Skip to content
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

Jump to bottom

Redundant redundant escapes #2838

Merged
merged 1 commit into from
Mar 10, 2024
Merged

Redundant redundant escapes #2838

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.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
34 changes: 2 additions & 32 deletions cli/src/generate/prepare_grammar/expand_tokens.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,6 @@ use crate::generate::nfa::{CharacterSet, Nfa, NfaState};
use crate::generate::rules::{Precedence, Rule};
use anyhow::{anyhow, Context, Result};
use lazy_static::lazy_static;
use regex::Regex;
use regex_syntax::ast::{
parse, Ast, ClassPerlKind, ClassSet, ClassSetBinaryOpKind, ClassSetItem, ClassUnicodeKind,
RepetitionKind, RepetitionRange,
Expand All @@ -13,8 +12,6 @@ use std::collections::HashMap;
use std::i32;

lazy_static! {
static ref CURLY_BRACE_REGEX: Regex =
Regex::new(r"(^|[^\\pP])\{([^}]*[^0-9A-Fa-f,}][^}]*)\}").unwrap();
static ref UNICODE_CATEGORIES: HashMap<&'static str, Vec<u32>> =
serde_json::from_str(UNICODE_CATEGORIES_JSON).unwrap();
static ref UNICODE_PROPERTIES: HashMap<&'static str, Vec<u32>> =
Expand All @@ -29,7 +26,6 @@ const UNICODE_CATEGORIES_JSON: &str = include_str!("./unicode-categories.json");
const UNICODE_PROPERTIES_JSON: &str = include_str!("./unicode-properties.json");
const UNICODE_CATEGORY_ALIASES_JSON: &str = include_str!("./unicode-category-aliases.json");
const UNICODE_PROPERTY_ALIASES_JSON: &str = include_str!("./unicode-property-aliases.json");
const ALLOWED_REDUNDANT_ESCAPED_CHARS: [char; 4] = ['!', '\'', '"', '/'];

struct NfaBuilder {
nfa: Nfa,
Expand Down Expand Up @@ -60,29 +56,6 @@ const fn get_completion_precedence(rule: &Rule) -> i32 {
0
}

fn preprocess_regex(content: &str) -> String {
let content = CURLY_BRACE_REGEX.replace(content, "$1\\{$2\\}");
let mut result = String::with_capacity(content.len());
let mut is_escaped = false;
for c in content.chars() {
if is_escaped {
if !ALLOWED_REDUNDANT_ESCAPED_CHARS.contains(&c) {
result.push('\\');
}
result.push(c);
is_escaped = false;
} else if c == '\\' {
is_escaped = true;
} else {
result.push(c);
}
}
if is_escaped {
result.push('\\');
}
result
}

pub fn expand_tokens(mut grammar: ExtractedLexicalGrammar) -> Result<LexicalGrammar> {
let mut builder = NfaBuilder {
nfa: Nfa::new(),
Expand Down Expand Up @@ -138,8 +111,7 @@ impl NfaBuilder {
fn expand_rule(&mut self, rule: &Rule, mut next_state_id: u32) -> Result<bool> {
match rule {
Rule::Pattern(s, f) => {
let s = preprocess_regex(s);
let ast = parse::Parser::new().parse(&s)?;
let ast = parse::Parser::new().parse(s)?;
self.expand_regex(&ast, next_state_id, f.contains('i'))
}
Rule::String(s) => {
Expand Down Expand Up @@ -847,11 +819,9 @@ mod tests {
("\u{00df}", Some((3, "\u{00df}"))),
],
},
// allowing un-escaped curly braces
Row {
rules: vec![
// Un-escaped curly braces
Rule::pattern(r"u{[0-9a-fA-F]+}", ""),
Rule::pattern(r"u\{[0-9a-fA-F]+\}", ""),
// Already-escaped curly braces
Rule::pattern(r"\{[ab]{3}\}", ""),
// Unicode codepoints
Expand Down