Skip to content
GitLab
Menu
Projects
Groups
Snippets
/
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
Neeme Kahusk
Lightewn
Commits
c54b3555
Commit
c54b3555
authored
Jun 26, 2015
by
Neeme Kahusk
Browse files
unique synset numbers
parent
3d582add
Changes
2
Hide whitespace changes
Inline
Side-by-side
tools/make-indexes.sh-mac
View file @
c54b3555
...
...
@@ -25,7 +25,7 @@ if [ "$NO_OF_ORIGSYNSETS" -eq "$NO_OF_UNIQESYNSETS" ] ; then
else
echo
"Synset numbers ARE NOT unique"
cat
$1
|grep
'^0'
|sed
-E
's/(0 @)([0-9]+)(@.+$)/\2/g'
|sort|uniq
>
all.numbers
cat
$1
|grep
'^0'
|sed
-E
's/(0 @)([0-9]+)(@.+$)/\2/g'
|sort|uniq
-c
|sort
-nr
|egrep
'^ {3}
2
'
|sed
-E
's/^ {3}
2
//g'
>
doubled.numbers
cat
$1
|grep
'^0'
|sed
-E
's/(0 @)([0-9]+)(@.+$)/\2/g'
|sort|uniq
-c
|sort
-nr
|egrep
'^ {3}
[2-9]
'
|sed
-E
's/^ {3}
[2-9]
//g'
>
doubled.numbers
# rm all.numbers
# rm doubled.numbers
...
...
tools/unique_synsets.py
View file @
c54b3555
...
...
@@ -34,14 +34,27 @@ def read_raw(filename):
al
=
read_raw
(
ALL_NUMBERS_FN
)
maximal
=
max
(
al
)
doub
=
read_raw
(
DOUBLED_NUMBERS_FN
)
taken
=
[]
print
al
print
doub
#
print al
#
print doub
print
len
(
al
)
print
len
(
doub
)
#
print len(al)
#
print len(doub)
p
=
eurown
.
Parser
(
WN_FN
)
s
=
p
.
parse_synset
()
print
s
.
polarisText
# s = p.parse_synset()
# print s.polarisText
sl
=
p
.
parse_wordnet
()
for
i
in
sl
:
if
i
.
number
in
doub
:
if
i
.
number
in
taken
:
i
.
number
=
maximal
+
1
maximal
=
i
.
number
taken
.
append
(
i
.
number
)
print
i
.
polarisText
Write
Preview
Supports
Markdown
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment