You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by sh...@apache.org on 2017/03/27 06:05:19 UTC
[25/39] lucene-solr:feature/autoscaling: SOLR-9221: Remove Solr
contribs: map-reduce, morphlines-core and morphlines-cell
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 bokm�l 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
-p� | on
-de | they / you(formal)
-med | with
-han | he
-av | of
-ikke | not
-ikkje | not *
-der | there
-s� | 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
-n� | 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)
-sj�l | self (reflective)
-her | here
-alle | all
-vil | will
-bli | become
-ble | became
-blei | became *
-blitt | have become
-kunne | could
-inn | in
-n�r | when
-v�re | 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
-� | 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)
-s�nn | such a
-inni | inside/within
-mellom | between
-v�r | our
-hver | each
-hvem | who
-vors | us/ours
-hvis | whose
-b�de | both
-bare | only/just
-enn | than
-fordi | as/because
-f�r | before
-mange | many
-ogs� | also
-slik | just
-v�rt | been
-v�re | to be
-b�e | both *
-begge | both
-siden | since
-dykk | your *
-dykkar | yours *
-dei | they *
-deira | them *
-deires | theirs *
-deim | them *
-di | your (fem.) *
-d� | as/when *
-eg | I *
-ein | a/an *
-eit | a/an *
-eitt | a/an *
-elles | or *
-honom | he *
-hj� | 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
- | � from SER
-com | with
-n�o | 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
-� | a + a
-seu | his
-sua | her
-ou | or
- | ser from SER
-quando | when
-muito | much
- | h� from HAV
-nos | em + os; us
-j� | already, now
- | est� from EST
-eu | I
-tamb�m | also
-s� | only, just
-pelo | per + o
-pela | per + a
-at� | 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
- | est�o from EST
-voc� | you
- | tinha from TER
- | foram from SER
-essa | that
-num | em + um
-nem | nor
-suas | her
-meu | my
-�s | a + as
-minha | my
- | t�m from TER
-numa | em + uma
-pelos | per + os
-elas | they
- | havia from HAV
- | seja from SER
-qual | which
- | ser� from SER
-n�s | 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
-voc�s | 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
-est�
-estamos
-est�o
-estive
-esteve
-estivemos
-estiveram
-estava
-est�vamos
-estavam
-estivera
-estiv�ramos
-esteja
-estejamos
-estejam
-estivesse
-estiv�ssemos
-estivessem
-estiver
-estivermos
-estiverem
-
- | forms of haver, to have (not including the infinitive):
-hei
-h�
-havemos
-h�o
-houve
-houvemos
-houveram
-houvera
-houv�ramos
-haja
-hajamos
-hajam
-houvesse
-houv�ssemos
-houvessem
-houver
-houvermos
-houverem
-houverei
-houver�
-houveremos
-houver�o
-houveria
-houver�amos
-houveriam
-
- | forms of ser, to be (not including the infinitive):
-sou
-somos
-s�o
-era
-�ramos
-eram
-fui
-foi
-fomos
-foram
-fora
-f�ramos
-seja
-sejamos
-sejam
-fosse
-f�ssemos
-fossem
-for
-formos
-forem
-serei
-ser�
-seremos
-ser�o
-seria
-ser�amos
-seriam
-
- | forms of ter, to have (not including the infinitive):
-tenho
-tem
-temos
-t�m
-tinha
-t�nhamos
-tinham
-tive
-teve
-tivemos
-tiveram
-tivera
-tiv�ramos
-tenha
-tenhamos
-tenham
-tivesse
-tiv�ssemos
-tivessem
-tiver
-tivermos
-tiverem
-terei
-ter�
-teremos
-ter�o
-teria
-ter�amos
-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
-aceast\u0103
-aceea
-acei
-aceia
-acel
-acela
-acele
-acelea
-acest
-acesta
-aceste
-acestea
-ace\u015fti
-ace\u015ftia
-acolo
-acum
-ai
-aia
-aib\u0103
-aici
-al
-\u0103la
-ale
-alea
-\u0103lea
-altceva
-altcineva
-am
-ar
-are
-a\u015f
-a\u015fadar
-asemenea
-asta
-\u0103sta
-ast\u0103zi
-astea
-\u0103stea
-\u0103\u015ftia
-asupra
-a\u0163i
-au
-avea
-avem
-ave\u0163i
-azi
-bine
-bucur
-bun\u0103
-ca
-c\u0103
-c\u0103ci
-c�nd
-care
-c\u0103rei
-c\u0103ror
-c\u0103rui
-c�t
-c�te
-c�\u0163i
-c\u0103tre
-c�tva
-ce
-cel
-ceva
-chiar
-c�nd
-cine
-cineva
-c�t
-c�te
-c�\u0163i
-c�tva
-contra
-cu
-cum
-cumva
-cur�nd
-cur�nd
-da
-d\u0103
-dac\u0103
-dar
-datorit\u0103
-de
-deci
-deja
-deoarece
-departe
-de\u015fi
-din
-dinaintea
-dintr
-dintre
-drept
-dup\u0103
-ea
-ei
-el
-ele
-eram
-este
-e\u015fti
-eu
-face
-f\u0103r\u0103
-fi
-fie
-fiecare
-fii
-fim
-fi\u0163i
-iar
-ieri
-�i
-�l
-�mi
-�mpotriva
-�n
-�nainte
-�naintea
-�nc�t
-�nc�t
-�ncotro
-�ntre
-�ntruc�t
-�ntruc�t
-�\u0163i
-la
-l�ng\u0103
-le
-li
-l�ng\u0103
-lor
-lui
-m\u0103
-m�ine
-mea
-mei
-mele
-mereu
-meu
-mi
-mine
-mult
-mult\u0103
-mul\u0163i
-ne
-nic\u0103ieri
-nici
-nimeni
-ni\u015fte
-noastr\u0103
-noastre
-noi
-no\u015ftri
-nostru
-nu
-ori
-oric�nd
-oricare
-oric�t
-orice
-oric�nd
-oricine
-oric�t
-oricum
-oriunde
-p�n\u0103
-pe
-pentru
-peste
-p�n\u0103
-poate
-pot
-prea
-prima
-primul
-prin
-printr
-sa
-s\u0103
-s\u0103i
-sale
-sau
-s\u0103u
-se
-\u015fi
-s�nt
-s�ntem
-s�nte\u0163i
-spre
-sub
-sunt
-suntem
-sunte\u0163i
-ta
-t\u0103i
-tale
-t\u0103u
-te
-\u0163i
-\u0163ie
-tine
-toat\u0103
-toate
-tot
-to\u0163i
-totu\u015fi
-tu
-un
-una
-unde
-undeva
-unei
-unele
-uneori
-unor
-v\u0103
-vi
-voastr\u0103
-voastre
-voi
-vo\u015ftri
-vostru
-vou\u0103
-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 `\u0451' is translated to `\u0435'.
-
-\u0438 | and
-\u0432 | in/into
-\u0432\u043e | alternative form
-\u043d\u0435 | not
-\u0447\u0442\u043e | what/that
-\u043e\u043d | he
-\u043d\u0430 | on/onto
-\u044f | i
-\u0441 | from
-\u0441\u043e | alternative form
-\u043a\u0430\u043a | how
-\u0430 | milder form of `no' (but)
-\u0442\u043e | conjunction and form of `that'
-\u0432\u0441\u0435 | all
-\u043e\u043d\u0430 | she
-\u0442\u0430\u043a | so, thus
-\u0435\u0433\u043e | him
-\u043d\u043e | but
-\u0434\u0430 | yes/and
-\u0442\u044b | thou
-\u043a | towards, by
-\u0443 | around, chez
-\u0436\u0435 | intensifier particle
-\u0432\u044b | you
-\u0437\u0430 | beyond, behind
-\u0431\u044b | conditional/subj. particle
-\u043f\u043e | up to, along
-\u0442\u043e\u043b\u044c\u043a\u043e | only
-\u0435\u0435 | her
-\u043c\u043d\u0435 | to me
-\u0431\u044b\u043b\u043e | it was
-\u0432\u043e\u0442 | here is/are, particle
-\u043e\u0442 | away from
-\u043c\u0435\u043d\u044f | me
-\u0435\u0449\u0435 | still, yet, more
-\u043d\u0435\u0442 | no, there isnt/arent
-\u043e | about
-\u0438\u0437 | out of
-\u0435\u043c\u0443 | to him
-\u0442\u0435\u043f\u0435\u0440\u044c | now
-\u043a\u043e\u0433\u0434\u0430 | when
-\u0434\u0430\u0436\u0435 | even
-\u043d\u0443 | so, well
-\u0432\u0434\u0440\u0443\u0433 | suddenly
-\u043b\u0438 | interrogative particle
-\u0435\u0441\u043b\u0438 | if
-\u0443\u0436\u0435 | already, but homonym of `narrower'
-\u0438\u043b\u0438 | or
-\u043d\u0438 | neither
-\u0431\u044b\u0442\u044c | to be
-\u0431\u044b\u043b | he was
-\u043d\u0435\u0433\u043e | prepositional form of \u0435\u0433\u043e
-\u0434\u043e | up to
-\u0432\u0430\u0441 | you accusative
-\u043d\u0438\u0431\u0443\u0434\u044c | indef. suffix preceded by hyphen
-\u043e\u043f\u044f\u0442\u044c | again
-\u0443\u0436 | already, but homonym of `adder'
-\u0432\u0430\u043c | to you
-\u0441\u043a\u0430\u0437\u0430\u043b | he said
-\u0432\u0435\u0434\u044c | particle `after all'
-\u0442\u0430\u043c | there
-\u043f\u043e\u0442\u043e\u043c | then
-\u0441\u0435\u0431\u044f | oneself
-\u043d\u0438\u0447\u0435\u0433\u043e | nothing
-\u0435\u0439 | to her
-\u043c\u043e\u0436\u0435\u0442 | usually with `\u0431\u044b\u0442\u044c' as `maybe'
-\u043e\u043d\u0438 | they
-\u0442\u0443\u0442 | here
-\u0433\u0434\u0435 | where
-\u0435\u0441\u0442\u044c | there is/are
-\u043d\u0430\u0434\u043e | got to, must
-\u043d\u0435\u0439 | prepositional form of \u0435\u0439
-\u0434\u043b\u044f | for
-\u043c\u044b | we
-\u0442\u0435\u0431\u044f | thee
-\u0438\u0445 | them, their
-\u0447\u0435\u043c | than
-\u0431\u044b\u043b\u0430 | she was
-\u0441\u0430\u043c | self
-\u0447\u0442\u043e\u0431 | in order to
-\u0431\u0435\u0437 | without
-\u0431\u0443\u0434\u0442\u043e | as if
-\u0447\u0435\u043b\u043e\u0432\u0435\u043a | man, person, one
-\u0447\u0435\u0433\u043e | genitive form of `what'
-\u0440\u0430\u0437 | once
-\u0442\u043e\u0436\u0435 | also
-\u0441\u0435\u0431\u0435 | to oneself
-\u043f\u043e\u0434 | beneath
-\u0436\u0438\u0437\u043d\u044c | life
-\u0431\u0443\u0434\u0435\u0442 | will be
-\u0436 | short form of intensifer particle `\u0436\u0435'
-\u0442\u043e\u0433\u0434\u0430 | then
-\u043a\u0442\u043e | who
-\u044d\u0442\u043e\u0442 | this
-\u0433\u043e\u0432\u043e\u0440\u0438\u043b | was saying
-\u0442\u043e\u0433\u043e | genitive form of `that'
-\u043f\u043e\u0442\u043e\u043c\u0443 | for that reason
-\u044d\u0442\u043e\u0433\u043e | genitive form of `this'
-\u043a\u0430\u043a\u043e\u0439 | which
-\u0441\u043e\u0432\u0441\u0435\u043c | altogether
-\u043d\u0438\u043c | prepositional form of `\u0435\u0433\u043e', `\u043e\u043d\u0438'
-\u0437\u0434\u0435\u0441\u044c | here
-\u044d\u0442\u043e\u043c | prepositional form of `\u044d\u0442\u043e\u0442'
-\u043e\u0434\u0438\u043d | one
-\u043f\u043e\u0447\u0442\u0438 | almost
-\u043c\u043e\u0439 | my
-\u0442\u0435\u043c | instrumental/dative plural of `\u0442\u043e\u0442', `\u0442\u043e'
-\u0447\u0442\u043e\u0431\u044b | full form of `in order that'
-\u043d\u0435\u0435 | her (acc.)
-\u043a\u0430\u0436\u0435\u0442\u0441\u044f | it seems
-\u0441\u0435\u0439\u0447\u0430\u0441 | now
-\u0431\u044b\u043b\u0438 | they were
-\u043a\u0443\u0434\u0430 | where to
-\u0437\u0430\u0447\u0435\u043c | why
-\u0441\u043a\u0430\u0437\u0430\u0442\u044c | to say
-\u0432\u0441\u0435\u0445 | all (acc., gen. preposn. plural)
-\u043d\u0438\u043a\u043e\u0433\u0434\u0430 | never
-\u0441\u0435\u0433\u043e\u0434\u043d\u044f | today
-\u043c\u043e\u0436\u043d\u043e | possible, one can
-\u043f\u0440\u0438 | by
-\u043d\u0430\u043a\u043e\u043d\u0435\u0446 | finally
-\u0434\u0432\u0430 | two
-\u043e\u0431 | alternative form of `\u043e', about
-\u0434\u0440\u0443\u0433\u043e\u0439 | another
-\u0445\u043e\u0442\u044c | even
-\u043f\u043e\u0441\u043b\u0435 | after
-\u043d\u0430\u0434 | above
-\u0431\u043e\u043b\u044c\u0448\u0435 | more
-\u0442\u043e\u0442 | that one (masc.)
