Support hex-string input and output for type BYTEA.

Both hex format and the traditional "escape" format are automatically
handled on input.  The output format is selected by the new GUC variable
bytea_output.

As committed, bytea_output defaults to HEX, which is an *incompatible
change*.  We will keep it this way for awhile for testing purposes, but
should consider whether to switch to the more backwards-compatible
default of ESCAPE before 8.5 is released.

Peter Eisentraut

1 files changed, 55 insertions, 19 deletions

diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index b9b54e6db63..c524454432e 100644
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.171 2009/06/11 14:49:04 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.172 2009/08/04 16:08:36 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -24,10 +24,14 @@
 #include "parser/scansup.h"
 #include "regex/regex.h"
 #include "utils/builtins.h"
+#include "utils/bytea.h"
 #include "utils/lsyscache.h"
 #include "utils/pg_locale.h"
 
 
+/* GUC variable */
+int		bytea_output = BYTEA_OUTPUT_HEX;
+
 typedef struct varlena unknown;
 
 typedef struct
@@ -186,10 +190,24 @@ byteain(PG_FUNCTION_ARGS)
 	char	   *inputText = PG_GETARG_CSTRING(0);
 	char	   *tp;
 	char	   *rp;
-	int byte;
+	int			bc;
 	bytea	   *result;
 
-	for (byte = 0, tp = inputText; *tp != '\0'; byte ++)
+	/* Recognize hex input */
+	if (inputText[0] == '\\' && inputText[1] == 'x')
+	{
+		size_t len = strlen(inputText);
+
+		bc = (len - 2)/2 + VARHDRSZ;		/* maximum possible length */
+		result = palloc(bc);
+		bc = hex_decode(inputText + 2, len - 2, VARDATA(result));
+		SET_VARSIZE(result, bc + VARHDRSZ);	/* actual length */
+
+		PG_RETURN_BYTEA_P(result);
+	}
+
+	/* Else, it's the traditional escaped style */
+	for (bc = 0, tp = inputText; *tp != '\0'; bc++)
 	{
 		if (tp[0] != '\\')
 			tp++;
@@ -204,7 +222,7 @@ byteain(PG_FUNCTION_ARGS)
 		else
 		{
 			/*
-			 * one backslash, not followed by 0 or ### valid octal
+			 * one backslash, not followed by another or ### valid octal
 			 */
 			ereport(ERROR,
 					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
@@ -212,10 +230,10 @@ byteain(PG_FUNCTION_ARGS)
 		}
 	}
 
-	byte	  +=VARHDRSZ;
+	bc += VARHDRSZ;
 
-	result = (bytea *) palloc(byte);
-	SET_VARSIZE(result, byte);
+	result = (bytea *) palloc(bc);
+	SET_VARSIZE(result, bc);
 
 	tp = inputText;
 	rp = VARDATA(result);
@@ -228,11 +246,11 @@ byteain(PG_FUNCTION_ARGS)
 				 (tp[2] >= '0' && tp[2] <= '7') &&
 				 (tp[3] >= '0' && tp[3] <= '7'))
 		{
-			byte = VAL(tp[1]);
-			byte	 <<=3;
-			byte	  +=VAL(tp[2]);
-			byte	 <<=3;
-			*rp++ = byte +VAL(tp[3]);
+			bc = VAL(tp[1]);
+			bc <<= 3;
+			bc += VAL(tp[2]);
+			bc <<= 3;
+			*rp++ = bc + VAL(tp[3]);
 
 			tp += 4;
 		}
@@ -259,21 +277,30 @@ byteain(PG_FUNCTION_ARGS)
 /*
  *		byteaout		- converts to printable representation of byte array
  *
- *		Non-printable characters are inserted as '\nnn' (octal) and '\' as
- *		'\\'.
- *
- *		NULL vlena should be an error--returning string with NULL for now.
+ *		In the traditional escaped format, non-printable characters are
+ *		printed as '\nnn' (octal) and '\' as '\\'.
  */
 Datum
 byteaout(PG_FUNCTION_ARGS)
 {
 	bytea	   *vlena = PG_GETARG_BYTEA_PP(0);
 	char	   *result;
-	char	   *vp;
 	char	   *rp;
-	int			val;			/* holds unprintable chars */
-	int			i;
+
+	if (bytea_output == BYTEA_OUTPUT_HEX)
+	{
+		/* Print hex format */
+		rp = result = palloc(VARSIZE_ANY_EXHDR(vlena) * 2 + 2 + 1);
+		*rp++ = '\\';
+		*rp++ = 'x';
+		rp += hex_encode(VARDATA_ANY(vlena), VARSIZE_ANY_EXHDR(vlena), rp);
+	}
+	else if (bytea_output == BYTEA_OUTPUT_ESCAPE)
+	{
+	/* Print traditional escaped format */
+	char	   *vp;
 	int			len;
+	int			i;
 
 	len = 1;					/* empty string has 1 char */
 	vp = VARDATA_ANY(vlena);
@@ -297,6 +324,8 @@ byteaout(PG_FUNCTION_ARGS)
 		}
 		else if ((unsigned char) *vp < 0x20 || (unsigned char) *vp > 0x7e)
 		{
+			int			val;			/* holds unprintable chars */
+
 			val = *vp;
 			rp[0] = '\\';
 			rp[3] = DIG(val & 07);
@@ -309,6 +338,13 @@ byteaout(PG_FUNCTION_ARGS)
 		else
 			*rp++ = *vp;
 	}
+	}
+	else
+	{
+		elog(ERROR, "unrecognized bytea_output setting: %d",
+			 bytea_output);
+		rp = result = NULL;		/* keep compiler quiet */
+	}
 	*rp = '\0';
 	PG_RETURN_CSTRING(result);
 }