recoll / Code / Diff of /src/utils/mimeparse.cpp

Diff of /src/utils/mimeparse.cpp [f1211d] .. [022e0e]

Switch to unified view


#ifndef lint
static char rcsid[] = "@(#$Id: mimeparse.cpp,v 1.21 2008-07-01 11:51:51 dockes Exp $ (C) 2004 J.F.Dockes";
#endif
/*
 *   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; either version 2 of the License, or
...
    if (it->second.chunks.empty())
        continue;
    string nm = it->first;
    // Create the name entry
    if (parsed.params.find(nm) == parsed.params.end())
        parsed.params[nm].clear();
    // Concatenate all chunks and decode the whole if the first one needs
    // to. Yes, this is not quite right.
    string value;
    for (vector<Chunk>::const_iterator vi = it->second.chunks.begin();
         vi != it->second.chunks.end(); vi++) {
...
                 const std::string& value, 
                 std::string &utf8)
{
    DPRINT((stderr, "DecodeParsed: charset [%s] enc [%s] val [%s]\n",
        charset.c_str(), encoding.c_str(), value.c_str()));
    utf8.clear();

    string decoded;
    if (!stringlowercmp("b", encoding)) {
    if (!base64_decode(value, decoded))
        return false;
...
    DPRINT((stderr, "rfc2047_decode: [%s]\n", in.c_str()));

    Rfc2047States state = rfc2047ready;
    string encoding, charset, value, utf8;

    out.clear();

    for (string::size_type ii = 0; ii < in.length(); ii++) {
    char ch = in[ii];
    switch (state) {
    case rfc2047base:
...
            // we sometimes find 8-bit chars in
            // there. Interpret as Iso8859.
            if (value.length() > 0) {
                transcode(value, utf8, "ISO-8859-1", "UTF-8");
                out += utf8;
              value.clear();
            }
            state = rfc2047charset; 
            }
            break;
        default: state = rfc2047base; out += '='; out += ch;break;
...
            if (!rfc2047_decodeParsed(charset, encoding, value, 
                          utf8)) {
                return false;
            }
            out += utf8;
          charset.clear();
          encoding.clear();
          value.clear();
            }
            break;
        default: state = rfc2047value; value += '?';value += ch;break;
        }
        }
...
    }

    if (value.length() > 0) {
    transcode(value, utf8, "ISO-8859-1", "UTF-8");
    out += utf8;
  value.clear();
    }
    if (state != rfc2047base) 
    return false;
    return true;
}

