Skip to content

Simplify string check in Lexer.lex_identifier #4420

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

Merged
merged 3 commits into from
Jan 5, 2023
Merged

Simplify string check in Lexer.lex_identifier #4420

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f02f327
Simplify string check
harupy Jan 4, 2023
d775965
Use try_from
harupy Jan 4, 2023
c640312
Address comments
harupy Jan 5, 2023
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
65 changes: 16 additions & 49 deletions compiler/parser/src/lexer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -241,59 +241,23 @@ where

// Lexer helper functions:
fn lex_identifier(&mut self) -> LexResult {
let mut name = String::new();
let start_pos = self.get_pos();

// Detect potential string like rb'' b'' f'' u'' r''
let mut saw_b = false;
let mut saw_r = false;
let mut saw_u = false;
let mut saw_f = false;
Comment on lines -248 to -251
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think the current logic is a bit difficult to verify if it's correct.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

oh definitely, the change makes it much better.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this originally came from the tokenizer code.

loop {
// Detect r"", f"", b"" and u""
if !(saw_b || saw_u || saw_f) && matches!(self.window[0], Some('b' | 'B')) {
saw_b = true;
} else if !(saw_b || saw_r || saw_u || saw_f)
&& matches!(self.window[0], Some('u' | 'U'))
{
saw_u = true;
} else if !(saw_r || saw_u) && matches!(self.window[0], Some('r' | 'R')) {
saw_r = true;
} else if !(saw_b || saw_u || saw_f) && matches!(self.window[0], Some('f' | 'F')) {
saw_f = true;
} else {
break;
match self.window[..3] {
[Some(c), Some('"' | '\''), ..] => {
if let Ok(kind) = StringKind::try_from(c) {
return self.lex_string(kind);
}
}

// Take up char into name:
name.push(self.next_char().unwrap());

// Check if we have a string:
if matches!(self.window[0], Some('"' | '\'')) {
let kind = if saw_r {
if saw_b {
StringKind::RawBytes
} else if saw_f {
StringKind::RawFString
} else {
StringKind::RawString
}
} else if saw_b {
StringKind::Bytes
} else if saw_u {
StringKind::Unicode
} else if saw_f {
StringKind::FString
} else {
StringKind::String
};

return self
.lex_string(kind)
.map(|(_, tok, end_pos)| (start_pos, tok, end_pos));
[Some(c1), Some(c2), Some('"' | '\'')] => {
if let Ok(kind) = StringKind::try_from([c1, c2]) {
return self.lex_string(kind);
}
}
}
_ => {}
};

let start_pos = self.get_pos();
let mut name = String::new();
while self.is_identifier_continuation() {
name.push(self.next_char().unwrap());
}
Expand Down Expand Up @@ -495,6 +459,9 @@ where

fn lex_string(&mut self, kind: StringKind) -> LexResult {
let start_pos = self.get_pos();
for _ in 0..kind.prefix_len() {
self.next_char();
}
let quote_char = self.next_char().unwrap();
let mut string_content = String::new();

Expand Down
2 changes: 1 addition & 1 deletion compiler/parser/src/string_parser.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ impl<'a> StringParser<'a> {
str_start: Location,
str_end: Location,
) -> Self {
let offset = kind.to_string().len() + if triple_quoted { 3 } else { 1 };
let offset = kind.prefix_len() + if triple_quoted { 3 } else { 1 };
Self {
chars: source.chars().peekable(),
kind,
Expand Down
37 changes: 37 additions & 0 deletions compiler/parser/src/token.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -240,6 +240,34 @@ pub enum StringKind {
Unicode,
}

impl TryFrom<char> for StringKind {
type Error = String;

fn try_from(ch: char) -> Result<Self, String> {
match ch {
'r' | 'R' => Ok(StringKind::RawString),
'f' | 'F' => Ok(StringKind::FString),
'u' | 'U' => Ok(StringKind::Unicode),
'b' | 'B' => Ok(StringKind::Bytes),
c => Err(format!("Unexpected string prefix: {c}")),
}
}
}

impl TryFrom<[char; 2]> for StringKind {
type Error = String;

fn try_from(chars: [char; 2]) -> Result<Self, String> {
match chars {
['r' | 'R', 'f' | 'F'] => Ok(StringKind::RawFString),
['f' | 'F', 'r' | 'R'] => Ok(StringKind::RawFString),
['r' | 'R', 'b' | 'B'] => Ok(StringKind::RawBytes),
['b' | 'B', 'r' | 'R'] => Ok(StringKind::RawBytes),
[c1, c2] => Err(format!("Unexpected string prefix: {c1}{c2}")),
}
}
}

impl fmt::Display for StringKind {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
use StringKind::*;
Expand Down Expand Up @@ -274,4 +302,13 @@ impl StringKind {
pub fn is_unicode(&self) -> bool {
matches!(self, StringKind::Unicode)
}

pub fn prefix_len(&self) -> usize {
use StringKind::*;
match self {
String => 0,
RawString | FString | Unicode | Bytes => 1,
RawFString | RawBytes => 2,
}
}
}