l10ntools/source/idxdict/idxdict.cxx

   1 /* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
   2 /*
   3  * Version: MPL 1.1 / GPLv3+ / LGPLv3+
   4  *
   5  * The contents of this file are subject to the Mozilla Public License Version
   6  * 1.1 (the "License"); you may not use this file except in compliance with
   7  * the License or as specified alternatively below. You may obtain a copy of
   8  * the License at http://www.mozilla.org/MPL/
   9  *
  10  * Software distributed under the License is distributed on an "AS IS" basis,
  11  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
  12  * for the specific language governing rights and limitations under the
  13  * License.
  14  *
  15  * The Initial Developer of the Original Code is
  16  *       Steven Butler <sebutler@gmail.com>
  17  * Portions created by the Initial Developer are Copyright (C) 2011 the
  18  * Initial Developer. All Rights Reserved.
  19  *
  20  * For minor contributions see the git repository.
  21  *
  22  * Alternatively, the contents of this file may be used under the terms of
  23  * either the GNU General Public License Version 3 or later (the "GPLv3+"), or
  24  * the GNU Lesser General Public License Version 3 or later (the "LGPLv3+"),
  25  * in which case the provisions of the GPLv3+ or the LGPLv3+ are applicable
  26  * instead of those above.
  27  */
  28 #include <iostream>
  29 #include <fstream>
  30 #include <string>
  31 #include <map>
  32 #include <stdlib.h>
  33 #include <string.h>
  34
  35 static const int MAXLINE = 1024*64;
  36
  37 using namespace std;
  38
  39 int main(int argc, char *argv[])
  40 {
  41         if (argc != 3 || strcmp(argv[1],"-o"))
  42         {
  43                 cout << "Usage: idxdict -o outputfile < input\n";
  44                 ::exit(99);
  45         }
  46         // This call improves performance by approx 5x
  47         cin.sync_with_stdio(false);
  48
  49         const char * outputFile(argv[2]);
  50         char inputBuffer[MAXLINE];
  51         multimap<string, size_t> entries;
  52         multimap<string,size_t>::iterator ret(entries.begin());
  53
  54         int line(1);
  55         cin.getline(inputBuffer, MAXLINE);
  56         const string encoding(inputBuffer);
  57         size_t currentOffset(encoding.size()+1);
  58         while (true)
  59         {
  60                 // Extract the next word, but not the entry count
  61                 cin.getline(inputBuffer, MAXLINE, '|');
  62
  63                 if (cin.eof()) break;
  64
  65                 string word(inputBuffer);
  66                 ret = entries.insert(ret, pair<string, size_t>(word, currentOffset));
  67                 currentOffset += word.size() + 1;
  68                 // Next is the entry count
  69                 cin.getline(inputBuffer, MAXLINE);
  70                 if (!cin.good())
  71                 {
  72                         cerr << "Unable to read entry - insufficient buffer?.\n";
  73                         exit(99);
  74                 }
  75                 currentOffset += strlen(inputBuffer)+1;
  76                 int entryCount(strtol(inputBuffer, NULL, 10));
  77                 for (int i(0); i < entryCount; ++i)
  78                 {
  79                         cin.getline(inputBuffer, MAXLINE);
  80                         currentOffset += strlen(inputBuffer)+1;
  81                         ++line;
  82                 }
  83         }
  84
  85         // Use binary mode to prevent any translation of LF to CRLF on Windows
  86         ofstream outputStream(outputFile, ios_base::binary| ios_base::trunc|ios_base::out);
  87         if (!outputStream.is_open())
  88         {
  89                 cerr << "Unable to open output file " << outputFile << endl;
  90                 ::exit(99);
  91         }
  92
  93         outputStream << encoding << '\n' << entries.size() << '\n';
  94
  95         for (multimap<string, size_t>::const_iterator ii(entries.begin());
  96                 ii != entries.end();
  97                 ++ii
  98         )
  99         {
 100                 outputStream << ii->first << '|' << ii->second << '\n';
 101         }
 102 }
 103
 104 /* vim:set shiftwidth=4 softtabstop=4 expandtab: */