lingo 1.8.3 → 1.8.4

data/lib/lingo/error.rb

@@ -26,7 +26,17 @@
 
 class Lingo
 
-  class LingoError < StandardError; end
+  class LingoError < StandardError
+
+    def class_name
+      klass.name.split('::').last
+    end
+
+    def error(msg = 'An error occurred')
+      "#{msg}: #{err} (#{err.class})"
+    end
+
+  end
 
   class NoWritableStoreError < LingoError
 
@@ -79,7 +89,7 @@ class Lingo
     end
 
     def to_s
-      "An error occured when trying to #{action} `#{file}': #{err} (#{err.class})"
+      error("An error occured when trying to #{action} `#{file}'")
     end
 
   end
@@ -103,7 +113,7 @@ class Lingo
     end
 
     def to_s
-      "Error loading config: #{err}"
+      error("Error loading config")
     end
 
   end
@@ -170,7 +180,21 @@ class Lingo
     end
 
     def to_s
-      "No such #{klass.name.split('::').last} type `#{name}'."
+      "No such #{class_name} type `#{name}'."
+    end
+
+  end
+
+  class LibraryLoadError < LingoError
+
+    attr_reader :klass, :lib, :err
+
+    def initialize(klass, lib, err)
+      @klass, @lib, @err = klass, lib, err
+    end
+
+    def to_s
+      error("#{class_name}: An error occured while trying to load '#{lib}'")
     end
 
   end

data/lib/lingo/language/grammar.rb

@@ -131,16 +131,16 @@ class Lingo
       def test_compound(fstr, infix, bstr, level = 1, tail = false)
         sta, seq, empty = [fstr.length, bstr.length], %w[? ?], [[], [], '']
 
-        if !(blex = @dic.select_with_suffix(bstr)).sort!.empty?
+        if !Lingo.sort!(blex = @dic.select_with_suffix(bstr)).empty?
           # 1. Word w/ suffix
           bform, seq[1] = tail ? bstr : blex.first.form, blex.first.attr
-        elsif tail && !(blex = @dic.select_with_infix(bstr)).sort!.empty?
+        elsif tail && !Lingo.sort!(blex = @dic.select_with_infix(bstr)).empty?
           # 2. Word w/ infix, unless tail part
           bform, seq[1] = bstr, blex.first.attr
         elsif infix == '-'
           blex, bsta, bseq = find_compound(bstr, level + 1, tail)
 
-          if !blex.sort!.empty?
+          if !Lingo.sort!(blex).empty?
             # 3. Compound
             bform, seq[1], sta[1..-1] = blex.first.form, bseq, bsta
           else
@@ -151,13 +151,13 @@ class Lingo
           return empty
         end
 
-        if !(flex = @dic.select_with_infix(fstr)).sort!.empty?
+        if !Lingo.sort!(flex = @dic.select_with_infix(fstr)).empty?
           # 1. Word w/ infix
           fform, seq[0] = fstr, flex.first.attr
         else
           flex, fsta, fseq = find_compound(fstr, level + 1, true)
 
-          if !flex.sort!.empty?
+          if !Lingo.sort!(flex).empty?
             # 2. Compound
             fform, seq[0], sta[0..0] = flex.first.form, fseq, fsta
           elsif infix == '-'
@@ -173,9 +173,9 @@ class Lingo
         }
 
         flex.concat(blex).delete_if { |l| l.attr == LA_COMPOUND }.
-          push(Lexical.new(fform + infix + bform, LA_COMPOUND)).sort!
+          push(Lexical.new(fform + infix + bform, LA_COMPOUND))
 
-        [flex, sta, seq.join]
+        [Lingo.sort!(flex), sta, seq.join]
       end
 
     end

data/lib/lingo/language/word.rb

@@ -73,7 +73,7 @@ class Lingo
 
       def lexicals=(lex)
         if lex.is_a?(Array)
-          @lexicals = lex.sort.uniq
+          @lexicals = Lingo.sort(lex).uniq
         else
           raise TypeError, "wrong argument type #{lex.class} (expected Array)"
         end
@@ -82,7 +82,7 @@ class Lingo
       def add_lexicals(lex)
         unless lex.empty?
           @lexicals.concat(lex).uniq!
-          @lexicals.sort!
+          Lingo.sort!(@lexicals)
         end
       end
 
