nushell/crates/nu-parser/src/parser.rs

5074 lines
166 KiB
Rust
Raw Normal View History

2021-09-02 10:25:22 +02:00
use crate::{
lex, lite_parse,
lite_parse::LiteCommand,
parse_keywords::{parse_extern, parse_for, parse_source},
2021-09-02 10:25:22 +02:00
type_check::{math_result_type, type_compatible},
LiteBlock, ParseError, Token, TokenContents,
2021-08-17 01:00:00 +02:00
};
2021-07-02 03:42:25 +02:00
2021-09-02 03:29:43 +02:00
use nu_protocol::{
ast::{
Block, Call, CellPath, Expr, Expression, FullCellPath, ImportPattern, ImportPatternHead,
ImportPatternMember, Operator, PathMember, Pipeline, RangeInclusion, RangeOperator,
},
2021-09-02 20:21:37 +02:00
engine::StateWorkingSet,
span, BlockId, Flag, PositionalArg, Signature, Span, Spanned, SyntaxShape, Type, Unit, VarId,
CONFIG_VARIABLE_ID, ENV_VARIABLE_ID, IN_VARIABLE_ID,
2021-09-02 03:29:43 +02:00
};
2021-07-23 23:19:30 +02:00
2021-09-26 20:39:19 +02:00
use crate::parse_keywords::{
2021-11-02 21:56:00 +01:00
parse_alias, parse_def, parse_def_predecl, parse_hide, parse_let, parse_module, parse_use,
2021-09-02 03:29:43 +02:00
};
2021-07-23 23:19:30 +02:00
2022-01-01 22:42:50 +01:00
use log::trace;
2022-03-01 00:31:53 +01:00
use std::{
collections::{HashMap, HashSet},
num::ParseIntError,
};
2021-11-02 21:56:00 +01:00
#[cfg(feature = "plugin")]
use crate::parse_keywords::parse_register;
2021-11-02 21:56:00 +01:00
2021-07-02 09:15:30 +02:00
#[derive(Debug, Clone)]
2021-06-30 03:42:56 +02:00
pub enum Import {}
2021-09-26 20:39:19 +02:00
pub fn garbage(span: Span) -> Expression {
2021-07-01 02:01:04 +02:00
Expression::garbage(span)
}
pub fn garbage_pipeline(spans: &[Span]) -> Pipeline {
Pipeline::from_vec(vec![garbage(span(spans))])
2021-09-10 09:28:43 +02:00
}
2021-07-01 03:31:02 +02:00
fn is_identifier_byte(b: u8) -> bool {
b != b'.' && b != b'[' && b != b'(' && b != b'{'
}
pub fn is_math_expression_like(
working_set: &mut StateWorkingSet,
span: Span,
expand_aliases_denylist: &[usize],
) -> bool {
let bytes = working_set.get_span_contents(span);
if bytes.is_empty() {
return false;
}
2022-04-06 21:10:25 +02:00
if bytes == b"true" || bytes == b"false" || bytes == b"null" || bytes == b"not" {
return true;
}
let b = bytes[0];
if b == b'('
|| b == b'{'
|| b == b'['
|| b == b'$'
|| b == b'"'
|| b == b'\''
|| b == b'`'
|| b == b'-'
{
return true;
}
if parse_number(bytes, span).1.is_none() {
return true;
}
if parse_filesize(working_set, span).1.is_none() {
return true;
}
if parse_duration(working_set, span).1.is_none() {
return true;
}
if parse_binary(working_set, span).1.is_none() {
return true;
}
if parse_range(working_set, span, expand_aliases_denylist)
.1
.is_none()
{
return true;
}
false
}
2021-07-01 03:31:02 +02:00
fn is_identifier(bytes: &[u8]) -> bool {
bytes.iter().all(|x| is_identifier_byte(*x))
}
fn is_variable(bytes: &[u8]) -> bool {
if bytes.len() > 1 && bytes[0] == b'$' {
is_identifier(&bytes[1..])
} else {
is_identifier(bytes)
}
}
2021-11-14 20:40:26 +01:00
pub fn trim_quotes(bytes: &[u8]) -> &[u8] {
if (bytes.starts_with(b"\"") && bytes.ends_with(b"\"") && bytes.len() > 1)
|| (bytes.starts_with(b"\'") && bytes.ends_with(b"\'") && bytes.len() > 1)
|| (bytes.starts_with(b"`") && bytes.ends_with(b"`") && bytes.len() > 1)
2021-11-14 20:40:26 +01:00
{
&bytes[1..(bytes.len() - 1)]
} else {
bytes
}
}
pub fn check_call(command: Span, sig: &Signature, call: &Call) -> Option<ParseError> {
2021-10-13 19:53:27 +02:00
// Allow the call to pass if they pass in the help flag
if call.named.iter().any(|(n, _)| n.item == "help") {
return None;
}
2021-07-02 04:22:54 +02:00
if call.positional.len() < sig.required_positional.len() {
// Comparing the types of all signature positional arguments against the parsed
// expressions found in the call. If one type is not found then it could be assumed
// that that positional argument is missing from the parsed call
for argument in &sig.required_positional {
let found = call.positional.iter().fold(false, |ac, expr| {
if argument.shape.to_type() == expr.ty || argument.shape == SyntaxShape::Any {
true
} else {
ac
}
});
if !found {
2022-01-04 00:14:33 +01:00
if let Some(last) = call.positional.last() {
return Some(ParseError::MissingPositional(
argument.name.clone(),
Span {
start: last.span.end,
end: last.span.end,
},
sig.call_signature(),
));
} else {
return Some(ParseError::MissingPositional(
argument.name.clone(),
Span {
start: command.end,
end: command.end,
},
2022-01-04 00:14:33 +01:00
sig.call_signature(),
));
}
}
}
2021-07-02 04:22:54 +02:00
let missing = &sig.required_positional[call.positional.len()];
2022-01-04 00:14:33 +01:00
if let Some(last) = call.positional.last() {
Some(ParseError::MissingPositional(
missing.name.clone(),
Span {
start: last.span.end,
end: last.span.end,
},
sig.call_signature(),
))
} else {
Some(ParseError::MissingPositional(
missing.name.clone(),
Span {
start: command.end,
end: command.end,
},
2022-01-04 00:14:33 +01:00
sig.call_signature(),
))
}
2021-07-02 04:22:54 +02:00
} else {
for req_flag in sig.named.iter().filter(|x| x.required) {
2021-10-11 23:17:45 +02:00
if call.named.iter().all(|(n, _)| n.item != req_flag.long) {
2021-07-02 04:22:54 +02:00
return Some(ParseError::MissingRequiredFlag(
req_flag.long.clone(),
command,
));
}
}
None
}
}
2021-09-26 20:39:19 +02:00
pub fn check_name<'a>(
2021-09-02 10:25:22 +02:00
working_set: &mut StateWorkingSet,
2021-09-13 21:59:11 +02:00
spans: &'a [Span],
) -> Option<(&'a Span, ParseError)> {
if spans.len() == 1 {
None
} else if spans.len() < 4 {
if working_set.get_span_contents(spans[1]) == b"=" {
let name = String::from_utf8_lossy(working_set.get_span_contents(spans[0]));
Some((
&spans[1],
ParseError::AssignmentMismatch(
format!("{} missing name", name),
"missing name".into(),
spans[1],
),
))
} else {
None
}
2021-09-10 09:28:43 +02:00
} else if working_set.get_span_contents(spans[2]) != b"=" {
2021-09-13 21:59:11 +02:00
let name = String::from_utf8_lossy(working_set.get_span_contents(spans[0]));
Some((
&spans[2],
ParseError::AssignmentMismatch(
format!("{} missing sign", name),
"missing equal sign".into(),
spans[2],
),
2021-09-10 09:28:43 +02:00
))
} else {
None
}
}
2021-09-02 10:25:22 +02:00
pub fn parse_external_call(
2021-10-08 23:51:47 +02:00
working_set: &mut StateWorkingSet,
2021-09-02 10:25:22 +02:00
spans: &[Span],
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
trace!("parse external");
2021-09-02 10:25:22 +02:00
let mut args = vec![];
let head_contents = working_set.get_span_contents(spans[0]);
let head_span = if head_contents.starts_with(b"^") {
Span {
start: spans[0].start + 1,
end: spans[0].end,
}
} else {
spans[0]
};
2022-03-03 20:05:55 +01:00
let head_contents = working_set.get_span_contents(head_span).to_vec();
2021-10-08 23:51:47 +02:00
let mut error = None;
let head = if head_contents.starts_with(b"$") || head_contents.starts_with(b"(") {
let (arg, err) = parse_expression(working_set, &[head_span], expand_aliases_denylist);
error = error.or(err);
Box::new(arg)
} else {
Box::new(Expression {
2022-03-03 20:05:55 +01:00
expr: Expr::String(String::from_utf8_lossy(&head_contents).to_string()),
span: head_span,
ty: Type::String,
custom_completion: None,
})
};
2021-09-02 10:25:22 +02:00
for span in &spans[1..] {
2021-10-08 23:51:47 +02:00
let contents = working_set.get_span_contents(*span);
if contents.starts_with(b"$") || contents.starts_with(b"(") {
let (arg, err) = parse_dollar_expr(working_set, *span, expand_aliases_denylist);
error = error.or(err);
args.push(arg);
} else if contents.starts_with(b"(") {
let (arg, err) =
parse_full_cell_path(working_set, None, *span, expand_aliases_denylist);
2021-10-08 23:51:47 +02:00
error = error.or(err);
args.push(arg);
} else {
args.push(Expression {
expr: Expr::String(String::from_utf8_lossy(contents).to_string()),
span: *span,
ty: Type::String,
custom_completion: None,
})
}
2021-07-01 02:01:04 +02:00
}
2021-09-02 10:25:22 +02:00
(
Expression {
expr: Expr::ExternalCall(head, args),
2021-09-02 10:25:22 +02:00
span: span(spans),
ty: Type::Any,
custom_completion: None,
2021-09-02 10:25:22 +02:00
},
2021-10-08 23:51:47 +02:00
error,
2021-09-02 10:25:22 +02:00
)
}
2021-07-01 02:01:04 +02:00
2021-09-02 10:25:22 +02:00
fn parse_long_flag(
working_set: &mut StateWorkingSet,
spans: &[Span],
spans_idx: &mut usize,
sig: &Signature,
expand_aliases_denylist: &[usize],
) -> (
Option<Spanned<String>>,
Option<Expression>,
Option<ParseError>,
) {
2021-09-02 10:25:22 +02:00
let arg_span = spans[*spans_idx];
let arg_contents = working_set.get_span_contents(arg_span);
if arg_contents.starts_with(b"--") {
2021-10-12 19:44:23 +02:00
// FIXME: only use the first flag you find?
2021-09-02 10:25:22 +02:00
let split: Vec<_> = arg_contents.split(|x| *x == b'=').collect();
let long_name = String::from_utf8(split[0].into());
if let Ok(long_name) = long_name {
2021-10-13 19:53:27 +02:00
let long_name = long_name[2..].to_string();
2021-09-02 10:25:22 +02:00
if let Some(flag) = sig.get_long_flag(&long_name) {
if let Some(arg_shape) = &flag.arg {
if split.len() > 1 {
// and we also have the argument
let long_name_len = long_name.len();
2021-09-02 10:25:22 +02:00
let mut span = arg_span;
span.start += long_name_len + 3; //offset by long flag and '='
let (arg, err) =
parse_value(working_set, span, arg_shape, expand_aliases_denylist);
2021-09-02 10:25:22 +02:00
(
Some(Spanned {
item: long_name,
span: Span {
start: arg_span.start,
end: arg_span.start + long_name_len + 2,
},
}),
Some(arg),
err,
)
2021-09-02 10:25:22 +02:00
} else if let Some(arg) = spans.get(*spans_idx + 1) {
let (arg, err) =
parse_value(working_set, *arg, arg_shape, expand_aliases_denylist);
2021-09-02 10:25:22 +02:00
*spans_idx += 1;
(
Some(Spanned {
item: long_name,
span: arg_span,
}),
Some(arg),
err,
)
2021-07-08 22:29:00 +02:00
} else {
2021-09-02 10:25:22 +02:00
(
Some(Spanned {
item: long_name,
span: arg_span,
}),
2021-09-02 10:25:22 +02:00
None,
2022-01-04 00:14:33 +01:00
Some(ParseError::MissingFlagParam(
arg_shape.to_string(),
arg_span,
)),
2021-09-02 10:25:22 +02:00
)
2021-07-08 22:29:00 +02:00
}
} else {
2021-09-02 10:25:22 +02:00
// A flag with no argument
(
Some(Spanned {
item: long_name,
span: arg_span,
}),
None,
None,
)
2021-07-08 22:29:00 +02:00
}
} else {
2021-09-02 10:25:22 +02:00
(
Some(Spanned {
item: long_name.clone(),
span: arg_span,
}),
2021-09-02 10:25:22 +02:00
None,
2021-09-21 06:03:06 +02:00
Some(ParseError::UnknownFlag(
sig.name.clone(),
long_name.clone(),
arg_span,
)),
2021-09-02 10:25:22 +02:00
)
2021-07-08 22:29:00 +02:00
}
} else {
(
Some(Spanned {
item: "--".into(),
span: arg_span,
}),
None,
Some(ParseError::NonUtf8(arg_span)),
)
2021-07-08 22:29:00 +02:00
}
2021-09-02 10:25:22 +02:00
} else {
(None, None, None)
2021-07-08 22:29:00 +02:00
}
2021-09-02 10:25:22 +02:00
}
2021-07-08 22:29:00 +02:00
2021-09-02 10:25:22 +02:00
fn parse_short_flags(
working_set: &mut StateWorkingSet,
spans: &[Span],
spans_idx: &mut usize,
positional_idx: usize,
sig: &Signature,
) -> (Option<Vec<Flag>>, Option<ParseError>) {
let mut error = None;
let arg_span = spans[*spans_idx];
let arg_contents = working_set.get_span_contents(arg_span);
if arg_contents.starts_with(b"-") && arg_contents.len() > 1 {
let short_flags = &arg_contents[1..];
let mut found_short_flags = vec![];
let mut unmatched_short_flags = vec![];
for short_flag in short_flags.iter().enumerate() {
let short_flag_char = char::from(*short_flag.1);
let orig = arg_span;
let short_flag_span = Span {
start: orig.start + 1 + short_flag.0,
end: orig.start + 1 + short_flag.0 + 1,
};
if let Some(flag) = sig.get_short_flag(short_flag_char) {
// If we require an arg and are in a batch of short flags, error
if !found_short_flags.is_empty() && flag.arg.is_some() {
error = error.or(Some(ParseError::ShortFlagBatchCantTakeArg(short_flag_span)))
2021-07-08 22:29:00 +02:00
}
2021-09-02 10:25:22 +02:00
found_short_flags.push(flag);
} else {
unmatched_short_flags.push(short_flag_span);
2021-07-08 22:29:00 +02:00
}
2021-09-02 10:25:22 +02:00
}
2021-07-08 22:29:00 +02:00
2021-09-02 10:25:22 +02:00
if found_short_flags.is_empty() {
// check to see if we have a negative number
if let Some(positional) = sig.get_positional(positional_idx) {
if positional.shape == SyntaxShape::Int || positional.shape == SyntaxShape::Number {
if String::from_utf8_lossy(arg_contents).parse::<f64>().is_ok() {
return (None, None);
2021-07-08 22:29:00 +02:00
} else if let Some(first) = unmatched_short_flags.first() {
2021-09-21 06:03:06 +02:00
let contents = working_set.get_span_contents(*first);
error = error.or_else(|| {
Some(ParseError::UnknownFlag(
sig.name.clone(),
format!("-{}", String::from_utf8_lossy(contents)),
2021-09-21 06:03:06 +02:00
*first,
))
});
2021-07-08 22:29:00 +02:00
}
} else if let Some(first) = unmatched_short_flags.first() {
2021-09-21 06:03:06 +02:00
let contents = working_set.get_span_contents(*first);
error = error.or_else(|| {
Some(ParseError::UnknownFlag(
sig.name.clone(),
format!("-{}", String::from_utf8_lossy(contents)),
2021-09-21 06:03:06 +02:00
*first,
))
});
2021-07-08 22:29:00 +02:00
}
2021-09-02 10:25:22 +02:00
} else if let Some(first) = unmatched_short_flags.first() {
2021-09-21 06:03:06 +02:00
let contents = working_set.get_span_contents(*first);
error = error.or_else(|| {
Some(ParseError::UnknownFlag(
sig.name.clone(),
format!("-{}", String::from_utf8_lossy(contents)),
2021-09-21 06:03:06 +02:00
*first,
))
});
2021-09-02 10:25:22 +02:00
}
} else if !unmatched_short_flags.is_empty() {
if let Some(first) = unmatched_short_flags.first() {
2021-09-21 06:03:06 +02:00
let contents = working_set.get_span_contents(*first);
error = error.or_else(|| {
Some(ParseError::UnknownFlag(
sig.name.clone(),
format!("-{}", String::from_utf8_lossy(contents)),
2021-09-21 06:03:06 +02:00
*first,
))
});
2021-07-08 22:29:00 +02:00
}
}
2021-09-02 10:25:22 +02:00
(Some(found_short_flags), error)
} else {
(None, None)
2021-07-08 22:29:00 +02:00
}
2021-09-02 10:25:22 +02:00
}
2021-07-08 22:29:00 +02:00
2021-09-02 10:25:22 +02:00
fn first_kw_idx(
working_set: &StateWorkingSet,
signature: &Signature,
spans: &[Span],
spans_idx: usize,
positional_idx: usize,
) -> (Option<usize>, usize) {
for idx in (positional_idx + 1)..signature.num_positionals() {
if let Some(PositionalArg {
shape: SyntaxShape::Keyword(kw, ..),
..
}) = signature.get_positional(idx)
{
#[allow(clippy::needless_range_loop)]
for span_idx in spans_idx..spans.len() {
let contents = working_set.get_span_contents(spans[span_idx]);
2021-08-26 23:48:27 +02:00
2021-09-02 10:25:22 +02:00
if contents == kw {
return (Some(idx), span_idx);
2021-08-26 23:48:27 +02:00
}
}
}
}
2021-09-02 10:25:22 +02:00
(None, spans.len())
}
2021-08-26 23:48:27 +02:00
2021-09-02 10:25:22 +02:00
fn calculate_end_span(
working_set: &StateWorkingSet,
signature: &Signature,
spans: &[Span],
spans_idx: usize,
positional_idx: usize,
) -> usize {
if signature.rest_positional.is_some() {
spans.len()
} else {
let (kw_pos, kw_idx) =
first_kw_idx(working_set, signature, spans, spans_idx, positional_idx);
2021-08-26 23:48:27 +02:00
2021-09-02 10:25:22 +02:00
if let Some(kw_pos) = kw_pos {
// We found a keyword. Keywords, once found, create a guidepost to
// show us where the positionals will lay into the arguments. Because they're
// keywords, they get to set this by being present
2021-08-26 23:48:27 +02:00
2021-09-02 10:25:22 +02:00
let positionals_between = kw_pos - positional_idx - 1;
if positionals_between > (kw_idx - spans_idx) {
kw_idx
2021-08-26 23:48:27 +02:00
} else {
2021-09-02 10:25:22 +02:00
kw_idx - positionals_between
}
} else {
// Make space for the remaining require positionals, if we can
if signature.num_positionals_after(positional_idx) == 0 {
spans.len()
} else if positional_idx < signature.required_positional.len()
2021-09-02 10:25:22 +02:00
&& spans.len() > (signature.required_positional.len() - positional_idx)
{
spans.len() - (signature.required_positional.len() - positional_idx - 1)
} else {
2021-09-04 09:59:38 +02:00
spans_idx + 1
2021-07-24 07:57:17 +02:00
}
}
}
2021-09-02 10:25:22 +02:00
}
2021-07-24 07:57:17 +02:00
pub fn parse_multispan_value(
2021-09-02 10:25:22 +02:00
working_set: &mut StateWorkingSet,
spans: &[Span],
spans_idx: &mut usize,
shape: &SyntaxShape,
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
let mut error = None;
match shape {
SyntaxShape::VarWithOptType => {
2022-01-01 22:42:50 +01:00
trace!("parsing: var with opt type");
2021-09-02 10:25:22 +02:00
let (arg, err) = parse_var_with_opt_type(working_set, spans, spans_idx);
error = error.or(err);
2021-07-08 23:16:25 +02:00
2021-09-02 10:25:22 +02:00
(arg, error)
}
SyntaxShape::RowCondition => {
2022-01-01 22:42:50 +01:00
trace!("parsing: row condition");
let (arg, err) =
parse_row_condition(working_set, &spans[*spans_idx..], expand_aliases_denylist);
2021-09-02 10:25:22 +02:00
error = error.or(err);
*spans_idx = spans.len() - 1;
2021-07-16 08:24:46 +02:00
2021-09-02 10:25:22 +02:00
(arg, error)
}
SyntaxShape::MathExpression => {
trace!("parsing: math expression");
let (arg, err) = parse_math_expression(
working_set,
&spans[*spans_idx..],
None,
expand_aliases_denylist,
);
error = error.or(err);
*spans_idx = spans.len() - 1;
(arg, error)
}
2021-09-02 10:25:22 +02:00
SyntaxShape::Expression => {
2022-01-01 22:42:50 +01:00
trace!("parsing: expression");
let (arg, err) =
parse_expression(working_set, &spans[*spans_idx..], expand_aliases_denylist);
2021-09-02 10:25:22 +02:00
error = error.or(err);
*spans_idx = spans.len() - 1;
2021-07-08 23:16:25 +02:00
2021-09-02 10:25:22 +02:00
(arg, error)
}
SyntaxShape::ImportPattern => {
trace!("parsing: import pattern");
let (arg, err) =
parse_import_pattern(working_set, &spans[*spans_idx..], expand_aliases_denylist);
error = error.or(err);
*spans_idx = spans.len() - 1;
(arg, error)
}
2021-09-02 10:25:22 +02:00
SyntaxShape::Keyword(keyword, arg) => {
2022-01-01 22:42:50 +01:00
trace!(
"parsing: keyword({}) {:?}",
String::from_utf8_lossy(keyword),
arg
);
2021-09-02 10:25:22 +02:00
let arg_span = spans[*spans_idx];
2021-07-08 23:16:25 +02:00
2021-09-02 10:25:22 +02:00
let arg_contents = working_set.get_span_contents(arg_span);
2021-07-17 07:28:25 +02:00
2021-09-02 10:25:22 +02:00
if arg_contents != keyword {
// When keywords mismatch, this is a strong indicator of something going wrong.
// We won't often override the current error, but as this is a strong indicator
// go ahead and override the current error and tell the user about the missing
// keyword/literal.
error = Some(ParseError::ExpectedKeyword(
String::from_utf8_lossy(keyword).into(),
arg_span,
))
}
2021-07-17 07:28:25 +02:00
2021-09-02 10:25:22 +02:00
*spans_idx += 1;
if *spans_idx >= spans.len() {
error = error.or_else(|| {
Some(ParseError::KeywordMissingArgument(
2022-01-04 00:14:33 +01:00
arg.to_string(),
2021-07-30 00:56:51 +02:00
String::from_utf8_lossy(keyword).into(),
2022-01-04 00:14:33 +01:00
Span {
start: spans[*spans_idx - 1].end,
end: spans[*spans_idx - 1].end,
},
2021-07-08 23:16:25 +02:00
))
2021-09-02 10:25:22 +02:00
});
return (
2021-07-08 23:16:25 +02:00
Expression {
2021-09-02 10:25:22 +02:00
expr: Expr::Keyword(
keyword.clone(),
spans[*spans_idx - 1],
Box::new(Expression::garbage(arg_span)),
),
2021-07-08 23:16:25 +02:00
span: arg_span,
ty: Type::Any,
custom_completion: None,
2021-07-08 23:16:25 +02:00
},
error,
2021-09-02 10:25:22 +02:00
);
2021-07-08 23:16:25 +02:00
}
2021-09-02 10:25:22 +02:00
let keyword_span = spans[*spans_idx - 1];
let (expr, err) =
parse_multispan_value(working_set, spans, spans_idx, arg, expand_aliases_denylist);
2021-09-02 10:25:22 +02:00
error = error.or(err);
let ty = expr.ty.clone();
2021-07-17 07:28:25 +02:00
2021-09-02 10:25:22 +02:00
(
Expression {
expr: Expr::Keyword(keyword.clone(), keyword_span, Box::new(expr)),
span: arg_span,
ty,
custom_completion: None,
2021-09-02 10:25:22 +02:00
},
error,
)
}
_ => {
// All other cases are single-span values
let arg_span = spans[*spans_idx];
2021-07-08 23:16:25 +02:00
let (arg, err) = parse_value(working_set, arg_span, shape, expand_aliases_denylist);
2021-09-02 10:25:22 +02:00
error = error.or(err);
(arg, error)
2021-07-08 23:16:25 +02:00
}
}
2021-09-02 10:25:22 +02:00
}
2021-07-08 23:16:25 +02:00
2021-09-02 10:25:22 +02:00
pub fn parse_internal_call(
working_set: &mut StateWorkingSet,
command_span: Span,
spans: &[Span],
decl_id: usize,
expand_aliases_denylist: &[usize],
2021-12-18 21:10:40 +01:00
) -> (Box<Call>, Option<ParseError>) {
2022-01-01 22:42:50 +01:00
trace!("parsing: internal call (decl id: {})", decl_id);
2021-09-02 10:25:22 +02:00
let mut error = None;
2021-07-02 00:40:08 +02:00
let mut call = Call::new(command_span);
2021-09-02 10:25:22 +02:00
call.decl_id = decl_id;
call.head = command_span;
2021-07-08 08:19:38 +02:00
2021-09-02 10:25:22 +02:00
let signature = working_set.get_decl(decl_id).signature();
2021-07-08 08:19:38 +02:00
2021-10-09 18:10:46 +02:00
if signature.creates_scope {
working_set.enter_scope();
}
2021-09-02 10:25:22 +02:00
// The index into the positional parameter in the definition
let mut positional_idx = 0;
2021-07-08 08:19:38 +02:00
2021-09-02 10:25:22 +02:00
// The index into the spans of argument data given to parse
// Starting at the first argument
let mut spans_idx = 0;
2021-07-02 00:40:08 +02:00
2021-09-02 10:25:22 +02:00
while spans_idx < spans.len() {
let arg_span = spans[spans_idx];
2021-07-08 23:16:25 +02:00
2021-09-02 10:25:22 +02:00
// Check if we're on a long flag, if so, parse
let (long_name, arg, err) = parse_long_flag(
working_set,
spans,
&mut spans_idx,
&signature,
expand_aliases_denylist,
);
2021-09-02 10:25:22 +02:00
if let Some(long_name) = long_name {
// We found a long flag, like --bar
error = error.or(err);
call.named.push((long_name, arg));
2021-09-02 10:25:22 +02:00
spans_idx += 1;
continue;
}
2021-07-02 00:40:08 +02:00
2021-09-02 10:25:22 +02:00
// Check if we're on a short flag or group of short flags, if so, parse
let (short_flags, err) = parse_short_flags(
working_set,
spans,
&mut spans_idx,
positional_idx,
&signature,
);
2021-07-08 22:29:00 +02:00
2021-09-02 10:25:22 +02:00
if let Some(short_flags) = short_flags {
error = error.or(err);
for flag in short_flags {
if let Some(arg_shape) = flag.arg {
if let Some(arg) = spans.get(spans_idx + 1) {
let (arg, err) =
parse_value(working_set, *arg, &arg_shape, expand_aliases_denylist);
2021-09-02 10:25:22 +02:00
error = error.or(err);
2021-10-11 23:17:45 +02:00
call.named.push((
Spanned {
item: flag.long.clone(),
span: spans[spans_idx],
},
Some(arg),
));
2021-09-02 10:25:22 +02:00
spans_idx += 1;
2021-07-08 08:19:38 +02:00
} else {
2022-01-04 00:14:33 +01:00
error = error.or_else(|| {
Some(ParseError::MissingFlagParam(
arg_shape.to_string(),
arg_span,
))
})
2021-07-02 00:40:08 +02:00
}
2021-09-02 10:25:22 +02:00
} else {
2021-10-11 23:17:45 +02:00
call.named.push((
Spanned {
item: flag.long.clone(),
span: spans[spans_idx],
},
None,
));
2021-07-08 08:19:38 +02:00
}
2021-07-08 22:29:00 +02:00
}
2021-09-02 10:25:22 +02:00
spans_idx += 1;
continue;
}
2021-07-08 22:29:00 +02:00
2021-09-02 10:25:22 +02:00
// Parse a positional arg if there is one
if let Some(positional) = signature.get_positional(positional_idx) {
let end = calculate_end_span(working_set, &signature, spans, spans_idx, positional_idx);
2021-07-17 01:22:01 +02:00
let end = if spans.len() > spans_idx && end == spans_idx {
end + 1
} else {
end
};
if spans[..end].is_empty() || spans_idx == end {
error = error.or_else(|| {
Some(ParseError::MissingPositional(
positional.name.clone(),
Span {
start: spans[spans_idx].end,
end: spans[spans_idx].end,
},
2022-01-04 00:14:33 +01:00
signature.call_signature(),
))
});
positional_idx += 1;
continue;
}
2021-09-02 10:25:22 +02:00
let orig_idx = spans_idx;
let (arg, err) = parse_multispan_value(
working_set,
&spans[..end],
&mut spans_idx,
&positional.shape,
expand_aliases_denylist,
2021-09-02 10:25:22 +02:00
);
error = error.or(err);
2021-07-23 23:46:55 +02:00
2021-09-02 10:25:22 +02:00
let arg = if !type_compatible(&positional.shape.to_type(), &arg.ty) {
let span = span(&spans[orig_idx..spans_idx]);
error = error.or_else(|| {
Some(ParseError::TypeMismatch(
positional.shape.to_type(),
arg.ty,
arg.span,
))
});
Expression::garbage(span)
2021-07-08 08:19:38 +02:00
} else {
2021-09-02 10:25:22 +02:00
arg
};
call.positional.push(arg);
positional_idx += 1;
} else {
call.positional.push(Expression::garbage(arg_span));
2022-01-04 00:14:33 +01:00
error = error.or_else(|| {
Some(ParseError::ExtraPositional(
signature.call_signature(),
arg_span,
))
})
2021-07-08 08:19:38 +02:00
}
2021-07-02 00:40:08 +02:00
2021-07-08 08:19:38 +02:00
error = error.or(err);
2021-09-02 10:25:22 +02:00
spans_idx += 1;
2021-07-08 08:19:38 +02:00
}
2021-09-02 10:25:22 +02:00
let err = check_call(command_span, &signature, &call);
error = error.or(err);
2021-07-31 07:20:40 +02:00
2021-10-09 18:10:46 +02:00
if signature.creates_scope {
working_set.exit_scope();
}
2021-10-12 19:44:23 +02:00
// FIXME: output type unknown
2021-12-18 21:10:40 +01:00
(Box::new(call), error)
2021-09-02 10:25:22 +02:00
}
2021-07-31 07:20:40 +02:00
2021-09-02 10:25:22 +02:00
pub fn parse_call(
working_set: &mut StateWorkingSet,
spans: &[Span],
2021-12-19 08:46:13 +01:00
head: Span,
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
2022-01-01 22:42:50 +01:00
trace!("parsing: call");
2021-10-29 22:50:28 +02:00
if spans.is_empty() {
return (
2021-12-19 08:46:13 +01:00
garbage(head),
Some(ParseError::UnknownState(
"Encountered command with zero spans".into(),
span(spans),
)),
2021-10-29 22:50:28 +02:00
);
}
2021-09-02 10:25:22 +02:00
let mut pos = 0;
let cmd_start = pos;
2021-10-29 22:50:28 +02:00
let mut name_spans = vec![];
2022-01-10 03:52:01 +01:00
let mut name = vec![];
2021-08-17 01:00:00 +02:00
2021-10-29 22:50:28 +02:00
for word_span in spans[cmd_start..].iter() {
// Find the longest group of words that could form a command
if is_math_expression_like(working_set, *word_span, expand_aliases_denylist) {
let bytes = working_set.get_span_contents(*word_span);
if bytes != b"true" && bytes != b"false" && bytes != b"null" && bytes != b"not" {
break;
}
2021-08-09 02:19:07 +02:00
}
2021-10-29 22:50:28 +02:00
name_spans.push(*word_span);
2021-09-02 10:25:22 +02:00
2022-01-10 03:52:01 +01:00
let name_part = working_set.get_span_contents(*word_span);
if name.is_empty() {
name.extend(name_part);
} else {
name.push(b' ');
name.extend(name_part);
}
2021-09-02 10:25:22 +02:00
// If the word is an alias, expand it and re-parse the expression
if let Some(alias_id) = working_set.find_alias(&name) {
if !expand_aliases_denylist.contains(&alias_id) {
2022-01-01 22:42:50 +01:00
trace!("expanding alias");
let expansion = working_set.get_alias(alias_id);
2022-02-15 03:09:21 +01:00
let expansion_span = span(expansion);
let orig_span = span(&[spans[cmd_start], spans[pos]]);
2021-10-29 22:50:28 +02:00
let mut new_spans: Vec<Span> = vec![];
2022-02-15 03:09:21 +01:00
new_spans.extend(&spans[0..cmd_start]);
2021-10-29 22:50:28 +02:00
new_spans.extend(expansion);
2022-03-03 20:05:55 +01:00
// TODO: This seems like it should be `pos + 1`. `pos` starts as 0
2021-10-29 22:50:28 +02:00
if spans.len() > pos {
new_spans.extend(&spans[(pos + 1)..]);
}
2021-08-17 01:00:00 +02:00
let mut expand_aliases_denylist = expand_aliases_denylist.to_vec();
expand_aliases_denylist.push(alias_id);
let lite_command = LiteCommand {
comments: vec![],
parts: new_spans.clone(),
};
let (mut result, err) =
parse_builtin_commands(working_set, &lite_command, &expand_aliases_denylist);
let mut result = result.expressions.remove(0);
2021-08-17 01:00:00 +02:00
2022-02-15 03:09:21 +01:00
result.replace_span(working_set, expansion_span, orig_span);
2021-08-17 01:00:00 +02:00
2022-02-15 03:09:21 +01:00
return (result, err);
2021-09-02 10:25:22 +02:00
}
2021-10-29 22:50:28 +02:00
}
2021-08-17 01:00:00 +02:00
2021-10-29 22:50:28 +02:00
pos += 1;
}
2022-01-10 03:52:01 +01:00
let mut maybe_decl_id = working_set.find_decl(&name);
2021-10-29 22:50:28 +02:00
while maybe_decl_id.is_none() {
// Find the longest command match
if name_spans.len() <= 1 {
// Keep the first word even if it does not match -- could be external command
break;
2021-06-30 03:42:56 +02:00
}
2021-09-11 14:07:19 +02:00
2021-10-29 22:50:28 +02:00
name_spans.pop();
pos -= 1;
2022-01-10 03:52:01 +01:00
let mut name = vec![];
for name_span in &name_spans {
let name_part = working_set.get_span_contents(*name_span);
if name.is_empty() {
name.extend(name_part);
} else {
name.push(b' ');
name.extend(name_part);
}
}
maybe_decl_id = working_set.find_decl(&name);
2021-10-29 22:50:28 +02:00
}
if let Some(decl_id) = maybe_decl_id {
2021-09-11 14:07:19 +02:00
// Before the internal parsing we check if there is no let or alias declarations
// that are missing their name, e.g.: let = 1 or alias = 2
if spans.len() > 1 {
let test_equal = working_set.get_span_contents(spans[1]);
2021-09-11 14:16:40 +02:00
if test_equal == [b'='] {
2022-01-01 22:42:50 +01:00
trace!("incomplete statement");
2021-09-11 14:07:19 +02:00
return (
2021-12-19 08:46:13 +01:00
garbage(span(spans)),
2021-09-11 14:07:19 +02:00
Some(ParseError::UnknownState(
2021-09-12 17:36:16 +02:00
"Incomplete statement".into(),
2021-09-11 14:07:19 +02:00
span(spans),
)),
);
}
}
2022-01-01 22:42:50 +01:00
trace!("parsing: internal call");
2021-09-02 10:25:22 +02:00
// parse internal command
2021-12-18 21:10:40 +01:00
let (call, err) = parse_internal_call(
2021-10-29 22:50:28 +02:00
working_set,
span(&spans[cmd_start..pos]),
&spans[pos..],
decl_id,
expand_aliases_denylist,
2021-10-29 22:50:28 +02:00
);
2021-09-02 10:25:22 +02:00
(
Expression {
expr: Expr::Call(call),
span: span(spans),
ty: Type::Any, // FIXME: calls should have known output types
custom_completion: None,
2021-09-02 10:25:22 +02:00
},
err,
)
} else {
// We might be parsing left-unbounded range ("..10")
let bytes = working_set.get_span_contents(spans[0]);
2022-01-01 22:42:50 +01:00
trace!("parsing: range {:?} ", bytes);
if let (Some(b'.'), Some(b'.')) = (bytes.get(0), bytes.get(1)) {
2022-01-01 22:42:50 +01:00
trace!("-- found leading range indicator");
let (range_expr, range_err) =
parse_range(working_set, spans[0], expand_aliases_denylist);
if range_err.is_none() {
2022-01-01 22:42:50 +01:00
trace!("-- successfully parsed range");
return (range_expr, range_err);
}
}
2022-01-01 22:42:50 +01:00
trace!("parsing: external call");
2021-10-29 22:50:28 +02:00
// Otherwise, try external command
parse_external_call(working_set, spans, expand_aliases_denylist)
2021-09-02 10:25:22 +02:00
}
}
2022-03-01 00:31:53 +01:00
pub fn parse_binary(
working_set: &mut StateWorkingSet,
span: Span,
) -> (Expression, Option<ParseError>) {
pub fn decode_hex(s: &str) -> Result<Vec<u8>, ParseIntError> {
(0..s.len())
.step_by(2)
.map(|i| u8::from_str_radix(&s[i..i + 2], 16))
.collect()
}
let token = working_set.get_span_contents(span);
if let Some(token) = token.strip_prefix(b"0x[") {
if let Some(token) = token.strip_suffix(b"]") {
let (lexed, err) = lex(token, span.start + 3, &[b',', b'\r', b'\n'], &[], true);
let mut hex_value = vec![];
for token in lexed {
match token.contents {
TokenContents::Item => {
let contents = working_set.get_span_contents(token.span);
hex_value.extend_from_slice(contents);
}
TokenContents::Pipe => {
return (
garbage(span),
Some(ParseError::Expected("binary".into(), span)),
);
}
TokenContents::Comment | TokenContents::Semicolon | TokenContents::Eol => {}
}
}
if hex_value.len() % 2 != 0 {
return (
garbage(span),
Some(ParseError::IncorrectValue(
"incomplete binary".into(),
span,
"number of binary digits needs to be a multiple of 2".into(),
)),
);
}
let str = String::from_utf8_lossy(&hex_value).to_string();
match decode_hex(&str) {
Ok(v) => {
return (
Expression {
expr: Expr::Binary(v),
span,
ty: Type::Binary,
custom_completion: None,
},
err,
)
}
Err(x) => {
return (
garbage(span),
Some(ParseError::IncorrectValue(
"not a binary value".into(),
span,
x.to_string(),
)),
)
}
}
}
}
(
garbage(span),
Some(ParseError::Expected("binary".into(), span)),
)
}
2021-09-07 00:02:24 +02:00
pub fn parse_int(token: &[u8], span: Span) -> (Expression, Option<ParseError>) {
if let Some(token) = token.strip_prefix(b"0x") {
if let Ok(v) = i64::from_str_radix(&String::from_utf8_lossy(token), 16) {
2021-07-01 02:01:04 +02:00
(
Expression {
2021-09-02 10:25:22 +02:00
expr: Expr::Int(v),
2021-07-01 02:01:04 +02:00
span,
2021-07-23 23:19:30 +02:00
ty: Type::Int,
custom_completion: None,
2021-07-01 02:01:04 +02:00
},
None,
)
} else {
(
garbage(span),
2021-09-02 10:25:22 +02:00
Some(ParseError::Mismatch(
"int".into(),
"incompatible int".into(),
span,
)),
2021-07-01 02:01:04 +02:00
)
}
2021-09-07 00:02:24 +02:00
} else if let Some(token) = token.strip_prefix(b"0b") {
if let Ok(v) = i64::from_str_radix(&String::from_utf8_lossy(token), 2) {
2021-08-08 22:21:21 +02:00
(
Expression {
2021-09-02 10:25:22 +02:00
expr: Expr::Int(v),
2021-08-08 22:21:21 +02:00
span,
2021-09-02 10:25:22 +02:00
ty: Type::Int,
custom_completion: None,
2021-08-08 22:21:21 +02:00
},
None,
)
} else {
(
garbage(span),
2021-09-02 10:25:22 +02:00
Some(ParseError::Mismatch(
"int".into(),
"incompatible int".into(),
span,
)),
2021-08-08 22:21:21 +02:00
)
}
2021-09-07 00:02:24 +02:00
} else if let Some(token) = token.strip_prefix(b"0o") {
if let Ok(v) = i64::from_str_radix(&String::from_utf8_lossy(token), 8) {
2021-09-02 10:25:22 +02:00
(
Expression {
expr: Expr::Int(v),
span,
ty: Type::Int,
custom_completion: None,
2021-09-02 10:25:22 +02:00
},
None,
)
2021-07-01 02:01:04 +02:00
} else {
(
garbage(span),
2021-09-02 10:25:22 +02:00
Some(ParseError::Mismatch(
"int".into(),
"incompatible int".into(),
span,
)),
2021-07-01 02:01:04 +02:00
)
}
2021-09-07 00:02:24 +02:00
} else if let Ok(x) = String::from_utf8_lossy(token).parse::<i64>() {
2021-09-02 10:25:22 +02:00
(
Expression {
expr: Expr::Int(x),
span,
ty: Type::Int,
custom_completion: None,
2021-09-02 10:25:22 +02:00
},
None,
)
} else {
(
garbage(span),
Some(ParseError::Expected("int".into(), span)),
)
2021-07-01 02:01:04 +02:00
}
2021-09-02 10:25:22 +02:00
}
2021-07-01 02:01:04 +02:00
2021-09-07 00:02:24 +02:00
pub fn parse_float(token: &[u8], span: Span) -> (Expression, Option<ParseError>) {
if let Ok(x) = String::from_utf8_lossy(token).parse::<f64>() {
2021-09-02 10:25:22 +02:00
(
Expression {
expr: Expr::Float(x),
span,
ty: Type::Float,
custom_completion: None,
2021-09-02 10:25:22 +02:00
},
None,
)
} else {
(
garbage(span),
Some(ParseError::Expected("float".into(), span)),
)
}
}
2021-07-30 05:26:06 +02:00
2021-09-07 00:02:24 +02:00
pub fn parse_number(token: &[u8], span: Span) -> (Expression, Option<ParseError>) {
2021-09-03 09:35:29 +02:00
if let (x, None) = parse_int(token, span) {
2021-09-02 10:25:22 +02:00
(x, None)
2021-09-03 09:35:29 +02:00
} else if let (x, None) = parse_float(token, span) {
2021-09-02 10:25:22 +02:00
(x, None)
} else {
(
garbage(span),
Some(ParseError::Expected("number".into(), span)),
)
2021-07-30 05:26:06 +02:00
}
2021-09-02 10:25:22 +02:00
}
2021-07-30 05:26:06 +02:00
pub fn parse_range(
working_set: &mut StateWorkingSet,
span: Span,
expand_aliases_denylist: &[usize],
) -> (Expression, Option<ParseError>) {
2022-01-01 22:42:50 +01:00
trace!("parsing: range");
// Range follows the following syntax: [<from>][<next_operator><next>]<range_operator>[<to>]
// where <next_operator> is ".."
