cblanken/boggler
1
0
Fork 0
mirror of https://codeberg.org/cblanken/boggler.git synced 2026-07-25 19:19:20 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update wordlist splitting script

Browse Source 
- Force lowercase on split
- Only match single (non compound) words
- Don't match punctuation
- Sort and uniquify
This commit is contained in:
cblanken
2022-09-23 10:20:48 -04:00
parent d5a102713d
commit da915b723c
1 changed files with 27 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/boggler/split_wordlist_en.sh
+27 -27
View File
@@ -1,35 +1,35 @@
#!/bin/sh
if [ -z $1 ] || [ -z $2 ]; then
echo "Usage: ./filter_prefix.sh WORDLIST OUT_DIR"
echo "Usage: WORDLIST OUT_DIR"
exit 0
else
grep -P "^a" $1 > "$2/words_a.txt"
grep -P "^b" $1 > "$2/words_b.txt"
grep -P "^c" $1 > "$2/words_c.txt"
grep -P "^d" $1 > "$2/words_d.txt"
grep -P "^e" $1 > "$2/words_e.txt"
grep -P "^f" $1 > "$2/words_f.txt"
grep -P "^g" $1 > "$2/words_g.txt"
grep -P "^h" $1 > "$2/words_h.txt"
grep -P "^i" $1 > "$2/words_i.txt"
grep -P "^j" $1 > "$2/words_j.txt"
grep -P "^k" $1 > "$2/words_k.txt"
grep -P "^l" $1 > "$2/words_l.txt"
grep -P "^m" $1 > "$2/words_m.txt"
grep -P "^n" $1 > "$2/words_n.txt"
grep -P "^o" $1 > "$2/words_o.txt"
grep -P "^p" $1 > "$2/words_p.txt"
grep -P "^q" $1 > "$2/words_q.txt"
grep -P "^r" $1 > "$2/words_r.txt"
grep -P "^s" $1 > "$2/words_s.txt"
grep -P "^t" $1 > "$2/words_t.txt"
grep -P "^u" $1 > "$2/words_u.txt"
grep -P "^v" $1 > "$2/words_v.txt"
grep -P "^w" $1 > "$2/words_w.txt"
grep -P "^x" $1 > "$2/words_x.txt"
grep -P "^y" $1 > "$2/words_y.txt"
grep -P "^z" $1 > "$2/words_z.txt"
grep -ioP "^a[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_a.txt"
grep -ioP "^b[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_b.txt"
grep -ioP "^c[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_c.txt"
grep -ioP "^d[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_d.txt"
grep -ioP "^e[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_e.txt"
grep -ioP "^f[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_f.txt"
grep -ioP "^g[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_g.txt"
grep -ioP "^h[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_h.txt"
grep -ioP "^i[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_i.txt"
grep -ioP "^j[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_j.txt"
grep -ioP "^k[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_k.txt"
grep -ioP "^l[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_l.txt"
grep -ioP "^m[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_m.txt"
grep -ioP "^n[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_n.txt"
grep -ioP "^o[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_o.txt"
grep -ioP "^p[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_p.txt"
grep -ioP "^q[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_q.txt"
grep -ioP "^r[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_r.txt"
grep -ioP "^s[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_s.txt"
grep -ioP "^t[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_t.txt"
grep -ioP "^u[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_u.txt"
grep -ioP "^v[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_v.txt"
grep -ioP "^w[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_w.txt"
grep -ioP "^x[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_x.txt"
grep -ioP "^y[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_y.txt"
grep -ioP "^z[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_z.txt"
touch "$2/words__.txt"
exit 0
fi