diff options
| author | Martin Czygan <martin.czygan@gmail.com> | 2021-06-10 01:59:27 +0200 |
|---|---|---|
| committer | Martin Czygan <martin.czygan@gmail.com> | 2021-06-10 01:59:27 +0200 |
| commit | 88b5068171df640724482f9c77d5bec7d62ffa43 (patch) | |
| tree | ba64f23ed32d0e8c3667e2dafca279fd0d2e9d61 | |
| parent | 2b88452ec73e0a34dedcfbcc515eb6a91ce7e3e6 (diff) | |
| download | refcat-88b5068171df640724482f9c77d5bec7d62ffa43.tar.gz refcat-88b5068171df640724482f9c77d5bec7d62ffa43.zip | |
tasks: sort may require too much memory, currently
| -rw-r--r-- | python/refcat/tasks.py | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py index 698ef24..50e13c7 100644 --- a/python/refcat/tasks.py +++ b/python/refcat/tasks.py @@ -462,7 +462,7 @@ class URLTabs(Refcat): class URLTabsCleaned(Refcat): """ - URLTabs, cleaned. + URLTabs, cleaned, unsorted. """ def requires(self): return URLTabs() @@ -471,7 +471,6 @@ class URLTabsCleaned(Refcat): output = shellout(""" zstdcat -T0 {input} | skate-cleanup -X -c url -B -S -f 3 | - LC_ALL=C sort -u -T {tmpdir} -k3,3 -S25% --parallel 4 | LC_ALL=C grep -E '^https?://' | zstd -T0 -c > {output} """, |