Skip to content

fix: do not break subsequent exclamation points or question marks in nlp/sentencize #5380

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 1 commit into from
Feb 22, 2025
Merged

fix: do not break subsequent exclamation points or question marks in nlp/sentencize #5380

Show file tree
Hide file tree
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.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion lib/node_modules/@stdlib/nlp/sentencize/lib/main.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,8 @@ function isEndOfSentence( tokens, i ) {
if (
( token === '!' || token === '?' ) &&
!RE_PREFIXES.test( tokens[ im1 ] ) &&
!RE_SUFFIXES.test( tokens[ ip1 ] )
!RE_SUFFIXES.test( tokens[ ip1 ] ) &&
( tokens[ ip1 ] !== '!' && tokens[ ip1 ] !== '?' )
) {
return true;
}
Expand Down
22 changes: 22 additions & 0 deletions lib/node_modules/@stdlib/nlp/sentencize/test/test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -289,6 +289,28 @@ tape( 'the function splits a string into an array of sentences (unfinished last
t.end();
});

tape( 'the function splits a string into an array of sentences (multiple punctuation marks)', function test( t ) {
var expected;
var actual;
var str;

str = 'HAPPY BIRTHDAY!!! Have an awesome day!';
expected = [ 'HAPPY BIRTHDAY!!!', 'Have an awesome day!' ];
actual = sentencize( str );
t.deepEqual( actual, expected, 'returns an array of sentences' );

str = 'What?? How can that be??';
expected = [ 'What??', 'How can that be??' ];
actual = sentencize( str );
t.deepEqual( actual, expected, 'returns an array of sentences' );

str = 'How dare you!?!';
expected = [ 'How dare you!?!' ];
actual = sentencize( str );
t.deepEqual( actual, expected, 'returns an array of sentences' );
t.end();
});

tape( 'the function returns an empty array if provided an empty string', function test( t ) {
var out = sentencize( '' );
t.equal( isArray( out ), true, 'returns an array' );
Expand Down
Loading