-\u0447\u0435\u0440\u0435\u0437 | across, in
-\u044d\u0442\u0438 | these
-\u043d\u0430\u0441 | us
-\u043f\u0440\u043e | about
-\u0432\u0441\u0435\u0433\u043e | in all, only, of all
-\u043d\u0438\u0445 | prepositional form of `\u043e\u043d\u0438' (they)
-\u043a\u0430\u043a\u0430\u044f | which, feminine
-\u043c\u043d\u043e\u0433\u043e | lots
-\u0440\u0430\u0437\u0432\u0435 | interrogative particle
-\u0441\u043a\u0430\u0437\u0430\u043b\u0430 | she said
-\u0442\u0440\u0438 | three
-\u044d\u0442\u0443 | this, acc. fem. sing.
-\u043c\u043e\u044f | my, feminine
-\u0432\u043f\u0440\u043e\u0447\u0435\u043c | moreover, besides
-\u0445\u043e\u0440\u043e\u0448\u043e | good
-\u0441\u0432\u043e\u044e | ones own, acc. fem. sing.
-\u044d\u0442\u043e\u0439 | oblique form of `\u044d\u0442\u0430', fem. `this'
-\u043f\u0435\u0440\u0435\u0434 | in front of
-\u0438\u043d\u043e\u0433\u0434\u0430 | sometimes
-\u043b\u0443\u0447\u0448\u0435 | better
-\u0447\u0443\u0442\u044c | a little
-\u0442\u043e\u043c | preposn. form of `that one'
-\u043d\u0435\u043b\u044c\u0437\u044f | one must not
-\u0442\u0430\u043a\u043e\u0439 | such a one
-\u0438\u043c | to them
-\u0431\u043e\u043b\u0435\u0435 | more
-\u0432\u0441\u0435\u0433\u0434\u0430 | always
-\u043a\u043e\u043d\u0435\u0447\u043d\u043e | of course
-\u0432\u0441\u044e | acc. fem. sing of `all'
-\u043c\u0435\u0436\u0434\u0443 | between
-
-
- | b: some paradigms
- |
- | personal pronouns
- |
- | \u044f \u043c\u0435\u043d\u044f \u043c\u043d\u0435 \u043c\u043d\u043e\u0439 [\u043c\u043d\u043e\u044e]
- | \u0442\u044b \u0442\u0435\u0431\u044f \u0442\u0435\u0431\u0435 \u0442\u043e\u0431\u043e\u0439 [\u0442\u043e\u0431\u043e\u044e]
- | \u043e\u043d \u0435\u0433\u043e \u0435\u043c\u0443 \u0438\u043c [\u043d\u0435\u0433\u043e, \u043d\u0435\u043c\u0443, \u043d\u0438\u043c]
- | \u043e\u043d\u0430 \u0435\u0435 \u044d\u0438 \u0435\u044e [\u043d\u0435\u0435, \u043d\u044d\u0438, \u043d\u0435\u044e]
- | \u043e\u043d\u043e \u0435\u0433\u043e \u0435\u043c\u0443 \u0438\u043c [\u043d\u0435\u0433\u043e, \u043d\u0435\u043c\u0443, \u043d\u0438\u043c]
- |
- | \u043c\u044b \u043d\u0430\u0441 \u043d\u0430\u043c \u043d\u0430\u043c\u0438
- | \u0432\u044b \u0432\u0430\u0441 \u0432\u0430\u043c \u0432\u0430\u043c\u0438
- | \u043e\u043d\u0438 \u0438\u0445 \u0438\u043c \u0438\u043c\u0438 [\u043d\u0438\u0445, \u043d\u0438\u043c, \u043d\u0438\u043c\u0438]
- |
- | \u0441\u0435\u0431\u044f \u0441\u0435\u0431\u0435 \u0441\u043e\u0431\u043e\u0439 [\u0441\u043e\u0431\u043e\u044e]
- |
- | demonstrative pronouns: \u044d\u0442\u043e\u0442 (this), \u0442\u043e\u0442 (that)
- |
- | \u044d\u0442\u043e\u0442 \u044d\u0442\u0430 \u044d\u0442\u043e \u044d\u0442\u0438
- | \u044d\u0442\u043e\u0433\u043e \u044d\u0442\u044b \u044d\u0442\u043e \u044d\u0442\u0438
- | \u044d\u0442\u043e\u0433\u043e \u044d\u0442\u043e\u0439 \u044d\u0442\u043e\u0433\u043e \u044d\u0442\u0438\u0445
- | \u044d\u0442\u043e\u043c\u0443 \u044d\u0442\u043e\u0439 \u044d\u0442\u043e\u043c\u0443 \u044d\u0442\u0438\u043c
- | \u044d\u0442\u0438\u043c \u044d\u0442\u043e\u0439 \u044d\u0442\u0438\u043c [\u044d\u0442\u043e\u044e] \u044d\u0442\u0438\u043c\u0438
- | \u044d\u0442\u043e\u043c \u044d\u0442\u043e\u0439 \u044d\u0442\u043e\u043c \u044d\u0442\u0438\u0445
- |
- | \u0442\u043e\u0442 \u0442\u0430 \u0442\u043e \u0442\u0435
- | \u0442\u043e\u0433\u043e \u0442\u0443 \u0442\u043e \u0442\u0435
- | \u0442\u043e\u0433\u043e \u0442\u043e\u0439 \u0442\u043e\u0433\u043e \u0442\u0435\u0445
- | \u0442\u043e\u043c\u0443 \u0442\u043e\u0439 \u0442\u043e\u043c\u0443 \u0442\u0435\u043c
- | \u0442\u0435\u043c \u0442\u043e\u0439 \u0442\u0435\u043c [\u0442\u043e\u044e] \u0442\u0435\u043c\u0438
- | \u0442\u043e\u043c \u0442\u043e\u0439 \u0442\u043e\u043c \u0442\u0435\u0445
- |
- | determinative pronouns
- |
- | (a) \u0432\u0435\u0441\u044c (all)
- |
- | \u0432\u0435\u0441\u044c \u0432\u0441\u044f \u0432\u0441\u0435 \u0432\u0441\u0435
- | \u0432\u0441\u0435\u0433\u043e \u0432\u0441\u044e \u0432\u0441\u0435 \u0432\u0441\u0435
- | \u0432\u0441\u0435\u0433\u043e \u0432\u0441\u0435\u0439 \u0432\u0441\u0435\u0433\u043e \u0432\u0441\u0435\u0445
- | \u0432\u0441\u0435\u043c\u0443 \u0432\u0441\u0435\u0439 \u0432\u0441\u0435\u043c\u0443 \u0432\u0441\u0435\u043c
- | \u0432\u0441\u0435\u043c \u0432\u0441\u0435\u0439 \u0432\u0441\u0435\u043c [\u0432\u0441\u0435\u044e] \u0432\u0441\u0435\u043c\u0438
- | \u0432\u0441\u0435\u043c \u0432\u0441\u0435\u0439 \u0432\u0441\u0435\u043c \u0432\u0441\u0435\u0445
- |
- | (b) \u0441\u0430\u043c (himself etc)
- |
- | \u0441\u0430\u043c \u0441\u0430\u043c\u0430 \u0441\u0430\u043c\u043e \u0441\u0430\u043c\u0438
- | \u0441\u0430\u043c\u043e\u0433\u043e \u0441\u0430\u043c\u0443 \u0441\u0430\u043c\u043e \u0441\u0430\u043c\u0438\u0445
- | \u0441\u0430\u043c\u043e\u0433\u043e \u0441\u0430\u043c\u043e\u0439 \u0441\u0430\u043c\u043e\u0433\u043e \u0441\u0430\u043c\u0438\u0445
- | \u0441\u0430\u043c\u043e\u043c\u0443 \u0441\u0430\u043c\u043e\u0439 \u0441\u0430\u043c\u043e\u043c\u0443 \u0441\u0430\u043c\u0438\u043c
- | \u0441\u0430\u043c\u0438\u043c \u0441\u0430\u043c\u043e\u0439 \u0441\u0430\u043c\u0438\u043c [\u0441\u0430\u043c\u043e\u044e] \u0441\u0430\u043c\u0438\u043c\u0438
