diff options
author | Tuomas Tynkkynen <tuomas@tuxera.com> | 2018-02-25T21·51+0200 |
---|---|---|
committer | Tuomas Tynkkynen <tuomas@tuxera.com> | 2018-03-02T15·30+0200 |
commit | a0e38c16bc7773d0fc62771a9935e079c00899ef (patch) | |
tree | 9f30fc3be4c4be6742d220a1b0363be8f053d383 | |
parent | 939cf4ccebb199e61da648873fb078ae8833263f (diff) |
libexpr: Recognize newline in more places in lexer
Flex's regexes have an annoying feature: the dot matches everything except a newline. This causes problems for expressions like: "${0}\ " where the backslash-newline combination matches this rule instead of the intended one mentioned in the comment: <STRING>\$|\\|\$\\ { /* This can only occur when we reach EOF, otherwise the above (...|\$[^\{\"\\]|\\.|\$\\.)+ would have triggered. This is technically invalid, but we leave the problem to the parser who fails with exact location. */ return STR; } However, the parser actually accepts the resulting token sequence ('"' DOLLAR_CURLY 0 '}' STR '"'), which is a problem because the lexer rule didn't assign anything to yylval. Ultimately this leads to a crash when dereferencing a NULL pointer in ExprConcatStrings::bindVars(). The fix does change the syntax of the language in some corner cases but I think it's only turning previously invalid (or crashing) syntax to valid syntax. E.g. "a\ b" and ''a''\ b'' were previously syntax errors but now both result in "a\nb". Found by afl-fuzz.
-rw-r--r-- | src/libexpr/lexer.l | 9 | ||||
-rw-r--r-- | tests/lang/eval-okay-backslash-newline-1.exp | 1 | ||||
-rw-r--r-- | tests/lang/eval-okay-backslash-newline-1.nix | 2 | ||||
-rw-r--r-- | tests/lang/eval-okay-backslash-newline-2.exp | 1 | ||||
-rw-r--r-- | tests/lang/eval-okay-backslash-newline-2.nix | 2 |
5 files changed, 11 insertions, 4 deletions
diff --git a/src/libexpr/lexer.l b/src/libexpr/lexer.l index e5e01fb5831a..1e9c29afa133 100644 --- a/src/libexpr/lexer.l +++ b/src/libexpr/lexer.l @@ -85,6 +85,7 @@ static Expr * unescapeStr(SymbolTable & symbols, const char * s, size_t length) %} +ANY .|\n ID [a-zA-Z\_][a-zA-Z0-9\_\'\-]* INT [0-9]+ FLOAT (([1-9][0-9]*\.[0-9]*)|(0?\.[0-9]+))([Ee][+-]?[0-9]+)? @@ -146,8 +147,8 @@ or { return OR_KW; } <INITIAL,INSIDE_DOLLAR_CURLY>\" { PUSH_STATE(STRING); return '"'; } -<STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)*\$/\" | -<STRING>([^\$\"\\]|\$[^\{\"\\]|\\.|\$\\.)+ { +<STRING>([^\$\"\\]|\$[^\{\"\\]|\\{ANY}|\$\\{ANY})*\$/\" | +<STRING>([^\$\"\\]|\$[^\{\"\\]|\\{ANY}|\$\\{ANY})+ { /* It is impossible to match strings ending with '$' with one regex because trailing contexts are only valid at the end of a rule. (A sane but undocumented limitation.) */ @@ -178,7 +179,7 @@ or { return OR_KW; } yylval->e = new ExprIndStr("''"); return IND_STR; } -<IND_STRING>\'\'\\. { +<IND_STRING>\'\'\\{ANY} { yylval->e = unescapeStr(data->symbols, yytext + 2, yyleng - 2); return IND_STR; } @@ -208,7 +209,7 @@ or { return OR_KW; } \#[^\r\n]* /* single-line comments */ \/\*([^*]|\*+[^*/])*\*+\/ /* long comments */ -. return yytext[0]; +{ANY} return yytext[0]; } diff --git a/tests/lang/eval-okay-backslash-newline-1.exp b/tests/lang/eval-okay-backslash-newline-1.exp new file mode 100644 index 000000000000..3e754364cc9c --- /dev/null +++ b/tests/lang/eval-okay-backslash-newline-1.exp @@ -0,0 +1 @@ +"a\nb" diff --git a/tests/lang/eval-okay-backslash-newline-1.nix b/tests/lang/eval-okay-backslash-newline-1.nix new file mode 100644 index 000000000000..7fef3dddd4dd --- /dev/null +++ b/tests/lang/eval-okay-backslash-newline-1.nix @@ -0,0 +1,2 @@ +"a\ +b" diff --git a/tests/lang/eval-okay-backslash-newline-2.exp b/tests/lang/eval-okay-backslash-newline-2.exp new file mode 100644 index 000000000000..3e754364cc9c --- /dev/null +++ b/tests/lang/eval-okay-backslash-newline-2.exp @@ -0,0 +1 @@ +"a\nb" diff --git a/tests/lang/eval-okay-backslash-newline-2.nix b/tests/lang/eval-okay-backslash-newline-2.nix new file mode 100644 index 000000000000..35ddf495c63b --- /dev/null +++ b/tests/lang/eval-okay-backslash-newline-2.nix @@ -0,0 +1,2 @@ +''a''\ +b'' |