NIHVIVO-2459 Improvements to stemmed autocomplete matching. NIHVIVO-2801 Fix error in SolrAutocompleteController.

This commit is contained in:
ryounes 2011-07-01 16:19:31 +00:00
parent cebc368738
commit 50b159710b
7 changed files with 97 additions and 36 deletions

View file

@ -259,7 +259,7 @@
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" enablePositionIncrements="true" />
words="stopwords-name.txt" enablePositionIncrements="true" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1"
generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0"
@ -458,7 +458,7 @@
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" enablePositionIncrements="true" />
words="stopwords-name.txt" enablePositionIncrements="true" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1"
generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0"
@ -470,7 +470,7 @@
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" enablePositionIncrements="true" />
words="stopwords-name.txt" enablePositionIncrements="true" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1"
generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0"

View file

@ -0,0 +1,38 @@
# Standard english stop words taken from Lucene's StopAnalyzer
# Stopwords used in autocomplete (label-matching) fields, since full list in stopwords.txt may be too inclusive. Since label includes things like
# book titles, we want a smaller set of stopwords.
a
an
and
are
as
at
be
but
by
for
if
in
into
is
it
no
not
of
on
or
s
t
that
the
their
then
there
these
they
this
to
was
will
with

View file

@ -130,9 +130,6 @@ our
out
over
re
said
same
see
should
since
so
@ -156,13 +153,10 @@ to
too
under
up
use
very
want
was
way
we
well
were
what
when