diff options
author | Martin Czygan <martin.czygan@gmail.com> | 2021-06-10 02:10:24 +0200 |
---|---|---|
committer | Martin Czygan <martin.czygan@gmail.com> | 2021-06-10 02:10:24 +0200 |
commit | ea784a826b6d0160575121f245675086b3dfc130 (patch) | |
tree | 5a72bbb8108683afcf5542c864662d2e828fa87e | |
parent | 4ac97dd20887a7adf97bdd6ec83e65ccd283b045 (diff) | |
download | refcat-ea784a826b6d0160575121f245675086b3dfc130.tar.gz refcat-ea784a826b6d0160575121f245675086b3dfc130.zip |
task: get rid of grep
-rw-r--r-- | python/refcat/tasks.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py index 50e13c7..09e88c4 100644 --- a/python/refcat/tasks.py +++ b/python/refcat/tasks.py @@ -470,8 +470,8 @@ class URLTabsCleaned(Refcat): def run(self): output = shellout(""" zstdcat -T0 {input} | - skate-cleanup -X -c url -B -S -f 3 | - LC_ALL=C grep -E '^https?://' | + skate-cleanup -c url -allow http,https -X -B -S -f 3 | + LC_ALL=C sort -T {tmpdir} -k3,3 -S25% --parallel 4 | zstd -T0 -c > {output} """, n=self.n, |