wroclaw-git-backups/nix
1
0
Fork 0
mirror of https://github.com/NixOS/nix synced 2025-06-28 22:01:15 +02:00
Code Activity

remove ExprIndStr

Browse source 
it can be replaced with StringToken if we add another bit if information to
StringToken, namely whether this string should take part in indentation scanning
or not. since all escaping terminates indentation scanning we need to set this
bit only for the non-escaped IND_STRING rule.

this improves performance by about 1%.

 before

  nix search --no-eval-cache --offline ../nixpkgs hello
    Time (mean ± σ):      8.880 s ±  0.048 s    [User: 6.809 s, System: 1.643 s]
    Range (min … max):    8.781 s …  8.993 s    20 runs

  nix eval -f ../nixpkgs/pkgs/development/haskell-modules/hackage-packages.nix
    Time (mean ± σ):     375.0 ms ±   2.2 ms    [User: 339.8 ms, System: 35.2 ms]
    Range (min … max):   371.5 ms … 379.3 ms    20 runs

  nix eval --raw --impure --expr 'with import <nixpkgs/nixos> {}; system'
    Time (mean ± σ):      2.831 s ±  0.040 s    [User: 2.536 s, System: 0.225 s]
    Range (min … max):    2.769 s …  2.912 s    20 runs

 after

  nix search --no-eval-cache --offline ../nixpkgs hello
    Time (mean ± σ):      8.832 s ±  0.048 s    [User: 6.757 s, System: 1.657 s]
    Range (min … max):    8.743 s …  8.921 s    20 runs

  nix eval -f ../nixpkgs/pkgs/development/haskell-modules/hackage-packages.nix
    Time (mean ± σ):     367.4 ms ±   3.2 ms    [User: 332.7 ms, System: 34.7 ms]
    Range (min … max):   364.6 ms … 374.6 ms    20 runs

  nix eval --raw --impure --expr 'with import <nixpkgs/nixos> {}; system'
    Time (mean ± σ):      2.810 s ±  0.030 s    [User: 2.517 s, System: 0.225 s]
    Range (min … max):    2.742 s …  2.854 s    20 runs
This commit is contained in:
pennae 2022-01-19 13:39:42 +01:00
parent bc443511eb
commit 0a7746603e
3 changed files with 57 additions and 54 deletions
Download patch file Download diff file Expand all files Collapse all files

18
src/libexpr/lexer.l
View file

@ -66,7 +66,7 @@ static void adjustLoc(YYLTYPE * loc, const char * s, size_t len)
// we make use of the fact that the parser receives a private copy of the input
// string and can munge around in it.
static Expr * unescapeStr(SymbolTable & symbols, char * s, size_t length)
static StringToken unescapeStr(SymbolTable & symbols, char * s, size_t length)
{
char * result = s;
char * t = s;
@ -89,7 +89,7 @@ static Expr * unescapeStr(SymbolTable & symbols, char * s, size_t length)
else *t = c;
t++;
}
return new ExprString(symbols.create({result, size_t(t - result)}));
return {result, size_t(t - result)};
}
@ -176,7 +176,7 @@ or { return OR_KW; }
/* It is impossible to match strings ending with '$' with one
regex because trailing contexts are only valid at the end
of a rule. (A sane but undocumented limitation.) */
yylval->e = unescapeStr(data->symbols, yytext, yyleng);
yylval->str = unescapeStr(data->symbols, yytext, yyleng);
return STR;
}
<STRING>\$\{ { PUSH_STATE(DEFAULT); return DOLLAR_CURLY; }
@ -191,26 +191,26 @@ or { return OR_KW; }
\'\'(\ *\n)? { PUSH_STATE(IND_STRING); return IND_STRING_OPEN; }
<IND_STRING>([^\$\']|\$[^\{\']|\'[^\'\$])+ {
yylval->e = new ExprIndStr(yytext);
yylval->str = {yytext, (size_t) yyleng, true};
return IND_STR;
}
<IND_STRING>\'\'\$ |
<IND_STRING>\$ {
yylval->e = new ExprIndStr("$");
yylval->str = {"$", 1};
return IND_STR;
}
<IND_STRING>\'\'\' {
yylval->e = new ExprIndStr("''");
yylval->str = {"''", 2};
return IND_STR;
}
<IND_STRING>\'\'\\{ANY} {
yylval->e = unescapeStr(data->symbols, yytext + 2, yyleng - 2);
yylval->str = unescapeStr(data->symbols, yytext + 2, yyleng - 2);
return IND_STR;
}
<IND_STRING>\$\{ { PUSH_STATE(DEFAULT); return DOLLAR_CURLY; }
<IND_STRING>\'\' { POP_STATE(); return IND_STRING_CLOSE; }
<IND_STRING>\' {
yylval->e = new ExprIndStr("'");
yylval->str = {"'", 1};
return IND_STR;
}
@ -264,7 +264,7 @@ or { return OR_KW; }
PUSH_STATE(INPATH_SLASH);
else
PUSH_STATE(INPATH);
yylval->e = new ExprString(data->symbols.create(string(yytext)));
yylval->str = {yytext, (size_t) yyleng};
return STR;
}
<INPATH>{ANY} |