Parent: [d392d3] (diff)

Child: [f0f983] (diff)

Download this file

mimeparse.cpp    557 lines (504 with data), 13.7 kB

  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
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
#ifndef lint
static char rcsid[] = "@(#$Id: mimeparse.cpp,v 1.4 2005-10-15 12:18:04 dockes Exp $ (C) 2004 J.F.Dockes";
#endif
#ifndef TEST_MIMEPARSE
#include <string>
#include <ctype.h>
#include <stdio.h>
#include <ctype.h>
#include "mimeparse.h"
using namespace std;
// Parsing a header value. Only content-type has parameters, but
// others are compatible with content-type syntax, only, parameters
// are not used. So we can parse all like content-type:
// headertype: value [; paramname=paramvalue] ...
// Value and paramvalues can be quoted strings, and there can be
// comments in there
// The lexical token returned by find_next_token
class Lexical {
public:
enum kind {none, token, separator};
kind what;
string value;
string error;
char quote;
Lexical() : what(none), quote(0) {}
void reset() {what = none; value.erase(); error.erase();quote = 0;}
};
// Skip mime comment. This must be called with in[start] == '('
int skip_comment(const string &in, unsigned int start, Lexical &lex)
{
int commentlevel = 0;
for (; start < in.size(); start++) {
if (in[start] == '\\') {
// Skip escaped char.
if (start+1 < in.size()) {
start++;
continue;
} else {
lex.error.append("\\ at end of string ");
return string::npos;
}
}
if (in[start] == '(')
commentlevel++;
if (in[start] == ')') {
if (--commentlevel == 0)
break;
}
}
if (start == in.size()) {
lex.error.append("Unclosed comment ");
return string::npos;
}
return start;
}
// Skip initial whitespace and (possibly nested) comments.
int skip_whitespace_and_comment(const string &in, unsigned int start,
Lexical &lex)
{
while (1) {
if ((start = in.find_first_not_of(" \t\r\n", start)) == string::npos)
return in.size();
if (in[start] == '(') {
if ((start = skip_comment(in, start, lex)) == string::npos)
return string::npos;
} else {
break;
}
}
return start;
}
/// Find next token in mime header value string.
/// @return the next starting position in string, string::npos for error
/// (ie unbalanced quoting)
/// @param in the input string
/// @param start the starting position
/// @param lex the returned token and its description
/// @param delims separators we should look for
int find_next_token(const string &in, unsigned int start,
Lexical &lex, string delims = ";=")
{
char oquot, cquot;
start = skip_whitespace_and_comment(in, start, lex);
if (start == string::npos || start == in.size())
return start;
// Begins with separator ? return it.
unsigned int delimi = delims.find_first_of(in[start]);
if (delimi != string::npos) {
lex.what = Lexical::separator;
lex.value = delims[delimi];
return start+1;
}
// Check for start of quoted string
oquot = in[start];
switch (oquot) {
case '<': cquot = '>';break;
case '"': cquot = '"';break;
default: cquot = 0; break;
}
if (cquot != 0) {
// Quoted string parsing
unsigned int end;
start++; // Skip quote character
for (end = start;end < in.size() && in[end] != cquot; end++) {
if (in[end] == '\\') {
// Skip escaped char.
if (end+1 < in.size()) {
end++;
} else {
// backslash at end of string: error
lex.error.append("\\ at end of string ");
return string::npos;
}
}
}
if (end == in.size()) {
// Found end of string before closing quote character: error
lex.error.append("Unclosed quoted string ");
return string::npos;
}
lex.what = Lexical::token;
lex.value = in.substr(start, end-start);
lex.quote = oquot;
return ++end;
} else {
unsigned int end = in.find_first_of(delims + " \t(", start);
lex.what = Lexical::token;
lex.quote = 0;
if (end == string::npos) {
end = in.size();
lex.value = in.substr(start);
} else {
lex.value = in.substr(start, end-start);
}
return end;
}
}
void stringtolower(string &out, const string& in)
{
for (unsigned int i = 0; i < in.size(); i++)
out.append(1, char(tolower(in[i])));
}
bool parseMimeHeaderValue(const string& value, MimeHeaderValue& parsed)
{
parsed.value.erase();
parsed.params.clear();
Lexical lex;
unsigned int start = 0;
start = find_next_token(value, start, lex);
if (start == string::npos || lex.what != Lexical::token)
return false;
parsed.value = lex.value;
for (;;) {
string paramname, paramvalue;
lex.reset();
start = find_next_token(value, start, lex);
if (start == value.size())
return true;
if (start == string::npos)
return false;
if (lex.what == Lexical::separator && lex.value[0] == ';')
continue;
if (lex.what != Lexical::token)
return false;
stringtolower(paramname, lex.value);
start = find_next_token(value, start, lex);
if (start == string::npos || lex.what != Lexical::separator ||
lex.value[0] != '=')
return false;
start = find_next_token(value, start, lex);
if (start == string::npos || lex.what != Lexical::token)
return false;
paramvalue = lex.value;
parsed.params[paramname] = paramvalue;
}
return true;
}
// Decode a string encoded with quoted-printable encoding.
bool qp_decode(const string& in, string &out)
{
out.reserve(in.length());
unsigned int ii;
for (ii = 0; ii < in.length(); ii++) {
if (in[ii] == '=') {
ii++; // Skip '='
if(ii >= in.length() - 1) { // Need at least 2 more chars
break;
} else if (in[ii] == '\r' && in[ii+1] == '\n') { // Soft nl, skip
ii++;
} else if (in[ii] != '\n' && in[ii] != '\r') { // decode
char c = in[ii];
char co;
if(c >= 'A' && c <= 'F') {
co = char((c - 'A' + 10) * 16);
} else if (c >= 'a' && c <= 'f') {
co = char((c - 'a' + 10) * 16);
} else if (c >= '0' && c <= '9') {
co = char((c - '0') * 16);
} else {
return false;
}
if(++ii >= in.length())
break;
c = in[ii];
if (c >= 'A' && c <= 'F') {
co += char(c - 'A' + 10);
} else if (c >= 'a' && c <= 'f') {
co += char(c - 'a' + 10);
} else if (c >= '0' && c <= '9') {
co += char(c - '0');
} else {
return false;
}
out += co;
}
} else {
out += in[ii];
}
}
return true;
}
// This is adapted from FreeBSD's code.
static const char Base64[] =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
static const char Pad64 = '=';
bool base64_decode(const string& in, string& out)
{
int io = 0, state = 0, ch;
char *pos;
unsigned int ii = 0;
out.reserve(in.length());
for (ii = 0; ii < in.length(); ii++) {
ch = in[ii];
if (isspace((unsigned char)ch)) /* Skip whitespace anywhere. */
continue;
if (ch == Pad64)
break;
pos = strchr(Base64, ch);
if (pos == 0) /* A non-base64 character. */
return false;
switch (state) {
case 0:
out[io] = (pos - Base64) << 2;
state = 1;
break;
case 1:
out[io] |= (pos - Base64) >> 4;
out[io+1] = ((pos - Base64) & 0x0f) << 4 ;
io++;
state = 2;
break;
case 2:
out[io] |= (pos - Base64) >> 2;
out[io+1] = ((pos - Base64) & 0x03) << 6;
io++;
state = 3;
break;
case 3:
out[io] |= (pos - Base64);
io++;
state = 0;
break;
default:
return false;
}
}
/*
* We are done decoding Base-64 chars. Let's see if we ended
* on a byte boundary, and/or with erroneous trailing characters.
*/
if (ch == Pad64) { /* We got a pad char. */
ch = in[ii++]; /* Skip it, get next. */
switch (state) {
case 0: /* Invalid = in first position */
case 1: /* Invalid = in second position */
return false;
case 2: /* Valid, means one byte of info */
/* Skip any number of spaces. */
for (; ii < in.length(); ch = in[ii++])
if (!isspace((unsigned char)ch))
break;
/* Make sure there is another trailing = sign. */
if (ch != Pad64)
return false;
ch = in[ii++]; /* Skip the = */
/* Fall through to "single trailing =" case. */
/* FALLTHROUGH */
case 3: /* Valid, means two bytes of info */
/*
* We know this char is an =. Is there anything but
* whitespace after it?
*/
for ((void)NULL; ii < in.length(); ch = in[ii++])
if (!isspace((unsigned char)ch))
return false;
/*
* Now make sure for cases 2 and 3 that the "extra"
* bits that slopped past the last full byte were
* zeros. If we don't check them, they become a
* subliminal channel.
*/
if (out[io] != 0)
return false;
}
} else {
/*
* We ended by seeing the end of the string. Make sure we
* have no partial bytes lying around.
