Created
December 9, 2023 13:52
-
-
Save fabiolimace/c1210534a4fb49186b093fa2766fc9ea to your computer and use it in GitHub Desktop.
List fixed tokens of a file, those which are not alpnanumeric only
This file contains 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
#!/usr/bin/gawk -f | |
NF { | |
for (i = 1; i <= NF; i++) { | |
if ( $i !~ /^[[:alnum:]]+$/ ) { | |
print $i; | |
} | |
} | |
} |
Utilization example: find all token patterns which include round brackets.
cat *.mixed.tokens.txt | grep -E --color=auto '[()]' | awk '{print $2}' | sed 's/[[:alnum:]-]//g' | sort | uniq -c | sort | tac | head -n 500
50775 )
47512 (
37302 ()
34230 ),
31194 ).
25420 (),
15718 ().
12324 (,
7065 /)
5469 );
3008 (/)
2914 ();
2881 .)
2576 (,%)
2506 ):
2493 ():
2190 //).
2190 //)
2088 (,%),
1998 .).
1975 /).
1798 (@)
1798 (.),
1650 (/),
1609 .),
1579 (,%).
1554 ("
1504 /),
1421 (.
1417 (.)
1403 (,%
1211 ..).
1100 ./).
1086 ./),
1076 (/).
1061 (.).
1045 ./)
998 ")
974 (“
907 ..)
879 "),
814 ,)
747 (%)
727 ").
676 )",
673 )".
670 (:
656 ("")
618 (/
612 ,).
604 )."
581 ”)
581 (+,%)
580 ,%)
513 )?
512 !)
511 (//)
510 (%),
469 ,%),
463 ()?
463 (%).
454 ”).
445 (%
442 ,%).
424 (""),
422 //),
406 (,%);
400 ”),
398 ..),
379 ?)
356 ,),
348 "")
338 (;
332 (↑,%)
317 )"
304 (,)
293 !),
291 (./)
291 (+,%),
289 ()",
288 !).
283 ?).
279 %)
262 (+,%).
255 “”)
255 .,).
252 .);
250 /.)
249 (..)
238 ("").
235 (.,
231 ?),
231 %).
226 (//),
222 ('
221 //.)
218 ()".
216 (,),
211 ""),
204 (↓,%)
203 (./),
193 (./).
186 ...)
186 .,)
186 .(
185 )”,
179 (“”)
178 "").
177 .,),
176 (@_)
169 (/,
169 (..
166 %),
165 /):
164 /);
164 ./);
154 (....,
152 //);
150 (%);
148 “”).
146 (...)
142 (..),
140 ....).
136 ()."
134 "(
132 ...).
130 (,).
128 ....)
123 ()”,
121 (/);
119 (..).
117 ')
114 “”),
114 (//).
114 (+,%
109 ()"
106 (+,%);
104 )”.
104 "()
103 (!)
100 (+%)
99 .):
99 (""
98 (/):
94 )!
93 (“”,
92 ..);
91 '),
90 (//
89 ....),
89 (?)
89 ($
87 ...),
83 :)
83 ../).
83 (...).
82 (↑%)
81 ("",
78 ");
77 ./):
77 (.);
76 (@.)
76 (....)
75 (//):
74 ;)
74 (&)
73 ."(
73 (+%
73 ()!
72 ../),
72 (+)
70 ()”.
68 ()/
67 //):
66 …)
66 (“”
65 +)
64 //)".
64 (./
64 (+%).
63 (“”),
62 ../)
62 ()”
61 .(...)
58 (’
58 (:)
57 (“”).
57 (,%,
56 (...),
56 (+
55 ,);
55 (+,
55 ())
54 //)"
54 /)."
54 )”
54 (+%),
53 (%,
52 //)."
52 .()
52 %);
51 :).
51 (&),
50 (–)
49 (....),
48 //.)"
48 (↓%)
48 (@),
48 ').
47 )/
47 (....
47 (..,
47 ()...