- | \u0441\u0430\u043c\u043e\u043c \u0441\u0430\u043c\u043e\u0439 \u0441\u0430\u043c\u043e\u043c \u0441\u0430\u043c\u0438\u0445
- |
- | stems of verbs `to be', `to have', `to do' and modal
- |
- | \u0431\u044b\u0442\u044c \u0431\u044b \u0431\u0443\u0434 \u0431\u044b\u0432 \u0435\u0441\u0442\u044c \u0441\u0443\u0442\u044c
- | \u0438\u043c\u0435
- | \u0434\u0435\u043b
- | \u043c\u043e\u0433 \u043c\u043e\u0436 \u043c\u043e\u0447\u044c
- | \u0443\u043c\u0435
- | \u0445\u043e\u0447 \u0445\u043e\u0442
- | \u0434\u043e\u043b\u0436
- | \u043c\u043e\u0436\u043d
- | \u043d\u0443\u0436\u043d
- | \u043d\u0435\u043b\u044c\u0437\u044f
-
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
- | s� = 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
-p� | on
-den | it, this/that
-med | with
-var | where, each
-sig | him(self) etc
-f�r | for
-s� | so (also: seed)
-till | to
-�r | 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
-d� | then, when
-sin | his
-nu | now
-har | have
-inte | inte n�gon = no one
-hans | his
-honom | him
-skulle | 'sake'
-hennes | her
-d�r | there
-min | my
-man | one (pronoun)
-ej | nor
-vid | at, by, on (also: vast)
-kunde | could
-n�got | some etc
-fr�n | from, off
-ut | out
-n�r | when
-efter | after, behind
-upp | up
-vi | we
-dem | them
-vara | be
-vad | what
-�ver | over
-�n | than
-dig | you
-kan | can
-sina | his
-h�r | here
-ha | have
-mot | towards
-alla | all
-under | under (also: wonder)
-n�gon | some etc
-eller | or (else)
-allt | all
-mycket | much
-sedan | since
-ju | why
-denna | this/that
-sj�lv | myself, yourself etc
-detta | this/that
-�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
-n�gra | some etc
-deras | their
-blir | from bli
-mina | my
-samma | (the) same
-vilken | who, that
-er | you, your
-s�dan | such a
-v�r | our
-blivit | from bli
-dess | its
-inom | within
-mellan | between
-s�dant | such a
-varf�r | why
-varje | each
-vilka | who, that
-ditt | thy
-vem | who
-vilket | who, that
-sitta | his
-s�dana | such a
-vart | each
-dina | thy
-vars | whose
-v�rt | our
-v�ra | 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
-\u0e44\u0e27\u0e49
-\u0e44\u0e21\u0e48
-\u0e44\u0e1b
-\u0e44\u0e14\u0e49
-\u0e43\u0e2b\u0e49
-\u0e43\u0e19
-\u0e42\u0e14\u0e22
-\u0e41\u0e2b\u0e48\u0e07
-\u0e41\u0e25\u0e49\u0e27
-\u0e41\u0e25\u0e30
-\u0e41\u0e23\u0e01
-\u0e41\u0e1a\u0e1a
-\u0e41\u0e15\u0e48
-\u0e40\u0e2d\u0e07
-\u0e40\u0e2b\u0e47\u0e19
-\u0e40\u0e25\u0e22
-\u0e40\u0e23\u0e34\u0e48\u0e21
-\u0e40\u0e23\u0e32
-\u0e40\u0e21\u0e37\u0e48\u0e2d
-\u0e40\u0e1e\u0e37\u0e48\u0e2d
-\u0e40\u0e1e\u0e23\u0e32\u0e30
-\u0e40\u0e1b\u0e47\u0e19\u0e01\u0e32\u0e23
-\u0e40\u0e1b\u0e47\u0e19
