         x.config(time: time, warmup: warmup)
-        x.report("Devanagari==>IAST") do
-          Sanscript.transliterate(deva_string, :devanagari, :iast)
-        end
-        x.report("Devanagari==>SLP1") do
-          Sanscript.transliterate(deva_string, :devanagari, :slp1)
-        end
-        x.report("Devanagari==>HK") do
-          Sanscript.transliterate(deva_string, :devanagari, :hk)
+        TEST_STRINGS[:brahmic].to_a.product(TEST_STRINGS_FLAT.keys).each do |(ak, av), bk|
+          next if ak == bk
+          x.report("#{ak} => #{bk}") do
+            Sanscript.transliterate(av, ak, bk)
+          end
         end
         x.compare!
       end

data/lib/sanscript/detect.rb

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+
 require "sanscript/detect/constants"
 
 module Sanscript
@@ -6,11 +7,13 @@ module Sanscript
   # Developed from code available @ https://github.com/sanskrit/detect.js
   module Detect
     if Regexp.method_defined?(:match?)
+      # :nocov:
       require "sanscript/detect/ruby24"
       extend Ruby24
     else
       require "sanscript/detect/ruby2x"
       extend Ruby2x
+      # :nocov:
     end
 
     # @!method detect_scheme(text)

data/lib/sanscript/detect/constants.rb

@@ -8,24 +8,14 @@ module Sanscript
     # between Devanagari and Malayalam.
     RE_BRAHMIC_RANGE = /[\u0900-\u0d7f]/
 
-    # Match each individual Brahmic script.
-    RE_BRAHMIC_SCRIPTS = {
-      devanagari: /\p{Devanagari}/,
-      bengali: /\p{Bengali}/,
-      gurmukhi: /\p{Gurmukhi}/,
-      gujarati: /\p{Gujarati}/,
-      oriya: /\p{Oriya}/,
-      tamil: /\p{Tamil}/,
-      telugu: /\p{Telugu}/,
-      kannada: /\p{Kannada}/,
-      malayalam: /\p{Malayalam}/,
-    }.freeze
+    # The order of individual brahmic scripts in 128 character unicode blocks.
+    BRAHMIC_SCRIPTS_ORDER = %i[devanagari bengali gurmukhi gujarati oriya tamil telugu kannada malayalam].freeze
 
     # Match on special Roman characters
-    RE_IAST_OR_KOLKATA_ONLY = /[āīūṛṝḷḹēōṃḥṅñṭḍṇśṣḻ]/i
+    RE_IAST_OR_KOLKATA_ONLY = /[āīūṛṝḷḹēōṃḥṅñṭḍṇśṣḻĀĪŪṚṜḶḸĒŌṂḤṄÑṬḌṆŚṢḺ]|[aiueoAIUEO]\u0304|[rlRL]\u0323\u0304?|[mhtdMHTD]\u0323|[nN][\u0307\u0303\u0323]|[sS][\u0301\u0323]|[lL]\u0331/
 
     # Match on Kolkata-specific Roman characters
-    RE_KOLKATA_ONLY = /[ēō]/i
+    RE_KOLKATA_ONLY = /[ēōĒŌ]|[eoEO]\u0304/
 
     # Match on ITRANS-only
     RE_ITRANS_ONLY = /ee|oo|\^[iI]|RR[iI]|L[iI]|~N|N\^|Ch|chh|JN|sh|Sh|\.a/
@@ -45,7 +35,7 @@ module Sanscript
     # Match ##...## or {#...#} control blocks.
     RE_CONTROL_BLOCK = /(?<!\\)##.*?(?<!\\)##|(?<!\\)\{#.*?(?<!\\)#\}/
 
-    private_constant :RE_BRAHMIC_RANGE, :RE_BRAHMIC_SCRIPTS, :RE_IAST_OR_KOLKATA_ONLY,
+    private_constant :RE_BRAHMIC_RANGE, :BRAHMIC_SCRIPTS_ORDER, :RE_IAST_OR_KOLKATA_ONLY,
                      :RE_KOLKATA_ONLY, :RE_ITRANS_ONLY, :RE_SLP1_ONLY, :RE_VELTHUIS_ONLY,
                      :RE_ITRANS_OR_VELTHUIS_ONLY, :RE_HARVARD_KYOTO, :RE_CONTROL_BLOCK
   end

data/lib/sanscript/detect/ruby24.rb

@@ -14,11 +14,8 @@ module Sanscript
         text = text.to_str.gsub(RE_CONTROL_BLOCK, "")
 
         # Brahmic schemes are all within a specific range of code points.
-        if RE_BRAHMIC_RANGE.match?(text)
-          RE_BRAHMIC_SCRIPTS.each do |script, regex|
-            return script if regex.match?(text)
-          end
-        end
+        brahmic_char = text[RE_BRAHMIC_RANGE]
+        return BRAHMIC_SCRIPTS_ORDER[(brahmic_char.ord - 0x0900) / 0x80] if brahmic_char
 
         # Romanizations
         if RE_IAST_OR_KOLKATA_ONLY.match?(text)

data/lib/sanscript/detect/ruby2x.rb

@@ -15,11 +15,8 @@ module Sanscript
         # rubocop:disable Style/CaseEquality
 
         # Brahmic schemes are all within a specific range of code points.
-        if RE_BRAHMIC_RANGE === text
-          RE_BRAHMIC_SCRIPTS.each do |script, regex|
-            return script if regex === text
-          end
-        end
+        brahmic_char = text[RE_BRAHMIC_RANGE]
+        return BRAHMIC_SCRIPTS_ORDER[(brahmic_char.ord - 0x0900) / 0x80] if brahmic_char
 
         # Romanizations
         if RE_IAST_OR_KOLKATA_ONLY === text

data/lib/sanscript/rust.rb

@@ -1,10 +1,12 @@
 # frozen_string_literal: true
+
 module Sanscript
   module_function
 
   # Attempts to load Rust native extension.
   # @return [bool] whether the extension loaded.
   def rust_load!
+    # :nocov:
     return RUST_AVAILABLE if defined?(RUST_AVAILABLE)
     require "thermite/fiddle"
     Thermite::Fiddle.load_module("init_rusty_sanscript",
@@ -13,6 +15,7 @@ module Sanscript
     defined?(Sanscript::Rust) ? true : false
   rescue Fiddle::DLError
     false
+    # :nocov:
   end
 
   # @return [bool] the enabled status of the Rust extension

data/lib/sanscript/transliterate.rb

@@ -128,7 +128,7 @@ module Sanscript
       add_roman_scheme(:itrans_dravidian, itrans_dravidian)
 
       # ensure deep freeze on alternates
-      @all_alternates.each { |_, scheme| scheme.deep_freeze }
+      @all_alternates.each_value { |alternates| alternates.deep_freeze } # rubocop:disable Style/SymbolProc
     end
 
     # Transliterate from one script to another.
@@ -195,14 +195,14 @@ module Sanscript
               token_lengths.push(f.length)
               token_lengths.concat(alts.map(&:length))
 
-              if group == :vowel_marks || group == :virama
+              if group == :vowel_marks || group == :virama # rubocop:disable MultipleComparison
                 marks[f] = t
                 alts.each { |alt| marks[alt] = t }
               else
                 letters[f] = t
                 alts.each { |alt| letters[alt] = t }
 
-                if group == :consonants || group == :other
+                if group == :consonants || group == :other # rubocop:disable MultipleComparison
                   consonants[f] = t
                   alts.each { |alt| consonants[alt] = t }
                 end
@@ -227,7 +227,7 @@ module Sanscript
       # @param data [String] the string to transliterate
       # @param map [Hash] map data generated from {#make_map}
       # @return [String] the transliterated string
-      def transliterate_roman(data, map, options = {})
+      def transliterate_roman(data, map, options = {}) # rubocop:disable MethodLength, CyclomaticComplexity
         data = data.to_str.chars
         buf = []
         token_buffer = []
@@ -239,7 +239,7 @@ module Sanscript
         until data.empty? && token_buffer.empty?
           # Match all token substrings to our map.
           token = data[0, max_token_length].join("")
-          max_token_length.downto(1) do |j|
+          max_token_length.downto(1) do |j| # rubocop:disable BlockLength
             token = token[0, j] unless j == max_token_length
             if j == 2
               if !control_char && token == "##"
@@ -302,7 +302,7 @@ module Sanscript
       # @param data [String] the string to transliterate
       # @param map [Hash] map data generated from {#make_map}
       # @return [String] the transliterated string
-      def transliterate_brahmic(data, map)
+      def transliterate_brahmic(data, map) # rubocop:disable MethodLength, CyclomaticComplexity
         data = data.to_str.chars
         buf = []
         had_roman_consonant = false

data/lib/sanscript/version.rb

@@ -1,7 +1,8 @@
 # frozen_string_literal: true
+
 module Sanscript
   # The version number
-  VERSION = "0.8.1"
+  VERSION = "0.9.1".freeze
 
   GEM_ROOT = Pathname.new(File.realpath(File.join(__dir__, "..", "..")))
   private_constant :GEM_ROOT

data/sanscript.gemspec

@@ -1,5 +1,6 @@
 # frozen_string_literal: true
 # coding: utf-8
+
 lib = File.expand_path("../lib", __FILE__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require "sanscript/version"
@@ -22,16 +23,16 @@ Gem::Specification.new do |spec|
 
   spec.required_ruby_version = "~> 2.2"
 
+  spec.add_development_dependency "benchmark-ips", "~> 2.7"
   spec.add_development_dependency "bundler", "~> 1.13"
-  spec.add_development_dependency "rake", "~> 12"
-  spec.add_development_dependency "rspec", "~> 3.5"
   spec.add_development_dependency "coveralls", "~> 0.8"
-  spec.add_development_dependency "rubocop", "~> 0.43"
-  spec.add_development_dependency "rubocop-rspec", "~> 1.7"
   spec.add_development_dependency "pry", "~> 0.10"
-  spec.add_development_dependency "benchmark-ips", "~> 2.7"
+  spec.add_development_dependency "rake", "~> 12"
+  spec.add_development_dependency "rspec", "~> 3.5"
+  spec.add_development_dependency "rubocop", "~> 0.51"
+  spec.add_development_dependency "rubocop-rspec", "~> 1.20"
   spec.add_development_dependency "yard", "~> 0.9"
 
-  spec.add_runtime_dependency "ragabash", "~> 0.2"
-  spec.add_runtime_dependency "thermite", "~> 0.7"
+  spec.add_runtime_dependency "ragabash", "~> 0.3"
+  spec.add_runtime_dependency "thermite", "~> 0.13"
 end

data/src/detect/mod.rs

@@ -14,13 +14,13 @@ lazy_static! {
 
   // Match any character in the block of Brahmic scripts
   // between Devanagari and Malayalam.
-  static ref RE_BRAHMIC_RANGE: Regex = Regex::new(r"[\x{0900}-\x{0d7f}]").unwrap();
+  static ref RE_BRAHMIC_RANGE: Regex = Regex::new(r"[\x{0900}-\x{0D7F}]").unwrap();
 
   // Match on special Roman characters
-  static ref RE_IAST_OR_KOLKATA_ONLY: Regex = Regex::new(r"(?i)[āīūṛṝḷḹēōṃḥṅñṭḍṇśṣḻ]").unwrap();
+  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();
 
   // Match on Kolkata-specific Roman characters
-  static ref RE_KOLKATA_ONLY: Regex = Regex::new(r"(?i)[ēō]").unwrap();
+  static ref RE_KOLKATA_ONLY: Regex = Regex::new(r"[ēōĒŌ]|[eoEO]\x{0304}").unwrap();
 
   // Match on ITRANS-only
   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! {
 #[no_mangle]
 pub extern fn detect_scheme(s: &str) -> usize {
   // Clean-up string of control characters.
-  let r_str = &RE_CONTROL_BLOCK.replace_all(
-                &RE_ESCAPED_CONTROL_CHAR.replace_all(s, ""), "");
+  let r_str = &RE_ESCAPED_CONTROL_CHAR.replace_all(s, "");
+  let r_str = &RE_CONTROL_BLOCK.replace_all(r_str, "");
 
   // Brahmic schemes are all within a specific range of code points.
   let brahmic_match = RE_BRAHMIC_RANGE.find(r_str);
   if brahmic_match != None {
     let brahmic_match = brahmic_match.unwrap();
-    let brahmic_codepoint = r_str.chars().nth(brahmic_match.0).unwrap() as usize;
+    let brahmic_codepoint = r_str.chars().nth(brahmic_match.start()).unwrap() as usize;
 
-    if brahmic_codepoint < 0x0980 {
-      return 1; // Devanagari
-    } else if brahmic_codepoint < 0x0A00 {
-      return 2; // Bengali
-    } else if brahmic_codepoint < 0x0A80 {
-      return 3; // Gurmukhi
-    } else if brahmic_codepoint < 0x0B00 {
-      return 4; // Gujarati
-    } else if brahmic_codepoint < 0x0B80 {
-      return 5; // Oriya
-    } else if brahmic_codepoint < 0x0C00 {
-      return 6; // Tamil
-    } else if brahmic_codepoint < 0x0C80 {
-      return 7; // Telugu
-    } else if brahmic_codepoint < 0x0D00 {
-      return 8; // Kannada
-    } else {
-      return 9; // Malayalam
+    return match brahmic_codepoint {
+      0x0900...0x097F => 1, // Devanagari
+      0x0980...0x09FF => 2, // Bengali
+      0x0A00...0x0A7F => 3, // Gurmukhi
+      0x0A80...0x0AFF => 4, // Gujarati
+      0x0B00...0x0B7F => 5, // Oriya
+      0x0B80...0x0BFF => 6, // Tamil
+      0x0C00...0x0C7F => 7, // Telugu
+      0x0C80...0x0CFF => 8, // Kannada
+      0x0D00...0x0D7F => 9, // Malayalam
+      _ => 0
     }
   }
 
