lucene-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From sha...@apache.org
Subject [25/39] lucene-solr:feature/autoscaling: SOLR-9221: Remove Solr contribs: map-reduce, morphlines-core and morphlines-cell
Date Mon, 27 Mar 2017 06:05:19 GMT
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1a574df/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_no.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_no.txt b/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_no.txt
deleted file mode 100644
index e76f36e..0000000
--- a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_no.txt
+++ /dev/null
@@ -1,192 +0,0 @@
- | 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 <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 *
-

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1a574df/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_pt.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_pt.txt b/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_pt.txt
deleted file mode 100644
index 276c1b4..0000000
--- a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_pt.txt
+++ /dev/null
@@ -1,251 +0,0 @@
- | 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

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1a574df/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_ro.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_ro.txt b/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_ro.txt
deleted file mode 100644
index 4fdee90..0000000
--- a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_ro.txt
+++ /dev/null
@@ -1,233 +0,0 @@
-# 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

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1a574df/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_ru.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_ru.txt b/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_ru.txt
deleted file mode 100644
index 6430769..0000000
--- a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_ru.txt
+++ /dev/null
@@ -1,241 +0,0 @@
- | 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
-

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1a574df/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_sv.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_sv.txt b/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_sv.txt
deleted file mode 100644
index 22bddfd..0000000
--- a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_sv.txt
+++ /dev/null
@@ -1,131 +0,0 @@
- | 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
-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
-

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1a574df/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_th.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_th.txt b/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_th.txt
deleted file mode 100644
index 07f0fab..0000000
--- a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_th.txt
+++ /dev/null
@@ -1,119 +0,0 @@
-# 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

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1a574df/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_tr.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_tr.txt b/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_tr.txt
deleted file mode 100644
index 84d9408..0000000
--- a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/stopwords_tr.txt
+++ /dev/null
@@ -1,212 +0,0 @@
-# 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

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1a574df/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/userdict_ja.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/userdict_ja.txt b/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/userdict_ja.txt
deleted file mode 100644
index 6f0368e..0000000
--- a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/lang/userdict_ja.txt
+++ /dev/null
@@ -1,29 +0,0 @@
-#
-# 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

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1a574df/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/protwords.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/protwords.txt b/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/protwords.txt
deleted file mode 100644
index 1dfc0ab..0000000
--- a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/protwords.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-# 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
-

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1a574df/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/schema.xml b/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/schema.xml
deleted file mode 100644
index 11c1f76..0000000
--- a/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/schema.xml
+++ /dev/null
@@ -1,927 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- 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.
--->
-
-<!--  
- This is the Solr schema file. This file should be named "schema.xml" and
- should be in the conf directory under the solr home
- (i.e. ./solr/conf/schema.xml by default) 
- or located where the classloader for the Solr webapp can find it.
-
- This example schema is the recommended starting point for users.
- It should be kept correct and concise, usable out-of-the-box.
-
- For more information, on how to customize this file, please see
- http://wiki.apache.org/solr/SchemaXml
-
- PERFORMANCE NOTE: this schema includes many optional features and should not
- be used for benchmarking.  To improve performance one could
-  - set stored="false" for all fields possible (esp large fields) when you
-    only need to search on the field but don't need to return the original
-    value.
-  - set indexed="false" if you don't need to search on the field, but only
-    return the field as a result of searching on other indexed fields.
-  - remove all unneeded copyField statements
-  - for best index size and searching performance, set "index" to false
-    for all general text fields, use copyField to copy them to the
-    catchall "text" field, and use that for searching.
-  - For maximum indexing performance, use the ConcurrentUpdateSolrServer
-    java client.
-  - Remember to run the JVM in server mode, and use a higher logging level
-    that avoids logging every request
--->
-
-<schema name="example" version="1.6">
-  <!-- attribute "name" is the name of this schema and is only used for display purposes.
-       version="x.y" is Solr's version number for the schema syntax and 
-       semantics.  It should not normally be changed by applications.
-
-       1.0: multiValued attribute did not exist, all fields are multiValued 
-            by nature
-       1.1: multiValued attribute introduced, false by default 
-       1.2: omitTermFreqAndPositions attribute introduced, true by default 
-            except for text fields.
-       1.3: removed optional field compress feature
-       1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
-            behavior when a single string produces multiple tokens.  Defaults 
-            to off for version >= 1.4
-       1.5: omitNorms defaults to true for primitive field types 
-            (int, float, boolean, string...)
-       1.6: useDocValuesAsStored defaults to true.
-     -->
-
-
-  <!-- Valid attributes for fields:
-    name: mandatory - the name for the field
-    type: mandatory - the name of a field type from the 
-      fieldType section
-    indexed: true if this field should be indexed (searchable or sortable)
-    stored: true if this field should be retrievable
-    multiValued: true if this field may contain multiple values per document
-    omitNorms: (expert) set to true to omit the norms associated with
-      this field (this disables length normalization and index-time
-      boosting for the field, and saves some memory).  Only full-text
-      fields or fields that need an index-time boost need norms.
-      Norms are omitted for primitive (non-analyzed) types by default.
-    termVectors: [false] set to true to store the term vector for a
-      given field.
-      When using MoreLikeThis, fields used for similarity should be
-      stored for best performance.
-    termPositions: Store position information with the term vector.  
-      This will increase storage costs.
-    termOffsets: Store offset information with the term vector. This 
-      will increase storage costs.
-    required: The field is required.  It will throw an error if the
-      value does not exist
-    default: a value that should be used if no value is specified
-      when adding a document.
-  -->
-
-  <!-- field names should consist of alphanumeric or underscore characters only and
-     not start with a digit.  This is not currently strictly enforced,
-     but other field names will not have first class support from all components
-     and back compatibility is not guaranteed.  Names with both leading and
-     trailing underscores (e.g. _version_) are reserved.
-  -->
-
-  <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false"/>
-  <field name="user_friends_count" type="tint" indexed="true" stored="true"/>
-  <field name="user_location" type="lowercase" indexed="true" stored="true"/>
-  <field name="user_description" type="text_en" indexed="true" stored="false"/>
-  <field name="user_statuses_count" type="tint" indexed="true" stored="true"/>
-  <field name="user_followers_count" type="tint" indexed="true" stored="true"/>
-  <field name="user_name" type="text_en" indexed="true" stored="true"/>
-  <field name="user_screen_name" type="text_en" indexed="true" stored="true"/>
-  <field name="created_at" type="tdate" indexed="true" stored="true"/>
-  <field name="text" type="text_en" indexed="true" stored="true" multiValued="true"/>
-  <field name="retweet_count" type="tint" indexed="true" stored="true"/>
-  <field name="retweeted" type="boolean" indexed="true" stored="false"/>
-  <field name="in_reply_to_user_id" type="long" indexed="true" stored="true"/>
-  <field name="source" type="lowercase" indexed="true" stored="true"/>
-  <field name="in_reply_to_status_id" type="long" indexed="true" stored="true" multiValued="true"/>
-  <field name="media_url_https" type="string" indexed="false" stored="true"/>
-  <field name="expanded_url" type="string" indexed="false" stored="true"/>
-
-  <!-- file metadata -->
-  <field name="file_download_url" type="string" indexed="false" stored="true"/>
-  <field name="file_upload_url" type="string" indexed="false" stored="true"/>
-  <field name="file_scheme" type="string" indexed="true" stored="true"/>
-  <field name="file_host" type="string" indexed="true" stored="true"/>
-  <field name="file_port" type="int" indexed="true" stored="true"/>
-  <field name="file_path" type="string" indexed="true" stored="true"/>
-  <field name="file_name" type="string" indexed="true" stored="true"/>
-  <field name="file_length" type="tlong" indexed="true" stored="true"/>
-  <field name="file_last_modified" type="tlong" indexed="true" stored="true"/>
-  <field name="file_owner" type="string" indexed="true" stored="true"/>
-  <field name="file_group" type="string" indexed="true" stored="true"/>
-  <field name="file_permissions_user" type="string" indexed="true" stored="true"/>
-  <field name="file_permissions_group" type="string" indexed="true" stored="true"/>
-  <field name="file_permissions_other" type="string" indexed="true" stored="true"/>
-  <field name="file_permissions_stickybit" type="boolean" indexed="true" stored="true"/>
-
-  <!-- tika metadata -->
-  <field name="content_type" type="lowercase" indexed="true" stored="true"/>
-
-  <field name="_version_" type="long" indexed="true" stored="true"/>
-  <dynamicField name="ignored_*" type="ignored"/>
-
-
-  <!-- Field to use to determine and enforce document uniqueness. 
