Bug 2629: add char-with-stroke support to word-phrase-utf.chr

This patch adds diacritic search support for the following characters-with-stroke:
a,b,c,d,e,h,l,r,t,u,y,z

Handles both uppercase and lowercase mappings.

Also corrects a note in word-phrase-utf.chr:  the 'equivalent' command is NOT for searching,
but rather for sorting.  See Zebra manual: http://www.indexdata.com/zebra/doc/character-map-files.html,
near the bottom.

Signed-off-by: Katrin Fischer <Katrin.Fischer.83@web.de>
Some notes:
- Copied the file to my koha-dev folder and reindexed
- Tried some simple searches like: Süden and Suden, schon und schön with success
- Added some of the new characters to a record and tried search with and
  without diacritics (ɨƗʉⱥɆɌ and iiuaer) with success.

Signed-off-by: Katrin Fischer <Katrin.Fischer.83@web.de>
Signed-off-by: Chris Cormack <chrisc@catalyst.net.nz>

diff --git a/etc/zebradb/etc/word-phrase-utf.chr b/etc/zebradb/etc/word-phrase-utf.chr
index b41b298..e0e2297 100644 (file)
--- a/etc/zebradb/etc/word-phrase-utf.chr
+++ b/etc/zebradb/etc/word-phrase-utf.chr
@@ -11,7 +11,7 @@ uppercase {0-9}{A-Z}
 # Breaking characters
 space {\001-\040}!"#$%&'\()*+,-./:;<=>?@\[\\]^_`\{|}~’
 
-# Characters to be considered equivalent for searching purposes
+# Characters to be considered equivalent for sorting purposes
 equivalent aáàãåâăąȧǎȁȃ
 equivalent ӕä(ae)
 equivalent ā(aa)
@@ -56,6 +56,8 @@ map ȁ                        a
 map Ȁ                 a
 map ȃ                 a
 map Ȃ                 a
+map ⱥ                        a
+map Ⱥ                 a
 # AE 
 map ӕ                 (ae)
 map Ӕ                 (ae)
@@ -84,6 +86,8 @@ map ȉ                        i
 map Ȉ                 i
 map ȋ                 i
 map Ȋ                 i
+map ɨ                 i
+map Ɨ                 i
 # U  
 map ū                 u
 map Ū                 u
@@ -109,6 +113,8 @@ map ȕ                      u
 map Ȕ                 u
 map ȗ                 u
 map Ȗ                 u
+map ʉ                 u
+map Ʉ                 u
 # E  
 map ê                 e
 map Ê                 e
@@ -134,6 +140,8 @@ map ȅ                      e
 map Ȅ                 e
 map ȇ                 e
 map Ȇ                 e
+map ɇ                 e
+map Ɇ                 e
 # O  
 map ô                 o
 map Ô                 o
@@ -175,6 +183,8 @@ map Ṝ                     r
 map ř                 r
 map Ř                 r
 map ṟ                        r
+map ɍ                 r
+map Ɍ                 r
 # L 
 map ḷ                        l
 map Ḷ                        l
@@ -182,6 +192,9 @@ map ḹ                     l
 map Ḹ                        l
 map ḻ                        l
 map Ḻ                        l
+map ł                 l
+map Ł                 l
+
 # N  
 map ṅ                        n
 map Ṅ                        n
@@ -198,9 +211,13 @@ map Ṇ                    n
 # T  
 map ṭ                        t
 map Ṭ                        t
+map ŧ                 t
+map Ŧ                 t
 # D 
 map ḍ                        d
 map Ḍ                        d
+map đ                 d
+map Đ                 d
 # S  
 map ś                 s
 map Ś                 s
@@ -221,6 +238,8 @@ map Ṃ                     m
 map ḥ                        h
 map Ḥ                        h
 map ẖ                        h
+map ħ                 h
+map Ħ                 h
 # Z 
 map ź                 z
 map Ź                 z
@@ -228,6 +247,8 @@ map ẓ                     z
 map Ẓ                        z
 map ż                 z
 map Ż                 z
+map ƶ                 z
+map Ƶ                 z
 #C 
 map ç                 c
 map Ç                 c
@@ -235,6 +256,8 @@ map ć                      c
 map Ć                 c
 map č                 c
 map Č                 c
+map ȼ                 c
+map Ȼ                 c
 # G 
 map ǥ                 g
 map Ǥ                 g
@@ -250,6 +273,8 @@ map Ḵ                     k
 # Y  
 map ý                 y
 map Ý                 y
+map ɏ                 y
+map Ɏ                 y
 
 # mapping blank string
 map (^impr\s)       @