// and <range_operator> is ".." or "..<"
// and one of the <from> or <to> bounds must be present (just '..' is not allowed since it
// looks like parent directory)
let contents = working_set.get_span_contents(span);
let token = if let Ok(s) = String::from_utf8(contents.into()) {
s
} else {
return (garbage(span), Some(ParseError::NonUtf8(span)));
};
if !token.contains("..") {
return (
garbage(span),
Some(ParseError::Expected(
"at least one range bound set".into(),
span,
)),
);
}
// First, figure out what exact operators are used and determine their positions
let dotdot_pos: Vec<_> = token.match_indices("..").map(|(pos, _)| pos).collect();
let (next_op_pos, range_op_pos) =
match dotdot_pos.len() {
1 => (None, dotdot_pos[0]),
2 => (Some(dotdot_pos[0]), dotdot_pos[1]),
_ => return (
garbage(span),
Some(ParseError::Expected(
"one range operator ('..' or '..<') and optionally one next operator ('..')"
.into(),
span,
)),
),
};
let (inclusion, range_op_str, range_op_span) = if let Some(pos) = token.find("..<") {
if pos == range_op_pos {
let op_str = "..<";
let op_span = Span::new(
span.start + range_op_pos,
span.start + range_op_pos + op_str.len(),
);
(RangeInclusion::RightExclusive, "..<", op_span)
} else {
return (
garbage(span),
Some(ParseError::Expected(
"inclusive operator preceding second range bound".into(),
span,
)),
);
}
} else {
let op_str = "..";
let op_span = Span::new(
span.start + range_op_pos,
span.start + range_op_pos + op_str.len(),
);
(RangeInclusion::Inclusive, "..", op_span)
};
// Now, based on the operator positions, figure out where the bounds & next are located and
// parse them
2021-10-12 19:44:23 +02:00
// TODO: Actually parse the next number in the range
let from = if token.starts_with("..") {
// token starts with either next operator, or range operator -- we don't care which one
None
} else {
let from_span = Span::new(span.start, span.start + dotdot_pos[0]);
match parse_value(
working_set,
from_span,
&SyntaxShape::Number,
expand_aliases_denylist,
) {
(expression, None) => Some(Box::new(expression)),
_ => {
return (
garbage(span),
Some(ParseError::Expected("number".into(), span)),
)
}
}
};
let to = if token.ends_with(range_op_str) {
None
} else {
let to_span = Span::new(range_op_span.end, span.end);
match parse_value(
working_set,
to_span,
&SyntaxShape::Number,
expand_aliases_denylist,
) {
(expression, None) => Some(Box::new(expression)),
_ => {
return (
garbage(span),
Some(ParseError::Expected("number".into(), span)),
)
}
}
};
2022-01-01 22:42:50 +01:00
trace!("-- from: {:?} to: {:?}", from, to);
if let (None, None) = (&from, &to) {
return (
garbage(span),
Some(ParseError::Expected(
"at least one range bound set".into(),
span,
)),
);
}
let (next, next_op_span) = if let Some(pos) = next_op_pos {
let next_op_span = Span::new(span.start + pos, span.start + pos + "..".len());
let next_span = Span::new(next_op_span.end, range_op_span.start);
match parse_value(
working_set,
next_span,
&SyntaxShape::Number,
expand_aliases_denylist,
) {
(expression, None) => (Some(Box::new(expression)), next_op_span),
_ => {
return (
garbage(span),
Some(ParseError::Expected("number".into(), span)),
)
}
}
} else {
2021-12-19 08:46:13 +01:00
(None, span)
};
let range_op = RangeOperator {
inclusion,
span: range_op_span,
next_op_span,
};
(
Expression {
expr: Expr::Range(from, next, to, range_op),
span,
ty: Type::Range,
custom_completion: None,
},
None,
)
}
2021-09-02 10:25:22 +02:00
pub(crate) fn parse_dollar_expr(
working_set: &mut StateWorkingSet,
span: Span,
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
trace!("parsing: dollar expression");
2021-09-02 10:25:22 +02:00
let contents = working_set.get_span_contents(span);
2021-07-30 05:26:06 +02:00
if contents.starts_with(b"$\"") || contents.starts_with(b"$'") {
parse_string_interpolation(working_set, span, expand_aliases_denylist)
} else if let (expr, None) = parse_range(working_set, span, expand_aliases_denylist) {
2021-09-05 00:40:15 +02:00
(expr, None)
2021-09-02 10:25:22 +02:00
} else {
parse_full_cell_path(working_set, None, span, expand_aliases_denylist)
2021-09-02 10:25:22 +02:00
}
}
2021-07-30 05:26:06 +02:00
2021-09-02 10:25:22 +02:00
pub fn parse_string_interpolation(
working_set: &mut StateWorkingSet,
span: Span,
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
#[derive(PartialEq, Eq, Debug)]
enum InterpolationMode {
String,
Expression,
}
let mut error = None;
2021-07-30 05:26:06 +02:00
2021-09-02 10:25:22 +02:00
let contents = working_set.get_span_contents(span);
2021-07-30 05:26:06 +02:00
let mut double_quote = false;
let (start, end) = if contents.starts_with(b"$\"") {
double_quote = true;
let end = if contents.ends_with(b"\"") && contents.len() > 2 {
span.end - 1
} else {
span.end
};
(span.start + 2, end)
} else if contents.starts_with(b"$'") {
let end = if contents.ends_with(b"'") && contents.len() > 2 {
span.end - 1
} else {
span.end
};
(span.start + 2, end)
2021-09-02 10:25:22 +02:00
} else {
(span.start, span.end)
2021-09-02 10:25:22 +02:00
};
let inner_span = Span { start, end };
let contents = working_set.get_span_contents(inner_span).to_vec();
let mut output = vec![];
let mut mode = InterpolationMode::String;
let mut token_start = start;
let mut delimiter_stack = vec![];
2021-09-02 10:25:22 +02:00
let mut b = start;
#[allow(clippy::needless_range_loop)]
while b != end {
if contents[b - start] == b'('
&& (if double_quote && (b - start) > 0 {
contents[b - start - 1] != b'\\'
} else {
true
})
&& mode == InterpolationMode::String
{
2021-09-02 10:25:22 +02:00
mode = InterpolationMode::Expression;
if token_start < b {
let span = Span {
start: token_start,
end: b,
};
let str_contents = working_set.get_span_contents(span);
let str_contents = if double_quote {
let (str_contents, err) = unescape_string(str_contents, span);
error = error.or(err);
str_contents
} else {
str_contents.to_vec()
};
2021-09-02 10:25:22 +02:00
output.push(Expression {
expr: Expr::String(String::from_utf8_lossy(&str_contents).to_string()),
2021-09-02 10:25:22 +02:00
span,
ty: Type::String,
custom_completion: None,
2021-09-02 10:25:22 +02:00
});
token_start = b;
2021-07-30 05:26:06 +02:00
}
}
if mode == InterpolationMode::Expression {
let byte = contents[b - start];
if let Some(b'\'') = delimiter_stack.last() {
if byte == b'\'' {
delimiter_stack.pop();
}
} else if let Some(b'"') = delimiter_stack.last() {
if byte == b'"' {
delimiter_stack.pop();
}
} else if let Some(b'`') = delimiter_stack.last() {
if byte == b'`' {
delimiter_stack.pop();
}
} else if byte == b'\'' {
delimiter_stack.push(b'\'')
} else if byte == b'"' {
delimiter_stack.push(b'"');
} else if byte == b'`' {
delimiter_stack.push(b'`')
} else if byte == b'(' {
delimiter_stack.push(b')');
} else if byte == b')' {
if let Some(b')') = delimiter_stack.last() {
delimiter_stack.pop();
}
if delimiter_stack.is_empty() {
2021-09-02 10:25:22 +02:00
mode = InterpolationMode::String;
if token_start < b {
let span = Span {
start: token_start,
end: b + 1,
};
2021-07-30 05:26:06 +02:00
let (expr, err) =
parse_full_cell_path(working_set, None, span, expand_aliases_denylist);
2021-09-02 10:25:22 +02:00
error = error.or(err);
output.push(expr);
}
token_start = b + 1;
continue;
2021-07-30 05:26:06 +02:00
}
}
}
2021-09-02 10:25:22 +02:00
b += 1;
}
2021-07-30 05:26:06 +02:00
2021-09-02 10:25:22 +02:00
match mode {
InterpolationMode::String => {
if token_start < end {
let span = Span {
start: token_start,
end,
};
let str_contents = working_set.get_span_contents(span);
let str_contents = if double_quote {
let (str_contents, err) = unescape_string(str_contents, span);
error = error.or(err);
str_contents
} else {
str_contents.to_vec()
};
2021-09-02 10:25:22 +02:00
output.push(Expression {
expr: Expr::String(String::from_utf8_lossy(&str_contents).to_string()),
2021-07-30 05:26:06 +02:00
span,
ty: Type::String,
custom_completion: None,
2021-09-02 10:25:22 +02:00
});
}
}
InterpolationMode::Expression => {
if token_start < end {
let span = Span {
start: token_start,
end,
};
let (expr, err) =
parse_full_cell_path(working_set, None, span, expand_aliases_denylist);
2021-09-02 10:25:22 +02:00
error = error.or(err);
output.push(expr);
}
2021-07-30 05:26:06 +02:00
}
2021-07-24 07:57:17 +02:00
}
2021-07-02 09:15:30 +02:00
(
Expression {
expr: Expr::StringInterpolation(output),
span,
ty: Type::String,
custom_completion: None,
},
error,
)
2021-09-02 10:25:22 +02:00
}
2021-07-24 07:57:17 +02:00
2021-09-02 10:25:22 +02:00
pub fn parse_variable_expr(
working_set: &mut StateWorkingSet,
span: Span,
) -> (Expression, Option<ParseError>) {
let contents = working_set.get_span_contents(span);
2022-03-19 20:12:10 +01:00
if contents == b"$nothing" {
return (
Expression {
expr: Expr::Nothing,
span,
ty: Type::Nothing,
custom_completion: None,
},
None,
);
2021-10-29 20:15:17 +02:00
} else if contents == b"$nu" {
return (
Expression {
2021-11-02 04:08:05 +01:00
expr: Expr::Var(nu_protocol::NU_VARIABLE_ID),
span,
ty: Type::Any,
2021-11-02 04:08:05 +01:00
custom_completion: None,
},
None,
);
} else if contents == b"$in" {
return (
Expression {
expr: Expr::Var(nu_protocol::IN_VARIABLE_ID),
span,
ty: Type::Any,
custom_completion: None,
},
None,
);
} else if contents == b"$config" {
return (
Expression {
expr: Expr::Var(nu_protocol::CONFIG_VARIABLE_ID),
span,
ty: Type::Any,
custom_completion: None,
},
None,
);
} else if contents == b"$env" {
return (
Expression {
expr: Expr::Var(nu_protocol::ENV_VARIABLE_ID),
span,
ty: Type::Any,
custom_completion: None,
},
None,
);
2021-09-02 10:25:22 +02:00
}
let (id, err) = parse_variable(working_set, span);
if err.is_none() {
if let Some(id) = id {
(
2021-07-02 09:15:30 +02:00
Expression {
2021-09-02 10:25:22 +02:00
expr: Expr::Var(id),
2021-07-02 09:15:30 +02:00
span,
2022-03-09 10:42:19 +01:00
ty: working_set.get_variable(id).ty.clone(),
custom_completion: None,
2021-07-02 09:15:30 +02:00
},
None,
2021-09-02 10:25:22 +02:00
)
} else {
(garbage(span), Some(ParseError::VariableNotFound(span)))
2021-07-02 09:15:30 +02:00
}
2021-09-02 10:25:22 +02:00
} else {
(garbage(span), err)
}
}
2021-07-02 09:15:30 +02:00
2021-10-02 04:59:11 +02:00
pub fn parse_cell_path(
working_set: &mut StateWorkingSet,
tokens: impl Iterator<Item = Token>,
mut expect_dot: bool,
span: Span,
) -> (Vec<PathMember>, Option<ParseError>) {
let mut error = None;
let mut tail = vec![];
for path_element in tokens {
let bytes = working_set.get_span_contents(path_element.span);
if expect_dot {
expect_dot = false;
if bytes.len() != 1 || bytes[0] != b'.' {
error = error.or_else(|| Some(ParseError::Expected('.'.into(), path_element.span)));
}
} else {
expect_dot = true;
match parse_int(bytes, path_element.span) {
(
Expression {
expr: Expr::Int(val),
span,
..
},
None,
) => tail.push(PathMember::Int {
val: val as usize,
span,
}),
_ => {
let (result, err) = parse_string(working_set, path_element.span);
error = error.or(err);
match result {
Expression {
expr: Expr::String(string),
span,
..
} => {
tail.push(PathMember::String { val: string, span });
}
_ => {
error =
error.or_else(|| Some(ParseError::Expected("string".into(), span)));
}
}
}
}
}
}
(tail, error)
}
2021-09-26 20:39:19 +02:00
pub fn parse_full_cell_path(
2021-09-02 10:25:22 +02:00
working_set: &mut StateWorkingSet,
2021-09-09 23:47:20 +02:00
implicit_head: Option<VarId>,
2021-09-02 10:25:22 +02:00
span: Span,
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
2021-09-26 20:39:19 +02:00
let full_cell_span = span;
2021-09-07 00:02:24 +02:00
let source = working_set.get_span_contents(span);
2021-09-02 10:25:22 +02:00
let mut error = None;
2021-07-08 08:19:38 +02:00
2021-11-21 19:13:09 +01:00
let (tokens, err) = lex(source, span.start, &[b'\n', b'\r'], &[b'.'], true);
2021-09-07 00:02:24 +02:00
error = error.or(err);
2021-09-02 10:25:22 +02:00
2021-09-09 23:47:20 +02:00
let mut tokens = tokens.into_iter().peekable();
if let Some(head) = tokens.peek() {
2021-09-07 00:02:24 +02:00
let bytes = working_set.get_span_contents(head.span);
2021-10-02 04:59:11 +02:00
let (head, expect_dot) = if bytes.starts_with(b"(") {
2022-01-01 22:42:50 +01:00
trace!("parsing: paren-head of full cell path");
let head_span = head.span;
2021-09-07 00:02:24 +02:00
let mut start = head.span.start;
let mut end = head.span.end;
2021-07-08 08:19:38 +02:00
2021-09-07 00:02:24 +02:00
if bytes.starts_with(b"(") {
start += 1;
}
if bytes.ends_with(b")") {
end -= 1;
} else {
error = error
.or_else(|| Some(ParseError::Unclosed(")".into(), Span { start: end, end })));
2021-09-07 00:02:24 +02:00
}
2021-07-02 09:15:30 +02:00
2021-09-07 00:02:24 +02:00
let span = Span { start, end };
2021-07-02 09:15:30 +02:00
2021-09-07 00:02:24 +02:00
let source = working_set.get_span_contents(span);
2021-07-02 09:15:30 +02:00
2021-11-21 19:13:09 +01:00
let (output, err) = lex(source, span.start, &[b'\n', b'\r'], &[], true);
2021-09-07 00:02:24 +02:00
error = error.or(err);
2021-07-02 09:15:30 +02:00
2021-09-09 23:47:20 +02:00
let (output, err) = lite_parse(&output);
2021-09-07 00:02:24 +02:00
error = error.or(err);
2021-07-02 09:15:30 +02:00
let (output, err) = parse_block(working_set, &output, true, expand_aliases_denylist);
2021-09-07 00:02:24 +02:00
error = error.or(err);
2021-07-02 09:15:30 +02:00
2021-09-07 00:02:24 +02:00
let block_id = working_set.add_block(output);
2021-09-09 23:47:20 +02:00
tokens.next();
2021-09-07 00:02:24 +02:00
2021-09-09 23:47:20 +02:00
(
Expression {
expr: Expr::Subexpression(block_id),
span: head_span,
ty: Type::Any, // FIXME
custom_completion: None,
2021-09-09 23:47:20 +02:00
},
true,
)
} else if bytes.starts_with(b"[") {
2022-01-01 22:42:50 +01:00
trace!("parsing: table head of full cell path");
let (output, err) =
parse_table_expression(working_set, head.span, expand_aliases_denylist);
error = error.or(err);
tokens.next();
2021-11-11 00:14:00 +01:00
(output, true)
} else if bytes.starts_with(b"{") {
2022-01-01 22:42:50 +01:00
trace!("parsing: record head of full cell path");
let (output, err) = parse_record(working_set, head.span, expand_aliases_denylist);
2021-11-11 00:14:00 +01:00
error = error.or(err);
tokens.next();
(output, true)
2021-09-07 00:02:24 +02:00
} else if bytes.starts_with(b"$") {
2022-01-01 22:42:50 +01:00
trace!("parsing: $variable head of full cell path");
2021-09-07 00:02:24 +02:00
let (out, err) = parse_variable_expr(working_set, head.span);
error = error.or(err);
2021-09-09 23:47:20 +02:00
tokens.next();
(out, true)
} else if let Some(var_id) = implicit_head {
(
Expression {
expr: Expr::Var(var_id),
span: Span::new(0, 0),
ty: Type::Any,
custom_completion: None,
2021-09-09 23:47:20 +02:00
},
false,
)
2021-09-07 00:02:24 +02:00
} else {
return (
garbage(span),
Some(ParseError::Mismatch(
"variable or subexpression".into(),
String::from_utf8_lossy(bytes).to_string(),
span,
)),
);
};
2021-10-02 04:59:11 +02:00
let (tail, err) = parse_cell_path(working_set, tokens, expect_dot, span);
error = error.or(err);
2021-09-07 00:02:24 +02:00
if !tail.is_empty() {
(
Expression {
expr: Expr::FullCellPath(Box::new(FullCellPath { head, tail })),
ty: Type::Any,
span: full_cell_span,
custom_completion: None,
},
error,
)
} else {
let ty = head.ty.clone();
(
Expression {
expr: Expr::FullCellPath(Box::new(FullCellPath { head, tail })),
ty,
span: full_cell_span,
custom_completion: None,
},
error,
)
}
2021-09-07 00:02:24 +02:00
} else {
(garbage(span), error)
}
2021-09-02 10:25:22 +02:00
}
2021-07-02 09:15:30 +02:00
2021-10-04 21:21:31 +02:00
pub fn parse_filepath(
working_set: &mut StateWorkingSet,
span: Span,
) -> (Expression, Option<ParseError>) {
let bytes = working_set.get_span_contents(span);
2021-11-14 20:40:26 +01:00
let bytes = trim_quotes(bytes);
2022-01-01 22:42:50 +01:00
trace!("parsing: filepath");
2021-10-04 21:21:31 +02:00
if let Ok(token) = String::from_utf8(bytes.into()) {
trace!("-- found {}", token);
2021-10-04 21:21:31 +02:00
(
Expression {
expr: Expr::Filepath(token),
2021-10-04 21:21:31 +02:00
span,
ty: Type::String,
custom_completion: None,
},
None,
)
} else {
(
garbage(span),
2021-11-18 20:32:27 +01:00
Some(ParseError::Expected("filepath".into(), span)),
2021-10-04 21:21:31 +02:00
)
}
}
/// Parse a datetime type, eg '2022-02-02'
pub fn parse_datetime(
working_set: &mut StateWorkingSet,
span: Span,
) -> (Expression, Option<ParseError>) {
trace!("parsing: datetime");
let bytes = working_set.get_span_contents(span);
if bytes.is_empty() || !bytes[0].is_ascii_digit() {
return (
garbage(span),
Some(ParseError::Mismatch(
"datetime".into(),
"non-datetime".into(),
span,
)),
);
}
let token = String::from_utf8_lossy(bytes).to_string();
if let Ok(datetime) = chrono::DateTime::parse_from_rfc3339(&token) {
return (
Expression {
expr: Expr::DateTime(datetime),
span,
ty: Type::Date,
custom_completion: None,
},
None,
);
}
// Just the date
let just_date = token.clone() + "T00:00:00+00:00";
if let Ok(datetime) = chrono::DateTime::parse_from_rfc3339(&just_date) {
return (
Expression {
expr: Expr::DateTime(datetime),
span,
ty: Type::Date,
custom_completion: None,
},
None,
);
}
// Date and time, assume UTC
let datetime = token + "+00:00";
if let Ok(datetime) = chrono::DateTime::parse_from_rfc3339(&datetime) {
return (
Expression {
expr: Expr::DateTime(datetime),
span,
ty: Type::Date,
custom_completion: None,
},
None,
);
}
(
garbage(span),
Some(ParseError::Mismatch(
"datetime".into(),
"non-datetime".into(),
span,
)),
)
}
2021-10-05 04:27:39 +02:00
/// Parse a duration type, eg '10day'
pub fn parse_duration(
working_set: &StateWorkingSet,
2021-10-05 04:27:39 +02:00
span: Span,
) -> (Expression, Option<ParseError>) {
2022-01-01 22:42:50 +01:00
trace!("parsing: duration");
let bytes = working_set.get_span_contents(span);
match parse_duration_bytes(bytes, span) {
Some(expression) => (expression, None),
None => (
garbage(span),
Some(ParseError::Mismatch(
"duration".into(),
"non-duration unit".into(),
span,
)),
),
}
}
pub fn parse_duration_bytes(bytes: &[u8], span: Span) -> Option<Expression> {
2021-10-05 04:27:39 +02:00
fn parse_decimal_str_to_number(decimal: &str) -> Option<i64> {
let string_to_parse = format!("0.{}", decimal);
if let Ok(x) = string_to_parse.parse::<f64>() {
return Some((1_f64 / x) as i64);
}
None
}
if bytes.is_empty() || (!bytes[0].is_ascii_digit() && bytes[0] != b'-') {
return None;
}
2021-10-05 04:27:39 +02:00
let token = String::from_utf8_lossy(bytes).to_string();
let upper = token.to_uppercase();
2021-10-05 04:27:39 +02:00
let unit_groups = [
(Unit::Nanosecond, "NS", None),
(Unit::Microsecond, "US", Some((Unit::Nanosecond, 1000))),
(Unit::Millisecond, "MS", Some((Unit::Microsecond, 1000))),
(Unit::Second, "SEC", Some((Unit::Millisecond, 1000))),
(Unit::Minute, "MIN", Some((Unit::Second, 60))),
(Unit::Hour, "HR", Some((Unit::Minute, 60))),
(Unit::Day, "DAY", Some((Unit::Minute, 1440))),
(Unit::Week, "WK", Some((Unit::Day, 7))),
];
if let Some(unit) = unit_groups.iter().find(|&x| upper.ends_with(x.1)) {
let mut lhs = token;
2021-10-05 04:27:39 +02:00
for _ in 0..unit.1.len() {
lhs.pop();
}
let input: Vec<&str> = lhs.split('.').collect();
let (value, unit_to_use) = match &input[..] {
[number_str] => (number_str.parse::<i64>().ok(), unit.0),
[number_str, decimal_part_str] => match unit.2 {
Some(unit_to_convert_to) => match (
number_str.parse::<i64>(),
parse_decimal_str_to_number(decimal_part_str),
) {
(Ok(number), Some(decimal_part)) => (
Some(
(number * unit_to_convert_to.1) + (unit_to_convert_to.1 / decimal_part),
),
unit_to_convert_to.0,
),
_ => (None, unit.0),
},
None => (None, unit.0),
},
_ => (None, unit.0),
};
if let Some(x) = value {
2022-01-01 22:42:50 +01:00
trace!("-- found {} {:?}", x, unit_to_use);
2021-10-05 04:27:39 +02:00
let lhs_span = Span::new(span.start, span.start + lhs.len());
let unit_span = Span::new(span.start + lhs.len(), span.end);
return Some(Expression {
expr: Expr::ValueWithUnit(
Box::new(Expression {
expr: Expr::Int(x),
span: lhs_span,
ty: Type::Number,
custom_completion: None,
}),
Spanned {
item: unit_to_use,
span: unit_span,
},
),
span,
ty: Type::Duration,
custom_completion: None,
});
2021-10-05 04:27:39 +02:00
}
}
None
2021-10-05 04:27:39 +02:00
}
/// Parse a unit type, eg '10kb'
pub fn parse_filesize(
working_set: &StateWorkingSet,
2021-10-05 04:27:39 +02:00
span: Span,
) -> (Expression, Option<ParseError>) {
2022-01-01 22:42:50 +01:00
trace!("parsing: duration");
2021-10-05 04:27:39 +02:00
fn parse_decimal_str_to_number(decimal: &str) -> Option<i64> {
let string_to_parse = format!("0.{}", decimal);
if let Ok(x) = string_to_parse.parse::<f64>() {
return Some((1_f64 / x) as i64);
}
None
}
let bytes = working_set.get_span_contents(span);
if bytes.is_empty() || (!bytes[0].is_ascii_digit() && bytes[0] != b'-') {
return (
garbage(span),
Some(ParseError::Mismatch(
"filesize".into(),
"non-filesize unit".into(),
span,
)),
);
}
2021-10-05 04:27:39 +02:00
let token = String::from_utf8_lossy(bytes).to_string();
let upper = token.to_uppercase();
2021-10-05 04:27:39 +02:00
let unit_groups = [
(Unit::Kilobyte, "KB", Some((Unit::Byte, 1000))),
(Unit::Megabyte, "MB", Some((Unit::Kilobyte, 1000))),
(Unit::Gigabyte, "GB", Some((Unit::Megabyte, 1000))),
(Unit::Terabyte, "TB", Some((Unit::Gigabyte, 1000))),
(Unit::Petabyte, "PB", Some((Unit::Terabyte, 1000))),
(Unit::Kibibyte, "KIB", Some((Unit::Byte, 1024))),
(Unit::Mebibyte, "MIB", Some((Unit::Kibibyte, 1024))),
(Unit::Gibibyte, "GIB", Some((Unit::Mebibyte, 1024))),
(Unit::Tebibyte, "TIB", Some((Unit::Gibibyte, 1024))),
(Unit::Pebibyte, "PIB", Some((Unit::Tebibyte, 1024))),
(Unit::Byte, "B", None),
];
if let Some(unit) = unit_groups.iter().find(|&x| upper.ends_with(x.1)) {
let mut lhs = token;
2021-10-05 04:27:39 +02:00
for _ in 0..unit.1.len() {
lhs.pop();
}
let input: Vec<&str> = lhs.split('.').collect();
let (value, unit_to_use) = match &input[..] {
[number_str] => (number_str.parse::<i64>().ok(), unit.0),
[number_str, decimal_part_str] => match unit.2 {
Some(unit_to_convert_to) => match (
number_str.parse::<i64>(),
parse_decimal_str_to_number(decimal_part_str),
) {
(Ok(number), Some(decimal_part)) => (
Some(
(number * unit_to_convert_to.1) + (unit_to_convert_to.1 / decimal_part),
),
unit_to_convert_to.0,
),
_ => (None, unit.0),
},
None => (None, unit.0),
},
_ => (None, unit.0),
};
if let Some(x) = value {
2022-01-01 22:42:50 +01:00
trace!("-- found {} {:?}", x, unit_to_use);
2021-10-05 04:27:39 +02:00
let lhs_span = Span::new(span.start, span.start + lhs.len());
let unit_span = Span::new(span.start + lhs.len(), span.end);
return (
Expression {
expr: Expr::ValueWithUnit(
Box::new(Expression {
expr: Expr::Int(x),
span: lhs_span,
ty: Type::Number,
custom_completion: None,
}),
Spanned {
item: unit_to_use,
span: unit_span,
},
),
span,
ty: Type::Filesize,
custom_completion: None,
},
None,
);
}
}
(
garbage(span),
Some(ParseError::Mismatch(
"filesize".into(),
"non-filesize unit".into(),
span,
)),
)
}
2021-10-04 21:21:31 +02:00
pub fn parse_glob_pattern(
working_set: &mut StateWorkingSet,
span: Span,
) -> (Expression, Option<ParseError>) {
2022-01-01 22:42:50 +01:00
trace!("parsing: glob pattern");
2021-10-04 21:21:31 +02:00
let bytes = working_set.get_span_contents(span);
2021-11-14 20:40:26 +01:00
let bytes = trim_quotes(bytes);
2021-10-04 21:21:31 +02:00
if let Ok(token) = String::from_utf8(bytes.into()) {
2022-01-01 22:42:50 +01:00
trace!("-- found {}", token);
2021-10-04 21:21:31 +02:00
(
Expression {
expr: Expr::GlobPattern(token),
2021-10-04 21:21:31 +02:00
span,
ty: Type::String,
custom_completion: None,
},
None,
)
} else {
(
garbage(span),
Some(ParseError::Expected("string".into(), span)),
)
}
}
pub fn unescape_string(bytes: &[u8], span: Span) -> (Vec<u8>, Option<ParseError>) {
let mut output = Vec::new();
let mut idx = 0;
let mut err = None;
while idx < bytes.len() {
if bytes[idx] == b'\\' {
// We're in an escape
idx += 1;
match bytes.get(idx) {
Some(b'"') => {
output.push(b'"');
idx += 1;
}
Some(b'\'') => {
output.push(b'\'');
idx += 1;
}
Some(b'\\') => {
output.push(b'\\');
idx += 1;
}
Some(b'/') => {
output.push(b'/');
idx += 1;
}
Some(b'(') => {
output.push(b'(');
idx += 1;
}
Some(b')') => {
output.push(b')');
idx += 1;
}
Some(b'{') => {
output.push(b'{');
idx += 1;
}
Some(b'}') => {
output.push(b'}');
idx += 1;
}
Some(b'$') => {
output.push(b'$');
idx += 1;
}
Some(b'^') => {
output.push(b'^');
idx += 1;
}
Some(b'#') => {
output.push(b'#');
idx += 1;
}
Some(b'|') => {
output.push(b'|');
idx += 1;
}
Some(b'~') => {
output.push(b'~');
idx += 1;
}
Some(b'a') => {
output.push(0x7);
idx += 1;
}
Some(b'b') => {
output.push(0x8);
idx += 1;
}
Some(b'e') => {
output.push(0x1b);
idx += 1;
}
Some(b'f') => {
output.push(0xc);
idx += 1;
}
Some(b'n') => {
output.push(b'\n');
idx += 1;
}
Some(b'r') => {
output.push(b'\r');
idx += 1;
}
Some(b't') => {
output.push(b'\t');
idx += 1;
}
Some(b'u') => {
match (
bytes.get(idx + 1),
bytes.get(idx + 2),
bytes.get(idx + 3),
bytes.get(idx + 4),
) {
(Some(h1), Some(h2), Some(h3), Some(h4)) => {
let s = String::from_utf8(vec![*h1, *h2, *h3, *h4]);
if let Ok(s) = s {
let int = u32::from_str_radix(&s, 16);
if let Ok(int) = int {
let result = char::from_u32(int);
if let Some(result) = result {
let mut buffer = vec![0; 4];
let result = result.encode_utf8(&mut buffer);
for elem in result.bytes() {
output.push(elem);
}
idx += 5;
continue;
}
}
}
err = Some(ParseError::Expected(
"unicode hex value".into(),
Span {
start: (span.start + idx),
end: span.end,
},
));
}
_ => {
err = Some(ParseError::Expected(
"unicode hex value".into(),
Span {
start: (span.start + idx),
end: span.end,
},
));
}
}
idx += 5;
}
_ => {
err = Some(ParseError::Expected(
"supported escape character".into(),
Span {
start: (span.start + idx),
end: span.end,
},
));
}
}
} else {
output.push(bytes[idx]);
idx += 1;
}
}
(output, err)
}
pub fn unescape_unquote_string(bytes: &[u8], span: Span) -> (String, Option<ParseError>) {
if bytes.starts_with(b"\"") {
// Needs unescaping
let bytes = trim_quotes(bytes);
let (bytes, err) = unescape_string(bytes, span);
if let Ok(token) = String::from_utf8(bytes) {
(token, err)
} else {
(
String::new(),
Some(ParseError::Expected("string".into(), span)),
)
}
} else {
let bytes = trim_quotes(bytes);
if let Ok(token) = String::from_utf8(bytes.into()) {
(token, None)
} else {
(
String::new(),
Some(ParseError::Expected("string".into(), span)),
)
}
}
}
2021-09-02 10:25:22 +02:00
pub fn parse_string(
working_set: &mut StateWorkingSet,
span: Span,
) -> (Expression, Option<ParseError>) {
2022-01-01 22:42:50 +01:00
trace!("parsing: string");
2021-09-02 10:25:22 +02:00
let bytes = working_set.get_span_contents(span);
2022-01-19 15:58:12 +01:00
let (s, err) = unescape_unquote_string(bytes, span);
2021-07-16 22:26:40 +02:00
(
Expression {
expr: Expr::String(s),
span,
ty: Type::String,
custom_completion: None,
},
err,
)
2021-09-02 10:25:22 +02:00
}
2021-07-02 09:15:30 +02:00
2021-11-04 03:32:35 +01:00
pub fn parse_string_strict(
working_set: &mut StateWorkingSet,
span: Span,
) -> (Expression, Option<ParseError>) {
2022-01-01 22:42:50 +01:00
trace!("parsing: string, with required delimiters");
2021-11-04 03:32:35 +01:00
let bytes = working_set.get_span_contents(span);
2022-01-19 15:58:12 +01:00
// Check for unbalanced quotes:
{
let bytes = if bytes.starts_with(b"$") {
&bytes[1..]
} else {
bytes
};
if bytes.starts_with(b"\"") && (bytes.len() == 1 || !bytes.ends_with(b"\"")) {
return (garbage(span), Some(ParseError::Unclosed("\"".into(), span)));
}
if bytes.starts_with(b"\'") && (bytes.len() == 1 || !bytes.ends_with(b"\'")) {
return (garbage(span), Some(ParseError::Unclosed("\'".into(), span)));
}
2022-01-19 15:58:12 +01:00
}
2021-11-04 03:32:35 +01:00
let (bytes, quoted) = if (bytes.starts_with(b"\"") && bytes.ends_with(b"\"") && bytes.len() > 1)
|| (bytes.starts_with(b"\'") && bytes.ends_with(b"\'") && bytes.len() > 1)
{
(&bytes[1..(bytes.len() - 1)], true)
} else if (bytes.starts_with(b"$\"") && bytes.ends_with(b"\"") && bytes.len() > 2)
|| (bytes.starts_with(b"$\'") && bytes.ends_with(b"\'") && bytes.len() > 2)
{
(&bytes[2..(bytes.len() - 1)], true)
2021-11-04 03:32:35 +01:00
} else {
(bytes, false)
};
if let Ok(token) = String::from_utf8(bytes.into()) {
2022-01-01 22:42:50 +01:00
trace!("-- found {}", token);
2021-11-04 03:32:35 +01:00
if quoted {
(
Expression {
expr: Expr::String(token),
span,
ty: Type::String,
custom_completion: None,
},
None,
)
} else if token.contains(' ') {
(
garbage(span),
Some(ParseError::Expected("string".into(), span)),
)
} else {
(
Expression {
expr: Expr::String(token),
span,
ty: Type::String,
custom_completion: None,
},
None,
)
}
} else {
(
garbage(span),
Some(ParseError::Expected("string".into(), span)),
)
}
}
2021-10-12 19:44:23 +02:00
//TODO: Handle error case for unknown shapes
2021-09-02 10:25:22 +02:00
pub fn parse_shape_name(
working_set: &StateWorkingSet,
2021-09-02 10:25:22 +02:00
bytes: &[u8],
span: Span,
) -> (SyntaxShape, Option<ParseError>) {
let result = match bytes {
b"any" => SyntaxShape::Any,
2022-03-01 00:31:53 +01:00
b"binary" => SyntaxShape::Binary,
b"block" => SyntaxShape::Block(None), //FIXME: Blocks should have known output types
2021-09-07 00:02:24 +02:00
b"cell-path" => SyntaxShape::CellPath,
b"duration" => SyntaxShape::Duration,
2021-10-04 21:21:31 +02:00
b"path" => SyntaxShape::Filepath,
b"expr" => SyntaxShape::Expression,
b"filesize" => SyntaxShape::Filesize,
2021-09-02 10:25:22 +02:00
b"glob" => SyntaxShape::GlobPattern,
b"int" => SyntaxShape::Int,
2021-09-02 10:25:22 +02:00
b"math" => SyntaxShape::MathExpression,
b"number" => SyntaxShape::Number,
b"operator" => SyntaxShape::Operator,
b"range" => SyntaxShape::Range,
b"cond" => SyntaxShape::RowCondition,
2021-10-12 06:49:17 +02:00
b"bool" => SyntaxShape::Boolean,
b"signature" => SyntaxShape::Signature,
b"string" => SyntaxShape::String,
b"variable" => SyntaxShape::Variable,
b"record" => SyntaxShape::Record,
b"list" => SyntaxShape::List(Box::new(SyntaxShape::Any)),
b"table" => SyntaxShape::Table,
_ => {
if bytes.contains(&b'@') {
let str = String::from_utf8_lossy(bytes);
let split: Vec<_> = str.split('@').collect();
let (shape, err) = parse_shape_name(
working_set,
split[0].as_bytes(),
Span {
start: span.start,
end: span.start + split[0].len(),
},
);
let command_name = trim_quotes(split[1].as_bytes());
let decl_id = working_set.find_decl(command_name);
if let Some(decl_id) = decl_id {
return (SyntaxShape::Custom(Box::new(shape), decl_id), err);
} else {
return (
shape,
Some(ParseError::UnknownCommand(Span {
start: span.start + split[0].len() + 1,
end: span.end,
})),
);
}
} else {
return (SyntaxShape::Any, Some(ParseError::UnknownType(span)));
}
}
2021-09-02 10:25:22 +02:00
};
(result, None)
}
2021-07-16 23:55:12 +02:00
2021-09-04 09:59:38 +02:00
pub fn parse_type(_working_set: &StateWorkingSet, bytes: &[u8]) -> Type {
2021-10-12 06:49:17 +02:00
match bytes {
b"int" => Type::Int,
b"float" => Type::Float,
b"range" => Type::Range,
2021-10-12 06:49:17 +02:00
b"bool" => Type::Bool,
b"string" => Type::String,
b"block" => Type::Block,
b"duration" => Type::Duration,
b"date" => Type::Date,
2021-10-12 06:49:17 +02:00
b"filesize" => Type::Filesize,
b"number" => Type::Number,
b"table" => Type::Table(vec![]), //FIXME
b"error" => Type::Error,
2021-10-12 06:49:17 +02:00
b"binary" => Type::Binary,
_ => Type::Any,
2021-07-16 08:24:46 +02:00
}
2021-09-02 10:25:22 +02:00
}
2021-07-16 08:24:46 +02:00
2021-09-26 20:39:19 +02:00
pub fn parse_import_pattern(
2021-09-27 02:23:22 +02:00
working_set: &mut StateWorkingSet,
spans: &[Span],
expand_aliases_denylist: &[usize],
) -> (Expression, Option<ParseError>) {
2021-09-26 20:39:19 +02:00
let mut error = None;
let (head, head_span) = if let Some(head_span) = spans.get(0) {
(
working_set.get_span_contents(*head_span).to_vec(),
head_span,
)
} else {
2021-09-26 20:39:19 +02:00
return (
garbage(span(spans)),
Some(ParseError::WrongImportPattern(span(spans))),
2021-09-26 20:39:19 +02:00
);
};
2021-09-26 20:39:19 +02:00
let maybe_overlay_id = working_set.find_overlay(&head);
let (import_pattern, err) = if let Some(tail_span) = spans.get(1) {
2021-09-26 20:39:19 +02:00
// FIXME: expand this to handle deeper imports once we support module imports
let tail = working_set.get_span_contents(*tail_span);
2021-09-26 20:39:19 +02:00
if tail == b"*" {
(
ImportPattern {
head: ImportPatternHead {
name: head,
id: maybe_overlay_id,
span: *head_span,
},
members: vec![ImportPatternMember::Glob { span: *tail_span }],
hidden: HashSet::new(),
2021-09-26 20:39:19 +02:00
},
None,
2021-09-26 20:39:19 +02:00
)
2021-09-27 02:23:22 +02:00
} else if tail.starts_with(b"[") {
let (result, err) = parse_list_expression(
working_set,
*tail_span,
&SyntaxShape::String,
expand_aliases_denylist,
);
2021-09-27 02:23:22 +02:00
error = error.or(err);
let mut output = vec![];
match result {
Expression {
expr: Expr::List(list),
..
} => {
for l in list {
let contents = working_set.get_span_contents(l.span);
output.push((contents.to_vec(), l.span));
}
(
ImportPattern {
head: ImportPatternHead {
name: head,
id: maybe_overlay_id,
span: *head_span,
},
2021-09-27 02:23:22 +02:00
members: vec![ImportPatternMember::List { names: output }],
hidden: HashSet::new(),
2021-09-27 02:23:22 +02:00
},
None,
2021-09-27 02:23:22 +02:00
)
}
_ => (
ImportPattern {
head: ImportPatternHead {
name: head,
id: maybe_overlay_id,
span: *head_span,
},
2021-09-27 02:23:22 +02:00
members: vec![],
hidden: HashSet::new(),
2021-09-27 02:23:22 +02:00
},
Some(ParseError::ExportNotFound(result.span)),
),
}
2021-09-26 20:39:19 +02:00
} else {
2021-11-14 20:40:26 +01:00
let tail = trim_quotes(tail);
2021-09-26 20:39:19 +02:00
(
ImportPattern {
head: ImportPatternHead {
name: head,
id: maybe_overlay_id,
span: *head_span,
},
2021-09-26 20:39:19 +02:00
members: vec![ImportPatternMember::Name {
name: tail.to_vec(),
span: *tail_span,
2021-09-26 20:39:19 +02:00
}],
hidden: HashSet::new(),
2021-09-26 20:39:19 +02:00
},
None,
2021-09-26 20:39:19 +02:00
)
}
} else {
(
ImportPattern {
head: ImportPatternHead {
name: head,
id: maybe_overlay_id,
span: *head_span,
},
2021-09-26 20:39:19 +02:00
members: vec![],
hidden: HashSet::new(),
2021-09-26 20:39:19 +02:00
},
None,
)
};
(
Expression {
expr: Expr::ImportPattern(import_pattern),
span: span(&spans[1..]),
ty: Type::List(Box::new(Type::String)),
custom_completion: None,
},
error.or(err),
)
2021-09-26 20:39:19 +02:00
}
2021-09-02 10:25:22 +02:00
pub fn parse_var_with_opt_type(
working_set: &mut StateWorkingSet,
spans: &[Span],
spans_idx: &mut usize,
) -> (Expression, Option<ParseError>) {
let bytes = working_set.get_span_contents(spans[*spans_idx]).to_vec();
2021-07-16 08:24:46 +02:00
if bytes.contains(&b' ')
|| bytes.contains(&b'"')
|| bytes.contains(&b'\'')
|| bytes.contains(&b'`')
{
2021-10-12 07:08:55 +02:00
return (
garbage(spans[*spans_idx]),
Some(ParseError::VariableNotValid(spans[*spans_idx])),
);
}
2021-09-02 10:25:22 +02:00
if bytes.ends_with(b":") {
// We end with colon, so the next span should be the type
if *spans_idx + 1 < spans.len() {
*spans_idx += 1;
let type_bytes = working_set.get_span_contents(spans[*spans_idx]);
2021-07-16 08:24:46 +02:00
2021-09-02 10:25:22 +02:00
let ty = parse_type(working_set, type_bytes);
2021-07-16 08:24:46 +02:00
2022-03-09 10:42:19 +01:00
let id = working_set.add_variable(
bytes[0..(bytes.len() - 1)].to_vec(),
spans[*spans_idx - 1],
ty.clone(),
);
2021-07-16 08:24:46 +02:00
2021-09-02 10:25:22 +02:00
(
Expression {
2021-10-25 22:04:23 +02:00
expr: Expr::VarDecl(id),
2021-09-02 10:25:22 +02:00
span: span(&spans[*spans_idx - 1..*spans_idx + 1]),
ty,
custom_completion: None,
2021-09-02 10:25:22 +02:00
},
None,
)
2021-07-16 08:24:46 +02:00
} else {
2022-03-09 10:42:19 +01:00
let id = working_set.add_variable(
bytes[0..(bytes.len() - 1)].to_vec(),
spans[*spans_idx],
Type::Any,
2022-03-09 10:42:19 +01:00
);
2021-07-16 08:24:46 +02:00
(
Expression {
2021-10-25 22:04:23 +02:00
expr: Expr::VarDecl(id),
2021-09-02 10:25:22 +02:00
span: spans[*spans_idx],
ty: Type::Any,
custom_completion: None,
2021-07-16 08:24:46 +02:00
},
2021-09-02 10:25:22 +02:00
Some(ParseError::MissingType(spans[*spans_idx])),
2021-07-16 08:24:46 +02:00
)
}
} else if bytes == b"$config" || bytes == b"config" {
(
Expression {
expr: Expr::Var(CONFIG_VARIABLE_ID),
span: spans[*spans_idx],
ty: Type::Any,
custom_completion: None,
},
None,
)
2021-09-02 10:25:22 +02:00
} else {
let id =
working_set.add_variable(bytes, span(&spans[*spans_idx..*spans_idx + 1]), Type::Any);
2021-07-08 00:55:46 +02:00
2021-09-02 10:25:22 +02:00
(
Expression {
2021-10-25 22:04:23 +02:00
expr: Expr::VarDecl(id),
2021-09-02 10:25:22 +02:00
span: span(&spans[*spans_idx..*spans_idx + 1]),
ty: Type::Any,
custom_completion: None,
2021-09-02 10:25:22 +02:00
},
None,
)
}
}
2021-09-09 23:47:20 +02:00
pub fn expand_to_cell_path(
working_set: &mut StateWorkingSet,
expression: &mut Expression,
var_id: VarId,
expand_aliases_denylist: &[usize],
2021-09-09 23:47:20 +02:00
) {
if let Expression {
expr: Expr::String(_),
span,
..
} = expression
{
// Re-parse the string as if it were a cell-path
let (new_expression, _err) =
parse_full_cell_path(working_set, Some(var_id), *span, expand_aliases_denylist);
2021-09-09 23:47:20 +02:00
*expression = new_expression;
}
}
2021-09-02 10:25:22 +02:00
pub fn parse_row_condition(
working_set: &mut StateWorkingSet,
spans: &[Span],
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
let var_id = working_set.add_variable(b"$it".to_vec(), span(spans), Type::Any);
let (expression, err) =
parse_math_expression(working_set, spans, Some(var_id), expand_aliases_denylist);
2021-09-09 23:47:20 +02:00
let span = span(spans);
2021-11-26 04:49:03 +01:00
let block_id = match expression.expr {
Expr::Block(block_id) => block_id,
_ => {
// We have an expression, so let's convert this into a block.
let mut block = Block::new();
let mut pipeline = Pipeline::new();
pipeline.expressions.push(expression);
block.pipelines.push(pipeline);
2021-11-26 04:49:03 +01:00
block.signature.required_positional.push(PositionalArg {
name: "$it".into(),
desc: "row condition".into(),
shape: SyntaxShape::Any,
var_id: Some(var_id),
2022-03-07 21:08:56 +01:00
default_value: None,
2021-11-26 04:49:03 +01:00
});
working_set.add_block(block)
}
};
2021-09-09 23:47:20 +02:00
(
Expression {
ty: Type::Bool,
span,
2021-11-26 04:49:03 +01:00
expr: Expr::RowCondition(block_id),
custom_completion: None,
2021-09-09 23:47:20 +02:00
},
err,
)
2021-09-02 10:25:22 +02:00
}
2021-07-16 23:55:12 +02:00
2021-09-02 10:25:22 +02:00
pub fn parse_signature(
working_set: &mut StateWorkingSet,
span: Span,
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
let bytes = working_set.get_span_contents(span);
2021-07-16 23:55:12 +02:00
2021-09-02 10:25:22 +02:00
let mut error = None;
let mut start = span.start;
let mut end = span.end;
2021-07-16 23:55:12 +02:00
2021-09-02 10:25:22 +02:00
if bytes.starts_with(b"[") {
start += 1;
2021-10-11 22:58:38 +02:00
} else {
error = error.or_else(|| {
Some(ParseError::Expected(
"[".into(),
Span {
start,
end: start + 1,
},
))
});
2021-09-02 10:25:22 +02:00
}
2021-10-11 22:58:38 +02:00
2021-09-02 10:25:22 +02:00
if bytes.ends_with(b"]") {
end -= 1;
} else {
error = error.or_else(|| Some(ParseError::Unclosed("]".into(), Span { start: end, end })));
2021-09-02 10:25:22 +02:00
}
2021-07-16 23:55:12 +02:00
let (sig, err) =
parse_signature_helper(working_set, Span { start, end }, expand_aliases_denylist);
2021-09-06 01:16:27 +02:00
error = error.or(err);
(
Expression {
expr: Expr::Signature(sig),
span,
ty: Type::Signature,
custom_completion: None,
2021-09-06 01:16:27 +02:00
},
error,
)
}
pub fn parse_signature_helper(
working_set: &mut StateWorkingSet,
span: Span,
expand_aliases_denylist: &[usize],
2021-09-06 01:16:27 +02:00
) -> (Box<Signature>, Option<ParseError>) {
2022-03-07 21:08:56 +01:00
#[allow(clippy::enum_variant_names)]
2021-09-06 01:16:27 +02:00
enum ParseMode {
ArgMode,
TypeMode,
2022-03-07 21:08:56 +01:00
DefaultValueMode,
2021-09-06 01:16:27 +02:00
}
2022-03-07 21:08:56 +01:00
#[derive(Debug)]
2021-09-06 01:16:27 +02:00
enum Arg {
Positional(PositionalArg, bool), // bool - required
RestPositional(PositionalArg),
2021-09-06 01:16:27 +02:00
Flag(Flag),
}
let mut error = None;
2021-09-02 10:25:22 +02:00
let source = working_set.get_span_contents(span);
2021-07-16 23:55:12 +02:00
2022-03-07 21:08:56 +01:00
let (output, err) = lex(
source,
span.start,
&[b'\n', b'\r', b','],
&[b':', b'='],
false,
);
2021-09-02 10:25:22 +02:00
error = error.or(err);
2021-07-16 23:55:12 +02:00
2021-09-02 10:25:22 +02:00
let mut args: Vec<Arg> = vec![];
let mut parse_mode = ParseMode::ArgMode;
2021-07-16 23:55:12 +02:00
2021-09-02 10:25:22 +02:00
for token in &output {
match token {
Token {
contents: crate::TokenContents::Item,
span,
} => {
let span = *span;
let contents = working_set.get_span_contents(span);
if contents == b":" {
match parse_mode {
ParseMode::ArgMode => {
parse_mode = ParseMode::TypeMode;
2021-07-16 23:55:12 +02:00
}
2022-03-07 21:08:56 +01:00
ParseMode::TypeMode | ParseMode::DefaultValueMode => {
2021-09-02 10:25:22 +02:00
// We're seeing two types for the same thing for some reason, error
error =
error.or_else(|| Some(ParseError::Expected("type".into(), span)));
}
}
2022-03-07 21:08:56 +01:00
} else if contents == b"=" {
match parse_mode {
ParseMode::ArgMode | ParseMode::TypeMode => {
parse_mode = ParseMode::DefaultValueMode;
}
ParseMode::DefaultValueMode => {
// We're seeing two default values for some reason, error
error = error.or_else(|| {
Some(ParseError::Expected("default value".into(), span))
});
}
}
2021-09-02 10:25:22 +02:00
} else {
match parse_mode {
ParseMode::ArgMode => {
if contents.starts_with(b"--") && contents.len() > 2 {
// Long flag
let flags: Vec<_> =
contents.split(|x| x == &b'(').map(|x| x.to_vec()).collect();
2021-10-13 19:53:27 +02:00
let long = String::from_utf8_lossy(&flags[0][2..]).to_string();
2021-09-02 10:25:22 +02:00
let variable_name = flags[0][2..].to_vec();
2022-03-09 10:42:19 +01:00
let var_id =
working_set.add_variable(variable_name, span, Type::Any);
2021-09-02 10:25:22 +02:00
if flags.len() == 1 {
args.push(Arg::Flag(Flag {
arg: None,
desc: String::new(),
long,
short: None,
required: false,
var_id: Some(var_id),
2022-03-07 21:08:56 +01:00
default_value: None,
2021-09-02 10:25:22 +02:00
}));
} else {
let short_flag = &flags[1];
let short_flag = if !short_flag.starts_with(b"-")
|| !short_flag.ends_with(b")")
{
error = error.or_else(|| {
Some(ParseError::Expected("short flag".into(), span))
});
short_flag
2021-07-17 20:52:50 +02:00
} else {
2021-09-02 10:25:22 +02:00
&short_flag[1..(short_flag.len() - 1)]
};
2021-07-17 00:39:30 +02:00
let short_flag =
String::from_utf8_lossy(short_flag).to_string();
let chars: Vec<char> = short_flag.chars().collect();
2021-10-13 19:53:27 +02:00
let long = String::from_utf8_lossy(&flags[0][2..]).to_string();
2021-09-02 10:25:22 +02:00
let variable_name = flags[0][2..].to_vec();
let var_id =
working_set.add_variable(variable_name, span, Type::Any);
2021-07-17 00:39:30 +02:00
2021-09-02 10:25:22 +02:00
if chars.len() == 1 {
2021-07-17 00:39:30 +02:00
args.push(Arg::Flag(Flag {
arg: None,
desc: String::new(),
2021-09-02 10:25:22 +02:00
long,
2021-07-17 00:39:30 +02:00
short: Some(chars[0]),
required: false,
2021-07-23 23:19:30 +02:00
var_id: Some(var_id),
2022-03-07 21:08:56 +01:00
default_value: None,
2021-07-17 00:39:30 +02:00
}));
2021-09-02 10:25:22 +02:00
} else {
2021-07-30 00:56:51 +02:00
error = error.or_else(|| {
2021-08-17 01:00:00 +02:00
Some(ParseError::Expected("short flag".into(), span))
2021-07-30 00:56:51 +02:00
});
2021-09-02 10:25:22 +02:00
}
}
} else if contents.starts_with(b"-") && contents.len() > 1 {
// Short flag
let short_flag = &contents[1..];
let short_flag = String::from_utf8_lossy(short_flag).to_string();
let chars: Vec<char> = short_flag.chars().collect();
if chars.len() > 1 {
error = error.or_else(|| {
Some(ParseError::Expected("short flag".into(), span))
});
2022-01-06 22:06:54 +01:00
}
2021-09-02 10:25:22 +02:00
2022-01-06 22:06:54 +01:00
let mut encoded_var_name = vec![0u8; 4];
let len = chars[0].encode_utf8(&mut encoded_var_name).len();
let variable_name = encoded_var_name[0..len].to_vec();
2022-03-09 10:42:19 +01:00
let var_id =
working_set.add_variable(variable_name, span, Type::Any);
2021-09-02 10:25:22 +02:00
2022-01-06 22:06:54 +01:00
args.push(Arg::Flag(Flag {
arg: None,
desc: String::new(),
long: String::new(),
short: Some(chars[0]),
required: false,
var_id: Some(var_id),
2022-03-07 21:08:56 +01:00
default_value: None,
2022-01-06 22:06:54 +01:00
}));
2021-09-02 10:25:22 +02:00
} else if contents.starts_with(b"(-") {
let short_flag = &contents[2..];
let short_flag = if !short_flag.ends_with(b")") {
error = error.or_else(|| {
Some(ParseError::Expected("short flag".into(), span))
});
short_flag
} else {
&short_flag[..(short_flag.len() - 1)]
};
2021-07-17 20:52:50 +02:00
2021-09-02 10:25:22 +02:00
let short_flag = String::from_utf8_lossy(short_flag).to_string();
let chars: Vec<char> = short_flag.chars().collect();
2021-07-17 20:52:50 +02:00
2021-09-02 10:25:22 +02:00
if chars.len() == 1 {
match args.last_mut() {
Some(Arg::Flag(flag)) => {
if flag.short.is_some() {
2021-07-30 00:56:51 +02:00
error = error.or_else(|| {
2021-08-17 01:00:00 +02:00
Some(ParseError::Expected(
2021-09-02 10:25:22 +02:00
"one short flag".into(),
2021-07-30 00:56:51 +02:00
span,
))
});
2021-09-02 10:25:22 +02:00
} else {
flag.short = Some(chars[0]);
2021-07-17 20:52:50 +02:00
}
}
2021-09-02 10:25:22 +02:00
_ => {
error = error.or_else(|| {
Some(ParseError::Expected(
"unknown flag".into(),
span,
))
});
}
2021-07-17 20:52:50 +02:00
}
2021-07-30 00:56:51 +02:00
} else {
2021-09-02 10:25:22 +02:00
error = error.or_else(|| {
Some(ParseError::Expected("short flag".into(), span))
});
2021-07-16 23:55:12 +02:00
}
2021-09-02 10:25:22 +02:00
} else if contents.ends_with(b"?") {
let contents: Vec<_> = contents[..(contents.len() - 1)].into();
let name = String::from_utf8_lossy(&contents).to_string();
let var_id = working_set.add_variable(contents, span, Type::Any);
2021-09-02 10:25:22 +02:00
// Positional arg, optional
args.push(Arg::Positional(
PositionalArg {
desc: String::new(),
name,
shape: SyntaxShape::Any,
var_id: Some(var_id),
2022-03-07 21:08:56 +01:00
default_value: None,
2021-09-02 10:25:22 +02:00
},
false,
))
2021-09-07 05:37:02 +02:00
} else if let Some(contents) = contents.strip_prefix(b"...") {
let name = String::from_utf8_lossy(contents).to_string();
let contents_vec: Vec<u8> = contents.to_vec();
2022-03-09 10:42:19 +01:00
let var_id =
working_set.add_variable(contents_vec, span, Type::Any);
2021-09-07 05:37:02 +02:00
args.push(Arg::RestPositional(PositionalArg {
desc: String::new(),
name,
shape: SyntaxShape::Any,
var_id: Some(var_id),
2022-03-07 21:08:56 +01:00
default_value: None,
}));
2021-09-02 10:25:22 +02:00
} else {
let name = String::from_utf8_lossy(contents).to_string();
let contents_vec = contents.to_vec();
2022-03-09 10:42:19 +01:00
let var_id =
working_set.add_variable(contents_vec, span, Type::Any);
2021-09-02 10:25:22 +02:00
// Positional arg, required
args.push(Arg::Positional(
PositionalArg {
desc: String::new(),
name,
shape: SyntaxShape::Any,
var_id: Some(var_id),
2022-03-07 21:08:56 +01:00
default_value: None,
2021-09-02 10:25:22 +02:00
},
true,
))
2021-07-16 23:55:12 +02:00
}
2021-09-02 10:25:22 +02:00
}
ParseMode::TypeMode => {
if let Some(last) = args.last_mut() {
let (syntax_shape, err) =
parse_shape_name(working_set, contents, span);
error = error.or(err);
2021-10-12 19:44:23 +02:00
//TODO check if we're replacing a custom parameter already
2021-09-02 10:25:22 +02:00
match last {
Arg::Positional(PositionalArg { shape, var_id, .. }, ..) => {
working_set.set_variable_type(var_id.expect("internal error: all custom parameters must have var_ids"), syntax_shape.to_type());
*shape = syntax_shape;
}
Arg::RestPositional(PositionalArg {
shape, var_id, ..
