Skip to content

Rewrite the lexer and parser in human_encoding #354

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ivanlele wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Rewrite the lexer and parser in human_encoding #354

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
69 changes: 68 additions & 1 deletion Cargo-recent.lock
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,12 @@ version = "0.11.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "32637268377fc7b10a8c6d51de3e7fba1ce5dd371a96e342b34e6078db558e7f"

[[package]]
name = "beef"
version = "0.5.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3a8241f3ebb85c056b509d4327ad0358fbbba6ffb340bf388f26350aeda225b1"

[[package]]
name = "bitcoin"
version = "0.32.8"
Expand Down Expand Up @@ -160,6 +166,12 @@ version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3a3076410a55c90011c298b04d0cfa770b00fa04e1e3c97d3f6c9de105a03844"

[[package]]
name = "fnv"
version = "1.0.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"

[[package]]
name = "getrandom"
version = "0.2.16"
Expand Down Expand Up @@ -238,6 +250,12 @@ dependencies = [
"wasm-bindgen",
]

[[package]]
name = "lazy_static"
version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"

[[package]]
name = "libc"
version = "0.2.178"
Expand All @@ -254,6 +272,40 @@ dependencies = [
"cc",
]

[[package]]
name = "logos"
version = "0.15.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ff472f899b4ec2d99161c51f60ff7075eeb3097069a36050d8037a6325eb8154"
dependencies = [
"logos-derive",
]

[[package]]
name = "logos-codegen"
version = "0.15.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "192a3a2b90b0c05b27a0b2c43eecdb7c415e29243acc3f89cc8247a5b693045c"
dependencies = [
"beef",
"fnv",
"lazy_static",
"proc-macro2",
"quote",
"regex-syntax",
"rustc_version",
"syn",
]

[[package]]
name = "logos-derive"
version = "0.15.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "605d9697bcd5ef3a42d38efc51541aa3d6a4a25f7ab6d1ed0da5ac632a26b470"
dependencies = [
"logos-codegen",
]

[[package]]
name = "memchr"
version = "2.7.6"
Expand Down Expand Up @@ -368,6 +420,15 @@ version = "0.8.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7a2d987857b319362043e95f5353c0535c1f58eec5336fdfcf626430af7def58"

[[package]]
name = "rustc_version"
version = "0.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cfcb3a22ef46e85b45de6ee7e79d063319ebb6594faafcf1c225ea92ab6e9b92"
dependencies = [
"semver",
]

[[package]]
name = "rustversion"
version = "1.0.22"
Expand Down Expand Up @@ -427,6 +488,12 @@ dependencies = [
"secp256k1-sys",
]

[[package]]
name = "semver"
version = "1.0.27"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d767eb0aabc880b29956c35734170f26ed551a859dbd361d140cdbeca61ab1e2"

[[package]]
name = "serde"
version = "1.0.228"
Expand Down Expand Up @@ -519,8 +586,8 @@ dependencies = [
"getrandom 0.2.16",
"ghost-cell",
"hex-conservative 0.2.2",
"logos",
"miniscript",
"santiago",
"serde",
"serde_json",
"simplicity-sys 0.6.2",
Expand Down
2 changes: 1 addition & 1 deletion Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ elements = { version = "0.25.0", optional = true, default-features = false }
ghost-cell = { version = "0.2.6", default-features = false }
hashes = { package = "bitcoin_hashes", version = "0.14" }
hex = { package = "hex-conservative", version = "0.2.1" }
santiago = "1.3"
logos = "0.15"
simplicity-sys = { version = "0.6.2", path = "./simplicity-sys" }
serde = { version = "1.0.103", features = ["derive"], optional = true }

Expand Down
4 changes: 1 addition & 3 deletions src/human_encoding/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,9 +15,7 @@ With that said, the rest of the document defines the encoding.

## Syntax

The syntax is defined in `src/human_encoding/parse/ast.rs`. It currently uses the
`santiago` parser generator, but we would like to move away from this, probably to
an ad-hoc parser, to avoid poor asymptotic behavior and to get better error messages.
The syntax is defined in `src/human_encoding/parse/ast.rs`.

Comments are started by `--` and end at the next newline. This is the only aspect
in which whitespace is significant.
Expand Down
27 changes: 5 additions & 22 deletions src/human_encoding/error.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,6 @@

//! Parsing Errors

use santiago::lexer::Lexeme;
use std::collections::BTreeMap;
use std::sync::{Arc, Mutex};
use std::{error, fmt, iter};
Expand All @@ -19,22 +18,6 @@ pub struct ErrorSet {
errors: BTreeMap<Option<Position>, Vec<Error>>,
}

impl<T> From<santiago::parser::ParseError<T>> for ErrorSet {
fn from(e: santiago::parser::ParseError<T>) -> Self {
let lex = e.at.map(|rc| (*rc).clone());
match lex.as_ref().map(|lex| &lex.position).map(Position::from) {
Some(pos) => ErrorSet::single(pos, Error::ParseFailed(lex)),
None => ErrorSet::single_no_position(Error::ParseFailed(lex)),
}
}
}

impl From<santiago::lexer::LexerError> for ErrorSet {
fn from(e: santiago::lexer::LexerError) -> Self {
ErrorSet::single(e.position, Error::LexFailed(e.message))
}
}

impl ErrorSet {
/// Constructs a new empty error set.
pub fn new() -> Self {
Expand Down Expand Up @@ -260,10 +243,10 @@ pub enum Error {
NameRepeated(Arc<str>),
/// Program did not have a `main` expression
NoMain,
/// Parsing failed (the parser provides us some extra information, but beyond
/// the line and column, it does not seem very useful to a user, so we drop it).
ParseFailed(Option<Lexeme>),
/// Lexing failed; here santiago provides us an error message which is useful
/// Parsing failed; the string (if any) is a description of the token at which
/// parsing failed.
ParseFailed(Option<String>),
/// Lexing failed
LexFailed(String),
/// A number was parsed in some context but was out of range.
NumberOutOfRange(String),
Expand Down Expand Up @@ -327,7 +310,7 @@ impl fmt::Display for Error {
write!(f, "number {} was out of allowable range", n)
}
Error::ParseFailed(None) => f.write_str("could not parse"),
Error::ParseFailed(Some(ref lex)) => write!(f, "could not parse `{}`", lex.raw),
Error::ParseFailed(Some(ref raw)) => write!(f, "could not parse `{}`", raw),
Error::LexFailed(ref msg) => write!(f, "could not parse: {}", msg),
Error::TypeCheck(ref e) => fmt::Display::fmt(e, f),
Error::Undefined(ref s) => write!(f, "reference to undefined symbol `{}`", s),
Expand Down
23 changes: 4 additions & 19 deletions src/human_encoding/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,31 +24,16 @@ pub use self::error::{Error, ErrorSet};
pub use self::named_node::NamedCommitNode;

/// Line/column pair
///
/// There is a similar type provided by the `santiago` library but it does not implement
/// `Copy`, among many other traits, which makes it unergonomic to use. Santiago positions
/// can be converted using `.into()`.
#[derive(Copy, Clone, Debug, PartialEq, Eq, PartialOrd, Ord, Default, Hash)]
pub struct Position {
line: usize,
column: usize,
}

impl<'a> From<&'a santiago::lexer::Position> for Position {
fn from(position: &'a santiago::lexer::Position) -> Position {
Position {
line: position.line,
column: position.column,
}
}
}

impl From<santiago::lexer::Position> for Position {
fn from(position: santiago::lexer::Position) -> Position {
Position {
line: position.line,
column: position.column,
}
impl Position {
/// Create a new position from line and column.
pub fn new(line: usize, column: usize) -> Self {
Position { line, column }
}
}

Expand Down
Loading
Loading