Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Improve search handling for non-LC call numbers #261

Draft
wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

Improve search handling for non-LC call numbers #261

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions searchworks-prod/schema.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -662,8 +662,10 @@
<!-- field designed for LC call number searching -->
<fieldType name="callnum_ws" class="solr.TextField" omitNorms="true" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<!-- LC: no space between class letters and digits; normalize to " ." before first cutter, no leading space -->
<charFilter class="solr.PatternReplaceCharFilterFactory" pattern="^ *([A-Za-z]{1,3}) ?(\d{1,4}(\.\d+)?) ?\.?([A-Za-z]\d+)" replacement="$1$2 .$4"/>
<!-- LC: no space between class letters and digits, no leading space -->
<charFilter class="solr.PatternReplaceCharFilterFactory" pattern="^ *([A-Za-z]{1,3}) +(\d{1,4})" replacement="$1$2" />
<!-- LC: normalize to " ." before first cutter or first letter of cutter (could be preceded by " ." "." " " or nothing) -->
<charFilter class="solr.PatternReplaceCharFilterFactory" pattern="^([A-Za-z]{1,3}\d{1,4}(\.\d+)?) *\.?([A-Za-z](\d+)?)" replacement="$1 .$3" />
<!-- LC: add space between first cutter letter and its digits to allow matching on first cutter letter only -->
<charFilter class="solr.PatternReplaceCharFilterFactory" pattern="^([A-Za-z]{1,3}\d{1,4}(\.\d+)? \.([A-Za-z]))(\d+)" replacement="$1 $4"/>
<!-- prepend yyyy to string so searches can be left anchored -->
Expand All @@ -674,7 +676,7 @@
<!-- Note that the query string could be a partial call number, so we can't combine all patterns -->
<analyzer type="query">
<!-- LC: no space between class letters and digits, no leading space -->
<charFilter class="solr.PatternReplaceCharFilterFactory" pattern="^ *([A-Za-z]{1,3}) *(\d{1,4})" replacement="$1$2" />
<charFilter class="solr.PatternReplaceCharFilterFactory" pattern="^ *([A-Za-z]{1,3}) +(\d{1,4})" replacement="$1$2" />
<!-- LC: normalize to " ." before first cutter or first letter of cutter (could be preceded by " ." "." " " or nothing) -->
<charFilter class="solr.PatternReplaceCharFilterFactory" pattern="^([A-Za-z]{1,3}\d{1,4}(\.\d+)?) *\.?([A-Za-z](\d+)?)" replacement="$1 .$3" />
<!-- LC: add space between first cutter letter and its digits to allow matching on first cutter letter only -->
Expand Down