summaryrefslogtreecommitdiff
path: root/contrib/unaccent/unaccent.rules
diff options
context:
space:
mode:
authorTeodor Sigaev2015-09-04 09:51:53 +0000
committerTeodor Sigaev2015-09-04 09:51:53 +0000
commit1bbd52cb9a4aa61a7dd751f5d1f7b44650d6122a (patch)
treecb52d878702e901529ce383c60ded775c7c76435 /contrib/unaccent/unaccent.rules
parent4aec49899e5782247e134f94ce1c6ee926f88e1c (diff)
Make unaccent handle all diacritics known to Unicode, and expand ligatures correctly
Add Python script for buiding unaccent.rules from Unicode data. Don't backpatch because unaccent changes may require tsvector/index rebuild. Thomas Munro <[email protected]>
Diffstat (limited to 'contrib/unaccent/unaccent.rules')
-rw-r--r--contrib/unaccent/unaccent.rules358
1 files changed, 292 insertions, 66 deletions
diff --git a/contrib/unaccent/unaccent.rules b/contrib/unaccent/unaccent.rules
index cc2f7a65858..73c24a188ba 100644
--- a/contrib/unaccent/unaccent.rules
+++ b/contrib/unaccent/unaccent.rules
@@ -4,22 +4,59 @@
à A
Ä A
Å A
-Æ A
+Ç C
+È E
+É E
+Ê E
+Ë E
+Ì I
+Í I
+Î I
+Ï I
+Ñ N
+Ò O
+Ó O
+Ô O
+Õ O
+Ö O
+Ù U
+Ú U
+Û U
+Ü U
+Ý Y
à a
á a
â a
ã a
ä a
å a
-æ a
+ç c
+è e
+é e
+ê e
+ë e
+ì i
+í i
+î i
+ï i
+ñ n
+ò o
+ó o
+ô o
+õ o
+ö o
+ù u
+ú u
+û u
+ü u
+ý y
+ÿ y
Ā A
ā a
Ă A
ă a
Ą A
ą a
-Ç C
-ç c
Ć C
ć c
Ĉ C
@@ -30,16 +67,6 @@
č c
Ď D
ď d
-Đ D
-đ d
-È E
-É E
-Ê E
-Ë E
-è e
-é e
-ê e
-ë e
Ē E
ē e
Ĕ E
@@ -60,17 +87,7 @@
ģ g
Ĥ H
ĥ h
-Ħ H
-ħ h
Ĩ I
-Ì I
-Í I
-Î I
-Ï I
-ì i
-í i
-î i
-ï i
ĩ i
Ī I
ī i
@@ -79,62 +96,36 @@
Į I
į i
İ I
-ı i
-IJ I
-ij i
+IJ IJ
+ij ij
Ĵ J
ĵ j
Ķ K
ķ k
-ĸ k
Ĺ L
ĺ l
Ļ L
ļ l
Ľ L
ľ l
-Ŀ L
-ŀ l
-Ł L
-ł l
-Ñ N
-ñ n
Ń N
ń n
Ņ N
ņ n
Ň N
ň n
-ʼn n
-Ŋ N
-ŋ n
-Ò O
-Ó O
-Ô O
-Õ O
-Ö O
-ò o
-ó o
-ô o
-õ o
-ö o
Ō O
ō o
Ŏ O
ŏ o
Ő O
ő o
-Œ E
-œ e
-Ø O
-ø o
Ŕ R
ŕ r
Ŗ R
ŗ r
Ř R
ř r
-ß S
Ś S
ś s
Ŝ S
@@ -147,16 +138,6 @@
ţ t
Ť T
ť t
-Ŧ T
-ŧ t
-Ù U
-Ú U
-Û U
-Ü U
-ù u
-ú u
-û u
-ü u
Ũ U
ũ u
Ū U
@@ -171,9 +152,6 @@
ų u
Ŵ W
ŵ w
-Ý Y
-ý y
-ÿ y
Ŷ Y
ŷ y
Ÿ Y
@@ -183,5 +161,253 @@
ż z
Ž Z
ž z
-ё е
+Ơ O
+ơ o
+Ư U
+ư u
+DŽ DZ
+Dž Dz
+dž dz
+LJ LJ
+Lj Lj
+lj lj
+NJ NJ
+Nj Nj
+nj nj
+Ǎ A
+ǎ a
+Ǐ I
+ǐ i
+Ǒ O
+ǒ o
+Ǔ U
+ǔ u
+Ǧ G
+ǧ g
+Ǩ K
+ǩ k
+Ǫ O
+ǫ o
+ǰ j
+DZ DZ
+Dz Dz
+dz dz
+Ǵ G
+ǵ g
+Ǹ N
+ǹ n
+Ȁ A
+ȁ a
+Ȃ A
+ȃ a
+Ȅ E
+ȅ e
+Ȇ E
+ȇ e
+Ȉ I
+ȉ i
+Ȋ I
+ȋ i
+Ȍ O
+ȍ o
+Ȏ O
+ȏ o
+Ȑ R
+ȑ r
+Ȓ R
+ȓ r
+Ȕ U
+ȕ u
+Ȗ U
+ȗ u
+Ș S
+ș s
+Ț T
+ț t
+Ȟ H
+ȟ h
+Ȧ A
+ȧ a
+Ȩ E
+ȩ e
+Ȯ O
+ȯ o
+Ȳ Y
+ȳ y
+Ḁ A
+ḁ a
+Ḃ B
+ḃ b
+Ḅ B
+ḅ b
+Ḇ B
+ḇ b
+Ḋ D
+ḋ d
+Ḍ D
+ḍ d
+Ḏ D
+ḏ d
+Ḑ D
+ḑ d
+Ḓ D
+ḓ d
+Ḙ E
+ḙ e
+Ḛ E
+ḛ e
+Ḟ F
+ḟ f
+Ḡ G
+ḡ g
+Ḣ H
+ḣ h
+Ḥ H
+ḥ h
+Ḧ H
+ḧ h
+Ḩ H
+ḩ h
+Ḫ H
+ḫ h
+Ḭ I
+ḭ i
+Ḱ K
+ḱ k
+Ḳ K
+ḳ k
+Ḵ K
+ḵ k
+Ḷ L
+ḷ l
+Ḻ L
+ḻ l
+Ḽ L
+ḽ l
+Ḿ M
+ḿ m
+Ṁ M
+ṁ m
+Ṃ M
+ṃ m
+Ṅ N
+ṅ n
+Ṇ N
+ṇ n
+Ṉ N
+ṉ n
+Ṋ N
+ṋ n
+Ṕ P
+ṕ p
+Ṗ P
+ṗ p
+Ṙ R
+ṙ r
+Ṛ R
+ṛ r
+Ṟ R
+ṟ r
+Ṡ S
+ṡ s
+Ṣ S
+ṣ s
+Ṫ T
+ṫ t
+Ṭ T
+ṭ t
+Ṯ T
+ṯ t
+Ṱ T
+ṱ t
+Ṳ U
+ṳ u
+Ṵ U
+ṵ u
+Ṷ U
+ṷ u
+Ṽ V
+ṽ v
+Ṿ V
+ṿ v
+Ẁ W
+ẁ w
+Ẃ W
+ẃ w
+Ẅ W
+ẅ w
+Ẇ W
+ẇ w
+Ẉ W
+ẉ w
+Ẋ X
+ẋ x
+Ẍ X
+ẍ x
+Ẏ Y
+ẏ y
+Ẑ Z
+ẑ z
+Ẓ Z
+ẓ z
+Ẕ Z
+ẕ z
+ẖ h
+ẗ t
+ẘ w
+ẙ y
+Ạ A
+ạ a
+Ả A
+ả a
+Ẹ E
+ẹ e
+Ẻ E
+ẻ e
+Ẽ E
+ẽ e
+Ỉ I
+ỉ i
+Ị I
+ị i
+Ọ O
+ọ o
+Ỏ O
+ỏ o
+Ụ U
+ụ u
+Ủ U
+ủ u
+Ỳ Y
+ỳ y
+Ỵ Y
+ỵ y
+Ỷ Y
+ỷ y
+Ỹ Y
+ỹ y
+ff ff
+fi fi
+fl fl
+ffi ffi
+ffl ffl
+st st
+Ø O
+ø o
+Đ D
+đ d
+ı i
+Ħ H
+ħ h
+Ł L
+ł l
+ʼn 'n
+Ŧ T
+ŧ t
Ё Е
+ё е
+Æ AE
+ß ss
+æ ae
+Œ OE
+œ oe