X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=lib%2Funinorm%2Fdecomposition.c;h=af7b049cb80b47fa7e826a6a367ab0bed606dec4;hb=7ef852ba849ac1fc4bef6d48e47e2dd3c0914feb;hp=d581bde2e35a02000f2259d6684c18cf41f6b06a;hpb=2d20b7af060d159440ad0aad6738a8e9a2a7f07b;p=gnulib.git

diff --git a/lib/uninorm/decomposition.c b/lib/uninorm/decomposition.c
index d581bde2e..af7b049cb 100644
--- a/lib/uninorm/decomposition.c
+++ b/lib/uninorm/decomposition.c
@@ -1,5 +1,5 @@
 /* Decomposition of Unicode characters.
-   Copyright (C) 2009 Free Software Foundation, Inc.
+   Copyright (C) 2009-2011 Free Software Foundation, Inc.
    Written by Bruno Haible <bruno@clisp.org>, 2009.
 
    This program is free software: you can redistribute it and/or modify it
@@ -27,55 +27,76 @@ uc_decomposition (ucs4_t uc, int *decomp_tag, ucs4_t *decomposition)
 {
   if (uc >= 0xAC00 && uc < 0xD7A4)
     {
-      /* Hangul syllable.  See Unicode standard, chapter 3,
-	 section "Hangul Syllable Decomposition".  */
-      unsigned int t, v, l;
+      /* Hangul syllable.  See Unicode standard, chapter 3, section
+         "Hangul Syllable Decomposition",  See also the clarification at
+         <http://www.unicode.org/versions/Unicode5.1.0/>, section
+         "Clarification of Hangul Jamo Handling".  */
+      unsigned int t;
 
       uc -= 0xAC00;
       t = uc % 28;
-      uc = uc / 28;
-      v = uc % 21;
-      l = uc / 21;
 
       *decomp_tag = UC_DECOMP_CANONICAL;
-      decomposition[0] = 0x1100 + l;
-      decomposition[1] = 0x1161 + v;
       if (t == 0)
-	return 2;
+        {
+          unsigned int v, l;
+
+          uc = uc / 28;
+          v = uc % 21;
+          l = uc / 21;
+
+          decomposition[0] = 0x1100 + l;
+          decomposition[1] = 0x1161 + v;
+          return 2;
+        }
       else
-	{
-	  decomposition[2] = 0x11A7 + t;
-	  return 3;
-	}
+        {
+#if 1 /* Return the pairwise decomposition, not the full decomposition.  */
+          decomposition[0] = 0xAC00 + uc - t; /* = 0xAC00 + (l * 21 + v) * 28; */
+          decomposition[1] = 0x11A7 + t;
+          return 2;
+#else
+          unsigned int v, l;
+
+          uc = uc / 28;
+          v = uc % 21;
+          l = uc / 21;
+
+          decomposition[0] = 0x1100 + l;
+          decomposition[1] = 0x1161 + v;
+          decomposition[2] = 0x11A7 + t;
+          return 3;
+#endif
+        }
     }
   else if (uc < 0x110000)
     {
       unsigned short entry = decomp_index (uc);
       if (entry != (unsigned short)(-1))
-	{
-	  const unsigned char *p;
-	  unsigned int element;
-	  unsigned int length;
+        {
+          const unsigned char *p;
+          unsigned int element;
+          unsigned int length;
 
-	  p = &gl_uninorm_decomp_chars_table[3 * (entry & 0x7FFF)];
-	  element = (p[0] << 16) | (p[1] << 8) | p[2];
-	  /* The first element has 5 bits for the decomposition type.  */
-	  *decomp_tag = (element >> 18) & 0x1f;
-	  length = 1;
-	  for (;;)
-	    {
-	      /* Every element has an 18 bits wide Unicode code point.  */
-	      *decomposition = element & 0x3ffff;
-	      /* Bit 23 tells whether there are more elements,  */
-	      if ((element & (1 << 23)) == 0)
-		break;
-	      p += 3;
-	      element = (p[0] << 16) | (p[1] << 8) | p[2];
-	      decomposition++;
-	      length++;
-	    }
-	  return length;
-	}
+          p = &gl_uninorm_decomp_chars_table[3 * (entry & 0x7FFF)];
+          element = (p[0] << 16) | (p[1] << 8) | p[2];
+          /* The first element has 5 bits for the decomposition type.  */
+          *decomp_tag = (element >> 18) & 0x1f;
+          length = 1;
+          for (;;)
+            {
+              /* Every element has an 18 bits wide Unicode code point.  */
+              *decomposition = element & 0x3ffff;
+              /* Bit 23 tells whether there are more elements,  */
+              if ((element & (1 << 23)) == 0)
+                break;
+              p += 3;
+              element = (p[0] << 16) | (p[1] << 8) | p[2];
+              decomposition++;
+              length++;
+            }
+          return length;
+        }
     }
   return -1;
 }