svn commit: r1241878 [3/3] - in /lucene/dev/trunk: lucene/contrib/ modules/analysis/common/src/java/org/apache/lucene/analysis/ca/ modules/analysis/common/src/java/org/apache/lucene/analysis/de/ modules/analysis/common/src/java/org/apache/lucene/analys...

[rm...@apache.org]

Added: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ja.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ja.txt?rev=1241878&view=auto
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ja.txt (added)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ja.txt Wed Feb  8 12:07:52 2012
@@ -0,0 +1,122 @@
+#
+# This file defines a stopword set for Japanese.
+#
+# The set is made up hand-picked frequent terms from taken from segmented Japanese
+# Wikipedia.  Punctuation characters and frequent kanji have mostly been left out.
+#
+# There is an overlap between these stopwords and the terms removed when used in
+# combination with the KuromojiPartOfSpeechStopFilter.  When editing this file, note
+# that comments are not allowed on the same line as stopwords.
+#
+# See LUCENE-3745 for frequency lists, etc. that can be useful for making your own set.
+#
+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

Added: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_lv.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_lv.txt?rev=1241878&view=auto
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_lv.txt (added)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_lv.txt Wed Feb  8 12:07:52 2012
@@ -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
+Å¡aipus
+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

Added: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_nl.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_nl.txt?rev=1241878&view=auto
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_nl.txt (added)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_nl.txt Wed Feb  8 12:07:52 2012
@@ -0,0 +1,117 @@
+ | 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.
+
+ | 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

Added: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_no.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_no.txt?rev=1241878&view=auto
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_no.txt (added)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_no.txt Wed Feb  8 12:07:52 2012
@@ -0,0 +1,192 @@
+ | 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.
+
+ | 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 <Ja...@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
+Ã¥              | 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 *
+

Added: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_pt.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_pt.txt?rev=1241878&view=auto
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_pt.txt (added)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_pt.txt Wed Feb  8 12:07:52 2012
@@ -0,0 +1,251 @@
+ | 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.
+
+ | 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

Added: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ro.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ro.txt?rev=1241878&view=auto
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ro.txt (added)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ro.txt Wed Feb  8 12:07:52 2012
@@ -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
+Å£i
+Å£ie
+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

Added: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ru.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ru.txt?rev=1241878&view=auto
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ru.txt (added)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_ru.txt Wed Feb  8 12:07:52 2012
@@ -0,0 +1,241 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/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.
+
+ | a russian 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.
+
+ | letter `ё' is translated to `е'.
+
+и              | and
+в              | in/into
+во             | alternative form
+не             | not
+что            | what/that
+он             | he
+на             | on/onto
+я              | i
+с              | from
+со             | alternative form
+как            | how
+а              | milder form of `no' (but)
+то             | conjunction and form of `that'
+все            | all
+она            | she
+так            | so, thus
+его            | him
+но             | but
+да             | yes/and
+ты             | thou
+к              | towards, by
+у              | around, chez
+же             | intensifier particle
+вы             | you
+за             | beyond, behind
+бы             | conditional/subj. particle
+по             | up to, along
+только         | only
+ее             | her
+мне            | to me
+было           | it was
+вот            | here is/are, particle
+от             | away from
+меня           | me
+еще            | still, yet, more
+нет            | no, there isnt/arent
+о              | about
+из             | out of
+ему            | to him
+теперь         | now
+когда          | when
+даже           | even
+ну             | so, well
+вдруг          | suddenly
+ли             | interrogative particle
+если           | if
+уже            | already, but homonym of `narrower'
+или            | or
+ни             | neither
+быть           | to be
+был            | he was
+него           | prepositional form of его
+до             | up to
+вас            | you accusative
+нибудь         | indef. suffix preceded by hyphen
+опять          | again
+уж             | already, but homonym of `adder'
+вам            | to you
+сказал         | he said
+ведь           | particle `after all'
+там            | there
+потом          | then
+себя           | oneself
+ничего         | nothing
+ей             | to her
+может          | usually with `быть' as `maybe'
+они            | they
+тут            | here
+где            | where
+есть           | there is/are
+надо           | got to, must
+ней            | prepositional form of  ей
+для            | for
+мы             | we
+тебя           | thee
+их             | them, their
+чем            | than
+была           | she was
+сам            | self
+чтоб           | in order to
+без            | without
+будто          | as if
+человек        | man, person, one
+чего           | genitive form of `what'
+раз            | once
+тоже           | also
+себе           | to oneself
+под            | beneath
+жизнь          | life
+будет          | will be
+ж              | short form of intensifer particle `же'
+тогда          | then
+кто            | who
+этот           | this
+говорил        | was saying
+того           | genitive form of `that'
+потому         | for that reason
+этого          | genitive form of `this'
+какой          | which
+совсем         | altogether
+ним            | prepositional form of `его', `они'
+здесь          | here
+этом           | prepositional form of `этот'
+один           | one
+почти          | almost
+мой            | my
+тем            | instrumental/dative plural of `тот', `то'
+чтобы          | full form of `in order that'
+нее            | her (acc.)
+кажется        | it seems
+сейчас         | now
+были           | they were
+куда           | where to
+зачем          | why
+сказать        | to say
+всех           | all (acc., gen. preposn. plural)
+никогда        | never
+сегодня        | today
+можно          | possible, one can
+при            | by
+наконец        | finally
+два            | two
+об             | alternative form of `о', about
+другой         | another
+хоть           | even
+после          | after
+над            | above
+больше         | more
+тот            | that one (masc.)
+через          | across, in
+эти            | these
+нас            | us
+про            | about
+всего          | in all, only, of all
+них            | prepositional form of `они' (they)
+какая          | which, feminine
+много          | lots
+разве          | interrogative particle
+сказала        | she said
+три            | three
+эту            | this, acc. fem. sing.
+моя            | my, feminine
+впрочем        | moreover, besides
+хорошо         | good
+свою           | ones own, acc. fem. sing.
+этой           | oblique form of `эта', fem. `this'
+перед          | in front of
+иногда         | sometimes
+лучше          | better
+чуть           | a little
+том            | preposn. form of `that one'
+нельзя         | one must not
+такой          | such a one
+им             | to them
+более          | more
+всегда         | always
+конечно        | of course
+всю            | acc. fem. sing of `all'
+между          | between
+
+
+  | b: some paradigms
+  |
+  | personal pronouns
+  |
+  | я  меня  мне  мной  [мною]
+  | ты  тебя  тебе  тобой  [тобою]
+  | он  его  ему  им  [него, нему, ним]
+  | она  ее  эи  ею  [нее, нэи, нею]
+  | оно  его  ему  им  [него, нему, ним]
+  |
+  | мы  нас  нам  нами
+  | вы  вас  вам  вами
+  | они  их  им  ими  [них, ним, ними]
+  |
+  |   себя  себе  собой   [собою]
+  |
+  | demonstrative pronouns: этот (this), тот (that)
+  |
+  | этот  эта  это  эти
+  | этого  эты  это  эти
+  | этого  этой  этого  этих
+  | этому  этой  этому  этим
+  | этим  этой  этим  [этою]  этими
+  | этом  этой  этом  этих
+  |
+  | тот  та  то  те
+  | того  ту  то  те
+  | того  той  того  тех
+  | тому  той  тому  тем
+  | тем  той  тем  [тою]  теми
+  | том  той  том  тех
+  |
+  | determinative pronouns
+  |
+  | (a) весь (all)
+  |
+  | весь  вся  все  все
+  | всего  всю  все  все
+  | всего  всей  всего  всех
+  | всему  всей  всему  всем
+  | всем  всей  всем  [всею]  всеми
+  | всем  всей  всем  всех
+  |
+  | (b) сам (himself etc)
+  |
+  | сам  сама  само  сами
+  | самого саму  само  самих
+  | самого самой самого  самих
+  | самому самой самому  самим
+  | самим  самой  самим  [самою]  самими
+  | самом самой самом  самих
+  |
+  | stems of verbs `to be', `to have', `to do' and modal
+  |
+  | быть  бы  буд  быв  есть  суть
+  | име
+  | дел
+  | мог   мож  мочь
+  | уме
+  | хоч  хот
+  | долж
+  | можн
+  | нужн
+  | нельзя
+

Added: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_sv.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_sv.txt?rev=1241878&view=auto
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_sv.txt (added)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_sv.txt Wed Feb  8 12:07:52 2012
@@ -0,0 +1,131 @@
+ | 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.
+
+ | 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
+Ã¥t             | 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
+

Added: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_th.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_th.txt?rev=1241878&view=auto
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_th.txt (added)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_th.txt Wed Feb  8 12:07:52 2012
@@ -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

Added: lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_tr.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_tr.txt?rev=1241878&view=auto
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_tr.txt (added)
+++ lucene/dev/trunk/solr/example/solr/conf/lang/stopwords_tr.txt Wed Feb  8 12:07:52 2012
@@ -0,0 +1,212 @@
+# Turkish stopwords from LUCENE-559
+# merged with the list from "Information Retrieval on Turkish Texts"
+#   (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
+acaba
+altmış
+altı
+ama
+ancak
+arada
+aslında
+ayrıca
+bana
+bazı
+belki
+ben
+benden
+beni
+benim
+beri
+beş
+bile
+bin
+bir
+birçok
+biri
+birkaç
+birkez
+birşey
+birşeyi
+biz
+bize
+bizden
+bizi
+bizim
+böyle
+böylece
+bu
+buna
+bunda
+bundan
+bunlar
+bunları
+bunların
+bunu
+bunun
+burada
+çok
+çünkü
+da
+daha
+dahi
+de
+defa
+değil
+diğer
+diye
+doksan
+dokuz
+dolayı
+dolayısıyla
+dört
+edecek
+eden
+ederek
+edilecek
+ediliyor
+edilmesi
+ediyor
+eğer
+elli
+en
+etmesi
+etti
+ettiği
+ettiğini
+gibi
+göre
+halen
+hangi
+hatta
+hem
+henüz
+hep
+hepsi
+her
+herhangi
+herkesin
+hiç
+hiçbir
+için
+iki
+ile
+ilgili
+ise
+işte
+itibaren
+itibariyle
+kadar
+karşın
+katrilyon
+kendi
+kendilerine
+kendini
+kendisi
+kendisine
+kendisini
+kez
+ki
+kim
+kimden
+kime
+kimi
+kimse
+kırk
+milyar
+milyon
+mu
+mü
+mı
+nasıl
+ne
+neden
+nedenle
+nerde
+nerede
+nereye
+niye
+niçin
+o
+olan
+olarak
+oldu
+olduğu
+olduğunu
+olduklarını
+olmadı
+olmadığı
+olmak
+olması
+olmayan
+olmaz
+olsa
+olsun
+olup
+olur
+olursa
+oluyor
+on
+ona
+ondan
+onlar
+onlardan
+onları
+onların
+onu
+onun
+otuz
+oysa
+öyle
+pek
+rağmen
+sadece
+sanki
+sekiz
+seksen
+sen
+senden
+seni
+senin
+siz
+sizden
+sizi
+sizin
+şey
+şeyden
+şeyi
+şeyler
+şöyle
+şu
+şuna
+şunda
+şundan
+şunları
+şunu
+tarafından
+trilyon
+tüm
+üç
+üzere
+var
+vardı
+ve
+veya
+ya
+yani
+yapacak
+yapılan
+yapılması
+yapıyor
+yapmak
+yaptı
+yaptığı
+yaptığını
+yaptıkları
+yedi
+yerine
+yetmiş
+yine
+yirmi
+yoksa
+yüz
+zaten

Modified: lucene/dev/trunk/solr/example/solr/conf/schema.xml
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/solr/conf/schema.xml?rev=1241878&r1=1241877&r2=1241878&view=diff
==============================================================================
--- lucene/dev/trunk/solr/example/solr/conf/schema.xml (original)
+++ lucene/dev/trunk/solr/example/solr/conf/schema.xml Wed Feb  8 12:07:52 2012
@@ -219,7 +219,7 @@
 
