added stopword support to the indexer, added indexer webbug

darcs-hash:20050814181035-7ad00-ed5d879d29fcee7f925f806456675605b058966a.gz

1 files changed, 115 insertions, 0 deletions

diff --git a/inc/lang/cs/stopwords.txt b/inc/lang/cs/stopwords.txt
new file mode 100644
index 000000000..08aee2a4c
--- /dev/null
+++ b/inc/lang/cs/stopwords.txt
@@ -0,0 +1,115 @@
+# This is a list of words the indexer ignores, one word per line
+# When you edit this file be sure to use UNIX line endings (single newline)
+# No need to include words shorter than 3 chars - these are ignored anyway
+# This list is based upon the ones found at http://www.ranks.nl/stopwords/
+dnes
+timto
+budes
+budem
+byli
+jses
+muj
+svym
+tomto
+tohle
+tuto
+tyto
+jej
+zda
+proc
+mate
+tato
+kam
+tohoto
+kdo
+kteri
+nam
+tom
+tomuto
+mit
+nic
+proto
+kterou
+byla
+toho
+protoze
+asi
+nasi
+napiste
+coz
+tim
+takze
+svych
+jeji
+svymi
+jste
+tedy
+teto
+bylo
+kde
+prave
+nad
+nejsou
+pod
+tema
+mezi
+pres
+pak
+vam
+ani
+kdyz
+vsak
+jsem
+tento
+clanku
+clanky
+aby
+jsme
+pred
+pta
+jejich
+byl
+jeste
+bez
+take
+pouze
+prvni
+vase
+ktera
+nas
+novy
+tipy
+pokud
+muze
+design
+strana
+jeho
+sve
+jine
+zpravy
+nove
+neni
+vas
+jen
+podle
+zde
+clanek
+email
+byt
+vice
+bude
+jiz
+nez
+ktery
+ktere
+nebo
+ten
+tak
+pri
+jsou
+jak
+dalsi
+ale
+jako
+zpet
+pro