-       Unless this field is marked with required="false", it will be a required field
-    -->
-  <uniqueKey>id</uniqueKey>
-
-  <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
-   parsing a query string that isn't explicit about the field.  Machine (non-user)
-   generated queries are best made explicit, or they can use the "df" request parameter
-   which takes precedence over this.
-   Note: Un-commenting defaultSearchField will be insufficient if your request handler
-   in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
-  <defaultSearchField>text</defaultSearchField> -->
-
-  <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
-   when parsing a query string to determine if a clause of the query should be marked as
-   required or optional, assuming the clause isn't already marked by some operator.
-   The default is OR, which is generally assumed so it is not a good idea to change it
-   globally here.  The "q.op" request parameter takes precedence over this.
-  <solrQueryParser defaultOperator="OR"/> -->
-
-  <!-- copyField commands copy one field to another at the time a document
-        is added to the index.  It's used either to index the same field differently,
-        or to add multiple fields to the same field for easier/faster searching.  -->
-
-
-  <!-- field type definitions. The "name" attribute is
-     just a label to be used by field definitions.  The "class"
-     attribute and any other attributes determine the real
-     behavior of the fieldType.
-       Class names starting with "solr" refer to java classes in a
-     standard package such as org.apache.solr.analysis
-  -->
-
-  <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
-  <fieldType name="string" class="solr.StrField" sortMissingLast="true"/>
-
-  <!-- boolean type: "true" or "false" -->
-  <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
-
-  <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
-       currently supported on types that are sorted internally as strings
-       and on numeric types.
-     This includes "string","boolean", and, as of 3.5 (and 4.x),
-     int, float, long, date, double, including the "Trie" variants.
-     - If sortMissingLast="true", then a sort on this field will cause documents
-       without the field to come after documents with the field,
-       regardless of the requested sort order (asc or desc).
-     - If sortMissingFirst="true", then a sort on this field will cause documents
-       without the field to come before documents with the field,
-       regardless of the requested sort order.
-     - If sortMissingLast="false" and sortMissingFirst="false" (the default),
-       then default lucene sorting will be used which places docs without the
-       field first in an ascending sort and last in a descending sort.
-  -->
-
-  <!--
-    Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
-  -->
-  <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
-  <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
-  <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
-  <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
-
-  <!--
-   Numeric field types that index each value at various levels of precision
-   to accelerate range queries when the number of values between the range
-   endpoints is large. See the javadoc for LegacyNumericRangeQuery for internal
-   implementation details.
-
-   Smaller precisionStep values (specified in bits) will lead to more tokens
-   indexed per value, slightly larger index size, and faster range queries.
-   A precisionStep of 0 disables indexing at different precision levels.
-  -->
-  <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
-  <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
-  <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
-  <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
-
-  <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
-       is a more restricted form of the canonical representation of dateTime
-       http://www.w3.org/TR/xmlschema-2/#dateTime    
-       The trailing "Z" designates UTC time and is mandatory.
-       Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
-       All other components are mandatory.
-
-       Expressions can also be used to denote calculations that should be
-       performed relative to "NOW" to determine the value, ie...
-
-             NOW/HOUR
-                ... Round to the start of the current hour
-             NOW-1DAY
-                ... Exactly 1 day prior to now
-             NOW/DAY+6MONTHS+3DAYS
-                ... 6 months and 3 days in the future from the start of
-                    the current day
-                    
-       Consult the TrieDateField javadocs for more information.
-
-       Note: For faster range queries, consider the tdate type
-    -->
-  <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
-
-  <!-- A Trie based date field for faster date range queries and date faceting. -->
-  <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
-
-
-  <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
-  <fieldType name="binary" class="solr.BinaryField"/>
-
-  <!-- The "RandomSortField" is not used to store or search any
-       data.  You can declare fields of this type it in your schema
-       to generate pseudo-random orderings of your docs for sorting 
-       or function purposes.  The ordering is generated based on the field
-       name and the version of the index. As long as the index version
-       remains unchanged, and the same field name is reused,
-       the ordering of the docs will be consistent.  
-       If you want different psuedo-random orderings of documents,
-       for the same version of the index, use a dynamicField and
-       change the field name in the request.
-   -->
-  <fieldType name="random" class="solr.RandomSortField" indexed="true"/>
-
-  <!-- solr.TextField allows the specification of custom text analyzers
-       specified as a tokenizer and a list of token filters. Different
-       analyzers may be specified for indexing and querying.
-
-       The optional positionIncrementGap puts space between multiple fields of
-       this type on the same document, with the purpose of preventing false phrase
-       matching across fields.
-
-       For more info on customizing your analyzer chain, please see
-       http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
-   -->
-
-  <!-- One can also specify an existing Analyzer class that has a
-       default constructor via the class attribute on the analyzer element.
-       Example:
-  <fieldType name="text_greek" class="solr.TextField">
-    <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
-  </fieldType>
-  -->
-
-  <!-- A text field that only splits on whitespace for exact matching of words -->
-  <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
-    <analyzer>
-      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-    </analyzer>
-  </fieldType>
-
-  <!-- A general text field that has reasonable, generic
-       cross-language defaults: it tokenizes with StandardTokenizer,
- removes stop words from case-insensitive "stopwords.txt"
- (empty by default), and down cases.  At query time only, it
- also applies synonyms. -->
-  <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
-    <analyzer type="index">
-      <tokenizer class="solr.StandardTokenizerFactory"/>
-      <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-      <!-- in this example, we will only use synonyms at query time
-      <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-      -->
-      <filter class="solr.LowerCaseFilterFactory"/>
-    </analyzer>
-    <analyzer type="query">
-      <tokenizer class="solr.StandardTokenizerFactory"/>
-      <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-      <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-    </analyzer>
-  </fieldType>
-
-  <!-- A text field with defaults appropriate for English: it
-       tokenizes with StandardTokenizer, removes English stop words
-       (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">
-    <analyzer type="index">
-      <tokenizer class="solr.StandardTokenizerFactory"/>
-      <!-- in this example, we will only use synonyms at query time
-      <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-      -->
-      <!-- Case insensitive stop word removal. -->
-      <filter class="solr.StopFilterFactory"
-              ignoreCase="true"
-              words="lang/stopwords_en.txt"
-
-      />
-      <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.EnglishPossessiveFilterFactory"/>
-      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
-      <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
-            <filter class="solr.EnglishMinimalStemFilterFactory"/>
-      -->
-      <filter class="solr.PorterStemFilterFactory"/>
-    </analyzer>
-    <analyzer type="query">
-      <tokenizer class="solr.StandardTokenizerFactory"/>
-      <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
-      <filter class="solr.StopFilterFactory"
-              ignoreCase="true"
-              words="lang/stopwords_en.txt"
-
-      />
-      <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.EnglishPossessiveFilterFactory"/>
-      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
-      <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
-            <filter class="solr.EnglishMinimalStemFilterFactory"/>
-      -->
-      <filter class="solr.PorterStemFilterFactory"/>
-    </analyzer>
-  </fieldType>
-
-  <!-- A text field with defaults appropriate for English, plus
- aggressive word-splitting and autophrase features enabled.
