summaryrefslogtreecommitdiff
path: root/src/modules/filters/utf8latin1.cpp
blob: db5237c0e0fce1cfb48f0bc117d2d08128c22f64 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
/******************************************************************************
 *
 *  utf8latin1.cpp -	SWFilter descendant to convert UTF-8 to Latin-1
 *
 * $Id: utf8latin1.cpp 3157 2014-04-17 03:56:12Z greg.hellings $
 *
 * Copyright 2001-2013 CrossWire Bible Society (http://www.crosswire.org)
 *	CrossWire Bible Society
 *	P. O. Box 2528
 *	Tempe, AZ  85280-2528
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the
 * Free Software Foundation version 2.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 */

#include <utf8latin1.h>
#include <swbuf.h>


SWORD_NAMESPACE_START


UTF8Latin1::UTF8Latin1(char rchar) : replacementChar(rchar) {
}


char UTF8Latin1::processText(SWBuf &text, const SWKey *key, const SWModule *module)
{
  unsigned char *from;

  unsigned long uchar;
  unsigned char significantFirstBits, subsequent;
  
  if ((unsigned long)key < 2) {// hack, we're en(1)/de(0)ciphering
	return (char)-1;
  }

  SWBuf orig = text;
  from = (unsigned char*)orig.c_str();

  
  // -------------------------------
  
  for (text = ""; *from; from++) {
    uchar = 0;
    if ((*from & 128) != 128) {
      //          	if (*from != ' ')
      uchar = *from;
    }
    else if ((*from & 128) && ((*from & 64) != 64)) {
      // error, do nothing
      continue;
    }
    else {
      *from <<= 1;
      for (subsequent = 1; (*from & 128); subsequent++) {
	*from <<= 1;
	from[subsequent] &= 63;
	uchar <<= 6;
	uchar |= from[subsequent];
      }
      subsequent--;
      *from <<=1;
      significantFirstBits = 8 - (2+subsequent);
      
      uchar |= (((short)*from) << (((6*subsequent)+significantFirstBits)-8));
      from += subsequent;
    }

    if (uchar < 0xff) {
        text += (unsigned char)uchar;
    }
    else {
        text += replacementChar;
    }
  }
  return 0;
}


SWORD_NAMESPACE_END