X-Git-Url: https://juplo.de/gitweb/?p=demos%2Fkafka%2Fdeduplication;a=blobdiff_plain;f=create-data.sh;h=ea429a393b47e7ad28385d558a806c04a2b479e2;hp=d64ca41dbc0910580624798b2684c1d533b53630;hb=5ad8c11b5c507e85b256888683b9508999e1b135;hpb=a84868373c1803dca9f6203085240b107af44257

diff --git a/create-data.sh b/create-data.sh
index d64ca41..ea429a3 100755
--- a/create-data.sh
+++ b/create-data.sh
@@ -1,17 +1,38 @@
 #!/bin/bash
 
-for i in `seq 1 333`;     do echo $(($i%7)):$i; done >  data.txt
-for i in `seq 70 578`;    do echo $(($i%7)):$i; done >> data.txt
-for i in `seq 400 1211`;  do echo $(($i%7)):$i; done >> data.txt
-for i in `seq 1000 1111`; do echo $(($i%7)):$i; done >> data.txt
-for i in `seq 1200 1711`; do echo $(($i%7)):$i; done >> data.txt
-for i in `seq 1688 3333`; do echo $(($i%7)):$i; done >> data.txt
-for i in `seq 2567 3500`; do echo $(($i%7)):$i; done >> data.txt
+function name()
+{
+  case $(($1%7)) in
+    0) echo "peter"
+       ;;
+    1) echo "franz"
+       ;;
+    2) echo "ute"
+       ;;
+    3) echo "klaus"
+       ;;
+    4) echo "paul"
+       ;;
+    5) echo "petra"
+       ;;
+    6) echo "siggi"
+       ;;
+  esac
+}
+
+for i in `seq 1 333`;     do echo $(name $i):$i; done >  data.txt
+for i in `seq 70 578`;    do echo $(name $i):$i; done >> data.txt
+for i in `seq 400 1211`;  do echo $(name $i):$i; done >> data.txt
+for i in `seq 1000 1111`; do echo $(name $i):$i; done >> data.txt
+for i in `seq 1200 1711`; do echo $(name $i):$i; done >> data.txt
+for i in `seq 1688 3333`; do echo $(name $i):$i; done >> data.txt
+for i in `seq 2567 3500`; do echo $(name $i):$i; done >> data.txt
+
+for i in `seq 1 3500`;    do echo $(name $i):$i | awk -F: '/^peter/ { print $2 }'; done > expected_peter.txt
+for i in `seq 1 3500`;    do echo $(name $i):$i | awk -F: '/^franz/ { print $2 }'; done > expected_franz.txt
+for i in `seq 1 3500`;    do echo $(name $i):$i | awk -F: '/^ute/   { print $2 }'; done > expected_ute.txt
+for i in `seq 1 3500`;    do echo $(name $i):$i | awk -F: '/^klaus/ { print $2 }'; done > expected_klaus.txt
+for i in `seq 1 3500`;    do echo $(name $i):$i | awk -F: '/^paul/  { print $2 }'; done > expected_paul.txt
+for i in `seq 1 3500`;    do echo $(name $i):$i | awk -F: '/^petra/ { print $2 }'; done > expected_petra.txt
+for i in `seq 1 3500`;    do echo $(name $i):$i | awk -F: '/^siggi/ { print $2 }'; done > expected_siggi.txt
 
-for i in `seq 1 3500`; do echo $(($i%7)):$i; done | grep ^0 > expected_0.txt
-for i in `seq 1 3500`; do echo $(($i%7)):$i; done | grep ^1 > expected_1.txt
-for i in `seq 1 3500`; do echo $(($i%7)):$i; done | grep ^2 > expected_2.txt
-for i in `seq 1 3500`; do echo $(($i%7)):$i; done | grep ^3 > expected_3.txt
-for i in `seq 1 3500`; do echo $(($i%7)):$i; done | grep ^4 > expected_4.txt
-for i in `seq 1 3500`; do echo $(($i%7)):$i; done | grep ^5 > expected_5.txt
-for i in `seq 1 3500`; do echo $(($i%7)):$i; done | grep ^6 > expected_6.txt