Fix bug #16043 with crashes when displaying new bidi control characters.

 src/bidi.c (bidi_get_type, bidi_get_category): Handle the isolate
 directional control characters.  Update type and category
 determination according to the UBA from Unicode v6.3.
 (bidi_category_t): New category EXPLICIT_FORMATTING.
 src/dispextern.h (bidi_type_t): Update to include new bidirectional
 properties introduced with Unicode v6.3.

 admin/unidata/unidata-gen.el (unidata-prop-alist): Update bidi-class
 to include the new isolate-related classes introduced with Unicode
 v6.3.
 (unidata-encode-val): Accept an additional optional argument, a
 warning message to emit when UnicodeData.txt defines bidi-class
 values that are not in unidata-prop-alist.  Add a comment
 explaining what should maintainers do if/when such a warning ever
 appears.
 (unidata-gen-table): Call unidata-encode-val with 3rd arg non-nil
 when generating uni-bidi.el.

3 files changed, 48 insertions, 24 deletions

diff --git a/src/ChangeLog b/src/ChangeLog
index a877bc885e7..4c7b3015877 100644
--- a/src/ChangeLog
+++ b/src/ChangeLog
@@ -1,3 +1,13 @@
+2013-12-04  Eli Zaretskii  <eliz@gnu.org>
+
+        * bidi.c (bidi_get_type, bidi_get_category): Handle the isolate
+        directional control characters.  Update type and category
+        determination according to the UBA from Unicode v6.3.
+        (bidi_category_t): New category EXPLICIT_FORMATTING.
+
+        * dispextern.h (bidi_type_t): Update to include new bidirectional
+        properties introduced with Unicode v6.3.  (Bug#16043)
+
 2013-12-04  Martin Rudalics  <rudalics@gmx.at>
 
         * xterm.c (XTflash): Fix coordinate of bottom area to flash
diff --git a/src/bidi.c b/src/bidi.c
index 98c3c17b78f..d3a617651f6 100644
--- a/src/bidi.c
+++ b/src/bidi.c
@@ -76,7 +76,8 @@ typedef enum {
   UNKNOWN_BC,
   NEUTRAL,
   WEAK,
-  STRONG
+  STRONG,
+  EXPLICIT_FORMATTING
 } bidi_category_t;
 
 /* UAX#9 says to search only for L, AL, or R types of characters, and
@@ -115,13 +116,9 @@ bidi_get_type (int ch, bidi_dir_t override)
   if (default_type == UNKNOWN_BT)
     emacs_abort ();
 
-  if (override == NEUTRAL_DIR)
-    return default_type;
-
   switch (default_type)
     {
-      /* Although UAX#9 does not tell, it doesn't make sense to
-         override NEUTRAL_B and LRM/RLM characters.  */
+      case WEAK_BN:
       case NEUTRAL_B:
       case LRE:
       case LRO:
@@ -129,20 +126,20 @@ bidi_get_type (int ch, bidi_dir_t override)
       case RLO:
       case PDF:
         return default_type;
+        /* FIXME: The isolate controls are treated as BN until we add
+           support for UBA v6.3.  */
+      case LRI:
+      case RLI:
+      case FSI:
+      case PDI:
+        return WEAK_BN;
       default:
-        switch (ch)
-          {
-            case LRM_CHAR:
-            case RLM_CHAR:
-              return default_type;
-            default:
-              if (override == L2R) /* X6 */
-                return STRONG_L;
-              else if (override == R2L)
-                return STRONG_R;
-              else
-                emacs_abort (); /* can't happen: handled above */
-          }
+        if (override == L2R)
+          return STRONG_L;
+        else if (override == R2L)
+          return STRONG_R;
+        else
+          return default_type;
     }
 }
 
@@ -163,12 +160,7 @@ bidi_get_category (bidi_type_t type)
       case STRONG_L:
       case STRONG_R:
       case STRONG_AL:
-      case LRE:
-      case LRO:
-      case RLE:
-      case RLO:
         return STRONG;
-      case PDF:         /* ??? really?? */
       case WEAK_EN:
       case WEAK_ES:
       case WEAK_ET:
@@ -176,12 +168,30 @@ bidi_get_category (bidi_type_t type)
       case WEAK_CS:
       case WEAK_NSM:
       case WEAK_BN:
+        /* FIXME */
+      case LRI:
+      case RLI:
+      case FSI:
+      case PDI:
         return WEAK;
       case NEUTRAL_B:
       case NEUTRAL_S:
       case NEUTRAL_WS:
       case NEUTRAL_ON:
         return NEUTRAL;
+      case LRE:
+      case LRO:
+      case RLE:
+      case RLO:
+      case PDF:
+#if 0
+        /* FIXME: This awaits implementation of isolate support.  */
+      case LRI:
+      case RLI:
+      case FSI:
+      case PDI:
+#endif
+        return EXPLICIT_FORMATTING;
       default:
         emacs_abort ();
     }
diff --git a/src/dispextern.h b/src/dispextern.h
index 2ce0a8f4c99..7de4edf2196 100644
--- a/src/dispextern.h
+++ b/src/dispextern.h
@@ -1895,6 +1895,10 @@ typedef enum {
   RLE,          /* right-to-left embedding */
   RLO,          /* right-to-left override */
   PDF,          /* pop directional format */
+  LRI,          /* left-to-right isolate */
+  RLI,          /* right-to-left isolate */
+  FSI,          /* first strong isolate */
+  PDI,          /* pop directional isolate */
   WEAK_ES,      /* european number separator */
   WEAK_ET,      /* european number terminator */
   WEAK_CS,      /* common separator */