Add exploreTestConfig, a new Solr configuration folder
parent
b84e0cabeb
commit
de81007302
@ -0,0 +1,31 @@
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
-->
|
||||
|
||||
<!-- If this file is found in the config directory, it will only be
|
||||
loaded once at startup. If it is found in Solr's data
|
||||
directory, it will be re-loaded every commit.
|
||||
|
||||
See http://wiki.apache.org/solr/QueryElevationComponent for more info
|
||||
|
||||
-->
|
||||
<elevate>
|
||||
<!-- Query elevation examples
|
||||
<query text="foo bar">
|
||||
<doc id="1" />
|
||||
<doc id="2" />
|
||||
<doc id="3" />
|
||||
</query>
|
||||
|
||||
for use with techproducts example
|
||||
|
||||
<query text="ipod">
|
||||
<doc id="MA147LL/A" /> put the actual ipod at the top
|
||||
<doc id="IW-02" exclude="true" /> exclude this cable
|
||||
</query>
|
||||
-->
|
||||
|
||||
</elevate>
|
@ -0,0 +1,8 @@
|
||||
# Set of Catalan contractions for ElisionFilter
|
||||
# TODO: load this as a resource from the analyzer and sync it in build.xml
|
||||
d
|
||||
l
|
||||
m
|
||||
n
|
||||
s
|
||||
t
|
@ -0,0 +1,15 @@
|
||||
# Set of French contractions for ElisionFilter
|
||||
# TODO: load this as a resource from the analyzer and sync it in build.xml
|
||||
l
|
||||
m
|
||||
t
|
||||
qu
|
||||
n
|
||||
s
|
||||
j
|
||||
d
|
||||
c
|
||||
jusqu
|
||||
quoiqu
|
||||
lorsqu
|
||||
puisqu
|
@ -0,0 +1,5 @@
|
||||
# Set of Irish contractions for ElisionFilter
|
||||
# TODO: load this as a resource from the analyzer and sync it in build.xml
|
||||
d
|
||||
m
|
||||
b
|
@ -0,0 +1,23 @@
|
||||
# Set of Italian contractions for ElisionFilter
|
||||
# TODO: load this as a resource from the analyzer and sync it in build.xml
|
||||
c
|
||||
l
|
||||
all
|
||||
dall
|
||||
dell
|
||||
nell
|
||||
sull
|
||||
coll
|
||||
pell
|
||||
gl
|
||||
agl
|
||||
dagl
|
||||
degl
|
||||
negl
|
||||
sugl
|
||||
un
|
||||
m
|
||||
t
|
||||
s
|
||||
v
|
||||
d
|
@ -0,0 +1,5 @@
|
||||
# Set of Irish hyphenations for StopFilter
|
||||
# TODO: load this as a resource from the analyzer and sync it in build.xml
|
||||
h
|
||||
n
|
||||
t
|
@ -0,0 +1,6 @@
|
||||
# Set of overrides for the dutch stemmer
|
||||
# TODO: load this as a resource from the analyzer and sync it in build.xml
|
||||
fiets fiets
|
||||
bromfiets bromfiets
|
||||
ei eier
|
||||
kind kinder
|
@ -0,0 +1,220 @@
|
||||
# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
|
||||
a
|
||||
abans
|
||||
ací
|
||||
ah
|
||||
així
|
||||
això
|
||||
al
|
||||
als
|
||||
aleshores
|
||||
algun
|
||||
alguna
|
||||
algunes
|
||||
alguns
|
||||
alhora
|
||||
allà
|
||||
allí
|
||||
allò
|
||||
altra
|
||||
altre
|
||||
altres
|
||||
amb
|
||||
ambdós
|
||||
ambdues
|
||||
apa
|
||||
aquell
|
||||
aquella
|
||||
aquelles
|
||||
aquells
|
||||
aquest
|
||||
aquesta
|
||||
aquestes
|
||||
aquests
|
||||
aquí
|
||||
baix
|
||||
cada
|
||||
cadascú
|
||||
cadascuna
|
||||
cadascunes
|
||||
cadascuns
|
||||
com
|
||||
contra
|
||||
d'un
|
||||
d'una
|
||||
d'unes
|
||||
d'uns
|
||||
dalt
|
||||
de
|
||||
del
|
||||
dels
|
||||
des
|
||||
després
|
||||
dins
|
||||
dintre
|
||||
donat
|
||||
doncs
|
||||
durant
|
||||
e
|
||||
eh
|
||||
el
|
||||
els
|
||||
em
|
||||
en
|
||||
encara
|
||||
ens
|
||||
entre
|
||||
érem
|
||||
eren
|
||||
éreu
|
||||
es
|
||||
és
|
||||
esta
|
||||
està
|
||||
estàvem
|
||||
estaven
|
||||
estàveu
|
||||
esteu
|
||||
et
|
||||
etc
|
||||
ets
|
||||
fins
|
||||
fora
|
||||
gairebé
|
||||
ha
|
||||
han
|
||||
has
|
||||
havia
|
||||
he
|
||||
hem
|
||||
heu
|
||||
hi
|
||||
ho
|
||||
i
|
||||
igual
|
||||
iguals
|
||||
ja
|
||||
l'hi
|
||||
la
|
||||
les
|
||||
li
|
||||
li'n
|
||||
llavors
|
||||
m'he
|
||||
ma
|
||||
mal
|
||||
malgrat
|
||||
mateix
|
||||
mateixa
|
||||
mateixes
|
||||
mateixos
|
||||
me
|
||||
mentre
|
||||
més
|
||||
meu
|
||||
meus
|
||||
meva
|
||||
meves
|
||||
molt
|
||||
molta
|
||||
moltes
|
||||
molts
|
||||
mon
|
||||
mons
|
||||
n'he
|
||||
n'hi
|
||||
ne
|
||||
ni
|
||||
no
|
||||
nogensmenys
|
||||
només
|
||||
nosaltres
|
||||
nostra
|
||||
nostre
|
||||
nostres
|
||||
o
|
||||
oh
|
||||
oi
|
||||
on
|
||||
pas
|
||||
pel
|
||||
pels
|
||||
per
|
||||
però
|
||||
perquè
|
||||
poc
|
||||
poca
|
||||
pocs
|
||||
poques
|
||||
potser
|
||||
propi
|
||||
qual
|
||||
quals
|
||||
quan
|
||||
quant
|
||||
que
|
||||
què
|
||||
quelcom
|
||||
qui
|
||||
quin
|
||||
quina
|
||||
quines
|
||||
quins
|
||||
s'ha
|
||||
s'han
|
||||
sa
|
||||
semblant
|
||||
semblants
|
||||
ses
|
||||
seu
|
||||
seus
|
||||
seva
|
||||
seva
|
||||
seves
|
||||
si
|
||||
sobre
|
||||
sobretot
|
||||
sóc
|
||||
solament
|
||||
sols
|
||||
son
|
||||
són
|
||||
sons
|
||||
sota
|
||||
sou
|
||||
t'ha
|
||||
t'han
|
||||
t'he
|
||||
ta
|
||||
tal
|
||||
també
|
||||
tampoc
|
||||
tan
|
||||
tant
|
||||
tanta
|
||||
tantes
|
||||
teu
|
||||
teus
|
||||
teva
|
||||
teves
|
||||
ton
|
||||
tons
|
||||
tot
|
||||
tota
|
||||
totes
|
||||
tots
|
||||
un
|
||||
una
|
||||
unes
|
||||
uns
|
||||
us
|
||||
va
|
||||
vaig
|
||||
vam
|
||||
van
|
||||
vas
|
||||
veu
|
||||
vosaltres
|
||||
vostra
|
||||
vostre
|
||||
vostres
|
@ -0,0 +1,172 @@
|
||||
a
|
||||
s
|
||||
k
|
||||
o
|
||||
i
|
||||
u
|
||||
v
|
||||
z
|
||||
dnes
|
||||
cz
|
||||
tímto
|
||||
budeš
|
||||
budem
|
||||
byli
|
||||
jseš
|
||||
můj
|
||||
svým
|
||||
ta
|
||||
tomto
|
||||
tohle
|
||||
tuto
|
||||
tyto
|
||||
jej
|
||||
zda
|
||||
proč
|
||||
máte
|
||||
tato
|
||||
kam
|
||||
tohoto
|
||||
kdo
|
||||
kteří
|
||||
mi
|
||||
nám
|
||||
tom
|
||||
tomuto
|
||||
mít
|
||||
nic
|
||||
proto
|
||||
kterou
|
||||
byla
|
||||
toho
|
||||
protože
|
||||
asi
|
||||
ho
|
||||
naši
|
||||
napište
|
||||
re
|
||||
což
|
||||
tím
|
||||
takže
|
||||
svých
|
||||
její
|
||||
svými
|
||||
jste
|
||||
aj
|
||||
tu
|
||||
tedy
|
||||
teto
|
||||
bylo
|
||||
kde
|
||||
ke
|
||||
pravé
|
||||
ji
|
||||
nad
|
||||
nejsou
|
||||
či
|
||||
pod
|
||||
téma
|
||||
mezi
|
||||
přes
|
||||
ty
|
||||
pak
|
||||
vám
|
||||
ani
|
||||
když
|
||||
však
|
||||
neg
|
||||
jsem
|
||||
tento
|
||||
článku
|
||||
články
|
||||
aby
|
||||
jsme
|
||||
před
|
||||
pta
|
||||
jejich
|
||||
byl
|
||||
ještě
|
||||
až
|
||||
bez
|
||||
také
|
||||
pouze
|
||||
první
|
||||
vaše
|
||||
která
|
||||
nás
|
||||
nový
|
||||
tipy
|
||||
pokud
|
||||
může
|
||||
strana
|
||||
jeho
|
||||
své
|
||||
jiné
|
||||
zprávy
|
||||
nové
|
||||
není
|
||||
vás
|
||||
jen
|
||||
podle
|
||||
zde
|
||||
už
|
||||
být
|
||||
více
|
||||
bude
|
||||
již
|
||||
než
|
||||
který
|
||||
by
|
||||
které
|
||||
co
|
||||
nebo
|
||||
ten
|
||||
tak
|
||||
má
|
||||
při
|
||||
od
|
||||
po
|
||||
jsou
|
||||
jak
|
||||
další
|
||||
ale
|
||||
si
|
||||
se
|
||||
ve
|
||||
to
|
||||
jako
|
||||
za
|
||||
zpět
|
||||
ze
|
||||
do
|
||||
pro
|
||||
je
|
||||
na
|
||||
atd
|
||||
atp
|
||||
jakmile
|
||||
přičemž
|
||||
já
|
||||
on
|
||||
ona
|
||||
ono
|
||||
oni
|
||||
ony
|
||||
my
|
||||
vy
|
||||
jí
|
||||
ji
|
||||
mě
|
||||
mne
|
||||
jemu
|
||||
tomu
|
||||
těm
|
||||
těmu
|
||||
němu
|
||||
němuž
|
||||
jehož
|
||||
jíž
|
||||
jelikož
|
||||
jež
|
||||
jakož
|
||||
načež
|
@ -0,0 +1,110 @@
|
||||
| From svn.tartarus.org/snowball/trunk/website/algorithms/danish/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 Danish 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 text sample.
|
||||
|
||||
|
||||
og | and
|
||||
i | in
|
||||
jeg | I
|
||||
det | that (dem. pronoun)/it (pers. pronoun)
|
||||
at | that (in front of a sentence)/to (with infinitive)
|
||||
en | a/an
|
||||
den | it (pers. pronoun)/that (dem. pronoun)
|
||||
til | to/at/for/until/against/by/of/into, more
|
||||
er | present tense of "to be"
|
||||
som | who, as
|
||||
på | on/upon/in/on/at/to/after/of/with/for, on
|
||||
de | they
|
||||
med | with/by/in, along
|
||||
han | he
|
||||
af | of/by/from/off/for/in/with/on, off
|
||||
for | at/for/to/from/by/of/ago, in front/before, because
|
||||
ikke | not
|
||||
der | who/which, there/those
|
||||
var | past tense of "to be"
|
||||
mig | me/myself
|
||||
sig | oneself/himself/herself/itself/themselves
|
||||
men | but
|
||||
et | a/an/one, one (number), someone/somebody/one
|
||||
har | present tense of "to have"
|
||||
om | round/about/for/in/a, about/around/down, if
|
||||
vi | we
|
||||
min | my
|
||||
havde | past tense of "to have"
|
||||
ham | him
|
||||
hun | she
|
||||
nu | now
|
||||
over | over/above/across/by/beyond/past/on/about, over/past
|
||||
da | then, when/as/since
|
||||
fra | from/off/since, off, since
|
||||
du | you
|
||||
ud | out
|
||||
sin | his/her/its/one's
|
||||
dem | them
|
||||
os | us/ourselves
|
||||
op | up
|
||||
man | you/one
|
||||
hans | his
|
||||
hvor | where
|
||||
eller | or
|
||||
hvad | what
|
||||
skal | must/shall etc.
|
||||
selv | myself/youself/herself/ourselves etc., even
|
||||
her | here
|
||||
alle | all/everyone/everybody etc.
|
||||
vil | will (verb)
|
||||
blev | past tense of "to stay/to remain/to get/to become"
|
||||
kunne | could
|
||||
ind | in
|
||||
når | when
|
||||
være | present tense of "to be"
|
||||
dog | however/yet/after all
|
||||
noget | something
|
||||
ville | would
|
||||
jo | you know/you see (adv), yes
|
||||
deres | their/theirs
|
||||
efter | after/behind/according to/for/by/from, later/afterwards
|
||||
ned | down
|
||||
skulle | should
|
||||
denne | this
|
||||
end | than
|
||||
dette | this
|
||||
mit | my/mine
|
||||
også | also
|
||||
under | under/beneath/below/during, below/underneath
|
||||
have | have
|
||||
dig | you
|
||||
anden | other
|
||||
hende | her
|
||||
mine | my
|
||||
alt | everything
|
||||
meget | much/very, plenty of
|
||||
sit | his, her, its, one's
|
||||
sine | his, her, its, one's
|
||||
vor | our
|
||||
mod | against
|
||||
disse | these
|
||||
hvis | if
|
||||
din | your/yours
|
||||
nogle | some
|
||||
hos | by/at
|
||||
blive | be/become
|
||||
mange | many
|
||||
ad | by/through
|
||||
bliver | present tense of "to be/to become"
|
||||
hendes | her/hers
|
||||
været | be
|
||||
thi | for (conj)
|
||||
jer | you
|
||||
sådan | such, like this/like that
|
@ -0,0 +1,294 @@
|
||||
| From svn.tartarus.org/snowball/trunk/website/algorithms/german/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 German stop word list. Comments begin with vertical bar. Each stop
|
||||
| word is at the start of a line.
|
||||
|
||||
| The number of forms in this list is reduced significantly by passing it
|
||||
| through the German stemmer.
