Import new data files from Unicode 9.0.0beta

* admin/unidata/UnicodeData.txt:
* admin/unidata/Blocks.txt:
* admin/unidata/BidiMirroring.txt:
* admin/unidata/BidiBrackets.txt: Update from Unicode 9.0.0beta.
* admin/unidata/unidata-gen.el (unidata-gen-files): Bind
'coding-system-for-read' to 'utf-8, as various Unicode data files
now actually use non-ASCII characters.
(unidata-setup-list, unidata-get-name): Support the new Tangut
Ideographs block.

* lisp/international/characters.el (standard-case-table): Add new
characters from Unicode 9.0.0.
(standard-category-table): Add Arabic block u+08A0..u+08FF.  Add
Cyrillic Extended-C block.
(char-width-table): Update ranges per Unicode 9.0.0.
* lisp/international/fontset.el (script-representative-chars): Add
new scripts defined by Unicode 9.0.0.
(otf-script-alist): Add new OTF script tags.
* lisp/international/mule-cmds.el (ucs-names): Update ranges per
Unicode 9.0.0 additions.

3 files changed, 141 insertions, 4 deletions

diff --git a/lisp/international/characters.el b/lisp/international/characters.el
index a43c0f68070..00f68f0fbbf 100644
--- a/lisp/international/characters.el
+++ b/lisp/international/characters.el
@@ -290,6 +290,7 @@ with L, LRE, or LRO Unicode bidi character type.")
     (map-charset-chars #'modify-category-entry (car charsets) ?b)
     (setq charsets (cdr charsets))))
 (modify-category-entry '(#x600 . #x6ff) ?b)
+(modify-category-entry '(#x8a0 . #x8ff) ?b)
 (modify-category-entry '(#xfb50 . #xfdff) ?b)
 (modify-category-entry '(#xfe70 . #xfefe) ?b)
 
@@ -700,6 +701,7 @@ with L, LRE, or LRO Unicode bidi character type.")
   (set-case-syntax-pair ?Ɜ ?ɜ tbl)
   (set-case-syntax-pair ?Ɡ ?ɡ tbl)
   (set-case-syntax-pair ?Ɬ ?ɬ tbl)
+  (set-case-syntax-pair ?Ɪ ?ɪ tbl)
   (set-case-syntax-pair ?Ʞ ?ʞ tbl)
   (set-case-syntax-pair ?Ʇ ?ʇ tbl)
   (set-case-syntax-pair ?Ʝ ?ʝ tbl)
@@ -810,6 +812,9 @@ with L, LRE, or LRO Unicode bidi character type.")
     (set-case-syntax-pair c (+ c #x1C60) tbl)
     (setq c (1+ c)))
 
+  ;; Cyrillic Extended-C
+  (modify-category-entry '(#x1C80 . #x1C8F) ?y)
+
   ;; general punctuation
   (setq c #x2000)
   (while (<= c #x200b)
@@ -903,6 +908,12 @@ with L, LRE, or LRO Unicode bidi character type.")
     (set-case-syntax-pair c (+ c 28) tbl)
     (setq c (1+ c)))
 
+  ;; Osage
+  (setq c #x104B0)
+  (while (<= c #x104D3)
+    (set-case-syntax-pair c (+ c 40) tbl)
+    (setq c (1+ c)))
+
   ;; Old Hungarian
   (setq c #x10c80)
   (while (<= c #x10cb2)
@@ -915,6 +926,12 @@ with L, LRE, or LRO Unicode bidi character type.")
     (set-case-syntax-pair c (+ c #x20) tbl)
     (setq c (1+ c)))
 
+  ;; Adlam
+  (setq c #x1e900)
+  (while (<= c #x1e921)
+    (set-case-syntax-pair c (+ c #x22) tbl)
+    (setq c (1+ c)))
+
   ;; Combining diacritics
   (modify-category-entry '(#x300 . #x362) ?^)
   ;; Combining marks
@@ -1183,7 +1200,40 @@ with L, LRE, or LRO Unicode bidi character type.")
 
 ;; 2: East Asian Wide and Full-width characters.
 (let ((l '((#x1100 . #x115F)
+           (#x231A . #x231B)
            (#x2329 . #x232A)
+           (#x23E9 . #x23EC)
+           (#x23F0 . #x23F0)
+           (#x23F3 . #x23F3)
+           (#x25FD . #x25FE)
+           (#x2614 . #x2615)
+           (#x2648 . #x2653)
+           (#x267F . #x267F)
+           (#x2693 . #x2693)
+           (#x26A1 . #x26A1)
+           (#x26AA . #x26AB)
+           (#x26BD . #x26BE)
+           (#x26C4 . #x26C5)
+           (#x26CE . #x26CE)
+           (#x26D4 . #x26D4)
+           (#x26EA . #x26EA)
+           (#x26F2 . #x26F3)
+           (#x26F5 . #x26F5)
+           (#x26FA . #x26FA)
+           (#x26FD . #x26FD)
+           (#x2705 . #x2705)
+           (#x270A . #x270B)
+           (#x2728 . #x2728)
+           (#x274C . #x274C)
+           (#x274E . #x274E)
+           (#x2753 . #x2755)
+           (#x2757 . #x2757)
+           (#x2795 . #x2797)
+           (#x27B0 . #x27B0)
+           (#x27BF . #x27BF)
+           (#x2B1B . #x2B1C)
+           (#x2B50 . #x2B50)
+           (#x2B55 . #x2B55)
            (#x2E80 . #x303E)
            (#x3040 . #xA4CF)
            (#xAC00 . #xD7A3)
@@ -1191,6 +1241,46 @@ with L, LRE, or LRO Unicode bidi character type.")
            (#xFE30 . #xFE6F)
            (#xFF01 . #xFF60)
            (#xFFE0 . #xFFE6)
+           (#x16FE0 . #x16FE0)
+           (#x17000 . #x187EC)
+           (#x18800 . #x18AF2)
+           (#x1F18E . #x1F18E)
+           (#x1F191 . #x1F19A)
+           (#x1F200 . #x1F202)
+           (#x1F210 . #x1F23B)
+           (#x1F300 . #x1F320)
+           (#x1F32D . #x1F335)
+           (#x1F337 . #x1F37C)
+           (#x1F37E . #x1F393)
+           (#x1F3A0 . #x1F3CA)
+           (#x1F3CF . #x1F3D3)
+           (#x1F3E0 . #x1F3F0)
+           (#x1F3F4 . #x1F3F4)
+           (#x1F3F8 . #x1F3FA)
+           (#x1F3FB . #x1F3FF)
+           (#x1F440 . #x1F440)
+           (#x1F442 . #x1F4FC)
+           (#x1F4FF . #x1F53D)
+           (#x1F54B . #x1F54E)
+           (#x1F550 . #x1F567)
+           (#x1F57A . #x1F57A)
+           (#x1F595 . #x1F596)
+           (#x1F5A4 . #x1F5A4)
+           (#x1F5FB . #x1F5FF)
+           (#x1F600 . #x1F64F)
+           (#x1F680 . #x1F6C5)
+           (#x1F6CC . #x1F6CC)
+           (#x1F6D0 . #x1F6D2)
+           (#x1F6EB . #x1F6EC)
+           (#x1F6F4 . #x1F6F6)
+           (#x1F910 . #x1F91E)
+           (#x1F920 . #x1F927)
+           (#x1F930 . #x1F930)
+           (#x1F933 . #x1F93E)
+           (#x1F940 . #x1F94B)
+           (#x1F950 . #x1F95E)
+           (#x1F980 . #x1F991)
+           (#x1F9C0 . #x1F9C0)
            (#x20000 . #x2FFFF)
            (#x30000 . #x3FFFF))))
   (dolist (elt l)
diff --git a/lisp/international/fontset.el b/lisp/international/fontset.el
index 2ecfa7e53af..90905a2ade9 100644
--- a/lisp/international/fontset.el
+++ b/lisp/international/fontset.el
@@ -205,6 +205,7 @@
         (deseret #x10400)
         (shavian #x10450)
         (osmanya #x10480)
+        (osage #x104B0)
         (elbasan #x10500)
         (caucasian-albanian #x10530)
         (linear-a #x10600)
@@ -220,17 +221,22 @@
         (khojki #x11200)
         (khudawadi #x112B0)
         (grantha #x11305)
+        (newa #x11400)
         (tirhuta #x11481)
         (siddham #x11580)
         (modi #x11600)
         (takri #x11680)
         (warang-citi #x118A1)
         (pau-cin-hau #x11AC0)
+        (bhaiksuki #x11C00)
+        (marchen #x11C72)
         (cuneiform #x12000)
         (cuneiform-numbers-and-punctuation #x12400)
         (mro #x16A40)
         (bassa-vah #x16AD0)
         (pahawh-hmong #x16B11)
+        (tangut #x17000)
+        (tangut-components #x18800)
         (duployan-shorthand #x1BC20)
         (byzantine-musical-symbol #x1D000)
         (musical-symbol #x1D100)
@@ -238,31 +244,38 @@
         (tai-xuan-jing-symbol #x1D300)
         (counting-rod-numeral #x1D360)
         (mende-kikakui #x1E810)
+        (adlam #x1E900)
         (mahjong-tile #x1F000)
         (domino-tile #x1F030)))
 
 (defvar otf-script-alist)
 
