Added a configuration parameter to set specific unaccenting/lowercasing for some characters to be handled differently than would result from using the Unicode database. Exemple: "a with ring above" could be set to be preserved by a Swedish locutor

tests/config/recoll.conf

@@ -15,6 +15,8 @@ daemSkippedPaths =  \
 
 defaultcharset = iso-8859-1
 
+unac_except_trans = åå Åå ää Ää öö Öö
+
 [/home/dockes/projets/fulltext/testrecoll/special]
 defaultcharset = iso-8859-1
 [/home/dockes/projets/fulltext/testrecoll/txt]

tests/lyx/lyx.sh

@@ -8,7 +8,9 @@ initvariables $0
 (
 recollq 'Bienvenue Dans Univers De Lyx' 
 recollq 'Welcome To Lyx' 
-recollq 'Udvozli Ont A LyX' 
+recollq 'LyX rendkivul jol dokumentalt'
+# cant use this one because o-diaeresis is in the swedish unacex
+# recollq 'Udvozli Ont A LyX' 
 ) 2> $mystderr | egrep -v '^Recoll query: ' > $mystdout
 
 diff -w ${myname}.txt $mystdout > $mydiffs 2>&1

tests/unacex/unacex.sh

@@ -0,0 +1,20 @@
+#!/bin/sh
+
+topdir=`dirname $0`/..
+. $topdir/shared.sh
+
+initvariables $0
+
+# We need an utf-8 locale for the 1st command to properly read its argument
+export LANG=fr_FR.UTF-8
+
+(
+# Should succeed
+recollq '"strippes: UNACEXååääöö"' 
+# Should fail
+recollq '"strippes: UNACEXaaaaoo"'
+)  2> $mystderr | egrep -v '^Recoll query: ' > $mystdout
+
+diff -w ${myname}.txt $mystdout > $mydiffs 2>&1
+
+checkresult

tests/unacex/unacex.txt

@@ -0,0 +1,3 @@
+1 results
+text/html	[file:///home/dockes/projets/fulltext/testrecoll/unacex/swedishchars.html]	[Some chars]	293	bytes	
+0 results