- This field is just like text_en, except it adds
- WordDelimiterFilter to enable splitting and matching of
- words on case-change, alpha numeric boundaries, and
- non-alphanumeric chars.  This means certain compound word
- cases will work, for example query "wi fi" will match
- document "WiFi" or "wi-fi".
-      -->
-  <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100"
-             autoGeneratePhraseQueries="true">
-    <analyzer type="index">
-      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-      <!-- in this example, we will only use synonyms at query time
-      <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-      -->
-      <!-- Case insensitive stop word removal. -->
-      <filter class="solr.StopFilterFactory"
-              ignoreCase="true"
-              words="lang/stopwords_en.txt"
-
-      />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
-              catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
-      <filter class="solr.PorterStemFilterFactory"/>
-    </analyzer>
-    <analyzer type="query">
-      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-      <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
-      <filter class="solr.StopFilterFactory"
-              ignoreCase="true"
-              words="lang/stopwords_en.txt"
-
-      />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
-              catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
-      <filter class="solr.PorterStemFilterFactory"/>
-    </analyzer>
-  </fieldType>
-
-  <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
-       but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
-  <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100"
-             autoGeneratePhraseQueries="true">
-    <analyzer>
-      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-      <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
-      <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"/>
-      <filter class="solr.EnglishMinimalStemFilterFactory"/>
-      <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
-           possible with WordDelimiterFilter in conjuncton with stemming. -->
-      <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
-    </analyzer>
-  </fieldType>
-
-  <!-- Just like text_general except it reverses the characters of
- each token, to enable more efficient leading wildcard queries. -->
-  <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
-    <analyzer type="index">
-      <tokenizer class="solr.StandardTokenizerFactory"/>
-      <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
-              maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
-    </analyzer>
-    <analyzer type="query">
-      <tokenizer class="solr.StandardTokenizerFactory"/>
-      <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
-      <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-    </analyzer>
-  </fieldType>
-
-  <!-- charFilter + WhitespaceTokenizer  -->
-  <!--
-  <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
-    <analyzer>
-      <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-    </analyzer>
-  </fieldType>
-  -->
-
-  <!-- This is an example of using the KeywordTokenizer along
-       With various TokenFilterFactories to produce a sortable field
-       that does not include some properties of the source text
-    -->
-  <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
-    <analyzer>
-      <!-- KeywordTokenizer does no actual tokenizing, so the entire
-           input string is preserved as a single token
-        -->
-      <tokenizer class="solr.KeywordTokenizerFactory"/>
-      <!-- The LowerCase TokenFilter does what you expect, which can be
-           when you want your sorting to be case insensitive
-        -->
-      <filter class="solr.LowerCaseFilterFactory"/>
-      <!-- The TrimFilter removes any leading or trailing whitespace -->
-      <filter class="solr.TrimFilterFactory"/>
-      <!-- The PatternReplaceFilter gives you the flexibility to use
-           Java Regular expression to replace any sequence of characters
-           matching a pattern with an arbitrary replacement string, 
-           which may include back references to portions of the original
-           string matched by the pattern.
-           
-           See the Java Regular Expression documentation for more
-           information on pattern and replacement string syntax.
-           
-           http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
-        -->
-      <filter class="solr.PatternReplaceFilterFactory"
-              pattern="([^a-z])" replacement="" replace="all"
-      />
-    </analyzer>
-  </fieldType>
-
-  <!--    
-  <fieldType name="phonetic" stored="false" indexed="true" class="solr.TextField" >
-    <analyzer>
-      <tokenizer class="solr.StandardTokenizerFactory"/>
-      <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
-    </analyzer>
-  </fieldType>
-  -->
-
-  <fieldType name="payloads" stored="false" indexed="true" class="solr.TextField">
-    <analyzer>
-      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-      <!--
-      The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
-      a token of "foo|1.4"  would be indexed as "foo" with a payload of 1.4f
-      Attributes of the DelimitedPayloadTokenFilterFactory : 
-       "delimiter" - a one character delimiter. Default is | (pipe)
- "encoder" - how to encode the following value into a playload
-    float -> org.apache.lucene.analysis.payloads.FloatEncoder,
-    integer -> o.a.l.a.p.IntegerEncoder
-    identity -> o.a.l.a.p.IdentityEncoder
-          Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
-       -->
-      <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
-    </analyzer>
-  </fieldType>
-
-  <!-- lowercases the entire field value, keeping it as a single token.  -->
-  <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
-    <analyzer>
-      <tokenizer class="solr.KeywordTokenizerFactory"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-    </analyzer>
-  </fieldType>
-
-  <!-- 
-    Example of using PathHierarchyTokenizerFactory at index time, so
-    queries for paths match documents at that path, or in descendent paths
-  -->
-  <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>
-  <!-- 
-    Example of using PathHierarchyTokenizerFactory at query time, so
-    queries for paths match documents at that path, or in ancestor paths
-  -->
-  <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>
-
-  <!-- since fields of this type are by default not stored or indexed,
-       any data added to them will be ignored outright.  -->
-  <fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField"/>
-
-  <!-- This point type indexes the coordinates as separate fields (subFields)
-    If subFieldType is defined, it references a type, and a dynamic field
-    definition is created matching *___<typename>.  Alternately, if 
-    subFieldSuffix is defined, that is used to create the subFields.
-    Example: if subFieldType="double", then the coordinates would be
-      indexed in fields myloc_0___double,myloc_1___double.
-    Example: if subFieldSuffix="_d" then the coordinates would be indexed
-      in fields myloc_0_d,myloc_1_d
-    The subFields are an implementation detail of the fieldType, and end
-    users normally should not need to know about them.
-   -->
-  <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
-
-  <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
-  <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
-
-  <!--
-   A Geohash is a compact representation of a latitude longitude pair in a single field.
-   See http://wiki.apache.org/solr/SpatialSearch
-  -->
-  <fieldType name="geohash" class="solr.GeoHashField"/>
-
-  <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
-       Parameters:
-         defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
-         precisionStep:   Specifies the precisionStep for the TrieLong field used for the amount
-         providerClass:   Lets you plug in other exchange provider backend:
-                          solr.FileExchangeRateProvider is the default and takes one parameter:
-                            currencyConfig: name of an xml file holding exhange rates
-                          solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
-                            ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
-                            refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
-  -->
-  <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD"
-             currencyConfig="currency.xml"/>
-
-
-  <!-- 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"/>
-      <!-- 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"/>
-      <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"/>
-      <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
-    </analyzer>
-  </fieldType>
-
-  <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
-  <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"/>
-      <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"/>
-      <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"/>
-      <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"/>
-      <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"/>
-      <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"/>
-      <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"/>
-    </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"/>
-      <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"/>
-      <filter class="solr.FrenchLightStemFilterFactory"/>
-      <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
-      <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
-    </analyzer>
-  </fieldType>
-
-  <!-- Irish -->
-  <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
-    <analyzer>
-      <tokenizer class="solr.StandardTokenizerFactory"/>
-      <!-- removes d', etc -->
-      <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
-      <!-- removes n-, etc. position increments is intentionally false! -->
-      <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
-      <filter class="solr.IrishLowerCaseFilterFactory"/>
-      <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
-      <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
-    </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"/>
-      <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"/>
-      <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"/>
-      <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"/>
-      <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"/>
-      <!-- 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"/>
-      <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"/>
-      <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"/>
-      <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"/>
-      <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
-      <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
-      <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
-    </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"/>
-      <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"/>
-      <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"/>
-      <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"/>
-      <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.ThaiTokenizerFactory"/>
-      <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt"/>
-    </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"/>
-      <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
-    </analyzer>
-  </fieldType>
-
-
-  <!-- Similarity is the scoring routine for each document vs. a query.
-       A custom Similarity or SimilarityFactory may be specified here, but 
-       the default is fine for most applications.  
-       For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
-    -->
-  <!--
-     <similarity class="com.example.solr.CustomSimilarityFactory">
-       <str name="paramkey">param value</str>
-     </similarity>
-    -->
-
-</schema>


Mime
View raw message