c526a38369
ultimately this is make it more convenient for us to wire up different elements of the analysis pipeline, without having to preload everything into memory before we need it separately the index layer now has a mechanism for storing internal key/value pairs. this is expected to be used to store the mapping, and possibly other pieces of data by the top layer, but not exposed to the user at the top.
144 lines
5.1 KiB
Go
144 lines
5.1 KiB
Go
package nl
|
|
|
|
import (
|
|
"github.com/couchbaselabs/bleve/analysis"
|
|
"github.com/couchbaselabs/bleve/registry"
|
|
)
|
|
|
|
const StopName = "stop_nl"
|
|
|
|
// 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 DutchStopWords = []byte(` | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/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"
|
|
|
|
| A Dutch stop word list. Comments begin with vertical bar. Each stop
|
|
| word is at the start of a line.
|
|
|
|
| This is a ranked list (commonest to rarest) of stopwords derived from
|
|
| a large sample of Dutch text.
|
|
|
|
| Dutch stop words frequently exhibit homonym clashes. These are indicated
|
|
| clearly below.
|
|
|
|
de | the
|
|
en | and
|
|
van | of, from
|
|
ik | I, the ego
|
|
te | (1) chez, at etc, (2) to, (3) too
|
|
dat | that, which
|
|
die | that, those, who, which
|
|
in | in, inside
|
|
een | a, an, one
|
|
hij | he
|
|
het | the, it
|
|
niet | not, nothing, naught
|
|
zijn | (1) to be, being, (2) his, one's, its
|
|
is | is
|
|
was | (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
|
|
op | on, upon, at, in, up, used up
|
|
aan | on, upon, to (as dative)
|
|
met | with, by
|
|
als | like, such as, when
|
|
voor | (1) before, in front of, (2) furrow
|
|
had | had, past tense all persons sing. of 'hebben' (have)
|
|
er | there
|
|
maar | but, only
|
|
om | round, about, for etc
|
|
hem | him
|
|
dan | then
|
|
zou | should/would, past tense all persons sing. of 'zullen'
|
|
of | or, whether, if
|
|
wat | what, something, anything
|
|
mijn | possessive and noun 'mine'
|
|
men | people, 'one'
|
|
dit | this
|
|
zo | so, thus, in this way
|
|
door | through by
|
|
over | over, across
|
|
ze | she, her, they, them
|
|
zich | oneself
|
|
bij | (1) a bee, (2) by, near, at
|
|
ook | also, too
|
|
tot | till, until
|
|
je | you
|
|
mij | me
|
|
uit | out of, from
|
|
der | Old Dutch form of 'van der' still found in surnames
|
|
daar | (1) there, (2) because
|
|
haar | (1) her, their, them, (2) hair
|
|
naar | (1) unpleasant, unwell etc, (2) towards, (3) as
|
|
heb | present first person sing. of 'to have'
|
|
hoe | how, why
|
|
heeft | present third person sing. of 'to have'
|
|
hebben | 'to have' and various parts thereof
|
|
deze | this
|
|
u | you
|
|
want | (1) for, (2) mitten, (3) rigging
|
|
nog | yet, still
|
|
zal | 'shall', first and third person sing. of verb 'zullen' (will)
|
|
me | me
|
|
zij | she, they
|
|
nu | now
|
|
ge | 'thou', still used in Belgium and south Netherlands
|
|
geen | none
|
|
omdat | because
|
|
iets | something, somewhat
|
|
worden | to become, grow, get
|
|
toch | yet, still
|
|
al | all, every, each
|
|
waren | (1) 'were' (2) to wander, (3) wares, (3)
|
|
veel | much, many
|
|
meer | (1) more, (2) lake
|
|
doen | to do, to make
|
|
toen | then, when
|
|
moet | noun 'spot/mote' and present form of 'to must'
|
|
ben | (1) am, (2) 'are' in interrogative second person singular of 'to be'
|
|
zonder | without
|
|
kan | noun 'can' and present form of 'to be able'
|
|
hun | their, them
|
|
dus | so, consequently
|
|
alles | all, everything, anything
|
|
onder | under, beneath
|
|
ja | yes, of course
|
|
eens | once, one day
|
|
hier | here
|
|
wie | who
|
|
werd | imperfect third person sing. of 'become'
|
|
altijd | always
|
|
doch | yet, but etc
|
|
wordt | present third person sing. of 'become'
|
|
wezen | (1) to be, (2) 'been' as in 'been fishing', (3) orphans
|
|
kunnen | to be able
|
|
ons | us/our
|
|
zelf | self
|
|
tegen | against, towards, at
|
|
na | after, near
|
|
reeds | already
|
|
wil | (1) present tense of 'want', (2) 'will', noun, (3) fender
|
|
kon | could; past tense of 'to be able'
|
|
niets | nothing
|
|
uw | your
|
|
iemand | somebody
|
|
geweest | been; past participle of 'be'
|
|
andere | other
|
|
`)
|
|
|
|
func TokenMapConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenMap, error) {
|
|
rv := analysis.NewTokenMap()
|
|
err := rv.LoadBytes(DutchStopWords)
|
|
return rv, err
|
|
}
|
|
|
|
func init() {
|
|
registry.RegisterTokenMap(StopName, TokenMapConstructor)
|
|
}
|