From f6d208d6e51810c73f0e02c477984a6b44627f11 Mon Sep 17 00:00:00 2001
From: Simon Riggs
Date: Fri, 15 May 2015 14:37:10 -0400
Subject: TABLESAMPLE, SQL Standard and extensible

Add a TABLESAMPLE clause to SELECT statements that allows
user to specify random BERNOULLI sampling or block level
SYSTEM sampling. Implementation allows for extensible
sampling functions to be written, using a standard API.
Basic version follows SQLStandard exactly. Usable
concrete use cases for the sampling API follow in later
commits.

Petr Jelinek

Reviewed by Michael Paquier and Simon Riggs
---
 src/include/access/heapam.h      |  4 +++
 src/include/access/relscan.h     |  1 +
 src/include/access/tablesample.h | 60 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 65 insertions(+)
 create mode 100644 src/include/access/tablesample.h

(limited to 'src/include/access')

diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h
index 49c8ca4d66e..eec7c95b218 100644
--- a/src/include/access/heapam.h
+++ b/src/include/access/heapam.h
@@ -114,8 +114,12 @@ extern HeapScanDesc heap_beginscan_strat(Relation relation, Snapshot snapshot,
 					 bool allow_strat, bool allow_sync);
 extern HeapScanDesc heap_beginscan_bm(Relation relation, Snapshot snapshot,
 				  int nkeys, ScanKey key);
+extern HeapScanDesc heap_beginscan_sampling(Relation relation,
+						Snapshot snapshot, int nkeys, ScanKey key,
+						bool allow_strat, bool allow_pagemode);
 extern void heap_setscanlimits(HeapScanDesc scan, BlockNumber startBlk,
 		   BlockNumber endBlk);
+extern void heapgetpage(HeapScanDesc scan, BlockNumber page);
 extern void heap_rescan(HeapScanDesc scan, ScanKey key);
 extern void heap_endscan(HeapScanDesc scan);
 extern HeapTuple heap_getnext(HeapScanDesc scan, ScanDirection direction);
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index 5a0d724aca5..1b9b2993957 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -29,6 +29,7 @@ typedef struct HeapScanDescData
 	int			rs_nkeys;		/* number of scan keys */
 	ScanKey		rs_key;			/* array of scan key descriptors */
 	bool		rs_bitmapscan;	/* true if this is really a bitmap scan */
+	bool		rs_samplescan;	/* true if this is really a sample scan */
 	bool		rs_pageatatime; /* verify visibility page-at-a-time? */
 	bool		rs_allow_strat; /* allow or disallow use of access strategy */
 	bool		rs_allow_sync;	/* allow or disallow use of syncscan */
diff --git a/src/include/access/tablesample.h b/src/include/access/tablesample.h
new file mode 100644
index 00000000000..222fa8d5561
--- /dev/null
+++ b/src/include/access/tablesample.h
@@ -0,0 +1,60 @@
+/*-------------------------------------------------------------------------
+ *
+ * tablesample.h
+ *        Public header file for TABLESAMPLE clause interface
+ *
+ *
+ * Portions Copyright (c) 1996-2015, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/access/tablesample.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef TABLESAMPLE_H
+#define TABLESAMPLE_H
+
+#include "access/relscan.h"
+#include "executor/executor.h"
+
+typedef struct TableSampleDesc {
+	HeapScanDesc	heapScan;
+	TupleDesc		tupDesc;	/* Mostly useful for tsmexaminetuple */
+
+	void		   *tsmdata;	/* private method data */
+
+	/* These point to he function of the TABLESAMPLE Method. */
+	FmgrInfo		tsminit;
+	FmgrInfo		tsmnextblock;
+	FmgrInfo		tsmnexttuple;
+	FmgrInfo		tsmexaminetuple;
+	FmgrInfo		tsmreset;
+	FmgrInfo		tsmend;
+} TableSampleDesc;
+
+
+extern TableSampleDesc *tablesample_init(SampleScanState *scanstate,
+										 TableSampleClause *tablesample);
+extern HeapTuple tablesample_getnext(TableSampleDesc *desc);
+extern void tablesample_reset(TableSampleDesc *desc);
+extern void tablesample_end(TableSampleDesc *desc);
+extern HeapTuple tablesample_source_getnext(TableSampleDesc *desc);
+extern HeapTuple tablesample_source_gettup(TableSampleDesc *desc, ItemPointer tid,
+										   bool *visible);
+
+extern Datum tsm_system_init(PG_FUNCTION_ARGS);
+extern Datum tsm_system_nextblock(PG_FUNCTION_ARGS);
+extern Datum tsm_system_nexttuple(PG_FUNCTION_ARGS);
+extern Datum tsm_system_end(PG_FUNCTION_ARGS);
+extern Datum tsm_system_reset(PG_FUNCTION_ARGS);
+extern Datum tsm_system_cost(PG_FUNCTION_ARGS);
+
+extern Datum tsm_bernoulli_init(PG_FUNCTION_ARGS);
+extern Datum tsm_bernoulli_nextblock(PG_FUNCTION_ARGS);
+extern Datum tsm_bernoulli_nexttuple(PG_FUNCTION_ARGS);
+extern Datum tsm_bernoulli_end(PG_FUNCTION_ARGS);
+extern Datum tsm_bernoulli_reset(PG_FUNCTION_ARGS);
+extern Datum tsm_bernoulli_cost(PG_FUNCTION_ARGS);
+
+
+#endif
-- 
cgit v1.2.3