Added ICU chain component - which used to be part of Pazpar2.
[yaz-moved-to-github.git] / util / yaz-icu-example.xml
1 <icu>
2   <icu_chain id="en:field" locale="en">
3     <display/>
4   </icu_chain>
5   <icu_chain id="en:sentence" locale="en">
6     <normalize rule="[:Control:] Any-Remove"/>
7     <tokenize rule="s"/>
8     <display/>
9     <normalize rule="[:Punctuation:] Remove"/>
10     <casemap rule="l"/>
11     <normal/>
12     <sort/>
13   </icu_chain>
14   <icu_chain id="en:word" locale="en">
15     <normalize rule="[:Control:] Any-Remove"/>
16     <tokenize rule="w"/>
17     <normalize rule="[[:WhiteSpace:][:Punctuation:]] Remove"/>
18     <display/>
19     <normalize rule="Lower"/>
20     <normal/>
21   </icu_chain>
22   <icu_chain id="en:number" locale="en">
23     <normalize rule="[:Letter:] Remove"/>
24     <tokenize rule="w"/>
25     <normalize rule="[:^Number:] Remove"/>
26     <display/>
27     <normal/>
28     <sort/>
29   </icu_chain>
30 </icu>