GNOME/libxml2
1
0
Fork 0
mirror of https://github.com/GNOME/libxml2.git synced 2025-10-18 09:41:21 +08:00
Code Issues Releases Wiki Activity

html: Chunk text data in push parser

Browse Source 
Follow the logic of the XML parser and chunk large text nodes.
This commit is contained in:
Nick Wellnhofer
2025-02-01 19:36:06 +01:00
parent 080285724b
commit c13fcc1910
2 changed files with 14 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
HTMLparser.c
View File

@@ -3113,6 +3113,7 @@ htmlParseCharData(htmlParserCtxtPtr ctxt, int partial) {
case '<':
if (mode == 0) {
done = 1;
complete = 1;
goto next_chunk;
}
if (mode == DATA_PLAINTEXT)
@@ -5146,16 +5147,16 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
} else {
ctxt->instate = XML_PARSER_CONTENT;
/*
* check that the text sequence is complete
* before handing out the data to the parser
* to avoid problems with erroneous end of
* data detection.
* We follow the logic of the XML push parser
*/
if ((!terminate) &&
(htmlParseLookupString(ctxt, 0, "<", 1, 0) < 0))
return;
if (avail < HTML_PARSER_BIG_BUFFER_SIZE) {
if ((!terminate) &&
(htmlParseLookupString(ctxt, 0, "<", 1, 0) < 0))
return;
}
ctxt->checkIndex = 0;
htmlParseCharData(ctxt, /* partial */ 0);
if (htmlParseCharData(ctxt, !terminate) == 0)
return;
}
break;