[MediaWiki-commits] [Gerrit] mediawiki...Wikispeech[master]: Don't create empty elements
jenkins-bot has submitted this change and it was merged. (
https://gerrit.wikimedia.org/r/345522 )
Change subject: Don't create empty elements
..
Don't create empty elements
These were created when a `CleanedText` only contained
whitespaces. The whitespaces were removed, but a `CleanedText` (with
the empty string) was created.
Bug: T159669
Change-Id: I2bb150b2e69357cd53e587344f41183da0b27bc1
---
M includes/Segmenter.php
M tests/phpunit/SegmenterTest.php
2 files changed, 34 insertions(+), 19 deletions(-)
Approvals:
Lokal Profil: Looks good to me, approved
jenkins-bot: Verified
diff --git a/includes/Segmenter.php b/includes/Segmenter.php
index ea98d09..9dcb75f 100644
--- a/includes/Segmenter.php
+++ b/includes/Segmenter.php
@@ -135,25 +135,28 @@
$startOffset,
$endOffset - $startOffset + 1
);
- $sentenceText = new CleanedText(
- $sentence,
- $text->path
- );
- array_push( $currentSegment['content'], $sentenceText );
- if ( $currentSegment['startOffset'] === null ) {
- // Record the start offset if this is the first text
added
- // to the segment.
- $currentSegment['startOffset'] = $startOffset;
- }
- $currentSegment['endOffset'] = $endOffset;
- if ( $ended ) {
- array_push( $segments, $currentSegment );
- // Create a fresh segment to add following text to.
- $currentSegment = [
- 'content' => [],
- 'startOffset' => null,
- 'endOffset' => null
- ];
+ if ( $sentence !== '' ) {
+ // Don't add `CleanedText`s with the empty string.
+ $sentenceText = new CleanedText(
+ $sentence,
+ $text->path
+ );
+ array_push( $currentSegment['content'], $sentenceText );
+ if ( $currentSegment['startOffset'] === null ) {
+ // Record the start offset if this is the first
text
+ // added to the segment.
+ $currentSegment['startOffset'] = $startOffset;
+ }
+ $currentSegment['endOffset'] = $endOffset;
+ if ( $ended ) {
+ array_push( $segments, $currentSegment );
+ // Create a fresh segment to add following text
to.
+ $currentSegment = [
+ 'content' => [],
+ 'startOffset' => null,
+ 'endOffset' => null
+ ];
+ }
}
return $endOffset;
}
diff --git a/tests/phpunit/SegmenterTest.php b/tests/phpunit/SegmenterTest.php
index a7fd816..155fa18 100644
--- a/tests/phpunit/SegmenterTest.php
+++ b/tests/phpunit/SegmenterTest.php
@@ -192,6 +192,18 @@
);
}
+ public function testRemoveTextWithOnlyWhitespacesOutsideSegments() {
+ $cleanedContent = [
+ new CleanedText( ' ' ),
+ new CleanedText( 'Sentence 1.' )
+ ];
+ $segments = Segmenter::segmentSentences( $cleanedContent );
+ $this->assertEquals(
+ 'Sentence 1.',
+ $segments[0]['content'][0]->string
+ );
+ }
+
public function testRemoveLeadingAndTrailingWhitespaces() {
$cleanedContent = [ new CleanedText( ' Sentence. ' ) ];
$segments = Segmenter::segmentSentences( $cleanedContent );
--
To view, visit https://gerrit.wikimedia.org/r/345522
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings
Gerrit-MessageType: merged
Gerrit-Change-Id: I2bb150b2e69357cd53e587344f41183da0b27bc1
Gerrit-PatchSet: 1
Gerrit-Project: mediawiki/extensions/Wikispeech
Gerrit-Branch: master
Gerrit-Owner: Sebastian Berlin (WMSE)
Gerrit-Reviewer: Lokal Profil
Gerrit-Reviewer: jenkins-bot <>
___
MediaWiki-commits mailing list
MediaWiki-commits@lists.wikimedia.org
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits
[MediaWiki-commits] [Gerrit] mediawiki...Wikispeech[master]: Don't create empty elements
Sebastian Berlin (WMSE) has uploaded a new change for review. (
https://gerrit.wikimedia.org/r/345522 )
Change subject: Don't create empty elements
..
Don't create empty elements
These were created when a `CleanedText` only contained
whitespaces. The whitespaces were removed, but a `CleanedText` (with
the empty string) was created.
Bug: T159669
Change-Id: I2bb150b2e69357cd53e587344f41183da0b27bc1
---
M includes/Segmenter.php
M tests/phpunit/SegmenterTest.php
2 files changed, 34 insertions(+), 19 deletions(-)
git pull ssh://gerrit.wikimedia.org:29418/mediawiki/extensions/Wikispeech
refs/changes/22/345522/1
diff --git a/includes/Segmenter.php b/includes/Segmenter.php
index ea98d09..9dcb75f 100644
--- a/includes/Segmenter.php
+++ b/includes/Segmenter.php
@@ -135,25 +135,28 @@
$startOffset,
$endOffset - $startOffset + 1
);
- $sentenceText = new CleanedText(
- $sentence,
- $text->path
- );
- array_push( $currentSegment['content'], $sentenceText );
- if ( $currentSegment['startOffset'] === null ) {
- // Record the start offset if this is the first text
added
- // to the segment.
- $currentSegment['startOffset'] = $startOffset;
- }
- $currentSegment['endOffset'] = $endOffset;
- if ( $ended ) {
- array_push( $segments, $currentSegment );
- // Create a fresh segment to add following text to.
- $currentSegment = [
- 'content' => [],
- 'startOffset' => null,
- 'endOffset' => null
- ];
+ if ( $sentence !== '' ) {
+ // Don't add `CleanedText`s with the empty string.
+ $sentenceText = new CleanedText(
+ $sentence,
+ $text->path
+ );
+ array_push( $currentSegment['content'], $sentenceText );
+ if ( $currentSegment['startOffset'] === null ) {
+ // Record the start offset if this is the first
text
+ // added to the segment.
+ $currentSegment['startOffset'] = $startOffset;
+ }
+ $currentSegment['endOffset'] = $endOffset;
+ if ( $ended ) {
+ array_push( $segments, $currentSegment );
+ // Create a fresh segment to add following text
to.
+ $currentSegment = [
+ 'content' => [],
+ 'startOffset' => null,
+ 'endOffset' => null
+ ];
+ }
}
return $endOffset;
}
diff --git a/tests/phpunit/SegmenterTest.php b/tests/phpunit/SegmenterTest.php
index a7fd816..155fa18 100644
--- a/tests/phpunit/SegmenterTest.php
+++ b/tests/phpunit/SegmenterTest.php
@@ -192,6 +192,18 @@
);
}
+ public function testRemoveTextWithOnlyWhitespacesOutsideSegments() {
+ $cleanedContent = [
+ new CleanedText( ' ' ),
+ new CleanedText( 'Sentence 1.' )
+ ];
+ $segments = Segmenter::segmentSentences( $cleanedContent );
+ $this->assertEquals(
+ 'Sentence 1.',
+ $segments[0]['content'][0]->string
+ );
+ }
+
public function testRemoveLeadingAndTrailingWhitespaces() {
$cleanedContent = [ new CleanedText( ' Sentence. ' ) ];
$segments = Segmenter::segmentSentences( $cleanedContent );
--
To view, visit https://gerrit.wikimedia.org/r/345522
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings
Gerrit-MessageType: newchange
Gerrit-Change-Id: I2bb150b2e69357cd53e587344f41183da0b27bc1
Gerrit-PatchSet: 1
Gerrit-Project: mediawiki/extensions/Wikispeech
Gerrit-Branch: master
Gerrit-Owner: Sebastian Berlin (WMSE)
___
MediaWiki-commits mailing list
MediaWiki-commits@lists.wikimedia.org
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits
