|
From: <rga...@us...> - 2002-10-22 22:11:00
|
Update of /cvsroot/csms/csms-core/src/test/resources/conf
In directory usw-pr-cvs1:/tmp/cvs-serv16794
Modified Files:
footballEvents.xml
Log Message:
Fixed problems with Bookings and Substitutions
Index: footballEvents.xml
===================================================================
RCS file: /cvsroot/csms/csms-core/src/test/resources/conf/footballEvents.xml,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** footballEvents.xml 18 Oct 2002 15:05:45 -0000 1.1
--- footballEvents.xml 22 Oct 2002 22:10:56 -0000 1.2
***************
*** 16,19 ****
--- 16,26 ----
-->
+ <!--
+ Template Regular Expressions in common use:
+
+ Skip whole commentary sections: [a-zA-Z\s\(\)\.,\-:]
+ Player Names: (?:(?:[Mac|Mc|A-Z][a-z]*\s)(?!\d)){1,3}
+ -->
+
<events type="match">
<!-- Get the data for the UID of this match -->
***************
*** 39,43 ****
<part name="homeTeam">[A-Z][a-zA-Z\s]*[\s]*</part>
<part name="homeScore">\d[\s]*</part>
! <unwantedPart>-[\s]*</unwantedPart>
<part name="awayScore">\d</part>
<unwantedPart>[\s]*</unwantedPart>
--- 46,50 ----
<part name="homeTeam">[A-Z][a-zA-Z\s]*[\s]*</part>
<part name="homeScore">\d[\s]*</part>
! <unwantedPart>-[\s]*</unwantedPart>b
<part name="awayScore">\d</part>
<unwantedPart>[\s]*</unwantedPart>
***************
*** 88,92 ****
<event type="booking">
! <!-- FIXME: This pattern matches bookings that do not have lines of commentary after the time and booking heading, but it fails if there are commentary lines -->
<pattern>
<sourceType>BBC Text Commentary</sourceType>
--- 95,107 ----
<event type="booking">
! <duplicateDetection>
! <part name="normalTimeMinutes"/>
! <part name="normalTimeSeconds"/>
! <part name="injuryTimeMinutes"/>
! <part name="injuryTimeSeconds"/>
! <part name="player"/>
! </duplicateDetection>
!
! <!-- Get a booking that is the first sentence in the commentary snippet -->
<pattern>
<sourceType>BBC Text Commentary</sourceType>
***************
*** 99,106 ****
<part name="injuryTimeSeconds">\d?\d?</part>
<unwantedPart>\)?</unwantedPart>
! <unwantedPart>\s*Booking\s*</unwantedPart>
! <!-- this makes the system lock up <unwantedPart>(?:(?:[^\.]*.)(?![^.][Bb]ooked\.))*</unwantedPart> -->
<part name="player">(?:(?:[Mac|Mc|A-Z][A-Za-z']*\s)(?!\))){1,3}</part>
! <unwantedPart>[^)]*\)\s*[Bb]ooked.</unwantedPart>
</pattern>
</event>
--- 114,175 ----
<part name="injuryTimeSeconds">\d?\d?</part>
<unwantedPart>\)?</unwantedPart>
! <unwantedPart>\s*Booking\s*</unwantedPart>
<part name="player">(?:(?:[Mac|Mc|A-Z][A-Za-z']*\s)(?!\))){1,3}</part>
! <unwantedPart>[^)]*\)\s*[Bb]ooked\sfor\s</unwantedPart>
! <part name="reason">[^\.]*</part>
! </pattern>
!
! <!-- Get a booking that is the second sentence in the commentary snippet -->
! <pattern>
! <sourceType>BBC Text Commentary</sourceType>
! <part name="normalTimeMinutes">\d\d?</part>
! <unwantedPart>:</unwantedPart>
! <part name="normalTimeSeconds">\d\d</part>
! <unwantedPart>\s*\(?</unwantedPart>
! <part name="injuryTimeMinutes">\d?\d?</part>
! <unwantedPart>:?</unwantedPart>
! <part name="injuryTimeSeconds">\d?\d?</part>
! <unwantedPart>\)?</unwantedPart>
! <unwantedPart>[^\.]*\.\s*</unwantedPart>
! <part name="player">(?:(?:[Mac|Mc|A-Z][A-Za-z']*\s)(?!\))){1,3}</part>
! <unwantedPart>[^)]*\)\s*[Bb]ooked\sfor\s</unwantedPart>
! <part name="reason">[^\.]*</part>
! </pattern>
!
