fixup: transliterator and spec rewrite.

Gemfile

@@ -4,3 +4,9 @@ gem "unicorn"
 gem "mechanize"
 gem "unicode_utils"
 gem "sinatra"
+
+group :development, :test do
+    gem "rspec"
+    gem "rubocop"
+    gem "pry"
+end

Gemfile.lock

@@ -1,68 +1,133 @@
 GEM
   remote: https://rubygems.org/
   specs:
-    addressable (2.8.0)
-      public_suffix (>= 2.0.2, < 5.0)
-    connection_pool (2.2.5)
-    domain_name (0.5.20190701)
-      unf (>= 0.0.5, < 1.0.0)
+    addressable (2.8.6)
+      public_suffix (>= 2.0.2, < 6.0)
+    ast (2.4.2)
+    base64 (0.2.0)
+    coderay (1.1.3)
+    connection_pool (2.4.1)
+    diff-lcs (1.5.1)
+    domain_name (0.6.20240107)
     http-cookie (1.0.5)
       domain_name (~> 0.5)
+    json (2.7.1)
     kgio (2.11.4)
-    mechanize (2.8.5)
+    language_server-protocol (3.17.0.3)
+    mechanize (2.10.0)
       addressable (~> 2.8)
+      base64
       domain_name (~> 0.5, >= 0.5.20190701)
       http-cookie (~> 1.0, >= 1.0.3)
       mime-types (~> 3.0)
       net-http-digest_auth (~> 1.4, >= 1.4.1)
       net-http-persistent (>= 2.5.2, < 5.0.dev)
+      nkf
       nokogiri (~> 1.11, >= 1.11.2)
       rubyntlm (~> 0.6, >= 0.6.3)
       webrick (~> 1.7)
       webrobots (~> 0.1.2)
-    mime-types (3.4.1)
+    method_source (1.0.0)
+    mime-types (3.5.2)
       mime-types-data (~> 3.2015)
-    mime-types-data (3.2022.0105)
-    mustermann (2.0.2)
+    mime-types-data (3.2024.0206)
+    mustermann (3.0.0)
       ruby2_keywords (~> 0.0.1)
     net-http-digest_auth (1.4.1)
-    net-http-persistent (4.0.1)
+    net-http-persistent (4.0.2)
       connection_pool (~> 2.2)
+    nkf (0.2.0)
+    nokogiri (1.16.2-aarch64-linux)
+      racc (~> 1.4)
+    nokogiri (1.16.2-arm-linux)
+      racc (~> 1.4)
+    nokogiri (1.16.2-arm64-darwin)
+      racc (~> 1.4)
+    nokogiri (1.16.2-x86-linux)
+      racc (~> 1.4)
+    nokogiri (1.16.2-x86_64-darwin)
+      racc (~> 1.4)
     nokogiri (1.16.2-x86_64-linux)
       racc (~> 1.4)
-    public_suffix (4.0.7)
+    parallel (1.24.0)
+    parser (3.3.0.5)
+      ast (~> 2.4.1)
+      racc
+    pry (0.14.2)
+      coderay (~> 1.1)
+      method_source (~> 1.0)
+    public_suffix (5.0.4)
     racc (1.7.3)
-    rack (2.2.6.4)
-    rack-protection (2.2.3)
-      rack
-    raindrops (0.20.0)
+    rack (3.0.9)
+    rack-protection (4.0.0)
+      base64 (>= 0.1.0)
+      rack (>= 3.0.0, < 4)
+    rack-session (2.0.0)
+      rack (>= 3.0.0)
+    rainbow (3.1.1)
+    raindrops (0.20.1)
+    regexp_parser (2.9.0)
+    rexml (3.2.6)
+    rspec (3.13.0)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.0)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.0)
+    rubocop (1.60.2)
+      json (~> 2.3)
+      language_server-protocol (>= 3.17.0)
+      parallel (~> 1.10)
+      parser (>= 3.3.0.2)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 1.8, < 3.0)
+      rexml (>= 3.2.5, < 4.0)
+      rubocop-ast (>= 1.30.0, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 2.4.0, < 3.0)
+    rubocop-ast (1.30.0)
+      parser (>= 3.2.1.0)
+    ruby-progressbar (1.13.0)
     ruby2_keywords (0.0.5)
     rubyntlm (0.6.3)
-    sinatra (2.2.3)
-      mustermann (~> 2.0)
-      rack (~> 2.2)
-      rack-protection (= 2.2.3)
+    sinatra (4.0.0)
+      mustermann (~> 3.0)
+      rack (>= 3.0.0, < 4)
+      rack-protection (= 4.0.0)
+      rack-session (>= 2.0.0, < 3)
       tilt (~> 2.0)
-    tilt (2.1.0)
-    unf (0.1.4)
-      unf_ext
-    unf_ext (0.0.8.2)
+    tilt (2.3.0)
+    unicode-display_width (2.5.0)
     unicode_utils (1.4.0)
     unicorn (6.1.0)
       kgio (~> 2.6)
       raindrops (~> 0.7)
-    webrick (1.7.0)
+    webrick (1.8.1)
     webrobots (0.1.2)
 
 PLATFORMS
+  aarch64-linux
+  arm-linux
+  arm64-darwin
+  x86-linux
+  x86_64-darwin
   x86_64-linux
-  x86_64-linux-musl
 
 DEPENDENCIES
   mechanize
+  pry
+  rspec
+  rubocop
   sinatra
   unicode_utils
   unicorn
 
 BUNDLED WITH
-   2.3.17
+   2.5.3

app.rb

@@ -15,47 +15,47 @@ def searchOTE(phoneNo)
 
   match = greekNo.match phoneNo if match.nil?
 
-  unless match.nil?
-    pageurl = 'https://www.11888.gr'
+  return if match.nil?
 
-    a = Mechanize.new
-    a.user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36'
-    page = a.get(pageurl)
-    cookies = page.header['Set-Cookie']
+  pageurl = 'https://www.11888.gr'
 
-    # Get the CSRF token.
-    tokenRE = /csrftoken=(.*?);/
+  a = Mechanize.new
+  a.user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36'
+  page = a.get(pageurl)
+  cookies = page.header['Set-Cookie']
 
-    csrftoken = '1'
-    csrftokenMatches = tokenRE.match cookies
+  # Get the CSRF token.
+  tokenRE = /csrftoken=(.*?);/
 
-    csrftoken = csrftokenMatches[1] unless csrftokenMatches.nil?
+  csrftoken = '1'
+  csrftokenMatches = tokenRE.match cookies
 
-    a.pre_connect_hooks << lambda do |_agent, request|
-      request['X-Requested-With'] = 'XMLHttpRequest'
-      request['Cookie'] = 'csrftoken=' + csrftoken + ';'
-      request['Accept'] = 'Accept: application/json, text/javascript, */*; q=0.01'
-      request['Referer'] = 'https://www.11888.gr'
-    end
+  csrftoken = csrftokenMatches[1] unless csrftokenMatches.nil?
 
-    pageurl = 'https://www.11888.gr/search/reverse/?phone=' + match[1]
+  a.pre_connect_hooks << lambda do |_agent, request|
+    request['X-Requested-With'] = 'XMLHttpRequest'
+    request['Cookie'] = 'csrftoken=' + csrftoken + ';'
+    request['Accept'] = 'Accept: application/json, text/javascript, */*; q=0.01'
+    request['Referer'] = 'https://www.11888.gr'
+  end
 
-    # Second call for the actual data (returned in JSON)
-    page = a.get(pageurl)
+  pageurl = 'https://www.11888.gr/search/reverse/?phone=' + match[1]
 
-    begin
-      parsed = JSON.parse(page.content)
-      unless parsed['data']['wp'].empty?
-        nameComps = parsed['data']['wp'][0]['name']
-        fullName = "#{nameComps['first'] || ''} #{nameComps['last']}"
-        fullName.strip!
-      end
-    rescue JSON::ParserError
-      fullName = nil
-    end
+  # Second call for the actual data (returned in JSON)
+  page = a.get(pageurl)
 
-    Transliterator.grToLat(fullName).gsub(%r{</?.*?>}, '').gsub(/\n/, ' - ') unless fullName.nil?
+  begin
+    parsed = JSON.parse(page.content)
+    unless parsed['data']['wp'].empty?
+      nameComps = parsed['data']['wp'][0]['name']
+      fullName = "#{nameComps['first'] || ''} #{nameComps['last']}"
+      fullName.strip!
+    end
+  rescue JSON::ParserError
+    fullName = nil
   end
+
+  Transliterator.gr_to_lat(CGI.escapeHTML(fullName)).gsub(%r{</?.*?>}, '').gsub(/\n/, ' - ') unless fullName.nil?
 end
 