}) => {
working_set.set_variable_type(var_id.expect("internal error: all custom parameters must have var_ids"), syntax_shape.to_type());
*shape = syntax_shape;
}
2021-09-02 10:25:22 +02:00
Arg::Flag(Flag { arg, var_id, .. }) => {
2021-10-12 06:49:17 +02:00
// Flags with a boolean type are just present/not-present switches
if syntax_shape != SyntaxShape::Boolean {
working_set.set_variable_type(var_id.expect("internal error: all custom parameters must have var_ids"), syntax_shape.to_type());
*arg = Some(syntax_shape)
}
2021-07-16 23:55:12 +02:00
}
}
}
2021-09-02 10:25:22 +02:00
parse_mode = ParseMode::ArgMode;
2021-07-16 23:55:12 +02:00
}
2022-03-07 21:08:56 +01:00
ParseMode::DefaultValueMode => {
if let Some(last) = args.last_mut() {
let (expression, err) = parse_value(
working_set,
span,
&SyntaxShape::Any,
expand_aliases_denylist,
);
2022-03-07 21:08:56 +01:00
error = error.or(err);
//TODO check if we're replacing a custom parameter already
match last {
Arg::Positional(
PositionalArg {
shape,
var_id,
default_value,
..
},
required,
) => {
let var_id = var_id.expect("internal error: all custom parameters must have var_ids");
2022-03-09 10:42:19 +01:00
let var_type = &working_set.get_variable(var_id).ty;
2022-03-07 21:08:56 +01:00
match var_type {
Type::Any => {
2022-03-07 21:08:56 +01:00
working_set.set_variable_type(
var_id,
expression.ty.clone(),
);
}
t => {
if t != &expression.ty {
error = error.or_else(|| {
Some(ParseError::AssignmentMismatch(
"Default value wrong type".into(),
format!("default value not {}", t),
expression.span,
))
})
}
}
}
*shape = expression.ty.to_shape();
*default_value = Some(expression);
*required = false;
}
Arg::RestPositional(..) => {
error = error.or_else(|| {
Some(ParseError::AssignmentMismatch(
"Rest parameter given default value".into(),
"can't have default value".into(),
expression.span,
))
})
}
Arg::Flag(Flag {
arg,
var_id,
default_value,
..
}) => {
let var_id = var_id.expect("internal error: all custom parameters must have var_ids");
2022-03-09 10:42:19 +01:00
let var_type = &working_set.get_variable(var_id).ty;
2022-03-07 21:08:56 +01:00
let expression_ty = expression.ty.clone();
let expression_span = expression.span;
*default_value = Some(expression);
// Flags with a boolean type are just present/not-present switches
if var_type != &Type::Bool {
match var_type {
Type::Any => {
2022-03-07 21:08:56 +01:00
*arg = Some(expression_ty.to_shape());
working_set
.set_variable_type(var_id, expression_ty);
}
t => {
if t != &expression_ty {
error = error.or_else(|| {
Some(ParseError::AssignmentMismatch(
"Default value wrong type".into(),
format!("default value not {}", t),
expression_span,
))
})
}
}
}
}
}
}
}
parse_mode = ParseMode::ArgMode;
}
2021-07-16 23:55:12 +02:00
}
}
2021-09-02 10:25:22 +02:00
}
Token {
contents: crate::TokenContents::Comment,
span,
} => {
let contents = working_set.get_span_contents(Span {
start: span.start + 1,
end: span.end,
});
let mut contents = String::from_utf8_lossy(contents).to_string();
contents = contents.trim().into();
if let Some(last) = args.last_mut() {
match last {
Arg::Flag(flag) => {
if !flag.desc.is_empty() {
flag.desc.push('\n');
2021-07-17 00:31:36 +02:00
}
2021-09-02 10:25:22 +02:00
flag.desc.push_str(&contents);
}
Arg::Positional(positional, ..) => {
if !positional.desc.is_empty() {
positional.desc.push('\n');
2021-07-17 00:31:36 +02:00
}
2021-09-02 10:25:22 +02:00
positional.desc.push_str(&contents);
2021-07-17 00:31:36 +02:00
}
Arg::RestPositional(positional) => {
if !positional.desc.is_empty() {
positional.desc.push('\n');
}
positional.desc.push_str(&contents);
}
2021-07-17 00:31:36 +02:00
}
}
2021-07-16 23:55:12 +02:00
}
2021-09-02 10:25:22 +02:00
_ => {}
2021-07-16 23:55:12 +02:00
}
2021-09-02 10:25:22 +02:00
}
2021-07-16 23:55:12 +02:00
2021-09-02 10:25:22 +02:00
let mut sig = Signature::new(String::new());
for arg in args {
match arg {
Arg::Positional(positional, required) => {
2021-09-07 05:37:02 +02:00
if required {
2022-03-07 21:08:56 +01:00
if !sig.optional_positional.is_empty() {
error = error.or_else(|| {
Some(ParseError::RequiredAfterOptional(
positional.name.clone(),
span,
))
})
}
2021-09-02 10:25:22 +02:00
sig.required_positional.push(positional)
} else {
sig.optional_positional.push(positional)
2021-07-17 00:53:45 +02:00
}
2021-07-16 23:55:12 +02:00
}
2021-09-02 10:25:22 +02:00
Arg::Flag(flag) => sig.named.push(flag),
Arg::RestPositional(positional) => {
if positional.name.is_empty() {
error = error.or(Some(ParseError::RestNeedsName(span)))
} else if sig.rest_positional.is_none() {
sig.rest_positional = Some(PositionalArg {
name: positional.name,
..positional
})
} else {
// Too many rest params
error = error.or(Some(ParseError::MultipleRestParams(span)))
}
}
2021-07-16 23:55:12 +02:00
}
}
2021-09-06 01:16:27 +02:00
(Box::new(sig), error)
2021-09-02 10:25:22 +02:00
}
2021-07-08 09:49:17 +02:00
2021-09-02 10:25:22 +02:00
pub fn parse_list_expression(
working_set: &mut StateWorkingSet,
span: Span,
element_shape: &SyntaxShape,
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
let bytes = working_set.get_span_contents(span);
2021-07-08 09:49:17 +02:00
2021-09-02 10:25:22 +02:00
let mut error = None;
2021-07-08 09:49:17 +02:00
2021-09-02 10:25:22 +02:00
let mut start = span.start;
let mut end = span.end;
2021-07-08 09:49:17 +02:00
2021-09-02 10:25:22 +02:00
if bytes.starts_with(b"[") {
start += 1;
}
if bytes.ends_with(b"]") {
end -= 1;
} else {
error = error.or_else(|| Some(ParseError::Unclosed("]".into(), Span { start: end, end })));
2021-09-02 10:25:22 +02:00
}
2021-07-08 09:49:17 +02:00
let inner_span = Span { start, end };
let source = working_set.get_span_contents(inner_span);
2021-07-08 09:49:17 +02:00
let (output, err) = lex(source, inner_span.start, &[b'\n', b'\r', b','], &[], true);
2021-09-02 10:25:22 +02:00
error = error.or(err);
2021-07-08 09:49:17 +02:00
2021-09-02 10:25:22 +02:00
let (output, err) = lite_parse(&output);
error = error.or(err);
2021-07-08 23:45:56 +02:00
2021-09-02 10:25:22 +02:00
let mut args = vec![];
2021-08-17 02:26:05 +02:00
2021-09-02 10:25:22 +02:00
let mut contained_type: Option<Type> = None;
2021-07-08 09:49:17 +02:00
2021-09-02 10:25:22 +02:00
if !output.block.is_empty() {
for arg in &output.block[0].commands {
let mut spans_idx = 0;
2021-07-08 23:45:56 +02:00
2021-09-02 10:25:22 +02:00
while spans_idx < arg.parts.len() {
let (arg, err) = parse_multispan_value(
working_set,
&arg.parts,
&mut spans_idx,
element_shape,
expand_aliases_denylist,
);
2021-09-02 10:25:22 +02:00
error = error.or(err);
if let Some(ref ctype) = contained_type {
if *ctype != arg.ty {
contained_type = Some(Type::Any);
2021-08-17 02:26:05 +02:00
}
2021-09-02 10:25:22 +02:00
} else {
contained_type = Some(arg.ty.clone());
}
2021-08-17 02:26:05 +02:00
2021-09-02 10:25:22 +02:00
args.push(arg);
2021-07-16 08:24:46 +02:00
2021-09-02 10:25:22 +02:00
spans_idx += 1;
2021-07-08 09:49:17 +02:00
}
}
}
2021-09-02 10:25:22 +02:00
(
Expression {
expr: Expr::List(args),
span,
ty: Type::List(Box::new(if let Some(ty) = contained_type {
2021-09-04 09:59:38 +02:00
ty
2021-09-02 10:25:22 +02:00
} else {
Type::Any
2021-09-02 10:25:22 +02:00
})),
custom_completion: None,
2021-09-02 10:25:22 +02:00
},
error,
)
}
pub fn parse_table_expression(
working_set: &mut StateWorkingSet,
2021-09-08 20:54:27 +02:00
original_span: Span,
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
2021-09-08 20:54:27 +02:00
let bytes = working_set.get_span_contents(original_span);
2021-09-02 10:25:22 +02:00
let mut error = None;
2021-07-06 00:58:56 +02:00
2021-09-08 20:54:27 +02:00
let mut start = original_span.start;
let mut end = original_span.end;
2021-07-06 00:58:56 +02:00
2021-09-02 10:25:22 +02:00
if bytes.starts_with(b"[") {
start += 1;
}
if bytes.ends_with(b"]") {
end -= 1;
} else {
error = error.or_else(|| Some(ParseError::Unclosed("]".into(), Span { start: end, end })));
2021-09-02 10:25:22 +02:00
}
2021-07-06 00:58:56 +02:00
let inner_span = Span { start, end };
2021-07-06 00:58:56 +02:00
let source = working_set.get_span_contents(inner_span);
2021-07-06 00:58:56 +02:00
2021-11-21 19:13:09 +01:00
let (output, err) = lex(source, start, &[b'\n', b'\r', b','], &[], true);
2021-09-02 10:25:22 +02:00
error = error.or(err);
2021-07-06 00:58:56 +02:00
2021-09-02 10:25:22 +02:00
let (output, err) = lite_parse(&output);
error = error.or(err);
2021-07-06 00:58:56 +02:00
2021-09-02 10:25:22 +02:00
match output.block.len() {
0 => (
Expression {
expr: Expr::List(vec![]),
span: original_span,
ty: Type::List(Box::new(Type::Any)),
custom_completion: None,
2021-09-02 10:25:22 +02:00
},
None,
),
1 => {
// List
parse_list_expression(
working_set,
original_span,
&SyntaxShape::Any,
expand_aliases_denylist,
)
2021-09-02 10:25:22 +02:00
}
_ => {
let mut table_headers = vec![];
let (headers, err) = parse_value(
working_set,
output.block[0].commands[0].parts[0],
&SyntaxShape::List(Box::new(SyntaxShape::Any)),
expand_aliases_denylist,
2021-09-02 10:25:22 +02:00
);
error = error.or(err);
if let Expression {
expr: Expr::List(headers),
..
} = headers
{
table_headers = headers;
2021-07-06 00:58:56 +02:00
}
2021-07-06 03:48:45 +02:00
2021-09-02 10:25:22 +02:00
let mut rows = vec![];
for part in &output.block[1].commands[0].parts {
let (values, err) = parse_value(
working_set,
*part,
2021-08-28 21:17:30 +02:00
&SyntaxShape::List(Box::new(SyntaxShape::Any)),
expand_aliases_denylist,
2021-08-28 21:17:30 +02:00
);
2021-07-06 03:48:45 +02:00
error = error.or(err);
if let Expression {
2021-09-02 10:25:22 +02:00
expr: Expr::List(values),
2021-09-08 20:54:27 +02:00
span,
2021-07-06 03:48:45 +02:00
..
2021-09-02 10:25:22 +02:00
} = values
2021-07-06 03:48:45 +02:00
{
2021-09-08 20:54:27 +02:00
match values.len().cmp(&table_headers.len()) {
std::cmp::Ordering::Less => {
error = error
.or(Some(ParseError::MissingColumns(table_headers.len(), span)))
2021-09-08 20:54:27 +02:00
}
std::cmp::Ordering::Equal => {}
std::cmp::Ordering::Greater => {
error = error.or_else(|| {
Some(ParseError::ExtraColumns(
table_headers.len(),
values[table_headers.len()].span,
))
})
}
}
2021-09-02 10:25:22 +02:00
rows.push(values);
2021-07-06 03:48:45 +02:00
}
}
2021-07-02 09:32:30 +02:00
2021-09-02 10:25:22 +02:00
(
Expression {
expr: Expr::Table(table_headers, rows),
span: original_span,
ty: Type::Table(vec![]), //FIXME
custom_completion: None,
2021-09-02 10:25:22 +02:00
},
error,
)
2021-07-02 09:32:30 +02:00
}
2021-09-02 10:25:22 +02:00
}
}
2021-07-02 09:32:30 +02:00
2021-09-02 10:25:22 +02:00
pub fn parse_block_expression(
working_set: &mut StateWorkingSet,
shape: &SyntaxShape,
2021-09-02 10:25:22 +02:00
span: Span,
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
2022-01-01 22:42:50 +01:00
trace!("parsing: block expression");
2021-09-02 10:25:22 +02:00
let bytes = working_set.get_span_contents(span);
let mut error = None;
2021-07-02 09:32:30 +02:00
2021-09-02 10:25:22 +02:00
let mut start = span.start;
let mut end = span.end;
2021-07-02 09:32:30 +02:00
2021-09-02 10:25:22 +02:00
if bytes.starts_with(b"{") {
start += 1;
} else {
return (
garbage(span),
Some(ParseError::Expected("block".into(), span)),
);
}
if bytes.ends_with(b"}") {
end -= 1;
} else {
error = error.or_else(|| Some(ParseError::Unclosed("}".into(), Span { start: end, end })));
2021-09-02 10:25:22 +02:00
}
2021-07-02 09:32:30 +02:00
2022-01-03 06:21:26 +01:00
let inner_span = Span { start, end };
2021-09-02 10:25:22 +02:00
2022-01-03 06:21:26 +01:00
let source = working_set.get_span_contents(inner_span);
2021-09-02 10:25:22 +02:00
let (output, err) = lex(source, start, &[], &[], false);
2021-09-02 10:25:22 +02:00
error = error.or(err);
2021-09-06 04:20:02 +02:00
working_set.enter_scope();
2021-09-08 00:00:20 +02:00
2021-09-02 10:25:22 +02:00
// Check to see if we have parameters
let (signature, amt_to_skip): (Option<(Box<Signature>, Span)>, usize) = match output.first() {
2021-09-02 10:25:22 +02:00
Some(Token {
contents: TokenContents::Pipe,
2021-09-06 01:16:27 +02:00
span,
}) => {
// We've found a parameter list
let start_point = span.start;
let mut token_iter = output.iter().enumerate().skip(1);
let mut end_span = None;
let mut amt_to_skip = 1;
for token in &mut token_iter {
if let Token {
2021-09-02 10:25:22 +02:00
contents: TokenContents::Pipe,
2021-09-06 01:16:27 +02:00
span,
} = token.1
{
end_span = Some(span);
amt_to_skip = token.0;
break;
2021-08-25 21:29:36 +02:00
}
}
2021-09-06 01:16:27 +02:00
let end_point = if let Some(span) = end_span {
span.end
} else {
end
};
let signature_span = Span {
start: start_point,
end: end_point,
};
let (signature, err) =
parse_signature_helper(working_set, signature_span, expand_aliases_denylist);
2021-09-06 01:16:27 +02:00
error = error.or(err);
(Some((signature, signature_span)), amt_to_skip)
2021-09-02 10:25:22 +02:00
}
2021-09-06 01:16:27 +02:00
_ => (None, 0),
2021-09-02 10:25:22 +02:00
};
2021-08-25 21:29:36 +02:00
2021-09-06 01:16:27 +02:00
let (output, err) = lite_parse(&output[amt_to_skip..]);
2021-09-02 10:25:22 +02:00
error = error.or(err);
2021-07-02 09:32:30 +02:00
// TODO: Finish this
if let SyntaxShape::Block(Some(v)) = shape {
if let Some((sig, sig_span)) = &signature {
if sig.num_positionals() != v.len() {
error = error.or_else(|| {
Some(ParseError::Expected(
format!(
"{} block parameter{}",
v.len(),
if v.len() > 1 { "s" } else { "" }
),
*sig_span,
))
});
}
for (expected, PositionalArg { name, shape, .. }) in
v.iter().zip(sig.required_positional.iter())
{
if expected != shape && *shape != SyntaxShape::Any {
error = error.or_else(|| {
Some(ParseError::ParameterMismatchType(
name.to_owned(),
expected.to_string(),
shape.to_string(),
*sig_span,
))
});
}
}
} else if !v.is_empty() {
error = error.or_else(|| {
Some(ParseError::Expected(
format!(
"{} block parameter{}",
v.len(),
if v.len() > 1 { "s" } else { "" }
),
Span {
start: span.start + 1,
end: span.start + 1,
},
))
});
}
}
let (mut output, err) = parse_block(working_set, &output, false, expand_aliases_denylist);
2021-09-02 10:25:22 +02:00
error = error.or(err);
2021-07-02 09:32:30 +02:00
2021-09-06 01:16:27 +02:00
if let Some(signature) = signature {
output.signature = signature.0;
2021-09-06 04:20:02 +02:00
} else if let Some(last) = working_set.delta.scope.last() {
2021-10-12 19:44:23 +02:00
// FIXME: this only supports the top $it. Is this sufficient?
2021-09-13 09:31:11 +02:00
2021-09-06 04:20:02 +02:00
if let Some(var_id) = last.get_var(b"$it") {
let mut signature = Signature::new("");
signature.required_positional.push(PositionalArg {
var_id: Some(*var_id),
name: "$it".into(),
desc: String::new(),
shape: SyntaxShape::Any,
2022-03-07 21:08:56 +01:00
default_value: None,
2021-09-06 04:20:02 +02:00
});
output.signature = Box::new(signature);
}
2021-09-06 01:16:27 +02:00
}
output.span = Some(span);
2021-10-25 22:04:23 +02:00
2021-09-06 04:20:02 +02:00
working_set.exit_scope();
2021-09-02 10:25:22 +02:00
let block_id = working_set.add_block(output);
2021-07-16 22:26:40 +02:00
2021-09-02 10:25:22 +02:00
(
Expression {
expr: Expr::Block(block_id),
span,
ty: Type::Block,
custom_completion: None,
2021-09-02 10:25:22 +02:00
},
error,
)
}
2021-07-02 09:32:30 +02:00
2021-09-02 10:25:22 +02:00
pub fn parse_value(
working_set: &mut StateWorkingSet,
span: Span,
shape: &SyntaxShape,
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
let bytes = working_set.get_span_contents(span);
if bytes.is_empty() {
return (garbage(span), Some(ParseError::IncompleteParser(span)));
}
2021-09-02 10:25:22 +02:00
// First, check the special-cases. These will likely represent specific values as expressions
// and may fit a variety of shapes.
//
// We check variable first because immediately following we check for variables with cell paths
2021-09-02 10:25:22 +02:00
// which might result in a value that fits other shapes (and require the variable to already be
// declared)
if shape == &SyntaxShape::Variable {
2022-01-01 22:42:50 +01:00
trace!("parsing: variable");
2021-09-02 10:25:22 +02:00
return parse_variable_expr(working_set, span);
}
2022-01-01 22:42:50 +01:00
// Check for reserved keyword values
match bytes {
b"true" => {
if matches!(shape, SyntaxShape::Boolean) || matches!(shape, SyntaxShape::Any) {
return (
Expression {
expr: Expr::Bool(true),
span,
ty: Type::Bool,
custom_completion: None,
},
None,
);
} else {
return (
Expression::garbage(span),
Some(ParseError::Expected("non-boolean value".into(), span)),
);
}
}
b"false" => {
if matches!(shape, SyntaxShape::Boolean) || matches!(shape, SyntaxShape::Any) {
return (
Expression {
expr: Expr::Bool(false),
span,
ty: Type::Bool,
custom_completion: None,
},
None,
);
} else {
return (
Expression::garbage(span),
Some(ParseError::Expected("non-boolean value".into(), span)),
);
}
}
b"null" => {
return (
Expression {
expr: Expr::Nothing,
span,
ty: Type::Nothing,
custom_completion: None,
},
None,
);
}
_ => {}
}
match bytes[0] {
b'$' => return parse_dollar_expr(working_set, span, expand_aliases_denylist),
b'(' => {
if let (expr, None) = parse_range(working_set, span, expand_aliases_denylist) {
2021-11-11 00:14:00 +01:00
return (expr, None);
} else {
return parse_full_cell_path(working_set, None, span, expand_aliases_denylist);
2021-11-11 00:14:00 +01:00
}
}
b'{' => {
if !matches!(shape, SyntaxShape::Block(..)) {
if let (expr, None) =
parse_full_cell_path(working_set, None, span, expand_aliases_denylist)
{
return (expr, None);
}
}
if matches!(shape, SyntaxShape::Block(_)) || matches!(shape, SyntaxShape::Any) {
return parse_block_expression(working_set, shape, span, expand_aliases_denylist);
} else if matches!(shape, SyntaxShape::Record) {
return parse_record(working_set, span, expand_aliases_denylist);
} else {
return (
Expression::garbage(span),
Some(ParseError::Expected("non-block value".into(), span)),
);
}
2021-09-04 08:52:28 +02:00
}
b'[' => match shape {
2021-09-02 10:25:22 +02:00
SyntaxShape::Any
| SyntaxShape::List(_)
| SyntaxShape::Table
| SyntaxShape::Signature => {}
_ => {
return (
Expression::garbage(span),
Some(ParseError::Expected("non-[] value".into(), span)),
);
2021-07-08 23:45:56 +02:00
}
},
_ => {}
2021-09-02 10:25:22 +02:00
}
2021-07-01 03:31:02 +02:00
2021-09-02 10:25:22 +02:00
match shape {
SyntaxShape::Custom(shape, custom_completion) => {
let (mut expression, err) =
parse_value(working_set, span, shape, expand_aliases_denylist);
expression.custom_completion = Some(*custom_completion);
(expression, err)
}
2021-09-07 00:02:24 +02:00
SyntaxShape::Number => parse_number(bytes, span),
SyntaxShape::Int => parse_int(bytes, span),
2021-10-05 04:27:39 +02:00
SyntaxShape::Duration => parse_duration(working_set, span),
SyntaxShape::DateTime => parse_datetime(working_set, span),
2021-10-05 04:27:39 +02:00
SyntaxShape::Filesize => parse_filesize(working_set, span),
SyntaxShape::Range => parse_range(working_set, span, expand_aliases_denylist),
2021-10-04 21:21:31 +02:00
SyntaxShape::Filepath => parse_filepath(working_set, span),
SyntaxShape::GlobPattern => parse_glob_pattern(working_set, span),
SyntaxShape::String => parse_string(working_set, span),
2022-03-01 00:31:53 +01:00
SyntaxShape::Binary => parse_binary(working_set, span),
2021-09-02 10:25:22 +02:00
SyntaxShape::Signature => {
if bytes.starts_with(b"[") {
parse_signature(working_set, span, expand_aliases_denylist)
2021-09-02 10:25:22 +02:00
} else {
(
Expression::garbage(span),
Some(ParseError::Expected("signature".into(), span)),
)
2021-07-09 08:23:20 +02:00
}
2021-09-02 10:25:22 +02:00
}
SyntaxShape::List(elem) => {
if bytes.starts_with(b"[") {
parse_list_expression(working_set, span, elem, expand_aliases_denylist)
2021-09-02 10:25:22 +02:00
} else {
(
Expression::garbage(span),
Some(ParseError::Expected("list".into(), span)),
)
2021-07-08 09:49:17 +02:00
}
2021-09-02 10:25:22 +02:00
}
SyntaxShape::Table => {
if bytes.starts_with(b"[") {
parse_table_expression(working_set, span, expand_aliases_denylist)
2021-09-02 10:25:22 +02:00
} else {
2021-07-02 08:44:37 +02:00
(
2021-09-02 10:25:22 +02:00
Expression::garbage(span),
Some(ParseError::Expected("table".into(), span)),
2021-07-02 08:44:37 +02:00
)
}
2021-07-01 02:01:04 +02:00
}
2021-10-02 04:59:11 +02:00
SyntaxShape::CellPath => {
let source = working_set.get_span_contents(span);
let mut error = None;
2021-11-21 19:13:09 +01:00
let (tokens, err) = lex(source, span.start, &[b'\n', b'\r'], &[b'.'], true);
2021-10-02 04:59:11 +02:00
error = error.or(err);
let tokens = tokens.into_iter().peekable();
let (cell_path, err) = parse_cell_path(working_set, tokens, false, span);
error = error.or(err);
(
Expression {
expr: Expr::CellPath(CellPath { members: cell_path }),
span,
ty: Type::CellPath,
custom_completion: None,
},
error,
)
}
2021-10-12 06:49:17 +02:00
SyntaxShape::Boolean => {
// Redundant, though we catch bad boolean parses here
if bytes == b"true" || bytes == b"false" {
2021-10-12 06:49:17 +02:00
(
Expression {
expr: Expr::Bool(true),
span,
ty: Type::Bool,
custom_completion: None,
},
None,
)
} else {
(
garbage(span),
Some(ParseError::Expected("bool".into(), span)),
)
}
}
2021-09-02 10:25:22 +02:00
SyntaxShape::Any => {
if bytes.starts_with(b"[") {
//parse_value(working_set, span, &SyntaxShape::Table)
parse_full_cell_path(working_set, None, span, expand_aliases_denylist)
} else {
let shapes = [
2022-03-01 00:31:53 +01:00
SyntaxShape::Binary,
SyntaxShape::Int,
SyntaxShape::Number,
SyntaxShape::Range,
SyntaxShape::DateTime,
SyntaxShape::Filesize,
SyntaxShape::Duration,
SyntaxShape::Record,
SyntaxShape::Block(None),
SyntaxShape::String,
];
for shape in shapes.iter() {
if let (s, None) =
parse_value(working_set, span, shape, expand_aliases_denylist)
{
return (s, None);
}
}
(
garbage(span),
Some(ParseError::Expected("any shape".into(), span)),
)
2021-07-02 08:44:37 +02:00
}
2021-09-02 10:25:22 +02:00
}
_ => (garbage(span), Some(ParseError::IncompleteParser(span))),
2021-07-02 08:44:37 +02:00
}
2021-09-02 10:25:22 +02:00
}
2021-07-02 08:44:37 +02:00
2021-09-02 10:25:22 +02:00
pub fn parse_operator(
working_set: &mut StateWorkingSet,
span: Span,
) -> (Expression, Option<ParseError>) {
let contents = working_set.get_span_contents(span);
let operator = match contents {
b"==" => Operator::Equal,
b"!=" => Operator::NotEqual,
b"<" => Operator::LessThan,
b"<=" => Operator::LessThanOrEqual,
b">" => Operator::GreaterThan,
b">=" => Operator::GreaterThanOrEqual,
b"=~" => Operator::Contains,
b"=^" => Operator::StartsWith,
2021-09-02 10:25:22 +02:00
b"!~" => Operator::NotContains,
b"+" => Operator::Plus,
b"-" => Operator::Minus,
b"*" => Operator::Multiply,
b"/" => Operator::Divide,
b"in" => Operator::In,
b"not-in" => Operator::NotIn,
b"mod" => Operator::Modulo,
b"&&" => Operator::And,
b"||" => Operator::Or,
b"**" => Operator::Pow,
_ => {
return (
garbage(span),
Some(ParseError::Expected("operator".into(), span)),
);
}
};
2021-07-02 08:44:37 +02:00
2021-09-02 10:25:22 +02:00
(
Expression {
expr: Expr::Operator(operator),
span,
ty: Type::Any,
custom_completion: None,
2021-09-02 10:25:22 +02:00
},
None,
)
}
2021-07-02 08:44:37 +02:00
2021-09-02 10:25:22 +02:00
pub fn parse_math_expression(
working_set: &mut StateWorkingSet,
spans: &[Span],
2021-09-09 23:47:20 +02:00
lhs_row_var_id: Option<VarId>,
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
// As the expr_stack grows, we increase the required precedence to grow larger
// If, at any time, the operator we're looking at is the same or lower precedence
// of what is in the expression stack, we collapse the expression stack.
//
// This leads to an expression stack that grows under increasing precedence and collapses
// under decreasing/sustained precedence
//
// The end result is a stack that we can fold into binary operations as right associations
// safely.
let mut expr_stack: Vec<Expression> = vec![];
let mut idx = 0;
let mut last_prec = 1000000;
let mut error = None;
2022-04-06 21:10:25 +02:00
let first_span = working_set.get_span_contents(spans[0]);
if first_span == b"not" {
if spans.len() > 1 {
let (remainder, err) = parse_math_expression(
working_set,
&spans[1..],
lhs_row_var_id,
expand_aliases_denylist,
);
return (
Expression {
expr: Expr::UnaryNot(Box::new(remainder)),
span: span(spans),
ty: Type::Bool,
custom_completion: None,
},
err,
);
} else {
return (
garbage(spans[0]),
Some(ParseError::Expected(
"expression".into(),
Span {
start: spans[0].end,
end: spans[0].end,
},
)),
);
}
}
let (mut lhs, err) = parse_value(
working_set,
spans[0],
&SyntaxShape::Any,
expand_aliases_denylist,
);
2021-09-02 10:25:22 +02:00
error = error.or(err);
idx += 1;
if idx >= spans.len() {
// We already found the one part of our expression, so let's expand
if let Some(row_var_id) = lhs_row_var_id {
expand_to_cell_path(working_set, &mut lhs, row_var_id, expand_aliases_denylist);
}
}
2021-09-02 10:25:22 +02:00
expr_stack.push(lhs);
while idx < spans.len() {
let (op, err) = parse_operator(working_set, spans[idx]);
2021-07-02 08:44:37 +02:00
error = error.or(err);
2021-09-02 10:25:22 +02:00
let op_prec = op.precedence();
2021-07-02 08:44:37 +02:00
2021-09-02 10:25:22 +02:00
idx += 1;
2021-07-02 08:44:37 +02:00
2021-09-02 10:25:22 +02:00
if idx == spans.len() {
// Handle broken math expr `1 +` etc
error = error.or(Some(ParseError::IncompleteMathExpression(spans[idx - 1])));
2021-07-02 08:44:37 +02:00
2021-09-02 10:25:22 +02:00
expr_stack.push(Expression::garbage(spans[idx - 1]));
expr_stack.push(Expression::garbage(spans[idx - 1]));
2021-07-22 21:50:59 +02:00
2021-09-02 10:25:22 +02:00
break;
}
2021-07-22 21:50:59 +02:00
let (rhs, err) = parse_value(
working_set,
spans[idx],
&SyntaxShape::Any,
expand_aliases_denylist,
);
2021-09-02 10:25:22 +02:00
error = error.or(err);
2021-07-02 08:44:37 +02:00
2022-03-25 04:23:08 +01:00
while op_prec <= last_prec && expr_stack.len() > 1 {
2021-11-06 08:31:28 +01:00
// Collapse the right associated operations first
// so that we can get back to a stack with a lower precedence
let mut rhs = expr_stack
.pop()
.expect("internal error: expression stack empty");
let mut op = expr_stack
.pop()
.expect("internal error: expression stack empty");
2022-03-25 04:23:08 +01:00
last_prec = op.precedence();
if last_prec < op_prec {
expr_stack.push(op);
expr_stack.push(rhs);
break;
}
2021-11-06 08:31:28 +01:00
let mut lhs = expr_stack
.pop()
.expect("internal error: expression stack empty");
if let Some(row_var_id) = lhs_row_var_id {
expand_to_cell_path(working_set, &mut lhs, row_var_id, expand_aliases_denylist);
2021-11-06 08:31:28 +01:00
}
2021-09-09 23:47:20 +02:00
2021-11-06 08:31:28 +01:00
let (result_ty, err) = math_result_type(working_set, &mut lhs, &mut op, &mut rhs);
error = error.or(err);
2021-07-02 08:44:37 +02:00
2021-11-06 08:31:28 +01:00
let op_span = span(&[lhs.span, rhs.span]);
expr_stack.push(Expression {
expr: Expr::BinaryOp(Box::new(lhs), Box::new(op), Box::new(rhs)),
span: op_span,
ty: result_ty,
custom_completion: None,
});
2021-07-02 08:44:37 +02:00
}
2021-09-02 10:25:22 +02:00
expr_stack.push(op);
expr_stack.push(rhs);
2021-07-02 08:44:37 +02:00
2021-09-02 10:25:22 +02:00
last_prec = op_prec;
2021-07-23 23:19:30 +02:00
2021-09-02 10:25:22 +02:00
idx += 1;
}
2021-07-02 08:44:37 +02:00
2021-09-02 10:25:22 +02:00
while expr_stack.len() != 1 {
let mut rhs = expr_stack
.pop()
.expect("internal error: expression stack empty");
let mut op = expr_stack
2021-07-02 08:44:37 +02:00
.pop()
.expect("internal error: expression stack empty");
2021-09-02 10:25:22 +02:00
let mut lhs = expr_stack
.pop()
.expect("internal error: expression stack empty");
2021-09-09 23:47:20 +02:00
if let Some(row_var_id) = lhs_row_var_id {
expand_to_cell_path(working_set, &mut lhs, row_var_id, expand_aliases_denylist);
2021-09-09 23:47:20 +02:00
}
2021-09-02 10:25:22 +02:00
let (result_ty, err) = math_result_type(working_set, &mut lhs, &mut op, &mut rhs);
error = error.or(err);
2021-07-02 08:44:37 +02:00
2021-09-02 10:25:22 +02:00
let binary_op_span = span(&[lhs.span, rhs.span]);
expr_stack.push(Expression {
expr: Expr::BinaryOp(Box::new(lhs), Box::new(op), Box::new(rhs)),
span: binary_op_span,
ty: result_ty,
custom_completion: None,
2021-09-02 10:25:22 +02:00
});
2021-07-01 02:01:04 +02:00
}
2021-09-02 10:25:22 +02:00
let output = expr_stack
.pop()
.expect("internal error: expression stack empty");
2021-07-02 00:40:08 +02:00
2021-09-02 10:25:22 +02:00
(output, error)
}
pub fn parse_expression(
working_set: &mut StateWorkingSet,
spans: &[Span],
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Expression, Option<ParseError>) {
2021-11-04 03:32:35 +01:00
let mut pos = 0;
let mut shorthand = vec![];
2021-09-02 10:25:22 +02:00
2021-11-04 03:32:35 +01:00
while pos < spans.len() {
// Check if there is any environment shorthand
let name = working_set.get_span_contents(spans[pos]);
let split = name.splitn(2, |x| *x == b'=');
2021-11-04 03:32:35 +01:00
let split: Vec<_> = split.collect();
if split.len() == 2 && !split[0].is_empty() {
let point = split[0].len() + 1;
let lhs = parse_string_strict(
working_set,
Span {
start: spans[pos].start,
end: spans[pos].start + point - 1,
},
);
let rhs = if spans[pos].start + point < spans[pos].end {
parse_string_strict(
working_set,
Span {
start: spans[pos].start + point,
end: spans[pos].end,
},
)
} else {
(
Expression {
expr: Expr::String(String::new()),
span: Span { start: 0, end: 0 },
2021-11-04 03:32:35 +01:00
ty: Type::Nothing,
custom_completion: None,
},
None,
)
};
if lhs.1.is_none() && rhs.1.is_none() {
shorthand.push((lhs.0, rhs.0));
pos += 1;
} else {
break;
}
} else {
break;
}
}
if pos == spans.len() {
return (
garbage(span(spans)),
Some(ParseError::UnknownCommand(spans[0])),
);
}
let (output, err) = if is_math_expression_like(working_set, spans[pos], expand_aliases_denylist)
{
parse_math_expression(working_set, &spans[pos..], None, expand_aliases_denylist)
2021-11-04 03:32:35 +01:00
} else {
let bytes = working_set.get_span_contents(spans[pos]);
// For now, check for special parses of certain keywords
match bytes {
b"def" => (
parse_call(
working_set,
&spans[pos..],
spans[0],
expand_aliases_denylist,
)
.0,
Some(ParseError::BuiltinCommandInPipeline("def".into(), spans[0])),
),
b"extern" => (
parse_call(
working_set,
&spans[pos..],
spans[0],
expand_aliases_denylist,
)
.0,
Some(ParseError::BuiltinCommandInPipeline(
"extern".into(),
spans[0],
)),
),
b"let" => (
parse_call(
working_set,
&spans[pos..],
spans[0],
expand_aliases_denylist,
)
.0,
Some(ParseError::BuiltinCommandInPipeline("let".into(), spans[0])),
),
b"alias" => (
parse_call(
working_set,
&spans[pos..],
spans[0],
expand_aliases_denylist,
)
.0,
Some(ParseError::BuiltinCommandInPipeline(
"alias".into(),
spans[0],
)),
),
b"module" => (
parse_call(
working_set,
&spans[pos..],
spans[0],
expand_aliases_denylist,
)
.0,
Some(ParseError::BuiltinCommandInPipeline(
"module".into(),
spans[0],
)),
),
b"use" => (
parse_call(
working_set,
&spans[pos..],
spans[0],
expand_aliases_denylist,
)
.0,
Some(ParseError::BuiltinCommandInPipeline("use".into(), spans[0])),
),
b"source" => (
parse_call(
working_set,
&spans[pos..],
spans[0],
expand_aliases_denylist,
)
.0,
Some(ParseError::BuiltinCommandInPipeline(
"source".into(),
spans[0],
)),
),
b"export" => (
parse_call(
working_set,
&spans[pos..],
spans[0],
expand_aliases_denylist,
)
.0,
Some(ParseError::UnexpectedKeyword("export".into(), spans[0])),
),
b"hide" => (
parse_call(
working_set,
&spans[pos..],
spans[0],
expand_aliases_denylist,
)
.0,
Some(ParseError::BuiltinCommandInPipeline(
"hide".into(),
spans[0],
)),
),
#[cfg(feature = "plugin")]
b"register" => (
parse_call(
working_set,
&spans[pos..],
spans[0],
expand_aliases_denylist,
)
.0,
Some(ParseError::BuiltinCommandInPipeline(
"plugin".into(),
spans[0],
)),
),
b"for" => parse_for(working_set, spans, expand_aliases_denylist),
_ => parse_call(
working_set,
&spans[pos..],
spans[0],
expand_aliases_denylist,
),
}
2021-11-04 03:32:35 +01:00
};
let with_env = working_set.find_decl(b"with-env");
if !shorthand.is_empty() {
if let Some(decl_id) = with_env {
let mut block = Block::default();
let ty = output.ty.clone();
block.pipelines = vec![Pipeline {
2021-11-04 03:32:35 +01:00
expressions: vec![output],
}];
2021-11-04 03:32:35 +01:00
let block_id = working_set.add_block(block);
let mut env_vars = vec![];
for sh in shorthand {
env_vars.push(sh.0);
env_vars.push(sh.1);
}
let positional = vec![
Expression {
expr: Expr::List(env_vars),
span: span(&spans[..pos]),
ty: Type::Any,
2021-11-04 03:32:35 +01:00
custom_completion: None,
},
Expression {
expr: Expr::Block(block_id),
span: span(&spans[pos..]),
ty,
custom_completion: None,
},
];
2022-02-21 18:58:04 +01:00
let expr = Expr::Call(Box::new(Call {
head: Span { start: 0, end: 0 },
decl_id,
named: vec![],
positional,
redirect_stdout: true,
redirect_stderr: false,
2022-02-21 18:58:04 +01:00
}));
2021-11-04 03:32:35 +01:00
(
Expression {
2022-02-21 18:58:04 +01:00
expr,
2021-11-04 03:32:35 +01:00
custom_completion: None,
span: span(spans),
ty: Type::Any,
2021-11-04 03:32:35 +01:00
},
err,
)
} else {
(output, err)
}
} else {
2021-11-04 03:32:35 +01:00
(output, err)
2021-07-01 02:01:04 +02:00
}
2021-09-02 10:25:22 +02:00
}
2021-07-01 02:01:04 +02:00
2021-09-02 10:25:22 +02:00
pub fn parse_variable(
working_set: &mut StateWorkingSet,
span: Span,
) -> (Option<VarId>, Option<ParseError>) {
let bytes = working_set.get_span_contents(span);
2021-07-01 02:01:04 +02:00
2021-09-02 10:25:22 +02:00
if is_variable(bytes) {
if let Some(var_id) = working_set.find_variable(bytes) {
(Some(var_id), None)
2021-07-01 02:01:04 +02:00
} else {
2021-09-02 10:25:22 +02:00
(None, None)
2021-07-01 02:01:04 +02:00
}
2021-09-02 10:25:22 +02:00
} else {
(None, Some(ParseError::Expected("variable".into(), span)))
2021-07-01 02:01:04 +02:00
}
2021-09-02 10:25:22 +02:00
}
2021-07-01 02:01:04 +02:00
pub fn parse_builtin_commands(
working_set: &mut StateWorkingSet,
lite_command: &LiteCommand,
expand_aliases_denylist: &[usize],
) -> (Pipeline, Option<ParseError>) {
let name = working_set.get_span_contents(lite_command.parts[0]);
2021-09-13 21:59:11 +02:00
match name {
b"def" | b"def-env" => parse_def(working_set, lite_command, expand_aliases_denylist),
b"extern" => parse_extern(working_set, lite_command, expand_aliases_denylist),
b"let" => parse_let(working_set, &lite_command.parts, expand_aliases_denylist),
b"for" => {
let (expr, err) = parse_for(working_set, &lite_command.parts, expand_aliases_denylist);
(Pipeline::from_vec(vec![expr]), err)
}
b"alias" => parse_alias(working_set, &lite_command.parts, expand_aliases_denylist),
b"module" => parse_module(working_set, &lite_command.parts, expand_aliases_denylist),
b"use" => parse_use(working_set, &lite_command.parts, expand_aliases_denylist),
b"source" => parse_source(working_set, &lite_command.parts, expand_aliases_denylist),
b"export" => (
garbage_pipeline(&lite_command.parts),
Some(ParseError::UnexpectedKeyword(
"export".into(),
lite_command.parts[0],
)),
),
b"hide" => parse_hide(working_set, &lite_command.parts, expand_aliases_denylist),
2021-11-02 21:56:00 +01:00
#[cfg(feature = "plugin")]
b"register" => parse_register(working_set, &lite_command.parts, expand_aliases_denylist),
2021-09-13 21:59:11 +02:00
_ => {
let (expr, err) =
parse_expression(working_set, &lite_command.parts, expand_aliases_denylist);
(Pipeline::from_vec(vec![expr]), err)
}
}
2021-09-02 10:25:22 +02:00
}
2021-06-30 03:42:56 +02:00
2021-11-11 00:14:00 +01:00
pub fn parse_record(
working_set: &mut StateWorkingSet,
span: Span,
expand_aliases_denylist: &[usize],
2021-11-11 00:14:00 +01:00
) -> (Expression, Option<ParseError>) {
let bytes = working_set.get_span_contents(span);
let mut error = None;
let mut start = span.start;
let mut end = span.end;
if bytes.starts_with(b"{") {
start += 1;
} else {
error = error.or_else(|| {
Some(ParseError::Expected(
"{".into(),
Span {
start,
end: start + 1,
},
))
});
}
if bytes.ends_with(b"}") {
end -= 1;
} else {
error = error.or_else(|| Some(ParseError::Unclosed("}".into(), Span { start: end, end })));
}
2022-01-03 06:21:26 +01:00
let inner_span = Span { start, end };
let source = working_set.get_span_contents(inner_span);
2021-11-11 00:14:00 +01:00
2021-11-21 19:13:09 +01:00
let (tokens, err) = lex(source, start, &[b'\n', b'\r', b','], &[b':'], true);
2021-11-11 00:14:00 +01:00
error = error.or(err);
let mut output = vec![];
let mut idx = 0;
while idx < tokens.len() {
let (field, err) = parse_value(
working_set,
tokens[idx].span,
&SyntaxShape::Any,
expand_aliases_denylist,
);
2021-11-11 00:14:00 +01:00
error = error.or(err);
idx += 1;
if idx == tokens.len() {
return (
garbage(span),
Some(ParseError::Expected("record".into(), span)),
);
}
let colon = working_set.get_span_contents(tokens[idx].span);
idx += 1;
if idx == tokens.len() || colon != b":" {
//FIXME: need better error
return (
garbage(span),
Some(ParseError::Expected("record".into(), span)),
);
}
let (value, err) = parse_value(
working_set,
tokens[idx].span,
&SyntaxShape::Any,
expand_aliases_denylist,
);
2021-11-11 00:14:00 +01:00
error = error.or(err);
idx += 1;
output.push((field, value));
}
(
Expression {
expr: Expr::Record(output),
span,
ty: Type::Any, //FIXME: but we don't know the contents of the fields, do we?
2021-11-11 00:14:00 +01:00
custom_completion: None,
},
error,
)
}
2021-09-02 10:25:22 +02:00
pub fn parse_block(
working_set: &mut StateWorkingSet,
lite_block: &LiteBlock,
scoped: bool,
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Block, Option<ParseError>) {
2022-01-01 22:42:50 +01:00
trace!("parsing block: {:?}", lite_block);
2021-09-02 10:25:22 +02:00
if scoped {
working_set.enter_scope();
}
2021-06-30 03:42:56 +02:00
let mut error = None;
2021-09-02 10:25:22 +02:00
// Pre-declare any definition so that definitions
// that share the same block can see each other
for pipeline in &lite_block.block {
if pipeline.commands.len() == 1 {
if let Some(err) = parse_def_predecl(
working_set,
&pipeline.commands[0].parts,
expand_aliases_denylist,
) {
error = error.or(Some(err));
}
2021-09-02 10:25:22 +02:00
}
}
2021-07-01 02:01:04 +02:00
2021-09-10 09:28:43 +02:00
let block: Block = lite_block
.block
.iter()
.enumerate()
.map(|(idx, pipeline)| {
2021-09-10 09:28:43 +02:00
if pipeline.commands.len() > 1 {
let mut output = pipeline
2021-09-10 09:28:43 +02:00
.commands
.iter()
.map(|command| {
let (expr, err) =
parse_expression(working_set, &command.parts, expand_aliases_denylist);
2021-09-10 09:44:31 +02:00
if error.is_none() {
error = err;
}
2021-06-30 03:42:56 +02:00
2021-09-10 09:28:43 +02:00
expr
})
.collect::<Vec<Expression>>();
for expr in output.iter_mut().skip(1) {
if expr.has_in_variable(working_set) {
*expr = wrap_expr_with_collect(working_set, expr);
}
}
2021-11-08 08:13:55 +01:00
Pipeline {
2021-09-10 09:28:43 +02:00
expressions: output,
}
2021-09-10 09:28:43 +02:00
} else {
let (mut pipeline, err) = parse_builtin_commands(
working_set,
&pipeline.commands[0],
expand_aliases_denylist,
);
if idx == 0 {
if let Some(let_decl_id) = working_set.find_decl(b"let") {
if let Some(let_env_decl_id) = working_set.find_decl(b"let-env") {
for expr in pipeline.expressions.iter_mut() {
if let Expression {
expr: Expr::Call(call),
..
} = expr
{
if call.decl_id == let_decl_id
|| call.decl_id == let_env_decl_id
{
// Do an expansion
if let Some(Expression {
expr: Expr::Keyword(_, _, expr),
..
}) = call.positional.get_mut(1)
{
if expr.has_in_variable(working_set) {
*expr = Box::new(wrap_expr_with_collect(
working_set,
expr,
));
}
}
continue;
}
}
}
}
}
}
2021-09-10 09:44:31 +02:00
if error.is_none() {
error = err;
}
2021-06-30 03:42:56 +02:00
pipeline
2021-09-10 09:28:43 +02:00
}
})
.into();
2021-06-30 03:42:56 +02:00
2021-09-02 10:25:22 +02:00
if scoped {
working_set.exit_scope();
2021-06-30 03:42:56 +02:00
}
2021-09-02 10:25:22 +02:00
(block, error)
}
2021-06-30 03:42:56 +02:00
pub fn discover_captures_in_block(
2021-10-25 22:04:23 +02:00
working_set: &StateWorkingSet,
block: &Block,
seen: &mut Vec<VarId>,
seen_blocks: &mut HashMap<BlockId, Vec<VarId>>,
2021-10-25 22:04:23 +02:00
) -> Vec<VarId> {
let mut output = vec![];
for flag in &block.signature.named {
if let Some(var_id) = flag.var_id {
seen.push(var_id);
}
}
for positional in &block.signature.required_positional {
if let Some(var_id) = positional.var_id {
seen.push(var_id);
}
}
for positional in &block.signature.optional_positional {
if let Some(var_id) = positional.var_id {
seen.push(var_id);
}
}
for positional in &block.signature.rest_positional {
if let Some(var_id) = positional.var_id {
seen.push(var_id);
}
}
for pipeline in &block.pipelines {
let result = discover_captures_in_pipeline(working_set, pipeline, seen, seen_blocks);
output.extend(&result);
2021-10-25 22:04:23 +02:00
}
output
}
fn discover_captures_in_pipeline(
2021-10-25 22:04:23 +02:00
working_set: &StateWorkingSet,
pipeline: &Pipeline,
seen: &mut Vec<VarId>,
seen_blocks: &mut HashMap<BlockId, Vec<VarId>>,
2021-10-25 22:04:23 +02:00
) -> Vec<VarId> {
let mut output = vec![];
for expr in &pipeline.expressions {
let result = discover_captures_in_expr(working_set, expr, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&result);
}
output
}
pub fn discover_captures_in_expr(
2021-10-25 22:04:23 +02:00
working_set: &StateWorkingSet,
expr: &Expression,
seen: &mut Vec<VarId>,
seen_blocks: &mut HashMap<BlockId, Vec<VarId>>,
2021-10-25 22:04:23 +02:00
) -> Vec<VarId> {
let mut output = vec![];
match &expr.expr {
Expr::BinaryOp(lhs, _, rhs) => {
let lhs_result = discover_captures_in_expr(working_set, lhs, seen, seen_blocks);
let rhs_result = discover_captures_in_expr(working_set, rhs, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&lhs_result);
output.extend(&rhs_result);
}
2022-04-06 21:10:25 +02:00
Expr::UnaryNot(expr) => {
let result = discover_captures_in_expr(working_set, expr, seen, seen_blocks);
output.extend(&result);
}
2021-10-25 22:04:23 +02:00
Expr::Block(block_id) => {
let block = working_set.get_block(*block_id);
let results = {
let mut seen = vec![];
discover_captures_in_block(working_set, block, &mut seen, seen_blocks)
};
seen_blocks.insert(*block_id, results.clone());
for var_id in results.into_iter() {
if !seen.contains(&var_id) {
output.push(var_id)
}
}
2021-10-25 22:04:23 +02:00
}
2022-03-01 00:31:53 +01:00
Expr::Binary(_) => {}
2021-10-25 22:04:23 +02:00
Expr::Bool(_) => {}
Expr::Call(call) => {
let decl = working_set.get_decl(call.decl_id);
if let Some(block_id) = decl.get_block_id() {
match seen_blocks.get(&block_id) {
Some(capture_list) => {
output.extend(capture_list);
}
None => {
let block = working_set.get_block(block_id);
if !block.captures.is_empty() {
output.extend(&block.captures);
} else {
let mut seen = vec![];
seen_blocks.insert(block_id, output.clone());
let result = discover_captures_in_block(
working_set,
block,
&mut seen,
seen_blocks,
);
output.extend(&result);
seen_blocks.insert(block_id, result);
}
}
}
}
2021-10-25 22:04:23 +02:00
for named in &call.named {
if let Some(arg) = &named.1 {
let result = discover_captures_in_expr(working_set, arg, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&result);
}
}
for positional in &call.positional {
let result = discover_captures_in_expr(working_set, positional, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&result);
}
}
Expr::CellPath(_) => {}
Expr::DateTime(_) => {}
Expr::ExternalCall(head, exprs) => {
let result = discover_captures_in_expr(working_set, head, seen, seen_blocks);
output.extend(&result);
2021-10-25 22:04:23 +02:00
for expr in exprs {
let result = discover_captures_in_expr(working_set, expr, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&result);
}
}
Expr::Filepath(_) => {}
Expr::Float(_) => {}
Expr::FullCellPath(cell_path) => {
let result = discover_captures_in_expr(working_set, &cell_path.head, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&result);
}
Expr::ImportPattern(_) => {}
2021-10-25 22:04:23 +02:00
Expr::Garbage => {}
Expr::Nothing => {}
2021-10-25 22:04:23 +02:00
Expr::GlobPattern(_) => {}
Expr::Int(_) => {}
Expr::Keyword(_, _, expr) => {
let result = discover_captures_in_expr(working_set, expr, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&result);
}
Expr::List(exprs) => {
for expr in exprs {
let result = discover_captures_in_expr(working_set, expr, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&result);
}
}
Expr::Operator(_) => {}
Expr::Range(expr1, expr2, expr3, _) => {
if let Some(expr) = expr1 {
let result = discover_captures_in_expr(working_set, expr, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&result);
}
if let Some(expr) = expr2 {
let result = discover_captures_in_expr(working_set, expr, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&result);
}
if let Some(expr) = expr3 {
let result = discover_captures_in_expr(working_set, expr, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&result);
}
}
2021-11-11 00:14:00 +01:00
Expr::Record(fields) => {
for (field_name, field_value) in fields {
output.extend(&discover_captures_in_expr(
working_set,
field_name,
seen,
seen_blocks,
));
output.extend(&discover_captures_in_expr(
working_set,
field_value,
seen,
seen_blocks,
));
2021-11-11 00:14:00 +01:00
}
}
Expr::Signature(sig) => {
// Something with a declaration, similar to a var decl, will introduce more VarIds into the stack at eval
for pos in &sig.required_positional {
if let Some(var_id) = pos.var_id {
seen.push(var_id);
}
}
for pos in &sig.optional_positional {
if let Some(var_id) = pos.var_id {
seen.push(var_id);
}
}
if let Some(rest) = &sig.rest_positional {
if let Some(var_id) = rest.var_id {
seen.push(var_id);
}
}
for named in &sig.named {
if let Some(var_id) = named.var_id {
seen.push(var_id);
}
}
}
2021-10-25 22:04:23 +02:00
Expr::String(_) => {}
Expr::StringInterpolation(exprs) => {
for expr in exprs {
let result = discover_captures_in_expr(working_set, expr, seen, seen_blocks);
output.extend(&result);
}
}
2021-11-26 04:49:03 +01:00
Expr::RowCondition(block_id) | Expr::Subexpression(block_id) => {
2021-10-25 22:04:23 +02:00
let block = working_set.get_block(*block_id);
let results = {
let mut seen = vec![];
discover_captures_in_block(working_set, block, &mut seen, seen_blocks)
};
seen_blocks.insert(*block_id, results.clone());
for var_id in results.into_iter() {
if !seen.contains(&var_id) {
output.push(var_id)
}
}
2021-10-25 22:04:23 +02:00
}
Expr::Table(headers, values) => {
for header in headers {
let result = discover_captures_in_expr(working_set, header, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&result);
}
for row in values {
for cell in row {
let result = discover_captures_in_expr(working_set, cell, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&result);
}
}
}
Expr::ValueWithUnit(expr, _) => {
let result = discover_captures_in_expr(working_set, expr, seen, seen_blocks);
2021-10-25 22:04:23 +02:00
output.extend(&result);
}
Expr::Var(var_id) => {
if (*var_id > ENV_VARIABLE_ID || *var_id == IN_VARIABLE_ID) && !seen.contains(var_id) {
2021-10-25 22:04:23 +02:00
output.push(*var_id);
}
}
Expr::VarDecl(var_id) => {
seen.push(*var_id);
}
}
output
}
fn wrap_expr_with_collect(working_set: &mut StateWorkingSet, expr: &Expression) -> Expression {
let span = expr.span;
if let Some(decl_id) = working_set.find_decl(b"collect") {
let mut output = vec![];
let var_id = working_set.next_var_id();
let mut signature = Signature::new("");
signature.required_positional.push(PositionalArg {
var_id: Some(var_id),
2021-12-30 04:26:40 +01:00
name: "$in".into(),
desc: String::new(),
shape: SyntaxShape::Any,
2022-03-07 21:08:56 +01:00
default_value: None,
});
let mut expr = expr.clone();
expr.replace_in_variable(working_set, var_id);
let block = Block {
pipelines: vec![Pipeline {
expressions: vec![expr],
}],
signature: Box::new(signature),
..Default::default()
};
let block_id = working_set.add_block(block);
output.push(Expression {
expr: Expr::Block(block_id),
span,
ty: Type::Any,
custom_completion: None,
});
2021-12-30 04:26:40 +01:00
// The containing, synthetic call to `collect`.
// We don't want to have a real span as it will confuse flattening
// The args are where we'll get the real info
Expression {
expr: Expr::Call(Box::new(Call {
2021-12-30 04:26:40 +01:00
head: Span::new(0, 0),
named: vec![],
positional: output,
decl_id,
redirect_stdout: true,
redirect_stderr: false,
})),
span,
ty: Type::String,
custom_completion: None,
}
} else {
Expression::garbage(span)
}
}
2021-09-06 22:41:30 +02:00
// Parses a vector of u8 to create an AST Block. If a file name is given, then
// the name is stored in the working set. When parsing a source without a file
// name, the source of bytes is stored as "source"
pub fn parse(
2021-09-02 10:25:22 +02:00
working_set: &mut StateWorkingSet,
2021-09-06 22:41:30 +02:00
fname: Option<&str>,
2021-09-02 10:25:22 +02:00
contents: &[u8],
scoped: bool,
expand_aliases_denylist: &[usize],
2021-09-02 10:25:22 +02:00
) -> (Block, Option<ParseError>) {
2022-01-01 22:42:50 +01:00
trace!("starting top-level parse");
2021-09-02 10:25:22 +02:00
let mut error = None;
2021-07-03 03:29:56 +02:00
2021-09-02 10:25:22 +02:00
let span_offset = working_set.next_span_start();
2021-09-06 22:41:30 +02:00
let name = match fname {
Some(fname) => fname.to_string(),
None => "source".to_string(),
};
2021-07-01 02:01:04 +02:00
2021-09-06 22:41:30 +02:00
working_set.add_file(name, contents);
2021-07-01 02:01:04 +02:00
let (output, err) = lex(contents, span_offset, &[], &[], false);
2021-09-02 10:25:22 +02:00
error = error.or(err);
2021-07-01 02:01:04 +02:00
2021-09-02 10:25:22 +02:00
let (output, err) = lite_parse(&output);
error = error.or(err);
2021-07-01 02:01:04 +02:00
let (mut output, err) = parse_block(working_set, &output, scoped, expand_aliases_denylist);
2021-09-02 10:25:22 +02:00
error = error.or(err);
let mut seen = vec![];
let mut seen_blocks = HashMap::new();
let captures = discover_captures_in_block(working_set, &output, &mut seen, &mut seen_blocks);
output.captures = captures;
// Also check other blocks that might have been imported
for (block_idx, block) in working_set.delta.blocks.iter().enumerate() {
let block_id = block_idx + working_set.permanent_state.num_blocks();
if !seen_blocks.contains_key(&block_id) {
let captures =
discover_captures_in_block(working_set, block, &mut seen, &mut seen_blocks);
seen_blocks.insert(block_id, captures);
}
}
for (block_id, captures) in seen_blocks.into_iter() {
// In theory, we should only be updating captures where we have new information
// the only place where this is possible would be blocks that are newly created
// by our working set delta. If we ever tried to modify the permanent state, we'd
// panic (again, in theory, this shouldn't be possible)
let block = working_set.get_block(block_id);
let block_captures_empty = block.captures.is_empty();
if !captures.is_empty() && block_captures_empty {
let block = working_set.get_block_mut(block_id);
block.captures = captures;
}
}
2021-09-02 10:25:22 +02:00
(output, error)
2021-06-30 03:42:56 +02:00
}