Add a very simple lisp grammer based on LALRPOP (whitespace problem)

This commit is contained in:
Sameer Rahmani 2020-06-13 17:55:27 +01:00
parent f4e7387733
commit e527beea5a
9 changed files with 689 additions and 2 deletions

543
Cargo.lock generated
View File

@ -1,5 +1,548 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
[[package]]
name = "aho-corasick"
version = "0.7.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8716408b8bc624ed7f65d223ddb9ac2d044c0547b6fa4b0d554f3a9540496ada"
dependencies = [
"memchr",
]
[[package]]
name = "arrayref"
version = "0.3.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a4c527152e37cf757a3f78aae5a06fbeefdb07ccc535c980a3208ee3060dd544"
[[package]]
name = "arrayvec"
version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cff77d8686867eceff3105329d4698d96c2391c176d5d03adc90c7389162b5b8"
[[package]]
name = "ascii-canvas"
version = "2.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ff8eb72df928aafb99fe5d37b383f2fe25bd2a765e3e5f7c365916b6f2463a29"
dependencies = [
"term",
]
[[package]]
name = "atty"
version = "0.2.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d9b39be18770d11421cdb1b9947a45dd3f37e93092cbf377614828a319d5fee8"
dependencies = [
"hermit-abi",
"libc",
"winapi",
]
[[package]]
name = "autocfg"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f8aac770f1885fd7e387acedd76065302551364496e46b3dd00860b2f8359b9d"
[[package]]
name = "base64"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b41b7ea54a0c9d92199de89e20e58d49f02f8e699814ef3fdf266f6f748d15c7"
[[package]]
name = "bit-set"
version = "0.5.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6e11e16035ea35e4e5997b393eacbf6f63983188f7a2ad25bfb13465f5ad59de"
dependencies = [
"bit-vec",
]
[[package]]
name = "bit-vec"
version = "0.6.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5f0dc55f2d8a1a85650ac47858bb001b4c0dd73d79e3c455a842925e68d29cd3"
[[package]]
name = "blake2b_simd"
version = "0.5.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d8fb2d74254a3a0b5cac33ac9f8ed0e44aa50378d9dbb2e5d83bd21ed1dc2c8a"
dependencies = [
"arrayref",
"arrayvec",
"constant_time_eq",
]
[[package]]
name = "block-buffer"
version = "0.7.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c0940dc441f31689269e10ac70eb1002a3a1d3ad1390e030043662eb7fe4688b"
dependencies = [
"block-padding",
"byte-tools",
"byteorder",
"generic-array",
]
[[package]]
name = "block-padding"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fa79dedbb091f449f1f39e53edf88d5dbe95f895dae6135a8d7b881fb5af73f5"
dependencies = [
"byte-tools",
]
[[package]]
name = "byte-tools"
version = "0.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e3b5ca7a04898ad4bcd41c90c5285445ff5b791899bb1b0abdd2a2aa791211d7"
[[package]]
name = "byteorder"
version = "1.3.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "08c48aae112d48ed9f069b33538ea9e3e90aa263cfa3d1c24309612b1f7472de"
[[package]]
name = "cfg-if"
version = "0.1.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4785bdd1c96b2a846b2bd7cc02e86b6b3dbf14e7e53446c4f54c92a361040822"
[[package]]
name = "constant_time_eq"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "245097e9a4535ee1e3e3931fcfcd55a796a44c643e8596ff6566d68f09b87bbc"
[[package]]
name = "crossbeam-utils"
version = "0.7.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c3c7c73a2d1e9fc0886a08b93e98eb643461230d5f1925e4036204d5f2e261a8"
dependencies = [
"autocfg",
"cfg-if",
"lazy_static",
]
[[package]]
name = "diff"
version = "0.1.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0e25ea47919b1560c4e3b7fe0aaab9becf5b84a10325ddf7db0f0ba5e1026499"
[[package]]
name = "digest"
version = "0.8.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f3d0c8c8752312f9713efd397ff63acb9f85585afbf179282e720e7704954dd5"
dependencies = [
"generic-array",
]
[[package]]
name = "dirs"
version = "1.0.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fd78930633bd1c6e35c4b42b1df7b0cbc6bc191146e512bb3bedf243fcc3901"
dependencies = [
"libc",
"redox_users",
"winapi",
]
[[package]]
name = "docopt"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7f525a586d310c87df72ebcd98009e57f1cc030c8c268305287a476beb653969"
dependencies = [
"lazy_static",
"regex",
"serde",
"strsim",
]
[[package]]
name = "either"
version = "1.5.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bb1f6b1ce1c140482ea30ddd3335fc0024ac7ee112895426e0a629a6c20adfe3"
[[package]]
name = "ena"
version = "0.14.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d7402b94a93c24e742487327a7cd839dc9d36fec9de9fb25b09f2dae459f36c3"
dependencies = [
"log",
]
[[package]]
name = "fake-simd"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e88a8acf291dafb59c2d96e8f59828f3838bb1a70398823ade51a84de6a6deed"
[[package]]
name = "fixedbitset"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "37ab347416e802de484e4d03c7316c48f1ecb56574dfd4a46a80f173ce1de04d"
[[package]]
name = "generic-array"
version = "0.12.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c68f0274ae0e023facc3c97b2e00f076be70e254bc851d972503b328db79b2ec"
dependencies = [
"typenum",
]
[[package]]
name = "getrandom"
version = "0.1.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7abc8dd8451921606d809ba32e95b6111925cd2906060d2dcc29c070220503eb"
dependencies = [
"cfg-if",
"libc",
"wasi",
]
[[package]]
name = "hermit-abi"
version = "0.1.13"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "91780f809e750b0a89f5544be56617ff6b1227ee485bcb06ebe10cdf89bd3b71"
dependencies = [
"libc",
]
[[package]]
name = "indexmap"
version = "1.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c398b2b113b55809ceb9ee3e753fcbac793f1956663f3c36549c1346015c2afe"
dependencies = [
"autocfg",
]
[[package]]
name = "itertools"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "284f18f85651fe11e8a991b2adb42cb078325c996ed026d994719efcfca1d54b"
dependencies = [
"either",
]
[[package]]
name = "lalrpop"
version = "0.19.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d6f55673d283313791404be21209bb433f128f7e5c451986df107eb5fdbd68d2"
dependencies = [
"ascii-canvas",
"atty",
"bit-set",
"diff",
"docopt",
"ena",
"itertools",
"lalrpop-util",
"petgraph",
"regex",
"regex-syntax",
"serde",
"serde_derive",
"sha2",
"string_cache",
"term",
"unicode-xid",
]
[[package]]
name = "lalrpop-util"
version = "0.19.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f7e88f15a7d31dfa8fb607986819039127f0161058a3b248a146142d276cbd28"
dependencies = [
"regex",
]
[[package]]
name = "lazy_static"
version = "1.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
[[package]]
name = "libc"
version = "0.2.71"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9457b06509d27052635f90d6466700c65095fdf75409b3fbdd903e988b886f49"
[[package]]
name = "log"
version = "0.4.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "14b6052be84e6b71ab17edffc2eeabf5c2c3ae1fdb464aae35ac50c67a44e1f7"
dependencies = [
"cfg-if",
]
[[package]]
name = "memchr"
version = "2.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3728d817d99e5ac407411fa471ff9800a778d88a24685968b36824eaf4bee400"
[[package]]
name = "new_debug_unreachable"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e4a24736216ec316047a1fc4252e27dabb04218aa4a3f37c6e7ddbf1f9782b54"
[[package]]
name = "opaque-debug"
version = "0.2.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2839e79665f131bdb5782e51f2c6c9599c133c6098982a54c794358bf432529c"
[[package]]
name = "petgraph"
version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "467d164a6de56270bd7c4d070df81d07beace25012d5103ced4e9ff08d6afdb7"
dependencies = [
"fixedbitset",
"indexmap",
]
[[package]]
name = "phf_shared"
version = "0.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c00cf8b9eafe68dde5e9eaa2cef8ee84a9336a47d566ec55ca16589633b65af7"
dependencies = [
"siphasher",
]
[[package]]
name = "precomputed-hash"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "925383efa346730478fb4838dbe9137d2a47675ad789c546d150a6e1dd4ab31c"
[[package]]
name = "proc-macro2"
version = "1.0.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "beae6331a816b1f65d04c45b078fd8e6c93e8071771f41b8163255bbd8d7c8fa"
dependencies = [
"unicode-xid",
]
[[package]]
name = "quote"
version = "1.0.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "aa563d17ecb180e500da1cfd2b028310ac758de548efdd203e18f283af693f37"
dependencies = [
"proc-macro2",
]
[[package]]
name = "redox_syscall"
version = "0.1.56"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2439c63f3f6139d1b57529d16bc3b8bb855230c8efcc5d3a896c8bea7c3b1e84"
[[package]]
name = "redox_users"
version = "0.3.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "09b23093265f8d200fa7b4c2c76297f47e681c655f6f1285a8780d6a022f7431"
dependencies = [
"getrandom",
"redox_syscall",
"rust-argon2",
]
[[package]]
name = "regex"
version = "1.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c3780fcf44b193bc4d09f36d2a3c87b251da4a046c87795a0d35f4f927ad8e6"
dependencies = [
"aho-corasick",
"memchr",
"regex-syntax",
"thread_local",
]
[[package]]
name = "regex-syntax"
version = "0.6.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "26412eb97c6b088a6997e05f69403a802a92d520de2f8e63c2b65f9e0f47c4e8"
[[package]]
name = "rust-argon2"
version = "0.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2bc8af4bda8e1ff4932523b94d3dd20ee30a87232323eda55903ffd71d2fb017"
dependencies = [
"base64",
"blake2b_simd",
"constant_time_eq",
"crossbeam-utils",
]
[[package]]
name = "serde"
version = "1.0.111"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c9124df5b40cbd380080b2cc6ab894c040a3070d995f5c9dc77e18c34a8ae37d"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.111"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3f2c3ac8e6ca1e9c80b8be1023940162bf81ae3cffbb1809474152f2ce1eb250"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "serene"
version = "0.1.0"
dependencies = [
"lalrpop",
"lalrpop-util",
"regex",
]
[[package]]
name = "sha2"
version = "0.8.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a256f46ea78a0c0d9ff00077504903ac881a1dafdc20da66545699e7776b3e69"
dependencies = [
"block-buffer",
"digest",
"fake-simd",
"opaque-debug",
]
[[package]]
name = "siphasher"
version = "0.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fa8f3741c7372e75519bd9346068370c9cdaabcc1f9599cbcf2a2719352286b7"
[[package]]
name = "string_cache"
version = "0.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2940c75beb4e3bf3a494cef919a747a2cb81e52571e212bfbd185074add7208a"
dependencies = [
"lazy_static",
"new_debug_unreachable",
"phf_shared",
"precomputed-hash",
"serde",
]
[[package]]
name = "strsim"
version = "0.9.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6446ced80d6c486436db5c078dde11a9f73d42b57fb273121e160b84f63d894c"
[[package]]
name = "syn"
version = "1.0.31"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b5304cfdf27365b7585c25d4af91b35016ed21ef88f17ced89c7093b43dba8b6"
dependencies = [
"proc-macro2",
"quote",
"unicode-xid",
]
[[package]]
name = "term"
version = "0.5.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "edd106a334b7657c10b7c540a0106114feadeb4dc314513e97df481d5d966f42"
dependencies = [
"byteorder",
"dirs",
"winapi",
]
[[package]]
name = "thread_local"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d40c6d1b69745a6ec6fb1ca717914848da4b44ae29d9b3080cbee91d72a69b14"
dependencies = [
"lazy_static",
]
[[package]]
name = "typenum"
version = "1.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "373c8a200f9e67a0c95e62a4f52fbf80c23b4381c05a17845531982fa99e6b33"
[[package]]
name = "unicode-xid"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "826e7639553986605ec5979c7dd957c7895e93eabed50ab2ffa7f6128a75097c"
[[package]]
name = "wasi"
version = "0.9.0+wasi-snapshot-preview1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cccddf32554fecc6acb585f82a32a72e28b48f8c4c1883ddfeeeaa96f7d8e519"
[[package]]
name = "winapi"
version = "0.3.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8093091eeb260906a183e6ae1abdba2ef5ef2257a21801128899c3fc699229c6"
dependencies = [
"winapi-i686-pc-windows-gnu",
"winapi-x86_64-pc-windows-gnu",
]
[[package]]
name = "winapi-i686-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
[[package]]
name = "winapi-x86_64-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"

View File

@ -6,4 +6,10 @@ edition = "2018"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[build-dependencies]
#lalrpop = "0.19.0"
lalrpop = { version = "0.19.0", features = ["lexer"] }
[dependencies]
lalrpop-util = "0.19.0"
regex = "1"

View File

@ -11,6 +11,7 @@ following commands to install them:
#+BEGIN_SRC bash
rustup component add rls --toolchain stable-x86_64-unknown-linux-gnu
rustup component add --toolchain stable-x86_64-unknown-linux-gnu clippy
rustup component add rustfmt
#+END_SRC
Use your desired toolchain instead of *stable-x86_64-unknown-linux-gnu*

5
build.rs Normal file
View File

@ -0,0 +1,5 @@
extern crate lalrpop;
fn main() {
lalrpop::process_root().unwrap();
}

37
src/ast.rs Normal file
View File

@ -0,0 +1,37 @@
// Note: I kept the number implementation simple for now
// but we need to decide on our approach to numbers, are
// we going to only support the 64bit variants? or should
// try to be smart and support 32 and 64 and switch between
// them ?
// What about usize and isize ?
#[derive(Debug, Clone)]
pub enum Number {
Integer(i32),
Float(f32),
}
impl PartialEq for Number {
fn eq(&self, other: &Self) -> bool {
let comb = (&self, &other);
match comb {
(Number::Integer(x), Number::Integer(y)) => *x == *y,
(Number::Float(x), Number::Float(y)) => *x == *y,
(Number::Integer(x), Number::Float(y)) => *x as f32 == *y,
(Number::Float(x), Number::Integer(y)) => *x == *y as f32,
}
}
}
impl Eq for Number {}
#[derive(Debug, Eq, PartialEq, Clone)]
pub enum Expr {
List(Vec<Expr>),
Symbol(String),
Str(String),
Quote(Box<Expr>),
Num(Number),
Comment,
Error(String),
}

1
src/collections.rs Normal file
View File

@ -0,0 +1 @@
pub mod list;

7
src/collections/list.rs Normal file
View File

@ -0,0 +1,7 @@
pub struct List {}
impl List {
pub fn h() {
println!("Uo")
}
}

58
src/grammer.lalrpop Normal file
View File

@ -0,0 +1,58 @@
//! Serene's grammer based on LALRPOP which is a LR(1) parser.
use std::str::FromStr;
use crate::ast;
grammar;
// A collection of Expr objects is simply a sequence of parsed AST objects.
pub Exprs: Vec<ast::Expr> = {
<v:(<Expr>)*> => v,
};
// Parse an AST expression.
Expr: ast::Expr = {
// Matches a list
"(" <Exprs> ")" => ast::Expr::List(<>),
// Matches a vector
// "[" <Exprs> "]" => Ast::Vector(<>),
// Match the literal value "nil".
// "nil" => Ast::Nil,
// Match a Num term.
Float => ast::Expr::Num(ast::Number::Float(<>)),
Decimal => ast::Expr::Num(ast::Number::Integer(<>)),
// Matches a string.
r#""(?:[^"\\]|\\.)*""# => {
let val = <>;
ast::Expr::Str(val[1..val.len() - 1].to_owned())
},
// Matches a quoted expr
"'" <Expr> => ast::Expr::Quote(Box::new(<>)),
// Match any token and treat it as an atom.
Symbol => ast::Expr::Symbol(<>),
! => ast::Expr::Error(format!("{:?}", <>)),
};
// Match any sequence of token characters.
Symbol: String = {
r#"[A-Za-z_?+*/=<>-]+[0-9A-Za-z_?+*/=<>-]*"# => (<>).to_owned()
};
// Match any valid integer value and treat it as a 32-bit signed integer.
Decimal: i32 = {
r"[0-9]+" => i32::from_str(<>).unwrap()
};
Float: f32 = {
r"[0-9]*\.[0-9]+" => f32::from_str(<>).unwrap()
};
match {
r"\s*" => { },
r";[^\n\r]*[\n\r]*" => { },
_
}

View File

@ -1,3 +1,32 @@
fn main() {
println!("Hello, world!");
#[macro_use]
extern crate lalrpop_util;
lalrpop_mod!(pub grammer);
pub mod ast;
pub mod collections;
use collections::list;
#[test]
fn grammer() {
assert!(grammer::ExprsParser::new().parse("a22").is_ok());
assert!(grammer::ExprsParser::new().parse("44").is_ok());
assert!(grammer::ExprsParser::new().parse("is-ok").is_ok());
assert!(grammer::ExprsParser::new().parse("is-ok?").is_ok());
assert!(grammer::ExprsParser::new().parse("is-ok+<<>_").is_ok());
println!("{:?}", grammer::ExprsParser::new().parse("(as
(sad asd) 3i)"));
assert!(true);
assert!(grammer::ExprsParser::new()
.parse("(\"asd\" (symbol (n)))")
.is_ok());
assert!(grammer::ExprsParser::new()
.parse("(\"asd\" (symbol (n 32)))")
.is_ok());
assert!(grammer::ExprsParser::new().parse("((22)").is_err());
}
fn main() {
list::List::h();
}