// tok must come from htmlcoarsetok
// returns all container tags found (including content) as CNC
// honors nested tags correctly
static LL<S> findContainerOrEmptyTag(L<S> tok, S tag) {
new LL<S> l;
for (int i = 1; i < l(tok); i += 2)
if (isEmptyTag(tok.get(i), tag))
l.add(tok.subList(i-1, i+1));
else if (isOpeningTag(tok.get(i), tag)) {
int j, level = 1;
for (j = i+2; j < tok.size(); j += 2)
if (isOpeningTag(tok.get(j), tag))
++level;
else if (isTag(tok.get(j), "/" + tag)) {
--level;
if (level == 0) {
l.add(subList(tok, i-1, j+2)); // actual CNC
break;
}
}
i = j;
}
ret l;
}
static LL<S> findContainerOrEmptyTag(S html, S tag) {
ret findContainerOrEmptyTag(htmlTok(html), tag);
}Began life as a copy of #1002309
download show line numbers debug dex old transpilations
Travelled to 14 computer(s): aoiabmzegqzx, bhatertpkbcr, cbybwowwnfue, cfunsshuasjs, ddnzoavkxhuk, gwrvuhgaqvyk, ishqpsrjomds, lpdgvwnxivlt, mqqgnosmbjvj, pyentgdyhuwx, pzhvpgtvlbxg, tslmcundralx, tvejysmllsmz, vouqrxazstgt
No comments. add comment
| Snippet ID: | #1005097 |
| Snippet name: | findContainerOrEmptyTag - HTML/XML parsing |
| Eternal ID of this version: | #1005097/3 |
| Text MD5: | 176a163bf36f402b2db1dbd44cbf8ae4 |
| Author: | stefan |
| Category: | javax |
| Type: | JavaX fragment (include) |
| Public (visible to everyone): | Yes |
| Archived (hidden from active list): | No |
| Created/modified: | 2021-07-24 03:13:06 |
| Source code size: | 847 bytes / 28 lines |
| Pitched / IR pitched: | No / No |
| Views / Downloads: | 1027 / 1011 |
| Version history: | 2 change(s) |
| Referenced in: | #1006654 - Standard functions list 2 (LIVE, continuation of #761) |