|
||||
|
||||
|
||||
aber | but
|
||||
|
||||
alle | all
|
||||
allem
|
||||
allen
|
||||
aller
|
||||
alles
|
||||
|
||||
als | than, as
|
||||
also | so
|
||||
am | an + dem
|
||||
an | at
|
||||
|
||||
ander | other
|
||||
andere
|
||||
anderem
|
||||
anderen
|
||||
anderer
|
||||
anderes
|
||||
anderm
|
||||
andern
|
||||
anderr
|
||||
anders
|
||||
|
||||
auch | also
|
||||
auf | on
|
||||
aus | out of
|
||||
bei | by
|
||||
bin | am
|
||||
bis | until
|
||||
bist | art
|
||||
da | there
|
||||
damit | with it
|
||||
dann | then
|
||||
|
||||
der | the
|
||||
den
|
||||
des
|
||||
dem
|
||||
die
|
||||
das
|
||||
|
||||
daß | that
|
||||
|
||||
derselbe | the same
|
||||
derselben
|
||||
denselben
|
||||
desselben
|
||||
demselben
|
||||
dieselbe
|
||||
dieselben
|
||||
dasselbe
|
||||
|
||||
dazu | to that
|
||||
|
||||
dein | thy
|
||||
deine
|
||||
deinem
|
||||
deinen
|
||||
deiner
|
||||
deines
|
||||
|
||||
denn | because
|
||||
|
||||
derer | of those
|
||||
dessen | of him
|
||||
|
||||
dich | thee
|
||||
dir | to thee
|
||||
du | thou
|
||||
|
||||
dies | this
|
||||
diese
|
||||
diesem
|
||||
diesen
|
||||
dieser
|
||||
dieses
|
||||
|
||||
|
||||
doch | (several meanings)
|
||||
dort | (over) there
|
||||
|
||||
|
||||
durch | through
|
||||
|
||||
ein | a
|
||||
eine
|
||||
einem
|
||||
einen
|
||||
einer
|
||||
eines
|
||||
|
||||
einig | some
|
||||
einige
|
||||
einigem
|
||||
einigen
|
||||
einiger
|
||||
einiges
|
||||
|
||||
einmal | once
|
||||
|
||||
er | he
|
||||
ihn | him
|
||||
ihm | to him
|
||||
|
||||
es | it
|
||||
etwas | something
|
||||
|
||||
euer | your
|
||||
eure
|
||||
eurem
|
||||
euren
|
||||
eurer
|
||||
eures
|
||||
|
||||
für | for
|
||||
gegen | towards
|
||||
gewesen | p.p. of sein
|
||||
hab | have
|
||||
habe | have
|
||||
haben | have
|
||||
hat | has
|
||||
hatte | had
|
||||
hatten | had
|
||||
hier | here
|
||||
hin | there
|
||||
hinter | behind
|
||||
|
||||
ich | I
|
||||
mich | me
|
||||
mir | to me
|
||||
|
||||
|
||||
ihr | you, to her
|
||||
ihre
|
||||
ihrem
|
||||
ihren
|
||||
ihrer
|
||||
ihres
|
||||
euch | to you
|
||||
|
||||
im | in + dem
|
||||
in | in
|
||||
indem | while
|
||||
ins | in + das
|
||||
ist | is
|
||||
|
||||
jede | each, every
|
||||
jedem
|
||||
jeden
|
||||
jeder
|
||||
jedes
|
||||
|
||||
jene | that
|
||||
jenem
|
||||
jenen
|
||||
jener
|
||||
jenes
|
||||
|
||||
jetzt | now
|
||||
kann | can
|
||||
|
||||
kein | no
|
||||
keine
|
||||
keinem
|
||||
keinen
|
||||
keiner
|
||||
keines
|
||||
|
||||
können | can
|
||||
könnte | could
|
||||
machen | do
|
||||
man | one
|
||||
|
||||
manche | some, many a
|
||||
manchem
|
||||
manchen
|
||||
mancher
|
||||
manches
|
||||
|
||||
mein | my
|
||||
meine
|
||||
meinem
|
||||
meinen
|
||||
meiner
|
||||
meines
|
||||
|
||||
mit | with
|
||||
muss | must
|
||||
musste | had to
|
||||
nach | to(wards)
|
||||
nicht | not
|
||||
nichts | nothing
|
||||
noch | still, yet
|
||||
nun | now
|
||||
nur | only
|
||||
ob | whether
|
||||
oder | or
|
||||
ohne | without
|
||||
sehr | very
|
||||
|
||||
sein | his
|
||||
seine
|
||||
seinem
|
||||
seinen
|
||||
seiner
|
||||
seines
|
||||
|
||||
selbst | self
|
||||
sich | herself
|
||||
|
||||
sie | they, she
|
||||
ihnen | to them
|
||||
|
||||
sind | are
|
||||
so | so
|
||||
|
||||
solche | such
|
||||
solchem
|
||||
solchen
|
||||
solcher
|
||||
solches
|
||||
|
||||
soll | shall
|
||||
sollte | should
|
||||
sondern | but
|
||||
sonst | else
|
||||
über | over
|
||||
um | about, around
|
||||
und | and
|
||||
|
||||
uns | us
|
||||
unse
|
||||
unsem
|
||||
unsen
|
||||
unser
|
||||
unses
|
||||
|
||||
unter | under
|
||||
viel | much
|
||||
vom | von + dem
|
||||
von | from
|
||||
vor | before
|
||||
während | while
|
||||
war | was
|
||||
waren | were
|
||||
warst | wast
|
||||
was | what
|
||||
weg | away, off
|
||||
weil | because
|
||||
weiter | further
|
||||
|
||||
welche | which
|
||||
welchem
|
||||
welchen
|
||||
welcher
|
||||
welches
|
||||
|
||||
wenn | when
|
||||
werde | will
|
||||
werden | will
|
||||
wie | how
|
||||
wieder | again
|
||||
will | want
|
||||
wir | we
|
||||
wird | will
|
||||
wirst | willst
|
||||
wo | where
|
||||
wollen | want
|
||||
wollte | wanted
|
||||
würde | would
|
||||
würden | would
|
||||
zu | to
|
||||
zum | zu + dem
|
||||
zur | zu + der
|
||||
zwar | indeed
|
||||
zwischen | between
|
||||
|
@ -0,0 +1,54 @@
|
||||
# Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
# contributor license agreements. See the NOTICE file distributed with
|
||||
# this work for additional information regarding copyright ownership.
|
||||
# The ASF licenses this file to You under the Apache License, Version 2.0
|
||||
# (the "License"); you may not use this file except in compliance with
|
||||
# the License. You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
# a couple of test stopwords to test that the words are really being
|
||||
# configured from this file:
|
||||
stopworda
|
||||
stopwordb
|
||||
|
||||
# Standard english stop words taken from Lucene's StopAnalyzer
|
||||
a
|
||||
an
|
||||
and
|
||||
are
|
||||
as
|
||||
at
|
||||
be
|
||||
but
|
||||
by
|
||||
for
|
||||
if
|
||||
in
|
||||
into
|
||||
is
|
||||
it
|
||||
no
|
||||
not
|
||||
of
|
||||
on
|
||||
or
|
||||
such
|
||||
that
|
||||
the
|
||||
their
|
||||
then
|
||||
there
|
||||
these
|
||||
they
|
||||
this
|
||||
to
|
||||
was
|
||||
will
|
||||
with
|
@ -0,0 +1,356 @@
|
||||
| From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/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 Spanish stop word list. Comments begin with vertical bar. Each stop
|
||||
| word is at the start of a line.
|
||||
|
||||
|
||||
| The following is a ranked list (commonest to rarest) of stopwords
|
||||
| deriving from a large sample of text.
|
||||
|
||||
| Extra words have been added at the end.
|
||||
|
||||
de | from, of
|
||||
la | the, her
|
||||
que | who, that
|
||||
el | the
|
||||
en | in
|
||||
y | and
|
||||
a | to
|
||||
los | the, them
|
||||
del | de + el
|
||||
se | himself, from him etc
|
||||
las | the, them
|
||||
por | for, by, etc
|
||||
un | a
|
||||
para | for
|
||||
con | with
|
||||
no | no
|
||||
una | a
|
||||
su | his, her
|
||||
al | a + el
|
||||
| es from SER
|
||||
lo | him
|
||||
como | how
|
||||
más | more
|
||||
pero | pero
|
||||
sus | su plural
|
||||
le | to him, her
|
||||
ya | already
|
||||
o | or
|
||||
| fue from SER
|
||||
este | this
|
||||
| ha from HABER
|
||||
sí | himself etc
|
||||
porque | because
|
||||
esta | this
|
||||
| son from SER
|
||||
entre | between
|
||||
| está from ESTAR
|
||||
cuando | when
|
||||
muy | very
|
||||
sin | without
|
||||
sobre | on
|
||||
| ser from SER
|
||||
| tiene from TENER
|
||||
también | also
|
||||
me | me
|
||||
hasta | until
|
||||
hay | there is/are
|
||||
donde | where
|
||||
| han from HABER
|
||||
quien | whom, that
|
||||
| están from ESTAR
|
||||
| estado from ESTAR
|
||||
desde | from
|
||||
todo | all
|
||||
nos | us
|
||||
durante | during
|
||||
| estados from ESTAR
|
||||
todos | all
|
||||
uno | a
|
||||
les | to them
|
||||
ni | nor
|
||||
contra | against
|
||||
otros | other
|
||||
| fueron from SER
|
||||
ese | that
|
||||
eso | that
|
||||
| había from HABER
|
||||
ante | before
|
||||
ellos | they
|
||||
e | and (variant of y)
|
||||
esto | this
|
||||
mí | me
|
||||
antes | before
|
||||
algunos | some
|
||||
qué | what?
|
||||
unos | a
|
||||
yo | I
|
||||
otro | other
|
||||
otras | other
|
||||
otra | other
|
||||
él | he
|
||||
tanto | so much, many
|
||||
esa | that
|
||||
estos | these
|
||||
mucho | much, many
|
||||
quienes | who
|
||||
nada | nothing
|
||||
muchos | many
|
||||
cual | who
|
||||
| sea from SER
|
||||
poco | few
|
||||
ella | she
|
||||
estar | to be
|
||||
| haber from HABER
|
||||
estas | these
|
||||
| estaba from ESTAR
|
||||
| estamos from ESTAR
|
||||
algunas | some
|
||||
algo | something
|
||||
nosotros | we
|
||||
|
||||
| other forms
|
||||
|
||||
mi | me
|
||||
mis | mi plural
|
||||
tú | thou
|
||||
te | thee
|
||||
ti | thee
|
||||
tu | thy
|
||||
tus | tu plural
|
||||
ellas | they
|
||||
nosotras | we
|
||||
vosotros | you
|
||||
vosotras | you
|
||||
os | you
|
||||
mío | mine
|
||||
mía |
|
||||
míos |
|
||||
mías |
|
||||
tuyo | thine
|
||||
tuya |
|
||||
tuyos |
|
||||
tuyas |
|
||||
suyo | his, hers, theirs
|
||||
suya |
|
||||
suyos |
|
||||
suyas |
|
||||
nuestro | ours
|
||||
nuestra |
|
||||
nuestros |
|
||||
nuestras |
|
||||
vuestro | yours
|
||||
vuestra |
|
||||
vuestros |
|
||||
vuestras |
|
||||
esos | those
|
||||
esas | those
|
||||
|
||||
| forms of estar, to be (not including the infinitive):
|
||||
estoy
|
||||
estás
|
||||
está
|
||||
estamos
|
||||
estáis
|
||||
están
|
||||
esté
|
||||
estés
|
||||
estemos
|
||||
estéis
|
||||
estén
|
||||
estaré
|
||||
estarás
|
||||
estará
|
||||
estaremos
|
||||
estaréis
|
||||
estarán
|
||||
estaría
|
||||
estarías
|
||||
estaríamos
|
||||
estaríais
|
||||
estarían
|
||||
estaba
|
||||
estabas
|
||||
estábamos
|
||||
estabais
|
||||
estaban
|
||||
estuve
|
||||
estuviste
|
||||
estuvo
|
||||
estuvimos
|
||||
estuvisteis
|
||||
estuvieron
|
||||
estuviera
|
||||
estuvieras
|
||||
estuviéramos
|
||||
estuvierais
|
||||
estuvieran
|
||||
estuviese
|
||||
estuvieses
|
||||
estuviésemos
|
||||
estuvieseis
|
||||
estuviesen
|
||||
estando
|
||||
estado
|
||||
estada
|
||||
estados
|
||||
estadas
|
||||
estad
|
||||
|
||||
| forms of haber, to have (not including the infinitive):
|
||||
he
|
||||
has
|
||||
ha
|
||||
hemos
|
||||
habéis
|
||||
han
|
||||
haya
|
||||
hayas
|
||||
hayamos
|
||||
hayáis
|
||||
hayan
|
||||
habré
|
||||
habrás
|
||||
habrá
|
||||
habremos
|
||||
habréis
|
||||
habrán
|
||||
habría
|
||||
habrías
|
||||
habríamos