-\u0e40\u0e1b\u0e34\u0e14\u0e40\u0e1c\u0e22
-\u0e40\u0e1b\u0e34\u0e14
-\u0e40\u0e19\u0e37\u0e48\u0e2d\u0e07\u0e08\u0e32\u0e01
-\u0e40\u0e14\u0e35\u0e22\u0e27\u0e01\u0e31\u0e19
-\u0e40\u0e14\u0e35\u0e22\u0e27
-\u0e40\u0e0a\u0e48\u0e19
-\u0e40\u0e09\u0e1e\u0e32\u0e30
-\u0e40\u0e04\u0e22
-\u0e40\u0e02\u0e49\u0e32
-\u0e40\u0e02\u0e32
-\u0e2d\u0e35\u0e01
-\u0e2d\u0e32\u0e08
-\u0e2d\u0e30\u0e44\u0e23
-\u0e2d\u0e2d\u0e01
-\u0e2d\u0e22\u0e48\u0e32\u0e07
-\u0e2d\u0e22\u0e39\u0e48
-\u0e2d\u0e22\u0e32\u0e01
-\u0e2b\u0e32\u0e01
-\u0e2b\u0e25\u0e32\u0e22
-\u0e2b\u0e25\u0e31\u0e07\u0e08\u0e32\u0e01
-\u0e2b\u0e25\u0e31\u0e07
-\u0e2b\u0e23\u0e37\u0e2d
-\u0e2b\u0e19\u0e36\u0e48\u0e07
-\u0e2a\u0e48\u0e27\u0e19
-\u0e2a\u0e48\u0e07
-\u0e2a\u0e38\u0e14
-\u0e2a\u0e4d\u0e32\u0e2b\u0e23\u0e31\u0e1a
-\u0e27\u0e48\u0e32
-\u0e27\u0e31\u0e19
-\u0e25\u0e07
-\u0e23\u0e48\u0e27\u0e21
-\u0e23\u0e32\u0e22
-\u0e23\u0e31\u0e1a
-\u0e23\u0e30\u0e2b\u0e27\u0e48\u0e32\u0e07
-\u0e23\u0e27\u0e21
-\u0e22\u0e31\u0e07
-\u0e21\u0e35
-\u0e21\u0e32\u0e01
-\u0e21\u0e32
-\u0e1e\u0e23\u0e49\u0e2d\u0e21
-\u0e1e\u0e1a
-\u0e1c\u0e48\u0e32\u0e19
-\u0e1c\u0e25
-\u0e1a\u0e32\u0e07
-\u0e19\u0e48\u0e32
-\u0e19\u0e35\u0e49
-\u0e19\u0e4d\u0e32
-\u0e19\u0e31\u0e49\u0e19
-\u0e19\u0e31\u0e01
-\u0e19\u0e2d\u0e01\u0e08\u0e32\u0e01
-\u0e17\u0e38\u0e01
-\u0e17\u0e35\u0e48\u0e2a\u0e38\u0e14
-\u0e17\u0e35\u0e48
-\u0e17\u0e4d\u0e32\u0e43\u0e2b\u0e49
-\u0e17\u0e4d\u0e32
-\u0e17\u0e32\u0e07
-\u0e17\u0e31\u0e49\u0e07\u0e19\u0e35\u0e49
-\u0e17\u0e31\u0e49\u0e07
-\u0e16\u0e49\u0e32
-\u0e16\u0e39\u0e01
-\u0e16\u0e36\u0e07
-\u0e15\u0e49\u0e2d\u0e07
-\u0e15\u0e48\u0e32\u0e07\u0e46
-\u0e15\u0e48\u0e32\u0e07
-\u0e15\u0e48\u0e2d
-\u0e15\u0e32\u0e21
-\u0e15\u0e31\u0e49\u0e07\u0e41\u0e15\u0e48
-\u0e15\u0e31\u0e49\u0e07
-\u0e14\u0e49\u0e32\u0e19
-\u0e14\u0e49\u0e27\u0e22
-\u0e14\u0e31\u0e07
-\u0e0b\u0e36\u0e48\u0e07
-\u0e0a\u0e48\u0e27\u0e07
-\u0e08\u0e36\u0e07
-\u0e08\u0e32\u0e01
-\u0e08\u0e31\u0e14
-\u0e08\u0e30
-\u0e04\u0e37\u0e2d
-\u0e04\u0e27\u0e32\u0e21
-\u0e04\u0e23\u0e31\u0e49\u0e07
-\u0e04\u0e07
-\u0e02\u0e36\u0e49\u0e19
-\u0e02\u0e2d\u0e07
-\u0e02\u0e2d
-\u0e02\u0e13\u0e30
-\u0e01\u0e48\u0e2d\u0e19
-\u0e01\u0e47
-\u0e01\u0e32\u0e23
-\u0e01\u0e31\u0e1a
-\u0e01\u0e31\u0e19
-\u0e01\u0e27\u0e48\u0e32
-\u0e01\u0e25\u0e48\u0e32\u0e27
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
-altm\u0131\u015f
-alt\u0131
-ama
-ancak
-arada
-asl\u0131nda
-ayr\u0131ca
-bana
-baz\u0131
-belki
-ben
-benden
-beni
-benim
-beri
-be\u015f
-bile
-bin
-bir
-bir�ok
-biri
-birka�
-birkez
-bir\u015fey
-bir\u015feyi
-biz
-bize
-bizden
-bizi
-bizim
-b�yle
-b�ylece
-bu
-buna
-bunda
