experteer-gettext 2.0.4

data/lib/gettext/parser/glade.rb

@@ -0,0 +1,100 @@
+=begin
+  parser/glade.rb - parser for Glade-2
+
+  Copyright (C) 2004,2005  Masao Mutoh
+ 
+  You may redistribute it and/or modify it under the same
+  license terms as Ruby.
+
+  $Id: glade.rb,v 1.5 2006/06/11 15:36:20 mutoh Exp $
+=end
+
+require 'cgi'
+require 'gettext'
+
+module GetText
+  module GladeParser
+    extend GetText
+    extend self
+    
+    bindtextdomain("rgettext")
+
+    TARGET1 = /<property.*translatable="yes">(.*)/
+    TARGET2 = /(.*)<\/property>/
+
+    def parse(file, targets = []) # :nodoc: 
+      lines = IO.readlines(file)
+      parse_lines(file, lines, targets)
+    end
+
+    #from ary of lines.
+    def parse_lines(file, lines, targets) # :nodoc:
+      cnt = 0
+      target = false
+      line_no = 0
+      val = nil
+      
+      loop do 
+        line = lines.shift
+        break unless line
+        
+        cnt += 1
+        if TARGET1 =~ line
+          line_no = cnt
+          val = $1 + "\n"
+          target = true
+          if TARGET2 =~ $1
+            val = $1
+            add_target(val, file, line_no, targets)
+            val = nil
+            target = false
+          end
+        elsif target
+          if TARGET2 =~ line
+            val << $1
+            add_target(val, file, line_no, targets)
+            val = nil
+            target = false
+          else
+            val << line
+          end
+        end
+      end
+      targets
+    end
+
+    XML_RE = /<\?xml/ 
+    GLADE_RE = /glade-2.0.dtd/
+ 
+    def target?(file) # :nodoc:
+      data = IO.readlines(file)
+      if XML_RE =~ data[0] and GLADE_RE =~ data[1]
+	true
+      else
+	if File.extname(file) == '.glade'
+	  raise _("`%{file}' is not glade-2.0 format.") % {:file => file}
+	end
+	false
+      end
+    end
+
+    def add_target(val, file, line_no, targets) # :nodoc:
+      return unless val.size > 0
+      assoc_data = targets.assoc(val)
+      val = CGI.unescapeHTML(val)
+      if assoc_data 
+        targets[targets.index(assoc_data)] = assoc_data << "#{file}:#{line_no}"
+      else
+        targets << [val.gsub(/\n/, '\n'), "#{file}:#{line_no}"]
+      end
+      targets
+    end
+  end
+end
+
+if __FILE__ == $0
+  # ex) ruby glade.rb foo.glade  bar.glade
+  ARGV.each do |file|
+    p GetText::GladeParser.parse(file)
+  end
+end

data/lib/gettext/parser/ruby.rb

@@ -0,0 +1,193 @@
+#!/usr/bin/ruby
+=begin
+  parser/ruby.rb - parser for ruby script
+
+  Copyright (C) 2003-2005  Masao Mutoh
+  Copyright (C) 2005       speakillof
+  Copyright (C) 2001,2002  Yasushi Shoji, Masao Mutoh
+ 
+  You may redistribute it and/or modify it under the same
+  license terms as Ruby.
+
+  $Id: ruby.rb,v 1.13 2008/12/01 14:30:30 mutoh Exp $
+=end
+
+require 'irb/ruby-lex.rb'
+require 'stringio'
+require 'gettext/translation_target.rb'
+
+class RubyLexX < RubyLex  # :nodoc: all
+  # Parser#parse resemlbes RubyLex#lex
+  def parse
+    until (  (tk = token).kind_of?(RubyToken::TkEND_OF_SCRIPT) && !@continue or tk.nil?  )
+      s = get_readed
+      if RubyToken::TkSTRING === tk
+        def tk.value
+          @value 
+        end
+        
+        def tk.value=(s)
+          @value = s
+        end
+        
+        if @here_header
+          s = s.sub(/\A.*?\n/, '').sub(/^.*\n\Z/, '')
+        else
+          begin
+            s = eval(s)
+          rescue Exception
+            # Do nothing.
+          end
+        end
+        
+        tk.value = s
+      end
+      
+      if $DEBUG
+        if tk.is_a? TkSTRING
+          $stderr.puts("#{tk}: #{tk.value}")
+        elsif tk.is_a? TkIDENTIFIER
+          $stderr.puts("#{tk}: #{tk.name}")
+        else
+          $stderr.puts(tk)
+        end
+      end
+      
+      yield tk
+    end
+    return nil
+  end
+
+  # Original parser does not keep the content of the comments,
+  # so monkey patching this with new token type and extended
+  # identify_comment implementation
+  RubyToken.def_token :TkCOMMENT_WITH_CONTENT, TkVal
+
+  def identify_comment
+    @ltype = "#"
+    get_readed # skip the hash sign itself
+
+    while ch = getc
+      if ch == "\n"
+        @ltype = nil
+        ungetc
+        break
+      end
+    end
+    return Token(TkCOMMENT_WITH_CONTENT, get_readed)
+  end
+
+end
+
+module GetText
+  module RubyParser
+    extend self
+    
+    ID = ['gettext', '_', 'N_', 'sgettext', 's_']
+    PLURAL_ID = ['ngettext', 'n_', 'Nn_', 'ns_', 'nsgettext']
+    MSGCTXT_ID = ['pgettext', 'p_']
+    MSGCTXT_PLURAL_ID = ['npgettext', 'np_']
+
+    def parse(file, targets = [])  # :nodoc:
+      lines = IO.readlines(file)
+      parse_lines(file, lines, targets)
+    end
+
+    def parse_lines(file_name, lines, targets)  # :nodoc:
+      file = StringIO.new(lines.join + "\n")
+      rl = RubyLexX.new
+      rl.set_input(file)
+      rl.skip_space = true
+      #rl.readed_auto_clean_up = true
+
+      target = nil
+      line_no = nil
+      last_extracted_comment = ''
+      reset_extracted_comment = false
+      rl.parse do |tk|
+        begin
+          case tk
+          when RubyToken::TkIDENTIFIER, RubyToken::TkCONSTANT
+            if ID.include?(tk.name)
+              target = TranslationTarget.new(:normal)
+            elsif PLURAL_ID.include?(tk.name)
+              target = TranslationTarget.new(:plural)
+            elsif MSGCTXT_ID.include?(tk.name)
+              target = TranslationTarget.new(:msgctxt)
+            elsif MSGCTXT_PLURAL_ID.include?(tk.name)
+              target = TranslationTarget.new(:msgctxt_plural)
+            else
+              target = nil
+            end
+            line_no = tk.line_no.to_s
+          when RubyToken::TkSTRING
+            target.set_current_attribute tk.value if target
+          when RubyToken::TkPLUS, RubyToken::TkNL
+            #do nothing
+          when RubyToken::TkCOMMA
+            target.advance_to_next_attribute if target
+          else
+            if target && target.msgid
+              existing=targets.find {|t| t.matches?(target)}
+              existing=targets.index(existing) if existing
+              if existing
+                target = targets[existing].merge(target)
+                targets[existing] = target
+              else
+                targets << target
+              end
+              target.occurrences << file_name + ":" + line_no
+              target.add_extracted_comment last_extracted_comment unless last_extracted_comment.empty?
+              target = nil
+            end
+          end
+        rescue
+          $stderr.print "\n\nError"
+          $stderr.print " parsing #{file_name}:#{tk.line_no}\n\t #{lines[tk.line_no - 1]}" if tk
+          $stderr.print "\n #{$!.inspect} in\n"
+          $stderr.print $!.backtrace.join("\n")
+          $stderr.print "\n"
+          exit 1
+        end
+
+        case tk 
+        when RubyToken::TkCOMMENT_WITH_CONTENT
+          last_extracted_comment = "" if reset_extracted_comment
+          if last_extracted_comment.empty?
+            # new comment from programmer to translator?
+            comment1 = tk.value.lstrip
+            if comment1 =~ /^TRANSLATORS\:/
+              last_extracted_comment += $'
+            end
+          else
+            last_extracted_comment += "\n" 
+            last_extracted_comment += tk.value
+          end
+          reset_extracted_comment = false
+        when RubyToken::TkNL
+        else
+          reset_extracted_comment = true
+        end
+      end
+      targets
+    end
+
+    def target?(file)  # :nodoc:
+      true # always true, as default parser.
+    end
+  end 
+end
+
+
+
+if __FILE__ == $0
+  require 'pp'
+  ARGV.each do |file|
+    pp GetText::RubyParser.parse(file)
+  end
+  
+  #rl = RubyLexX.new; rl.set_input(ARGF)  
+  #rl.parse do |tk|
+    #p tk
+  #end  
+end

data/lib/gettext/poparser.rb

@@ -0,0 +1,355 @@
+=begin
+  poparser.rb - Generate a .mo
+
+  Copyright (C) 2003-2009 Masao Mutoh <mutomasa at gmail.com>
+
+  You may redistribute it and/or modify it under the same
+  license terms as Ruby.
+=end
+
+#
+# DO NOT MODIFY!!!!
+# This file is automatically generated by Racc 1.4.6
+# from Racc grammer file "".
+#
+
+require 'racc/parser.rb'
+module GetText
+  class PoParser < Racc::Parser
+
+module_eval(<<'...end poparser.ry/module_eval...', 'poparser.ry', 108)
+  include GetText
+  GetText.bindtextdomain("rgettext")
+
+  def unescape(orig)
+    ret = orig.gsub(/\\n/, "\n")
+    ret.gsub!(/\\t/, "\t")
+    ret.gsub!(/\\r/, "\r")
+    ret.gsub!(/\\"/, "\"")
+    ret
+  end
+  
+  def parse(str, data, ignore_fuzzy = true)
+    @comments = []
+    @data = data
+    @fuzzy = false
+    @msgctxt = ""
+    $ignore_fuzzy = ignore_fuzzy
+
+    str.strip!
+    @q = []
+    until str.empty? do
+      case str
+      when /\A\s+/
+	str = $'
+      when /\Amsgctxt/
+	@q.push [:MSGCTXT, $&]
+	str = $'
+      when /\Amsgid_plural/
+	@q.push [:MSGID_PLURAL, $&]
+	str = $'
+      when /\Amsgid/
+	@q.push [:MSGID, $&]
+	str = $'
+      when /\Amsgstr/
+	@q.push [:MSGSTR, $&]
+	str = $'
+      when /\A\[(\d+)\]/
+	@q.push [:PLURAL_NUM, $1]
+	str = $'
+      when /\A\#~(.*)/
+	$stderr.print _("Warning: obsolete msgid exists.\n")
+	$stderr.print "         #{$&}\n"
+	@q.push [:COMMENT, $&]
+	str = $'
+      when /\A\#(.*)/
+	@q.push [:COMMENT, $&]
+	str = $'      
+      when /\A\"(.*)\"/
+	@q.push [:STRING, $1]
+	str = $'
+      else
+	#c = str[0,1]
+	#@q.push [:STRING, c]
+	str = str[1..-1]
+      end
+    end 
+    @q.push [false, '$end']
+    if $DEBUG
+      @q.each do |a,b|
+      puts "[#{a}, #{b}]"
+      end
+    end
+    @yydebug = true if $DEBUG
+    do_parse
+
+    if @comments.size > 0
+      @data.set_comment(:last, @comments.join("\n"))
+    end
+    @data
+  end
+  
+  def next_token
+    @q.shift
+  end
+
+  def on_message(msgid, msgstr)
+    if msgstr.size > 0
+      @data[msgid] = msgstr
+      @data.set_comment(msgid, @comments.join("\n"))
+    end
+    @comments.clear
+    @msgctxt = ""
+  end
+      
+  def on_comment(comment)
+    @fuzzy = true if (/fuzzy/ =~ comment)
+    @comments << comment
+  end 
+
+  def parse_file(po_file, data, ignore_fuzzy = true)
+    args = [ po_file ]
+    # In Ruby 1.9, we must detect proper encoding of a PO file.
