1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344
|
package en
import (
"github.com/blevesearch/bleve/analysis"
"github.com/blevesearch/bleve/registry"
)
const StopName = "stop_en"
// EnglishStopWords is the built-in list of stopwords used by the "stop_en" TokenFilter.
//
// this content was obtained from:
// lucene-4.7.2/analysis/common/src/resources/org/apache/lucene/analysis/snowball/
// ` was changed to ' to allow for literal string
var EnglishStopWords = []byte(` | From svn.tartarus.org/snowball/trunk/website/algorithms/english/stop.txt
| This file is distributed under the BSD License.
| See http://snowball.tartarus.org/license.php
| Also see http://www.opensource.org/licenses/bsd-license.html
| - Encoding was converted to UTF-8.
| - This notice was added.
|
| NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
| An English stop word list. Comments begin with vertical bar. Each stop
| word is at the start of a line.
| Many of the forms below are quite rare (e.g. "yourselves") but included for
| completeness.
| PRONOUNS FORMS
| 1st person sing
i | subject, always in upper case of course
me | object
my | possessive adjective
| the possessive pronoun 'mine' is best suppressed, because of the
| sense of coal-mine etc.
myself | reflexive
| 1st person plural
we | subject
| us | object
| care is required here because US = United States. It is usually
| safe to remove it if it is in lower case.
our | possessive adjective
ours | possessive pronoun
ourselves | reflexive
| second person (archaic 'thou' forms not included)
you | subject and object
your | possessive adjective
yours | possessive pronoun
yourself | reflexive (singular)
yourselves | reflexive (plural)
| third person singular
he | subject
him | object
his | possessive adjective and pronoun
himself | reflexive
she | subject
her | object and possessive adjective
hers | possessive pronoun
herself | reflexive
it | subject and object
its | possessive adjective
itself | reflexive
| third person plural
they | subject
them | object
their | possessive adjective
theirs | possessive pronoun
themselves | reflexive
| other forms (demonstratives, interrogatives)
what
which
who
whom
this
that
these
those
| VERB FORMS (using F.R. Palmer's nomenclature)
| BE
am | 1st person, present
is | -s form (3rd person, present)
are | present
was | 1st person, past
were | past
be | infinitive
been | past participle
being | -ing form
| HAVE
have | simple
has | -s form
had | past
having | -ing form
| DO
do | simple
does | -s form
did | past
doing | -ing form
| The forms below are, I believe, best omitted, because of the significant
| homonym forms:
| He made a WILL
| old tin CAN
| merry month of MAY
| a smell of MUST
| fight the good fight with all thy MIGHT
| would, could, should, ought might however be included
| | AUXILIARIES
| | WILL
|will
would
| | SHALL
|shall
should
| | CAN
|can
could
| | MAY
|may
|might
| | MUST
|must
| | OUGHT
ought
| COMPOUND FORMS, increasingly encountered nowadays in 'formal' writing
| pronoun + verb
i'm
you're
he's
she's
it's
we're
they're
i've
you've
we've
they've
i'd
you'd
he'd
she'd
we'd
they'd
i'll
you'll
he'll
she'll
we'll
they'll
| verb + negation
isn't
aren't
wasn't
weren't
hasn't
haven't
hadn't
doesn't
don't
didn't
| auxiliary + negation
won't
wouldn't
shan't
shouldn't
can't
cannot
couldn't
mustn't
| miscellaneous forms
let's
that's
who's
what's
here's
there's
when's
where's
why's
how's
| rarer forms
| daren't needn't
| doubtful forms
| oughtn't mightn't
| ARTICLES
a
an
the
| THE REST (Overlap among prepositions, conjunctions, adverbs etc is so
| high, that classification is pointless.)
and
but
if
or
because
as
until
while
of
at
by
for
with
about
against
between
into
through
during
before
after
above
below
to
from
up
down
in
out
on
off
over
under
again
further
then
once
here
there
when
where
why
how
all
any
both
each
few
more
most
other
some
such
no
nor
not
only
own
same
so
than
too
very
| Just for the record, the following words are among the commonest in English
| one
| every
| least
| less
| many
| now
| ever
| never
| say
| says
| said
| also
| get
| go
| goes
| just
| made
| make
| put
| see
| seen
| whether
| like
| well
| back
| even
| still
| way
| take
| since
| another
| however
| two
| three
| four
| five
| first
| second
| new
| old
| high
| long
`)
func TokenMapConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenMap, error) {
rv := analysis.NewTokenMap()
err := rv.LoadBytes(EnglishStopWords)
return rv, err
}
func init() {
registry.RegisterTokenMap(StopName, TokenMapConstructor)
}
|