 def searchAll(phoneNumber)

transliterator.rb

@@ -2,55 +2,59 @@
 require 'unicode_utils/titlecase'
 
 module Transliterator
-  GreekChars = Array['α', 'β', 'γ', 'δ', 'ε', 'ζ', 'η', 'θ', 'ι', 'κ', 'λ', 'μ', 'ν', 'ξ', 'ο', 'π', 'ρ', 'σ', 'τ', 'υ', 'φ', 'χ', 'ψ', 'ω', 'ς']
-  LatinChars = Array['a', 'v', 'g', 'd', 'e', 'z', 'i', 'th', 'i', 'k', 'l', 'm', 'n', 'x', 'o', 'p', 'r', 's', 't', 'i', 'f', 'ch', 'ps', 'o', 's']
-  SpecChars = Array['ο', 'α', 'ε']
-
-  def self.grToLat(inString)
-    outString = ''
-    inString = UnicodeUtils.downcase(inString)
-
-    specCharFound = nil
-
-    inString.each_char do |ch|
-      if GreekChars.include?(ch)
-
-        if !specCharFound.nil?
-          if specCharFound == 'ο'
-            if ch == 'υ'
-              outString += 'u'
-              specCharFound = nil
-              next
-            end
-          elsif specCharFound == 'α'
-            if ch == 'υ'
-              outString += 'f'
-              specCharFound = nil
-              next
-            elsif ch == 'ι'
-              outString += 'e'
-              specCharFound = nil
-              next
-            end
-          elsif specCharFound == 'ε'
-            if ch == 'υ'
-              outString += 'f'
-              specCharFound = nil
-              next
-            end
-          end
-
-          outString += LatinChars[GreekChars.index(ch)]
-          specCharFound = nil
+  GREEK_TO_LATIN = {
+    # Basic mappings
+    'α' => 'a', 'β' => 'b', 'γ' => 'g', 'δ' => 'd', 'ε' => 'e',
+    'ζ' => 'z', 'η' => 'i', 'θ' => 'th', 'ι' => 'i', 'κ' => 'k',
+    'λ' => 'l', 'μ' => 'm', 'ν' => 'n', 'ξ' => 'x', 'ο' => 'o',
+    'π' => 'p', 'ρ' => 'r', 'σ' => 's', 'τ' => 't', 'υ' => 'y',
+    'φ' => 'f', 'χ' => 'ch', 'ψ' => 'ps', 'ω' => 'o', 'ς' => 's'
+  }.freeze
+  # Special rules for DIPTHONGS followed by specific characters
+  # Including 'ευ' and 'αυ' cases based on the next character
 
+  DIPTHONGS = {
+    'ευ' => { 'default' => 'ef', 'exceptions' => 'ev' },
+    'αυ' => { 'default' => 'af', 'exceptions' => 'av' }
+  }.freeze
+
+  VOWELS = %w[α ε η ι ο υ ω].freeze
+
+  def self.gr_to_lat(in_string) # rubocop:disable Metrics/MethodLength, Metrics/AbcSize, Metrics/CyclomaticComplexity, Metrics/PerceivedComplexity
+    out_string = ''
+    normalized_string = UnicodeUtils.downcase(in_string).unicode_normalize(:nfd).gsub(/[\u0300-\u036f]/, '')
+
+    i = 0
+    while i < normalized_string.length
+      ch = normalized_string[i]
+      next_ch = normalized_string[i + 1] || ''
+
+      # Handle DIPTHONGS
+      diphthong_handled = false
+      DIPTHONGS.each do |diphthong, rules|
+        next unless (ch + next_ch).start_with?(diphthong)
+
+        out_string += if i + 2 < normalized_string.length && VOWELS.include?(normalized_string[i + 2])
+                        rules['exceptions']
+                      else
+                        rules['default']
+                      end
+        i += 2 # Skip the next character as part of diphthong
+        diphthong_handled = true
+        break
+      end
+
+      unless diphthong_handled
+        if GREEK_TO_LATIN[ch]
+          out_string += GREEK_TO_LATIN[ch]
+          i += 1
         else
-          specCharFound = ch if SpecChars.include?(ch)
-          outString += LatinChars[GreekChars.index(ch)]
+          out_string += ch
+          i += 1
         end
-      else
-        outString += ch
       end
     end
-    UnicodeUtils.titlecase(outString)
+
+    UnicodeUtils.titlecase(out_string)
   end
 end