From 29a5dc417ee3c5e8c1832773a6a8b6158b77741a Mon Sep 17 00:00:00 2001 From: Peter Kleiweg Date: Thu, 16 Apr 2026 13:15:55 +0200 Subject: [PATCH] */txt2corpus.sh : rm -f $corpus.data.dz $corpus.index --- AT5/txt2corpus.sh | 1 + GG/txt2corpus.sh | 1 + NOS/txt2corpus.sh | 1 + NU/txt2corpus.sh | 1 + NieuwsNL/txt2corpus.sh | 1 + Oog/txt2corpus.sh | 1 + RO/txt2corpus.sh | 1 + RTVNoord/txt2corpus.sh | 1 + Sargasso/txt2corpus.sh | 1 + Sikkom/txt2corpus.sh | 1 + Tzum/txt2corpus.sh | 1 + VRT/txt2corpus.sh | 1 + 12 files changed, 12 insertions(+) diff --git a/AT5/txt2corpus.sh b/AT5/txt2corpus.sh index 0534355..a781cc9 100755 --- a/AT5/txt2corpus.sh +++ b/AT5/txt2corpus.sh @@ -56,6 +56,7 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus. ../../../metadata cd xml +rm -f $corpus.data.dz $corpus.index alto -o $corpus.data.dz *.xml 2> /dev/null cd ../.. diff --git a/GG/txt2corpus.sh b/GG/txt2corpus.sh index 25cf7d4..8576e04 100755 --- a/GG/txt2corpus.sh +++ b/GG/txt2corpus.sh @@ -54,6 +54,7 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus. ../../../metadata cd xml +rm -f $corpus.data.dz $corpus.index alto -o $corpus.data.dz *.xml 2> /dev/null cd ../.. diff --git a/NOS/txt2corpus.sh b/NOS/txt2corpus.sh index 7e58cb2..65d41c6 100755 --- a/NOS/txt2corpus.sh +++ b/NOS/txt2corpus.sh @@ -56,6 +56,7 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus. ../../../metadata cd xml +rm -f $corpus.data.dz $corpus.index alto -o $corpus.data.dz *.xml 2> /dev/null # telling per bericht, niet per zin diff --git a/NU/txt2corpus.sh b/NU/txt2corpus.sh index 0e21291..5f8ae5d 100755 --- a/NU/txt2corpus.sh +++ b/NU/txt2corpus.sh @@ -54,6 +54,7 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus. ../../../metadata cd xml +rm -f $corpus.data.dz $corpus.index alto -o $corpus.data.dz *.xml 2> /dev/null # telling per bericht, niet per zin diff --git a/NieuwsNL/txt2corpus.sh b/NieuwsNL/txt2corpus.sh index 193c969..61c0b11 100755 --- a/NieuwsNL/txt2corpus.sh +++ b/NieuwsNL/txt2corpus.sh @@ -56,6 +56,7 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus. ../../../../metadata cd xml +rm -f $corpus.data.dz $corpus.index alto -o $corpus.data.dz *.xml 2> /dev/null # telling per bericht, niet per zin diff --git a/Oog/txt2corpus.sh b/Oog/txt2corpus.sh index 083e049..6cba832 100755 --- a/Oog/txt2corpus.sh +++ b/Oog/txt2corpus.sh @@ -56,6 +56,7 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus. ../../../metadata cd xml +rm -f $corpus.data.dz $corpus.index alto -o $corpus.data.dz *.xml 2> /dev/null # telling per bericht, niet per zin diff --git a/RO/txt2corpus.sh b/RO/txt2corpus.sh index afb4331..a4b0545 100755 --- a/RO/txt2corpus.sh +++ b/RO/txt2corpus.sh @@ -56,6 +56,7 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus. ../../../metadata cd xml +rm -f $corpus.data.dz $corpus.index alto -o $corpus.data.dz *.xml 2> /dev/null # telling per bericht, niet per zin diff --git a/RTVNoord/txt2corpus.sh b/RTVNoord/txt2corpus.sh index c2ade29..138fccf 100755 --- a/RTVNoord/txt2corpus.sh +++ b/RTVNoord/txt2corpus.sh @@ -54,6 +54,7 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus. ../../../metadata cd xml +rm -f $corpus.data.dz $corpus.index alto -o $corpus.data.dz *.xml 2> /dev/null # telling per bericht, niet per zin diff --git a/Sargasso/txt2corpus.sh b/Sargasso/txt2corpus.sh index 5391ce4..a89b861 100755 --- a/Sargasso/txt2corpus.sh +++ b/Sargasso/txt2corpus.sh @@ -56,6 +56,7 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus. ../../../metadata cd xml +rm -f $corpus.data.dz $corpus.index alto -o $corpus.data.dz *.xml 2> /dev/null # telling per bericht, niet per zin diff --git a/Sikkom/txt2corpus.sh b/Sikkom/txt2corpus.sh index d18b92d..d2df7be 100755 --- a/Sikkom/txt2corpus.sh +++ b/Sikkom/txt2corpus.sh @@ -54,6 +54,7 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus. ../../../metadata cd xml +rm -f $corpus.data.dz $corpus.index alto -o $corpus.data.dz *.xml 2> /dev/null cd ../.. diff --git a/Tzum/txt2corpus.sh b/Tzum/txt2corpus.sh index 1bd4d6d..a69971a 100755 --- a/Tzum/txt2corpus.sh +++ b/Tzum/txt2corpus.sh @@ -56,6 +56,7 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus. ../../../metadata cd xml +rm -f $corpus.data.dz $corpus.index alto -o $corpus.data.dz *.xml 2> /dev/null # telling per bericht, niet per zin diff --git a/VRT/txt2corpus.sh b/VRT/txt2corpus.sh index 1b55734..3c82ead 100755 --- a/VRT/txt2corpus.sh +++ b/VRT/txt2corpus.sh @@ -54,6 +54,7 @@ Alpino -flag treebank xml debug=1 end_hook=xml user_max=900000 -parse < $corpus. ../../../metadata cd xml +rm -f $corpus.data.dz $corpus.index alto -o $corpus.data.dz *.xml 2> /dev/null # telling per bericht, niet per zin