   // Romanizations
-  if RE_IAST_OR_KOLKATA_ONLY.is_match(r_str) {
+  return if RE_IAST_OR_KOLKATA_ONLY.is_match(r_str) {
     if RE_KOLKATA_ONLY.is_match(r_str) {
-      return 11; // Kolkata
+      11 // Kolkata
     } else {
-      return 10; // IAST
+      10 // IAST
     }
   } else if RE_ITRANS_ONLY.is_match(r_str) {
-    return 12; // ITRANS
+    12 // ITRANS
   } else if RE_SLP1_ONLY.is_match(r_str) {
-    return 13; // SLP1
+    13 // SLP1
   } else if RE_VELTHUIS_ONLY.is_match(r_str) {
-    return 14; // Velthuis
+    14 // Velthuis
   } else if RE_ITRANS_OR_VELTHUIS_ONLY.is_match(r_str) {
-    return 12; // ITRANS
+    12 // ITRANS
   } else if RE_HARVARD_KYOTO.is_match(r_str) {
-    return 15; // HK
+    15 // HK
+  } else {
+    0 // Unknown
   }
-  return 0; // Unknown
 }

data/src/lib.rs

@@ -4,3 +4,33 @@ extern crate regex;
 
 #[macro_use] mod rb;
 pub mod detect;
+
+#[cfg(test)]
+mod tests {
+    use detect::detect_scheme;
+
+    #[test]
+    fn detect_devanagari() {
+        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);
+    }
+
+    #[test]
+    fn detect_malayalam() {
+        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);
+    }
+
+    #[test]
+    fn detect_iast() {
+        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);
+    }
+
+    #[test]
+    fn detect_slp1() {
+        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);
+    }
+
+    #[test]
+    fn detect_hk() {
+        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);
+    }
+}

metadata

@@ -1,127 +1,127 @@
 --- !ruby/object:Gem::Specification
 name: sanscript
 version: !ruby/object:Gem::Version
-  version: 0.8.1
+  version: 0.9.1
 platform: ruby
 authors:
 - Tim Bellefleur
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-01-10 00:00:00.000000000 Z
+date: 2017-11-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: bundler
+  name: benchmark-ips
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.13'
+        version: '2.7'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.13'
+        version: '2.7'
 - !ruby/object:Gem::Dependency
-  name: rake
+  name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '12'
+        version: '1.13'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '12'
+        version: '1.13'
 - !ruby/object:Gem::Dependency
-  name: rspec
+  name: coveralls
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.5'
+        version: '0.8'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.5'
+        version: '0.8'
 - !ruby/object:Gem::Dependency
-  name: coveralls
+  name: pry
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: '0.10'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: '0.10'
 - !ruby/object:Gem::Dependency
-  name: rubocop
+  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.43'
+        version: '12'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.43'
+        version: '12'
 - !ruby/object:Gem::Dependency
-  name: rubocop-rspec
+  name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.7'
+        version: '3.5'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.7'
+        version: '3.5'
 - !ruby/object:Gem::Dependency
-  name: pry
+  name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.10'
+        version: '0.51'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.10'
+        version: '0.51'
 - !ruby/object:Gem::Dependency
-  name: benchmark-ips
+  name: rubocop-rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.7'
+        version: '1.20'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.7'
+        version: '1.20'
 - !ruby/object:Gem::Dependency
   name: yard
   requirement: !ruby/object:Gem::Requirement
@@ -142,28 +142,28 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.2'
+        version: '0.3'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.2'
+        version: '0.3'
 - !ruby/object:Gem::Dependency
   name: thermite
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.7'
+        version: '0.13'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.7'
+        version: '0.13'
 description: 
 email:
 - nomoon@phoebus.ca
@@ -222,7 +222,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.6.8
+rubygems_version: 2.7.2
 signing_key: 
 specification_version: 4
 summary: Ruby port and extension of Sanscript.js transliterator by learnsanskrit.org