	a/src/utils/mimeparse.cpp		b/src/utils/mimeparse.cpp
1	#ifndef lint	1	#ifndef lint
2	static char rcsid[] = "@(#$Id: mimeparse.cpp,v 1.20 2007-12-13 06:58:22 dockes Exp $ (C) 2004 J.F.Dockes";	2	static char rcsid[] = "@(#$Id: mimeparse.cpp,v 1.21 2008-07-01 11:51:51 dockes Exp $ (C) 2004 J.F.Dockes";
3	#endif	3	#endif
4	/*	4	/*
5	* This program is free software; you can redistribute it and/or modify	5	* This program is free software; you can redistribute it and/or modify
6	* it under the terms of the GNU General Public License as published by	6	* it under the terms of the GNU General Public License as published by
7	* the Free Software Foundation; either version 2 of the License, or	7	* the Free Software Foundation; either version 2 of the License, or
	...		...
358	if (it->second.chunks.empty())	358	if (it->second.chunks.empty())
359	continue;	359	continue;
360	string nm = it->first;	360	string nm = it->first;
361	// Create the name entry	361	// Create the name entry
362	if (parsed.params.find(nm) == parsed.params.end())	362	if (parsed.params.find(nm) == parsed.params.end())
363	parsed.params[nm] = "";	363	parsed.params[nm].clear();
364	// Concatenate all chunks and decode the whole if the first one needs	364	// Concatenate all chunks and decode the whole if the first one needs
365	// to. Yes, this is not quite right.	365	// to. Yes, this is not quite right.
366	string value;	366	string value;
367	for (vector<Chunk>::const_iterator vi = it->second.chunks.begin();	367	for (vector<Chunk>::const_iterator vi = it->second.chunks.begin();
368	vi != it->second.chunks.end(); vi++) {	368	vi != it->second.chunks.end(); vi++) {
	...		...
435	const std::string& value,	435	const std::string& value,
436	std::string &utf8)	436	std::string &utf8)
437	{	437	{
438	DPRINT((stderr, "DecodeParsed: charset [%s] enc [%s] val [%s]\n",	438	DPRINT((stderr, "DecodeParsed: charset [%s] enc [%s] val [%s]\n",
439	charset.c_str(), encoding.c_str(), value.c_str()));	439	charset.c_str(), encoding.c_str(), value.c_str()));
440	utf8 = "";	440	utf8.clear();
441		441
442	string decoded;	442	string decoded;
443	if (!stringlowercmp("b", encoding)) {	443	if (!stringlowercmp("b", encoding)) {
444	if (!base64_decode(value, decoded))	444	if (!base64_decode(value, decoded))
445	return false;	445	return false;
	...		...
483	DPRINT((stderr, "rfc2047_decode: [%s]\n", in.c_str()));	483	DPRINT((stderr, "rfc2047_decode: [%s]\n", in.c_str()));
484		484
485	Rfc2047States state = rfc2047ready;	485	Rfc2047States state = rfc2047ready;
486	string encoding, charset, value, utf8;	486	string encoding, charset, value, utf8;
487		487
488	out = "";	488	out.clear();
489		489
490	for (string::size_type ii = 0; ii < in.length(); ii++) {	490	for (string::size_type ii = 0; ii < in.length(); ii++) {
491	char ch = in[ii];	491	char ch = in[ii];
492	switch (state) {	492	switch (state) {
493	case rfc2047base:	493	case rfc2047base:
	...		...
521	// we sometimes find 8-bit chars in	521	// we sometimes find 8-bit chars in
522	// there. Interpret as Iso8859.	522	// there. Interpret as Iso8859.
523	if (value.length() > 0) {	523	if (value.length() > 0) {
524	transcode(value, utf8, "ISO-8859-1", "UTF-8");	524	transcode(value, utf8, "ISO-8859-1", "UTF-8");
525	out += utf8;	525	out += utf8;
526	value = "";	526	value.clear();
527	}	527	}
528	state = rfc2047charset;	528	state = rfc2047charset;
529	}	529	}
530	break;	530	break;
531	default: state = rfc2047base; out += '='; out += ch;break;	531	default: state = rfc2047base; out += '='; out += ch;break;
	...		...
566	if (!rfc2047_decodeParsed(charset, encoding, value,	566	if (!rfc2047_decodeParsed(charset, encoding, value,
567	utf8)) {	567	utf8)) {
568	return false;	568	return false;
569	}	569	}
570	out += utf8;	570	out += utf8;
571	charset = encoding = value = "";	571	charset.clear();
		572	encoding.clear();
		573	value.clear();
572	}	574	}
573	break;	575	break;
574	default: state = rfc2047value; value += '?';value += ch;break;	576	default: state = rfc2047value; value += '?';value += ch;break;
575	}	577	}
576	}	578	}
	...		...
581	}	583	}
582		584
583	if (value.length() > 0) {	585	if (value.length() > 0) {
584	transcode(value, utf8, "ISO-8859-1", "UTF-8");	586	transcode(value, utf8, "ISO-8859-1", "UTF-8");
585	out += utf8;	587	out += utf8;
586	value = "";	588	value.clear();
587	}	589	}
588	if (state != rfc2047base)	590	if (state != rfc2047base)
589	return false;	591	return false;
590	return true;	592	return true;
591	}	593	}