From becd60e9c3305efb216c8cc559cf8adac4ed0a1b Mon Sep 17 00:00:00 2001 From: Tomas Cohen Arazi Date: Tue, 11 Jun 2013 10:46:36 -0300 Subject: [PATCH] Bug 10431 - Spanish Zebra character sorting file MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit This patch provides a definition file for Spanish (es) character sorting in Zebra. It is based on the ideas from Hugo Agud and Pablo Bianchi . Makefile.PL is fixed to notice the existence of the 'es' language. The docs for koha-create are touched too. To test: Tarball ======= - Go through the install process, choosing 'es' for the Zebra's language step - Koha should work as usual. - Running this should show the lang definition is properly set. $ grep -R "lang_defs/es" /etc/koha/* (stuff like zebradb/zebra-biblios-dom.cfg:profilePath:...etc/koha/zebra/lang_defs/es... should show) - This file should be present: /etc/koha/zebradb/lang_defs/es/sort-string-utf.chr Packages ======== - Build your own package, it shouldn't break the packaging - Try the new package, using koha-create to set an instance using --lang 'es' Sponsored-by: Universidad Nacional de Córdoba Signed-off-by: Galen Charlton Signed-off-by: Chris Cormack Signed-off-by: Kyle M Hall Signed-off-by: Galen Charlton (cherry picked from commit 343c93ea4358d7b78dec25dfbcca525eabbfa6bf) Signed-off-by: Tomas Cohen Arazi --- Makefile.PL | 2 +- debian/scripts/koha-create | 2 +- etc/zebradb/lang_defs/es/sort-string-utf.chr | 42 ++++++++++++++++++++ 3 files changed, 44 insertions(+), 2 deletions(-) create mode 100644 etc/zebradb/lang_defs/es/sort-string-utf.chr diff --git a/Makefile.PL b/Makefile.PL index f306e2d866..0f09af394c 100644 --- a/Makefile.PL +++ b/Makefile.PL @@ -476,7 +476,7 @@ my %valid_config_values = ( 'AUTH_INDEX_MODE' => { 'grs1' => 1, 'dom' => 1 }, 'BIB_INDEX_MODE' => { 'grs1' => 1, 'dom' => 1 }, 'ZEBRA_MARC_FORMAT' => { 'marc21' => 1, 'normarc' => 1, 'unimarc' => 1 }, # FIXME should generate from contents of distributation - 'ZEBRA_LANGUAGE' => { 'en' => 1, 'fr' => 1, 'nb' => 1 }, # FIXME should generate from contents of distribution + 'ZEBRA_LANGUAGE' => { 'en' => 1, 'es' => 1, 'fr' => 1, 'nb' => 1 }, # FIXME should generate from contents of distribution 'ZEBRA_TOKENIZER' => { chr => 1, icu => 1 }, 'RUN_DATABASE_TESTS' => { 'yes' => 1, 'no' => 1 }, 'USE_MEMCACHED' => { 'yes' => 1, 'no' => 1 }, diff --git a/debian/scripts/koha-create b/debian/scripts/koha-create index 5bedbf894c..830c747076 100755 --- a/debian/scripts/koha-create +++ b/debian/scripts/koha-create @@ -21,7 +21,7 @@ set -e usage="Usage: $0 [--create-db|--request-db|--populate-db|--use-db] \ [--marcflavor marc21|normarc|unimarc] \ - [--zebralang en|nb|fr] \ + [--zebralang en|nb|fr|es] \ [--defaultsql /path/to/some.sql] \ [--configfile /path/to/config] [--passwdfile /path/to/passwd] \ [--database database] [--adminuser n] instancename" diff --git a/etc/zebradb/lang_defs/es/sort-string-utf.chr b/etc/zebradb/lang_defs/es/sort-string-utf.chr new file mode 100644 index 0000000000..aa295cbcae --- /dev/null +++ b/etc/zebradb/lang_defs/es/sort-string-utf.chr @@ -0,0 +1,42 @@ +# Koha's Zebra character map file for spanish +# +encoding utf-8 +# Character sort order definition +lowercase {0-9}{a-y}üzæäøöå +uppercase {0-9}{A-Y}ÜZÆÄØÖÅ + +# Breaking characters +space {\001-\040}!"#$%&'\()*+,-./:;<=>?@\[\\]^_`\{|}~ + +# Characters to be considered equivalent for searching purposes. +equivalent uü + +# Supplemental mappings +map (ä) a +map (æ) æ +map (ø) ø +map (å) a +map (ö) o +map (Ä) A +map (&Aelig;) Æ +map (Ø) Ø +map (Å) A +map (Ö) O + +map âàáäÂÀÂÄ a +map êèéëÊÈÉË e +map îïíÎÏ i +map ôöóÔÖ o +map ûùüÛÜÙ u +map çÇ c +map ñ n + +map (^El\s) @ +map (^En\s) @ +map (^La\s) @ +map (^Los\s) @ +map (^Las\s) @ +map (^Un\s) @ +map (^Unos\s) @ +map (^Una\s) @ +map (^Unas\s) @ -- 2.39.5