47 (')
47 (!).
46 (",
45 (....).
44 /"),
44 .,);
43 ."()
43 )...
41 (...)".
41 (...
40 ,%);
40 "(...)
39 …).
38 ).”
38 ()()
38 '')
37 ./"),
37 ))
36 @)
36 (@).
35 /)".
35 ./)".
35 ..)."
34 )*
34 (::)
34 (+).
34 ('),
33 ’),
33 :),
33 .():
33 ,/)
33 ('')
33 ''),
33 $,)
32 ”);
32 (...)"
32 "");
31 §).
31 ..)"
31 (:),
31 (/.
30 ()),
30 (&).
30 (!),
29 )";
29 (°
29 (?
28 ..):
28 .)"
28 ($,
28 (#)
28 '').
27 .)".
27 +).
27 (/.)
26 ’)
26 ./.).
26 (/.,
26 (.:
26 (./,
26 ($)
26 (!
25 ?);
25 +),
25 ).
25 (?).
24 )..
24 (“,
24 (+%);
24 ('/)
24 ("");
23 :(...)
23 .)."
23 )…
23 (@__)
23 ()).
22 °).
22 °)
22 (↓,%
22 (↑,%
22 ().:
22 '/)
21 §),
21 :(
21 ..)".
21 .(/):
21 .").
21 .")
21 (=
21 (+),
21 (#).
21 ".(
21 "(.
20 °),
20 §)
20 /)"
20 /")
20 ./)."
20 ..,),
20 (§
20 (;)
20 ("/"),
19 ”):
19 /@)
19 .(,
19 (×
19 (°)
19 '/),
19 &)
18 ;()
18 ....);
18 ."),
18 ,/),
18 +,%)
18 (//,
18 ($.,).
18 (#),
17 ’).
17 (§).
17 (.):
17 ().”
17 ().#
17 (''),
17 (%):
16 …),
16 “()
16 ;():.
16 ://)
16 ///)
16 /.).
16 .(/)
16 )'
16 (:).
16 ((
16 ($,).
15 ”.)
15 §);
15 ,/).
15 ,()
15 ).*
15 (“”);
15 ().,
15 ("/")
14 “”);
14 ?"),
14 :()
14 /").
14 .”)
14 ./.),
14 ./.)
14 ..,).
14 ..,)
14 )","":"(,
14 (_)
14 (?),
14 (;).
14 (...)."
14 (+,%,
14 (+);
14 '/);
14 &),
14 $)
14 "(,
13 “(
13 /.),
13 ./)"
13 .(;
13 .(...)"
13 (./.,
13 (,,
13 (''
13 (&
13 ($.
13 (""):
13 ".)
13 "):
13 !”).
12 ])
12 [])
12 ?”).
12 ,):
12 ).•
12 )'.
12 (’)
12 (§,
12 (§)
12 (@):
12 (...,
12 (.,)
12 (*
12 (').
12 (&,
12 ($.,
12 ($),
11 .../).
11 .(...).
11 .(.)
11 .(.
11 +/)
11 )•
11 ).,
11 (“:
11 (‘
11 (°),
11 (~
11 (@_),
11 (://..//)
11 (.,%
11 (*)
11 ()',
11 &).
11 %):
11 $,).
11 #)
11 !):
10 ²)
10 _)
10 ?!),
10 ?!)
10 :);
10 ./")
10 ..../).
10 ...);
10 ).".
10 )).
10 )),
10 )#
10 (…)
10 (×)
10 (§),
10 (@..)
10 (/;
10 (/:
10 (///)
10 (./):
10 (.../)
10 (.)"
10 ()#
10 (()
10 ($.,)
10 (")
10 ("'
10 (""),(//////.)
10 $).
10 !);
9 °);
9 @).
9 //.).
9 ..,);
9 .().
9 (…),
9 (³/),
9 (=)
9 (,")
9 (+/)
9 ().“
9 ()..
9 ($.)
9 ($,),
9 (":
9 (!,
9 $.,).
9 !”)
8 _/)
8 ]);
8 []).
8 []),
8 @_)
8 ?").
8 ?")
8 ://./)
8 //.);
8 //)..
8 /+)
8 /()
8 .;)
8 .//)
8 ./)",
8 .....).
8 ...").
8 ."(,
8 ).“
8 ).:
8 (−,%)
8 (↑%
8 (@.).
8 (;),
Another usage: list only the previous patterns which start with a closing bracket:
cat *.mixed.tokens.txt | grep -E --color=auto '[()]' | awk '{print $2}' | sed 's/[[:alnum:]-]//g' | grep '^).*$' | sort | uniq -c | sort | tac | awk '$1 >= 10'
50775 )
34230 ),
31194 ).
5469 );
2506 ):
676 )",
673 )".
604 )."
513 )?
317 )"
185 )”,
104 )”.
94 )!
54 )”
47 )/
43 )...
38 ).”
37 ))
34 )*
29 )";
25 ).
24 )..
23 )…
16 )'
15 ).*
14 )","":"(,
12 ).•
12 )'.
11 )•
11 ).,
10 ).".
10 )).
10 )),
10 )#
Another usage: the contrary.
cat *.mixed.tokens.txt | grep -E --color=auto '[()]' | awk '{print $2}' | sed 's/[[:alnum:]-]//g' | grep '^.*($' | sort | uniq -c | sort | tac | awk '$1 >= 5'
47512 (
186 .(
134 "(
73 ."(
21 :(
21 ".(
16 ((
13 “(
7 [(
7 ,(
6 ?(
6 ;(
6 ./(
6 .,(
6 ).(
5 ”(
5 /(
5 ..(
5 %(
Another usage: replace all groups of alphanumerics chars with 'a'.
cat *.mixed.tokens.txt | awk '{print $2}' | sed -E 's/[[:alnum:]-]+/a/g' | sort | uniq -c | sort | tac | head -n 100
507817 a,
353375 a.
99448 a:
95085 a
59447 a;
57525 "a
50199 a)
48918 a.a
48288 a?
47675 a,a
47599 a",
47215 (a
39301 “a
35448 a/a
35136 a".
34452 (a)
33975 a),
33481 a”,
32763 a"
30400 a).
28052 "a"
25635 “a”
24726 (a),
24025 a”
22246 a!
21300 a”.
18659 a."
18228 a,a%
16376 a/a,
14942 (a).
14562 a.a,
14464 'a
14233 a.a.a/a
13697 a,a.
12917 a'
10958 (a,
10103 "a",
9895 a.a/a,
9190 “a”,
8910 a/a.
8888 'a'
8579 a.a/a
8159 a/a/a
8074 a...
7795 a.a.
7649 a,a%.
7601 a.a.a
7468 a/a/a,
7284 a,a,
7014 a/a)
6943 a,a%,
6894 "a".
6636 a.a,a
6537 “a”.
6373 a.a.a.a.a
6312 #a
6258 a…
5909 a.”
5890 a',
5592 ‘a
5402 a);
5027 a/a/a.
4643 "a,
4519 a.a.a,
4273 ‘a’
4234 a’
3766 a]
3611 a.a.a.
3521 a'a
3325 a.a/a.
3157 a:a
2975 (a/a)
2916 @a
2880 [a
2843 (a);
2795 a.a;
2722 a://a.a/a
2663 a.a.a.a.a,
2574 (a,a%)
2537 a%
2476 a'.
2428 a):
2343 (a):
2282 a.a,a.
2232 a,a%;
2189 a"a.
2176 a/a/a)
2161 a/a/a).
2081 (a,a%),
2024 a’a
1978 “a,
1975 *a
1956 [a]
1937 a/a).
1896 a/a/a;
1892 a’,
1888 a.a)
1888 'a',
1792 (@a)
1788 a.a).
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
OUTPUT SAMPLE: