t.multiple.tokens.body

来自「一个C语言写的快速贝叶斯垃圾邮件过滤工具」· BODY 代码 · 共 105 行

#!/bin/sh

. ${srcdir=.}/t.frame

INP=${TMPDIR}/test.inp
REF=${TMPDIR}/test.ref
OUT=${TMPDIR}/test.out
CORRECT=${SYSTEST}/outputs/multiple.wordlists.ref

cat <<EOF > $INP
aaa 
bbb ccc
ddd eee fff
EOF

cat <<EOF > $REF
::: 1 :::
aaa
bbb
ccc
ddd
eee
fff
::: 2 :::
aaa
bbb
aaa*bbb
ccc
bbb*ccc
ddd
ccc*ddd
eee
ddd*eee
fff
eee*fff
::: 3 :::
aaa
bbb
aaa*bbb
ccc
bbb*ccc
aaa*bbb*ccc
ddd
ccc*ddd
bbb*ccc*ddd
eee
ddd*eee
ccc*ddd*eee
fff
eee*fff
ddd*eee*fff
::: 4 :::
aaa
bbb
aaa*bbb
ccc
bbb*ccc
aaa*bbb*ccc
ddd
ccc*ddd
bbb*ccc*ddd
aaa*bbb*ccc*ddd
eee
ddd*eee
ccc*ddd*eee
bbb*ccc*ddd*eee
fff
eee*fff
ddd*eee*fff
ccc*ddd*eee*fff
::: 5 :::
aaa
bbb
aaa*bbb
ccc
bbb*ccc
aaa*bbb*ccc
ddd
ccc*ddd
bbb*ccc*ddd
aaa*bbb*ccc*ddd
eee
ddd*eee
ccc*ddd*eee
bbb*ccc*ddd*eee
aaa*bbb*ccc*ddd*eee
fff
eee*fff
ddd*eee*fff
ccc*ddd*eee*fff
bbb*ccc*ddd*eee*fff
EOF

for COUNT in 1 2 3 4 5 ; do
    echo "::: $COUNT :::" >> $OUT
    $BOGOLEXER -C -H -p --multi-token-count $COUNT < $INP >> $OUT
done

if  [ $verbose -eq 0 ]; then
    diff $REF $OUT
    cmp  $REF $OUT
else
    diff $DIFF_BRIEF $REF $OUT
fi