Many hyperlinks are disabled.
Use anonymous login
to enable hyperlinks.
Overview
| Comment: | wip |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | HTML5CustomNames |
| Files: | files | file ages | folders |
| SHA3-256: |
2184b00acacb3debfc10836ef22094f7 |
| User & Date: | rolf 2024-06-29 01:35:05 |
Context
|
2024-06-30
| ||
| 23:23 | wip check-in: e77b8c2886 user: rolf tags: HTML5CustomNames | |
|
2024-06-29
| ||
| 01:35 | wip check-in: 2184b00aca user: rolf tags: HTML5CustomNames | |
|
2024-06-28
| ||
| 00:07 | Updated to defines to what expat uses. check-in: b23076ff1f user: rolf tags: trunk | |
Changes
Changes to generic/dom.c.
351 352 353 354 355 356 357 358 359 360 361 362 363 364 |
if (!clen) return 0;
if (UTF8_XMLCHAR((unsigned const char *)p,clen))
p += clen;
else return 0;
}
return 1;
}
/*---------------------------------------------------------------------------
| domClearString
|
\--------------------------------------------------------------------------*/
void
domClearString (
|
> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > |
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 |
if (!clen) return 0;
if (UTF8_XMLCHAR((unsigned const char *)p,clen))
p += clen;
else return 0;
}
return 1;
}
/*---------------------------------------------------------------------------
| domIsHTMLCustomChar
|
\--------------------------------------------------------------------------*/
int
domIsHTMLCustomName (
const char *str
)
{
const char *p;
int clen, dashseen = 0;
Tcl_UniChar uniChar;
p = str;
if (*p < 'a' || *p > 'z') {
return 0;
}
p++;
while (*p) {
clen = UTF8_CHAR_LEN(*p);
if (clen == 0) return 0;
if (clen == 1) {
if (*p == '-') {
dashseen = 1;
p++;
continue;
} else if (*p == '.'
|| (*p >= '0' && *p <= '9')
|| *p == '_'
|| (*p >= 'a' && *p <= 'z')) {
p++;
continue;
}
return 0;
}
if (clen == 4) return 1;
clen = Tcl_UtfToUniChar (str, &uniChar);
if (uniChar == 0xB7
|| (uniChar >= 0xC0 && uniChar <= 0xD6)
|| (uniChar >= 0xD8 && uniChar <= 0xF6)
|| (uniChar >= 0xF8 && uniChar <= 0x37D)
|| (uniChar >= 0x37F && uniChar <= 0x1FFF)
|| (uniChar >= 0x200C && uniChar <= 0x200D)
|| (uniChar >= 0x203F && uniChar <= 0x2040)
|| (uniChar >= 0x2070 && uniChar <= 0x218F)
|| (uniChar >= 0x2C00 && uniChar <= 0x2FEF)
|| (uniChar >= 0x3001 && uniChar <= 0xD7FF)
|| (uniChar >= 0xF900 && uniChar <= 0xFDCF)
|| (uniChar >= 0xFDF0 && uniChar <= 0xFFFD)) {
p += clen;
continue;
}
return 0;
}
if (!dashseen) return 0;
switch (str[0]) {
case 'a': if (!strcmp(str,"annotation-xml")) {return 0;} break;
case 'c': if (!strcmp(str,"color-profile")) {return 0;} break;
case 'f': if (!strcmp(str,"font-face") ||
!strcmp(str,"font-face-src") ||
!strcmp(str,"font-face-uri") ||
!strcmp(str,"font-face-format") ||
!strcmp(str,"font-face-name")) {return 0;} break;
case 'm': if (!strcmp(str,"missing-glyph")) {return 0;} break;
}
return 1;
}
/*---------------------------------------------------------------------------
| domClearString
|
\--------------------------------------------------------------------------*/
void
domClearString (
|
Changes to generic/dom.h.
912 913 914 915 916 917 918 919 920 921 922 923 924 925 |
int domIsChar (const char *str);
void domClearString (char *str, char *replacement, domLength repllen,
Tcl_DString *clearedstr, int *changed);
int domIsBMPChar (const char *str);
int domIsComment (const char *str);
int domIsCDATA (const char *str);
int domIsPIValue (const char *str);
void domCopyTo (domNode *node, domNode *parent, int copyNS);
void domCopyNS (domNode *from, domNode *to);
domAttrNode * domCreateXMLNamespaceNode (domNode *parent);
void domRenumberTree (domNode *node);
int domPrecedes (domNode *node, domNode *other);
void domNormalize (domNode *node, int forXPath,
domFreeCallback freeCB, void *clientData);
|
> |
912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 |
int domIsChar (const char *str);
void domClearString (char *str, char *replacement, domLength repllen,
Tcl_DString *clearedstr, int *changed);
int domIsBMPChar (const char *str);
int domIsComment (const char *str);
int domIsCDATA (const char *str);
int domIsPIValue (const char *str);
int domIsHTMLCustomName (const char *str);
void domCopyTo (domNode *node, domNode *parent, int copyNS);
void domCopyNS (domNode *from, domNode *to);
domAttrNode * domCreateXMLNamespaceNode (domNode *parent);
void domRenumberTree (domNode *node);
int domPrecedes (domNode *node, domNode *other);
void domNormalize (domNode *node, int forXPath,
domFreeCallback freeCB, void *clientData);
|
Changes to generic/domhtml.c.
