text_rank 1.1.7 → 1.2.5
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.codeclimate.yml +1 -6
- data/.rubocop.yml +60 -1075
- data/.ruby-version +1 -1
- data/.travis.yml +13 -5
- data/{LICENSE.txt → LICENSE} +0 -0
- data/README.md +2 -1
- data/bin/console +3 -3
- data/lib/page_rank.rb +2 -0
- data/lib/page_rank/base.rb +9 -8
- data/lib/page_rank/dense.rb +2 -1
- data/lib/page_rank/sparse.rb +6 -7
- data/lib/text_rank.rb +12 -9
- data/lib/text_rank/char_filter.rb +1 -1
- data/lib/text_rank/char_filter/ascii_folding.rb +5 -1
- data/lib/text_rank/char_filter/strip_possessive.rb +2 -2
- data/lib/text_rank/char_filter/undo_contractions.rb +1 -137
- data/lib/text_rank/char_filter/undo_contractions.yml +135 -0
- data/lib/text_rank/fingerprint.rb +20 -28
- data/lib/text_rank/fingerprint_overlap.rb +55 -0
- data/lib/text_rank/graph_strategy/coocurrence.rb +15 -6
- data/lib/text_rank/keyword_extractor.rb +32 -25
- data/lib/text_rank/rank_filter/collapse_adjacent.rb +53 -25
- data/lib/text_rank/rank_filter/normalize_probability.rb +2 -1
- data/lib/text_rank/rank_filter/normalize_unit_vector.rb +2 -1
- data/lib/text_rank/token_filter/part_of_speech.rb +0 -1
- data/lib/text_rank/token_filter/stopwords.rb +1 -321
- data/lib/text_rank/token_filter/stopwords.yml +317 -0
- data/lib/text_rank/tokenizer.rb +1 -1
- data/lib/text_rank/tokenizer/money.rb +11 -6
- data/lib/text_rank/tokenizer/number.rb +4 -3
- data/lib/text_rank/tokenizer/punctuation.rb +4 -1
- data/lib/text_rank/tokenizer/url.rb +3 -0
- data/lib/text_rank/tokenizer/whitespace.rb +4 -1
- data/lib/text_rank/tokenizer/word.rb +5 -2
- data/lib/text_rank/version.rb +3 -1
- data/text_rank.gemspec +10 -10
- metadata +48 -32
@@ -1,5 +1,3 @@
|
|
1
|
-
require 'set'
|
2
|
-
|
3
1
|
module TextRank
|
4
2
|
module TokenFilter
|
5
3
|
##
|
@@ -15,325 +13,7 @@ module TextRank
|
|
15
13
|
class Stopwords
|
16
14
|
|
17
15
|
# Default English stop-word list.
|
18
|
-
STOP_WORDS = Set.new(
|
19
|
-
a
|
20
|
-
about
|
21
|
-
above
|
22
|
-
across
|
23
|
-
after
|
24
|
-
afterwards
|
25
|
-
again
|
26
|
-
against
|
27
|
-
all
|
28
|
-
almost
|
29
|
-
alone
|
30
|
-
along
|
31
|
-
already
|
32
|
-
also
|
33
|
-
although
|
34
|
-
always
|
35
|
-
am
|
36
|
-
among
|
37
|
-
amongst
|
38
|
-
amoungst
|
39
|
-
amount
|
40
|
-
an
|
41
|
-
and
|
42
|
-
another
|
43
|
-
any
|
44
|
-
anyhow
|
45
|
-
anyone
|
46
|
-
anything
|
47
|
-
anyway
|
48
|
-
anywhere
|
49
|
-
are
|
50
|
-
around
|
51
|
-
as
|
52
|
-
at
|
53
|
-
back
|
54
|
-
be
|
55
|
-
became
|
56
|
-
because
|
57
|
-
become
|
