p209327/nlnieuws
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

@his="normal" weg

Browse Source
This commit is contained in:
Peter Kleiweg
2026-03-26 13:17:51 +01:00
parent 010bc3ca59
commit b4d6d06146
2 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
collect.sh
View File

@@ -55,28 +55,28 @@ do
# score nieuw-extra-$ds-$i > nieuw-extra-$ds-$i.score
alto \
'fp://node[(@neclass="LOC" and @his="normal" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="LOC"] and @his="normal")]' \
'fp://node[(@neclass="LOC" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="LOC"])]' \
tt:%l $files | sort | uniq -c | grep -v '^ *1 ' | sed -e 's/\([0-9]\) */\1\t/' | \
sort -f -k 2 | sort -n -r -k 1,1 -s > locaties-$ds-$i
# score locaties-$ds-$i > locaties-$ds-$i.score
alto \
'fp://node[(@neclass="PER" and @his="normal" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="PER"] and @his="normal")]' \
'fp://node[(@neclass="PER" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="PER"])]' \
tt:%l $files | sort | uniq -c | grep -v '^ *1 ' | sed -e 's/\([0-9]\) */\1\t/' | \
sort -f -k 2 | sort -n -r -k 1,1 -s > personen-$ds-$i
# score personen-$ds-$i > personen-$ds-$i.score
alto \
'fp://node[(@neclass="ORG" and @his="normal" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="ORG"] and @his=" normal")]' \
'fp://node[(@neclass="ORG" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="ORG"])]' \
tt:%l $files | sort | uniq -c | grep -v '^ *1 ' | sed -e 's/\([0-9]\) */\1\t/' | \
sort -f -k 2 | sort -n -r -k 1,1 -s > organisaties-$ds-$i
# score organisaties-$ds-$i > organisaties-$ds-$i.score
alto \
'fp://node[(@neclass="MISC" and @his="normal" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="MISC"] and @his="normal")]' \
'fp://node[(@neclass="MISC" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="MISC"])]' \
tt:%l $files | sort | uniq -c | grep -v '^ *1 ' | sed -e 's/\([0-9]\) */\1\t/' | \
sort -f -k 2 | sort -n -r -k 1,1 -s > overigen-$ds-$i

16
namen.sh
View File

@@ -83,26 +83,26 @@ case $XN in
XVALID=1
;;
4)
# bestaande locaties
EXPR='fp://node[(@neclass="LOC" and @his="normal" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="LOC"] and @his="normal")]'
# bestaande en nieuwe locaties
EXPR='fp://node[(@neclass="LOC" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="LOC"])]'
TEMPLATE='tt:%l'
XVALID=1
;;
5)
# bestaande personen
EXPR='fp://node[(@neclass="PER" and @his="normal" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="PER"] and @his="normal")]'
# bestaande en nieuwe personen
EXPR='fp://node[(@neclass="PER" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="PER"])]'
TEMPLATE='tt:%l'
XVALID=1
;;
6)
# bestaande organisaties
EXPR='fp://node[(@neclass="ORG" and @his="normal" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="ORG"] and @his="normal")]'
# bestaande en nieuwe organisaties
EXPR='fp://node[(@neclass="ORG" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="ORG"])]'
TEMPLATE='tt:%l'
XVALID=1
;;
7)
# bestaande andere namen (boeken, films, events, .. )
EXPR='fp://node[(@neclass="MISC" and @his="normal" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="MISC"] and @his="normal")]'
# bestaande en nieuwe andere namen (boeken, films, events, .. )
EXPR='fp://node[(@neclass="MISC" and not(@rel="mwp")) or (@cat="mwu" and node[@pt="spec" and @neclass="MISC"])]'
TEMPLATE='tt:%l'
XVALID=1
;;