-bundan
-bunlar
-bunlar\u0131
-bunlar\u0131n
-bunu
-bunun
-burada
-�ok
-��nk�
-da
-daha
-dahi
-de
-defa
-de\u011fil
-di\u011fer
-diye
-doksan
-dokuz
-dolay\u0131
-dolay\u0131s\u0131yla
-d�rt
-edecek
-eden
-ederek
-edilecek
-ediliyor
-edilmesi
-ediyor
-e\u011fer
-elli
-en
-etmesi
-etti
-etti\u011fi
-etti\u011fini
-gibi
-g�re
-halen
-hangi
-hatta
-hem
-hen�z
-hep
-hepsi
-her
-herhangi
-herkesin
-hi�
-hi�bir
-i�in
-iki
-ile
-ilgili
-ise
-i\u015fte
-itibaren
-itibariyle
-kadar
-kar\u015f\u0131n
-katrilyon
-kendi
-kendilerine
-kendini
-kendisi
-kendisine
-kendisini
-kez
-ki
-kim
-kimden
-kime
-kimi
-kimse
-k\u0131rk
-milyar
-milyon
-mu
-m�
-m\u0131
-nas\u0131l
-ne
-neden
-nedenle
-nerde
-nerede
-nereye
-niye
-ni�in
-o
-olan
-olarak
-oldu
-oldu\u011fu
-oldu\u011funu
-olduklar\u0131n\u0131
-olmad\u0131
-olmad\u0131\u011f\u0131
-olmak
-olmas\u0131
-olmayan
-olmaz
-olsa
-olsun
-olup
-olur
-olursa
-oluyor
-on
-ona
-ondan
-onlar
-onlardan
-onlar\u0131
-onlar\u0131n
-onu
-onun
-otuz
-oysa
-�yle
-pek
-ra\u011fmen
-sadece
-sanki
-sekiz
-seksen
-sen
-senden
-seni
-senin
-siz
-sizden
-sizi
-sizin
-\u015fey
-\u015feyden
-\u015feyi
-\u015feyler
-\u015f�yle
-\u015fu
-\u015funa
-\u015funda
-\u015fundan
-\u015funlar\u0131
-\u015funu
-taraf\u0131ndan
-trilyon
-t�m
-��
-�zere
-var
-vard\u0131
-ve
-veya
-ya
-yani
-yapacak
-yap\u0131lan
-yap\u0131lmas\u0131
-yap\u0131yor
-yapmak
-yapt\u0131
-yapt\u0131\u011f\u0131
-yapt\u0131\u011f\u0131n\u0131
-yapt\u0131klar\u0131
-yedi
-yerine
-yetmi\u015f
-yine
-yirmi
-yoksa
-y�z
-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
-\u65e5\u672c\u7d4c\u6e08\u65b0\u805e,\u65e5\u672c \u7d4c\u6e08 \u65b0\u805e,\u30cb\u30db\u30f3 \u30b1\u30a4\u30b6\u30a4 \u30b7\u30f3\u30d6\u30f3,\u30ab\u30b9\u30bf\u30e0\u540d\u8a5e
-\u95a2\u897f\u56fd\u969b\u7a7a\u6e2f,\u95a2\u897f \u56fd\u969b \u7a7a\u6e2f,\u30ab\u30f3\u30b5\u30a4 \u30b3\u30af\u30b5\u30a4 \u30af\u30a6\u30b3\u30a6,\u30ab\u30b9\u30bf\u30e0\u540d\u8a5e
-
-# Custom segmentation for compound katakana
-\u30c8\u30fc\u30c8\u30d0\u30c3\u30b0,\u30c8\u30fc\u30c8 \u30d0\u30c3\u30b0,\u30c8\u30fc\u30c8 \u30d0\u30c3\u30b0,\u304b\u305a\u30ab\u30ca\u540d\u8a5e
-\u30b7\u30e7\u30eb\u30c0\u30fc\u30d0\u30c3\u30b0,\u30b7\u30e7\u30eb\u30c0\u30fc \u30d0\u30c3\u30b0,\u30b7\u30e7\u30eb\u30c0\u30fc \u30d0\u30c3\u30b0,\u304b\u305a\u30ab\u30ca\u540d\u8a5e
-
-# Custom reading for former sumo wrestler
-\u671d\u9752\u9f8d,\u671d\u9752\u9f8d,\u30a2\u30b5\u30b7\u30e7\u30a6\u30ea\u30e5\u30a6,\u30ab\u30b9\u30bf\u30e0\u4eba\u540d
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 \ufeef to \ufef1, 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>