wroclaw-git-backups/nix
1
0
Fork 0
mirror of https://github.com/NixOS/nix synced 2025-07-01 20:51:48 +02:00
Code Activity

correctly parse strings with null bytes and throw error

Browse source
This commit is contained in:
Philipp Otterbein 2025-01-04 16:14:06 +01:00
parent 442a2623e4
commit a44e9dd1ea
7 changed files with 22 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

25
src/libexpr/lexer.l
View file

@ -41,16 +41,18 @@ namespace nix {
// we make use of the fact that the parser receives a private copy of the input
// string and can munge around in it.
static StringToken unescapeStr(SymbolTable & symbols, char * s, size_t length)
// getting the position is expensive and thus it is implemented lazily.
static StringToken unescapeStr(char * const s, size_t length, std::function<Pos()> && pos)
{
char * result = s;
bool noNullByte = true;
char * t = s;
char c;
// the input string is terminated with *two* NULs, so we can safely take
// *one* character after the one being checked against.
while ((c = *s++)) {
for (size_t i = 0; i < length; t++) {
char c = s[i++];
noNullByte &= c != '\0';
if (c == '\\') {
c = *s++;
c = s[i++];
if (c == 'n') *t = '\n';
else if (c == 'r') *t = '\r';
else if (c == 't') *t = '\t';
@ -59,12 +61,14 @@ static StringToken unescapeStr(SymbolTable & symbols, char * s, size_t length)
else if (c == '\r') {
/* Normalise CR and CR/LF into LF. */
*t = '\n';
if (*s == '\n') s++; /* cr/lf */
if (s[i] == '\n') i++; /* cr/lf */
}
else *t = c;
t++;
}
return {result, size_t(t - result)};
if (!noNullByte) {
forceNoNullByte({s, size_t(t - s)}, std::move(pos));
}
return {s, size_t(t - s)};
}
static void requireExperimentalFeature(const ExperimentalFeature & feature, const Pos & pos)
@ -175,7 +179,7 @@ or { return OR_KW; }
/* 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->str = unescapeStr(state->symbols, yytext, yyleng);
yylval->str = unescapeStr(yytext, yyleng, [&]() { return state->positions[CUR_POS]; });
return STR;
}
<STRING>\$\{ { PUSH_STATE(DEFAULT); return DOLLAR_CURLY; }
@ -191,6 +195,7 @@ or { return OR_KW; }
\'\'(\ *\n)? { PUSH_STATE(IND_STRING); return IND_STRING_OPEN; }
<IND_STRING>([^\$\']|\$[^\{\']|\'[^\'\$])+ {
yylval->str = {yytext, (size_t) yyleng, true};
forceNoNullByte(yylval->str, [&]() { return state->positions[CUR_POS]; });
return IND_STR;
}
<IND_STRING>\'\'\$ |
@ -203,7 +208,7 @@ or { return OR_KW; }
return IND_STR;
}
<IND_STRING>\'\'\\{ANY} {
yylval->str = unescapeStr(state->symbols, yytext + 2, yyleng - 2);
yylval->str = unescapeStr(yytext + 2, yyleng - 2, [&]() { return state->positions[CUR_POS]; });
return IND_STR;
}
<IND_STRING>\$\{ { PUSH_STATE(DEFAULT); return DOLLAR_CURLY; }