trunk/apertium-tools/apertium-utils/transliterate/transliterate.cpp

   1 /*
   2  * Copyright (C) 2007 Francis Tyers
   3  *
   4  * This program is free software; you can redistribute it and/or modify
   5  * it under the terms of the GNU General Public License as published by
   6  * the Free Software Foundation; either version 2 of the License, or
   7  * (at your option) any later version.
   8  *
   9  * This program is distributed in the hope that it will be useful,
  10  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  11  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12  * GNU General Public License for more details.
  13  *
  14  * You should have received a copy of the GNU General Public License
  15  * along with this program; if not, write to the Free Software
  16  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  17  *
  18  */
  19
  20 #include <cwctype>
  21 #include <transliterate.h>
  22 #include <XMLParseUtil.h>
  23
  24 #include "entry.h"
  25
  26 using namespace std;
  27
  28 wstring const Transliterator::TRANSLITERATOR_TRANSLITERATOR_ELEM        =       L"transliterator";
  29 wstring const Transliterator::TRANSLITERATOR_TABLE_ELEM                 =       L"table";
  30 wstring const Transliterator::TRANSLITERATOR_TABLE_NAME_ATTR            =       L"name";
  31 wstring const Transliterator::TRANSLITERATOR_TRANSFORM_ELEM             =       L"transform";
  32
  33 wstring const Transliterator::TRANSLITERATOR_LEFT_ATTR                  =       L"left";
  34 wstring const Transliterator::TRANSLITERATOR_RIGHT_ATTR                 =       L"right";
  35
  36 Transliterator::Transliterator(string const &file, string const &_direction, wstring const &_name)
  37 {
  38         init(file, _direction, _name);
  39 }
  40
  41 Transliterator::Transliterator(string const &file, string const &_direction)
  42 {
  43         wstring const _name = L"default";
  44         init(file, _direction, _name);
  45 }
  46
  47 Transliterator::Transliterator(string const &file)
  48 {
  49         wstring const _name = L"default";
  50         string const _direction = "lr";
  51         init(file, _direction, _name);
  52 }
  53
  54 void Transliterator::init(string const &file, string const &_direction, wstring const &_name)
  55 {
  56         reader = xmlReaderForFile(file.c_str(), NULL, 0);
  57
  58         direction = _direction;
  59         name = _name;
  60         iter = table.begin();
  61
  62         int ret = xmlTextReaderRead(reader);
  63
  64         while(ret == 1) {
  65                 process_node();
  66                 ret = xmlTextReaderRead(reader);
  67         }
  68
  69         if(ret != 0) {
  70                 wcerr << L"Error: Parse error at the end of input." << endl;
  71         }
  72
  73         xmlFreeTextReader(reader);
  74         xmlCleanupParser();
  75 }
  76
  77 Transliterator::~Transliterator()
  78 {
  79 //      wcout << L"--" << endl << "~Transliterator()" << endl;
  80 }
  81
  82 /*
  83  *      Transliterate a string.
  84  */
  85 wstring
  86 Transliterator::transliterate(wstring in)
  87 {
  88         wstring out;
  89         wstring r = L"";
  90
  91         // iterate through the string 1 char at a time.
  92         for(unsigned int i = 0; i < in.length(); i++) {
  93
  94                 r = in[i];
  95
  96                 // iterate through the transliteration table
  97                 for(unsigned int j = 0; j < table.size(); j++) {
  98                         Entry e = table.at(j);
  99
 100                         if(direction == "rl") {
 101                                 if(in[i] == (unsigned int)(e.right())[0]) {
 102                                         r = e.left();
 103                                 }
 104                         } else {
 105                                 if(in[i] == (unsigned int)(e.left())[0]) {
 106                                         r = e.right();
 107                                 }
 108                         }
 109                 }
 110
 111                 out += r;
 112         }
 113
 114         return out;
 115 }
 116
 117 void
 118 Transliterator::process_node(void)
 119 {
 120         wstring nombre = XMLParseUtil::towstring(xmlTextReaderConstName(reader));
 121         // this needs to be static as it must remain through all calls.
 122         wstring static table_name = L"";
 123
 124         if(nombre == L"#text") {
 125                 // ignore this
 126         } else if(nombre == TRANSLITERATOR_TRANSLITERATOR_ELEM) {
 127 //              wcout << L"Transliterator" << endl;
 128         } else if(nombre == TRANSLITERATOR_TABLE_ELEM) {
 129                 table_name = XMLParseUtil::attrib(reader, TRANSLITERATOR_TABLE_NAME_ATTR);
 130 //              wcout << L"  Table " << table_name << endl;
 131         } else if(nombre == TRANSLITERATOR_TRANSFORM_ELEM) {
 132
 133                 if(table_name == name) {
 134                         wstring const &left  = XMLParseUtil::attrib(reader, TRANSLITERATOR_LEFT_ATTR);
 135                         wstring const &right = XMLParseUtil::attrib(reader, TRANSLITERATOR_RIGHT_ATTR);
 136 //                      wcout << L"  Replace " << left << L" --> " << right << endl;
 137
 138                         Entry e = Entry(left, right);
 139                         iter = table.insert(iter, e);
 140                 }
 141         } else if(nombre == L"#comment") {
 142                 // ignore this
 143         } else {
 144                 wcerr << "Error (" << xmlTextReaderGetParserLineNumber(reader);
 145                 wcerr << "): Invalid node '<" << nombre << ">'." << endl;
 146         }
 147 }