emelie/tidy-html5
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Issue #379 - Care about 'ix' going negative.

Browse source 
How this lasted so long in the code is a mystery! But of course it will
only be a read out-of-bounds if testing the first character in the lexer,
and it is a spacey char.

A big thanks to @gaa-cifasis for running ASAN tests on Tidy.
This commit is contained in:
Geoff McLane 2016-03-06 17:31:00 +01:00
parent b83d5ffb03
commit 8dda04f1df
1 changed files with 8 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
src/pprint.c
View file

@ -1034,10 +1034,11 @@ static void PPrintText( TidyDocImpl* doc, uint mode, uint indent,
ix = IncrWS( ix, end, indent, ixWS ); ix = IncrWS( ix, end, indent, ixWS );
} }
else if (( c == '&' ) && (TY_(HTMLVersion)(doc) == HT50) && else if (( c == '&' ) && (TY_(HTMLVersion)(doc) == HT50) &&
(((ix + 1) == end) || (((ix + 1) < end) && (isspace(doc->lexer->lexbuf[ix+1])))) ) (((ix + 1) == end) || (((ix + 1) < end) && (isspace(doc->lexer->lexbuf[ix+1] & 0xff)))) )
{ {
/*\ /*\
* Issue #207 - This is an unambiguous ampersand need not be 'quoted' in HTML5 * Issue #207 - This is an unambiguous ampersand need not be 'quoted' in HTML5
* Issue #379 - Ensure only 0 to 255 passed to 'isspace' to avoid debug assert
\*/ \*/
PPrintChar( doc, c, (mode | CDATA) ); PPrintChar( doc, c, (mode | CDATA) );
} }
@ -1866,8 +1867,11 @@ static int TextEndsWithNewline(Lexer *lexer, Node *node, uint mode )
if ( (mode & (CDATA|COMMENT)) && TY_(nodeIsText)(node) && node->end > node->start ) if ( (mode & (CDATA|COMMENT)) && TY_(nodeIsText)(node) && node->end > node->start )
{ {
uint ch, ix = node->end - 1; uint ch, ix = node->end - 1;
/* Skip non-newline whitespace. */ /*\
while ( ix >= node->start && (ch = (lexer->lexbuf[ix] & 0xff)) * Skip non-newline whitespace.
* Issue #379 - Only if ix is GT start can it be decremented!
\*/
while ( ix > node->start && (ch = (lexer->lexbuf[ix] & 0xff))
&& ( ch == ' ' || ch == '\t' || ch == '\r' ) ) && ( ch == ' ' || ch == '\t' || ch == '\r' ) )
--ix; --ix;