Author: cedric@yterium.com
Date: Mon Jul 17 10:50:31 2006
New Revision: 4039
Log:
les dicos stopwords
Added:
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/ct.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/cz.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/da.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/de.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/en.big.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/en.huge.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/en.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/es.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/fr.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/hu.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/it.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/lt.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/nl.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/no.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/pl.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/pt.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/ru.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/sk.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/tr.sl
_plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/ua.sl
Added: _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/ct.sl
--- _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/ct.sl (added)
+++ _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/ct.sl Mon Jul 17 10:50:31 2006
@@ -0,0 +1,140 @@
+# Stopword list for "catalan", charset iso-8859-1
+# 19/10/2001 23:23
+#
+# The Cthulhu Group
+#
+# jgay@ajgirona.org
+# pplaniol@ajgirona.org
+
+Charset: iso-8859-1
+Language: ct
+
+
+de
+es
+i
+a
+o
+un
+una
+unes
+uns
+un
+tot
+també
+altre
+algun
+alguna
+alguns
+algunes
+ser
+és
+soc
+ets
+som
+estic
+està
+estem
+esteu
+estan
+com
+en
+per
+perquè
+per que
+estat
+estava
+ans
+abans
+éssent
+ambdós
+però
+per
+poder
+potser
+puc
+podem
+podeu
+poden
+vaig
+va
+van
+fer
+faig
+fa
+fem
+feu
+fan
+cada
+fi
+inclòs
+primer
+des de
+conseguir
+consegueixo
+consigueix
+consigueixes
+conseguim
+consigueixen
+anar
+haver
+tenir
+tinc
+te
+tenim
+teniu
+tene
+el
+la
+les
+els
+seu
+aquí
+meu
+teu
+ells
+elles
+ens
+nosaltres
+vosaltres
+si
+dins
+sols
+solament
+saber
+saps
+sap
+sabem
+sabeu
+saben
+últim
+llarg
+bastant
+fas
+molts
+aquells
+aquelles
+seus
+llavors
+sota
+dalt
+ús
+molt
+era
+eres
+erem
+eren
+mode
+bé
+quant
+quan
+on
+mentre
+qui
+amb
+entre
+sense
+jo
+aquell
+
+
Added: _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/cz.sl
--- _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/cz.sl (added)
+++ _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/cz.sl Mon Jul 17 10:50:31 2006
@@ -0,0 +1,154 @@
+#Subject: my distr. + stopword(lang, word)
+#Date: Wed, 10 Nov 1999 14:59:39 +0100 (CET)
+#From: Builder <cbob@ms.anet.cz>
+#To: bar@izhcom.ru
+#
+# Hallo,
+#
+#I'm sending you a stoplist for Czech, it's base on frequent analyze of
+#about 10 000 pages. But this is only in ASCII charset.
+#
+
+
+Charset: us-ascii
+Language: cz
+
+
+se
+dnes
+cz
+timto
+budes
+budem
+byli
+jses
+muj
+svym
+ta
+tomto
+tohle
+tuto
+tyto
+jej
+zda
+proc
+mate
+tato
+kam
+tohoto
+kdo
+kteri
+mi
+nam
+tom
+tomuto
+mit
+nic
+proto
+kterou
+byla
+toho
+protoze
+asi
+ho
+nasi
+napiste
+re
+coz
+tim
+takze
+svych
+jeji
+svymi
+jste
+aj
+tu
+tedy
+teto
+bylo
+kde
+ke
+prave
+ji
+nad
+nejsou
+ci
+pod
+tema
+mezi
+pres
+ty
+pak
+vam
+ani
+kdyz
+vsak
+ne
+jsem
+tento
+clanku
+clanky
+aby
+jsme
+pred
+pta
+jejich
+byl
+jeste
+az
+bez
+take
+pouze
+prvni
+vase
+ktera
+nas
+novy
+tipy
+pokud
+muze
+strana
+jeho
+sve
+jine
+zpravy
+nove
+neni
+vas
+jen
+podle
+zde
+clanek
+uz
+email
+byt
+vice
+bude
+jiz
+nez
+ktery
+by
+ktere
+co
+nebo
+ten
+tak
+ma
+pri
+od
+po
+jsou
+jak
+dalsi
+ale
+si
+ve
+to
+jako
+za
+zpet
+ze
+do
+pro
+je
+na
Added: _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/da.sl
--- _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/da.sl (added)
+++ _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/da.sl Mon Jul 17 10:50:31 2006
@@ -0,0 +1,112 @@
+#
+# Danish stoplist
+# File created by Hans Kejser Hansen <hkh@netnords.dk> ,
+# August 31th, 2000
+#
+
+Charset: latin1
+Language: da
+
+
+af
+alle
+andet
+andre
+at
+begge
+da
+de
+den
+denne
+der
+deres
+det
+dette
+dig
+din
+dog
+du
+ej
+eller
+en
+end
+ene
+eneste
+enhver
+et
+fem
+fire
+flere
+fleste
+for
+fordi
+forrige
+fra
+få
+før
+god
+han
+hans
+har
+hendes
+her
+hun
+hvad
+hvem
+hver
+hvilken
+hvis
+hvor
+hvordan
+hvorfor
+hvornår
+i
+ikke
+ind
+ingen
+intet
+jeg
+jeres
+kan
+kom
+kommer
+lav
+lidt
+lille
+man
+mand
+mange
+med
+meget
+men
+mens
+mere
+mig
+ned
+ni
+nogen
+noget
+ny
+nyt
+nær
+næste
+næsten
+og
+op
+otte
+over
+på
+se
+seks
+ses
+som
+stor
+store
+syv
+ti
+til
+to
+tre
+ud
+var
+
Added: _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/de.sl
--- _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/de.sl (added)
+++ _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/de.sl Mon Jul 17 10:50:31 2006
@@ -0,0 +1,144 @@
+#
+# German stoplist
+# File created by Fredy Kuenzler <fredy@kuenzler.ch>,
+# May 6th, 1999
+# based on the stopword(lang, word)s-list published on
+# http://ls6-www.informatik.uni-dortmund.de/ir/projects/freeWAIS-sf/stopword(lang, word)S
+# for the UdmSearch Project.
