Improve regex for xs:time and xs:dateTime; allow up to twelve decimal seconds, and prohibit the hour 24 and decimal seconds ending with 0

Author: tvdijen

src/XML/Assert/DateTimeTrait.php

@@ -30,6 +30,17 @@ trait DateTimeTrait
      * * ss is a two-integer-digit numeral that represents the whole seconds;
      * * '.' s+ (if present) represents the fractional seconds;
      * * zzzzzz (if present) represents the timezone (as described below).
+     *
+     * Except for trailing fractional zero digits in the seconds representation, '24:00:00' time representations,
+     * and timezone (for timezoned values), the mapping from literals to values is one-to-one.
+     * Where there is more than one possible representation, the canonical representation is as follows:
+
+     * The 2-digit numeral representing the hour must not be '24';
+     * The fractional second string, if present, must not end in '0';
+     * for timezoned values, the timezone must be represented with 'Z' (All timezoned dateTime values are UTC.).
+
+
+     * Note: we're restricting decimal seconds to 12, although strictly the standards allow an infite number.
      */
     private static string $datetime_regex = '/^
         -?
@@ -49,10 +60,10 @@ trait DateTimeTrait
                 (02-(0[1-9]|(1|2)[0-9]))
         )
         T
-        ([0-1][0-9]|2[0-4])
+        ([0-1][0-9]|2[0-3])
         :(0[0-9]|[1-5][0-9])
         :(0[0-9]|[1-5][0-9])
-        (\.[0-9]{0,6})?
+        (\.[0-9]{0,11}[1-9])?
         (
             [+-]([0-1][0-9]|2[0-4])
             :(0[0-9]|[1-5][0-9])

src/XML/Assert/TimeTrait.php

@@ -11,12 +11,35 @@
  */
 trait TimeTrait
 {
+    /**
+     * The ·lexical space· of time consists of finite-length sequences of characters of the form:
+     * hh ':' mm ':' ss ('.' s+)? (zzzzzz)?, where
+     *
+     * * hh is a two-digit numeral that represents the hour; '24' is permitted if the minutes and seconds represented
+     *   are zero, and the dateTime value so represented is the first instant of the following day
+     *   (the hour property of a dateTime object in the ·value space· cannot have a value greater than 23);
+     * * ':' is a separator between parts of the time-of-day portion;
+     * * the second mm is a two-digit numeral that represents the minute;
+     * * ss is a two-integer-digit numeral that represents the whole seconds;
+     * * '.' s+ (if present) represents the fractional seconds;
+     * * zzzzzz (if present) represents the timezone (as described below).
+     *
+     * Except for trailing fractional zero digits in the seconds representation, '24:00:00' time representations,
+     * and timezone (for timezoned values), the mapping from literals to values is one-to-one.
+     * Where there is more than one possible representation, the canonical representation is as follows:
+     *
+     * The 2-digit numeral representing the hour must not be '24';
+     * The fractional second string, if present, must not end in '0';
+     * for timezoned values, the timezone must be represented with 'Z' (All timezoned dateTime values are UTC.).
+     *
+     * Note: we're restricting decimal seconds to 12, although strictly the standards allow an infite number.
+     */
     private static string $time_regex = '/^
-        ([0-1][0-9]|2[0-4])
+        ([0-1][0-9]|2[0-3])
         :
         (0[0-9]|[1-5][0-9])
         :(0[0-9]|[1-5][0-9])
-        (\.[0-9]{0,6})?
+        (\.[0-9]{0,11}[1-9])?
         ([+-]([0-1][0-9]|2[0-4]):(0[0-9]|[1-5][0-9])|Z)?
         $/Dx';
 

tests/XML/Assert/DateTimeTest.php

@@ -48,7 +48,7 @@ public static function provideValidDateTime(): array
             'valid with negative value' => [true, '-2001-10-26T21:32:52'],
             'valid with subseconds' => [true, '2001-10-26T21:32:52.12679'],
             'valid with more than four digit year' => [true, '-22001-10-26T21:32:52+02:00'],
-            'valid with sub-seconds' => [true, '2001-10-26T21:32:52.12679'],
+            'valid with up to twelve sub-seconds' => [true, '2001-10-26T21:32:52.126798764382'],
         ];
     }
 
@@ -62,9 +62,12 @@ public static function provideInvalidDateTime(): array
             'missing time' => [false, '2001-10-26'],
             'missing second' => [false, '2001-10-26T21:32'],
             'hour out of range' => [false, '2001-10-26T25:32:52+02:00'],
+            'hour twenty-four' => [false, '2001-10-26T24:32:52+02:00'],
             'year 0000' => [false, '0000-10-26T25:32:52+02:00'],
             'prefixed zero' => [false, '02001-10-26T25:32:52+02:00'],
             'wrong format' => [false, '01-10-26T21:32'],
+            'too many sub-seconds' => [false, '2001-10-26T21:32:52.1267987643821'],
+            'sub-seconds ending with zero' => [false, '2001-10-26T21:32:52.12670'],
         ];
     }
 }

tests/XML/Assert/TimeTest.php

@@ -46,6 +46,7 @@ public static function provideValidTime(): array
             'valid time with Zulu timezone' => [true, '19:32:52Z'],
             'valid time with 00:00 timezone' => [true, '19:32:52+00:00'],
             'valid time with sub-seconds' =>  [true, '21:32:52.12679'],
+            'valid with up to twelve sub-seconds' => [true, '21:32:52.126798764382'],
         ];
     }
 
@@ -58,7 +59,10 @@ public static function provideInvalidTime(): array
         return [
             'invalid negative hour' => [false, '-10:00:00'],
             'invalid hour out of range' => [false, '25:25:10'],
+            'invalid hour twenty-four' => [false, '24:25:10'],
             'invalid invalid format' => [false, '1:20:10'],
+            'too many sub-seconds' => [false, '21:32:52.1267987643821'],
+            'sub-seconds ending with zero' => [false, '21:32:52.12670'],
         ];
     }
 }