diff options
Diffstat (limited to 'src/libexpr/parser/grammar.hh')
| -rw-r--r-- | src/libexpr/parser/grammar.hh | 122 |
1 files changed, 71 insertions, 51 deletions
diff --git a/src/libexpr/parser/grammar.hh b/src/libexpr/parser/grammar.hh index 2c5a3d1be..701b40505 100644 --- a/src/libexpr/parser/grammar.hh +++ b/src/libexpr/parser/grammar.hh @@ -12,7 +12,7 @@ // eolf rules in favor of reproducing the old flex lexer as faithfully as // possible, and deferring calculation of positions to downstream users. -namespace nix::parser::grammar { +namespace nix::parser::grammar::v1 { using namespace tao::pegtl; namespace p = tao::pegtl; @@ -225,7 +225,8 @@ struct string : _string, seq< > {}; struct _ind_string { - template<bool Indented, typename... Inner> + struct line_start : semantic, star<one<' '>> {}; + template<typename... Inner> struct literal : semantic, seq<Inner...> {}; struct interpolation : semantic, seq< p::string<'$', '{'>, seps, @@ -233,34 +234,53 @@ struct _ind_string { must<one<'}'>> > {}; struct escape : semantic, must<any> {}; + /* Marker for non-empty lines */ + struct has_content : semantic, seq<> {}; }; struct ind_string : _ind_string, seq< TAO_PEGTL_STRING("''"), + // Strip first line completely if empty opt<star<one<' '>>, one<'\n'>>, - star< - sor< - _ind_string::literal< - true, + list< + seq< + // Start a line with some indentation + // (we always match even the empty string if no indentation, as this creates the line) + _ind_string::line_start, + // The actual line + opt< plus< sor< - not_one<'$', '\''>, - seq<one<'$'>, not_one<'{', '\''>>, - seq<one<'\''>, not_one<'\'', '$'>> - > - > - >, - _ind_string::interpolation, - _ind_string::literal<false, one<'$'>>, - _ind_string::literal<false, one<'\''>, not_at<one<'\''>>>, - seq<one<'\''>, _ind_string::literal<false, p::string<'\'', '\''>>>, - seq< - p::string<'\'', '\''>, - sor< - _ind_string::literal<false, one<'$'>>, - seq<one<'\\'>, _ind_string::escape> + _ind_string::literal< + plus< + sor< + not_one<'$', '\'', '\n'>, + // TODO probably factor this out like the others for performance + seq<one<'$'>, not_one<'{', '\'', '\n'>>, + seq<one<'$'>, at<one<'\n'>>>, + seq<one<'\''>, not_one<'\'', '$', '\n'>>, + seq<one<'\''>, at<one<'\n'>>> + > + > + >, + _ind_string::interpolation, + _ind_string::literal<one<'$'>>, + _ind_string::literal<one<'\''>, not_at<one<'\''>>>, + seq<one<'\''>, _ind_string::literal<p::string<'\'', '\''>>>, + seq< + p::string<'\'', '\''>, + sor< + _ind_string::literal<one<'$'>>, + seq<one<'\\'>, _ind_string::escape> + > + > + >, + _ind_string::has_content > > - > + >, + // End of line, LF. CR is just ignored and not treated as ending a line + // (for the purpose of indentation stripping) + _ind_string::literal<one<'\n'>> >, must<TAO_PEGTL_STRING("''")> > {}; @@ -352,10 +372,10 @@ struct formals : semantic, _formals, seq< struct _attr { struct simple : semantic, sor<t::identifier, t::kw_or> {}; - struct string : semantic, seq<grammar::string> {}; + struct string : semantic, seq<grammar::v1::string> {}; struct expr : semantic, seq< TAO_PEGTL_STRING("${"), seps, - must<grammar::expr>, seps, + must<grammar::v1::expr>, seps, must<one<'}'>> > {}; }; @@ -452,9 +472,9 @@ struct _expr { struct id : semantic, t::identifier {}; struct int_ : semantic, t::integer {}; struct float_ : semantic, t::floating {}; - struct string : semantic, seq<grammar::string> {}; - struct ind_string : semantic, seq<grammar::ind_string> {}; - struct path : semantic, seq<grammar::path> {}; + struct string : semantic, seq<grammar::v1::string> {}; + struct ind_string : semantic, seq<grammar::v1::ind_string> {}; + struct path : semantic, seq<grammar::v1::path> {}; struct uri : semantic, t::uri {}; struct ancient_let : semantic, _attrset<must, t::kw_let, seps> {}; struct rec_set : semantic, _attrset<must, t::kw_rec, seps> {}; @@ -628,34 +648,34 @@ struct nothing : p::nothing<Rule> { template<typename Self, typename OpCtx, typename AttrPathT, typename ExprT> struct operator_semantics { - struct has_attr : grammar::op::has_attr { + struct has_attr : grammar::v1::op::has_attr { AttrPathT path; }; struct OpEntry { OpCtx ctx; uint8_t prec; - grammar::op::kind assoc; + grammar::v1::op::kind assoc; std::variant< - grammar::op::not_, - grammar::op::unary_minus, - grammar::op::implies, - grammar::op::or_, - grammar::op::and_, - grammar::op::equals, - grammar::op::not_equals, - grammar::op::less_eq, - grammar::op::greater_eq, - grammar::op::update, - grammar::op::concat, - grammar::op::less, - grammar::op::greater, - grammar::op::plus, - grammar::op::minus, - grammar::op::mul, - grammar::op::div, - grammar::op::pipe_right, - grammar::op::pipe_left, + grammar::v1::op::not_, + grammar::v1::op::unary_minus, + grammar::v1::op::implies, + grammar::v1::op::or_, + grammar::v1::op::and_, + grammar::v1::op::equals, + grammar::v1::op::not_equals, + grammar::v1::op::less_eq, + grammar::v1::op::greater_eq, + grammar::v1::op::update, + grammar::v1::op::concat, + grammar::v1::op::less, + grammar::v1::op::greater, + grammar::v1::op::plus, + grammar::v1::op::minus, + grammar::v1::op::mul, + grammar::v1::op::div, + grammar::v1::op::pipe_right, + grammar::v1::op::pipe_left, has_attr > op; }; @@ -676,7 +696,7 @@ struct operator_semantics { auto & [ctx, precedence, kind, op] = ops.back(); // NOTE this relies on associativity not being mixed within a precedence level. if ((precedence > toPrecedence) - || (kind != grammar::op::kind::leftAssoc && precedence == toPrecedence)) + || (kind != grammar::v1::op::kind::leftAssoc && precedence == toPrecedence)) break; std::visit([&, ctx=std::move(ctx)] (auto & op) { exprs.push_back(static_cast<Self &>(*this).applyOp(ctx, op, args...)); @@ -694,9 +714,9 @@ struct operator_semantics { void pushOp(OpCtx ctx, auto o, auto &... args) { - if (o.kind != grammar::op::kind::unary) + if (o.kind != grammar::v1::op::kind::unary) reduce(o.precedence, args...); - if (!ops.empty() && o.kind == grammar::op::kind::nonAssoc) { + if (!ops.empty() && o.kind == grammar::v1::op::kind::nonAssoc) { auto & [_pos, _prec, _kind, _o] = ops.back(); if (_kind == o.kind && _prec == o.precedence) Self::badOperator(ctx, args...); |