nac3/nac3parser/src/parser.rs

231 lines
6.4 KiB
Rust
Raw Normal View History

//! Python parsing.
//!
//! Use this module to parse python code into an AST.
//! There are three ways to parse python code. You could
//! parse a whole program, a single statement, or a single
//! expression.
use std::iter;
use nac3ast::Location;
pub use crate::mode::Mode;
use crate::{
ast::{self, FileName},
error::ParseError,
lexer, python,
};
/*
* Parse python code.
* Grammar may be inspired by antlr grammar for python:
* https://github.com/antlr/grammars-v4/tree/master/python3
*/
/// Parse a full python program, containing usually multiple lines.
2021-12-28 01:28:55 +08:00
pub fn parse_program(source: &str, file: FileName) -> Result<ast::Suite, ParseError> {
parse(source, Mode::Module, file).map(|top| match top {
ast::Mod::Module { body, .. } => body,
_ => unreachable!(),
})
}
/// Parses a python expression
///
/// # Example
/// ```
2021-11-03 17:11:00 +08:00
/// use nac3parser::{parser, ast};
/// let expr = parser::parse_expression("1 + 2").unwrap();
///
/// assert_eq!(
/// expr,
/// ast::Expr {
2021-12-28 01:38:16 +08:00
/// location: ast::Location::new(1, 3, Default::default()),
/// custom: (),
/// node: ast::ExprKind::BinOp {
/// left: Box::new(ast::Expr {
2021-12-28 01:38:16 +08:00
/// location: ast::Location::new(1, 1, Default::default()),
/// custom: (),
/// node: ast::ExprKind::Constant {
/// value: ast::Constant::Int(1.into()),
/// kind: None,
/// }
/// }),
/// op: ast::Operator::Add,
/// right: Box::new(ast::Expr {
2021-12-28 01:38:16 +08:00
/// location: ast::Location::new(1, 5, Default::default()),
/// custom: (),
/// node: ast::ExprKind::Constant {
/// value: ast::Constant::Int(2.into()),
/// kind: None,
/// }
/// })
/// }
/// },
/// );
///
/// ```
pub fn parse_expression(source: &str) -> Result<ast::Expr, ParseError> {
2024-06-12 15:13:09 +08:00
parse(source, Mode::Expression, FileName::default()).map(|top| match top {
ast::Mod::Expression { body } => *body,
_ => unreachable!(),
})
}
// Parse a given source code
2021-12-28 01:28:55 +08:00
pub fn parse(source: &str, mode: Mode, file: FileName) -> Result<ast::Mod, ParseError> {
let lxr = lexer::make_tokenizer(source, file);
2024-06-12 15:13:09 +08:00
let marker_token = (Location::default(), mode.to_marker(), Location::default());
let tokenizer = iter::once(Ok(marker_token)).chain(lxr);
2024-06-12 14:45:03 +08:00
python::TopParser::new().parse(tokenizer).map_err(ParseError::from)
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_parse_empty() {
2024-06-17 14:07:38 +08:00
let parse_ast = parse_program("", FileName::default()).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_print_hello() {
let source = String::from("print('Hello world')");
2024-06-17 14:07:38 +08:00
let parse_ast = parse_program(&source, FileName::default()).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_print_2() {
let source = String::from("print('Hello world', 2)");
2024-06-17 14:07:38 +08:00
let parse_ast = parse_program(&source, FileName::default()).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_kwargs() {
let source = String::from("my_func('positional', keyword=2)");
2024-06-17 14:07:38 +08:00
let parse_ast = parse_program(&source, FileName::default()).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_if_elif_else() {
let source = String::from("if 1: 10\nelif 2: 20\nelse: 30");
2024-06-17 14:07:38 +08:00
let parse_ast = parse_program(&source, FileName::default()).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_lambda() {
let source = "lambda x, y: x * y"; // lambda(x, y): x * y";
2024-06-17 14:07:38 +08:00
let parse_ast = parse_program(source, FileName::default()).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_tuples() {
let source = "a, b = 4, 5";
2024-06-17 14:07:38 +08:00
insta::assert_debug_snapshot!(parse_program(source, FileName::default()).unwrap());
}
#[test]
fn test_parse_class() {
let source = "\
class Foo(A, B):
def __init__(self):
pass
def method_with_default(self, arg='default'):
pass";
2024-06-17 14:07:38 +08:00
insta::assert_debug_snapshot!(parse_program(source, FileName::default()).unwrap());
}
#[test]
fn test_parse_dict_comprehension() {
let source = String::from("{x1: x2 for y in z}");
let parse_ast = parse_expression(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_list_comprehension() {
let source = String::from("[x for y in z]");
let parse_ast = parse_expression(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_double_list_comprehension() {
let source = String::from("[x for y, y2 in z for a in b if a < 5 if a > 10]");
let parse_ast = parse_expression(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
2024-06-12 14:45:03 +08:00
#[test]
fn test_more_comment() {
let source = "\
a: int # nac3: sf1
# nac3: sdf4
for i in (1, '12'): # nac3: sf2
a: int
# nac3: 3
# nac3: 5
while i < 2: # nac3: 4
# nac3: real pass
pass
# nac3: expr1
# nac3: expr3
1 + 2 # nac3: expr2
# nac3: if3
# nac3: if1
if 1: # nac3: if2
3";
2024-06-17 14:07:38 +08:00
insta::assert_debug_snapshot!(parse_program(source, FileName::default()).unwrap());
}
2024-06-12 14:45:03 +08:00
#[test]
fn test_sample_comment() {
let source = "\
# nac3: while1
# nac3: while2
# normal comment
while test: # nac3: while3
# nac3: simple assign0
a = 3 # nac3: simple assign1
";
2024-06-17 14:07:38 +08:00
insta::assert_debug_snapshot!(parse_program(source, FileName::default()).unwrap());
}
#[test]
fn test_comment_ambiguity() {
let source = "\
if a: d; # nac3: for d
if b: c # nac3: for c
if d: # nac3: for if d
b; b + 3; # nac3: for b + 3
a = 3; a + 3; b = a; # nac3: notif
# nac3: smallsingle1
# nac3: smallsingle3
aa = 3 # nac3: smallsingle2
if a: # nac3: small2
a
for i in a: # nac3: for1
pass
";
2024-06-17 14:07:38 +08:00
insta::assert_debug_snapshot!(parse_program(source, FileName::default()).unwrap());
}
#[test]
fn test_comment_should_fail() {
let source = "\
if a: # nac3: something
a = 3
";
2024-06-17 14:07:38 +08:00
assert!(parse_program(source, FileName::default()).is_err());
}
}