Ignore:
Timestamp:
Sep 26, 2011, 12:44:15 PM (10 years ago)
Author:
Nicklas Nordborg
Message:

Fixes #1623: Create reporter importer for GTF files

File:
1 edited

Legend:

Unmodified
Added
Removed
  • trunk/data/plugin_configfile.xml

    r4509 r5759  
    925925    </parameter>
    926926  </configuration>
     927  <configuration pluginClassName="net.sf.basedb.plugins.gtf.GtfReporterImporter">
     928    <configname>gene_id (no prefix)</configname>
     929    <description>A configuration that uses the gene_id (no prefix) instead of the transcript_id as reporter id.</description>
     930    <parameter>
     931      <name>trimQuotes</name>
     932      <label>Remove quotes</label>
     933      <description>If true quotes (" or ') around data value will be removed.</description>
     934      <class>java.lang.Boolean</class>
     935      <value>true</value>
     936    </parameter>
     937    <parameter>
     938      <name>dataHeaderRegexp</name>
     939      <label>Data header</label>
     940      <description>A regular expression that matches the header line just before the data begins. For example: Block\tRow\tColumn.*</description>
     941      <class>java.lang.String</class>
     942      <value>&lt;seqname&gt;\t.*&lt;gene_id&gt;.*</value>
     943    </parameter>
     944    <parameter>
     945      <name>reporterIdColumnMapping</name>
     946      <label>External ID</label>
     947      <description>Mapping that picks the reporter's external ID from the data columns. For example: \ID\</description>
     948      <class>java.lang.String</class>
     949      <value>\gene_id\</value>
     950    </parameter>
     951    <parameter>
     952      <name>minDataColumns</name>
     953      <label>Min data columns</label>
     954      <description>The minimum number of columns for a line to be counted as a data line.</description>
     955      <class>java.lang.Integer</class>
     956      <value>4</value>
     957    </parameter>
     958    <parameter>
     959      <name>complexExpressions</name>
     960      <label>Complex column mappings</label>
     961      <description>disallow = Only allow simple mappings that are constant value or pick the value from one column only, for example, '1.6' or '\Row\'
     962allow = Allow expression and complex mappings, for example, '\Row\, \Column\' or '=2*col('radius')'</description>
     963      <class>java.lang.String</class>
     964      <value>disallow</value>
     965    </parameter>
     966    <parameter>
     967      <name>charset</name>
     968      <label>Character set</label>
     969      <description>The character set to use when reading the file. This setting overrides the character set specified by the file. If neither this parameter nor the file specifies a character set, the system default is used (ISO-8859-1).</description>
     970      <class>java.lang.String</class>
     971      <value>ISO-8859-1</value>
     972    </parameter>
     973    <parameter>
     974      <name>nameColumnMapping</name>
     975      <label>Name</label>
     976      <description>Mapping that picks the reporter's name from the data columns. For example: \Name\</description>
     977      <class>java.lang.String</class>
     978      <value>\gene_id\</value>
     979    </parameter>
     980    <parameter>
     981      <name>dataSplitterRegexp</name>
     982      <label>Data splitter</label>
     983      <description>A regular expression that splits each data line into individual columns. For example, split on tabs: \t</description>
     984      <class>java.lang.String</class>
     985      <value>\t</value>
     986    </parameter>
     987    <parameter>
     988      <name>decimalSeparator</name>
     989      <label>Decimal separator</label>
     990      <description>The decimal separator used in numeric values, if not specified dot is assumed.</description>
     991      <class>java.lang.String</class>
     992      <value>dot</value>
     993    </parameter>
     994  </configuration>
     995  <configuration pluginClassName="net.sf.basedb.plugins.gtf.GtfReporterImporter">
     996    <configname>transcript_id (no prefix)</configname>
     997    <description>A configuration that uses the transcript_id (no prefix) as reporter id.</description>
     998    <parameter>
     999      <name>trimQuotes</name>
     1000      <label>Remove quotes</label>
     1001      <description>If true quotes (" or ') around data value will be removed.</description>
     1002      <class>java.lang.Boolean</class>
     1003      <value>true</value>
     1004    </parameter>
     1005    <parameter>
     1006      <name>dataHeaderRegexp</name>
     1007      <label>Data header</label>
     1008      <description>A regular expression that matches the header line just before the data begins. For example: Block\tRow\tColumn.*</description>
     1009      <class>java.lang.String</class>
     1010      <value>&lt;seqname&gt;\t.*&lt;transcript_id&gt;.*</value>
     1011    </parameter>
     1012    <parameter>
     1013      <name>reporterIdColumnMapping</name>
     1014      <label>External ID</label>
     1015      <description>Mapping that picks the reporter's external ID from the data columns. For example: \ID\</description>
     1016      <class>java.lang.String</class>
     1017      <value>\transcript_id\</value>
     1018    </parameter>
     1019    <parameter>
     1020      <name>minDataColumns</name>
     1021      <label>Min data columns</label>
     1022      <description>The minimum number of columns for a line to be counted as a data line.</description>
     1023      <class>java.lang.Integer</class>
     1024      <value>4</value>
     1025    </parameter>
     1026    <parameter>
     1027      <name>complexExpressions</name>
     1028      <label>Complex column mappings</label>
     1029      <description>disallow = Only allow simple mappings that are constant value or pick the value from one column only, for example, '1.6' or '\Row\'
     1030allow = Allow expression and complex mappings, for example, '\Row\, \Column\' or '=2*col('radius')'</description>
     1031      <class>java.lang.String</class>
     1032      <value>disallow</value>
     1033    </parameter>
     1034    <parameter>
     1035      <name>charset</name>
     1036      <label>Character set</label>
     1037      <description>The character set to use when reading the file. This setting overrides the character set specified by the file. If neither this parameter nor the file specifies a character set, the system default is used (ISO-8859-1).</description>
     1038      <class>java.lang.String</class>
     1039      <value>ISO-8859-1</value>
     1040    </parameter>
     1041    <parameter>
     1042      <name>nameColumnMapping</name>
     1043      <label>Name</label>
     1044      <description>Mapping that picks the reporter's name from the data columns. For example: \Name\</description>
     1045      <class>java.lang.String</class>
     1046      <value>\transcript_id\</value>
     1047    </parameter>
     1048    <parameter>
     1049      <name>dataSplitterRegexp</name>
     1050      <label>Data splitter</label>
     1051      <description>A regular expression that splits each data line into individual columns. For example, split on tabs: \t</description>
     1052      <class>java.lang.String</class>
     1053      <value>\t</value>
     1054    </parameter>
     1055    <parameter>
     1056      <name>decimalSeparator</name>
     1057      <label>Decimal separator</label>
     1058      <description>The decimal separator used in numeric values, if not specified dot is assumed.</description>
     1059      <class>java.lang.String</class>
     1060      <value>dot</value>
     1061    </parameter>
     1062  </configuration>
    9271063</configfile>
Note: See TracChangeset for help on using the changeset viewer.