|
||||
habríais
|
||||
habrían
|
||||
había
|
||||
habías
|
||||
habíamos
|
||||
habíais
|
||||
habían
|
||||
hube
|
||||
hubiste
|
||||
hubo
|
||||
hubimos
|
||||
hubisteis
|
||||
hubieron
|
||||
hubiera
|
||||
hubieras
|
||||
hubiéramos
|
||||
hubierais
|
||||
hubieran
|
||||
hubiese
|
||||
hubieses
|
||||
hubiésemos
|
||||
hubieseis
|
||||
hubiesen
|
||||
habiendo
|
||||
habido
|
||||
habida
|
||||
habidos
|
||||
habidas
|
||||
|
||||
| forms of ser, to be (not including the infinitive):
|
||||
soy
|
||||
eres
|
||||
es
|
||||
somos
|
||||
sois
|
||||
son
|
||||
sea
|
||||
seas
|
||||
seamos
|
||||
seáis
|
||||
sean
|
||||
seré
|
||||
serás
|
||||
será
|
||||
seremos
|
||||
seréis
|
||||
serán
|
||||
sería
|
||||
serías
|
||||
seríamos
|
||||
seríais
|
||||
serían
|
||||
era
|
||||
eras
|
||||
éramos
|
||||
erais
|
||||
eran
|
||||
fui
|
||||
fuiste
|
||||
fue
|
||||
fuimos
|
||||
fuisteis
|
||||
fueron
|
||||
fuera
|
||||
fueras
|
||||
fuéramos
|
||||
fuerais
|
||||
fueran
|
||||
fuese
|
||||
fueses
|
||||
fuésemos
|
||||
fueseis
|
||||
fuesen
|
||||
siendo
|
||||
sido
|
||||
| sed also means 'thirst'
|
||||
|
||||
| forms of tener, to have (not including the infinitive):
|
||||
tengo
|
||||
tienes
|
||||
tiene
|
||||
tenemos
|
||||
tenéis
|
||||
tienen
|
||||
tenga
|
||||
tengas
|
||||
tengamos
|
||||
tengáis
|
||||
tengan
|
||||
tendré
|
||||
tendrás
|
||||
tendrá
|
||||
tendremos
|
||||
tendréis
|
||||
tendrán
|
||||
tendría
|
||||
tendrías
|
||||
tendríamos
|
||||
tendríais
|
||||
tendrían
|
||||
tenía
|
||||
tenías
|
||||
teníamos
|
||||
teníais
|
||||
tenían
|
||||
tuve
|
||||
tuviste
|
||||
tuvo
|
||||
tuvimos
|
||||
tuvisteis
|
||||
tuvieron
|
||||
tuviera
|
||||
tuvieras
|
||||
tuviéramos
|
||||
tuvierais
|
||||
tuvieran
|
||||
tuviese
|
||||
tuvieses
|
||||
tuviésemos
|
||||
tuvieseis
|
||||
tuviesen
|
||||
teniendo
|
||||
tenido
|
||||
tenida
|
||||
tenidos
|
||||
tenidas
|
||||
tened
|
||||
|
@ -0,0 +1,99 @@
|
||||
# example set of basque stopwords
|
||||
al
|
||||
anitz
|
||||
arabera
|
||||
asko
|
||||
baina
|
||||
bat
|
||||
batean
|
||||
batek
|
||||
bati
|
||||
batzuei
|
||||
batzuek
|
||||
batzuetan
|
||||
batzuk
|
||||
bera
|
||||
beraiek
|
||||
berau
|
||||
berauek
|
||||
bere
|
||||
berori
|
||||
beroriek
|
||||
beste
|
||||
bezala
|
||||
da
|
||||
dago
|
||||
dira
|
||||
ditu
|
||||
du
|
||||
dute
|
||||
edo
|
||||
egin
|
||||
ere
|
||||
eta
|
||||
eurak
|
||||
ez
|
||||
gainera
|
||||
gu
|
||||
gutxi
|
||||
guzti
|
||||
haiei
|
||||
haiek
|
||||
haietan
|
||||
hainbeste
|
||||
hala
|
||||
han
|
||||
handik
|
||||
hango
|
||||
hara
|
||||
hari
|
||||
hark
|
||||
hartan
|
||||
hau
|
||||
hauei
|
||||
hauek
|
||||
hauetan
|
||||
hemen
|
||||
hemendik
|
||||
hemengo
|
||||
hi
|
||||
hona
|
||||
honek
|
||||
honela
|
||||
honetan
|
||||
honi
|
||||
hor
|
||||
hori
|
||||
horiei
|
||||
horiek
|
||||
horietan
|
||||
horko
|
||||
horra
|
||||
horrek
|
||||
horrela
|
||||
horretan
|
||||
horri
|
||||
hortik
|
||||
hura
|
||||
izan
|
||||
ni
|
||||
noiz
|
||||
nola
|
||||
non
|
||||
nondik
|
||||
nongo
|
||||
nor
|
||||
nora
|
||||
ze
|
||||
zein
|
||||
zen
|
||||
zenbait
|
||||
zenbat
|
||||
zer
|
||||
zergatik
|
||||
ziren
|
||||
zituen
|
||||
zu
|
||||
zuek
|
||||
zuen
|
||||
zuten
|
@ -0,0 +1,97 @@
|
||||
| From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/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"
|
||||
|
||||
| forms of BE
|
||||
|
||||
olla
|
||||
olen
|
||||
olet
|
||||
on
|
||||
olemme
|
||||
olette
|
||||
ovat
|
||||
ole | negative form
|
||||
|
||||
oli
|
||||
olisi
|
||||
olisit
|
||||
olisin
|
||||
olisimme
|
||||
olisitte
|
||||
olisivat
|
||||
olit
|
||||
olin
|
||||
olimme
|
||||
olitte
|
||||
olivat
|
||||
ollut
|
||||
olleet
|
||||
|
||||
en | negation
|
||||
et
|
||||
ei
|
||||
emme
|
||||
ette
|
||||
eivät
|
||||
|
||||
|Nom Gen Acc Part Iness Elat Illat Adess Ablat Allat Ess Trans
|
||||
minä minun minut minua minussa minusta minuun minulla minulta minulle | I
|
||||
sinä sinun sinut sinua sinussa sinusta sinuun sinulla sinulta sinulle | you
|
||||
hän hänen hänet häntä hänessä hänestä häneen hänellä häneltä hänelle | he she
|
||||
me meidän meidät meitä meissä meistä meihin meillä meiltä meille | we
|
||||
te teidän teidät teitä teissä teistä teihin teillä teiltä teille | you
|
||||
he heidän heidät heitä heissä heistä heihin heillä heiltä heille | they
|
||||
|
||||
tämä tämän tätä tässä tästä tähän tallä tältä tälle tänä täksi | this
|
||||
tuo tuon tuotä tuossa tuosta tuohon tuolla tuolta tuolle tuona tuoksi | that
|
||||
se sen sitä siinä siitä siihen sillä siltä sille sinä siksi | it
|
||||
nämä näiden näitä näissä näistä näihin näillä näiltä näille näinä näiksi | these
|
||||
nuo noiden noita noissa noista noihin noilla noilta noille noina noiksi | those
|
||||
ne niiden niitä niissä niistä niihin niillä niiltä niille niinä niiksi | they
|
||||
|
||||
kuka kenen kenet ketä kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who
|
||||
ketkä keiden ketkä keitä keissä keistä keihin keillä keiltä keille keinä keiksi | (pl)
|
||||
mikä minkä minkä mitä missä mistä mihin millä miltä mille minä miksi | which what
|
||||
mitkä | (pl)
|
||||
|
||||
joka jonka jota jossa josta johon jolla jolta jolle jona joksi | who which
|
||||
jotka joiden joita joissa joista joihin joilla joilta joille joina joiksi | (pl)
|
||||
|
||||
| conjunctions
|
||||
|
||||
että | that
|
||||
ja | and
|
||||
jos | if
|
||||
koska | because
|
||||
kuin | than
|
||||
mutta | but
|
||||
niin | so
|
||||
sekä | and
|
||||
sillä | for
|
||||
tai | or
|
||||
vaan | but
|
||||
vai | or
|
||||
vaikka | although
|
||||
|
||||
|
||||
| prepositions
|
||||
|
||||
kanssa | with
|
||||
mukaan | according to
|
||||
noin | about
|
||||
poikki | across
|
||||
yli | over, across
|
||||
|
||||
| other
|
||||
|
||||
kun | when
|
||||
niin | so
|
||||
nyt | now
|
||||
itse | self
|
||||
|
@ -0,0 +1,186 @@
|
||||
| From svn.tartarus.org/snowball/trunk/website/algorithms/french/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 French stop word list. Comments begin with vertical bar. Each stop
|
||||
| word is at the start of a line.
|
||||
|
||||
au | a + le
|
||||
aux | a + les
|
||||
avec | with
|
||||
ce | this
|
||||
ces | these
|
||||
dans | with
|
||||
de | of
|
||||
des | de + les
|
||||
du | de + le
|
||||
elle | she
|
||||
en | `of them' etc
|
||||
et | and
|
||||
eux | them
|
||||
il | he
|
||||
je | I
|
||||
la | the
|
||||
le | the
|
||||
leur | their
|
||||
lui | him
|
||||
ma | my (fem)
|
||||
mais | but
|
||||
me | me
|
||||
même | same; as in moi-même (myself) etc
|
||||
mes | me (pl)
|
||||
moi | me
|
||||
mon | my (masc)
|
||||
ne | not
|
||||
nos | our (pl)
|
||||
notre | our
|
||||
nous | we
|
||||
on | one
|
||||
ou | where
|
||||
par | by
|
||||
pas | not
|
||||
pour | for
|
||||
qu | que before vowel
|
||||
que | that
|
||||
qui | who
|
||||
sa | his, her (fem)
|
||||
se | oneself
|
||||
ses | his (pl)
|
||||
son | his, her (masc)
|
||||
sur | on
|
||||
ta | thy (fem)
|
||||
te | thee
|
||||
tes | thy (pl)
|
||||
toi | thee
|
||||
ton | thy (masc)
|
||||
tu | thou
|
||||
un | a
|
||||
une | a
|
||||
vos | your (pl)
|
||||
votre | your
|
||||
vous | you
|
||||
|
||||
| single letter forms
|
||||
|
||||
c | c'
|
||||
d | d'
|
||||
j | j'
|
||||
l | l'
|
||||
à | to, at
|
||||
m | m'
|
||||
n | n'
|
||||
s | s'
|
||||
t | t'
|
||||
y | there
|
||||
|
||||
| forms of être (not including the infinitive):
|
||||
été
|
||||
étée
|
||||
étées
|
||||
étés
|
||||
étant
|
||||
suis
|
||||
es
|
||||
est
|
||||
sommes
|
||||
êtes
|
||||
sont
|
||||
serai
|
||||
seras
|
||||
sera
|
||||
serons
|
||||
serez
|
||||
seront
|
||||
serais
|
||||
serait
|
||||
serions
|
||||
seriez
|
||||
seraient
|
||||
étais
|
||||
était
|
||||
étions
|
||||
étiez
|
||||
étaient
|
||||
fus
|
||||
fut
|
||||
fûmes
|
||||
fûtes
|
||||
furent
|
||||
sois
|
||||
soit
|
||||
soyons
|
||||
soyez
|
||||
soient
|
||||
fusse
|
||||
fusses
|
||||
fût
|
||||
fussions
|
||||
fussiez
|
||||
fussent
|
||||
|
||||
| forms of avoir (not including the infinitive):
|
||||
ayant
|
||||
eu
|
||||
eue
|
||||
eues
|
||||
eus
|
||||
ai
|
||||
as
|
||||
avons
|
||||
avez
|
||||
ont
|
||||
aurai
|
||||
auras
|
||||
aura
|
||||
aurons
|
||||
aurez
|
||||
auront
|
||||
aurais
|
||||
aurait
|
||||
aurions
|
||||
auriez
|
||||
auraient
|
||||
avais
|
||||
avait
|
||||
avions
|
||||
aviez
|
||||
avaient
|
||||
eut
|
||||
eûmes
|
||||
eûtes
|
||||
eurent
|
||||
aie
|
||||
aies
|
||||
ait
|
||||
ayons
|
||||
ayez
|
||||
aient
|
||||
eusse
|
||||
eusses
|
||||
eût
|
||||
eussions
|
||||
eussiez
|
||||
eussent
|
||||
|
||||
| Later additions (from Jean-Christophe Deschamps)
|
||||
ceci | this
|
||||
cela | that
|
||||
celà | that
|
||||
cet | this
|
||||
cette | this
|
||||
ici | here
|
||||
ils | they
|
||||
les | the (pl)
|
||||
leurs | their (pl)
|
||||
quel | which
|
||||
quels | which
|
||||
quelle | which
|
||||
quelles | which
|
||||
sans | without
|
||||
soi | oneself
|
||||
|
@ -0,0 +1,110 @@
|
||||
|
||||
a
|
||||
ach
|
||||
ag
|
||||
agus
|
||||
an
|
||||
aon
|
||||
ar
|
||||
arna
|
||||
as
|
||||
b'
|
||||
ba
|
||||
beirt
|
||||
bhúr
|
||||
caoga
|
||||
ceathair
|
||||
ceathrar
|
||||
chomh
|
||||
chtó
|
||||
chuig
|
||||
chun
|
||||
cois
|
||||
céad
|
||||
cúig
|
||||
cúigear
|
||||
d'
|
||||
daichead
|
||||
dar
|
||||
de
|
||||
deich
|
||||
deichniúr
|
||||
den
|
||||
dhá
|
||||
do
|
||||
don
|
||||
dtí
|
||||
dá
|
||||
dár
|
||||
dó
|
||||
faoi
|
||||
faoin
|
||||
faoina
|
||||
faoinár
|
||||
fara
|
||||
fiche
|
||||
gach
|
||||
gan
|
||||
go
|
||||
gur
|
||||
haon
|
||||
hocht
|
||||
i
|
||||
iad
|
||||
idir
|
||||
in
|
||||
ina
|
||||
ins
|
||||
inár
|
||||
is
|
||||
le
|
||||
leis
|
||||
lena
|
||||
lenár
|
||||
m'
|
||||
mar
|
||||
mo
|
||||
mé
|
||||
na
|
||||
nach
|
||||
naoi
|
||||
naonúr
|
||||
ná
|
||||
ní
|
||||
níor
|
||||
nó
|
||||
nócha
|
||||
ocht
|
||||
ochtar
|
||||
os
|
||||
roimh
|
||||
sa
|
||||
seacht
|
||||
seachtar
|
||||
seachtó
|
||||
seasca
|
||||
seisear
|
||||
siad
|
||||
sibh
|
||||
sinn
|
||||
sna
|
||||
sé
|
||||
sí
|
||||
tar
|
||||
thar
|
||||
thú
|
||||
triúr
|
||||
trí
|
||||
trína
|
||||
trínár
|
||||
tríocha
|
||||
tú
|
||||
um
|
||||
ár
|
||||
é
|
||||
éis
|
||||
í
|
||||
ó
|
||||
ón
|
||||
óna
|
||||
ónár
|
@ -0,0 +1,161 @@
|
||||
# galican stopwords
|
||||
a
|
||||
aínda
|
||||
alí
|
||||
aquel
|
||||
aquela
|
||||
aquelas
|
||||
aqueles
|
||||
aquilo
|
||||
aquí
|
||||
ao
|
||||
aos
|
||||
as
|
||||
así
|
||||
á
|
||||
ben
|
||||
cando
|
||||
che
|
||||
co
|
||||
coa
|
||||
comigo
|
||||
con
|
||||
connosco
|
||||
contigo
|
||||
convosco
|
||||
coas
|
||||
cos
|
||||
cun
|
||||
cuns
|
||||
cunha
|
||||
cunhas
|
||||
da
|
||||
dalgunha
|
||||
dalgunhas
|
||||
dalgún
|
||||
dalgúns
|
||||
das
|
||||
de
|
||||
del
|
||||
dela
|
||||
delas
|
||||
deles
|
||||
desde
|
||||
deste
|
||||
do
|
||||
dos
|
||||
dun
|
||||
duns
|
||||
dunha
|
||||
dunhas
|
||||
e
|
||||
el
|
||||
ela
|
||||
elas
|
||||
eles
|
||||
en
|
||||
era
|
||||
eran
|
||||
esa
|
||||
esas
|
||||
ese
|
||||
eses
|
||||
esta
|
||||
estar
|
||||
estaba
|
||||
está
|
||||
están
|
||||
este
|
||||
estes
|
||||
estiven
|
||||
estou
|
||||
eu
|
||||
é
|
||||
facer
|
||||
foi
|
||||
foron
|
||||
fun
|
||||
había
|
||||
hai
|
||||
iso
|
||||
isto
|
||||
la
|
||||
las
|
||||
lle
|
||||
lles
|
||||
lo
|
||||
los
|
||||
mais
|
||||
me
|
||||
meu
|
||||
meus
|
||||
min
|
||||
miña
|
||||
miñas
|
||||
moi
|
||||
na
|
||||
nas
|
||||
neste
|
||||
nin
|
||||
no
|
||||
non
|
||||
nos
|
||||
nosa
|
||||
nosas
|
||||
noso
|
||||
nosos
|
||||
nós
|
||||
nun
|
||||
nunha
|
||||
nuns
|
||||
nunhas
|
||||
o
|
||||
os
|
||||
ou
|
||||
ó
|
||||
ós
|
||||
para
|
||||
pero
|
||||
pode
|
||||
pois
|
||||
pola
|
||||
polas
|
||||
polo
|
||||
polos
|
||||
por
|
||||
que
|
||||
se
|
||||
senón
|
||||
ser
|
||||
seu
|
||||
seus
|
||||
sexa
|
||||
sido
|
||||
sobre
|
||||
súa
|
||||
súas
|
||||
tamén
|
||||
tan
|
||||
te
|
||||
ten
|
||||
teñen
|
||||
teño
|
||||
ter
|
||||
teu
|
||||
teus
|
||||
ti
|
||||
tido
|
||||
tiña
|
||||
tiven
|
||||
túa
|
||||
túas
|
||||
un
|
||||
unha
|
||||
unhas
|
||||
uns
|
||||
vos
|
||||
vosa
|
||||
vosas
|
||||
voso
|
||||
vosos
|
||||
vós
|
@ -0,0 +1,235 @@
|
||||
# Also see http://www.opensource.org/licenses/bsd-license.html
|
||||
# See http://members.unine.ch/jacques.savoy/clef/index.html.
|
||||
# This file was created by Jacques Savoy and is distributed under the BSD license.
|
||||
# Note: by default this file also contains forms normalized by HindiNormalizer
|
||||
# for spelling variation (see section below), such that it can be used whether or
|
||||
# not you enable that feature. When adding additional entries to this list,
|
||||
# please add the normalized form as well.
|
||||
अंदर
|
||||
अत
|
||||
अपना
|
||||
अपनी
|
||||
अपने
|
||||
अभी
|
||||
आदि
|
||||
आप
|
||||
इत्यादि
|
||||
इन
|
||||
इनका
|
||||
इन्हीं
|
||||
इन्हें
|
||||
इन्हों
|
||||
इस
|
||||
इसका
|
||||
इसकी
|
||||
इसके
|
||||
इसमें
|
||||
इसी
|
||||
इसे
|
||||
उन
|
||||
उनका
|
||||
उनकी
|
||||
उनके
|
||||
उनको
|
||||
उन्हीं
|
||||
उन्हें
|
||||
उन्हों
|
||||
उस
|
||||
उसके
|
||||
उसी
|
||||
उसे
|
||||
एक
|
||||
एवं
|
||||
एस
|
||||
ऐसे
|
||||
और
|
||||
कई
|
||||
कर
|
||||
करता
|
||||
करते
|
||||
करना
|
||||
करने
|
||||
करें
|
||||
कहते
|
||||
कहा
|
||||
का
|
||||
काफ़ी
|
||||
कि
|
||||
कितना
|
||||
किन्हें
|
||||
किन्हों
|
||||
किया
|
||||
किर
|
||||
किस
|
||||
किसी
|
||||
किसे
|
||||
की
|
||||
कुछ
|
||||
कुल
|
||||
के
|
||||
को
|
||||
कोई
|
||||
कौन
|
||||
कौनसा
|
||||
गया
|
||||
घर
|
||||
जब
|
||||
जहाँ
|
||||
जा
|
||||
जितना
|
||||
जिन
|
||||
जिन्हें
|
||||
जिन्हों
|
||||
जिस
|
||||
जिसे
|
||||
जीधर
|
||||
जैसा
|
||||
जैसे
|
||||
जो
|
||||
तक
|
||||
तब
|
||||
तरह
|
||||
तिन
|
||||
तिन्हें
|
||||
तिन्हों
|
||||
तिस
|
||||
तिसे
|
||||
तो
|
||||
था
|
||||
थी
|
||||
थे
|
||||
दबारा
|
||||
दिया
|
||||
दुसरा
|
||||
दूसरे
|
||||
दो
|
||||
द्वारा
|
||||
न
|
||||
नहीं
|
||||
ना
|
||||
निहायत
|
||||
नीचे
|
||||
ने
|
||||
पर
|
||||
पर
|
||||
पहले
|
||||
पूरा
|
||||
पे
|
||||
फिर
|
||||
बनी
|
||||
बही
|
||||
बहुत
|
||||
बाद
|
||||
बाला
|
||||
बिलकुल
|
||||
भी
|
||||
भीतर
|
||||
मगर
|
||||
मानो
|
||||
मे
|
||||
में
|
||||
यदि
|
||||
यह
|
||||
यहाँ
|
||||
यही
|
||||
या
|
||||
यिह
|
||||
ये
|
||||
रखें
|
||||
रहा
|
||||
रहे
|
||||
ऱ्वासा
|
||||
लिए
|
||||
लिये
|
||||
लेकिन
|
||||
व
|
||||
वर्ग
|
||||
वह
|
||||
वह
|
||||
वहाँ
|
||||
वहीं
|
||||
वाले
|
||||
वुह
|
||||
वे
|
||||
वग़ैरह
|
||||
संग
|
||||
सकता
|
||||
सकते
|
||||
सबसे
|
||||
सभी
|
||||
साथ
|
||||
साबुत
|
||||
साभ
|
||||
सारा
|
||||
से
|
||||
सो
|
||||
ही
|
||||
हुआ
|
||||
हुई
|
||||
हुए
|
||||
है
|
||||
हैं
|
||||
हो
|
||||
होता
|
||||
होती
|
||||
होते
|
||||
होना
|
||||
होने
|
||||
# additional normalized forms of the above
|
||||
अपनि
|
||||
जेसे
|
||||
होति
|
||||
सभि
|
||||
तिंहों
|
||||
इंहों
|
||||
दवारा
|
||||
इसि
|
||||
किंहें
|
||||
थि
|
||||
उंहों
|
||||
ओर
|
||||
जिंहें
|
||||
वहिं
|
||||
अभि
|
||||
बनि
|
||||
हि
|
||||
उंहिं
|
||||
उंहें
|
||||
हें
|
||||
वगेरह
|
||||
एसे
|
||||
रवासा
|
||||
कोन
|
||||
निचे
|
||||
काफि
|
||||
उसि
|
||||
पुरा
|
||||
भितर
|
||||
हे
|
||||
बहि
|
||||
वहां
|
||||
कोइ
|
||||
यहां
|
||||
जिंहों
|
||||
तिंहें
|
||||
किसि
|
||||
कइ
|
||||
यहि
|
||||
इंहिं
|
||||
जिधर
|
||||
इंहें
|
||||
अदि
|
||||
इतयादि
|
||||
हुइ
|
||||
कोनसा
|
||||
इसकि
|
||||
दुसरे
|
||||
जहां
|
||||
अप
|
||||
किंहों
|
||||
उनकि
|
||||
भि
|
||||
वरग
|
||||
हुअ
|
||||
जेसा
|
||||
नहिं
|
@ -0,0 +1,211 @@
|
||||
| From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/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"
|
||||
|
||||
| Hungarian stop word list
|
||||
| prepared by Anna Tordai
|
||||
|
||||
a
|
||||
ahogy
|
||||
ahol
|
||||
aki
|
||||
akik
|
||||
akkor
|
||||
alatt
|
||||
által
|
||||
általában
|
||||
amely
|
||||
amelyek
|
||||
amelyekben
|
||||
amelyeket
|
||||
amelyet
|
||||
amelynek
|
||||
ami
|
||||
amit
|
||||
amolyan
|
||||
amíg
|
||||
amikor
|
||||
át
|
||||
abban
|
||||
ahhoz
|
||||
annak
|
||||
arra
|
||||
arról
|
||||
az
|
||||
azok
|
||||
azon
|
||||
azt
|
||||
azzal
|
||||
azért
|
||||
aztán
|
||||
azután
|
||||
azonban
|
||||
bár
|
||||
be
|
||||
belül
|
||||
benne
|
||||
cikk
|
||||
cikkek
|
||||
cikkeket
|
||||
csak
|
||||
de
|
||||
e
|
||||
eddig
|
||||
egész
|
||||
egy
|
||||
egyes
|
||||
egyetlen
|
||||
egyéb
|
||||
egyik
|
||||
egyre
|
||||
ekkor
|
||||
el
|
||||
elég
|
||||
ellen
|
||||
elő
|
||||
először
|
||||
előtt
|
||||
első
|
||||
én
|
||||
éppen
|
||||
ebben
|
||||
ehhez
|
||||
emilyen
|
||||
ennek
|
||||
erre
|
||||
ez
|
||||
ezt
|
||||
ezek
|
||||
ezen
|
||||
ezzel
|
||||
ezért
|
||||
és
|
||||
fel
|
||||
felé
|
||||
hanem
|
||||
hiszen
|
||||
hogy
|
||||
hogyan
|
||||
igen
|
||||
így
|
||||
illetve
|
||||
ill.
