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

collect.sh: case-insensitive sort

Browse Source
This commit is contained in:
Peter Kleiweg
2026-03-25 17:47:26 +01:00
parent 9686b8b846
commit a1f0a76331
1 changed files with 16 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
collect.sh
View File

@@ -30,51 +30,59 @@ do
alto \
'fp://node[((@cat="mwu" and node[@pt="spec"]) or (@pt and @*="eigen" and not(@rel="mwp"))) and not(@his="normal") and not(@his_1="decap" or @his_1="0")]' \
tt:%w $files | sort | uniq -c | grep -v '^ *1 ' | sed -e 's/\([0-9]\) */\1\t/' | sort -nr > nieuw-namen-$ds-$i
tt:%w $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 > nieuw-namen-$ds-$i
score nieuw-namen-$ds-$i > nieuw-namen-$ds-$i.score
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 $files | sort | uniq -c | grep -v '^ *1 ' | sed -e 's/\([0-9]\) */\1\t/' | sort -nr > nieuw-woorden-$ds-$i
tt:%w $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 > nieuw-woorden-$ds-$i
score nieuw-woorden-$ds-$i > nieuw-woorden-$ds-$i.score
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' $files | sort | uniq -c | grep -v '^ *1 ' | sed -e 's/\([0-9]\) */\1\t/' | sort -nr > nieuw-extra-$ds-$i
'tt:%w\t%l\t%P' $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 > nieuw-extra-$ds-$i
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")]' \
tt:%l $files | sort | uniq -c | grep -v '^ *1 ' | sed -e 's/\([0-9]\) */\1\t/' | sort -nr > locaties-$ds-$i
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")]' \
tt:%l $files | sort | uniq -c | grep -v '^ *1 ' | sed -e 's/\([0-9]\) */\1\t/' | sort -nr > personen-$ds-$i
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")]' \
tt:%l $files | sort | uniq -c | grep -v '^ *1 ' | sed -e 's/\([0-9]\) */\1\t/' | sort -nr > organisaties-$ds-$i
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")]' \
tt:%l $files | sort | uniq -c | grep -v '^ *1 ' | sed -e 's/\([0-9]\) */\1\t/' | sort -nr > overigen-$ds-$i
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
score overigen-$ds-$i > overigen-$ds-$i.score
alto \
'fp://node[@pt and @his and not(../@his="normal" or @rel="mwp" or ../@his="name" or ../@his_1="decap") and not(@his="normal" or @his="name" or @his="skip" or @his="robust_skip" or @his="w_dia" or @his="wo_dia" or @his="decap" or @his="within_word_conjunct") and not(@pt="n") ]' \
'tt:%w\t%P' $files | sort | uniq -c | grep -v '^ *1 ' | sed -e 's/\([0-9]\) */\1\t/' | sort -nr > overigen-extra-$ds-$i
'tt:%w\t%P' $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-extra-$ds-$i
score overigen-extra-$ds-$i > overigen-extra-$ds-$i.score