diverse aanpassingen
This commit is contained in:
24
collect.sh
24
collect.sh
@@ -62,7 +62,11 @@ do
|
||||
|
||||
for i in 1 4
|
||||
do
|
||||
files=$(find .. $(week2files $ds $i) | grep -E "$regex")
|
||||
files=$(find .. $(week2files $ds $i) | grep -E "$regex") || true
|
||||
if [ -z "$files" ]
|
||||
then
|
||||
continue
|
||||
fi
|
||||
|
||||
# tellingen met tags
|
||||
|
||||
@@ -86,7 +90,7 @@ do
|
||||
|
||||
say $part-nieuwe-woorden-$ds-$i
|
||||
alto \
|
||||
'fp://node[@his and not(@rel="mwp" or @cat="mwu") and not(@his="normal" or @his="name" or @his="prefix_name" or @his_1="decap" or @his_1="0" or @his="skip" or @his="robust_skip" or @his="w_dia" or @his="wo_dia" or @his="within_word_conjunct")]' \
|
||||
'fp://node[@his and not(@rel="mwp" or @cat="mwu") and not(@his="normal" or @his="decap" or @his="name" or @his="prefix_name" or @his_1="decap" or @his_1="0" or @his="skip" or @his="robust_skip" or @his="w_dia" or @his="wo_dia" or @his="within_word_conjunct")]' \
|
||||
'tt:%w\t%d\t%I' $files \
|
||||
| sed -e 's/pubdate: "[-0-9]*"//' \
|
||||
| sed -e 's/\.[0-9][0-9]*$//' | sort | uniq \
|
||||
@@ -125,18 +129,18 @@ do
|
||||
| sed -e 's/\.[0-9][0-9]*$//' | sort | uniq \
|
||||
| items2count > $part-overige-namen-$ds-$i
|
||||
|
||||
# tellingen met postags
|
||||
# tellingen met tags en postags
|
||||
|
||||
say $part-nieuwe-woorden-extra-$ds-$i
|
||||
alto \
|
||||
'fp://node[@his and not(@rel="mwp" or @cat="mwu") and not(@his="normal" or @his="name" or @his="prefix_name" or @his_1="decap" or @
|
||||
his_1="0" or @his="skip" or @his="robust_skip" or @his="w_dia" or @his="wo_dia" or @his="within_word_conjunct")]' \
|
||||
'tt:%w\t%l\t%P\t%I' $files \
|
||||
'fp://node[@his and not(@rel="mwp" or @cat="mwu") and not(@his="normal" or @his="decap" or @his="name" or @his="prefix_name" or @his_1="decap" or @his_1="0" or @his="skip" or @his="robust_skip" or @his="w_dia" or @his="wo_dia" or @his="within_word_conjunct")]' \
|
||||
'tt:%w\t%d\t%l\t%P\t%I' $files \
|
||||
| sed -e 's/pubdate: "[-0-9]*"//' \
|
||||
| sed -e 's/\.[0-9][0-9]*$//' | sort | uniq \
|
||||
| sed -e 's/\(.*\)\t.*/\1/' | uniq -c \
|
||||
| grep -v '^ *1 ' \
|
||||
| sed -e 's/\([0-9]\) */\1\t/' | sort -f -k 2 | sort -n -r -k 1,1 -s \
|
||||
> $part-nieuwe-woorden-extra-$ds-$i
|
||||
| items2count > $part-nieuwe-woorden-extra-$ds-$i
|
||||
top20 $part-nieuwe-woorden-extra-$ds-$i
|
||||
|
||||
# tellingen met postags
|
||||
|
||||
say $part-nieuwe-adjww-extra-$ds-$i
|
||||
alto \
|
||||
|
||||
Reference in New Issue
Block a user