Improve parsing of scalar literals

* Unify parsing of string literals and scalar literals, to (e.g.) ensure escapes are handled uniformly. Notably, this makes unicode escapes valid in scalar literals.
* Add a variety of custom error messages about specific failure cases of parsing string/scalar literals. For example, if we're expecting a string (e.g. a package name in the header) and the user tried using single quotes, give a clear message about that.
* Fix formatting of unicode escapes (they previously used {}, now correctly use () to match roc strings)
This commit is contained in:
Joshua Warner 2023-01-07 14:41:08 -08:00
parent 6fc593142d
commit 94070e8ba6
No known key found for this signature in database
GPG key ID: 89AD497003F93FDD
22 changed files with 411 additions and 173 deletions

View file

@ -18,7 +18,7 @@ use roc_module::called_via::CalledVia;
use roc_module::ident::{ForeignSymbol, Lowercase, TagName};
use roc_module::low_level::LowLevel;
use roc_module::symbol::Symbol;
use roc_parse::ast::{self, Defs, EscapedChar, StrLiteral};
use roc_parse::ast::{self, Defs, StrLiteral};
use roc_parse::pattern::PatternType::*;
use roc_problem::can::{PrecedenceProblem, Problem, RuntimeError};
use roc_region::all::{Loc, Region};
@ -2297,7 +2297,7 @@ fn flatten_str_lines<'a>(
);
}
}
EscapedChar(escaped) => buf.push(unescape_char(escaped)),
EscapedChar(escaped) => buf.push(escaped.unescape()),
}
}
}
@ -2355,19 +2355,6 @@ fn desugar_str_segments(var_store: &mut VarStore, segments: Vec<StrSegment>) ->
loc_expr.value
}
/// Returns the char that would have been originally parsed to
pub fn unescape_char(escaped: &EscapedChar) -> char {
use EscapedChar::*;
match escaped {
Backslash => '\\',
Quote => '"',
CarriageReturn => '\r',
Tab => '\t',
Newline => '\n',
}
}
#[derive(Clone, Debug)]
pub struct Declarations {
pub declarations: Vec<DeclarationTag>,

View file

@ -1,6 +1,6 @@
use crate::annotation::freshen_opaque_def;
use crate::env::Env;
use crate::expr::{canonicalize_expr, unescape_char, Expr, IntValue, Output};
use crate::expr::{canonicalize_expr, Expr, IntValue, Output};
use crate::num::{
finish_parsing_base, finish_parsing_float, finish_parsing_num, FloatBound, IntBound, NumBound,
ParsedNumResult,
@ -935,7 +935,7 @@ fn flatten_str_lines(lines: &[&[StrSegment<'_>]]) -> Pattern {
Interpolated(loc_expr) => {
return Pattern::UnsupportedPattern(loc_expr.region);
}
EscapedChar(escaped) => buf.push(unescape_char(escaped)),
EscapedChar(escaped) => buf.push(escaped.unescape()),
}
}
}