Last active
December 11, 2015 16:31
-
-
Save MrTrick/6203663b8706150308b5 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
awk <50knouns.txt '{print $1}' | sort -u > N.txt | |
aspell -len_GB dump master | sort -u > A.txt | |
tr <sowpods.txt '[:upper;]' '[:lower;]' | sort -u > S.txt | |
alias D=diff --new-line-format="" --unchanged-line-format="" | |
D A.txt N.txt > A_notN.txt | |
D A.txt S.txt > A_notS.txt | |
D N.txt A.txt > N_notA.txt | |
D S.txt A.txt > S_notA.txt | |
D N.txt S.txt > N_notS.txt | |
D S.txt N.txt > S_notN.txt | |
D A_notN.txt S.txt > A_notNS.txt | |
D N_notS.txt A.txt > N_notAS.txt | |
D S_notA.txt N.txt > S_notAN.txt | |
wc -l {A,N,S}* | |
# 80599 A_notNS.txt | |
# 112347 A_notN.txt | |
# 89753 A_notS.txt | |
# 135331 A.txt | |
# 13842 N_notAS.txt | |
# 16251 N_notA.txt | |
# 22996 N_notS.txt | |
# 39235 N.txt | |
# 218453 S_notAN.txt | |
# 220862 S_notA.txt | |
# 250201 S_notN.txt | |
# 266440 S.txt | |
alias INT='diff --new-line-format="" --old-line-format=""' | |
INT A.txt N.txt > AN.txt | |
INT A.txt S.txt > AS.txt | |
INT N.txt S.txt > NS.txt | |
D AN.txt S.txt > AN_notS.txt | |
D AS.txt N.txt > AS_notN.txt | |
D NS.txt A.txt > NS_notA.txt | |
wc -l {A,N,S}{A,N,S}* 2>/dev/null | |
# 9154 AN_notS.txt | |
# 22984 AN.txt | |
# 31748 AS_notN.txt | |
# 45578 AS.txt | |
# 2409 NS_notA.txt | |
# 16239 NS.txt | |
# 128112 total | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment