jenkins-bot has submitted this change and it was merged.
Change subject: Support 5+ digit years in DateTimeParser
......................................................................
Support 5+ digit years in DateTimeParser
Bug: 62648
Change-Id: I03b799542a8d6f334116d6a56d34ff9bbec88f40
---
M lib/includes/parsers/DateTimeParser.php
M lib/tests/phpunit/parsers/DateTimeParserTest.php
2 files changed, 43 insertions(+), 5 deletions(-)
Approvals:
WikidataJenkins: Verified
Thiemo Mättig (WMDE): Looks good to me, approved
jenkins-bot: Verified
diff --git a/lib/includes/parsers/DateTimeParser.php
b/lib/includes/parsers/DateTimeParser.php
index 85b26bc..8c408fa 100644
--- a/lib/includes/parsers/DateTimeParser.php
+++ b/lib/includes/parsers/DateTimeParser.php
@@ -34,9 +34,10 @@
}
/**
- * Parses the provided string and returns the result.
+ * Parses the provided string
*
- * @param string $value
+ * @param string $value in a format as specified by the PHP DateTime
object
+ * there are exceptions as we can handel 5+ digit dates
*
* @throws ParseException
* @return TimeValue
@@ -44,6 +45,10 @@
protected function stringParse( $value ) {
$calendarModelParser = new CalendarModelParser();
$options = $this->getOptions();
+
+ //Place to put large years when they are found
+ $largeYear = null;
+
try{
$value = $this->getValueWithFixedYearLengths(
$this->getValueWithFixedSeparators(
@@ -55,10 +60,21 @@
)
);
+ //PHP's DateTime object also cant handel larger than 4
digit years
+ //e.g. 1 June 202020
+ if( preg_match( '/^(.*[^\d]|)(\d{5,})(.*|)$/', $value,
$matches ) ) {
+ $value = $matches[1] . substr( $matches[2], -4
) . $matches[3];
+ $largeYear = $matches[2];
+ }
+
//Parse using the DateTime object (this will allow us
to format the date in a nicer way)
//TODO try to match and remove BCE etc. before putting
the value into the DateTime object to get - dates!
$dateTime = new DateTime( $value );
- $timeString = '+' . $dateTime->format( 'Y-m-d\TH:i:s\Z'
);
+ if( $largeYear === null ) {
+ $timeString = '+' . $dateTime->format(
'Y-m-d\TH:i:s\Z' );
+ } else {
+ $timeString = '+' . $largeYear .
$dateTime->format( '-m-d\TH:i:s\Z' );
+ }
//Pass the reformatted string into a base parser that
parses this +/-Y-m-d\TH:i:s\Z format with a precision
$valueParser = new \ValueParsers\TimeParser(
$calendarModelParser, $options );
@@ -114,4 +130,4 @@
return $value;
}
-}
\ No newline at end of file
+}
diff --git a/lib/tests/phpunit/parsers/DateTimeParserTest.php
b/lib/tests/phpunit/parsers/DateTimeParserTest.php
index de40bec..c9e5912 100644
--- a/lib/tests/phpunit/parsers/DateTimeParserTest.php
+++ b/lib/tests/phpunit/parsers/DateTimeParserTest.php
@@ -84,6 +84,10 @@
array( '+0000000000000055-01-09T00:00:00Z', 0 ,
0 , 0 , TimeValue::PRECISION_DAY , TimeFormatter::CALENDAR_GREGORIAN ),
'555-01-09' =>
array( '+0000000000000555-01-09T00:00:00Z', 0 ,
0 , 0 , TimeValue::PRECISION_DAY , TimeFormatter::CALENDAR_GREGORIAN ),
+ '33300-1-1' =>
+ array( '+0000000000033300-01-01T00:00:00Z', 0 ,
0 , 0 , TimeValue::PRECISION_DAY , TimeFormatter::CALENDAR_GREGORIAN ),
+ '3330002-1-1' =>
+ array( '+0000000003330002-01-01T00:00:00Z', 0 ,
0 , 0 , TimeValue::PRECISION_DAY , TimeFormatter::CALENDAR_GREGORIAN ),
//Less than 4 digit years
'10/10/10' =>
@@ -104,6 +108,25 @@
array( '+0000000000000111-07-04T00:00:00Z', 0 ,
0 , 0 , TimeValue::PRECISION_DAY , TimeFormatter::CALENDAR_GREGORIAN ),
'4th July 1' =>
array( '+0000000000000001-07-04T00:00:00Z', 0 ,
0 , 0 , TimeValue::PRECISION_DAY , TimeFormatter::CALENDAR_GREGORIAN ),
+
+ //More than 4 digit years
+ '4th July 10000' =>
+ array( '+0000000000010000-07-04T00:00:00Z', 0 ,
0 , 0 , TimeValue::PRECISION_DAY , TimeFormatter::CALENDAR_GREGORIAN ),
+ '10/10/22000' =>
+ array( '+0000000000022000-10-10T00:00:00Z', 0 ,
0 , 0 , TimeValue::PRECISION_DAY , TimeFormatter::CALENDAR_GREGORIAN ),
+ '1-1-33300' =>
+ array( '+0000000000033300-01-01T00:00:00Z', 0 ,
0 , 0 , TimeValue::PRECISION_DAY , TimeFormatter::CALENDAR_GREGORIAN ),
+ '4th July 7214614279199781' =>
+ array( '+7214614279199781-07-04T00:00:00Z', 0 ,
0 , 0 , TimeValue::PRECISION_DAY , TimeFormatter::CALENDAR_GREGORIAN ),
+
+ //Testing Leap Year stuff
+ '10000-02-29' =>
+ array( '+0000000000010000-02-29T00:00:00Z', 0 ,
0 , 0 , TimeValue::PRECISION_DAY , TimeFormatter::CALENDAR_GREGORIAN ),
+ '10100-02-29' =>
+ array( '+0000000000010100-03-01T00:00:00Z', 0 ,
0 , 0 , TimeValue::PRECISION_DAY , TimeFormatter::CALENDAR_GREGORIAN ),
+ '10400-02-29' =>
+ array( '+0000000000010400-02-29T00:00:00Z', 0 ,
0 , 0 , TimeValue::PRECISION_DAY , TimeFormatter::CALENDAR_GREGORIAN ),
+
);
@@ -126,7 +149,6 @@
'Jann 2014',
// Not within the scope of this parser
- '1 July 20000', // The DateTime object cant parse years
with more than 4 digits
'100BC', // The DateTime object cant parse BC years
);
--
To view, visit https://gerrit.wikimedia.org/r/119040
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings
Gerrit-MessageType: merged
Gerrit-Change-Id: I03b799542a8d6f334116d6a56d34ff9bbec88f40
Gerrit-PatchSet: 8
Gerrit-Project: mediawiki/extensions/Wikibase
Gerrit-Branch: master
Gerrit-Owner: Addshore <addshorew...@gmail.com>
Gerrit-Reviewer: Addshore <addshorew...@gmail.com>
Gerrit-Reviewer: Adrian Lang <adrian.l...@wikimedia.de>
Gerrit-Reviewer: Aude <aude.w...@gmail.com>
Gerrit-Reviewer: Daniel Kinzler <daniel.kinz...@wikimedia.de>
Gerrit-Reviewer: Jeroen De Dauw <jeroended...@gmail.com>
Gerrit-Reviewer: Thiemo Mättig (WMDE) <thiemo.maet...@wikimedia.de>
Gerrit-Reviewer: Tobias Gritschacher <tobias.gritschac...@wikimedia.de>
Gerrit-Reviewer: WikidataJenkins <wikidata-servi...@wikimedia.de>
Gerrit-Reviewer: jenkins-bot <>
_______________________________________________
MediaWiki-commits mailing list
MediaWiki-commits@lists.wikimedia.org
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits
