Many hyperlinks are disabled.
Use anonymous login
to enable hyperlinks.
Overview
| Comment: | Fix two bugs (introduced with this branch) that become manifest with invalid UTF-8 sequences. |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | comment-formatter-utf8 |
| Files: | files | file ages | folders |
| SHA1: |
b86a2fc7eb209681531ce6df583cdab2 |
| User & Date: | florian 2018-11-24 07:16:00 |
Context
|
2018-11-24
| ||
| 07:49 | Minor optimizations: drop a few redundant comparisons and calculations, and take advantage of the logical AND short-circuit by testing the least expensive and most unlikely condition first. Also fold away the iterative comments into cross references. check-in: 490d38ff user: florian tags: comment-formatter-utf8 | |
| 07:16 | Fix two bugs (introduced with this branch) that become manifest with invalid UTF-8 sequences. check-in: b86a2fc7 user: florian tags: comment-formatter-utf8 | |
|
2018-11-16
| ||
| 19:39 | Fix a bug (already present on trunk) with the (non-legacy) comment printing algorithm, detected while running the regression tests from test/comment.test with UTF-8 text: the function to print the indent (modified to a calculate-only function on this branch) was handed a pointer to the current line index and the current line index, thus performing checks at (current line index * 2), causing random increments of the current line index. check-in: 70dd8f74 user: florian tags: comment-formatter-utf8 | |
Changes
Changes to src/comformat.c.
169
170
171
172
173
174
175
176
177
178
179
180
181
182
...
402
403
404
405
406
407
408
409
410
411
412
413
414
415
|
int maxUTF8=1; /* Expected sequence length. */
if( (c&0xe0)==0xc0 )maxUTF8=2; /* UTF-8 lead byte 110vvvvv */
else if( (c&0xf0)==0xe0 )maxUTF8=3; /* UTF-8 lead byte 1110vvvv */
else if( (c&0xf8)==0xf0 )maxUTF8=4; /* UTF-8 lead byte 11110vvv */
while( i<lengthBytes-1 &&
cchUTF8<maxUTF8 &&
(zString[i+1]&0xc0)==0x80 ){ /* UTF-8 trail byte 10vvvvvv */
i++;
}
}
}
return lengthUTF8;
}
................................................................................
int maxUTF8=1; /* Expected sequence length. */
if( (c&0xe0)==0xc0 )maxUTF8=2; /* UTF-8 lead byte 110vvvvv */
else if( (c&0xf0)==0xe0 )maxUTF8=3; /* UTF-8 lead byte 1110vvvv */
else if( (c&0xf8)==0xf0 )maxUTF8=4; /* UTF-8 lead byte 11110vvv */
zBuf[k++] = c;
while( cchUTF8<maxUTF8 &&
(zText[i+1]&0xc0)==0x80 ){ /* UTF-8 trail byte 10vvvvvv */
zBuf[k++] = zText[++i];
}
}
else if( fossil_isspace(c) ){
si = i;
sk = k;
if( k==0 || zBuf[k-1]!=' ' ){
|
>
>
|
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
...
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
|
int maxUTF8=1; /* Expected sequence length. */
if( (c&0xe0)==0xc0 )maxUTF8=2; /* UTF-8 lead byte 110vvvvv */
else if( (c&0xf0)==0xe0 )maxUTF8=3; /* UTF-8 lead byte 1110vvvv */
else if( (c&0xf8)==0xf0 )maxUTF8=4; /* UTF-8 lead byte 11110vvv */
while( i<lengthBytes-1 &&
cchUTF8<maxUTF8 &&
(zString[i+1]&0xc0)==0x80 ){ /* UTF-8 trail byte 10vvvvvv */
cchUTF8++;
i++;
}
}
}
return lengthUTF8;
}
................................................................................
int maxUTF8=1; /* Expected sequence length. */
if( (c&0xe0)==0xc0 )maxUTF8=2; /* UTF-8 lead byte 110vvvvv */
else if( (c&0xf0)==0xe0 )maxUTF8=3; /* UTF-8 lead byte 1110vvvv */
else if( (c&0xf8)==0xf0 )maxUTF8=4; /* UTF-8 lead byte 11110vvv */
zBuf[k++] = c;
while( cchUTF8<maxUTF8 &&
(zText[i+1]&0xc0)==0x80 ){ /* UTF-8 trail byte 10vvvvvv */
cchUTF8++;
zBuf[k++] = zText[++i];
}
}
else if( fossil_isspace(c) ){
si = i;
sk = k;
if( k==0 || zBuf[k-1]!=' ' ){
|