Normalise Hex and unicode escape sequences in string

Author: MichaReiser

crates/ruff_python_formatter/resources/test/fixtures/ruff/expression/bytes.py

@@ -118,3 +118,5 @@
     b'c'
     )
 }
+
+b"Unicode Escape sequence don't apply to bytes: \N{0x} \u{ABCD} \U{ABCDEFGH}"

crates/ruff_python_formatter/resources/test/fixtures/ruff/expression/string.py

@@ -133,3 +133,8 @@
 
 # https://github.com/astral-sh/ruff/issues/7460
 trailing_preferred_quote_texts = [''' "''', ''' ""''', ''' """''', ''' """"''']
+
+a = f"""\x1F"""
+a = """\x1F"""
+a = """\\x1F"""
+a = """\\\x1F"""

crates/ruff_python_formatter/src/lib.rs

@@ -211,13 +211,8 @@ if True:
     #[test]
     fn quick_test() {
         let source = r#"
-def main() -> None:
-    if True:
-        some_very_long_variable_name_abcdefghijk = Foo()
-        some_very_long_variable_name_abcdefghijk = some_very_long_variable_name_abcdefghijk[
-            some_very_long_variable_name_abcdefghijk.some_very_long_attribute_name
-            == "This is a very long string abcdefghijk"
-        ]
+x = "\N{ox}\N{OX}"
+
 
 "#;
         let source_type = PySourceType::Python;

crates/ruff_python_formatter/src/other/bytes_literal.rs

@@ -2,6 +2,7 @@ use ruff_python_ast::BytesLiteral;
 use ruff_text_size::Ranged;
 
 use crate::prelude::*;
+use crate::preview::is_hex_codes_in_unicode_sequences_enabled;
 use crate::string::{Quoting, StringPart};
 
 #[derive(Default)]
@@ -17,6 +18,7 @@ impl FormatNodeRule<BytesLiteral> for FormatBytesLiteral {
                 &locator,
                 f.options().quote_style(),
                 f.context().docstring(),
+                is_hex_codes_in_unicode_sequences_enabled(f.context()),
             )
             .fmt(f)
     }

crates/ruff_python_formatter/src/other/f_string.rs

@@ -2,6 +2,7 @@ use ruff_python_ast::FString;
 use ruff_text_size::Ranged;
 
 use crate::prelude::*;
+use crate::preview::is_hex_codes_in_unicode_sequences_enabled;
 use crate::string::{Quoting, StringPart};
 
 /// Formats an f-string which is part of a larger f-string expression.
@@ -31,6 +32,7 @@ impl Format<PyFormatContext<'_>> for FormatFString<'_> {
                 &locator,
                 f.options().quote_style(),
                 f.context().docstring(),
+                is_hex_codes_in_unicode_sequences_enabled(f.context()),
             )
             .fmt(f);
 

crates/ruff_python_formatter/src/other/string_literal.rs

@@ -2,6 +2,7 @@ use ruff_python_ast::StringLiteral;
 use ruff_text_size::Ranged;
 
 use crate::prelude::*;
+use crate::preview::is_hex_codes_in_unicode_sequences_enabled;
 use crate::string::{docstring, Quoting, StringPart};
 use crate::QuoteStyle;
 
@@ -61,6 +62,7 @@ impl Format<PyFormatContext<'_>> for FormatStringLiteral<'_> {
             &locator,
             quote_style,
             f.context().docstring(),
+            is_hex_codes_in_unicode_sequences_enabled(f.context()),
         );
 
         if self.layout.is_docstring() {

crates/ruff_python_formatter/src/preview.rs

@@ -57,3 +57,8 @@ pub(crate) const fn is_module_docstring_newlines_enabled(context: &PyFormatConte
 pub(crate) const fn is_dummy_implementations_enabled(context: &PyFormatContext) -> bool {
     context.is_preview()
 }
+
+/// Returns `true` if the [`hex_codes_in_unicode_sequences`](https://github.com/psf/black/pull/2916) preview style is enabled.
+pub(crate) const fn is_hex_codes_in_unicode_sequences_enabled(context: &PyFormatContext) -> bool {
+    context.is_preview()
+}

crates/ruff_python_formatter/src/string/mod.rs

@@ -253,6 +253,7 @@ impl StringPart {
         locator: &'a Locator,
         configured_style: QuoteStyle,
         parent_docstring_quote_char: Option<QuoteChar>,
+        normalize_hex: bool,
     ) -> NormalizedString<'a> {
         // Per PEP 8, always prefer double quotes for triple-quoted strings.
         let preferred_style = if self.quotes.triple {
@@ -310,7 +311,7 @@ impl StringPart {
             configured_style
         };
 
-        let raw_content = locator.slice(self.content_range);
+        let raw_content = &locator.slice(self.content_range);
 
         let quotes = match quoting {
             Quoting::Preserve => self.quotes,
@@ -327,7 +328,7 @@ impl StringPart {
             }
         };
 
-        let normalized = normalize_string(locator.slice(self.content_range), quotes, self.prefix);
+        let normalized = normalize_string(raw_content, quotes, self.prefix, normalize_hex);
 
         NormalizedString {
             prefix: self.prefix,
@@ -423,6 +424,10 @@ impl StringPrefix {
     pub(super) const fn is_fstring(self) -> bool {
         self.contains(StringPrefix::F_STRING)
     }
+
+    pub(super) const fn is_byte(self) -> bool {
+        self.contains(StringPrefix::BYTE)
+    }
 }
 
 impl Format<PyFormatContext<'_>> for StringPrefix {
@@ -722,7 +727,12 @@ impl TryFrom<char> for QuoteChar {
 /// with the provided [`StringQuotes`] style.
 ///
 /// Returns the normalized string and whether it contains new lines.
-fn normalize_string(input: &str, quotes: StringQuotes, prefix: StringPrefix) -> Cow<str> {
+fn normalize_string(
+    input: &str,
+    quotes: StringQuotes,
+    prefix: StringPrefix,
+    normalize_hex: bool,
+) -> Cow<str> {
     // The normalized string if `input` is not yet normalized.
     // `output` must remain empty if `input` is already normalized.
     let mut output = String::new();
@@ -734,15 +744,15 @@ fn normalize_string(input: &str, quotes: StringQuotes, prefix: StringPrefix) ->
     let preferred_quote = quote.as_char();
     let opposite_quote = quote.invert().as_char();
 
-    let mut chars = input.char_indices().peekable();
+    let mut chars = input.char_indices();
 
     let is_raw = prefix.is_raw_string();
     let is_fstring = prefix.is_fstring();
     let mut formatted_value_nesting = 0u32;
 
     while let Some((index, c)) = chars.next() {
         if is_fstring && matches!(c, '{' | '}') {
-            if chars.peek().copied().is_some_and(|(_, next)| next == c) {
+            if chars.as_str().starts_with(c) {
                 // Skip over the second character of the double braces
                 chars.next();
             } else if c == '{' {
@@ -757,7 +767,7 @@ fn normalize_string(input: &str, quotes: StringQuotes, prefix: StringPrefix) ->
             output.push_str(&input[last_index..index]);
 
             // Skip over the '\r' character, keep the `\n`
-            if chars.peek().copied().is_some_and(|(_, next)| next == '\n') {
+            if chars.as_str().starts_with('\n') {
                 chars.next();
             }
             // Replace the `\r` with a `\n`
@@ -766,24 +776,47 @@ fn normalize_string(input: &str, quotes: StringQuotes, prefix: StringPrefix) ->
             }
 
             last_index = index + '\r'.len_utf8();
-        } else if !quotes.triple && !is_raw {
+        } else if !is_raw {
             if c == '\\' {
-                if let Some((_, next)) = chars.peek().copied() {
-                    #[allow(clippy::if_same_then_else)]
-                    if next == opposite_quote && formatted_value_nesting == 0 {
-                        // Remove the escape by ending before the backslash and starting again with the quote
-                        chars.next();
-                        output.push_str(&input[last_index..index]);
-                        last_index = index + '\\'.len_utf8();
-                    } else if next == preferred_quote {
-                        // Quote is already escaped, skip over it.
-                        chars.next();
-                    } else if next == '\\' {
+                if let Some((_, next)) = chars.clone().next() {
+                    if !quotes.triple {
+                        #[allow(clippy::if_same_then_else)]
+                        if next == opposite_quote && formatted_value_nesting == 0 {
+                            // Remove the escape by ending before the backslash and starting again with the quote
+                            chars.next();
+                            output.push_str(&input[last_index..index]);
+                            last_index = index + '\\'.len_utf8();
+                            continue;
+                        } else if next == preferred_quote {
+                            // Quote is already escaped, skip over it.
+                            chars.next();
+                            continue;
+                        }
+                    }
+                    if next == '\\' {
                         // Skip over escaped backslashes
                         chars.next();
+                    } else if normalize_hex {
+                        if let Some(normalised) = UnicodeEscape::new(next, !prefix.is_byte())
+                            .and_then(|escape| escape.normalize(&chars.as_str()[next.len_utf8()..]))
+                        {
+                            // Length of the `\` plus the length of the escape sequence character (`u` | `U` | `x`)
+                            let escape_start_len = '\\'.len_utf8() + next.len_utf8();
+                            let escape_start_offset = index + escape_start_len;
+                            if let Cow::Owned(normalised) = &normalised {
+                                output.push_str(&input[last_index..escape_start_offset]);
+                                output.push_str(normalised);
+                                last_index = escape_start_offset + normalised.len();
+                            };
+
+                            // Skip over the escape sequence characters
+                            for _ in 0..escape_start_len + normalised.len() {
+                                chars.next();
+                            }
+                        }
                     }
                 }
-            } else if c == preferred_quote && formatted_value_nesting == 0 {
+            } else if !quotes.triple && c == preferred_quote && formatted_value_nesting == 0 {
                 // Escape the quote
                 output.push_str(&input[last_index..index]);
                 output.push('\\');
@@ -802,3 +835,136 @@ fn normalize_string(input: &str, quotes: StringQuotes, prefix: StringPrefix) ->
 