*/
if (state != 0)
return false;
}
return true;
}
#include "transcode.h"
#include "smallut.h"
// Decode a parsed encoded word
static bool rfc2047_decodeParsed(const std::string& charset,
const std::string& encoding,
const std::string& value,
std::string &utf8)
{
// fprintf(stderr, "DecodeParsed: charset [%s] enc [%s] val [%s]\n",
// charset.c_str(), encoding.c_str(), value.c_str());
utf8 = "";
string decoded;
if (!stringlowercmp("b", encoding)) {
if (!base64_decode(value, decoded))
return false;
// fprintf(stderr, "FromB64: [%s]\n", decoded.c_str());
} else if (!stringlowercmp("q", encoding)) {
if (!qp_decode(value, decoded))
return false;
// Need to translate _ to ' ' here
string temp;
for (string::size_type pos = 0; pos < decoded.length(); pos++)
if (decoded[pos] == '_')
temp += ' ';
else
temp += decoded[pos];
decoded = temp;
// fprintf(stderr, "FromQP: [%s]\n", decoded.c_str());
} else {
// fprintf(stderr, "Bad encoding [%s]\n", encoding.c_str());
return false;
}
if (!transcode(decoded, utf8, charset, "UTF-8")) {
// fprintf(stderr, "Transcode failed\n");
return false;
}
return true;
}
// Parse a mail header encoded value
typedef enum {rfc2047base, rfc2047open_eq, rfc2047charset, rfc2047encoding,
rfc2047value, rfc2047close_q} Rfc2047States;
bool rfc2047_decode(const std::string& in, std::string &out)
{
Rfc2047States state = rfc2047base;
string encoding, charset, value, utf8;
out = "";
for (unsigned int ii = 0; ii < in.length(); ii++) {
char ch = in[ii];
switch (state) {
case rfc2047base:
{
switch (ch) {
case '=': state = rfc2047open_eq; break;
default: value += ch;
}
}
break;
case rfc2047open_eq:
{
switch (ch) {
case '?':
{
// Transcode current (unencoded part) value:
// we sometimes find 8-bit chars in
// there. Interpret as Iso8859.
if (value.length() > 0) {
transcode(value, utf8, "ISO8859-1", "UTF-8");
out += utf8;
value = "";
}
state = rfc2047charset;
}
break;
default: state = rfc2047base; out += '='; out += ch;break;
}
}
break;
case rfc2047charset:
{
switch (ch) {
case '?': state = rfc2047encoding; break;
default: charset += ch; break;
}
}
break;
case rfc2047encoding:
{
switch (ch) {
case '?': state = rfc2047value; break;
default: encoding += ch; break;
}
}
break;
case rfc2047value:
{
switch (ch) {
case '?': state = rfc2047close_q; break;
default: value += ch;break;
}
}
break;
case rfc2047close_q:
{
switch (ch) {
case '=':
{
string utf8;
state = rfc2047base;
if (!rfc2047_decodeParsed(charset, encoding, value,
utf8)) {
return false;
}
out += utf8;
charset = encoding = value = "";
}
break;
default: state = rfc2047value; value += '?';value += ch;break;
}
}
break;
default: // ??
return false;
}
}
if (value.length() > 0) {
transcode(value, utf8, "ISO8859-1", "UTF-8");
out += utf8;
value = "";
}
if (state != rfc2047base)
return false;
return true;
}
#else
#include <string>
#include "mimeparse.h"
using namespace std;
int
main(int argc, const char **argv)
{
#if 0
// const char *tr = "text/html; charset=utf-8; otherparam=garb";
const char *tr = "text/html;charset = UTF-8 ; otherparam=garb; \n"
"QUOTEDPARAM=\"quoted value\"";
MimeHeaderValue parsed;
if (!parseMimeHeaderValue(tr, parsed)) {
fprintf(stderr, "PARSE ERROR\n");
}
printf("'%s' \n", parsed.value.c_str());
map<string, string>::iterator it;
for (it = parsed.params.begin();it != parsed.params.end();it++) {
printf(" '%s' = '%s'\n", it->first.c_str(), it->second.c_str());
}
#elif 0
const char *qp = "=41=68 =e0 boire=\r\n continue 1ere\ndeuxieme\n\r3eme "
"agrave is: '=E0' probable skipped decode error: =\n"
"Actual decode error =xx this wont show";
string out;
if (!qp_decode(string(qp), out)) {
fprintf(stderr, "qp_decode returned error\n");
}
printf("Decoded: '%s'\n", out.c_str());
#elif 0
//'C'est � boire qu'il nous faut �viter l'exc�s.'
//'Deuxi�me ligne'
//'Troisi�me ligne'
//'Et la fin (pas de nl). '
const char *b64 =
"Qydlc3Qg4CBib2lyZSBxdSdpbCBub3VzIGZhdXQg6XZpdGVyIGwnZXhj6HMuCkRldXhp6G1l\r\n"
"IGxpZ25lClRyb2lzaehtZSBsaWduZQpFdCBsYSBmaW4gKHBhcyBkZSBubCkuIA==\r\n";
string out;
if (!base64_decode(string(b64), out)) {
fprintf(stderr, "base64_decode returned error\n");
}
printf("Decoded: '%s'\n", out.c_str());
#elif 1
char line [1024];
string out;
while (fgets(line, 1023, stdin)) {
int l = strlen(line);
if (l == 0)
continue;
line[l-1] = 0;
fprintf(stderr, "Line: [%s]\n", line);
rfc2047_decode(line, out);
fprintf(stderr, "Out: [%s]\n", out.c_str());
}
#endif
}
#endif // TEST_MIMEPARSE