Added new ICU test case which illustrates removal of diacritics

diff --git a/test/Makefile.am b/test/Makefile.am
index 58dd782..a3e34de 100644 (file)
--- a/test/Makefile.am
+++ b/test/Makefile.am
@@ -26,8 +26,9 @@ EXTRA_DIST = tstodr.asn tstodrcodec.c tstodrcodec.h cql2xcqlsample \
  marccol3.u8.marc marccol3.u8.1.lst marccol3.u8.2.lst \
  marccol4.u8.marc marccol4.u8.1.lst marccol4.u8.2.lst \
  marccol5.u8.marc marccol5.u8.1.lst marccol5.u8.2.lst \
- tst_record_conv.xsl \
- tsticu-0.xml tsticu-0.input tsticu-0.output
+ tsticu-0.xml tsticu-0.input tsticu-0.output \
+ tsticu-1.xml tsticu-1.input tsticu-1.output \
+ tst_record_conv.xsl 
 
 YAZCOMP = ../util/yaz-asncomp
 YAZCOMPLINE = $(YAZCOMP) -d z.tcl -i yaz -I../include $(YCFLAGS)

diff --git a/test/tsticu-1.input b/test/tsticu-1.input
new file mode 100644 (file)
index 0000000..6e4709c
--- /dev/null
+++ b/test/tsticu-1.input
@@ -0,0 +1,4 @@
+Børn
+Le Carré
+Le Carre
+Le Carré

diff --git a/test/tsticu-1.output b/test/tsticu-1.output
new file mode 100644 (file)
index 0000000..3989b6a
--- /dev/null
+++ b/test/tsticu-1.output
@@ -0,0 +1,7 @@
+1 1 'børn' 'Børn' '+EKC\x01\x85\xA5\x06\x01\x09'
+2 2 'le' 'Le' '?1\x01\x06\x01\x06'
+3 2 'carre' 'Carre' '-)KK1\x01\x09\x01\x09'
+4 3 'le' 'Le' '?1\x01\x06\x01\x06'
+5 3 'carre' 'Carre' '-)KK1\x01\x09\x01\x09'
+6 4 'le' 'Le' '?1\x01\x06\x01\x06'
+7 4 'carre' 'Carre' '-)KK1\x01\x09\x01\x09'

diff --git a/test/tsticu-1.xml b/test/tsticu-1.xml
new file mode 100644 (file)
index 0000000..581bc51
--- /dev/null
+++ b/test/tsticu-1.xml
@@ -0,0 +1,7 @@
+<icu_chain locale="en">
+  <transform rule="[:Control:] Any-Remove"/>
+  <tokenize rule="l"/>
+  <transform rule="NFD; [[:WhiteSpace:][:Punctuation:][:Diacritic:]] Remove"/>
+  <display/>
+  <casemap rule="l"/>
+</icu_chain>