! <!-- Get a booking that is the third sentence in the commentary snippet -->
! <pattern>
! <sourceType>BBC Text Commentary</sourceType>
! <part name="normalTimeMinutes">\d\d?</part>
! <unwantedPart>:</unwantedPart>
! <part name="normalTimeSeconds">\d\d</part>
! <unwantedPart>\s*\(?</unwantedPart>
! <part name="injuryTimeMinutes">\d?\d?</part>
! <unwantedPart>:?</unwantedPart>
! <part name="injuryTimeSeconds">\d?\d?</part>
! <unwantedPart>\)?</unwantedPart>
! <unwantedPart>[^\.]*\.\s*</unwantedPart>
! <unwantedPart>[^\.]*\.\s*</unwantedPart>
! <part name="player">(?:(?:[Mac|Mc|A-Z][A-Za-z']*\s)(?!\))){1,3}</part>
! <unwantedPart>[^)]*\)\s*[Bb]ooked\sfor\s</unwantedPart>
! <part name="reason">[^\.]*</part>
! </pattern>
!
! <!-- Get a booking that is the fourth sentence in the commentary snippet -->
! <pattern>
! <sourceType>BBC Text Commentary</sourceType>
! <part name="normalTimeMinutes">\d\d?</part>
! <unwantedPart>:</unwantedPart>
! <part name="normalTimeSeconds">\d\d</part>
! <unwantedPart>\s*\(?</unwantedPart>
! <part name="injuryTimeMinutes">\d?\d?</part>
! <unwantedPart>:?</unwantedPart>
! <part name="injuryTimeSeconds">\d?\d?</part>
! <unwantedPart>\)?</unwantedPart>
! <unwantedPart>[^\.]*\.\s*</unwantedPart>
! <unwantedPart>[^\.]*\.\s*</unwantedPart>
! <unwantedPart>[^\.]*\.\s*</unwantedPart>
! <part name="player">(?:(?:[Mac|Mc|A-Z][A-Za-z']*\s)(?!\))){1,3}</part>
! <unwantedPart>[^)]*\)\s*[Bb]ooked\sfor\s</unwantedPart>
! <part name="reason">[^\.]*</part>
</pattern>
</event>
***************
*** 134,138 ****
<part name="injuryTimeSeconds">\d?\d?</part>
<unwantedPart>\)?</unwantedPart>
! <unwantedPart>[a-zA-Z]+\s?[a-zA-Z]*\s?[Ss]ubstitution\s?:\s</unwantedPart>
<part name="playerOff">(?:(?:[Mac|Mc|A-Z][a-z]*\s)){1,3}</part>
<unwantedPart>replaced\sby\s</unwantedPart>
--- 203,207 ----
<part name="injuryTimeSeconds">\d?\d?</part>
<unwantedPart>\)?</unwantedPart>
! <unwantedPart>[a-zA-Z\s\(\)\.,\-]*[Ss]ubstitution\s?:\s?</unwantedPart>
<part name="playerOff">(?:(?:[Mac|Mc|A-Z][a-z]*\s)){1,3}</part>
<unwantedPart>replaced\sby\s</unwantedPart>
***************
*** 154,160 ****
<part name="injuryTimeSeconds">\d?\d?</part>
<unwantedPart>\)?</unwantedPart>
! <unwantedPart>[a-zA-Z\s]*:[a-zA-Z\s]*\([a-zA-Z\)]*\.\s?</unwantedPart>
! <unwantedPart>[a-zA-Z]+\s?[a-zA-Z]*\s?[Ss]ubstitution\s?:\s</unwantedPart>
<part name="playerOff">(?:(?:[Mac|Mc|A-Z][a-z]*\s)){1,3}</part>
<unwantedPart>replaced\sby\s</unwantedPart>
--- 223,229 ----
<part name="injuryTimeSeconds">\d?\d?</part>
<unwantedPart>\)?</unwantedPart>
! <unwantedPart>[a-zA-Z\s\(\)\.,\-]*[Ss]ubstitution\s?:\s?</unwantedPart>
! <unwantedPart>[a-zA-Z\s\(\)\.,\-]*[Ss]ubstitution\s?:\s</unwantedPart>
<part name="playerOff">(?:(?:[Mac|Mc|A-Z][a-z]*\s)){1,3}</part>
<unwantedPart>replaced\sby\s</unwantedPart>
|