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
....
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
|
int hasContent;
domNode *pnode;
domNode *node = NULL, *parent_node = parent;
domTextNode *tnode;
domAttrNode *attrnode, *lastAttr;
int ampersandSeen = 0;
int only_whites = 0;
int hnew, autoclose, ignore;
char tmp[250], *y = NULL;
Tcl_HashEntry *h;
domProcessingInstructionNode *pinode;
x = &(html[*pos]);
while ( (c=*x)!=0 ) {
................................................................................
}
/*----------------------------------------------------------------
| new tag/element
|
\---------------------------------------------------------------*/
while ((c=*x)!=0 && c!='/' && c!='>' && c!='<' && !SPACE(c) ) {
if (!isalnum(c)) goto readText;
*x = tolower(c);
x++;
}
hasContent = 1;
if (c==0) {
RetError("Missing \">\"",(start-html) );
}
if ( (x-start)==1) {
RetError("Null markup name",(start-html) );
|
|
>
<
>
>
>
>
>
>
>
>
|
|
>
>
>
>
>
>
>
>
>
>
|
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
....
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
|
int hasContent;
domNode *pnode;
domNode *node = NULL, *parent_node = parent;
domTextNode *tnode;
domAttrNode *attrnode, *lastAttr;
int ampersandSeen = 0;
int only_whites = 0;
int hnew, autoclose, ignore, maybeCustomName, rc;
char tmp[250], *y = NULL;
Tcl_HashEntry *h;
domProcessingInstructionNode *pinode;
x = &(html[*pos]);
while ( (c=*x)!=0 ) {
................................................................................
}
/*----------------------------------------------------------------
| new tag/element
|
\---------------------------------------------------------------*/
maybeCustomName = 0;
while ((c=*x)!=0 && c!='/' && c!='>' && c!='<' && !SPACE(c) ) {
if (!maybeCustomName && !isalnum(c)) maybeCustomName = 1;
x++;
}
if (!maybeCustomName) {
c = *x;
*x = '\0'; /* temporarily terminate the string */
x = start + 1;
while (*x) {
*x = tolower(*x);
x++;
}
*x = c;
} else {
c = *x;
*x = '\0'; /* temporarily terminate the string */
rc = domIsHTMLCustomName (start+1);
*x = c;
if (!rc) {
goto readText;
}
}
hasContent = 1;
if (c==0) {
RetError("Missing \">\"",(start-html) );
}
if ( (x-start)==1) {
RetError("Null markup name",(start-html) );
|
Changes to tests/htmlreader.test.
2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 |
<head><title></title></head><body><form><select id="L" name="nls_language">
<option value="">--
</option><option selected="selected" value="en_US">en_US
</option><option value="de_DE">de_DE
</option>
</select></form></body>
</html>}
test html-3.1 {Bad data} {
set data {line 6 column 17 - Warning: <script> lacks "type" attribute
line 10 column 17 - Warning: <script> lacks "type" attribute
line 11 column 17 - Warning: <table> lacks "summary" attribute}
set doc [dom parse -html $data]
set result [$doc asHTML]
|
> > > > > > > > > > > > > > > > > > > > > > |
2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 |
<head><title></title></head><body><form><select id="L" name="nls_language">
<option value="">--
</option><option selected="selected" value="en_US">en_US
</option><option value="de_DE">de_DE
</option>
</select></form></body>
</html>}
test html-2.9 {HTML parsing} {
set doc [dom parse -html {<HTML><MATH-field>x = 1 + 1</MATH-field></HTML>}]
set result [$doc asHTML]
$doc delete
set result
} {<html><MATH-field>x = 1 + 1</MATH-field></html>}
test html-2.10 {HTML parsing} {
set doc [dom parse -html {<HTML><mytag>foo</mytag></HTML>}]
set result [$doc asHTML]
$doc delete
set result
} {<html><mytag>foo</mytag></html>}
test html-2.11 {HTML parsing} {
set doc [dom parse -html {<HTML><math-field>x = 1 + 1</math-field></HTML>}]
set result [$doc asHTML]
$doc delete
set result
} {<HTML><math-field>x = 1 + 1</math-field></HTML>}
test html-3.1 {Bad data} {
set data {line 6 column 17 - Warning: <script> lacks "type" attribute
line 10 column 17 - Warning: <script> lacks "type" attribute
line 11 column 17 - Warning: <table> lacks "summary" attribute}
set doc [dom parse -html $data]
set result [$doc asHTML]
|