/[pcre]/code/trunk/pcre_valid_utf8.c
ViewVC logotype

Diff of /code/trunk/pcre_valid_utf8.c

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 653 by ph10, Mon Jun 6 17:46:22 2011 UTC revision 654 by ph10, Tue Aug 2 11:00:40 2011 UTC
# Line 64  the range 0 to 0x7fffffff, up to 6 bytes Line 64  the range 0 to 0x7fffffff, up to 6 bytes
64  the canonical format. Once somebody had pointed out RFC 3629 to me (it  the canonical format. Once somebody had pointed out RFC 3629 to me (it
65  obsoletes 2279), additional restrictions were applied. The values are now  obsoletes 2279), additional restrictions were applied. The values are now
66  limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the  limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the
67  subrange 0xd000 to 0xdfff is excluded. However, the format of 5-byte and 6-byte  subrange 0xd000 to 0xdfff is excluded. However, the format of 5-byte and 6-byte
68  characters is still checked.  characters is still checked.
69    
70  From release 8.13 more information about the details of the error are passed  From release 8.13 more information about the details of the error are passed
71  back in the returned value:  back in the returned value:
72    
73  PCRE_UTF8_ERR0   No error  PCRE_UTF8_ERR0   No error
# Line 96  PCRE_UTF8_ERR21  Byte with the illegal v Line 96  PCRE_UTF8_ERR21  Byte with the illegal v
96  Arguments:  Arguments:
97    string       points to the string    string       points to the string
98    length       length of string, or -1 if the string is zero-terminated    length       length of string, or -1 if the string is zero-terminated
99    errp         pointer to an error position offset variable    errp         pointer to an error position offset variable
100    
101  Returns:       = 0    if the string is a valid UTF-8 string  Returns:       = 0    if the string is a valid UTF-8 string
102                 > 0    otherwise, setting the offset of the bad character                 > 0    otherwise, setting the offset of the bad character
# Line 117  if (length < 0) Line 117  if (length < 0)
117  for (p = string; length-- > 0; p++)  for (p = string; length-- > 0; p++)
118    {    {
119    register int ab, c, d;    register int ab, c, d;
120    
121    c = *p;    c = *p;
122    if (c < 128) continue;                /* ASCII character */    if (c < 128) continue;                /* ASCII character */
123    
124    if (c < 0xc0)                         /* Isolated 10xx xxxx byte */    if (c < 0xc0)                         /* Isolated 10xx xxxx byte */
125      {      {
126      *erroroffset = p - string;      *erroroffset = p - string;
127      return PCRE_UTF8_ERR20;      return PCRE_UTF8_ERR20;
128      }      }
129    
130    if (c >= 0xfe)                        /* Invalid 0xfe or 0xff bytes */    if (c >= 0xfe)                        /* Invalid 0xfe or 0xff bytes */
131      {      {
132      *erroroffset = p - string;      *erroroffset = p - string;
133      return PCRE_UTF8_ERR21;      return PCRE_UTF8_ERR21;
134      }      }
135    
136    ab = _pcre_utf8_table4[c & 0x3f];     /* Number of additional bytes */    ab = _pcre_utf8_table4[c & 0x3f];     /* Number of additional bytes */
137    if (length < ab)    if (length < ab)
138      {      {
139      *erroroffset = p - string;          /* Missing bytes */      *erroroffset = p - string;          /* Missing bytes */
140      return ab - length;                 /* Codes ERR1 to ERR5 */      return ab - length;                 /* Codes ERR1 to ERR5 */
141      }      }
142    length -= ab;                         /* Length remaining */    length -= ab;                         /* Length remaining */
143    
144    /* Check top bits in the second byte */    /* Check top bits in the second byte */
145    
146    if (((d = *(++p)) & 0xc0) != 0x80)    if (((d = *(++p)) & 0xc0) != 0x80)
147      {      {
148      *erroroffset = p - string - 1;      *erroroffset = p - string - 1;
149      return PCRE_UTF8_ERR6;      return PCRE_UTF8_ERR6;
150      }      }
151    
152    /* For each length, check that the remaining bytes start with the 0x80 bit    /* For each length, check that the remaining bytes start with the 0x80 bit
153    set and not the 0x40 bit. Then check for an overlong sequence, and for the    set and not the 0x40 bit. Then check for an overlong sequence, and for the
