(read_escape): Provide a Unicode character escape syntax; \u followed by

exactly four or \U followed by exactly eight hex digits in a comment or
string is read as a Unicode character with that code point.

1 files changed, 49 insertions, 0 deletions

diff --git a/src/lread.c b/src/lread.c
index 31f974d9bc0..a0d4ad825dd 100644
--- a/src/lread.c
+++ b/src/lread.c
@@ -1764,6 +1764,9 @@ read_escape (readcharfun, stringp, byterep)
      int *byterep;
 {
   register int c = READCHAR;
+  /* \u allows up to four hex digits, \U up to eight. Default to the
+     behaviour for \u, and change this value in the case that \U is seen. */
+  int unicode_hex_count = 4;
 
   *byterep = 0;
 
@@ -1928,6 +1931,52 @@ read_escape (readcharfun, stringp, byterep)
         return i;
       }
 
+    case 'U':
+      /* Post-Unicode-2.0: Up to eight hex chars.  */
+      unicode_hex_count = 8;
+    case 'u':
+
+      /* A Unicode escape. We only permit them in strings and characters,
+         not arbitrarily in the source code, as in some other languages.  */
+      {
+        int i = 0;
+        int count = 0;
+        Lisp_Object lisp_char;
+        struct gcpro gcpro1;
+
+        while (++count <= unicode_hex_count)
+          {
+            c = READCHAR;
+            /* isdigit(), isalpha() may be locale-specific, which we don't
+               want. */
+            if      (c >= '0' && c <= '9')  i = (i << 4) + (c - '0');
+            else if (c >= 'a' && c <= 'f')  i = (i << 4) + (c - 'a') + 10;
+            else if (c >= 'A' && c <= 'F')  i = (i << 4) + (c - 'A') + 10;
+            else
+              {
+                error ("Non-hex digit used for Unicode escape");
+                break;
+              }
+          }
+
+        GCPRO1 (readcharfun);
+        lisp_char = call2(intern("decode-char"), intern("ucs"),
+                          make_number(i));
+        UNGCPRO;
+
+        if (EQ(Qnil, lisp_char))
+          {
+            /* This is ugly and horrible and trashes the user's data.  */
+            XSETFASTINT (i, MAKE_CHAR (charset_katakana_jisx0201,
+                                       34 + 128, 46 + 128));
+            return i;
+          }
+        else
+          {
+            return XFASTINT (lisp_char);
+          }
+      }
+
     default:
       if (BASE_LEADING_CODE_P (c))
         c = read_multibyte (c, readcharfun);