Skip to content

Commit

Permalink
more dedup files added
Browse files Browse the repository at this point in the history
  • Loading branch information
jorgtied committed Dec 2, 2022
1 parent 41f716f commit 4d12cbc
Show file tree
Hide file tree
Showing 978 changed files with 16 additions and 3 deletions.
2 changes: 1 addition & 1 deletion OPUS
Submodule OPUS updated 2428 files
6 changes: 4 additions & 2 deletions index/Makefile
Original file line number Diff line number Diff line change
Expand Up @@ -39,18 +39,20 @@ all: ${LANGUAGE}.sent2id.db
dedup: ${LANGUAGE}.dedup.gz


SWIFT_PARAMS = --use-slo --segment-size 5G --changed --skip-identical

.PHONY: upload
upload:
which a-get
swift upload --use-slo --segment-size 5G OPUS-index ${LANGUAGE}.dedup.gz ${LANGUAGE}.*.db
swift upload OPUS-index ${SWIFT_PARAMS} ${LANGUAGE}.dedup.gz ${LANGUAGE}.*.db
swift list OPUS-index | grep '\.dedup.gz$$' | sed 's#^#https://object.pouta.csc.fi/OPUS-index/#' > index.txt
swift list OPUS-index | grep '\.db$$' | sed 's#^#https://object.pouta.csc.fi/OPUS-index/#' >> index.txt
find done -name '${LANGUAGE}.done' | xargs git add

.PHONY: upload-all
upload-all:
which a-get
-swift upload --use-slo --segment-size 5G OPUS-index *.dedup.gz *.db
-swift upload OPUS-index ${SWIFT_PARAMS} *.dedup.gz *.db
swift list OPUS-index | grep '\.dedup.gz$$' | sed 's#^#https://object.pouta.csc.fi/OPUS-index/#' > index.txt
swift list OPUS-index | grep '\.db$$' | sed 's#^#https://object.pouta.csc.fi/OPUS-index/#' >> index.txt
find done -name '*.done' | xargs git add
Expand Down
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file added index/done/DGT/v4/mono/cs.done
Empty file.
Empty file added index/done/DGT/v4/mono/es.done
Empty file.
Empty file added index/done/DGT/v4/mono/et.done
Empty file.
Empty file added index/done/DGT/v4/mono/fr.done
Empty file.
Empty file added index/done/DGT/v4/mono/sk.done
Empty file.
Empty file added index/done/DOGC/v2/mono/ca.done
Empty file.
Empty file added index/done/DOGC/v2/mono/es.done
Empty file.
Empty file added index/done/DOGC/v3/mono/ca.done
Empty file.
Empty file added index/done/DOGC/v3/mono/es.done
Empty file.
Empty file added index/done/ECB/v1/mono/cs.done
Empty file.
Empty file added index/done/ECB/v1/mono/es.done
Empty file.
Empty file added index/done/ECB/v1/mono/et.done
Empty file.
Empty file added index/done/ECB/v1/mono/fr.done
Empty file.
Empty file added index/done/ECB/v1/mono/sk.done
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Empty file.
Loading

0 comments on commit 4d12cbc

Please sign in to comment.