154    excluded range 0xd800 to 0xdfff. */    excluded range 0xd800 to 0xdfff. */
155    
# Line 157  for (p = string; length-- > 0; p++) Line 157  for (p = string; length-- > 0; p++)
157      {      {
158      /* 2-byte character. No further bytes to check for 0x80. Check first byte      /* 2-byte character. No further bytes to check for 0x80. Check first byte
159      for for xx00 000x (overlong sequence). */      for for xx00 000x (overlong sequence). */
160    
161      case 1: if ((c & 0x3e) == 0)      case 1: if ((c & 0x3e) == 0)
162        {        {
163        *erroroffset = p - string - 1;        *erroroffset = p - string - 1;
164        return PCRE_UTF8_ERR15;        return PCRE_UTF8_ERR15;
165        }        }
166      break;      break;
167    
168      /* 3-byte character. Check third byte for 0x80. Then check first 2 bytes      /* 3-byte character. Check third byte for 0x80. Then check first 2 bytes
169        for 1110 0000, xx0x xxxx (overlong sequence) or        for 1110 0000, xx0x xxxx (overlong sequence) or
170            1110 1101, 1010 xxxx (0xd800 - 0xdfff) */            1110 1101, 1010 xxxx (0xd800 - 0xdfff) */
171    
172      case 2:      case 2:
173      if ((*(++p) & 0xc0) != 0x80)     /* Third byte */      if ((*(++p) & 0xc0) != 0x80)     /* Third byte */
174        {        {
175        *erroroffset = p - string - 2;        *erroroffset = p - string - 2;
176        return PCRE_UTF8_ERR7;        return PCRE_UTF8_ERR7;
177        }        }
178      if (c == 0xe0 && (d & 0x20) == 0)      if (c == 0xe0 && (d & 0x20) == 0)
179        {        {
180        *erroroffset = p - string - 2;        *erroroffset = p - string - 2;
181        return PCRE_UTF8_ERR16;        return PCRE_UTF8_ERR16;
182        }        }
183      if (c == 0xed && d >= 0xa0)      if (c == 0xed && d >= 0xa0)
184        {        {
185        *erroroffset = p - string - 2;        *erroroffset = p - string - 2;
186        return PCRE_UTF8_ERR14;        return PCRE_UTF8_ERR14;
187        }        }
188      break;      break;
189    
190      /* 4-byte character. Check 3rd and 4th bytes for 0x80. Then check first 2      /* 4-byte character. Check 3rd and 4th bytes for 0x80. Then check first 2
191         bytes for for 1111 0000, xx00 xxxx (overlong sequence), then check for a         bytes for for 1111 0000, xx00 xxxx (overlong sequence), then check for a
192         character greater than 0x0010ffff (f4 8f bf bf) */         character greater than 0x0010ffff (f4 8f bf bf) */
193    
194      case 3:      case 3:
195      if ((*(++p) & 0xc0) != 0x80)     /* Third byte */      if ((*(++p) & 0xc0) != 0x80)     /* Third byte */
196        {        {
197        *erroroffset = p - string - 2;        *erroroffset = p - string - 2;
198        return PCRE_UTF8_ERR7;        return PCRE_UTF8_ERR7;
199        }        }
200      if ((*(++p) & 0xc0) != 0x80)     /* Fourth byte */      if ((*(++p) & 0xc0) != 0x80)     /* Fourth byte */
201        {        {
202        *erroroffset = p - string - 3;        *erroroffset = p - string - 3;
203        return PCRE_UTF8_ERR8;        return PCRE_UTF8_ERR8;
204        }        }
205      if (c == 0xf0 && (d & 0x30) == 0)      if (c == 0xf0 && (d & 0x30) == 0)
206        {        {
207        *erroroffset = p - string - 3;        *erroroffset = p - string - 3;
208        return PCRE_UTF8_ERR17;        return PCRE_UTF8_ERR17;
209        }        }
210      if (c > 0xf4 || (c == 0xf4 && d > 0x8f))      if (c > 0xf4 || (c == 0xf4 && d > 0x8f))
211        {        {
212        *erroroffset = p - string - 3;        *erroroffset = p - string - 3;
213        return PCRE_UTF8_ERR13;        return PCRE_UTF8_ERR13;
214        }        }
215      break;      break;
216    
217      /* 5-byte and 6-byte characters are not allowed by RFC 3629, and will be      /* 5-byte and 6-byte characters are not allowed by RFC 3629, and will be
218      rejected by the length test below. However, we do the appropriate tests      rejected by the length test below. However, we do the appropriate tests
219      here so that overlong sequences get diagnosed, and also in case there is      here so that overlong sequences get diagnosed, and also in case there is
220      ever an option for handling these larger code points. */      ever an option for handling these larger code points. */
221    
222      /* 5-byte character. Check 3rd, 4th, and 5th bytes for 0x80. Then check for      /* 5-byte character. Check 3rd, 4th, and 5th bytes for 0x80. Then check for
223      1111 1000, xx00 0xxx */      1111 1000, xx00 0xxx */
224    
225      case 4:      case 4:
226      if ((*(++p) & 0xc0) != 0x80)     /* Third byte */      if ((*(++p) & 0xc0) != 0x80)     /* Third byte */
227        {        {
228        *erroroffset = p - string - 2;        *erroroffset = p - string - 2;
229        return PCRE_UTF8_ERR7;        return PCRE_UTF8_ERR7;
230        }        }
231      if ((*(++p) & 0xc0) != 0x80)     /* Fourth byte */      if ((*(++p) & 0xc0) != 0x80)     /* Fourth byte */
232        {        {
233        *erroroffset = p - string - 3;        *erroroffset = p - string - 3;
234        return PCRE_UTF8_ERR8;        return PCRE_UTF8_ERR8;
235        }        }
236      if ((*(++p) & 0xc0) != 0x80)     /* Fifth byte */      if ((*(++p) & 0xc0) != 0x80)     /* Fifth byte */
237        {        {
238        *erroroffset = p - string - 4;        *erroroffset = p - string - 4;
239        return PCRE_UTF8_ERR9;        return PCRE_UTF8_ERR9;
240        }        }
241      if (c == 0xf8 && (d & 0x38) == 0)      if (c == 0xf8 && (d & 0x38) == 0)
242        {        {
243        *erroroffset = p - string - 4;        *erroroffset = p - string - 4;
244        return PCRE_UTF8_ERR18;        return PCRE_UTF8_ERR18;
245        }        }
246      break;      break;
247    
248      /* 6-byte character. Check 3rd-6th bytes for 0x80. Then check for      /* 6-byte character. Check 3rd-6th bytes for 0x80. Then check for
# Line 251  for (p = string; length-- > 0; p++) Line 251  for (p = string; length-- > 0; p++)
251      case 5:      case 5:
252      if ((*(++p) & 0xc0) != 0x80)     /* Third byte */      if ((*(++p) & 0xc0) != 0x80)     /* Third byte */
253        {        {
254        *erroroffset = p - string - 2;        *erroroffset = p - string - 2;
255        return PCRE_UTF8_ERR7;        return PCRE_UTF8_ERR7;
256        }        }
257      if ((*(++p) & 0xc0) != 0x80)     /* Fourth byte */      if ((*(++p) & 0xc0) != 0x80)     /* Fourth byte */
258        {        {
259        *erroroffset = p - string - 3;        *erroroffset = p - string - 3;
260        return PCRE_UTF8_ERR8;        return PCRE_UTF8_ERR8;
261        }        }
262      if ((*(++p) & 0xc0) != 0x80)     /* Fifth byte */      if ((*(++p) & 0xc0) != 0x80)     /* Fifth byte */
263        {        {
264        *erroroffset = p - string - 4;        *erroroffset = p - string - 4;
265        return PCRE_UTF8_ERR9;        return PCRE_UTF8_ERR9;
266        }        }
267      if ((*(++p) & 0xc0) != 0x80)     /* Sixth byte */      if ((*(++p) & 0xc0) != 0x80)     /* Sixth byte */
268        {        {
269        *erroroffset = p - string - 5;        *erroroffset = p - string - 5;
270        return PCRE_UTF8_ERR10;        return PCRE_UTF8_ERR10;
271        }        }
272      if (c == 0xfc && (d & 0x3c) == 0)      if (c == 0xfc && (d & 0x3c) == 0)
273        {        {
274        *erroroffset = p - string - 5;        *erroroffset = p - string - 5;
275        return PCRE_UTF8_ERR19;        return PCRE_UTF8_ERR19;
276        }        }
277      break;      break;
278      }      }
279    
280    /* Character is valid under RFC 2279, but 4-byte and 5-byte characters are    /* Character is valid under RFC 2279, but 4-byte and 5-byte characters are
281    excluded by RFC 3629. The pointer p is currently at the last byte of the    excluded by RFC 3629. The pointer p is currently at the last byte of the
282    character. */    character. */
283    
284    if (ab > 3)    if (ab > 3)
285      {      {
286      *erroroffset = p - string - ab;      *erroroffset = p - string - ab;
287      return (ab == 4)? PCRE_UTF8_ERR11 : PCRE_UTF8_ERR12;      return (ab == 4)? PCRE_UTF8_ERR11 : PCRE_UTF8_ERR12;
288      }      }
289    }    }
290    
291  #else  /* SUPPORT_UTF8 */  #else  /* SUPPORT_UTF8 */
292  (void)(string);  /* Keep picky compilers happy */  (void)(string);  /* Keep picky compilers happy */
293  (void)(length);  (void)(length);

Legend:
Removed from v.653  
changed lines
  Added in v.654

  ViewVC Help
Powered by ViewVC 1.1.5