Created
August 21, 2020 05:12
-
-
Save lgrz/44f9e52bf90b75b04d900faa9305fce9 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<parmeters> | |
<memory>128G</memory> | |
<index>myindex</index> | |
<storeDocs>true</storeDocs> | |
<stemmer><name>krovetz</name></stemmer> | |
<corpus> | |
<path>/path/to/corpus</path> | |
<class>warc</class> | |
<inlink>/path/to/links/sorted</inlink> | |
</corpus> | |
<metadata> | |
<forward>url</forward> | |
<backward>url</backward> | |
</metadata> | |
<field><name>mainbody</name></field> | |
<field><name>heading</name></field> | |
<field><name>inlink</name></field> | |
<field><name>body</name></field> | |
<field><name>title</name></field> | |
<field><name>table</name></field> | |
<field><name>td</name></field> | |
<field><name>a</name></field> | |
<field><name>applet</name></field> | |
<field><name>embed</name></field> | |
<field><name>object</name></field> | |
<field><name>blink</name></field> | |
<field><name>marquee</name></field> | |
<field><name>script</name></field> | |
</parmeters> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment