Changeset 33207

Show
Ignore:
Timestamp:
23.06.2019 22:52:51 (3 weeks ago)
Author:
davidb
Message:

More careful pulling apart of metadata through plugins and classifiers

Files:
1 modified

Legend:

Unmodified
Added
Removed
  • main/trunk/model-sites-dev/heritage-nz/collect/pdf-reports/etc/collectionConfig.xml

    r33190 r33207  
    175175            <plugin name="MetadataCSVPlugin"> 
    176176              <option name="-process_exp" value="\/?PDF-BOUND.*\.csv$"/> 
    177               <option name="-metadata_value_separator" value="\s*\|\s*"/> 
     177              <option name="-metadata_value_separator" value="\s*(\||\x{2502}])\s*"/> 
    178178            </plugin> 
    179179            <plugin name="CSVPlugin"> 
     
    298298            <option name="-removeprefix" value="\&quot;|\'|\(|(\d+\s*)|(\d+\w*\s+and\s+\d+\w*)"/> --> 
    299299            <option name="-removeprefix" value=".*?(?=[A-Z][a-z])"/> 
     300<!-- 
    300301            <option name="-removesuffix" value="\):.*$"/> 
     302--> 
     303<!-- 
     304            <option name="-removesuffix" value="(?&lt;=^(?:Archaeological Assessment)|(?:Archaeological Authority)).*$"/> 
     305--> 
     306 
     307 
    301308        </classifier> 
    302309<!-- 
     
    390397        <classifier name="AZCompactList"> 
    391398          <option name="-metadata" value="SiteNo"/> 
     399          <option name="-sorttype" value="alphanumerical"/> 
     400<!-- 
     401          <option name="-sort" value="SiteNoOrdering"/> 
     402--> 
    392403          <option name="-buttonname" value="NZAA Site Number"/> 
    393404          <option name="-removesuffix" value="(-|/|,|\.| ).*$"/>