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 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124
|
/**
* Yudit Unicode Editor Source File
*
* GNU Copyright (C) 1997-2023 Gaspar Sinai <gaspar@yudit.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, version 2,
* dated June 1991. See file COPYYING for details.
*
* 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.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include "stoolkit/sencoder/SB_DeShape.h"
#include "stoolkit/SString.h"
#include "stoolkit/SStringVector.h"
#include "stoolkit/STextData.h"
#define SS_ESC 27
/**
* @author: Gaspar Sinai <gaspar@yudit.org>
* @version: 2000-05-12
* This is the counterpart of SB_Shape. It does just the
* Opposite thing - it takes Presentation Forms and
* convert them back into normal characters - reverse of
* Roman Czyborra's arabjoin.
*/
SB_DeShape::SB_DeShape() : SBEncoder ("\n,\r\n,\r"), shape ("shape"), interface(false)
{
ok = shape.isOK();
}
SB_DeShape::~SB_DeShape ()
{
}
/**
* return false if this generic encoder does not exist.
*/
bool
SB_DeShape::isOK() const
{
return ok;
}
/**
* This is encoding a unicode string into a bytestring
* @param input is a unicode string.
*/
const SString&
SB_DeShape::encode (const SV_UCS4& input)
{
return interface.encode (convert(input));
}
/**
* Decode an input string into a unicode string.
* @param input is a string.
* he output can be null, in this case a line is not
* read fully. If input size is zero output will be flushed.
*/
const SV_UCS4&
SB_DeShape::decode (const SString& _input)
{
SV_UCS4 decd = interface.decode (_input);
return convert (decd);
}
/**
* Decode an input string into a unicode string.
* @param input is a string.
* he output can be null, in this case a line is not
* read fully. If input size is zero output will be flushed.
*/
const SV_UCS4&
SB_DeShape::convert (const SV_UCS4& decd)
{
for (unsigned int i=0; i<decd.size(); )
{
SV_UCS4 ret;
unsigned int n = shape.lift (decd, i, true, &ret);
/* the composition comes at the end - if any */
if (n>=i+1)
{
ucs4string.append (ret);
i = n;
}
else
{
ucs4string.append (decd[i]);
i++;
}
}
return ucs4string;
}
/**
* These methods guess the line delimiters for the input
* The one without arguments is giving the 'first approximation'
* It returns an inclusive list of all possibilities.
*/
const SStringVector&
SB_DeShape::delimiters ()
{
return realDelimiters;
}
/**
* These methods guess the line delimiters for the input
* The one without arguments is giving the 'first approximation'
* It returns an exact list
*/
const SStringVector&
SB_DeShape::delimiters (const SString& sample)
{
return sampleDelimiters;
}
|