58
|
-
becomes
|
59
|
-
becoming
|
60
|
-
been
|
61
|
-
before
|
62
|
-
beforehand
|
63
|
-
behind
|
64
|
-
being
|
65
|
-
below
|
66
|
-
beside
|
67
|
-
besides
|
68
|
-
between
|
69
|
-
beyond
|
70
|
-
bill
|
71
|
-
both
|
72
|
-
bottom
|
73
|
-
but
|
74
|
-
by
|
75
|
-
call
|
76
|
-
can
|
77
|
-
cannot
|
78
|
-
cant
|
79
|
-
co
|
80
|
-
con
|
81
|
-
could
|
82
|
-
couldnt
|
83
|
-
cry
|
84
|
-
de
|
85
|
-
describe
|
86
|
-
detail
|
87
|
-
do
|
88
|
-
done
|
89
|
-
down
|
90
|
-
due
|
91
|
-
during
|
92
|
-
each
|
93
|
-
eg
|
94
|
-
eight
|
95
|
-
either
|
96
|
-
eleven
|
97
|
-
else
|
98
|
-
elsewhere
|
99
|
-
empty
|
100
|
-
enough
|
101
|
-
etc
|
102
|
-
even
|
103
|
-
ever
|
104
|
-
every
|
105
|
-
everyone
|
106
|
-
everything
|
107
|
-
everywhere
|
108
|
-
except
|
109
|
-
few
|
110
|
-
fifteen
|
111
|
-
fify
|
112
|
-
fill
|
113
|
-
find
|
114
|
-
fire
|
115
|
-
first
|
116
|
-
five
|
117
|
-
for
|
118
|
-
former
|
119
|
-
formerly
|
120
|
-
forty
|
121
|
-
found
|
122
|
-
four
|
123
|
-
from
|
124
|
-
front
|
125
|
-
full
|
126
|
-
further
|
127
|
-
get
|
128
|
-
give
|
129
|
-
go
|
130
|
-
had
|
131
|
-
has
|
132
|
-
hasnt
|
133
|
-
have
|
134
|
-
he
|
135
|
-
hence
|
136
|
-
her
|
137
|
-
here
|
138
|
-
hereafter
|
139
|
-
hereby
|
140
|
-
herein
|
141
|
-
hereupon
|
142
|
-
hers
|
143
|
-
herself
|
144
|
-
him
|
145
|
-
himself
|
146
|
-
his
|
147
|
-
how
|
148
|
-
however
|
149
|
-
hundred
|
150
|
-
ie
|
151
|
-
if
|
152
|
-
in
|
153
|
-
inc
|
154
|
-
indeed
|
155
|
-
interest
|
156
|
-
into
|
157
|
-
is
|
158
|
-
it
|
159
|
-
its
|
160
|
-
itself
|
161
|
-
keep
|
162
|
-
last
|
163
|
-
latter
|
164
|
-
latterly
|
165
|
-
least
|
166
|
-
less
|
167
|
-
ltd
|
168
|
-
made
|
169
|
-
many
|
170
|
-
may
|
171
|
-
me
|
172
|
-
meanwhile
|
173
|
-
might
|
174
|
-
mill
|
175
|
-
mine
|
176
|
-
more
|
177
|
-
moreover
|
178
|
-
most
|
179
|
-
mostly
|
180
|
-
move
|
181
|
-
much
|
182
|
-
must
|
183
|
-
my
|
184
|
-
myself
|
185
|
-
name
|
186
|
-
namely
|
187
|
-
neither
|
188
|
-
never
|
189
|
-
nevertheless
|
190
|
-
next
|
191
|
-
nine
|
192
|
-
no
|
193
|
-
nobody
|
194
|
-
none
|
195
|
-
noone
|
196
|
-
nor
|
197
|
-
not
|
198
|
-
nothing
|
199
|
-
now
|
200
|
-
nowhere
|
201
|
-
of
|
202
|
-
off
|
203
|
-
often
|
204
|
-
on
|
205
|
-
once
|
206
|
-
one
|
207
|
-
only
|
208
|
-
onto
|
209
|
-
or
|
210
|
-
other
|
211
|
-
others
|
212
|
-
otherwise
|
213
|
-
our
|
214
|
-
ours
|
215
|
-
ourselves
|
216
|
-
out
|
217
|
-
over
|
218
|
-
own
|
219
|
-
part
|
220
|
-
per
|
221
|
-
perhaps
|
222
|
-
please
|
223
|
-
put
|
224
|
-
rather
|
225
|
-
re
|
226
|
-
same
|
227
|
-
see
|
228
|
-
seem
|
229
|
-
seemed
|
230
|
-
seeming
|
231
|
-
seems
|
232
|
-
serious
|
233
|
-
several
|
234
|
-
she
|
235
|
-
should
|
236
|
-
show
|
237
|
-
side
|
238
|
-
since
|
239
|
-
sincere
|
240
|
-
six
|
241
|
-
sixty
|
242
|
-
so
|
243
|
-
some
|
244
|
-
somehow
|
245
|
-
someone
|
246
|
-
something
|
247
|
-
sometime
|
248
|
-
sometimes
|
249
|
-
somewhere
|
250
|
-
still
|
251
|
-
such
|
252
|
-
system
|
253
|
-
take
|
254
|
-
ten
|
255
|
-
than
|
256
|
-
that
|
257
|
-
the
|
258
|
-
their
|
259
|
-
them
|
260
|
-
themselves
|
261
|
-
then
|
262
|
-
thence
|
263
|
-
there
|
264
|
-
thereafter
|
265
|
-
thereby
|
266
|
-
therefore
|
267
|
-
therein
|
268
|
-
thereupon
|
269
|
-
these
|
270
|
-
they
|
271
|
-
thickv
|
272
|
-
thin
|
273
|
-
third
|
274
|
-
this
|
275
|
-
those
|
276
|
-
though
|
277
|
-
three
|
278
|
-
through
|
279
|
-
throughout
|
280
|
-
thru
|
281
|
-
thus
|
282
|
-
to
|
283
|
-
together
|
284
|
-
too
|
285
|
-
top
|
286
|
-
toward
|
287
|
-
towards
|
288
|
-
twelve
|
289
|
-
twenty
|
290
|
-
two
|
291
|
-
un
|
292
|
-
under
|
293
|
-
until
|
294
|
-
up
|
295
|
-
upon
|
296
|
-
us
|
297
|
-
very
|
298
|
-
via
|
299
|
-
was
|
300
|
-
we
|
301
|
-
well
|
302
|
-
were
|
303
|
-
what
|
304
|
-
whatever
|
305
|
-
when
|
306
|
-
whence
|
307
|
-
whenever
|
308
|
-
where
|
309
|
-
whereafter
|
310
|
-
whereas
|
311
|
-
whereby
|
312
|
-
wherein
|
313
|
-
whereupon
|
314
|
-
wherever
|
315
|
-
whether
|
316
|
-
which
|
317
|
-
while
|
318
|
-
whither
|
319
|
-
who
|
320
|
-
whoever
|
321
|
-
whole
|
322
|
-
whom
|
323
|
-
whose
|
324
|
-
why
|
325
|
-
will
|
326
|
-
with
|
327
|
-
within
|
328
|
-
without
|
329
|
-
would
|
330
|
-
yet
|
331
|
-
you
|
332
|
-
your
|
333
|
-
yours
|
334
|
-
yourself
|
335
|
-
yourselves
|
336
|
-
])
|
16
|
+
STOP_WORDS = Set.new(YAML.load_file(File.expand_path('stopwords.yml', __dir__)))
|
337
17
|
|
338
18
|
# Perform the filter
|
339
19
|
# @param tokens [Array<String>]
|
@@ -0,0 +1,317 @@
|
|
1
|
+
- a
|
2
|
+
- about
|
3
|
+
- above
|
4
|
+
- across
|
5
|
+
- after
|
6
|
+
- afterwards
|
7
|
+
- again
|
8
|
+
- against
|
9
|
+
- all
|
10
|
+
- almost
|
11
|
+
- alone
|
12
|
+
- along
|
13
|
+
- already
|
14
|
+
- also
|
15
|
+
- although
|
16
|
+
- always
|
17
|
+
- am
|
18
|
+
- among
|
19
|
+
- amongst
|
20
|
+
- amoungst
|
21
|
+
- amount
|
22
|
+
- an
|
23
|
+
- and
|
24
|
+
- another
|
25
|
+
- any
|
26
|
+
- anyhow
|
27
|
+
- anyone
|
28
|
+
- anything
|
29
|
+
- anyway
|
30
|
+
- anywhere
|
31
|
+
- are
|
32
|
+
- around
|
33
|
+
- as
|
34
|
+
- at
|
35
|
+
- back
|
36
|
+
- be
|
37
|
+
- became
|
38
|
+
- because
|
39
|
+
- become
|
40
|
+
- becomes
|
41
|
+
- becoming
|
42
|
+
- been
|
43
|
+
- before
|
44
|
+
- beforehand
|
45
|
+
- behind
|
46
|
+
- being
|
47
|
+
- below
|
48
|
+
- beside
|
49
|
+
- besides
|
50
|
+
- between
|
51
|
+
- beyond
|
52
|
+
- bill
|
53
|
+
- both
|
54
|
+
- bottom
|
55
|
+
- but
|
56
|
+
- by
|
57
|
+
- call
|
58
|
+
- can
|
59
|
+
- cannot
|
60
|
+
- cant
|
61
|
+
- co
|
62
|
+
- con
|
63
|
+
- could
|
64
|
+
- couldnt
|
65
|
+
- cry
|
66
|
+
- de
|
67
|
+
- describe
|
68
|
+
- detail
|
69
|
+
- do
|
70
|
+
- done
|
71
|
+
- down
|
72
|
+
- due
|
73
|
+
- during
|
74
|
+
- each
|
75
|
+
- eg
|
76
|
+
- eight
|
77
|
+
- either
|
78
|
+
- eleven
|
79
|
+
- else
|
80
|
+
- elsewhere
|
81
|
+
- empty
|
82
|
+
- enough
|
83
|
+
- etc
|
84
|
+
- even
|
85
|
+
- ever
|
86
|
+
- every
|
87
|
+
- everyone
|
88
|
+
- everything
|
89
|
+
- everywhere
|
90
|
+
- except
|
91
|
+
- few
|
92
|
+
- fifteen
|
93
|
+
- fify
|
94
|
+
- fill
|
95
|
+
- find
|
96
|
+
- fire
|
97
|
+
- first
|
98
|
+
- five
|
99
|
+
- for
|
100
|
+
- former
|
101
|
+
- formerly
|
102
|
+
- forty
|
103
|
+
- found
|
104
|
+
- four
|
105
|
+
- from
|
106
|
+
- front
|
107
|
+
- full
|
108
|
+
- further
|
109
|
+
- get
|
110
|
+
- give
|
111
|
+
- go
|
112
|
+
- had
|
113
|
+
- has
|
114
|
+
- hasnt
|
115
|
+
- have
|
116
|
+
- he
|
117
|
+
- hence
|
118
|
+
- her
|
119
|
+
- here
|
120
|
+
- hereafter
|
121
|
+
- hereby
|
122
|
+
- herein
|
123
|
+
- hereupon
|
124
|
+
- hers
|
125
|
+
- herself
|
126
|
+
- him
|
127
|
+
- himself
|
128
|
+
- his
|
129
|
+
- how
|
130
|
+
- however
|
131
|
+
- hundred
|
132
|
+
- ie
|
133
|
+
- if
|
134
|
+
- in
|
135
|
+
- inc
|
136
|
+
- indeed
|
137
|
+
- interest
|
138
|
+
- into
|
139
|
+
- is
|
140
|
+
- it
|
141
|
+
- its
|
142
|
+
- itself
|
143
|
+
- keep
|
144
|
+
- last
|
145
|
+
- latter
|
146
|
+
- latterly
|
147
|
+
- least
|
148
|
+
- less
|
149
|
+
- ltd
|
150
|
+
- made
|
151
|
+
- many
|
152
|
+
- may
|
153
|
+
- me
|
154
|
+
- meanwhile
|
155
|
+
- might
|
156
|
+
- mill
|
157
|
+
- mine
|
158
|
+
- more
|
159
|
+
- moreover
|
160
|
+
- most
|
161
|
+
- mostly
|
162
|
+
- move
|
163
|
+
- much
|
164
|
+
- must
|
165
|
+
- my
|
166
|
+
- myself
|
167
|
+
- name
|
168
|
+
- namely
|
169
|
+
- neither
|
170
|
+
- never
|
171
|
+
- nevertheless
|
172
|
+
- next
|
173
|
+
- nine
|
174
|
+
- no
|
175
|
+
- nobody
|
176
|
+
- none
|
177
|
+
- noone
|
178
|
+
- nor
|
179
|
+
- not
|
180
|
+
- nothing
|
181
|
+
- now
|
182
|
+
- nowhere
|
183
|
+
- of
|
184
|
+
- off
|
185
|
+
- often
|
186
|
+
- on
|
187
|
+
- once
|
188
|
+
- one
|
189
|
+
- only
|
190
|
+
- onto
|
191
|
+
- or
|
192
|
+
- other
|
193
|
+
- others
|
194
|
+
- otherwise
|
195
|
+
- our
|
196
|
+
- ours
|
197
|
+
- ourselves
|
198
|
+
- out
|
199
|
+
- over
|
200
|
+
- own
|
201
|
+
- part
|
202
|
+
- per
|
203
|
+
- perhaps
|
204
|
+
- please
|
205
|
+
- put
|
206
|
+
- rather
|
207
|
+
- re
|
208
|
+
- same
|
209
|
+
- see
|
210
|
+
- seem
|
211
|
+
- seemed
|
212
|
+
- seeming
|
213
|
+
- seems
|
214
|
+
- serious
|
215
|
+
- several
|
216
|
+
- she
|
217
|
+
- should
|
218
|
+
- show
|
219
|
+
- side
|
220
|
+
- since
|
221
|
+
- sincere
|
222
|
+
- six
|
223
|
+
- sixty
|
224
|
+
- so
|
225
|
+
- some
|
226
|
+
- somehow
|
227
|
+
- someone
|
228
|
+
- something
|
229
|
+
- sometime
|
230
|
+
- sometimes
|
231
|
+
- somewhere
|
232
|
+
- still
|
233
|
+
- such
|
234
|
+
- system
|
235
|
+
- take
|
236
|
+
- ten
|
237
|
+
- than
|
238
|
+
- that
|
239
|
+
- the
|
240
|
+
- their
|
241
|
+
- them
|
242
|
+
- themselves
|
243
|
+
- then
|
244
|
+
- thence
|
245
|
+
- there
|
246
|
+
- thereafter
|
247
|
+
- thereby
|
248
|
+
- therefore
|
249
|
+
- therein
|
250
|
+
- thereupon
|
251
|
+
- these
|
252
|
+
- they
|
253
|
+
- thickv
|
254
|
+
- thin
|
255
|
+
- third
|
256
|
+
- this
|
257
|
+
- those
|
258
|
+
- though
|
259
|
+
- three
|
260
|
+
- through
|
261
|
+
- throughout
|
262
|
+
- thru
|
263
|
+
- thus
|
264
|
+
- to
|
265
|
+
- together
|
266
|
+
- too
|
267
|
+
- top
|
268
|
+
- toward
|
269
|
+
- towards
|
270
|
+
- twelve
|
271
|
+
- twenty
|
272
|
+
- two
|
273
|
+
- un
|
274
|
+
- under
|
275
|
+
- until
|
276
|
+
- up
|
277
|
+
- upon
|
278
|
+
- us
|
279
|
+
- very
|
280
|
+
- via
|
281
|
+
- was
|
282
|
+
- we
|
283
|
+
- well
|
284
|
+
- were
|
285
|
+
- what
|
286
|
+
- whatever
|
287
|
+
- when
|
288
|
+
- whence
|
289
|
+
- whenever
|
290
|
+
- where
|
291
|
+
- whereafter
|
292
|
+
- whereas
|
293
|
+
- whereby
|
294
|
+
- wherein
|
295
|
+
- whereupon
|
296
|
+
- wherever
|
297
|
+
- whether
|
298
|
+
- which
|
299
|
+
- while
|
300
|
+
- whither
|
301
|
+
- who
|
302
|
+
- whoever
|
303
|
+
- whole
|
304
|
+
- whom
|
305
|
+
- whose
|
306
|
+
- why
|
307
|
+
- will
|
308
|
+
- with
|
309
|
+
- within
|
310
|
+
- without
|
311
|
+
- would
|
312
|
+
- yet
|
313
|
+
- you
|
314
|
+
- your
|
315
|
+
- yours
|
316
|
+
- yourself
|
317
|
+
- yourselves
|