Parsing support for snake_case identifiers

In this initial commit, I have done the following:

- Added unit tests to roc_parse's ident.rs file to cover at least the
  simplest Ident enum cases (Tag, OpaqueRef, and simple Access)
- Added '_' as a valid "rest" character in both uppercase and lowercase
  identifier parts
- Updated the test_syntax snapshots appropriately

There is still a lot left to do here. Such as:

- Do we want to allow multiple '_'s to parse successfully?
- Handle qualified access
- Handle accessor functions
- Handle record update functions
- Remove the UnderscoreInMiddle case from BadIdent
- Write unit tests for Malformed Idents

I am not a "Rustacean" by any means, but have been through the Book in
years past.  Any feedback on the way I wrote the tests or any other part
of the implementation would be very appreciated.
This commit is contained in:
Anthony Bullard 2024-11-20 09:00:57 -06:00
parent d7825428df
commit a2083cec30
No known key found for this signature in database
31 changed files with 1214 additions and 460 deletions

View file

@ -1,5 +1,5 @@
use bumpalo::Bump;
use roc_fmt::{annotation::Formattable, header::fmt_header};
use roc_fmt::{annotation::Formattable, annotation::MigrationFlags, header::fmt_header};
use roc_parse::{
ast::{Defs, Expr, FullAst, Header, Malformed, SpacesBefore},
header::parse_module_defs,
@ -83,24 +83,25 @@ impl<'a> Output<'a> {
pub fn format(&self) -> InputOwned {
let arena = Bump::new();
let mut buf = Buf::new_in(&arena);
let flags = MigrationFlags::new(false);
match self {
Output::Header(header) => {
fmt_header(&mut buf, header);
fmt_header(&mut buf, header, &flags);
buf.fmt_end_of_file();
InputOwned::Header(buf.as_str().to_string())
}
Output::ModuleDefs(defs) => {
defs.format(&mut buf, 0);
defs.format(&mut buf, &flags, 0);
buf.fmt_end_of_file();
InputOwned::ModuleDefs(buf.as_str().to_string())
}
Output::Expr(expr) => {
expr.format(&mut buf, 0);
expr.format(&mut buf, &flags, 0);
InputOwned::Expr(buf.as_str().to_string())
}
Output::Full(full) => {
fmt_header(&mut buf, &full.header);
full.defs.format(&mut buf, 0);
fmt_header(&mut buf, &full.header, &flags);
full.defs.format(&mut buf, &flags, 0);
buf.fmt_end_of_file();
InputOwned::Full(buf.as_str().to_string())
}

View file

@ -1,13 +0,0 @@
Closure(
[
@1-11 MalformedIdent(
"the_answer",
UnderscoreInMiddle(
@5,
),
),
],
@15-17 Num(
"42",
),
)

View file

@ -1,42 +0,0 @@
Defs(
Defs {
tags: [
EitherIndex(0),
],
regions: [
@0-3,
],
space_before: [
Slice<roc_parse::ast::CommentOrNewline> { start: 0, length: 0 },
],
space_after: [
Slice<roc_parse::ast::CommentOrNewline> { start: 0, length: 0 },
],
spaces: [],
type_defs: [
Alias {
header: TypeHeader {
name: @0-1 "J",
vars: [],
},
ann: @2-3 Apply(
"",
"R",
[],
),
},
],
value_defs: [],
},
@5-8 SpaceBefore(
MalformedIdent(
"n_p",
UnderscoreInMiddle(
@7,
),
),
[
Newline,
],
),
)

View file

@ -0,0 +1,15 @@
SpaceAfter(
Closure(
[
@1-11 Identifier {
ident: "the_answer",
},
],
@15-17 Num(
"42",
),
),
[
Newline,
],
)

View file

@ -0,0 +1,45 @@
SpaceAfter(
Defs(
Defs {
tags: [
EitherIndex(0),
],
regions: [
@0-3,
],
space_before: [
Slice<roc_parse::ast::CommentOrNewline> { start: 0, length: 0 },
],
space_after: [
Slice<roc_parse::ast::CommentOrNewline> { start: 0, length: 0 },
],
spaces: [],
type_defs: [
Alias {
header: TypeHeader {
name: @0-1 "J",
vars: [],
},
ann: @2-3 Apply(
"",
"R",
[],
),
},
],
value_defs: [],
},
@4-7 SpaceBefore(
Var {
module_name: "",
ident: "n_p",
},
[
Newline,
],
),
),
[
Newline,
],
)