     normalized
 }
+
+#[derive(Copy, Clone, Debug, PartialEq, Eq)]
+enum UnicodeEscape {
+    /// A hex escape sequence of either 2 (`\x`), 4 (`\u`) or 8 (`\U`) hex characters.
+    Hex(usize),
+
+    /// An escaped unicode name (`\N{name}`)
+    CharacterName,
+}
+
+impl UnicodeEscape {
+    fn new(first: char, allow_unicode: bool) -> Option<UnicodeEscape> {
+        Some(match first {
+            'x' => UnicodeEscape::Hex(2),
+            'u' if allow_unicode => UnicodeEscape::Hex(4),
+            'U' if allow_unicode => UnicodeEscape::Hex(8),
+            'N' if allow_unicode => UnicodeEscape::CharacterName,
+            _ => return None,
+        })
+    }
+
+    /// Normalises `\u..`, `\U..`, `\x..` and `\N{..}` escape sequences to:
+    ///
+    /// * `\u`, `\U'` and `\x`: To use lower case for the characters `a-f`.
+    /// * `\N`: To use uppercase letters
+    fn normalize(self, input: &str) -> Option<Cow<str>> {
+        let mut normalised = String::new();
+
+        let len = match self {
+            UnicodeEscape::Hex(len) => {
+                // It's not a valid escape sequence if the input string has fewer characters
+                // left than required by the escape sequence.
+                if input.len() < len {
+                    return None;
+                }
+
+                for (index, c) in input.char_indices().take(len) {
+                    match c {
+                        '0'..='9' | 'a'..='f' => {
+                            if !normalised.is_empty() {
+                                normalised.push(c);
+                            }
+                        }
+                        'A'..='F' => {
+                            if normalised.is_empty() {
+                                normalised.reserve(len);
+                                normalised.push_str(&input[..index]);
+                                normalised.push(c.to_ascii_lowercase());
+                            } else {
+                                normalised.push(c.to_ascii_lowercase());
+                            }
+                        }
+                        _ => {
+                            // not a valid escape sequence
+                            return None;
+                        }
+                    }
+                }
+
+                len
+            }
+            UnicodeEscape::CharacterName => {
+                let mut char_indices = input.char_indices();
+
+                if !matches!(char_indices.next(), Some((_, '{'))) {
+                    return None;
+                }
+
+                loop {
+                    if let Some((index, c)) = char_indices.next() {
+                        match c {
+                            '}' => {
+                                if !normalised.is_empty() {
+                                    normalised.push('}');
+                                }
+
+                                // Name must be at least two characters long.
+                                if index < 3 {
+                                    return None;
+                                }
+
+                                break index + '}'.len_utf8();
+                            }
+                            '0'..='9' | 'A'..='Z' | ' ' | '-' => {
+                                if !normalised.is_empty() {
+                                    normalised.push(c);
+                                }
+                            }
+                            'a'..='z' => {
+                                if normalised.is_empty() {
+                                    normalised.reserve(c.len_utf8() + '}'.len_utf8());
+                                    normalised.push_str(&input[..index]);
+                                    normalised.push(c.to_ascii_uppercase());
+                                } else {
+                                    normalised.push(c.to_ascii_uppercase());
+                                }
+                            }
+                            _ => {
+                                // Seems like an invalid escape sequence, don't normalise it.
+                                return None;
+                            }
+                        }
+                    } else {
+                        // Unterminated escape sequence, dont' normalise it.
+                        return None;
+                    }
+                }
+            }
+        };
+
+        Some(if normalised.is_empty() {
+            Cow::Borrowed(&input[..len])
+        } else {
+            Cow::Owned(normalised)
+        })
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use crate::string::UnicodeEscape;
+    use std::borrow::Cow;
+
+    #[test]
+    fn normalize_32_escape() {
+        let escape_sequence = UnicodeEscape::new('U', true).unwrap();
+
+        assert_eq!(
+            Some(Cow::Owned("0001f60e".to_string())),
+            escape_sequence.normalize("0001F60E")
+        );
+    }
+}