Skip to content

Commit e4fa5fc

Browse files
committed
Support markdown formatted codeblocks
1 parent 460d2a1 commit e4fa5fc

File tree

1 file changed

+2
-1
lines changed

1 file changed

+2
-1
lines changed

charabia/src/separators.rs

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -12,6 +12,7 @@
1212
/// - Zp Paragraph Separator
1313
/// - Zs Space Separator
1414
/// plus ". ", ", " and ។ល។" (៘ decomposition) to categorize them as hard separators
15+
/// and "`" to understand markdown formatted text
1516
#[rustfmt::skip]
1617
pub const DEFAULT_SEPARATORS: &[&str] = &[
1718
". ", ", ", "_", "‿", "⁀", "⁔", "︳", "︴", "﹍", "﹎", "﹏", "_", "-", "֊", "־", "᐀", "᠆", "‐", "‒", "–",
@@ -58,7 +59,7 @@ pub const DEFAULT_SEPARATORS: &[&str] = &[
5859
"𑪠", "𑪡", "𑪢", "𑱁", "𑱂", "𑱃", "𑱄", "𑱅", "𑱰", "𑱱", "𑻷", "𑻸", "𑿿", "𒑰", "𒑱", "𒑲", "𒑳", "𒑴", "𖩮",
5960
"𖩯", "𖫵", "𖬷", "𖬸", "𖬹", "𖬺", "𖬻", "𖭄", "𖺗", "𖺘", "𖺙", "𖺚", "𖿢", "𛲟", "𝪇", "𝪈", "𝪉", "𝪊", "𝪋",
6061
"𞥞", "𞥟", "\n", "\r", "\u{2029}", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ", " ",
61-
" ", " "
62+
" ", " ", "`"
6263
];
6364

6465
#[rustfmt::skip]

0 commit comments

Comments
 (0)