mirror of
https://github.com/rspeer/wordfreq.git
synced 2024-12-23 09:21:37 +00:00
parent
8e963dc312
commit
7494ae27a7
@ -63,7 +63,7 @@ rule convert_opensubtitles
|
||||
|
||||
# To convert SUBTLEX, we take the 1st and Nth columns, strip the header,
|
||||
# run it through ftfy, convert tabs to commas and spurious CSV formatting to
|
||||
# and remove lines with unfixable half-mojibake.
|
||||
# spaces, and remove lines with unfixable half-mojibake.
|
||||
rule convert_subtlex
|
||||
command = cut -f $textcol,$freqcol $in | tail -n +$startrow | ftfy | tr ' ",' ', ' | grep -v 'â,' > $out
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user