View file

@ -4,6 +4,7 @@ extern crate indoc;
#[cfg(test)]
mod test_fmt {
use bumpalo::Bump;
use roc_fmt::annotation::MigrationFlags;
use roc_fmt::def::fmt_defs;
use roc_fmt::header::fmt_header;
use roc_fmt::Buf;
@ -36,11 +37,12 @@ mod test_fmt {
state: State<'a>,
buf: &mut Buf<'_>,
) {
fmt_header(buf, header);
let flags = MigrationFlags::new(false);
fmt_header(buf, header, &flags);
match parse_module_defs(arena, state, Defs::default()) {
Ok(loc_defs) => {
fmt_defs(buf, &loc_defs, 0);
fmt_defs(buf, &loc_defs, &flags, 0);
}
Err(error) => {
let src = if src.len() > 1000 {
@ -1492,7 +1494,7 @@ mod test_fmt {
fn parenthetical_def() {
expr_formats_same(indoc!(
r"
(UserId userId) = 5
(UserId user_id) = 5
y = 10
42
@ -1502,7 +1504,7 @@ mod test_fmt {
expr_formats_same(indoc!(
r"
# A
(UserId userId) = 5
(UserId user_id) = 5
# B
y = 10
@ -1539,13 +1541,13 @@ mod test_fmt {
fn lambda_returns_record() {
expr_formats_same(indoc!(
r"
toRecord = \_ -> {
to_record = \_ -> {
x: 1,
y: 2,
z: 3,
}
toRecord
to_record
"
));
@ -1560,7 +1562,7 @@ mod test_fmt {
expr_formats_same(indoc!(
r"
toRecord = \_ ->
to_record = \_ ->
val = 0
{
@ -1569,32 +1571,32 @@ mod test_fmt {
z: 3,
}
toRecord
to_record
"
));
expr_formats_to(
indoc!(
r"
toRecord = \_ ->
to_record = \_ ->
{
x: 1,
y: 2,
z: 3,
}
toRecord
to_record
"
),
indoc!(
r"
toRecord = \_ -> {
to_record = \_ -> {
x: 1,
y: 2,
z: 3,
}
toRecord
to_record
"
),
);
@ -1604,13 +1606,13 @@ mod test_fmt {
fn lambda_returns_list() {
expr_formats_same(indoc!(
r"
toList = \_ -> [
to_list = \_ -> [
1,
2,
3,
]
toList
to_list
"
));
@ -1625,7 +1627,7 @@ mod test_fmt {
expr_formats_same(indoc!(
r"
toList = \_ ->
to_list = \_ ->
val = 0
[
@ -1634,32 +1636,32 @@ mod test_fmt {
3,
]
toList
to_list
"
));
expr_formats_to(
indoc!(
r"
toList = \_ ->
to_list = \_ ->
[
1,
2,
3,
]
toList
to_list
"
),
indoc!(
r"
toList = \_ -> [
to_list = \_ -> [
1,
2,
3,
]
toList
to_list
"
),
);
@ -3116,7 +3118,7 @@ mod test_fmt {
expr_formats_same(indoc!(
r"
myDef =
my_def =
list = [
a,
b,
@ -3127,7 +3129,7 @@ mod test_fmt {
d,
}
myDef
my_def
"
));
@ -3672,7 +3674,7 @@ mod test_fmt {
fn def_when() {
expr_formats_same(indoc!(
r"
myLongFunctionName = \x ->
my_long_function_name = \x ->
when b is
1 | 2 ->
when c is
@ -4974,10 +4976,10 @@ mod test_fmt {
exposes []
packages {}
imports []
provides [ mainForHost ]
provides [ main_for_host ]
mainForHost : { init : ({} -> Model) as Init, update : (Model, Str -> Model) as Update, view : (Model -> Str) as View }
mainForHost = main
main_for_host : { init : ({} -> Model) as Init, update : (Model, Str -> Model) as Update, view : (Model -> Str) as View }
main_for_host = main
"#
),
indoc!(
@ -4987,10 +4989,10 @@ mod test_fmt {
exposes []
packages {}
imports []
provides [mainForHost]
provides [main_for_host]
mainForHost : { init : ({} -> Model) as Init, update : (Model, Str -> Model) as Update, view : (Model -> Str) as View }
mainForHost = main
main_for_host : { init : ({} -> Model) as Init, update : (Model, Str -> Model) as Update, view : (Model -> Str) as View }
main_for_host = main
"#
),
);
@ -5313,8 +5315,8 @@ mod test_fmt {
fn backpassing_simple() {
expr_formats_same(indoc!(
r"
getChar = \ctx ->
x <- Task.await (getCharScope scope)
get_char = \ctx ->
x <- Task.await (get_char_scope scope)
42
42
@ -5326,8 +5328,8 @@ mod test_fmt {
fn backpassing_apply_tag() {
expr_formats_same(indoc!(
r"
getChar = \ctx ->
(T val newScope) <- Task.await (getCharScope scope)
get_char = \ctx ->
(T val new_scope) <- Task.await (get_char_scope scope)
42
42
@ -5406,9 +5408,9 @@ mod test_fmt {
fn backpassing_body_on_newline() {
expr_formats_same(indoc!(
r"
getChar = \ctx ->
get_char = \ctx ->
x <-
Task.await (getCharScope scope)
Task.await (get_char_scope scope)
42
42

View file

@ -265,12 +265,10 @@ mod test_snapshots {
fail/where_type_variable.expr,
fail/wild_case_arrow.expr,
malformed/bad_opaque_ref.expr,
malformed/malformed_ident_due_to_underscore.expr,
malformed/malformed_pattern_field_access.expr, // See https://github.com/roc-lang/roc/issues/399
malformed/malformed_pattern_module_name.expr, // See https://github.com/roc-lang/roc/issues/399
malformed/module_dot_tuple.expr,
malformed/qualified_tag.expr,
malformed/underscore_expr_in_def.expr,
pass/ability_demand_signature_is_multiline.expr,
pass/ability_multi_line.expr,
pass/ability_single_line.expr,
@ -575,6 +573,7 @@ mod test_snapshots {
pass/return_with_after.expr,
pass/separate_defs.moduledefs,
pass/single_arg_closure.expr,
pass/single_arg_with_underscore_closure.expr,
pass/single_underscore_closure.expr,
pass/space_before_colon.full,
pass/space_before_parens_space_after.expr,
@ -627,6 +626,7 @@ mod test_snapshots {
pass/unary_not.expr,
pass/unary_not_with_parens.expr,
pass/underscore_backpassing.expr,
pass/underscore_expr_in_def.expr,
pass/underscore_in_assignment_pattern.expr,
pass/value_def_confusion.expr,
pass/var_else.expr,