kloenk/lix
0
0
Fork 0
forked from lix-project/lix
Code Pull requests Activity

lexer: remove catch-all rules hiding real errors

Browse source 
With catch-all rules, we hide potential errors.
It turns out that a4744254 made one cath-all useless. Flex detected that
is was impossible to reach.
The other is more subtle, as it can only trigger on unfinished escapes
in unfinished strings, which only occurs at EOF.
This commit is contained in:
Guillaume Maudoux 2017-05-01 01:07:33 +02:00
parent a474425425
commit a143014d73
1 changed files with 17 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
src/libexpr/lexer.l
View file

@ -142,18 +142,26 @@ or { return OR_KW; }
\{ { return '{'; } \{ { return '{'; }
<INSIDE_DOLLAR_CURLY>\{ { PUSH_STATE(INSIDE_DOLLAR_CURLY); return '{'; } <INSIDE_DOLLAR_CURLY>\{ { PUSH_STATE(INSIDE_DOLLAR_CURLY); return '{'; }
<INITIAL,INSIDE_DOLLAR_CURLY>\" { PUSH_STATE(STRING); return '"'; } <INITIAL,INSIDE_DOLLAR_CURLY>\" {
PUSH_STATE(STRING); return '"';
}
<STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)*\$/\" | <STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)*\$/\" |
<STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)+ { <STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)+ {
/* It is impossible to match strings ending with '$' with one /* It is impossible to match strings ending with '$' with one
regex because trailing contexts are only valid at the end regex because trailing contexts are only valid at the end
of a rule. (A sane but undocumented limitation.) */ of a rule. (A sane but undocumented limitation.) */
yylval->e = unescapeStr(data->symbols, yytext); yylval->e = unescapeStr(data->symbols, yytext);
return STR; return STR;
} }
<STRING>\$\{ { PUSH_STATE(INSIDE_DOLLAR_CURLY); return DOLLAR_CURLY; } <STRING>\$\{ { PUSH_STATE(INSIDE_DOLLAR_CURLY); return DOLLAR_CURLY; }
<STRING>\" { POP_STATE(); return '"'; } <STRING>\" { POP_STATE(); return '"'; }
<STRING>. return yytext[0]; /* just in case: shouldn't be reached */ <STRING>\$|\\|\$\\ {
/* This can only occur when we reach EOF, otherwise the above
(...|\$[^\{\"\\]|\\.|\$\\.)+ would have triggered.
This is technically invalid, but we leave the problem to the
parser who fails with exact location. */
return STR;
}
<INITIAL,INSIDE_DOLLAR_CURLY>\'\'(\ *\n)? { PUSH_STATE(IND_STRING); return IND_STRING_OPEN; } <INITIAL,INSIDE_DOLLAR_CURLY>\'\'(\ *\n)? { PUSH_STATE(IND_STRING); return IND_STRING_OPEN; }
<IND_STRING>([^\$\']|\$[^\{\']|\'[^\'\$])+ { <IND_STRING>([^\$\']|\$[^\{\']|\'[^\'\$])+ {
@ -179,7 +187,6 @@ or { return OR_KW; }
yylval->e = new ExprIndStr("'"); yylval->e = new ExprIndStr("'");
return IND_STR; return IND_STR;
} }
<IND_STRING>. return yytext[0]; /* just in case: shouldn't be reached */
<INITIAL,INSIDE_DOLLAR_CURLY>{ <INITIAL,INSIDE_DOLLAR_CURLY>{