KevinMidboe/linguist
1
0
Fork 0
mirror of https://github.com/KevinMidboe/linguist.git synced 2025-10-29 17:50:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Lexer crash fix (#3900)

Browse Source 
* input may return 0 for EOF

Stops overruns into fread from nothing.

* remove two trailing contexts

* fix up sgml tokens
This commit is contained in:
Ashe Connor
2017-11-10 22:11:32 +11:00
committed by GitHub
parent 0f4955e5d5
commit c9b3d19c6f
4 changed files with 260 additions and 6325 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
ext/linguist/tokenizer.l
View File

@@ -9,25 +9,25 @@
#define eat_until_eol() do { \
int c; \
while ((c = input(yyscanner)) != '\n' && c != EOF); \
if (c == EOF) \
yyterminate(); \
while ((c = input(yyscanner)) != '\n' && c != EOF && c); \
if (c == EOF || !c) \
return 0; \
} while (0)
#define eat_until_unescaped(q) do { \
int c; \
while ((c = input(yyscanner)) != EOF) { \
while ((c = input(yyscanner)) != EOF && c) { \
if (c == '\n') \
break; \
if (c == '\\') { \
c = input(yyscanner); \
if (c == EOF) \
yyterminate(); \
if (c == EOF || !c) \
return 0; \
} else if (c == q) \
break; \
} \
if (c == EOF) \
yyterminate(); \
if (c == EOF || !c) \
return 0; \
} while (0)
%}
@@ -84,7 +84,7 @@
\" { eat_until_unescaped('"'); }
' { eat_until_unescaped('\''); }
(0x[0-9a-fA-F]([0-9a-fA-F]|\.)*|[0-9]([0-9]|\.)*)([uU][lL]{0,2}|([eE][-+][0-9]*)?[fFlL]*) { /* nothing */ }
\<[^ \t\n\r<>]+/>|" "[^<>\n]{0,2048}> {
\<[[:alnum:]_!./?-]+ {
if (strcmp(yytext, "<!--") == 0) {
BEGIN(xml_comment);
} else {
@@ -93,8 +93,8 @@
return 1;
}
}
<sgml>[[:alnum:]_]+=/\" { feed_token(strdup(yytext), REGULAR_TOKEN); input(yyscanner); eat_until_unescaped('"'); return 1; }
<sgml>[[:alnum:]_]+=/' { feed_token(strdup(yytext), REGULAR_TOKEN); input(yyscanner); eat_until_unescaped('\''); return 1; }
<sgml>[[:alnum:]_]+=\" { feed_token(strndup(yytext, strlen(yytext) - 1), REGULAR_TOKEN); eat_until_unescaped('"'); return 1; }
<sgml>[[:alnum:]_]+=' { feed_token(strndup(yytext, strlen(yytext) - 1), REGULAR_TOKEN); eat_until_unescaped('\''); return 1; }
<sgml>[[:alnum:]_]+=[[:alnum:]_]* { feed_token(strdup(yytext), REGULAR_TOKEN); *(strchr(yyextra->token, '=') + 1) = 0; return 1; }
<sgml>[[:alnum:]_]+ { feed_token(strdup(yytext), REGULAR_TOKEN); return 1; }
<sgml>\> { BEGIN(INITIAL); }