|
||||
ill
|
||||
ilyen
|
||||
ilyenkor
|
||||
ison
|
||||
ismét
|
||||
itt
|
||||
jó
|
||||
jól
|
||||
jobban
|
||||
kell
|
||||
kellett
|
||||
keresztül
|
||||
keressünk
|
||||
ki
|
||||
kívül
|
||||
között
|
||||
közül
|
||||
legalább
|
||||
lehet
|
||||
lehetett
|
||||
legyen
|
||||
lenne
|
||||
lenni
|
||||
lesz
|
||||
lett
|
||||
maga
|
||||
magát
|
||||
majd
|
||||
majd
|
||||
már
|
||||
más
|
||||
másik
|
||||
meg
|
||||
még
|
||||
mellett
|
||||
mert
|
||||
mely
|
||||
melyek
|
||||
mi
|
||||
mit
|
||||
míg
|
||||
miért
|
||||
milyen
|
||||
mikor
|
||||
minden
|
||||
mindent
|
||||
mindenki
|
||||
mindig
|
||||
mint
|
||||
mintha
|
||||
mivel
|
||||
most
|
||||
nagy
|
||||
nagyobb
|
||||
nagyon
|
||||
ne
|
||||
néha
|
||||
nekem
|
||||
neki
|
||||
nem
|
||||
néhány
|
||||
nélkül
|
||||
nincs
|
||||
olyan
|
||||
ott
|
||||
össze
|
||||
ő
|
||||
ők
|
||||
őket
|
||||
pedig
|
||||
persze
|
||||
rá
|
||||
s
|
||||
saját
|
||||
sem
|
||||
semmi
|
||||
sok
|
||||
sokat
|
||||
sokkal
|
||||
számára
|
||||
szemben
|
||||
szerint
|
||||
szinte
|
||||
talán
|
||||
tehát
|
||||
teljes
|
||||
tovább
|
||||
továbbá
|
||||
több
|
||||
úgy
|
||||
ugyanis
|
||||
új
|
||||
újabb
|
||||
újra
|
||||
után
|
||||
utána
|
||||
utolsó
|
||||
vagy
|
||||
vagyis
|
||||
valaki
|
||||
valami
|
||||
valamint
|
||||
való
|
||||
vagyok
|
||||
van
|
||||
vannak
|
||||
volt
|
||||
voltam
|
||||
voltak
|
||||
voltunk
|
||||
vissza
|
||||
vele
|
||||
viszont
|
||||
volna
|
@ -0,0 +1,46 @@
|
||||
# example set of Armenian stopwords.
|
||||
այդ
|
||||
այլ
|
||||
այն
|
||||
այս
|
||||
դու
|
||||
դուք
|
||||
եմ
|
||||
են
|
||||
ենք
|
||||
ես
|
||||
եք
|
||||
է
|
||||
էի
|
||||
էին
|
||||
էինք
|
||||
էիր
|
||||
էիք
|
||||
էր
|
||||
ըստ
|
||||
թ
|
||||
ի
|
||||
ին
|
||||
իսկ
|
||||
իր
|
||||
կամ
|
||||
համար
|
||||
հետ
|
||||
հետո
|
||||
մենք
|
||||
մեջ
|
||||
մի
|
||||
ն
|
||||
նա
|
||||
նաև
|
||||
նրա
|
||||
նրանք
|
||||
որ
|
||||
որը
|
||||
որոնք
|
||||
որպես
|
||||
ու
|
||||
ում
|
||||
պիտի
|
||||
վրա
|
||||
և
|
@ -0,0 +1,359 @@
|
||||
# from appendix D of: A Study of Stemming Effects on Information
|
||||
# Retrieval in Bahasa Indonesia
|
||||
ada
|
||||
adanya
|
||||
adalah
|
||||
adapun
|
||||
agak
|
||||
agaknya
|
||||
agar
|
||||
akan
|
||||
akankah
|
||||
akhirnya
|
||||
aku
|
||||
akulah
|
||||
amat
|
||||
amatlah
|
||||
anda
|
||||
andalah
|
||||
antar
|
||||
diantaranya
|
||||
antara
|
||||
antaranya
|
||||
diantara
|
||||
apa
|
||||
apaan
|
||||
mengapa
|
||||
apabila
|
||||
apakah
|
||||
apalagi
|
||||
apatah
|
||||
atau
|
||||
ataukah
|
||||
ataupun
|
||||
bagai
|
||||
bagaikan
|
||||
sebagai
|
||||
sebagainya
|
||||
bagaimana
|
||||
bagaimanapun
|
||||
sebagaimana
|
||||
bagaimanakah
|
||||
bagi
|
||||
bahkan
|
||||
bahwa
|
||||
bahwasanya
|
||||
sebaliknya
|
||||
banyak
|
||||
sebanyak
|
||||
beberapa
|
||||
seberapa
|
||||
begini
|
||||
beginian
|
||||
beginikah
|
||||
beginilah
|
||||
sebegini
|
||||
begitu
|
||||
begitukah
|
||||
begitulah
|
||||
begitupun
|
||||
sebegitu
|
||||
belum
|
||||
belumlah
|
||||
sebelum
|
||||
sebelumnya
|
||||
sebenarnya
|
||||
berapa
|
||||
berapakah
|
||||
berapalah
|
||||
berapapun
|
||||
betulkah
|
||||
sebetulnya
|
||||
biasa
|
||||
biasanya
|
||||
bila
|
||||
bilakah
|
||||
bisa
|
||||
bisakah
|
||||
sebisanya
|
||||
boleh
|
||||
bolehkah
|
||||
bolehlah
|
||||
buat
|
||||
bukan
|
||||
bukankah
|
||||
bukanlah
|
||||
bukannya
|
||||
cuma
|
||||
percuma
|
||||
dahulu
|
||||
dalam
|
||||
dan
|
||||
dapat
|
||||
dari
|
||||
daripada
|
||||
dekat
|
||||
demi
|
||||
demikian
|
||||
demikianlah
|
||||
sedemikian
|
||||
dengan
|
||||
depan
|
||||
di
|
||||
dia
|
||||
dialah
|
||||
dini
|
||||
diri
|
||||
dirinya
|
||||
terdiri
|
||||
dong
|
||||
dulu
|
||||
enggak
|
||||
enggaknya
|
||||
entah
|
||||
entahlah
|
||||
terhadap
|
||||
terhadapnya
|
||||
hal
|
||||
hampir
|
||||
hanya
|
||||
hanyalah
|
||||
harus
|
||||
haruslah
|
||||
harusnya
|
||||
seharusnya
|
||||
hendak
|
||||
hendaklah
|
||||
hendaknya
|
||||
hingga
|
||||
sehingga
|
||||
ia
|
||||
ialah
|
||||
ibarat
|
||||
ingin
|
||||
inginkah
|
||||
inginkan
|
||||
ini
|
||||
inikah
|
||||
inilah
|
||||
itu
|
||||
itukah
|
||||
itulah
|
||||
jangan
|
||||
jangankan
|
||||
janganlah
|
||||
jika
|
||||
jikalau
|
||||
juga
|
||||
justru
|
||||
kala
|
||||
kalau
|
||||
kalaulah
|
||||
kalaupun
|
||||
kalian
|
||||
kami
|
||||
kamilah
|
||||
kamu
|
||||
kamulah
|
||||
kan
|
||||
kapan
|
||||
kapankah
|
||||
kapanpun
|
||||
dikarenakan
|
||||
karena
|
||||
karenanya
|
||||
ke
|
||||
kecil
|
||||
kemudian
|
||||
kenapa
|
||||
kepada
|
||||
kepadanya
|
||||
ketika
|
||||
seketika
|
||||
khususnya
|
||||
kini
|
||||
kinilah
|
||||
kiranya
|
||||
sekiranya
|
||||
kita
|
||||
kitalah
|
||||
kok
|
||||
lagi
|
||||
lagian
|
||||
selagi
|
||||
lah
|
||||
lain
|
||||
lainnya
|
||||
melainkan
|
||||
selaku
|
||||
lalu
|
||||
melalui
|
||||
terlalu
|
||||
lama
|
||||
lamanya
|
||||
selama
|
||||
selama
|
||||
selamanya
|
||||
lebih
|
||||
terlebih
|
||||
bermacam
|
||||
macam
|
||||
semacam
|
||||
maka
|
||||
makanya
|
||||
makin
|
||||
malah
|
||||
malahan
|
||||
mampu
|
||||
mampukah
|
||||
mana
|
||||
manakala
|
||||
manalagi
|
||||
masih
|
||||
masihkah
|
||||
semasih
|
||||
masing
|
||||
mau
|
||||
maupun
|
||||
semaunya
|
||||
memang
|
||||
mereka
|
||||
merekalah
|
||||
meski
|
||||
meskipun
|
||||
semula
|
||||
mungkin
|
||||
mungkinkah
|
||||
nah
|
||||
namun
|
||||
nanti
|
||||
nantinya
|
||||
nyaris
|
||||
oleh
|
||||
olehnya
|
||||
seorang
|
||||
seseorang
|
||||
pada
|
||||
padanya
|
||||
padahal
|
||||
paling
|
||||
sepanjang
|
||||
pantas
|
||||
sepantasnya
|
||||
sepantasnyalah
|
||||
para
|
||||
pasti
|
||||
pastilah
|
||||
per
|
||||
pernah
|
||||
pula
|
||||
pun
|
||||
merupakan
|
||||
rupanya
|
||||
serupa
|
||||
saat
|
||||
saatnya
|
||||
sesaat
|
||||
saja
|
||||
sajalah
|
||||
saling
|
||||
bersama
|
||||
sama
|
||||
sesama
|
||||
sambil
|
||||
sampai
|
||||
sana
|
||||
sangat
|
||||
sangatlah
|
||||
saya
|
||||
sayalah
|
||||
se
|
||||
sebab
|
||||
sebabnya
|
||||
sebuah
|
||||
tersebut
|
||||
tersebutlah
|
||||
sedang
|
||||
sedangkan
|
||||
sedikit
|
||||
sedikitnya
|
||||
segala
|
||||
segalanya
|
||||
segera
|
||||
sesegera
|
||||
sejak
|
||||
sejenak
|
||||
sekali
|
||||
sekalian
|
||||
sekalipun
|
||||
sesekali
|
||||
sekaligus
|
||||
sekarang
|
||||
sekarang
|
||||
sekitar
|
||||
sekitarnya
|
||||
sela
|
||||
selain
|
||||
selalu
|
||||
seluruh
|
||||
seluruhnya
|
||||
semakin
|
||||
sementara
|
||||
sempat
|
||||
semua
|
||||
semuanya
|
||||
sendiri
|
||||
sendirinya
|
||||
seolah
|
||||
seperti
|
||||
sepertinya
|
||||
sering
|
||||
seringnya
|
||||
serta
|
||||
siapa
|
||||
siapakah
|
||||
siapapun
|
||||
disini
|
||||
disinilah
|
||||
sini
|
||||
sinilah
|
||||
sesuatu
|
||||
sesuatunya
|
||||
suatu
|
||||
sesudah
|
||||
sesudahnya
|
||||
sudah
|
||||
sudahkah
|
||||
sudahlah
|
||||
supaya
|
||||
tadi
|
||||
tadinya
|
||||
tak
|
||||
tanpa
|
||||
setelah
|
||||
telah
|
||||
tentang
|
||||
tentu
|
||||
tentulah
|
||||
tentunya
|
||||
tertentu
|
||||
seterusnya
|
||||
tapi
|
||||
tetapi
|
||||
setiap
|
||||
tiap
|
||||
setidaknya
|
||||
tidak
|
||||
tidakkah
|
||||
tidaklah
|
||||
toh
|
||||
waduh
|
||||
wah
|
||||
wahai
|
||||
sewaktu
|
||||
walau
|
||||
walaupun
|
||||
wong
|
||||
yaitu
|
||||
yakni
|
||||
yang
|
@ -0,0 +1,303 @@
|
||||
| From svn.tartarus.org/snowball/trunk/website/algorithms/italian/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 Italian stop word list. Comments begin with vertical bar. Each stop
|
||||
| word is at the start of a line.
|
||||
|
||||
ad | a (to) before vowel
|
||||
al | a + il
|
||||
allo | a + lo
|
||||
ai | a + i
|
||||
agli | a + gli
|
||||
all | a + l'
|
||||
agl | a + gl'
|
||||
alla | a + la
|
||||
alle | a + le
|
||||
con | with
|
||||
col | con + il
|
||||
coi | con + i (forms collo, cogli etc are now very rare)
|
||||
da | from
|
||||
dal | da + il
|
||||
dallo | da + lo
|
||||
dai | da + i
|
||||
dagli | da + gli
|
||||
dall | da + l'
|
||||
dagl | da + gll'
|
||||
dalla | da + la
|
||||
dalle | da + le
|
||||
di | of
|
||||
del | di + il
|
||||
dello | di + lo
|
||||
dei | di + i
|
||||
degli | di + gli
|
||||
dell | di + l'
|
||||
degl | di + gl'
|
||||
della | di + la
|
||||
delle | di + le
|
||||
in | in
|
||||
nel | in + el
|
||||
nello | in + lo
|
||||
nei | in + i
|
||||
negli | in + gli
|
||||
nell | in + l'
|
||||
negl | in + gl'
|
||||
nella | in + la
|
||||
nelle | in + le
|
||||
su | on
|
||||
sul | su + il
|
||||
sullo | su + lo
|
||||
sui | su + i
|
||||
sugli | su + gli
|
||||
sull | su + l'
|
||||
sugl | su + gl'
|
||||
sulla | su + la
|
||||
sulle | su + le
|
||||
per | through, by
|
||||
tra | among
|
||||
contro | against
|
||||
io | I
|
||||
tu | thou
|
||||
lui | he
|
||||
lei | she
|
||||
noi | we
|
||||
voi | you
|
||||
loro | they
|
||||
mio | my
|
||||
mia |
|
||||
miei |
|
||||
mie |
|
||||
tuo |
|
||||
tua |
|
||||
tuoi | thy
|
||||
tue |
|
||||
suo |
|
||||
sua |
|
||||
suoi | his, her
|
||||
sue |
|
||||
nostro | our
|
||||
nostra |
|
||||
nostri |
|
||||
nostre |
|
||||
vostro | your
|
||||
vostra |
|
||||
vostri |
|
||||
vostre |
|
||||
mi | me
|
||||
ti | thee
|
||||
ci | us, there
|
||||
vi | you, there
|
||||
lo | him, the
|
||||
la | her, the
|
||||
li | them
|
||||
le | them, the
|
||||
gli | to him, the
|
||||
ne | from there etc
|
||||
il | the
|
||||
un | a
|
||||
uno | a
|
||||
una | a
|
||||
ma | but
|
||||
ed | and
|
||||
se | if
|
||||
perché | why, because
|
||||
anche | also
|
||||
come | how
|
||||
dov | where (as dov')
|
||||
dove | where
|
||||
che | who, that
|
||||
chi | who
|
||||
cui | whom
|
||||
non | not
|
||||
più | more
|
||||
quale | who, that
|
||||
quanto | how much
|
||||
quanti |
|
||||
quanta |
|
||||
quante |
|
||||
quello | that
|
||||
quelli |
|
||||
quella |
|
||||
quelle |
|
||||
questo | this
|
||||
questi |
|
||||
questa |
|
||||
queste |
|
||||
si | yes
|
||||
tutto | all
|
||||
tutti | all
|
||||
|
||||
| single letter forms:
|
||||
|
||||
a | at
|
||||
c | as c' for ce or ci
|
||||
e | and
|
||||
i | the
|
||||
l | as l'
|
||||
o | or
|
||||
|
||||
| forms of avere, to have (not including the infinitive):
|
||||
|
||||
ho
|
||||
hai
|
||||
ha
|
||||
abbiamo
|
||||
avete
|
||||
hanno
|
||||
abbia
|
||||
abbiate
|
||||
abbiano
|
||||
avrò
|
||||
avrai
|
||||
avrà
|
||||
avremo
|
||||
avrete
|
||||
avranno
|
||||
avrei
|
||||
avresti
|
||||
avrebbe
|
||||
avremmo
|
||||
avreste
|
||||
avrebbero
|
||||
avevo
|
||||
avevi
|
||||
aveva
|
||||
avevamo
|
||||
avevate
|
||||
avevano
|
||||
ebbi
|
||||
avesti
|
||||
ebbe
|
||||
avemmo
|
||||
aveste
|
||||
ebbero
|
||||
avessi
|
||||
avesse
|
||||
avessimo
|
||||
avessero
|
||||
avendo
|
||||
avuto
|
||||
avuta
|
||||
avuti
|
||||
avute
|
||||
|
||||
| forms of essere, to be (not including the infinitive):
|
||||
sono
|
||||
sei
|
||||
è
|
||||
siamo
|
||||
siete
|
||||
sia
|
||||
siate
|
||||
siano
|
||||
sarò
|
||||
sarai
|
||||
sarà
|
||||
saremo
|
||||
sarete
|
||||
saranno
|
||||
sarei
|
||||
saresti
|
||||
sarebbe
|
||||
saremmo
|
||||
sareste
|
||||
sarebbero
|
||||
ero
|
||||
eri
|
||||
era
|
||||
eravamo
|
||||
eravate
|
||||
erano
|
||||
fui
|
||||
fosti
|
||||
fu
|
||||
fummo
|
||||
foste
|
||||
furono
|
||||
fossi
|
||||
fosse
|
||||
fossimo
|
||||
fossero
|
||||
essendo
|
||||
|
||||
| forms of fare, to do (not including the infinitive, fa, fat-):
|
||||
faccio
|
||||
fai
|
||||
facciamo
|
||||
fanno
|
||||
faccia
|
||||
facciate
|
||||
facciano
|
||||
farò
|
||||
farai
|
||||
farà
|
||||
faremo
|
||||
farete
|
||||
faranno
|
||||
farei
|
||||
faresti
|
||||
farebbe
|
||||
faremmo
|
||||
fareste
|
||||
farebbero
|
||||
facevo
|
||||
facevi
|
||||
faceva
|
||||
facevamo
|
||||
facevate
|
||||
facevano
|
||||
feci
|
||||
facesti
|
||||
fece
|
||||
facemmo
|
||||
faceste
|
||||
fecero
|
||||
facessi
|
||||
facesse
|
||||
facessimo
|
||||
facessero
|
||||
facendo
|
||||
|
||||
| forms of stare, to be (not including the infinitive):
|
||||
sto
|
||||
stai
|
||||
sta
|
||||
stiamo
|
||||
stanno
|
||||
stia
|
||||
stiate
|
||||
stiano
|
||||
starò
|
||||
starai
|
||||
starà
|
||||
staremo
|
||||
starete
|
||||
staranno
|
||||
starei
|
||||
staresti
|
||||
starebbe
|
||||
staremmo
|
||||
stareste
|
||||
starebbero
|
||||
stavo
|
||||
stavi
|
||||
stava
|
||||
stavamo
|
||||
stavate
|
||||
stavano
|
||||
stetti
|
||||
stesti
|
||||
stette
|
||||
stemmo
|
||||
steste
|
||||
stettero
|
||||
stessi
|
||||
stesse
|
||||
stessimo
|
||||
stessero
|
||||
stando
|
@ -0,0 +1,127 @@
|
||||
#
|
||||
# This file defines a stopword set for Japanese.
|
||||
#
|
||||
# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
|
||||
# Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745
|
||||
# for frequency lists, etc. that can be useful for making your own set (if desired)
|
||||
#
|
||||
# Note that there is an overlap between these stopwords and the terms stopped when used
|
||||
# in combination with the JapanesePartOfSpeechStopFilter. When editing this file, note
|
||||
# that comments are not allowed on the same line as stopwords.
|
||||
#
|
||||
# Also note that stopping is done in a case-insensitive manner. Change your StopFilter
|
||||
# configuration if you need case-sensitive stopping. Lastly, note that stopping is done
|
||||
# using the same character width as the entries in this file. Since this StopFilter is
|
||||
# normally done after a CJKWidthFilter in your chain, you would usually want your romaji
|
||||
# entries to be in half-width and your kana entries to be in full-width.
|
||||
#
|
||||
の
|
||||
に
|
||||
は
|
||||
を
|
||||
た
|
||||
が
|
||||
で
|
||||
て
|
||||
と
|
||||
し
|
||||
れ
|
||||
さ
|
||||
ある
|
||||
いる
|
||||
も
|
||||
する
|
||||
から
|
||||
な
|
||||
こと
|
||||
として
|
||||
い
|
||||
や
|
||||
れる
|
||||
など
|
||||
なっ
|
||||
ない
|
||||
この
|
||||
ため
|
||||
その
|
||||
あっ
|
||||
よう
|
||||
また
|
||||
もの
|
||||
という
|
||||
あり
|
||||
まで
|
||||
られ
|
||||
なる
|
||||
へ
|
||||
か
|
||||
だ
|
||||
これ
|
||||
によって
|
||||
により
|
||||
おり
|
||||
より
|
||||
による
|
||||
ず
|
||||
なり
|
||||
られる
|
||||
において
|
||||
ば
|
||||
なかっ
|
||||
なく
|
||||
しかし
|
||||
について
|
||||
せ
|
||||
だっ
|
||||
その後
|
||||
できる
|
||||
それ
|
||||
う
|
||||
ので
|
||||
なお
|
||||
のみ
|
||||
でき
|
||||
き
|
||||
つ
|
||||
における
|
||||
および
|
||||
いう
|
||||
さらに
|
||||
でも
|
||||
ら
|
||||
たり
|
||||
その他
|
||||
に関する
|
||||
たち
|
||||
ます
|
||||
ん
|
||||
なら
|
||||
に対して
|
||||
特に
|
||||
せる
|
||||
及び
|
||||
これら
|
||||
とき
|
||||
では
|
||||
にて
|
||||
ほか
|
||||
ながら
|
||||
うち
|
||||
そして
|
||||
とともに
|
||||
ただし
|
||||
かつて
|
||||
それぞれ
|
||||
または
|
||||
お
|
||||
ほど
|
||||
ものの
|
||||
に対する
|
||||
ほとんど
|
||||
と共に
|
||||
といった
|
||||
です
|
||||
とも
|
||||
ところ
|
||||
ここ
|
||||
##### End of file
|
@ -0,0 +1,172 @@
|
||||
# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
|
||||
# the original list of over 800 forms was refined:
|
||||
# pronouns, adverbs, interjections were removed
|
||||
#
|
||||
# prepositions
|
||||
aiz
|
||||
ap
|
||||
ar
|
||||
apakš
|
||||
ārpus
|
||||
augšpus
|
||||
bez
|
||||
caur
|
||||
dēļ
|
||||
gar
|
||||
iekš
|
||||
iz
|
||||
kopš
|
||||
labad
|
||||
lejpus
|
||||
līdz
|
||||
no
|
||||
otrpus
|
||||
pa
|
||||
par
|
||||
pār
|
||||
pēc
|
||||
pie
|
||||
pirms
|
||||
pret
|
||||
priekš
|
||||
starp
|
||||
šaipus
|
||||
uz
|
||||
viņpus
|
||||
virs
|
||||
virspus
|
||||
zem
|
||||
apakšpus
|
||||
# Conjunctions
|
||||
un
|
||||
bet
|
||||
jo
|
||||
ja
|
||||
ka
|
||||
lai
|
||||
tomēr
|
||||
tikko
|
||||
turpretī
|
||||
arī
|
||||
kaut
|
||||
gan
|
||||
tādēļ
|
||||
tā
|
||||
ne
|
||||
tikvien
|
||||
vien
|
||||
kā
|
||||
ir
|
||||
te
|
||||
vai
|
||||
kamēr
|
||||
# Particles
|
||||
ar
|
||||
diezin
|
||||
droši
|
||||
diemžēl
|
||||
nebūt
|
||||
ik
|
||||
it
|
||||
taču
|
||||
nu
|
||||
pat
|
||||
tiklab
|
||||
iekšpus
|
||||
nedz
|
||||
tik
|
||||
nevis
|
||||
turpretim
|
||||
jeb
|
||||
iekam
|
||||
iekām
|
||||
iekāms
|
||||
kolīdz
|
||||
līdzko
|
||||
tiklīdz
|
||||
jebšu
|
||||
tālab
|
||||
tāpēc
|
||||
nekā
|
||||
itin
|
||||
jā
|
||||
jau
|
||||
jel
|
||||
nē
|
||||
nezin
|
||||
tad
|
||||
tikai
|
||||
vis
|
||||
tak
|
||||
iekams
|
||||
vien
|
||||
# modal verbs
|
||||
būt
|
||||
biju
|
||||
biji
|
||||
bija
|
||||
bijām
|
||||
bijāt
|
||||
esmu
|
||||
esi
|
||||
esam
|
||||
esat
|
||||
būšu
|
||||
būsi
|
||||
būs
|
||||
būsim
|
||||
būsiet
|
||||
tikt
|
||||
tiku
|
||||
tiki
|
||||
tika
|
||||
tikām
|
||||
tikāt
|
||||
tieku
|
||||
tiec
|
||||
tiek
|
||||
tiekam
|
||||
tiekat
|
||||
tikšu
|
||||
tiks
|
||||
tiksim
|
||||
tiksiet
|
||||
tapt
|
||||
tapi
|
||||
tapāt
|
||||
topat
|
||||
tapšu
|
||||
tapsi
|
||||
taps
|
||||
tapsim
|
||||
tapsiet
|
||||
kļūt
|
||||
kļuvu
|
||||
kļuvi
|
||||
kļuva
|
||||
kļuvām
|
||||
kļuvāt
|
||||
kļūstu
|
||||
kļūsti
|
||||
kļūst
|
||||
kļūstam
|
||||
kļūstat
|
||||
kļūšu
|
||||
kļūsi
|
||||
kļūs
|
||||
kļūsim
|
||||
kļūsiet
|
||||
# verbs
|
||||
varēt
|
||||
varēju
|
||||
varējām
|
||||
varēšu
|
||||
varēsim
|
||||
var
|
||||
varēji
|
||||
varējāt
|
||||
varēsi
|
||||
varēsiet
|
||||
varat
|
||||
varēja
|
||||
varēs
|
@ -0,0 +1,119 @@
|
||||
| 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
|
@ -0,0 +1,194 @@
|
||||
| From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/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 Norwegian stop word list. Comments begin with vertical bar. Each stop
|
||||
| word is at the start of a line.
|
||||
|
||||
| This stop word list is for the dominant bokmål dialect. Words unique
|
||||
| to nynorsk are marked *.
|
||||
|
||||
| Revised by Jan Bruusgaard <Jan.Bruusgaard@ssb.no>, Jan 2005
|
||||
|
||||
og | and
|
||||
i | in
|
||||
jeg | I
|
||||
det | it/this/that
|
||||
at | to (w. inf.)
|
||||
en | a/an
|
||||
et | a/an
|
||||
den | it/this/that
|
||||
til | to
|
||||
er | is/am/are
|
||||
som | who/that
|
||||
på | on
|
||||
de | they / you(formal)
|
||||
med | with
|
||||
han | he
|
||||
av | of
|
||||
ikke | not
|
||||
ikkje | not *
|
||||
der | there
|
||||
så | so
|
||||
var | was/were
|
||||
meg | me
|
||||
seg | you
|
||||
men | but
|
||||
ett | one
|
||||
har | have
|
||||
om | about
|
||||
vi | we
|
||||
min | my
|
||||
mitt | my
|
||||
ha | have
|
||||
hadde | had
|
||||
hun | she
|
||||
nå | now
|
||||
over | over
|
||||
da | when/as
|
||||
ved | by/know
|
||||
fra | from
|
||||
du | you
|
||||
ut | out
|
||||
sin | your
|
||||
dem | them
|
||||
oss | us
|
||||
opp | up
|
||||
man | you/one
|
||||
kan | can
|
||||
hans | his
|
||||
hvor | where
|
||||
eller | or
|
||||
hva | what
|
||||
skal | shall/must
|
||||
selv | self (reflective)
|
||||
sjøl | self (reflective)
|
||||
her | here
|
||||
alle | all
|
||||
vil | will
|
||||
bli | become
|
||||
ble | became
|
||||
blei | became *
|
||||
blitt | have become
|
||||
kunne | could
|
||||
inn | in
|
||||
når | when
|
||||
være | be
|
||||
kom | come
|
||||
noen | some
|
||||
noe | some
|
||||
ville | would
|
||||
dere | you
|
||||
som | who/which/that
|
||||
deres | their/theirs
|
||||
kun | only/just
|
||||
ja | yes
|
||||
etter | after
|
||||
ned | down
|
||||
skulle | should
|
||||
denne | this
|
||||
for | for/because
|
||||
deg | you
|
||||
si | hers/his
|
||||
sine | hers/his
|
||||
sitt | hers/his
|
||||
mot | against
|
||||
å | to
|
||||
meget | much
|
||||
hvorfor | why
|
||||
dette | this
|
||||
disse | these/those
|
||||
uten | without
|
||||
hvordan | how
|
||||
ingen | none
|
||||
din | your
|
||||
ditt | your
|
||||
blir | become
|
||||
samme | same
|
||||
hvilken | which
|
||||
hvilke | which (plural)
|
||||
sånn | such a
|
||||
inni | inside/within
|
||||
mellom | between
|
||||
vår | our
|
||||
hver | each
|
||||
hvem | who
|
||||
vors | us/ours
|
||||
hvis | whose
|
||||
både | both
|
||||
bare | only/just
|
||||
enn | than
|
||||
fordi | as/because
|
||||
før | before
|
||||
mange | many
|
||||
også | also
|
||||
slik | just
|
||||
vært | been
|
||||
være | to be
|
||||
båe | both *
|
||||
begge | both
|
||||
siden | since
|
||||
dykk | your *
|
||||
dykkar | yours *
|
||||
dei | they *
|
||||
deira | them *
|
||||
deires | theirs *
|
||||
deim | them *
|
||||
di | your (fem.) *
|
||||
då | as/when *
|
||||
eg | I *
|
||||
ein | a/an *
|
||||
eit | a/an *
|
||||
eitt | a/an *
|
||||
elles | or *
|
||||
honom | he *
|
||||
hjå | at *
|
||||
ho | she *
|
||||
hoe | she *
|
||||
henne | her
|
||||
hennar | her/hers
|
||||
hennes | hers
|
||||
hoss | how *
|
||||
hossen | how *
|
||||
ikkje | not *
|
||||
ingi | noone *
|
||||
inkje | noone *
|
||||
korleis | how *
|
||||
korso | how *
|
||||
kva | what/which *
|
||||
kvar | where *
|
||||
kvarhelst | where *
|
||||
kven | who/whom *
|
||||
kvi | why *
|
||||
kvifor | why *
|
||||
me | we *
|
||||
medan | while *
|
||||
mi | my *
|
||||
mine | my *
|
||||
mykje | much *
|
||||
no | now *
|
||||
nokon | some (masc./neut.) *
|
||||
noka | some (fem.) *
|
||||
nokor | some *
|
||||
noko | some *
|
||||
nokre | some *
|
||||
si | his/hers *
|
||||
sia | since *
|
||||
sidan | since *
|
||||
so | so *
|
||||
somt | some *
|
||||
somme | some *
|
||||
um | about*
|
||||
upp | up *
|
||||
vere | be *
|
||||
vore | was *
|
||||
verte | become *
|
||||
vort | become *
|
||||
varte | became *
|
||||
vart | became *
|
||||
|
@ -0,0 +1,253 @@
|
||||
| From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/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 Portuguese stop word list. Comments begin with vertical bar. Each stop
|
||||
| word is at the start of a line.
|
||||
|
||||
|
||||
| The following is a ranked list (commonest to rarest) of stopwords
|
||||
| deriving from a large sample of text.
|
||||
|
||||
| Extra words have been added at the end.
|
||||
|
||||
de | of, from
|
||||
a | the; to, at; her
|
||||
o | the; him
|
||||
que | who, that
|
||||
e | and
|
||||
do | de + o
|
||||
da | de + a
|
||||
em | in
|
||||
um | a
|
||||
para | for
|
||||
| é from SER
|
||||
com | with
|
||||
não | not, no
|
||||
uma | a
|
||||
os | the; them
|
||||
no | em + o
|
||||
se | himself etc
|
||||
na | em + a
|
||||
por | for
|
||||
mais | more
|
||||
as | the; them
|
||||
dos | de + os
|
||||
como | as, like
|
||||
mas | but
|
||||
| foi from SER
|
||||
ao | a + o
|
||||
ele | he
|
||||
das | de + as
|
||||
| tem from TER
|
||||
à | a + a
|
||||
seu | his
|
||||
sua | her
|
||||
ou | or
|
||||
| ser from SER
|
||||
quando | when
|
||||
muito | much
|
||||
| há from HAV
|
||||
nos | em + os; us
|
||||
já | already, now
|
||||
| está from EST
|
||||
eu | I
|
||||
também | also
|
||||
só | only, just
|
||||
pelo | per + o
|
||||
pela | per + a
|
||||
até | up to
|
||||
isso | that
|
||||
ela | he
|
||||
entre | between
|
||||
| era from SER
|
||||
depois | after
|
||||
sem | without
|
||||
mesmo | same
|
||||
aos | a + os
|
||||
| ter from TER
|
||||
seus | his
|
||||
quem | whom
|
||||
nas | em + as
|
||||
me | me
|
||||
esse | that
|
||||
eles | they
|
||||
| estão from EST
|
||||
você | you
|
||||
| tinha from TER
|
||||
| foram from SER
|
||||
essa | that
|
||||
num | em + um
|
||||
nem | nor
|
||||
suas | her
|
||||
meu | my
|
||||
às | a + as
|
||||
minha | my
|
||||
| têm from TER
|
||||
numa | em + uma
|
||||
pelos | per + os
|
||||
elas | they
|
||||
| havia from HAV
|
||||
| seja from SER
|
||||
qual | which
|
||||
| será from SER
|
||||
nós | we
|
||||
| tenho from TER
|
||||
lhe | to him, her
|
||||
deles | of them
|
||||
essas | those
|
||||
esses | those
|
||||
pelas | per + as
|
||||
este | this
|
||||
| fosse from SER
|
||||
dele | of him
|
||||
|
||||
| other words. There are many contractions such as naquele = em+aquele,
|
||||
| mo = me+o, but they are rare.
|
||||
| Indefinite article plural forms are also rare.
|
||||
|
||||
tu | thou
|
||||
te | thee
|
||||
vocês | you (plural)
|
||||
vos | you
|
||||
lhes | to them
|
||||
meus | my
|
||||
minhas
|
||||
teu | thy
|
||||
tua
|
||||
teus
|
||||
tuas
|
||||
nosso | our
|
||||
nossa
|
||||
nossos
|
||||
nossas
|
||||
|
||||
dela | of her
|
||||
delas | of them
|
||||
|
||||
esta | this
|
||||
estes | these
|
||||
estas | these
|
||||
aquele | that
|
||||
aquela | that
|
||||
aqueles | those
|
||||
aquelas | those
|
||||
isto | this
|
||||
aquilo | that
|
||||
|
||||
| forms of estar, to be (not including the infinitive):
|
||||
estou
|
||||
está
|
||||
estamos
|
||||
estão
|
||||
estive
|
||||
esteve
|
||||
estivemos
|
||||
estiveram
|
||||
estava
|
||||
estávamos
|
||||
estavam
|
||||
estivera
|
||||
estivéramos
|
||||
esteja
|
||||
estejamos
|
||||
estejam
|
||||
estivesse
|
||||
estivéssemos
|
||||
estivessem
|
||||
estiver
|
||||
estivermos
|
||||
estiverem
|
||||
|
||||
| forms of haver, to have (not including the infinitive):
|
||||
hei
|
||||
há
|
||||
havemos
|
||||
hão
|
||||
houve
|
||||
houvemos
|
||||
houveram
|
||||
houvera
|
||||
houvéramos
|
||||
haja
|
||||
hajamos
|
||||
hajam
|
||||
houvesse
|
||||
houvéssemos
|
||||
houvessem
|
||||
houver
|
||||
houvermos
|
||||
houverem
|
||||
houverei
|
||||
houverá
|
||||
houveremos
|
||||
houverão
|
||||
houveria
|
||||
houveríamos
|
||||
houveriam
|
||||
|
||||
| forms of ser, to be (not including the infinitive):
|
||||
sou
|
||||
somos
|
||||
são
|
||||
era
|
||||
éramos
|
||||
eram
|
||||
fui
|
||||
foi
|
||||
fomos
|
||||
foram
|
||||
fora
|
||||
fôramos
|
||||
seja
|
||||
sejamos
|
||||
sejam
|
||||
fosse
|
||||
fôssemos
|
||||
fossem
|
||||
for
|
||||
formos
|
||||
forem
|
||||
serei
|
||||
será
|
||||
seremos
|
||||
serão
|
||||
seria
|
||||
seríamos
|
||||
seriam
|
||||
|
||||
| forms of ter, to have (not including the infinitive):
|
||||
tenho
|
||||
tem
|
||||
temos
|
||||
tém
|
||||
tinha
|
||||
tínhamos
|
||||
tinham
|
||||
tive
|
||||
teve
|
||||
tivemos
|
||||
tiveram
|
||||
tivera
|
||||
tivéramos
|
||||
tenha
|
||||
tenhamos
|
||||
tenham
|
||||
tivesse
|
||||
tivéssemos
|
||||
tivessem
|
||||
tiver
|
||||
tivermos
|
||||
tiverem
|
||||
terei
|
||||
terá
|
||||
teremos
|
||||
terão
|
||||
teria
|
||||
teríamos
|
||||
teriam
|
@ -0,0 +1,233 @@
|
||||
# This file was created by Jacques Savoy and is distributed under the BSD license.
|
||||
# See http://members.unine.ch/jacques.savoy/clef/index.html.
|
||||
# Also see http://www.opensource.org/licenses/bsd-license.html
|
||||
acea
|
||||
aceasta
|
||||
această
|
||||
aceea
|
||||
acei
|
||||
aceia
|
||||
acel
|
||||
acela
|
||||
acele
|
||||
acelea
|
||||
acest
|
||||
acesta
|
||||
aceste
|
||||
acestea
|
||||
aceşti
|
||||
aceştia
|
||||
acolo
|
||||
acum
|
||||
ai
|
||||
aia
|
||||
aibă
|
||||
aici
|
||||
al
|
||||
ăla
|
||||
ale
|
||||
alea
|
||||
ălea
|
||||
altceva
|
||||
altcineva
|
||||
am
|
||||
ar
|
||||
are
|
||||
aş
|
||||
aşadar
|
||||
asemenea
|
||||
asta
|
||||
ăsta
|
||||
astăzi
|
||||
astea
|
||||
ăstea
|
||||
ăştia
|
||||
asupra
|
||||
aţi
|
||||
au
|
||||
avea
|
||||
avem
|
||||
aveţi
|
||||
azi
|
||||
bine
|
||||
bucur
|
||||
bună
|
||||
ca
|
||||
că
|
||||
căci
|
||||
când
|
||||
care
|
||||
cărei
|
||||
căror
|
||||
cărui
|
||||
cât
|
||||
câte
|
||||
câţi
|
||||
către
|
||||
câtva
|
||||
ce
|
||||
cel
|
||||
ceva
|
||||
chiar
|
||||
cînd
|
||||
cine
|
||||
cineva
|
||||
cît
|
||||
cîte
|
||||
cîţi
|
||||
cîtva
|
||||
contra
|
||||
cu
|
||||
cum
|
||||
cumva
|
||||
curând
|
||||
curînd
|
||||
da
|
||||
dă
|
||||
dacă
|
||||
dar
|
||||
datorită
|
||||
de
|
||||
deci
|
||||
deja
|
||||
deoarece
|
||||
departe
|
||||
deşi
|
||||
din
|
||||
dinaintea
|
||||
dintr
|
||||
dintre
|
||||
drept
|
||||
după
|
||||
ea
|
||||
ei
|
||||
el
|
||||
ele
|
||||
eram
|
||||
este
|
||||
eşti
|
||||
eu
|
||||
face
|
||||
fără
|
||||
fi
|
||||
fie
|
||||
fiecare
|
||||
fii
|
||||
fim
|
||||
fiţi
|
||||
iar
|
||||
ieri
|
||||
îi
|
||||
îl
|
||||
îmi
|
||||
împotriva
|
||||
în
|
||||
înainte
|
||||
înaintea
|
||||
încât
|
||||
încît
|
||||
încotro
|
||||
între
|
||||
întrucât
|
||||
întrucît
|
||||
îţi
|
||||
la
|
||||
lângă
|
||||
le
|
||||
li
|
||||
lîngă
|
||||
lor
|
||||
lui
|
||||
mă
|
||||
mâine
|
||||
mea
|
||||
mei
|
||||
mele
|
||||
mereu
|
||||
meu
|
||||
mi
|
||||
mine
|
||||
mult
|
||||
multă
|
||||
mulţi
|
||||
ne
|
||||
nicăieri
|
||||
nici
|
||||
nimeni
|
||||
nişte
|
||||
noastră
|
||||
noastre
|
||||
noi
|
||||
noştri
|
||||
nostru
|
||||
nu
|
||||
ori
|
||||
oricând
|
||||
oricare
|
||||
oricât
|
||||
orice
|
||||
oricînd
|
||||
oricine
|
||||
oricît
|
||||
oricum
|
||||
oriunde
|
||||
până
|
||||
pe
|
||||
pentru
|
||||
peste
|
||||
pînă
|
||||
poate
|
||||
pot
|
||||
prea
|
||||
prima
|
||||
primul
|
||||
prin
|
||||
printr
|
||||
sa
|
||||
să
|
||||
săi
|
||||
sale
|
||||
sau
|
||||
său
|
||||
se
|
||||
şi
|
||||
sînt
|
||||
sîntem
|
||||
sînteţi
|
||||
spre
|
||||
sub
|
||||
sunt
|
||||
suntem
|
||||
sunteţi
|
||||
ta
|
||||
tăi
|
||||
tale
|
||||
tău
|
||||
te
|
||||
ţi
|
||||
ţie
|
||||
tine
|
||||
toată
|
||||
toate
|
||||
tot
|
||||
toţi
|
||||
totuşi
|
||||
tu
|
||||
un
|
||||
una
|
||||
unde
|
||||
undeva
|
||||
unei
|
||||
unele
|
||||
uneori
|
||||
unor
|
||||
vă
|
||||
vi
|
||||
voastră
|
||||
voastre
|
||||
voi
|
||||
voştri
|
||||
vostru
|
||||
vouă
|
||||
vreo
|
||||
vreun
|
@ -0,0 +1,133 @@
|
||||
| From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/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 Swedish 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 text sample.
|
||||
|
||||
| Swedish stop words occasionally exhibit homonym clashes. For example
|
||||
| så = so, but also seed. These are indicated clearly below.
|
||||
|
||||
och | and
|
||||
det | it, this/that
|
||||
att | to (with infinitive)
|
||||
i | in, at
|
||||
en | a
|
||||
jag | I
|
||||
hon | she
|
||||
som | who, that
|
||||
han | he
|
||||
på | on
|
||||
den | it, this/that
|
||||
med | with
|
||||
var | where, each
|
||||
sig | him(self) etc
|
||||
för | for
|
||||
så | so (also: seed)
|
||||
till | to
|
||||
är | is
|
||||
men | but
|
||||
ett | a
|
||||
om | if; around, about
|
||||
hade | had
|
||||
de | they, these/those
|
||||
av | of
|
||||
icke | not, no
|
||||
mig | me
|
||||
du | you
|
||||
henne | her
|
||||
då | then, when
|
||||
sin | his
|
||||
nu | now
|
||||
har | have
|
||||
inte | inte någon = no one
|
||||
hans | his
|
||||
honom | him
|
||||
skulle | 'sake'
|
||||
hennes | her
|
||||
där | there
|
||||
min | my
|
||||
man | one (pronoun)
|
||||
ej | nor
|
||||
vid | at, by, on (also: vast)
|
||||
kunde | could
|
||||
något | some etc
|
||||
från | from, off
|
||||
ut | out
|
||||
när | when
|
||||
efter | after, behind
|
||||
upp | up
|
||||
vi | we
|
||||
dem | them
|
||||
vara | be
|
||||
vad | what
|
||||
över | over
|
||||
än | than
|
||||
dig | you
|
||||
kan | can
|
||||
sina | his
|
||||
här | here
|
||||
ha | have
|
||||
mot | towards
|
||||
alla | all
|
||||
under | under (also: wonder)
|
||||
någon | some etc
|
||||
eller | or (else)
|
||||
allt | all
|
||||
mycket | much
|
||||
sedan | since
|
||||
ju | why
|
||||
denna | this/that
|
||||
själv | myself, yourself etc
|
||||
detta | this/that
|
||||
åt | to
|
||||
utan | without
|
||||
varit | was
|
||||
hur | how
|
||||
ingen | no
|
||||
mitt | my
|
||||
ni | you
|
||||
bli | to be, become
|
||||
blev | from bli
|
||||
oss | us
|
||||
din | thy
|
||||
dessa | these/those
|
||||
några | some etc
|
||||
deras | their
|
||||
blir | from bli
|
||||
mina | my
|
||||
samma | (the) same
|
||||
vilken | who, that
|
||||
er | you, your
|
||||
sådan | such a
|
||||
vår | our
|
||||
blivit | from bli
|
||||
dess | its
|
||||
inom | within
|
||||
mellan | between
|
||||
sådant | such a
|
||||
varför | why
|
||||
varje | each
|
||||
vilka | who, that
|
||||
ditt | thy
|
||||
vem | who
|
||||
vilket | who, that
|
||||
sitta | his
|
||||
sådana | such a
|
||||
vart | each
|
||||
dina | thy
|
||||
vars | whose
|
||||
vårt | our
|
||||
våra | our
|
||||
ert | your
|
||||
era | your
|
||||
vilkas | whose
|
||||
|
@ -0,0 +1,119 @@
|
||||
# Thai stopwords from:
|
||||
# "Opinion Detection in Thai Political News Columns
|
||||
# Based on Subjectivity Analysis"
|
||||
# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
|
||||
ไว้
|
||||
ไม่
|
||||
ไป
|
||||
ได้
|
||||
ให้
|
||||
ใน
|
||||
โดย
|
||||
แห่ง
|
||||
แล้ว
|
||||
และ
|
||||
แรก
|
||||
แบบ
|
||||
แต่
|
||||
เอง
|
||||
เห็น
|
||||
เลย
|
||||
เริ่ม
|
||||
เรา
|
||||
เมื่อ
|
||||
เพื่อ
|
||||
เพราะ
|
||||
เป็นการ
|
||||
เป็น
|
||||
เปิดเผย
|
||||
เปิด
|
||||
เนื่องจาก
|
||||
เดียวกัน
|
||||
เดียว
|
||||
เช่น
|
||||
เฉพาะ
|
||||
เคย
|
||||
เข้า
|
||||
เขา
|
||||
อีก
|
||||
อาจ
|
||||
อะไร
|
||||
ออก
|
||||
อย่าง
|
||||
อยู่
|
||||
อยาก
|
||||
หาก
|
||||
หลาย
|
||||
หลังจาก
|
||||
หลัง
|
||||
หรือ
|
||||
หนึ่ง
|
||||
ส่วน
|
||||
ส่ง
|
||||
สุด
|
||||
สําหรับ
|
||||
ว่า
|
||||
วัน
|
||||
ลง
|
||||
ร่วม
|
||||
ราย
|
||||
รับ
|
||||
ระหว่าง
|
||||
รวม
|
||||
ยัง
|
||||
มี
|
||||
มาก
|
||||
มา
|
||||
พร้อม
|
||||
พบ
|
||||
ผ่าน
|
||||
ผล
|
||||
บาง
|
||||
น่า
|
||||
นี้
|
||||
นํา
|
||||
นั้น
|
||||
นัก
|
||||
นอกจาก
|
||||
ทุก
|
||||
ที่สุด
|
||||
ที่
|
||||
ทําให้
|
||||
ทํา
|
||||
ทาง
|
||||
ทั้งนี้
|
||||
ทั้ง
|
||||
ถ้า
|
||||
ถูก
|
||||
ถึง
|
||||
ต้อง
|
||||
ต่างๆ
|
||||
ต่าง
|
||||
ต่อ
|
||||
ตาม
|
||||
ตั้งแต่
|
||||
ตั้ง
|
||||
ด้าน
|
||||
ด้วย
|
||||
ดัง
|
||||
ซึ่ง
|
||||
ช่วง
|
||||
จึง
|
||||
จาก
|
||||
จัด
|
||||
จะ
|
||||
คือ
|
||||
ความ
|
||||
ครั้ง
|
||||
คง
|
||||
ขึ้น
|
||||
ของ
|
||||
ขอ
|
||||
ขณะ
|
||||
ก่อน
|
||||
ก็
|
||||
การ
|
||||
กับ
|
||||
กัน
|
||||
กว่า
|
||||
กล่าว
|
@ -0,0 +1,29 @@
|
||||
#
|
||||
# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
|
||||
#
|
||||
# Add entries to this file in order to override the statistical model in terms
|
||||
# of segmentation, readings and part-of-speech tags. Notice that entries do
|
||||
# not have weights since they are always used when found. This is by-design
|
||||
# in order to maximize ease-of-use.
|
||||
#
|
||||
# Entries are defined using the following CSV format:
|
||||
# <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
|
||||
#
|
||||
# Notice that a single half-width space separates tokens and readings, and
|
||||
# that the number tokens and readings must match exactly.
|
||||
#
|
||||
# Also notice that multiple entries with the same <text> is undefined.
|
||||
#
|
||||
# Whitespace only lines are ignored. Comments are not allowed on entry lines.
|
||||
#
|
||||
|
||||
# Custom segmentation for kanji compounds
|
||||
日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
|
||||
関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
|
||||
|
||||
# Custom segmentation for compound katakana
|
||||
トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
|
||||
ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
|
||||
|
||||
# Custom reading for former sumo wrestler
|
||||
朝青龍,朝青龍,アサショウリュウ,カスタム人名
|
@ -0,0 +1,411 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!-- Solr managed schema - automatically generated - DO NOT EDIT -->
|
||||
<schema name="dnet" version="1.0">
|
||||
<uniqueKey>__indexrecordidentifier</uniqueKey>
|
||||
<fieldType name="ancestor_path" class="solr.TextField">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<fieldType name="binary" class="solr.BinaryField"/>
|
||||
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
|
||||
<fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
|
||||
<fieldType name="date" class="solr.TrieDateField" positionIncrementGap="0" docValues="true" precisionStep="0"/>
|
||||
<fieldType name="dates" class="solr.TrieDateField" positionIncrementGap="0" docValues="true" multiValued="true" precisionStep="0"/>
|
||||
<fieldType name="descendent_path" class="solr.TextField">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<fieldType name="double" class="solr.TrieDoubleField" positionIncrementGap="0" docValues="true" precisionStep="0"/>
|
||||
<fieldType name="doubles" class="solr.TrieDoubleField" positionIncrementGap="0" docValues="true" multiValued="true" precisionStep="0"/>
|
||||
<fieldType name="float" class="solr.TrieFloatField" positionIncrementGap="0" docValues="true" precisionStep="0"/>
|
||||
<fieldType name="floats" class="solr.TrieFloatField" positionIncrementGap="0" docValues="true" multiValued="true" precisionStep="0"/>
|
||||
<fieldType name="ignored" class="solr.StrField" indexed="false" stored="false" docValues="false" multiValued="true"/>
|
||||
<fieldType name="int" class="solr.TrieIntField" positionIncrementGap="0" docValues="true" precisionStep="0"/>
|
||||
<fieldType name="ints" class="solr.TrieIntField" positionIncrementGap="0" docValues="true" multiValued="true" precisionStep="0"/>
|
||||
<fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
|
||||
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType" geo="true" maxDistErr="0.001" distErrPct="0.025" distanceUnits="kilometers"/>
|
||||
<fieldType name="long" class="solr.TrieLongField" positionIncrementGap="0" docValues="true" precisionStep="0"/>
|
||||
<fieldType name="longs" class="solr.TrieLongField" positionIncrementGap="0" docValues="true" multiValued="true" precisionStep="0"/>
|
||||
<fieldType name="ngramtext" class="solr.TextField">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.NGramFilterFactory" maxGramSize="25" minGramSize="3"/>
|
||||
<filter class="solr.TrimFilterFactory"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
|
||||
<fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
|
||||
<fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
|
||||
<fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
|
||||
<fieldType name="personName" class="solr.TextField" positionIncrementGap="100">
|
||||
<analyzer>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<fieldType name="personNamePrefix" class="solr.TextField" positionIncrementGap="100">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.NGramFilterFactory" maxGramSize="30" minGramSize="1"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
|
||||
<fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
|
||||
<fieldType name="phonetic_en" class="solr.TextField" indexed="true" stored="false">
|
||||
<analyzer>
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<fieldType name="pint" class="solr.IntPointField" docValues="true"/>
|
||||
<fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
|
||||
<fieldType name="plong" class="solr.LongPointField" docValues="true"/>
|
||||
<fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
|
||||
<fieldType name="point" class="solr.PointType" subFieldSuffix="_d" dimension="2"/>
|
||||
<fieldType name="random" class="solr.RandomSortField" indexed="true"/>
|
||||
<fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true"/>
|
||||
<fieldType name="string_ci" class="solr.TextField" omitNorms="true" sortMissingLast="true">
|
||||
<analyzer>
|
||||
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<fieldType name="strings" class="solr.StrField" sortMissingLast="true" docValues="true" multiValued="true"/>
|
||||
<fieldType name="tdate" class="solr.TrieDateField" positionIncrementGap="0" docValues="true" precisionStep="6"/>
|
||||
<fieldType name="tdates" class="solr.TrieDateField" positionIncrementGap="0" docValues="true" multiValued="true" precisionStep="6"/>
|
||||
<fieldType name="tdouble" class="solr.TrieDoubleField" positionIncrementGap="0" docValues="true" precisionStep="8"/>
|
||||
<fieldType name="tdoubles" class="solr.TrieDoubleField" positionIncrementGap="0" docValues="true" multiValued="true" precisionStep="8"/>
|
||||
<fieldType name="text_common" class="solr.TextField" positionIncrementGap="100" multiValued="true">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
||||
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
||||
<filter class="solr.PorterStemFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
|
||||
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
||||
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
||||
<filter class="solr.PorterStemFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<fieldType name="text_en_splitting" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="1"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
||||
<filter class="solr.PorterStemFilterFactory"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
|
||||
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="0"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
||||
<filter class="solr.PorterStemFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<fieldType name="text_en_splitting_tight" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
|
||||
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
||||
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
<filter class="solr.FlattenGraphFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
|
||||
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
||||
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
||||
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.ReversedWildcardFilterFactory" maxPosQuestion="2" maxFractionAsterisk="0.33" maxPosAsterisk="3" withOriginal="true"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.StandardTokenizerFactory"/>
|
||||
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
|
||||
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
|
||||
<analyzer>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<fieldType name="tfloat" class="solr.TrieFloatField" positionIncrementGap="0" docValues="true" precisionStep="8"/>
|
||||
<fieldType name="tfloats" class="solr.TrieFloatField" positionIncrementGap="0" docValues="true" multiValued="true" precisionStep="8"/>
|
||||
<fieldType name="tint" class="solr.TrieIntField" positionIncrementGap="0" docValues="true" precisionStep="8"/>
|
||||
<fieldType name="tints" class="solr.TrieIntField" positionIncrementGap="0" docValues="true" multiValued="true" precisionStep="8"/>
|
||||
<fieldType name="tlong" class="solr.TrieLongField" positionIncrementGap="0" docValues="true" precisionStep="8"/>
|
||||
<fieldType name="tlongs" class="solr.TrieLongField" positionIncrementGap="0" docValues="true" multiValued="true" precisionStep="8"/>
|
||||
|
||||
<!-- Indexed fields -->
|
||||
<field name="__all" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="__deleted" type="boolean" default="false" omitNorms="true" omitTermFreqAndPositions="true" indexed="true" stored="false"/>
|
||||
<field name="__dsid" type="string" omitNorms="true" omitTermFreqAndPositions="true" indexed="true" stored="true"/>
|
||||
<field name="__dsversion" type="pdate" omitNorms="true" omitTermFreqAndPositions="true" indexed="true" stored="true"/>
|
||||
<field name="__indexrecordidentifier" type="string" multiValued="false" indexed="true" required="true" stored="true"/>
|
||||
<field name="__result" type="string" docValues="false" multiValued="false" indexed="false" stored="true"/>
|
||||
<field name="_root_" type="string" docValues="false" indexed="true" stored="false"/>
|
||||
<field name="_version_" type="long" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="authorid" type="string_ci" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="authoridtype" type="string_ci" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="categoryid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="categoryname" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="collectedfrom" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="collectedfromdatasourceid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="collectedfromname" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="community" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="communityid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="communityname" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="conceptid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="conceptname" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="contextid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="contextname" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="contexttype" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="counter_affiliation" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="counter_authorship" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="counter_dedup" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="counter_doi" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="counter_outcome" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="counter_outcome_claimed" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="counter_outcome_collected" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="counter_outcome_inferred" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="counter_participation" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="counter_publicationdataset" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="counter_publicationdataset_claimed" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="counter_publicationdataset_collected" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="counter_publicationdataset_inferred" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="counter_similarity" type="pint" multiValued="false" indexed="true" stored="true"/>
|
||||
<field name="country" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="datasourcecompatibilityid" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="datasourcecompatibilityname" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="datasourceenglishname" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="datasourceodcontenttypes" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="datasourceoddescription" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="datasourceodlanguages" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="datasourceodsubjects" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="datasourceofficialname" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="datasourcesubject" type="ngramtext" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="datasourcetypename" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="datasourcetypeuiid" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="datasourcetypeuiname" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="dateofcollection" type="pdate" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="deletedbyinference" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="externalrefclass" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="externalrefid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="externalreflabel" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="externalrefsite" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="funder" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="funderid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="funderjurisdiction" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="fundername" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="funderoriginalname" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="fundershortname" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="fundinglevel0_description" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="fundinglevel0_id" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="fundinglevel0_name" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="fundinglevel1_description" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="fundinglevel1_id" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="fundinglevel1_name" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="fundinglevel2_description" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="fundinglevel2_id" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="fundinglevel2_name" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="inferenceprovenance" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="inferred" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="instancetypename" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="oafentity" type="string" multiValued="true" indexed="false" stored="false"/>
|
||||
<field name="oaftype" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="objidentifier" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="organizationalternativenames" type="ngramtext" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="organizationcountryname" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="organizationdupid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="organizationecenterprise" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="organizationecinternationalorganization" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="organizationecinternationalorganizationeurinterests" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="organizationeclegalbody" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="organizationeclegalperson" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="organizationecnonprofit" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="organizationecnutscode" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="organizationecresearchorganization" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="organizationecsmevalidated" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="organizationlegalname" type="ngramtext" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="organizationlegalshortname" type="ngramtext" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="originalid" type="string_ci" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="pid" type="string_ci" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="pidclassid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="pidclassname" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="projectacronym" type="ngramtext" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="projectcallidentifier" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="projectcode" type="ngramtext" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="projectcode_nt" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="projectcontracttypename" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="projectduration" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="projectecarticle29_3" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="projectecsc39" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="projectenddate" type="pdate" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="projectendyear" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="projectkeywords" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="projectoamandatepublications" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="projectstartdate" type="pdate" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="projectstartyear" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="projectsubject" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="projecttitle" type="ngramtext" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="provenanceactionclassid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relclass" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relcollectedfromid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relcollectedfromname" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relcontracttypeid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relcontracttypename" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="reldatasourcecompatibilityid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relfunder" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relfunderid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relfunderjurisdiction" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relfundername" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relfundershortname" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relfundinglevel0_id" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relfundinglevel0_name" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relfundinglevel1_id" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relfundinglevel1_name" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relfundinglevel2_id" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relfundinglevel2_name" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relinferenceprovenance" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relinferred" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relorganizationcountryid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relorganizationcountryname" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relorganizationid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relorganizationname" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relorganizationshortname" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relproject" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relprojectcode" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relprojectid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relprojectname" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relprojecttitle" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relprovenanceactionclassid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relresultid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="relresulttype" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="reltrust" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resultacceptanceyear" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="resultaccessright" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resultauthor" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resultauthor_nt" type="string_ci" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resultbestaccessright" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="resultdateofacceptance" type="pdate" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="resultdescription" type="text_en" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resultdupid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resultembargoenddate" type="pdate" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="resultembargoendyear" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="resulthostingdatasource" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resulthostingdatasourceid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resulthostingdatasourcename" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resultidentifier" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resultlanguagename" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="resultlicense" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resultpublisher" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resultsource" type="text_common" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resultsubject" type="text_en" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resultsubjectclass" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resulttitle" type="text_en" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="resulttypeid" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="resulttypename" type="string" multiValued="false" indexed="true" stored="false"/>
|
||||
<field name="semrelid" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="text" type="text_common" indexed="false" stored="false"/>
|
||||
<field name="trust" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
<field name="versioning" type="string" multiValued="true" indexed="true" stored="false"/>
|
||||
|
||||
<!-- Copy fields -->
|
||||
<copyField source="datasourceenglishname" dest="__all"/>
|
||||
<copyField source="datasourceoddescription" dest="__all"/>
|
||||
<copyField source="datasourceofficialname" dest="__all"/>
|
||||
<copyField source="datasourcesubject" dest="__all"/>
|
||||
<copyField source="externalreflabel" dest="__all"/>
|
||||
<copyField source="fundinglevel0_description" dest="__all"/>
|
||||
<copyField source="fundinglevel1_description" dest="__all"/>
|
||||
<copyField source="fundinglevel2_description" dest="__all"/>
|
||||
<copyField source="organizationalternativenames" dest="__all"/>
|
||||
<copyField source="organizationecenterprise" dest="__all"/>
|
||||
<copyField source="organizationecinternationalorganization" dest="__all"/>
|
||||
<copyField source="organizationecinternationalorganizationeurinterests" dest="__all"/>
|
||||
<copyField source="organizationeclegalbody" dest="__all"/>
|
||||
<copyField source="organizationeclegalperson" dest="__all"/>
|
||||
<copyField source="organizationecnonprofit" dest="__all"/>
|
||||
<copyField source="organizationecnutscode" dest="__all"/>
|
||||
<copyField source="organizationecresearchorganization" dest="__all"/>
|
||||
<copyField source="organizationecsmevalidated" dest="__all"/>
|
||||
<copyField source="organizationlegalname" dest="__all"/>
|
||||
<copyField source="organizationlegalshortname" dest="__all"/>
|
||||
<copyField source="projectacronym" dest="__all"/>
|
||||
<copyField source="projectcode" dest="__all"/>
|
||||
<copyField source="projectkeywords" dest="__all"/>
|
||||
<copyField source="projecttitle" dest="__all"/>
|
||||
<copyField source="relcontracttypename" dest="__all"/>
|
||||
<copyField source="relorganizationcountryname" dest="__all"/>
|
||||
<copyField source="relorganizationname" dest="__all"/>
|
||||
<copyField source="relorganizationshortname" dest="__all"/>
|
||||
<copyField source="relprojecttitle" dest="__all"/>
|
||||
<copyField source="resultpublisher" dest="__all"/>
|
||||
<copyField source="resultsource" dest="__all"/>
|
||||
|
||||
<!-- Commented copy fields below are queried independently by /exploreSearch query handler -->
|
||||
<!-- <copyField source="resultidentifier" dest="__all"/> -->
|
||||
<!-- <copyField source="resultauthor" dest="__all"/> -->
|
||||
<!-- <copyField source="resulttitle" dest="__all"/> -->
|
||||
<!-- <copyField source="resultdescription" dest="__all"/> -->
|
||||
|
||||
</schema>
|
@ -0,0 +1,20 @@
|
||||
{"params":{
|
||||
"query":{
|
||||
"defType":"edismax",
|
||||
"q.alt":"*:*",
|
||||
"rows":"10",
|
||||
"fl":"*,score",
|
||||
"":{"v":0}
|
||||
},
|
||||
"facets":{
|
||||
"facet":"on",
|
||||
"facet.mincount": "1",
|
||||
"":{"v":0}
|
||||
},
|
||||
"velocity":{
|
||||
"wt": "velocity",
|
||||
"v.template":"browse",
|
||||
"v.layout": "layout",
|
||||
"":{"v":0}
|
||||
}
|
||||
}}
|
@ -0,0 +1,21 @@
|
||||
# The ASF licenses this file to You under the Apache License, Version 2.0
|
||||
# (the "License"); you may not use this file except in compliance with
|
||||
# the License. You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
# Use a protected word file to protect against the stemmer reducing two
|
||||
# unrelated words to the same base word.
|
||||
|
||||
# Some non-words that normally won't be encountered,
|
||||
# just to test that they won't be stemmed.
|
||||
dontstems
|
||||
zwhacky
|
||||
|
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,14 @@
|
||||
# Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
# contributor license agreements. See the NOTICE file distributed with
|
||||
# this work for additional information regarding copyright ownership.
|
||||
# The ASF licenses this file to You under the Apache License, Version 2.0
|
||||
# (the "License"); you may not use this file except in compliance with
|
||||
# the License. You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
@ -0,0 +1,29 @@
|
||||
# The ASF licenses this file to You under the Apache License, Version 2.0
|
||||
# (the "License"); you may not use this file except in compliance with
|
||||
# the License. You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
#-----------------------------------------------------------------------
|
||||
#some test synonym mappings unlikely to appear in real input text
|
||||
aaafoo => aaabar
|
||||
bbbfoo => bbbfoo bbbbar
|
||||
cccfoo => cccbar cccbaz
|
||||
fooaaa,baraaa,bazaaa
|
||||
|
||||
# Some synonym groups specific to this example
|
||||
GB,gib,gigabyte,gigabytes
|
||||
MB,mib,megabyte,megabytes
|
||||
Television, Televisions, TV, TVs
|
||||
#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
|
||||
#after us won't split it into two words.
|
||||
|
||||
# Synonym mappings can be used for spelling correction too
|
||||
pixima => pixma
|
||||
|
Loading…
Reference in New Issue