+    if String.instance_methods.include?(:encode)
+      encoding = detect_file_encoding(po_file)
+      args << "r:#{encoding}"
+    end
+    parse(File.open(*args) {|io| io.read }, data, ignore_fuzzy)
+  end
+
+  def detect_file_encoding(po_file)
+    open(po_file, :encoding => 'ASCII-8BIT') do |input|
+      input.lines.each do |line|
+        return Encoding.find($1) if %r["Content-Type:.*\scharset=(.*)\\n"] =~ line
+      end
+    end
+    Encoding.default_external
+  end
+  private :detect_file_encoding
+...end poparser.ry/module_eval...
+##### State transition tables begin ###
+
+racc_action_table = [
+     3,    13,     5,     7,     9,    15,    16,    17,    20,    17,
+    13,    17,    13,    13,    11,    17,    23,    20,    13,    17 ]
+
+racc_action_check = [
+     1,    16,     1,     1,     1,    12,    12,    12,    18,    18,
+     7,    14,    15,     9,     3,    19,    20,    21,    23,    25 ]
+
+racc_action_pointer = [
+   nil,     0,   nil,    14,   nil,   nil,   nil,     3,   nil,     6,
+   nil,   nil,     0,   nil,     4,     5,    -6,   nil,     2,     8,
+     8,    11,   nil,    11,   nil,    12 ]
+
+racc_action_default = [
+    -1,   -16,    -2,   -16,    -3,   -13,    -4,   -16,    -6,   -16,
+    -7,    26,   -16,   -15,    -5,   -16,   -16,   -14,   -16,    -8,
+   -16,    -9,   -11,   -16,   -10,   -12 ]
+
+racc_goto_table = [
+    12,    22,    14,     4,    24,     6,     2,     8,    18,    19,
+    10,    21,     1,   nil,   nil,   nil,    25 ]
+
+racc_goto_check = [
+     5,     9,     5,     3,     9,     4,     2,     6,     5,     5,
+     7,     8,     1,   nil,   nil,   nil,     5 ]
+
+racc_goto_pointer = [
+   nil,    12,     5,     2,     4,    -7,     6,     9,    -7,   -17 ]
+
+racc_goto_default = [
+   nil,   nil,   nil,   nil,   nil,   nil,   nil,   nil,   nil,   nil ]
+
+racc_reduce_table = [
+  0, 0, :racc_error,
+  0, 10, :_reduce_none,
+  2, 10, :_reduce_none,
+  2, 10, :_reduce_none,
+  2, 10, :_reduce_none,
+  2, 12, :_reduce_5,
+  1, 13, :_reduce_none,
+  1, 13, :_reduce_none,
+  4, 15, :_reduce_8,
+  5, 16, :_reduce_9,
+  2, 17, :_reduce_10,
+  1, 17, :_reduce_none,
+  3, 18, :_reduce_12,
+  1, 11, :_reduce_13,
+  2, 14, :_reduce_14,
+  1, 14, :_reduce_15 ]
+
+racc_reduce_n = 16
+
+racc_shift_n = 26
+
+racc_token_table = {
+  false => 0,
+  :error => 1,
+  :COMMENT => 2,
+  :MSGID => 3,
+  :MSGCTXT => 4,
+  :MSGID_PLURAL => 5,
+  :MSGSTR => 6,
+  :STRING => 7,
+  :PLURAL_NUM => 8 }
+
+racc_nt_base = 9
+
+racc_use_result_var = true
+
+Racc_arg = [
+  racc_action_table,
+  racc_action_check,
+  racc_action_default,
+  racc_action_pointer,
+  racc_goto_table,
+  racc_goto_check,
+  racc_goto_default,
+  racc_goto_pointer,
+  racc_nt_base,
+  racc_reduce_table,
+  racc_token_table,
+  racc_shift_n,
+  racc_reduce_n,
+  racc_use_result_var ]
+
+Racc_token_to_s_table = [
+  "$end",
+  "error",
+  "COMMENT",
+  "MSGID",
+  "MSGCTXT",
+  "MSGID_PLURAL",
+  "MSGSTR",
+  "STRING",
+  "PLURAL_NUM",
+  "$start",
+  "msgfmt",
+  "comment",
+  "msgctxt",
+  "message",
+  "string_list",
+  "single_message",
+  "plural_message",
+  "msgstr_plural",
+  "msgstr_plural_line" ]
+
+Racc_debug_parser = true
+
+##### State transition tables end #####
+
+# reduce 0 omitted
+
+# reduce 1 omitted
+
+# reduce 2 omitted
+
+# reduce 3 omitted
+
+# reduce 4 omitted
+
+module_eval(<<'.,.,', 'poparser.ry', 23)
+  def _reduce_5(val, _values, result)
+        @msgctxt = unescape(val[1]) + "\004"
+  
+    result
+  end
+.,.,
+
+# reduce 6 omitted
+
+# reduce 7 omitted
+
+module_eval(<<'.,.,', 'poparser.ry', 35)
+  def _reduce_8(val, _values, result)
+        if @fuzzy and $ignore_fuzzy 
+      if val[1] != ""
+        $stderr.print _("Warning: fuzzy message was ignored.\n")
+        $stderr.print "         msgid '#{val[1]}'\n"
+      else
+        on_message('', unescape(val[3]))
+      end
+      @fuzzy = false
+    else
+      on_message(@msgctxt + unescape(val[1]), unescape(val[3]))
+    end
+    result = ""
+  
+    result
+  end
+.,.,
+
+module_eval(<<'.,.,', 'poparser.ry', 52)
+  def _reduce_9(val, _values, result)
+        if @fuzzy and $ignore_fuzzy
+      if val[1] != ""
+        $stderr.print _("Warning: fuzzy message was ignored.\n")
+        $stderr.print "msgid = '#{val[1]}\n"
+      else
+        on_message('', unescape(val[3]))
+      end
+      @fuzzy = false
+    else
+      on_message(@msgctxt + unescape(val[1]) + "\000" + unescape(val[3]), unescape(val[4]))
+    end
+    result = ""
+  
+    result
+  end
+.,.,
+
+module_eval(<<'.,.,', 'poparser.ry', 70)
+  def _reduce_10(val, _values, result)
+        if val[0].size > 0
+      result = val[0] + "\000" + val[1]
+    else
+      result = ""
+    end
+  
+    result
+  end
+.,.,
+
+# reduce 11 omitted
+
+module_eval(<<'.,.,', 'poparser.ry', 82)
+  def _reduce_12(val, _values, result)
+        result = val[2]
+  
+    result
+  end
+.,.,
+
+module_eval(<<'.,.,', 'poparser.ry', 89)
+  def _reduce_13(val, _values, result)
+        on_comment(val[0])
+  
+    result
+  end
+.,.,
+
+module_eval(<<'.,.,', 'poparser.ry', 97)
+  def _reduce_14(val, _values, result)
+        result = val.delete_if{|item| item == ""}.join
+  
+    result
+  end
+.,.,
+
+module_eval(<<'.,.,', 'poparser.ry', 101)
+  def _reduce_15(val, _values, result)
+        result = val[0]
+  
+    result
+  end
+.,.,
+
+def _reduce_none(val, _values, result)
+  val[0]
+end
+
+  end   # class PoParser
+  end   # module GetText
+
+