Initial commit

First prototype parser ready
2022-05-25 02:07:49 +02:00
commit 9a553b7b68
6 changed files with 331 additions and 0 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1 @@
+/target
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -0,0 +1,162 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+
+[[package]]
+name = "ahash"
+version = "0.3.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e8fd72866655d1904d6b0997d0b07ba561047d070fbe29de039031c641b61217"
+dependencies = [
+ "const-random",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
+
+[[package]]
+name = "chumsky"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8d02796e4586c6c41aeb68eae9bfb4558a522c35f1430c14b40136c3706e09e4"
+dependencies = [
+ "ahash",
+]
+
+[[package]]
+name = "const-random"
+version = "0.1.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f590d95d011aa80b063ffe3253422ed5aa462af4e9867d43ce8337562bac77c4"
+dependencies = [
+ "const-random-macro",
+ "proc-macro-hack",
+]
+
+[[package]]
+name = "const-random-macro"
+version = "0.1.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "615f6e27d000a2bffbc7f2f6a8669179378fa27ee4d0a509e985dfc0a7defb40"
+dependencies = [
+ "getrandom",
+ "lazy_static",
+ "proc-macro-hack",
+ "tiny-keccak",
+]
+
+[[package]]
+name = "crunchy"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7a81dae078cea95a014a339291cec439d2f232ebe854a9d672b796c6afafa9b7"
+
+[[package]]
+name = "getrandom"
+version = "0.2.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9be70c98951c83b8d2f8f60d7065fa6d5146873094452a1008da8c2f1e4205ad"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "wasi",
+]
+
+[[package]]
+name = "lazy_static"
+version = "1.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
+
+[[package]]
+name = "libc"
+version = "0.2.126"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "349d5a591cd28b49e1d1037471617a32ddcda5731b99419008085f72d5a53836"
+
+[[package]]
+name = "orchid"
+version = "0.1.0"
+dependencies = [
+ "chumsky",
+ "thiserror",
+]
+
+[[package]]
+name = "proc-macro-hack"
+version = "0.5.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dbf0c48bc1d91375ae5c3cd81e3722dff1abcf81a30960240640d223f59fe0e5"
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.39"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c54b25569025b7fc9651de43004ae593a75ad88543b17178aa5e1b9c4f15f56f"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a1feb54ed693b93a84e14094943b84b7c4eae204c512b7ccb95ab0c66d278ad1"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "syn"
+version = "1.0.95"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fbaf6116ab8924f39d52792136fb74fd60a80194cf1b1c6ffa6453eef1c3f942"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "thiserror"
+version = "1.0.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bd829fe32373d27f76265620b5309d0340cb8550f523c1dda251d6298069069a"
+dependencies = [
+ "thiserror-impl",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "1.0.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0396bc89e626244658bef819e22d0cc459e795a5ebe878e6ec336d1674a8d79a"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "tiny-keccak"
+version = "2.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2c9d3793400a45f954c52e73d068316d76b6f4e36977e3fcebb13a2721e80237"
+dependencies = [
+ "crunchy",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d22af068fba1eb5edcb4aea19d382b2a3deb4c8f9d475c589b6ada9e0fd493ee"
+
+[[package]]
+name = "wasi"
+version = "0.10.2+wasi-snapshot-preview1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fd6fbd9a79829dd1ad0cc20627bf1ed606756a7f77edff7b66b7064f9cb327c6"
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -0,0 +1,10 @@
+[package]
+name = "orchid"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+thiserror = "1.0"
+chumsky = "0.8"
--- a/README.md
+++ b/README.md
@@ -0,0 +1,2 @@
+Orchid will be a functional language with a powerful macro language and
+optimizer. Further explanation and demos coming soon!
--- a/src/main.rs
+++ b/src/main.rs
@@ -0,0 +1,13 @@
+use std::io::{self, Read};
+
+use chumsky::Parser;
+
+mod parse;
+
+fn main() {
+    let mut input = String::new();
+    let mut stdin = io::stdin();
+    stdin.read_to_string(&mut input).unwrap();
+    let output = parse::parser().parse(input);
+    println!("\nParsed:\n{:?}", output);
+}
--- a/src/parse.rs
+++ b/src/parse.rs
@@ -0,0 +1,143 @@
+use std::fmt::Debug;
+use chumsky::{self, prelude::*, Parser};
+
+#[derive(Debug)]
+pub enum Expr {
+    Num(f64),
+    Int(u64),
+    Char(char),
+    Str(String),
+    Name(String),
+    S(Vec<Expr>),
+    Lambda(String, Vec<Expr>)
+}
+
+fn uint_parser(base: u32) -> impl Parser<char, u64, Error = Simple<char>> {
+    text::int(base).map(move |s: String| u64::from_str_radix(&s, base).unwrap())
+}
+
+fn e_parser() -> impl Parser<char, i32, Error = Simple<char>> {
+    return choice((
+        just('e')
+            .ignore_then(text::int(10))
+            .map(|s: String| s.parse().unwrap()),
+        just("e-")
+            .ignore_then(text::int(10))
+            .map(|s: String| -s.parse::<i32>().unwrap()),
+        empty().map(|()| 0)
+    ))
+}
+
+fn nat2u(base: u64) -> impl Fn((u64, i32),) -> u64 {
+    return move |(val, exp)| {
+        if exp == 0 {val}
+        else {val * base.checked_pow(exp.try_into().unwrap()).unwrap()}
+    };
+}
+
+fn nat2f(base: u64) -> impl Fn((f64, i32),) -> f64 {
+    return move |(val, exp)| {
+        if exp == 0 {val}
+        else {val * (base as f64).powf(exp.try_into().unwrap())}
+    }
+}
+
+fn e_uint_parser(base: u32) -> impl Parser<char, u64, Error = Simple<char>> {
+    if base > 14 {panic!("exponential in base that uses the digit 'e' is ambiguous")}
+    uint_parser(base).then(e_parser()).map(nat2u(base.into()))
+}
+
+fn int_parser() -> impl Parser<char, u64, Error = Simple<char>> {
+    choice((
+        just("0b").ignore_then(e_uint_parser(2)),
+        just("0x").ignore_then(uint_parser(16)),
+        just('0').ignore_then(e_uint_parser(8)),
+        e_uint_parser(10), // Dec has no prefix
+    ))
+}
+
+fn dotted_parser(base: u32) -> impl Parser<char, f64, Error = Simple<char>> {
+    uint_parser(base)
+    .then_ignore(just('.'))
+    .then(text::digits(base))
+    .map(move |(wh, frac)| {
+        let frac_num = u64::from_str_radix(&frac, base).unwrap() as f64;
+        let dexp = base.pow(frac.len().try_into().unwrap());
+        wh as f64 + (frac_num / dexp as f64)
+    })
+}
+
+fn e_float_parser(base: u32) -> impl Parser<char, f64, Error = Simple<char>> {
+    if base > 14 {panic!("exponential in base that uses the digit 'e' is ambiguous")}
+    dotted_parser(base).then(e_parser()).map(nat2f(base.into()))
+}
+
+fn float_parser() -> impl Parser<char, f64, Error = Simple<char>> {
+    choice((
+        just("0b").ignore_then(e_float_parser(2)),
+        just("0x").ignore_then(dotted_parser(16)),
+        just('0').ignore_then(e_float_parser(8)),
+        e_float_parser(10),
+    ))
+}
+
+fn text_parser(delim: char) -> impl Parser<char, char, Error = Simple<char>> {
+    let escape = just('\\').ignore_then(
+        just('\\')
+            .or(just('/'))
+            .or(just('"'))
+            .or(just('b').to('\x08'))
+            .or(just('f').to('\x0C'))
+            .or(just('n').to('\n'))
+            .or(just('r').to('\r'))
+            .or(just('t').to('\t'))
+            .or(just('u').ignore_then(
+                filter(|c: &char| c.is_digit(16))
+                    .repeated()
+                    .exactly(4)
+                    .collect::<String>()
+                    .validate(|digits, span, emit| {
+                        char::from_u32(u32::from_str_radix(&digits, 16).unwrap())
+                            .unwrap_or_else(|| {
+                                emit(Simple::custom(span, "invalid unicode character"));
+                                '\u{FFFD}' // unicode replacement character
+                            })
+                    }),
+            )),
+    );
+    filter(move |&c| c != '\\' && c != delim).or(escape)
+}
+
+fn char_parser() -> impl Parser<char, char, Error = Simple<char>> {
+    just('\'').ignore_then(text_parser('\'')).then_ignore(just('\''))
+}
+
+fn str_parser() -> impl Parser<char, String, Error = Simple<char>> {
+    just('"')
+    .ignore_then(text_parser('"').repeated())
+    .then_ignore(just('"'))
+    .collect()
+}
+
+pub fn parser() -> impl Parser<char, Expr, Error = Simple<char>> {
+    return recursive(|expr| {
+        let lambda = just('\\')
+            .ignore_then(text::ident())
+            .then_ignore(just('.'))
+            .then(expr.clone().repeated().at_least(1))
+            .map(|(name, body)| Expr::Lambda(name, body));
+        let sexpr = expr.clone()
+            .repeated()
+            .delimited_by(just('('), just(')'))
+            .map(Expr::S);
+        choice((
+            float_parser().map(Expr::Num),
+            int_parser().map(Expr::Int),
+            char_parser().map(Expr::Char),
+            str_parser().map(Expr::Str),
+            text::ident().map(Expr::Name),
+            sexpr,
+            lambda
+        )).padded()
+    }).then_ignore(end())
+}