Surrogate pair support for U& string and identifier syntax

This is mainly to make the functionality consistent with the proposed \u
escape syntax.

diff --git a/doc/src/sgml/syntax.sgml b/doc/src/sgml/syntax.sgml
index c2dd31b98d37b591ff64774aeab6ed6d8fd46b8c..c805e2e7141b9572945ddf5ddb87e268e83bb105 100644 (file)
--- a/doc/src/sgml/syntax.sgml
+++ b/doc/src/sgml/syntax.sgml
@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/syntax.sgml,v 1.134 2009/08/27 20:08:02 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/syntax.sgml,v 1.135 2009/09/21 22:22:07 petere Exp $ -->
 
 <chapter id="sql-syntax">
  <title>SQL Syntax</title>
@@ -238,6 +238,10 @@ U&amp;"d!0061t!+000061" UESCAPE '!'
     The Unicode escape syntax works only when the server encoding is
     UTF8.  When other server encodings are used, only code points in
     the ASCII range (up to <literal>\007F</literal>) can be specified.
+    Both the 4-digit and the 6-digit form can be used to specify
+    UTF-16 surrogate pairs to compose characters with code points
+    larger than <literal>\FFFF</literal> (although the availability of
+    the 6-digit form technically makes this unnecessary).
    </para>
 
    <para>
@@ -497,6 +501,10 @@ U&amp;'d!0061t!+000061' UESCAPE '!'
      UTF8.  When other server encodings are used, only code points in
      the ASCII range (up to <literal>\007F</literal>) can be
      specified.
+     Both the 4-digit and the 6-digit form can be used to specify
+     UTF-16 surrogate pairs to compose characters with code points
+     larger than <literal>\FFFF</literal> (although the availability
+     of the 6-digit form technically makes this unnecessary).
     </para>
 
     <para>

diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l
index a5ed54792b66ae3c0f83915c4a08854bf4487450..d40bd9dd97e3b351de4c4148a9e022033890ca6b 100644 (file)
--- a/src/backend/parser/scan.l
+++ b/src/backend/parser/scan.l
@@ -24,7 +24,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *   $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.157 2009/07/14 20:24:10 tgl Exp $
+ *   $PostgreSQL: pgsql/src/backend/parser/scan.l,v 1.158 2009/09/21 22:22:07 petere Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -1097,11 +1097,30 @@ check_unicode_value(pg_wchar c, char *loc, base_yyscan_t yyscanner)
    }
 }
 
+static bool
+is_utf16_surrogate_first(pg_wchar c)
+{
+   return (c >= 0xD800 && c <= 0xDBFF);
+}
+
+static bool
+is_utf16_surrogate_second(pg_wchar c)
+{
+   return (c >= 0xDC00 && c <= 0xDFFF);
+}
+
+static pg_wchar
+surrogate_pair_to_codepoint(pg_wchar first, pg_wchar second)
+{
+   return ((first & 0x3FF) << 10) + 0x10000 + (second & 0x3FF);
+}
+
 static char *
 litbuf_udeescape(unsigned char escape, base_yyscan_t yyscanner)
 {
    char *new;
    char *litbuf, *in, *out;
+   pg_wchar pair_first = 0;
 
    if (isxdigit(escape)
        || escape == '+'
@@ -1131,6 +1150,11 @@ litbuf_udeescape(unsigned char escape, base_yyscan_t yyscanner)
        {
            if (in[1] == escape)
            {
+               if (pair_first)
+               {
+                   ADVANCE_YYLLOC(in - litbuf + 3);   /* 3 for U&" */
+                   yyerror("invalid Unicode surrogate pair");
+               }
                *out++ = escape;
                in += 2;
            }
@@ -1138,9 +1162,27 @@ litbuf_udeescape(unsigned char escape, base_yyscan_t yyscanner)
            {
                pg_wchar unicode = hexval(in[1]) * 16*16*16 + hexval(in[2]) * 16*16 + hexval(in[3]) * 16 + hexval(in[4]);
                check_unicode_value(unicode, in, yyscanner);
-               unicode_to_utf8(unicode, (unsigned char *) out);
+               if (pair_first)
+               {
+                   if (is_utf16_surrogate_second(unicode))
+                   {
+                       unicode = surrogate_pair_to_codepoint(pair_first, unicode);
+                       pair_first = 0;
+                   }
+                   else
+                   {
+                       ADVANCE_YYLLOC(in - litbuf + 3);   /* 3 for U&" */
+                       yyerror("invalid Unicode surrogate pair");
+                   }
+               }
+               if (is_utf16_surrogate_first(unicode))
+                   pair_first = unicode;
+               else
+               {
+                   unicode_to_utf8(unicode, (unsigned char *) out);
+                   out += pg_mblen(out);
+               }
                in += 5;
-               out += pg_mblen(out);
            }
            else if (in[1] == '+'
                     && isxdigit(in[2]) && isxdigit(in[3])
@@ -1150,9 +1192,27 @@ litbuf_udeescape(unsigned char escape, base_yyscan_t yyscanner)
                pg_wchar unicode = hexval(in[2]) * 16*16*16*16*16 + hexval(in[3]) * 16*16*16*16 + hexval(in[4]) * 16*16*16
                                    + hexval(in[5]) * 16*16 + hexval(in[6]) * 16 + hexval(in[7]);
                check_unicode_value(unicode, in, yyscanner);
-               unicode_to_utf8(unicode, (unsigned char *) out);
+               if (pair_first)
+               {
+                   if (is_utf16_surrogate_second(unicode))
+                   {
+                       unicode = surrogate_pair_to_codepoint(pair_first, unicode);
+                       pair_first = 0;
+                   }
+                   else
+                   {
+                       ADVANCE_YYLLOC(in - litbuf + 3);   /* 3 for U&" */
+                       yyerror("invalid Unicode surrogate pair");
+                   }
+               }
+               if (is_utf16_surrogate_first(unicode))
+                   pair_first = unicode;
+               else
+               {
+                   unicode_to_utf8(unicode, (unsigned char *) out);
+                   out += pg_mblen(out);
+               }
                in += 8;
-               out += pg_mblen(out);
            }
            else
            {
@@ -1161,7 +1221,14 @@ litbuf_udeescape(unsigned char escape, base_yyscan_t yyscanner)
            }
        }
        else
+       {
+           if (pair_first)
+           {
+               ADVANCE_YYLLOC(in - litbuf + 3);   /* 3 for U&" */
+               yyerror("invalid Unicode surrogate pair");
+           }
            *out++ = *in++;
+       }
    }
 
    *out = '\0';