@@ -122,6 +122,10 @@ class Lingo
         attr == WA_COMPOUND && get_class('x+').empty?
       end
 
+      def multiword_size(wc_re = LA_MULTIWORD)
+        lex = get_class(wc_re).first and lex.form.count(' ') + 1
+      end
+
       def <<(*other)
         other.flatten!
         lexicals.concat(other)

data/lib/lingo/language/word_form.rb

@@ -38,7 +38,7 @@ class Lingo
 
       attr_accessor :form, :attr, :src
 
-      def initialize(form, attr = '-', src = nil)
+      def initialize(form, attr = WA_UNSET, src = nil)
         @form, @attr, @src = form || '', attr || '', src
       end
 

data/lib/lingo/show_progress.rb

@@ -28,7 +28,7 @@ class Lingo
 
   class ShowProgress
 
-    def initialize(obj, max, name = nil, doit = true, text = 'progress')
+    def initialize(obj, max, name = nil, doit = true, text = 'progress', nl = true)
       return yield self unless max && doit
 
       @out = obj.instance_variable_get(:@lingo).config.stderr
@@ -53,7 +53,8 @@ class Lingo
 
       yield self
 
-      print "#{@clr} done.\n"
+      print "#{@clr} done."
+      print "\n" if nl
     end
 
     def [](value)

data/lib/lingo/srv.rb

@@ -24,7 +24,6 @@
 ###############################################################################
 #++
 
-require 'json'
 require_relative 'app'
 
 class Lingo
@@ -44,14 +43,24 @@ class Lingo
     post('/') { doit }
 
     def doit
-      q = params[:q]
-      r = LINGO.talk(q) if q && !q.empty?
+      to_json(q = params[:q], case q
+        when String then talk(q)
+        when Array  then q.inject({}) { |h, k| h[k] = talk(k); h }
+      end)
+    end
+
+    def talk(q)
+      r = LINGO.talk(q) unless q.empty?
+      return r unless r && SRC_SEP
 
-      r = r.inject(Hash.new { |h, k| h[k] = [] }) { |h, s|
+      r.inject(Hash.new { |h, k| h[k] = [] }) { |h, s|
         a, b = s.split(SRC_SEP, 2); h[b] << a; h
-      } if r && SRC_SEP
+      }
+    end
 
-      to_json(q, r)
+    if ENV['LINGO_NO_SORT']
+      alias_method :_talk, :talk
+      def talk(q) _talk(q).to_a end
     end
 
   end

data/lib/lingo/srv/lingosrv.cfg

@@ -7,7 +7,7 @@ meeting:
     - word_searcher: { source: sys-dic, mode: first }
     - decomposer:    { source: sys-dic }
     - multi_worder:  { source: sys-mul }
-    - sequencer:     { stopper: PUNC,OTHR }
+    - sequencer:     { stopper: 'PUNC,OTHR' }
     - synonymer:     { skip: '?,t', source: sys-syn }
 
     - vector_filter: { debug: 'true', prompt: '' }

data/lib/lingo/version.rb

@@ -4,7 +4,7 @@ class Lingo
 
     MAJOR = 1
     MINOR = 8
-    TINY  = 3
+    TINY  = 4
 
     class << self
 

data/lib/lingo/web.rb

@@ -24,8 +24,8 @@
 ###############################################################################
 #++
 
-require 'json'
-require 'nuggets/util/ruby'
+require 'strscan'
+require 'nuggets/ruby'
 
 require_relative 'app'
 
@@ -35,7 +35,7 @@ class Lingo
 
     init_app(__FILE__)
 
-    UILANGS, LANGS = %w[en de], Lingo.list(:lang).map! { |lang|
+    HL, L = %w[en de ru], Lingo.list(:lang).map! { |lang|
       lang[%r{.*/(\w+)\.}, 1]
     }.uniq.sort!
 
@@ -50,15 +50,45 @@ class Lingo
 
     LINGO = Hash.new { |h, k| h[k] = Lingo.call(cfg, ['-l', k]) }
 
+    CFG, s = '', StringScanner.new('')
+    c = lambda { |n| %Q{<span style="color:#{n}">#{s.matched}</span>} }
+
+    File.foreach(cfg) { |line|
+      s.string = line.chomp
+
+      until s.eos?
+        CFG << if s.scan(/\s+/)   then c[:black]
+        elsif s.scan(/---|[{}:]/) then c[:purple]
+        elsif s.scan(/-/)         then c[:olive]
+        elsif s.scan(/,/)         then c[:black]
+        elsif s.scan(/[\w-]+/)    then c[s.peek(1) == ':' ? :teal : :black]
+        elsif s.scan(/'.*?'/)     then c[:maroon]
+        elsif s.scan(/"/)
+          buf = c[:maroon]
+
+          until s.scan(/"/)
+            buf << (s.scan(/\\\w/) ? c[:purple] : (s.scan(/./); c[:maroon]))
+          end
+
+          buf << c[:maroon]
+        else s.rest
+        end
+      end
+
+      CFG << "\n"
+    }
+
     before do
-      @uilang = if hal = env['HTTP_ACCEPT_LANGUAGE']
-        hals = hal.split(',').map { |l| l.split('-').first.strip }
-        (hals & UILANGS).first
-      end || UILANGS.first
+      @hl = if v = params[:hl] || cookies[:hl] || env['HTTP_ACCEPT_LANGUAGE']
+        v = v.split(',').map { |l| l.split('-').first.strip }
+        (v & HL).first
+      end || HL.first
+
+      cookies[:hl] = @hl unless cookies[:hl] == @hl
 
       @q = params[:q]
-      @l = params[:l] || @uilang
-      @l = LANGS.first unless LANGS.include?(@l)
+      @l = params[:l] || @hl
+      @l = L.first unless L.include?(@l)
     end
 
     get('')   { redirect url_for('/') }
@@ -71,7 +101,7 @@ class Lingo
       end
 
       def t(*t)
-        (i = UILANGS.index(@uilang)) && t[i] || t.first
+        (i = HL.index(@hl)) && t[i] || t.first
       end
     end
 

data/lib/lingo/web/lingoweb.cfg

@@ -7,7 +7,7 @@ meeting:
     - word_searcher: { source: sys-dic, mode: first }
     - decomposer:    { source: sys-dic }
     - multi_worder:  { source: sys-mul }
-    - sequencer:     { stopper: PUNC,OTHR }
+    - sequencer:     { stopper: 'PUNC,OTHR' }
     - synonymer:     { skip: '?,t', source: sys-syn }
 
     - vector_filter: { debug: 'true', prompt: '' }

data/lib/lingo/web/public/lingoweb.css

@@ -1,5 +1,6 @@
 html, body {
   margin-top:       0;
+  font-size:        90%;
 }
 
 a img {
@@ -22,16 +23,18 @@ textarea {
 }
 
 #welcome {
-  font-size:        70%;
+  font-size:        85%;
   color:            #333333;
   margin-bottom:    0.5em;
   text-align:       center;
+  margin:           0 15%;
 }
 
-#legend {
-  font-size:        75%;
+#legend, #config {
   color:            #333333;
   margin-bottom:    0.5em;
+  width:            50%;
+  float:            left;
 }
 
 #legend table {
@@ -39,13 +42,13 @@ textarea {
 }
 
 #legend th {
-  font-size:        110%;
   font-weight:      normal;
   font-family:      monospace;
   text-align:       left;
 }
 
 #legend td {
+  font-size:        85%;
   padding-left:     1em;
 }
 

data/lib/lingo/web/views/index.erb

@@ -4,7 +4,7 @@
 <html xmlns="http://www.w3.org/1999/xhtml">
 <head>
   <meta http-equiv="content-type" content="application/xhtml+xml; charset=utf-8" />
-  <title>Lingo Web - <%= t 'Automatic indexing online', 'Automatische Indexierung Online' %></title>
+  <title>Lingo Web - <%= t 'Automatic indexing online', 'Automatische Indexierung Online', 'Автоматическая обработка текстов онлайн' %></title>
   <link rel="stylesheet" type="text/css" href="<%= url_for '/lingoweb.css' %>" />
 </head>
 <body>
@@ -13,34 +13,45 @@
   </div>
 
   <div id="welcome">
-    <strong><%= t 'Welcome to Lingo Web!', 'Willkommen bei Lingo Web!' %></strong>
-    <%= t %q{
-      Lingo Web provides the opportunity to test the functionality of
-      <a href="http://lex-lingo.de">Lingo</a>.<br />
-      Lingo is an open source indexing system for research and teaching.
-    }, %q{
-      Lingo Web bietet die Möglichkeit, die Funktionsweise von
-      <a href="http://lex-lingo.de">Lingo</a> zu testen.<br />
-      Lingo ist ein frei verfügbares System zur linguistisch und statistisch
-      basierten automatischen Indexierung des Deutschen und Englischen.
+    <strong><%= t 'Welcome to Lingo Web!', 'Willkommen bei Lingo Web!', 'Добро пожаловать в Lingo Web!' %></strong>
+    <%= t %Q{
+      <a href="http://lex-lingo.de">Lingo</a> is an open source indexing system
+      based on<br />linguistic and statistic analysis that currently offers
+      support for <a href="#{url_for '/?l=de'}">German</a>,
+      <a href="#{url_for '/?l=en'}">English</a>, and
+      <a href="#{url_for '/?l=ru'}">Russian</a>.
+    }, %Q{
+      <a href="http://lex-lingo.de">Lingo</a> ist ein frei verfügbares System
+      zur linguistisch und statistisch<br />basierten automatischen Indexierung
+      und bringt aktuell Unterstützung für
+      <a href="#{url_for '/?l=de'}">Deutsch</a>,
+      <a href="#{url_for '/?l=en'}">Englisch</a> und
+      <a href="#{url_for '/?l=ru'}">Russisch</a> mit.
+    }, %Q{
+      <a href="http://lex-lingo.de">Lingo</a> – бесплатное программное обеспечение
+      для автоматической обработки текстов (АОТ) на естественном языке, как
+      лингвистической, так и статистической. Lingo может обрабатывать тексты на
+      <a href="#{url_for '/?l=de'}">английском</a>,
+      <a href="#{url_for '/?l=en'}">немецком</a> и
+      <a href="#{url_for '/?l=ru'}">русском</a> языке.
     } %>
   </div>
 
   <div id="main">
     <form action="<%= url_for '/' %>" method="post">
       <div>
-        <fieldset><legend><strong><%= t 'Input', 'Eingabe' %></strong></legend>
+        <fieldset><legend><strong><%= t 'Input', 'Eingabe', 'ввод данных' %></strong></legend>
           <textarea name="q" rows="20" cols="50"><%= @q %></textarea>
         </fieldset>
 
-        <fieldset><legend><strong><%= t 'Output', 'Ausgabe' %></strong></legend>
+        <fieldset><legend><strong><%= t 'Output', 'Ausgabe', 'вывод данных' %></strong></legend>
           <textarea readonly="readonly" rows="20" cols="50"><%= @r %></textarea>
         </fieldset>
 
         <br />
 
-        <strong><%= t 'Language', 'Sprache' %></strong> = <select name="l">
-        <% for l in LANGS %>
+        <strong><%= t 'Language', 'Sprache', 'язык' %></strong> = <select name="l">
+        <% for l in L %>
           <option value="<%= l %>"<%= ' selected="selected"' if l == @l %>><%= l %></option>
         <% end %>
         </select>
@@ -48,9 +59,9 @@
         <br />
         <br />
 
-        <input type="submit" value="<%= t 'Start processing...', 'Verarbeitung starten...' %>"></input> |
-        <input type="reset" value="<%= t 'Reset form', 'Formular zurücksetzen' %>"></input> |
-        <a href="<%= url_for '/' %>"><%= t 'New request', 'Neue Anfrage' %></a>
+        <input type="submit" value="<%= t 'Start processing...', 'Verarbeitung starten...', 'начать обработку...' %>"></input> |
+        <input type="reset" value="<%= t 'Reset form', 'Formular zurücksetzen', 'очистить формуляр' %>"></input> |
+        <a href="<%= url_for '/' %>"><%= t 'New request', 'Neue Anfrage', 'новый запрос' %></a>
       </div>
     </form>
 
@@ -58,31 +69,78 @@
   </div>
 
   <div id="legend">
-    <strong><%= t 'Legend', 'Legende' %></strong>:
+    <strong><%= t 'Legend', 'Legende', 'Сокращения' %></strong>:
     <table>
-      <tr><th>s       </th><td><%= t 'Noun',                                                    'Substantiv' %></td></tr>
-      <tr><th>a       </th><td><%= t 'Adjective',                                               'Adjektiv' %></td></tr>
-      <tr><th>v       </th><td><%= t 'Verb',                                                    'Verb' %></td></tr>
-      <tr><th>e       </th><td><%= t 'Proper name',                                             'Eigenname' %></td></tr>
-      <tr><th>w       </th><td><%= t 'Word class without suffixes',                             'Wortklasse ohne Suffixe' %></td></tr>
-      <tr><th>t       </th><td><%= t 'Word class without suffixes (e.g. high frequency terms)', 'Wortklasse ohne Suffixe (z.B. Hochfrequenzterme)' %></td></tr>
-      <tr><th>y       </th><td><%= t 'Synonym',                                                 'Synonym' %></td></tr>
-      <tr><th>q (=SEQ)</th><td><%= t 'Sequence (algorithmically identified phrase)',            'Sequenz (algorithmisch erkannter Mehrwortbegriff)' %></td></tr>
-      <tr><th>m (=MUL)</th><td><%= t 'Phrase',                                                  'Mehrwortbegriff' %></td></tr>
-      <tr><th>k (=KOM)</th><td><%= t 'Compound',                                                'Kompositum' %></td></tr>
-      <tr><th>+       </th><td><%= t 'Part of a compound',                                      'Kompositum-Bestandteil' %></td></tr>
-      <tr><th>x+      </th><td><%= t 'Unknown part of a hyphenated compound',                   'unbekannter Kompositum-Bestandteil einer Bindestrich-Konstruktion' %></td></tr>
-      <tr><th>?       </th><td><%= t 'Unknown word',                                            'unbekanntes Wort' %></td></tr>
-      <tr><th>MU?     </th><td><%= t 'Part of a phrase (unknown word)',                         'Mehrwortbestandteil (unbekanntes Wort)' %></td></tr>
-      <tr><th>HELP    </th><td><%= t 'e.g. Special characters',                                 'z.B. unbekanntes Sonderzeichen' %></td></tr>
-      <tr><th>ABRV    </th><td><%= t 'Possible abbreviation with a full stop in the middle',    'mögliche Abk. mit eingeschlossenem Punkt (z.B. "Ausst.Kat")' %></td></tr>
-      <tr><th>PUNC    </th><td><%= t 'Punctuation etc.',                                        'Satzzeichen etc.' %></td></tr>
-      <tr><th>OTHR    </th><td><%= t 'Other character',                                         'Sonstiges Zeichen' %></td></tr>
-      <tr><th>URLS    </th><td><%= t 'URL',                                                     'URL' %></td></tr>
-      <tr><th>NUMS    </th><td><%= t 'Number',                                                  'Zahl' %></td></tr>
+      <tr><th>s       </th><td><%= t 'Noun',
+                                     'Substantiv',
+                                     'существительное' %></td></tr>
+      <tr><th>a       </th><td><%= t 'Adjective',
+                                     'Adjektiv',
+                                     'прилагательное' %></td></tr>
+      <tr><th>v       </th><td><%= t 'Verb',
+                                     'Verb',
+                                     'глагол' %></td></tr>
+      <tr><th>e       </th><td><%= t 'Proper name',
+                                     'Eigenname',
+                                     'имя собственное' %></td></tr>
+      <tr><th>w       </th><td><%= t 'Word class without suffixes',
+                                     'Wortklasse ohne Suffixe',
+                                     'бесфлективная часть речи' %></td></tr>
+      <tr><th>t       </th><td><%= t 'Word class without suffixes (e.g. high frequency terms)',
+                                     'Wortklasse ohne Suffixe (z.B. Hochfrequenzterme)',
+                                     'бесфлективная часть речи (н-р  высокочастотные термины)' %></td></tr>
+      <tr><th>y       </th><td><%= t 'Synonym',
+                                     'Synonym',
+                                     'синоним' %></td></tr>
+      <tr><th>q (=SEQ)</th><td><%= t 'Sequence (algorithmically identified phrase)',
+                                     'Sequenz (algorithmisch erkannter Mehrwortbegriff)',
+                                     'сочетание (составная лексема, алгоритмически выделяемая)' %></td></tr>
+      <tr><th>m (=MUL)</th><td><%= t 'Phrase',
+                                     'Mehrwortbegriff',
+                                     'составная лексема' %></td></tr>
+      <tr><th>k (=KOM)</th><td><%= t 'Compound',
+                                     'Kompositum',
+                                     'сложное слово' %></td></tr>
+      <tr><th>+       </th><td><%= t 'Part of a compound',
+                                     'Kompositum-Bestandteil',
+                                     'компонент сложного слова' %></td></tr>
+      <tr><th>x+      </th><td><%= t 'Unknown part of a hyphenated compound',
+                                     'unbekannter Kompositum-Bestandteil einer Bindestrich-Konstruktion',
+                                     'неизвестный компонент сложного слова, пишущегося через дефис' %></td></tr>
+      <tr><th>?       </th><td><%= t 'Unknown word',
+                                     'unbekanntes Wort',
+                                     'неизвестное слово' %></td></tr>
+      <tr><th>MU?     </th><td><%= t 'Part of a phrase (unknown word)',
+                                     'Mehrwortbestandteil (unbekanntes Wort)',
+                                     'часть составной лексемы (неизвестное слово)' %></td></tr>
+      <tr><th>HELP    </th><td><%= t 'e.g. Special characters',
+                                     'z.B. unbekanntes Sonderzeichen',
+                                     'н-р, неизвестный спецсимвол' %></td></tr>
+      <tr><th>ABRV    </th><td><%= t 'Possible abbreviation with a full stop in the middle',
+                                     'mögliche Abk. mit eingeschlossenem Punkt (z.B. "Ausst.Kat")',
+                                     'возможное сокращение с точкой внутри' %></td></tr>
+      <tr><th>PUNC    </th><td><%= t 'Punctuation etc.',
+                                     'Satzzeichen etc.',
+                                     'знак пунктуации' %></td></tr>
+      <tr><th>OTHR    </th><td><%= t 'Other character',
+                                     'Sonstiges Zeichen',
+                                     'прочие знаки' %></td></tr>
+      <tr><th>URLS    </th><td><%= t 'URL',
+                                     'URL',
+                                     'URL' %></td></tr>
+      <tr><th>NUMS    </th><td><%= t 'Number',
+                                     'Zahl',
+                                     'числительное' %></td></tr>
     </table>
   </div>
 
+  <div id="config">
+    <strong><%= t 'Configuration', 'Konfiguration', 'конфигурация' %></strong>:
+    <pre><%= CFG %></pre>
+  </div>
+
+  <br style="clear: both" />
+
   <div id="footer">
     <em>powered by</em> <a href="http://lex-lingo.de">Lingo</a>
     <em>and</em> <a href="http://www.sinatrarb.com">Sinatra</a>