diff options
Diffstat (limited to 'src/libexpr/lexer.l')
| -rw-r--r-- | src/libexpr/lexer.l | 24 |
1 files changed, 14 insertions, 10 deletions
diff --git a/src/libexpr/lexer.l b/src/libexpr/lexer.l index 828356bbf447..29ca327c1e4e 100644 --- a/src/libexpr/lexer.l +++ b/src/libexpr/lexer.l @@ -49,9 +49,10 @@ static void adjustLoc(YYLTYPE * loc, const char * s, size_t len) } -static Expr * unescapeStr(SymbolTable & symbols, const char * s) +static Expr * unescapeStr(SymbolTable & symbols, const char * s, size_t length) { string t; + t.reserve(length); char c; while ((c = *s++)) { if (c == '\\') { @@ -84,13 +85,14 @@ static Expr * unescapeStr(SymbolTable & symbols, const char * s) %} +ANY .|\n ID [a-zA-Z\_][a-zA-Z0-9\_\'\-]* INT [0-9]+ FLOAT (([1-9][0-9]*\.[0-9]*)|(0?\.[0-9]+))([Ee][+-]?[0-9]+)? PATH [a-zA-Z0-9\.\_\-\+]*(\/[a-zA-Z0-9\.\_\-\+]+)+\/? HPATH \~(\/[a-zA-Z0-9\.\_\-\+]+)+\/? SPATH \<[a-zA-Z0-9\.\_\-\+]+(\/[a-zA-Z0-9\.\_\-\+]+)*\> -URI [a-zA-Z][a-zA-Z0-9\+\-\.]*\:\/\/[a-zA-Z0-9\%\/\?\:\@\&\=\+\$\,\-\_\.\!\~\*\']+|channel\:[a-zA-Z0-9\%\/\?\:\@\&\=\+\$\,\-\_\.\!\~\*\']+ +URI [a-zA-Z][a-zA-Z0-9\+\-\.]*\:[a-zA-Z0-9\%\/\?\:\@\&\=\+\$\,\-\_\.\!\~\*\']+ %% @@ -145,12 +147,12 @@ or { return OR_KW; } <INITIAL,INSIDE_DOLLAR_CURLY>\" { PUSH_STATE(STRING); return '"'; } -<STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)*\$/\" | -<STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)+ { +<STRING>([^\$\"\\]|\$[^\{\"\\]|\\{ANY}|\$\\{ANY})*\$/\" | +<STRING>([^\$\"\\]|\$[^\{\"\\]|\\{ANY}|\$\\{ANY})+ { /* It is impossible to match strings ending with '$' with one regex because trailing contexts are only valid at the end of a rule. (A sane but undocumented limitation.) */ - yylval->e = unescapeStr(data->symbols, yytext); + yylval->e = unescapeStr(data->symbols, yytext, yyleng); return STR; } <STRING>\$\{ { PUSH_STATE(INSIDE_DOLLAR_CURLY); return DOLLAR_CURLY; } @@ -177,8 +179,8 @@ or { return OR_KW; } yylval->e = new ExprIndStr("''"); return IND_STR; } -<IND_STRING>\'\'\\. { - yylval->e = unescapeStr(data->symbols, yytext + 2); +<IND_STRING>\'\'\\{ANY} { + yylval->e = unescapeStr(data->symbols, yytext + 2, yyleng - 2); return IND_STR; } <IND_STRING>\$\{ { PUSH_STATE(INSIDE_DOLLAR_CURLY); return DOLLAR_CURLY; } @@ -207,11 +209,13 @@ or { return OR_KW; } \#[^\r\n]* /* single-line comments */ \/\*([^*]|\*+[^*/])*\*+\/ /* long comments */ -. return yytext[0]; +{ANY} { + /* Don't return a negative number, as this will cause + Bison to stop parsing without an error. */ + return (unsigned char) yytext[0]; + } } -<<EOF>> { data->atEnd = true; return 0; } - %% |