+# Amended by Fredy Kuenzler.
+#
+
+Charset: latin1
+Language: de
+
+
+aber
+als
+am
+an
+auch
+auf
+aus
+bei
+bin
+bis
+bist
+da
+dadurch
+daher
+darum
+das
+daß
+dass
+dein
+deine
+dem
+den
+der
+des
+dessen
+deshalb
+die
+dies
+dieser
+dieses
+doch
+dort
+du
+durch
+ein
+eine
+einem
+einen
+einer
+eines
+er
+es
+euer
+eure
+für
+hatte
+hatten
+hattest
+hattet
+hier
+hinter
+ich
+ihr
+ihre
+im
+in
+ist
+ja
+jede
+jedem
+jeden
+jeder
+jedes
+jener
+jenes
+jetzt
+kann
+kannst
+können
+könnt
+machen
+mein
+meine
+mit
+muß
+mußt
+musst
+müssen
+müßt
+nach
+nachdem
+nein
+nicht
+nun
+oder
+seid
+sein
+seine
+sich
+sie
+sind
+soll
+sollen
+sollst
+sollt
+sonst
+soweit
+sowie
+und
+unser
+unsere
+unter
+vom
+von
+vor
+wann
+warum
+was
+weiter
+weitere
+wenn
+wer
+werde
+werden
+werdet
+weshalb
+wie
+wieder
+wieso
+wir
+wird
+wirst
+wo
+woher
+wohin
+zu
+zum
+zur
+über
+
Added: _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/en.big.sl
--- _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/en.big.sl (added)
+++ _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/en.big.sl Mon Jul 17 10:50:31 2006
@@ -0,0 +1,204 @@
+#
+# English stoplist
+#
+
+Charset: us-ascii
+Language: en
+
+
+a
+accordance
+according
+accordingly
+about
+again
+against
+ah
+all
+although
+always
+am
+anymore
+anyone
+away
+approximately
+after
+also
+an
+and
+another
+any
+are
+as
+at
+back
+be
+begin
+begins
+beginning
+beginnings
+below
+between
+before
+both
+because
+been
+being
+but
+by
+can
+could
+cannot
+come
+did
+do
+due
+doing
+during
+does
+each
+end
+even
+either
+enough
+especially
+etc
+for
+from
+followed
+following
+further
+found
+far
+get
+go
+give
+given
+giving
+goes
+got
+had
+have
+he
+her
+here
+his
+how
+has
+hers
+herself
+him
+himself
+hardly
+however
+herein
+i
+if
+in
+into
+is
+it
+its
+invention
+itself
+just
+may
+me
+might
+much
+must
+my
+more
+myself
+means
+mainly
+mostly
+no
+not
+nor
+now
+nearly
+next
+nay
+near
+of
+off
+on
+only
+or
+other
+our
+out
+over
+overall
+otherwise
+ourselves
+onto
+should
+so
+some
+still
+such
+same
+seem
+seen
+several
+show
+showed
+shown
+showns
+significant
+significantly
+since
+suggest
+shall
+she
+than
+that
+the
+their
+them
+then
+there
+these
+they
+this
+those
+to
+too
+try
+two
+themselves
+thou
+though
+throughout
+thus
+therefore
+thereof
+thereto
+under
+up
+us
+using
+upon
+was
+we
+were
+what
+when
+where
+which
+while
+who
+why
+will
+with
+within
+without
+would
+you
+your
+yes
+yours
+yourself
+yourselves
Added: _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/en.huge.sl
--- _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/en.huge.sl (added)
+++ _plugins_/_agora_/mnogosearch/mnogosearch/etc/stopwords/en.huge.sl Mon Jul 17 10:50:31 2006
@@ -0,0 +1,718 @@
+#
+# Date: Sun, 3 Sep 2000 11:00:42 -0700
+# From: Shane Wegner <shane@cm.nu>
+# To: udmsearch@search.udm.net
+# Subject: UdmSearch: Another stopwords list
+#
+# I thought I'd share this list with other UdmSearch users. I was using the
+# stop.en.1.txt file but this cut my database by about 25%.
+#
+# Any words in here people think one might actually wish to search on?
+#
+
+#
+# Modified and extended by Maxime Zakharov. 3 Nov 2003
+#
+
+Charset: us-ascii
+Language: en
+
+
+a
+able
+about
+above
+abst
+accordance
+according
+accordingly
+across
+act
+actually
+added
+adj
+adopted
+affected
+affecting
+affects
+after
+afterwards
+again
+against
+ah
+all
+almost
+alone
+along
+already
+also
+although
+always
+am
+among
+amongst
+an
+and
+announce
+another
+any
+anybody
+anyhow
+anymore
+anyone
+anything
+anyway
+anyways
+anywhere
+apparently
+approximately
+are
+aren
+arent
+arise
+around
+as
+ask
+asking
+aside
+at
+auth
+available
+away
+awfully
+
+b
+back
+be
+became
+because
+become
+becomes
+becoming
+been
+before
+beforehand
+begin
+beginning
[... 2847 lines stripped ...]