Add Position::offset, and recompute line/column info based on source

This commit is contained in:
Joshua Warner 2021-12-23 21:06:08 -08:00
parent 443d738f9b
commit 4b04ec6bbc
7 changed files with 279 additions and 300 deletions

View file

@ -8,8 +8,12 @@ use std::fmt;
#[derive(Clone)]
pub struct State<'a> {
/// The raw input bytes from the file.
/// Beware: bytes[0] always points the the current byte the parser is examining.
bytes: &'a [u8],
/// Length of the original input in bytes
input_len: usize,
/// Current position within the input (line/column)
pub xyzlcol: LineColumn,
@ -22,6 +26,7 @@ impl<'a> State<'a> {
pub fn new(bytes: &'a [u8]) -> State<'a> {
State {
bytes,
input_len: bytes.len(),
xyzlcol: LineColumn::default(),
indent_column: 0,
}
@ -40,7 +45,10 @@ impl<'a> State<'a> {
/// Returns the current position
pub const fn pos(&self) -> Position {
Position::new(self.xyzlcol.line, self.xyzlcol.column)
Position::new(
(self.input_len - self.bytes.len()) as u32,
self.xyzlcol.line,
self.xyzlcol.column)
}
/// Returns whether the parser has reached the end of the input
@ -95,6 +103,7 @@ impl<'a> State<'a> {
Region::new(
self.pos(),
Position::new(
self.pos().bump_column(length).offset,
self.xyzlcol.line,
self
.xyzlcol

View file

@ -366,7 +366,7 @@ mod test_parse {
assert_segments(r#""Hi, \u(123)!""#, |arena| {
bumpalo::vec![in arena;
Plaintext("Hi, "),
Unicode(Loc::new(Position::new(0, 8), Position::new(0, 11), "123")),
Unicode(Loc::new(Position::new(0, 0, 0), Position::new(0, 0, 0), "123")),
Plaintext("!")
]
});
@ -376,7 +376,7 @@ mod test_parse {
fn unicode_escape_in_front() {
assert_segments(r#""\u(1234) is a unicode char""#, |arena| {
bumpalo::vec![in arena;
Unicode(Loc::new(Position::new(0, 4), Position::new(0, 8), "1234")),
Unicode(Loc::new(Position::new(0, 0, 0), Position::new(0, 0, 0), "1234")),
Plaintext(" is a unicode char")
]
});
@ -387,7 +387,7 @@ mod test_parse {
assert_segments(r#""this is unicode: \u(1)""#, |arena| {
bumpalo::vec![in arena;
Plaintext("this is unicode: "),
Unicode(Loc::new(Position::new(0, 21), Position::new(0, 22), "1"))
Unicode(Loc::new(Position::new(0, 0, 0), Position::new(0, 0, 0), "1"))
]
});
}
@ -396,11 +396,11 @@ mod test_parse {
fn unicode_escape_multiple() {
assert_segments(r#""\u(a1) this is \u(2Bcd) unicode \u(ef97)""#, |arena| {
bumpalo::vec![in arena;
Unicode(Loc::new(Position::new(0, 4), Position::new(0, 6), "a1")),
Unicode(Loc::new(Position::new(0, 0, 0), Position::new(0, 0, 0), "a1")),
Plaintext(" this is "),
Unicode(Loc::new(Position::new(0, 19), Position::new(0, 23), "2Bcd")),
Unicode(Loc::new(Position::new(0, 0, 0), Position::new(0, 0, 0), "2Bcd")),
Plaintext(" unicode "),
Unicode(Loc::new(Position::new(0, 36), Position::new(0, 40), "ef97"))
Unicode(Loc::new(Position::new(0, 0, 0), Position::new(0, 0, 0), "ef97"))
]
});
}
@ -417,7 +417,7 @@ mod test_parse {
bumpalo::vec![in arena;
Plaintext("Hi, "),
Interpolated(Loc::new(Position::new(0, 7), Position::new(0, 11), expr)),
Interpolated(Loc::new(Position::new(0, 0, 0), Position::new(0, 0, 0), expr)),
Plaintext("!")
]
});
@ -432,7 +432,7 @@ mod test_parse {
});
bumpalo::vec![in arena;
Interpolated(Loc::new(Position::new(0, 3), Position::new(0, 7), expr)),
Interpolated(Loc::new(Position::new(0, 0, 0), Position::new(0, 0, 0), expr)),
Plaintext(", hi!")
]
});
@ -448,7 +448,7 @@ mod test_parse {
bumpalo::vec![in arena;
Plaintext("Hello "),
Interpolated(Loc::new(Position::new(0, 9), Position::new(0, 13), expr))
Interpolated(Loc::new(Position::new(0, 0, 0), Position::new(0, 0, 0), expr))
]
});
}
@ -468,9 +468,9 @@ mod test_parse {
bumpalo::vec![in arena;
Plaintext("Hi, "),
Interpolated(Loc::new(Position::new(0, 7), Position::new(0, 11), expr1)),
Interpolated(Loc::new(Position::new(0, 0, 0), Position::new(0, 0, 0), expr1)),
Plaintext("! How is "),
Interpolated(Loc::new(Position::new(0, 23), Position::new(0, 30), expr2)),
Interpolated(Loc::new(Position::new(0, 0, 0), Position::new(0, 0, 0), expr2)),
Plaintext(" going?")
]
});