compressed-datum-slicing-20190313b.patch

diff --git a/src/backend/access/heap/tuptoaster.c b/src/backend/access/heap/tuptoaster.c
index cd921a4600..46b7d7a2a6 100644
--- a/src/backend/access/heap/tuptoaster.c
+++ b/src/backend/access/heap/tuptoaster.c
@@ -75,6 +75,7 @@ static struct varlena *toast_fetch_datum(struct varlena *attr);
 static struct varlena *toast_fetch_datum_slice(struct varlena *attr,
 						int32 sliceoffset, int32 length);
 static struct varlena *toast_decompress_datum(struct varlena *attr);
+static struct varlena *toast_decompress_datum_slice(struct varlena *attr, int32 slicelength);
 static int toast_open_indexes(Relation toastrel,
 				   LOCKMODE lock,
 				   Relation **toastidxs,
@@ -301,7 +302,11 @@ heap_tuple_untoast_attr_slice(struct varlena *attr,
 	{
 		struct varlena *tmp = preslice;
 
-		preslice = toast_decompress_datum(tmp);
+		/* Decompress enough to encompass the slice and the offset */
+		if (slicelength > 0 && sliceoffset >= 0)
+			preslice = toast_decompress_datum_slice(tmp, slicelength + sliceoffset);
+		else
+			preslice = toast_decompress_datum(tmp);
 
 		if (tmp != attr)
 			pfree(tmp);
@@ -2279,6 +2284,36 @@ toast_decompress_datum(struct varlena *attr)
 }
 
 
+/* ----------
+ * toast_decompress_datum_slice -
+ *
+ * Decompress the front of a compressed version of a varlena datum.
+ * offset handling happens in heap_tuple_untoast_attr_slice.
+ * Here we just decompress a slice from the front.
+ */
+static struct varlena *
+toast_decompress_datum_slice(struct varlena *attr, int32 slicelength)
+{
+	struct varlena *result;
+	int32 rawsize;
+
+	Assert(VARATT_IS_COMPRESSED(attr));
+
+	result = (struct varlena *) palloc(slicelength + VARHDRSZ);
+	SET_VARSIZE(result, slicelength + VARHDRSZ);
+
+	rawsize = pglz_decompress_checked(TOAST_COMPRESS_RAWDATA(attr),
+						VARSIZE(attr) - TOAST_COMPRESS_HDRSZ,
+						VARDATA(result),
+						slicelength, false);
+	if (rawsize < 0)
+		elog(ERROR, "compressed data is corrupted");
+
+	SET_VARSIZE(result, rawsize + VARHDRSZ);
+	return result;
+}
+
+
 /* ----------
  * toast_open_indexes
  *
diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index 39c394331b..d89c0b7201 100644
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -1835,7 +1835,7 @@ text_starts_with(PG_FUNCTION_ARGS)
 		result = false;
 	else
 	{
-		text	   *targ1 = DatumGetTextPP(arg1);
+		text	   *targ1 = text_substring(arg1, 1, len2, false);
 		text	   *targ2 = DatumGetTextPP(arg2);
 
 		result = (memcmp(VARDATA_ANY(targ1), VARDATA_ANY(targ2),
@@ -5237,17 +5237,22 @@ text_concat_ws(PG_FUNCTION_ARGS)
 Datum
 text_left(PG_FUNCTION_ARGS)
 {
-	text	   *str = PG_GETARG_TEXT_PP(0);
-	const char *p = VARDATA_ANY(str);
-	int			len = VARSIZE_ANY_EXHDR(str);
-	int			n = PG_GETARG_INT32(1);
-	int			rlen;
+	int		n = PG_GETARG_INT32(1);
 
 	if (n < 0)
+	{
+		text	   *str = PG_GETARG_TEXT_PP(0);
+		const char *p = VARDATA_ANY(str);
+		int			len = VARSIZE_ANY_EXHDR(str);
+		int			rlen;
 		n = pg_mbstrlen_with_len(p, len) + n;
-	rlen = pg_mbcharcliplen(p, len, n);
-
-	PG_RETURN_TEXT_P(cstring_to_text_with_len(p, rlen));
+		rlen = pg_mbcharcliplen(p, len, n);
+		PG_RETURN_TEXT_P(cstring_to_text_with_len(p, rlen));
+	}
+	else
+	{
+		PG_RETURN_TEXT_P(text_substring(PG_GETARG_DATUM(0), 1, n, false));
+	}
 }
 
 /*
diff --git a/src/common/pg_lzcompress.c b/src/common/pg_lzcompress.c
index f15725a57c..05b2b3d5d1 100644
--- a/src/common/pg_lzcompress.c
+++ b/src/common/pg_lzcompress.c
@@ -681,6 +681,22 @@ pglz_compress(const char *source, int32 slen, char *dest,
 int32
 pglz_decompress(const char *source, int32 slen, char *dest,
 				int32 rawsize)
+{
+	return pglz_decompress_checked(source, slen, dest, rawsize, true);
+}
+
+/* ----------
+ * pglz_decompress_checked -
+ *
+ *		Decompresses source into dest. Returns the number of bytes
+ *		decompressed in the destination buffer, and *optionally*
+ *      checks that both the source and dest buffers have been
+ *      fully read and written to, respectively.
+ * ----------
+ */
+int32
+pglz_decompress_checked(const char *source, int32 slen, char *dest,
+						 int32 rawsize, bool check_buffers)
 {
 	const unsigned char *sp;
 	const unsigned char *srcend;
@@ -701,8 +717,9 @@ pglz_decompress(const char *source, int32 slen, char *dest,
 		unsigned char ctrl = *sp++;
 		int			ctrlc;
 
-		for (ctrlc = 0; ctrlc < 8 && sp < srcend; ctrlc++)
+		for (ctrlc = 0; ctrlc < 8 && sp < srcend && dp < destend; ctrlc++)
 		{
+
 			if (ctrl & 1)
 			{
 				/*
@@ -721,25 +738,13 @@ pglz_decompress(const char *source, int32 slen, char *dest,
 				if (len == 18)
 					len += *sp++;
 
-				/*
-				 * Check for output buffer overrun, to ensure we don't clobber
-				 * memory in case of corrupt input.  Note: we must advance dp
-				 * here to ensure the error is detected below the loop.  We
-				 * don't simply put the elog inside the loop since that will
-				 * probably interfere with optimization.
-				 */
-				if (dp + len > destend)
-				{
-					dp += len;
-					break;
-				}
-
 				/*
 				 * Now we copy the bytes specified by the tag from OUTPUT to
 				 * OUTPUT. It is dangerous and platform dependent to use
 				 * memcpy() here, because the copied areas could overlap
 				 * extremely!
 				 */
+				len = Min(len, destend - dp);
 				while (len--)
 				{
 					*dp = dp[-off];
@@ -752,9 +757,6 @@ pglz_decompress(const char *source, int32 slen, char *dest,
 				 * An unset control bit means LITERAL BYTE. So we just copy
 				 * one from INPUT to OUTPUT.
 				 */
-				if (dp >= destend)	/* check for buffer overrun */
-					break;		/* do not clobber memory */
-
 				*dp++ = *sp++;
 			}
 
@@ -767,12 +769,15 @@ pglz_decompress(const char *source, int32 slen, char *dest,
 
 	/*
 	 * Check we decompressed the right amount.
+	 * If we are slicing, then we won't necessarily
+	 * be at the end of the source or dest buffers
+	 * when we hit a stop, so we don't test them.
 	 */
-	if (dp != destend || sp != srcend)
+	if (check_buffers && (dp != destend || sp != srcend))
 		return -1;
 
 	/*
 	 * That's it.
 	 */
-	return rawsize;
+	return (char*)dp - dest;
 }
diff --git a/src/include/common/pg_lzcompress.h b/src/include/common/pg_lzcompress.h
index d4b2e8a53c..63fab7b642 100644
--- a/src/include/common/pg_lzcompress.h
+++ b/src/include/common/pg_lzcompress.h
@@ -87,5 +87,7 @@ extern int32 pglz_compress(const char *source, int32 slen, char *dest,
 			  const PGLZ_Strategy *strategy);
 extern int32 pglz_decompress(const char *source, int32 slen, char *dest,
 				int32 rawsize);
+extern int32 pglz_decompress_checked(const char *source, int32 slen, char *dest,
+				int32 rawsize, bool check_buffers);
 
 #endif							/* _PG_LZCOMPRESS_H_ */