compose: Update sequences from libX11 1.7.2wip/smcv/compose-files

This adds support for sequences like <Compose>,G,u -> capital G with
breve. Previously, only a capital U was accepted for E, G, I and O
(but a lower-case u was accepted for A and U for some reason).

Signed-off-by: Simon McVittie <smcv@debian.org>

5 files changed, 26 insertions, 13 deletions

diff --git a/gtk/compose/Compose.pre b/gtk/compose/Compose.pre
index 61d5c07a65..10613efa08 100644
--- a/gtk/compose/Compose.pre
+++ b/gtk/compose/Compose.pre
@@ -924,9 +924,11 @@ XCOMM Part 3
 <Multi_key> <e> <minus> 		: "ē"   U0113 # LATIN SMALL LETTER E WITH MACRON
 <dead_breve> <E>                 	: "Ĕ"   U0114 # LATIN CAPITAL LETTER E WITH BREVE
 <Multi_key> <U> <E>              	: "Ĕ"   U0114 # LATIN CAPITAL LETTER E WITH BREVE
+<Multi_key> <u> <E>              	: "Ĕ"   U0114 # LATIN CAPITAL LETTER E WITH BREVE
 <Multi_key> <b> <E>              	: "Ĕ"   U0114 # LATIN CAPITAL LETTER E WITH BREVE
 <dead_breve> <e>                 	: "ĕ"   U0115 # LATIN SMALL LETTER E WITH BREVE
 <Multi_key> <U> <e>              	: "ĕ"   U0115 # LATIN SMALL LETTER E WITH BREVE
+<Multi_key> <u> <e>              	: "ĕ"   U0115 # LATIN SMALL LETTER E WITH BREVE
 <Multi_key> <b> <e>              	: "ĕ"   U0115 # LATIN SMALL LETTER E WITH BREVE
 <dead_abovedot> <E>              	: "Ė"   U0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE
 <Multi_key> <period> <E>         	: "Ė"   U0116 # LATIN CAPITAL LETTER E WITH DOT ABOVE
@@ -960,14 +962,18 @@ XCOMM Part 3
 <Multi_key> <asciicircum> <g>    	: "ĝ"   U011D # LATIN SMALL LETTER G WITH CIRCUMFLEX
 <dead_breve> <G>                 	: "Ğ"   U011E # LATIN CAPITAL LETTER G WITH BREVE
 <Multi_key> <U> <G>              	: "Ğ"   U011E # LATIN CAPITAL LETTER G WITH BREVE
+<Multi_key> <u> <G>              	: "Ğ"   U011E # LATIN CAPITAL LETTER G WITH BREVE
 <Multi_key> <G> <U> 			: "Ğ"   U011E # LATIN CAPITAL LETTER G WITH BREVE
+<Multi_key> <G> <u> 			: "Ğ"   U011E # LATIN CAPITAL LETTER G WITH BREVE
 <Multi_key> <b> <G>              	: "Ğ"   U011E # LATIN CAPITAL LETTER G WITH BREVE
 <Multi_key> <breve> <G> 		: "Ğ"   U011E # LATIN CAPITAL LETTER G WITH BREVE
 <Multi_key> <G> <breve> 		: "Ğ"   U011E # LATIN CAPITAL LETTER G WITH BREVE
 <Multi_key> <G> <parenleft> 		: "Ğ"   U011E # LATIN CAPITAL LETTER G WITH BREVE
 <dead_breve> <g>                 	: "ğ"   U011F # LATIN SMALL LETTER G WITH BREVE
 <Multi_key> <U> <g>              	: "ğ"   U011F # LATIN SMALL LETTER G WITH BREVE
+<Multi_key> <u> <g>              	: "ğ"   U011F # LATIN SMALL LETTER G WITH BREVE
 <Multi_key> <g> <U> 			: "ğ"   U011F # LATIN SMALL LETTER G WITH BREVE
+<Multi_key> <g> <u> 			: "ğ"   U011F # LATIN SMALL LETTER G WITH BREVE
 <Multi_key> <b> <g>              	: "ğ"   U011F # LATIN SMALL LETTER G WITH BREVE
 <Multi_key> <breve> <g> 		: "ğ"   U011F # LATIN SMALL LETTER G WITH BREVE
 <Multi_key> <g> <breve> 		: "ğ"   U011F # LATIN SMALL LETTER G WITH BREVE
@@ -1016,9 +1022,11 @@ XCOMM Part 3
 <Multi_key> <i> <minus> 		: "ī"   U012B # LATIN SMALL LETTER I WITH MACRON
 <dead_breve> <I>                 	: "Ĭ"   U012C # LATIN CAPITAL LETTER I WITH BREVE
 <Multi_key> <U> <I>              	: "Ĭ"   U012C # LATIN CAPITAL LETTER I WITH BREVE
+<Multi_key> <u> <I>              	: "Ĭ"   U012C # LATIN CAPITAL LETTER I WITH BREVE
 <Multi_key> <b> <I>              	: "Ĭ"   U012C # LATIN CAPITAL LETTER I WITH BREVE
 <dead_breve> <i>                 	: "ĭ"   U012D # LATIN SMALL LETTER I WITH BREVE
 <Multi_key> <U> <i>              	: "ĭ"   U012D # LATIN SMALL LETTER I WITH BREVE
+<Multi_key> <u> <i>              	: "ĭ"   U012D # LATIN SMALL LETTER I WITH BREVE
 <Multi_key> <b> <i>              	: "ĭ"   U012D # LATIN SMALL LETTER I WITH BREVE
 <dead_ogonek> <I>                	: "Į"   U012E # LATIN CAPITAL LETTER I WITH OGONEK
 <Multi_key> <semicolon> <I>      	: "Į"   U012E # LATIN CAPITAL LETTER I WITH OGONEK
@@ -1123,9 +1131,11 @@ XCOMM Part 3
 <Multi_key> <o> <minus>         	: "ō"   U014D # LATIN SMALL LETTER O WITH MACRON
 <dead_breve> <O>                 	: "Ŏ"   U014E # LATIN CAPITAL LETTER O WITH BREVE
 <Multi_key> <U> <O>              	: "Ŏ"   U014E # LATIN CAPITAL LETTER O WITH BREVE
+<Multi_key> <u> <O>              	: "Ŏ"   U014E # LATIN CAPITAL LETTER O WITH BREVE
 <Multi_key> <b> <O>              	: "Ŏ"   U014E # LATIN CAPITAL LETTER O WITH BREVE
 <dead_breve> <o>                 	: "ŏ"   U014F # LATIN SMALL LETTER O WITH BREVE
 <Multi_key> <U> <o>              	: "ŏ"   U014F # LATIN SMALL LETTER O WITH BREVE
+<Multi_key> <u> <o>              	: "ŏ"   U014F # LATIN SMALL LETTER O WITH BREVE
 <Multi_key> <b> <o>              	: "ŏ"   U014F # LATIN SMALL LETTER O WITH BREVE
 <dead_doubleacute> <O>           	: "Ő"   U0150 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
 <Multi_key> <equal> <O>          	: "Ő"   U0150 # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
@@ -6019,8 +6029,7 @@ XCOMM Characters from "Miscellaneous Technical"
 <Multi_key> <minus> <U2191>                     : "⍏"   U234f   # - ↑ APL FUNCTIONAL SYMBOL UPWARDS VANE
 <Multi_key> <U2191> <U2395>                     : "⍐"   U2350   # ↑ ⎕ APL FUNCTIONAL SYMBOL QUAD UPWARDS ARROW
 <Multi_key> <U2395> <U2191>                     : "⍐"   U2350   # ⎕ ↑ APL FUNCTIONAL SYMBOL QUAD UPWARDS ARROW
-XCOMM I cannot get anything to work with <macron>. Given that no extant APLs use ⍑ I will just leave the lines
-XCOMM in place.
+XCOMM The next two somehow don't work.  However, no extant APL uses "⍑".
 <Multi_key> <macron> <U22a4>                    : "⍑"   U2351   # ¯ ⊤ APL FUNCTIONAL SYMBOL UP TACK OVERBAR
 <Multi_key> <U22a4> <macron>                    : "⍑"   U2351   # ⊤ ¯ APL FUNCTIONAL SYMBOL UP TACK OVERBAR
 <Multi_key> <U2207> <bar>                       : "⍒"   U2352   # ∇ | APL FUNCTIONAL SYMBOL DEL STILE
@@ -6035,10 +6044,7 @@ XCOMM in place.
 <Multi_key> <minus> <U2193>                     : "⍖"   U2356   # - ↓ APL FUNCTIONAL SYMBOL DOWNWARDS VANE
 <Multi_key> <U2193> <U2395>                     : "⍗"   U2357   # ↓ ⎕ APL FUNCTIONAL SYMBOL QUAD DOWNWARDS ARROW
 <Multi_key> <U2395> <U2193>                     : "⍗"   U2357   # ⎕ ↓ APL FUNCTIONAL SYMBOL QUAD DOWNWARDS ARROW
-XCOMM This line clashes with the <apostrophe> <underscore> <E> (and similar) that appear to be there to provide
-XCOMM a work around for the problems with <macron>. Or to cope with keyboards that do not have <macron> (more likely).
-XCOMM All APL keyboards have <macron>, it is used as the -ve sign for numbers.
-XCOMM I do not know of an extant APL using ⍘
+XCOMM The <apostrophe> <underscore> is used elsewhere.  However, no extant APL uses "⍘".
 <Multi_key> <underscore> <apostrophe>           : "⍘"   U2358   # _ ' APL FUNCTIONAL SYMBOL QUOTE UNDERBAR
 <Multi_key> <U2206> <underscore>                : "⍙"   U2359   # ∆ _ APL FUNCTIONAL SYMBOL DELTA UNDERBAR
 <Multi_key> <underscore> <U2206>                : "⍙"   U2359   # _ ∆ APL FUNCTIONAL SYMBOL DELTA UNDERBAR
@@ -6079,10 +6085,7 @@ XCOMM I do not know of an extant APL using ⍘
 <Multi_key> <asciitilde> <0>                    : "⍬"   U236c   # ~ 0 APL FUNCTIONAL SYMBOL ZILDE
 <Multi_key> <bar> <asciitilde>                  : "⍭"   U236d   # | ~ APL FUNCTIONAL SYMBOL STILE TILDE
 <Multi_key> <asciitilde> <bar>                  : "⍭"   U236d   # ~ | APL FUNCTIONAL SYMBOL STILE TILDE
-XCOMM This line does not work. It clashes with
-XCOMM <underscore> <semicolon> <O> for Ǭ and
-XCOMM <underscore> <semicolon> <o> for ǭ.
-XCOMM Given that no extant APLs use ⍮ I will just leave the line in place.
+XCOMM The <underscore> <semicolon> is used elsewhere.  However, no extant APL uses "⍮".
 <Multi_key> <semicolon> <underscore>            : "⍮"   U236e   # ; _ APL FUNCTIONAL SYMBOL SEMICOLON UNDERBAR
 <Multi_key> <U2260> <U2395>                     : "⍯"   U236f   # ≠ ⎕ APL FUNCTIONAL SYMBOL QUAD NOT EQUAL
 <Multi_key> <U2395> <U2260>                     : "⍯"   U236f   # ⎕ ≠ APL FUNCTIONAL SYMBOL QUAD NOT EQUAL
diff --git a/gtk/compose/gtkcomposedata.h b/gtk/compose/gtkcomposedata.h
index 442696218c..09b0263a7f 100644
--- a/gtk/compose/gtkcomposedata.h
+++ b/gtk/compose/gtkcomposedata.h
@@ -3,7 +3,7 @@
 
 #define MAX_SEQ_LEN 5
 #define N_INDEX_SIZE 30
-#define DATA_SIZE 16447
+#define DATA_SIZE 16477
 #define N_CHARS 1241
 
 #endif
diff --git a/gtk/compose/sequences-big-endian b/gtk/compose/sequences-big-endian
index 516577970c..e8b971c317 100644
--- a/gtk/compose/sequences-big-endian
+++ b/gtk/compose/sequences-big-endian
diff --git a/gtk/compose/sequences-little-endian b/gtk/compose/sequences-little-endian
index 39984d4125..dad83a8cc6 100644
--- a/gtk/compose/sequences-little-endian
+++ b/gtk/compose/sequences-little-endian
diff --git a/testsuite/gtk/compose/system.expected b/testsuite/gtk/compose/system.expected
index c807827bbf..93c51ebb68 100644
--- a/testsuite/gtk/compose/system.expected
+++ b/testsuite/gtk/compose/system.expected
@@ -1,7 +1,7 @@
-# n_sequences: 4874
+# n_sequences: 4884
 # max_seq_len: 5
 # n_index_size: 30
-# data_size: 16447
+# data_size: 16477
 # n_chars: 1241
 <U7ae> <U7e9> : "ΐ" # U390
 <U7ae> <U7f5> : "ΰ" # U3b0
@@ -1959,6 +1959,7 @@
 <Uff20> <U47> <U2e> : "Ġ" # U120
 <Uff20> <U47> <U54> : ">" # U3e
 <Uff20> <U47> <U55> : "Ğ" # U11e
+<Uff20> <U47> <U75> : "Ğ" # U11e
 <Uff20> <U47> <U1a2> : "Ğ" # U11e
 <Uff20> <U48> <U2c> : "Ḩ" # U1e28
 <Uff20> <U49> <U22> : "Ï" # Ucf
@@ -2512,6 +2513,7 @@
 <Uff20> <U67> <U2e> : "ġ" # U121
 <Uff20> <U67> <U55> : "ğ" # U11f
 <Uff20> <U67> <U74> : ">" # U3e
+<Uff20> <U67> <U75> : "ğ" # U11f
 <Uff20> <U67> <U1a2> : "ğ" # U11f
 <Uff20> <U68> <U2c> : "ḩ" # U1e29
 <Uff20> <U69> <U22> : "ï" # Uef
@@ -2611,11 +2613,19 @@
 <Uff20> <U75> <U3b> : "ų" # U173
 <Uff20> <U75> <U3e> : "û" # Ufb
 <Uff20> <U75> <U41> : "Ă" # U102
+<Uff20> <U75> <U45> : "Ĕ" # U114
+<Uff20> <U75> <U47> : "Ğ" # U11e
+<Uff20> <U75> <U49> : "Ĭ" # U12c
+<Uff20> <U75> <U4f> : "Ŏ" # U14e
 <Uff20> <U75> <U55> : "Ŭ" # U16c
 <Uff20> <U75> <U5e> : "û" # Ufb
 <Uff20> <U75> <U5f> : "ū" # U16b
 <Uff20> <U75> <U60> : "ù" # Uf9
 <Uff20> <U75> <U61> : "ă" # U103
+<Uff20> <U75> <U65> : "ĕ" # U115
+<Uff20> <U75> <U67> : "ğ" # U11f
+<Uff20> <U75> <U69> : "ĭ" # U12d
+<Uff20> <U75> <U6f> : "ŏ" # U14f
 <Uff20> <U75> <U75> : "ŭ" # U16d
 <Uff20> <U75> <U7e> : "ũ" # U169
 <Uff20> <U75> <Ua8> : "ü" # Ufc