-;; The below was synchronized with the latest Jan 3, 2013 version of
+;; The below was synchronized with the latest Feb 25, 2016 version of
 ;; https://www.microsoft.com/typography/otspec/scripttags.htm.
 (setq otf-script-alist
-      '((arab . arabic)
+      '((adlm . adlam)
+        (ahom . ahom)
+        (hluw . anatolian)
+        (arab . arabic)
         (armi . aramaic)
         (armn . armenian)
         (avst . avestan)
         (bali . balinese)
         (bamu . bamum)
+        (bass . bassa-vah)
         (batk . batak)
         (bng2 . bengali)
         (beng . bengali)
+        (bhks . bhaiksuki)
         (bopo . bopomofo)
-        (brai . braille)
         (brah . brahmi)
+        (brai . braille)
         (bugi . buginese)
         (buhd . buhid)
         (byzm . byzantine-musical-symbol)
         (cans . canadian-aboriginal)
         (cari . carian)
+        (aghb . caucasian-albanian)
         (cakm . chakma)
         (cham . cham)
         (cher . cherokee)
@@ -273,11 +286,14 @@
         (dsrt . deseret)
         (deva . devanagari)
         (dev2 . devanagari)
+        (dupl . duployan-shorthand)
         (egyp . egyptian)
+        (elba . elbasan)
         (ethi . ethiopic)
         (geor . georgian)
         (glag . glagolitic)
         (goth . gothic)
+        (gran . grantha)
         (grek . greek)
         (gujr . gujarati)
         (gjr2 . gujarati)
@@ -287,6 +303,7 @@
         (hang . hangul)
         (jamo . hangul)
         (hano . hanunoo)
+        (hatr . hatran)
         (hebr . hebrew)
         (phli . inscriptional-pahlavi)
         (prti . inscriptional-parthian)
@@ -298,43 +315,67 @@
         (kali . kayah-li)
         (khar . kharoshthi)
         (khmr . khmer)
+        (khoj . khojki)
+        (sind . khudawadi)
         (lao\  . lao)
         (latn . latin)
         (lepc . lepcha)
         (limb . limbu)
+        (lina . linear_a)
         (linb . linear_b)
         (lisu . lisu)
         (lyci . lycian)
         (lydi . lydian)
+        (mahj . mahajani)
+        (marc . marchen)
         (mlym . malayalam)
         (mlm2 . malayalam)
         (mand . mandaic)
+        (mani . manichaean)
         (math . mathematical)
         (mtei . meetei-mayek)
+        (mend . mende-kikakui)
         (merc . meroitic)
         (mero . meroitic)
+        (plrd . miao)
+        (modi . modi)
         (mong . mongolian)
+        (mroo . mro)
+        (mult . multani)
         (musc . musical-symbol)
         (mym2 . burmese)
         (mymr . burmese)
+        (nbat . nabataean)
+        (newa . newa)
         (nko\  . nko)
         (ogam . ogham)
         (olck . ol-chiki)
         (ital . old_italic)
         (xpeo . old_persian)
+        (narb . old-north-arabian)
+        (perm . old-permic)
         (sarb . old-south-arabian)
         (orkh . old-turkic)
         (orya . oriya)
         (ory2 . oriya)
+        (osge . osage)
         (osma . osmanya)
+        (hmng . pahawh-hmong)
+        (palm . palmyrene)
+        (pauc . pau-cin-hau)
         (phag . phags-pa)
+        (phli . inscriptional-pahlavi)
         (phnx . phoenician)
+        (phlp . psalter-pahlavi)
+        (prti . inscriptional-parthian)
         (rjng . rejang)
         (runr . runic)
         (samr . samaritan)
         (saur . saurashtra)
         (shrd . sharada)
         (shaw . shavian)
+        (sidd . siddham)
+        (sgnw . sutton-sign-writing)
         (sinh . sinhala)
         (sora . sora-sompeng)
         (sund . sundanese)
@@ -349,14 +390,17 @@
         (takr . takri)
         (taml . tamil)
         (tml2 . tamil)
+        (tang . tangut)
         (telu . telugu)
         (tel2 . telugu)
         (thaa . thaana)
         (thai . thai)
         (tibt . tibetan)
         (tfng . tifinagh)
+        (tirh . tirhuta)
         (ugar . ugaritic)
         (vai\  . vai)
+        (wara . warang-citi)
         (yi\ \   . yi)))
 
 ;; Set standard fontname specification of characters in the default
diff --git a/lisp/international/mule-cmds.el b/lisp/international/mule-cmds.el
index dc9699099e8..dbf12247fc6 100644
--- a/lisp/international/mule-cmds.el
+++ b/lisp/international/mule-cmds.el
@@ -2939,7 +2939,10 @@ on encoding."
                (#x14400 . #x14646)
                ;; (#x14647 . #x167FF) unused
                (#x16800 . #x16F9F)
-               ;; (#x16FA0 . #x1AFFF) unused
+               (#x16FE0 . #x16FE0)
+               ;; (#x17000 . #x187FF) Tangut Ideographs
+               ;; (#x18800 . #x18AFF) Tangut Components
+               ;; (#x18B00 . #x1AFFF) unused
                (#x1B000 . #x1B0FF)
                ;; (#x1B100 . #x1BBFF) unused
                (#x1BC00 . #x1BCAF)