     <!-- A text field with defaults appropriate for English: it
          tokenizes with StandardTokenizer, removes English stop words
-         (stopwords_en.txt), down cases, protects words from protwords.txt, and
+         (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
          finally applies Porter's stemming.  The query time analyzer
          also applies synonyms from synonyms.txt. -->
     <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
@@ -234,7 +234,7 @@
         -->
         <filter class="solr.StopFilterFactory"
                 ignoreCase="true"
-                words="stopwords_en.txt"
+                words="lang/stopwords_en.txt"
                 enablePositionIncrements="true"
                 />
         <filter class="solr.LowerCaseFilterFactory"/>
@@ -250,7 +250,7 @@
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
         <filter class="solr.StopFilterFactory"
                 ignoreCase="true"
-                words="stopwords_en.txt"
+                words="lang/stopwords_en.txt"
                 enablePositionIncrements="true"
                 />
         <filter class="solr.LowerCaseFilterFactory"/>
@@ -287,7 +287,7 @@
         -->
         <filter class="solr.StopFilterFactory"
                 ignoreCase="true"
-                words="stopwords_en.txt"
+                words="lang/stopwords_en.txt"
                 enablePositionIncrements="true"
                 />
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
@@ -300,7 +300,7 @@
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
         <filter class="solr.StopFilterFactory"
                 ignoreCase="true"
-                words="stopwords_en.txt"
+                words="lang/stopwords_en.txt"
                 enablePositionIncrements="true"
                 />
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
@@ -316,7 +316,7 @@
       <analyzer>
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
-        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -454,6 +454,323 @@
    -->
     <fieldtype name="geohash" class="solr.GeoHashField"/>
 
+   <!-- some examples for different languages (generally ordered by ISO code) -->
+
+    <!-- Arabic -->
+    <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- for any non-arabic -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" enablePositionIncrements="true"/>
+        <!-- normalizes ﻯ to ﻱ, etc -->
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.ArabicStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Bulgarian -->
+    <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/> 
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" enablePositionIncrements="true"/>
+        <filter class="solr.BulgarianStemFilterFactory"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- Catalan -->
+    <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" enablePositionIncrements="true"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- CJK bigram (see text_ja for an alternative Japanese configuration) -->
+    <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- for any non-CJK -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.CJKBigramFilterFactory"/>     
+      </analyzer>
+    </fieldType>
+
+    <!-- Czech -->
+    <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" enablePositionIncrements="true"/>
+        <filter class="solr.CzechStemFilterFactory"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- Danish -->
+    <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" enablePositionIncrements="true"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- German -->
+    <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/>
+        <filter class="solr.GermanNormalizationFilterFactory"/>
+        <filter class="solr.GermanLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Greek -->
+    <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- greek specific lowercase for sigma -->
+        <filter class="solr.GreekLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" enablePositionIncrements="true"/>
+        <filter class="solr.GreekStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Spanish -->
+    <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" enablePositionIncrements="true"/>
+        <filter class="solr.SpanishLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Basque -->
+    <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" enablePositionIncrements="true"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Persian -->
+    <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <!-- for ZWNJ -->
+        <charFilter class="solr.PersianCharFilterFactory"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.PersianNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" enablePositionIncrements="true"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Finnish -->
+    <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" enablePositionIncrements="true"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+        <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- French -->
+    <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/>
+        <filter class="solr.FrenchLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Galician -->
+    <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" enablePositionIncrements="true"/>
+        <filter class="solr.GalicianStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Hindi -->
+    <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <!-- normalizes unicode representation -->
+        <filter class="solr.IndicNormalizationFilterFactory"/>
+        <!-- normalizes variation in spelling -->
+        <filter class="solr.HindiNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" enablePositionIncrements="true"/>
+        <filter class="solr.HindiStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Hungarian -->
+    <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" enablePositionIncrements="true"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+        <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->   
+      </analyzer>
+    </fieldType>
+    
+    <!-- Armenian -->
+    <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" enablePositionIncrements="true"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Indonesian -->
+    <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" enablePositionIncrements="true"/>
+        <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+        <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Italian -->
+    <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" enablePositionIncrements="true"/>
+        <filter class="solr.ItalianLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Latvian -->
+    <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" enablePositionIncrements="true"/>
+        <filter class="solr.LatvianStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Dutch -->
+    <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" enablePositionIncrements="true"/>
+        <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Norwegian -->
+    <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" enablePositionIncrements="true"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Portuguese -->
+    <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" enablePositionIncrements="true"/>
+        <filter class="solr.PortugueseLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+        <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Romanian -->
+    <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" enablePositionIncrements="true"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Russian -->
+    <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" enablePositionIncrements="true"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+        <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Swedish -->
+    <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" enablePositionIncrements="true"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+        <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Thai -->
+    <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ThaiWordFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Turkish -->
+    <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.TurkishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+      </analyzer>
+    </fieldType>
  </types>