Jun 26, 2024 · Jun 8, 2024
diff --git a/scripts/unicode.py b/scripts/unicode.py

    #[inline]
    fn is_alphabetic(c: char) -> bool {
        match c {
            'a' ..= 'z' | 'A' ..= 'Z' => true,
            c if c > '\x7f' => super::derived_property::Alphabetic(c),
            _ => false,
        if super::UNICODE_VERSION_U8 == char::UNICODE_VERSION {
            c.is_alphabetic()
        } else {
            match c {
                'a' ..= 'z' | 'A' ..= 'Z' => true,
                c if c > '\\x7f' => super::derived_property::Alphabetic(c),
                _ => false,
            }
        }
    }

    #[inline]
    fn is_numeric(c: char) -> bool {
        match c {
            '0' ..= '9' => true,
            c if c > '\x7f' => super::general_category::N(c),
            _ => false,
        if super::UNICODE_VERSION_U8 == char::UNICODE_VERSION {
            c.is_numeric()
        } else {
            match c {
                '0' ..= '9' => true,
                c if c > '\\x7f' => super::general_category::N(c),
                _ => false,
            }
        }
    }

 /// The version of [Unicode](http://www.unicode.org/)
 /// that this version of unicode-segmentation is based on.
 pub const UNICODE_VERSION: (u64, u64, u64) = (%s, %s, %s);
 """ % UNICODE_VERSION)

        rf.write("""
 const UNICODE_VERSION_U8: (u8, u8, u8) = (%s, %s, %s);
 """ % UNICODE_VERSION)

        # download and parse all the data
diff --git a/src/tables.rs b/src/tables.rs
 /// that this version of unicode-segmentation is based on.
 pub const UNICODE_VERSION: (u64, u64, u64) = (15, 1, 0);

 const UNICODE_VERSION_U8: (u8, u8, u8) = (15, 1, 0);

 pub mod util {
    #[inline]
    pub fn bsearch_range_table(c: char, r: &[(char,char)]) -> bool {

    #[inline]
    fn is_alphabetic(c: char) -> bool {
        match c {
            'a' ..= 'z' | 'A' ..= 'Z' => true,
            c if c > '' => super::derived_property::Alphabetic(c),
            _ => false,
        if super::UNICODE_VERSION_U8 == char::UNICODE_VERSION {
            c.is_alphabetic()
        } else {
            match c {
                'a' ..= 'z' | 'A' ..= 'Z' => true,
                c if c > '\x7f' => super::derived_property::Alphabetic(c),
                _ => false,
            }
        }
    }

    #[inline]
    fn is_numeric(c: char) -> bool {
        match c {
            '0' ..= '9' => true,
            c if c > '' => super::general_category::N(c),
            _ => false,
        if super::UNICODE_VERSION_U8 == char::UNICODE_VERSION {
            c.is_numeric()
        } else {
            match c {
                '0' ..= '9' => true,
                c if c > '\x7f' => super::general_category::N(c),
                _ => false,
            }
        }
    }
Original file line number	Diff line number	Diff line change
Expand Up		@@ -232,19 +232,27 @@ def emit_util_mod(f):

		#[inline]
		fn is_alphabetic(c: char) -> bool {
		match c {
		'a' ..= 'z' \| 'A' ..= 'Z' => true,
		c if c > '\x7f' => super::derived_property::Alphabetic(c),
		_ => false,
		if super::UNICODE_VERSION_U8 == char::UNICODE_VERSION {
		c.is_alphabetic()
		} else {
		match c {
		'a' ..= 'z' \| 'A' ..= 'Z' => true,
		c if c > '\\x7f' => super::derived_property::Alphabetic(c),
		_ => false,
		}
		}
		}

		#[inline]
		fn is_numeric(c: char) -> bool {
		match c {
		'0' ..= '9' => true,
		c if c > '\x7f' => super::general_category::N(c),
		_ => false,
		if super::UNICODE_VERSION_U8 == char::UNICODE_VERSION {
		c.is_numeric()
		} else {
		match c {
		'0' ..= '9' => true,
		c if c > '\\x7f' => super::general_category::N(c),
		_ => false,
		}
		}
		}

Expand DownExpand Up		@@ -388,6 +396,10 @@ def emit_break_module(f, break_table, break_cats, name):
		/// The version of [Unicode](http://www.unicode.org/)
		/// that this version of unicode-segmentation is based on.
		pub const UNICODE_VERSION: (u64, u64, u64) = (%s, %s, %s);
		""" % UNICODE_VERSION)

		rf.write("""
		const UNICODE_VERSION_U8: (u8, u8, u8) = (%s, %s, %s);
		""" % UNICODE_VERSION)

		# download and parse all the data
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -16,6 +16,8 @@
		/// that this version of unicode-segmentation is based on.
		pub const UNICODE_VERSION: (u64, u64, u64) = (15, 1, 0);

		const UNICODE_VERSION_U8: (u8, u8, u8) = (15, 1, 0);

		pub mod util {
		#[inline]
		pub fn bsearch_range_table(c: char, r: &[(char,char)]) -> bool {
Expand All		@@ -29,19 +31,27 @@ pub mod util {

		#[inline]
		fn is_alphabetic(c: char) -> bool {
		match c {
		'a' ..= 'z' \| 'A' ..= 'Z' => true,
		c if c > '' => super::derived_property::Alphabetic(c),
		_ => false,
		if super::UNICODE_VERSION_U8 == char::UNICODE_VERSION {
		c.is_alphabetic()
		} else {
		match c {
		'a' ..= 'z' \| 'A' ..= 'Z' => true,
		c if c > '\x7f' => super::derived_property::Alphabetic(c),
		_ => false,
		}
		}
		}

		#[inline]
		fn is_numeric(c: char) -> bool {
		match c {
		'0' ..= '9' => true,
		c if c > '' => super::general_category::N(c),
		_ => false,
		if super::UNICODE_VERSION_U8 == char::UNICODE_VERSION {
		c.is_numeric()
		} else {
		match c {
		'0' ..= '9' => true,
		c if c > '\x7f' => super::general_category::N(c),
		_ => false,
		}
		}
		}

Expand Down