Import wiredtiger: 7ecb3f4a13db0f7a5476012dab95f9369649f863 from branch mongodb-master

ref: 9443b440b5..7ecb3f4a13
for: 5.3.0

WT-8289       Provide a means to get K/V pair on duplicate key error

5 files changed, 130 insertions, 50 deletions

diff --git a/src/third_party/wiredtiger/import.data b/src/third_party/wiredtiger/import.data
index b5fa1ae4190..0d4327401f9 100644
--- a/src/third_party/wiredtiger/import.data
+++ b/src/third_party/wiredtiger/import.data
@@ -2,5 +2,5 @@
     "vendor": "wiredtiger",
     "github": "wiredtiger/wiredtiger.git",
     "branch": "mongodb-master",
-    "commit": "9443b440b5788d34f376939230fb22f241ce7ff3"
+    "commit": "7ecb3f4a13db0f7a5476012dab95f9369649f863"
 }
diff --git a/src/third_party/wiredtiger/src/btree/bt_cursor.c b/src/third_party/wiredtiger/src/btree/bt_cursor.c
index 68fa71f7679..60a567b56a8 100644
--- a/src/third_party/wiredtiger/src/btree/bt_cursor.c
+++ b/src/third_party/wiredtiger/src/btree/bt_cursor.c
@@ -898,11 +898,9 @@ retry:
          * If not overwriting, fail if the key exists, else insert the key/value pair.
          */
         if (!F_ISSET(cursor, WT_CURSTD_OVERWRITE) && cbt->compare == 0) {
-            WT_WITH_UPDATE_VALUE_SKIP_BUF(
-              ret = __wt_cursor_valid(cbt, cbt->tmp, WT_RECNO_OOB, &valid));
-            WT_ERR(ret);
+            WT_ERR(__wt_cursor_valid(cbt, cbt->tmp, WT_RECNO_OOB, &valid));
             if (valid)
-                WT_ERR(WT_DUPLICATE_KEY);
+                goto duplicate;
         }
 
         ret = __cursor_row_modify(cbt, &cbt->iface.value, WT_UPDATE_STANDARD);
@@ -926,13 +924,11 @@ retry:
          */
         if (!F_ISSET(cursor, WT_CURSTD_OVERWRITE)) {
             if (cbt->compare == 0) {
-                WT_WITH_UPDATE_VALUE_SKIP_BUF(
-                  ret = __wt_cursor_valid(cbt, NULL, cbt->recno, &valid));
-                WT_ERR(ret);
+                WT_ERR(__wt_cursor_valid(cbt, NULL, cbt->recno, &valid));
                 if (valid)
-                    WT_ERR(WT_DUPLICATE_KEY);
+                    goto duplicate;
             } else if (__cursor_fix_implicit(btree, cbt))
-                WT_ERR(WT_DUPLICATE_KEY);
+                goto duplicate;
         }
 
         WT_ERR(__cursor_col_modify(cbt, &cbt->iface.value, WT_UPDATE_STANDARD));
@@ -944,6 +940,18 @@ err:
         goto retry;
     }
 
+    /* Return the found value for any duplicate key. */
+    if (0) {
+duplicate:
+        if (F_ISSET(cursor, WT_CURSTD_DUP_NO_VALUE))
+            ret = WT_DUPLICATE_KEY;
+        else {
+            __wt_value_return(cbt, cbt->upd_value);
+            if ((ret = __cursor_localvalue(cursor)) == 0)
+                ret = WT_DUPLICATE_KEY;
+        }
+    }
+
     /* Insert doesn't maintain a position across calls, clear resources. */
     if (ret == 0) {
 done:
@@ -952,7 +960,7 @@ done:
             F_SET(cursor, WT_CURSTD_KEY_EXT);
     }
     WT_TRET(__cursor_reset(cbt));
-    if (ret != 0)
+    if (ret != 0 && ret != WT_DUPLICATE_KEY)
         __cursor_state_restore(cursor, &state);
 
     return (ret);
diff --git a/src/third_party/wiredtiger/src/cursor/cur_table.c b/src/third_party/wiredtiger/src/cursor/cur_table.c
index e95c1a5e4ae..c456ae06888 100644
--- a/src/third_party/wiredtiger/src/cursor/cur_table.c
+++ b/src/third_party/wiredtiger/src/cursor/cur_table.c
@@ -505,29 +505,31 @@ __curtable_insert(WT_CURSOR *cursor)
     JOINABLE_CURSOR_UPDATE_API_CALL(cursor, session, insert);
     WT_ERR(__curtable_open_indices(ctable));
 
+    cp = ctable->cg_cursors;
+    primary = *cp++;
+
     /*
      * Split out the first insert, it may be allocating a recno.
      *
      * If the table has indices, we also need to know whether this record is replacing an existing
      * record so that the existing index entries can be removed. We discover if this is an overwrite
      * by configuring the primary cursor for no-overwrite, and checking if the insert detects a
-     * duplicate key.
+     * duplicate key. By default, when insert finds a duplicate, it returns the value it found. We
+     * don't want that value to overwrite our own, override that behavior.
      */
-    cp = ctable->cg_cursors;
-    primary = *cp++;
-
     flag_orig = F_MASK(primary, WT_CURSTD_OVERWRITE);
-    if (ctable->table->nindices > 0)
+    if (ctable->table->nindices > 0) {
         F_CLR(primary, WT_CURSTD_OVERWRITE);
+        F_SET(primary, WT_CURSTD_DUP_NO_VALUE);
+    }
     ret = primary->insert(primary);
 
     /*
-     * !!!
-     * WT_CURSOR.insert clears the set internally/externally flags
-     * but doesn't touch the items. We could make a copy each time
-     * for overwrite cursors, but for now we just reset the flags.
+     * WT_CURSOR.insert clears the set internally/externally flags but doesn't touch the items. We
+     * could make a copy each time for overwrite cursors, but for now we just reset the flags.
      */
     F_SET(primary, flag_orig | WT_CURSTD_KEY_EXT | WT_CURSTD_VALUE_EXT);
+    F_CLR(primary, WT_CURSTD_DUP_NO_VALUE);
 
     if (ret == WT_DUPLICATE_KEY && F_ISSET(cursor, WT_CURSTD_OVERWRITE)) {
         WT_ERR(__curtable_update(cursor));
diff --git a/src/third_party/wiredtiger/src/include/wiredtiger.in b/src/third_party/wiredtiger/src/include/wiredtiger.in
index e91773e72d5..29db28a0b69 100644
--- a/src/third_party/wiredtiger/src/include/wiredtiger.in
+++ b/src/third_party/wiredtiger/src/include/wiredtiger.in
@@ -446,7 +446,9 @@ struct __wt_cursor {
 	 *
 	 * If the cursor was not configured with "overwrite=true", both the key
 	 * and value must be set and the record must not already exist; the
-	 * record will be inserted.
+	 * record will be inserted. If the record already exists, the
+	 * ::WT_DUPLICATE_KEY error is returned and the value found in the tree
+	 * can be retrieved using WT_CURSOR::get_value.
 	 *
 	 * @snippet ex_all.c Insert a new record and fail if the record exists
 	 *
@@ -464,7 +466,8 @@ struct __wt_cursor {
 	 * with "append=true", the cursor ends with no key set and a subsequent
 	 * call to the WT_CURSOR::get_key method will fail. The cursor ends with
 	 * no value set and a subsequent call to the WT_CURSOR::get_value method
-	 * will fail.
+	 * will fail, except for the ::WT_DUPLICATE_KEY error return, in which
+	 * case the value currently stored for the key can be retrieved.
 	 *
 	 * Inserting a new record after the current maximum record in a
 	 * fixed-length bit field column-store (that is, a store with an
@@ -709,34 +712,35 @@ struct __wt_cursor {
 	const char *internal_uri;
 
 /* AUTOMATIC FLAG VALUE GENERATION START 0 */
-#define	WT_CURSTD_APPEND		0x0000001u
-#define	WT_CURSTD_BULK			0x0000002u
-#define	WT_CURSTD_CACHEABLE		0x0000004u
-#define	WT_CURSTD_CACHED		0x0000008u
-#define	WT_CURSTD_DEAD			0x0000010u
-#define	WT_CURSTD_DEBUG_COPY_KEY	0x0000020u
-#define	WT_CURSTD_DEBUG_COPY_VALUE	0x0000040u
-#define	WT_CURSTD_DEBUG_RESET_EVICT	0x0000080u
-#define	WT_CURSTD_DUMP_HEX		0x0000100u
-#define	WT_CURSTD_DUMP_JSON		0x0000200u
-#define	WT_CURSTD_DUMP_PRETTY		0x0000400u
-#define	WT_CURSTD_DUMP_PRINT		0x0000800u
-#define	WT_CURSTD_HS_READ_ALL	0x0001000u
-#define	WT_CURSTD_HS_READ_COMMITTED	0x0002000u
-#define	WT_CURSTD_IGNORE_TOMBSTONE	0x0004000u
-#define	WT_CURSTD_JOINED		0x0008000u
-#define	WT_CURSTD_KEY_EXT		0x0010000u	/* Key points out of tree. */
-#define	WT_CURSTD_KEY_INT		0x0020000u	/* Key points into tree. */
-#define	WT_CURSTD_KEY_ONLY		0x0040000u
-#define	WT_CURSTD_META_INUSE		0x0080000u
-#define	WT_CURSTD_OPEN			0x0100000u
-#define	WT_CURSTD_OVERWRITE		0x0200000u
-#define	WT_CURSTD_PREFIX_SEARCH		0x0400000u
-#define	WT_CURSTD_RAW			0x0800000u
-#define	WT_CURSTD_RAW_SEARCH		0x1000000u
-#define	WT_CURSTD_VALUE_EXT		0x2000000u	/* Value points out of tree. */
-#define	WT_CURSTD_VALUE_INT		0x4000000u	/* Value points into tree. */
-#define WT_CURSTD_VERSION_CURSOR 0x8000000u /* Version cursor. */
+#define	WT_CURSTD_APPEND		0x00000001u
+#define	WT_CURSTD_BULK			0x00000002u
+#define	WT_CURSTD_CACHEABLE		0x00000004u
+#define	WT_CURSTD_CACHED		0x00000008u
+#define	WT_CURSTD_DEAD			0x00000010u
+#define	WT_CURSTD_DEBUG_COPY_KEY	0x00000020u
+#define	WT_CURSTD_DEBUG_COPY_VALUE	0x00000040u
+#define	WT_CURSTD_DEBUG_RESET_EVICT	0x00000080u
+#define	WT_CURSTD_DUMP_HEX		0x00000100u
+#define	WT_CURSTD_DUMP_JSON		0x00000200u
+#define	WT_CURSTD_DUMP_PRETTY		0x00000400u
+#define	WT_CURSTD_DUMP_PRINT		0x00000800u
+#define	WT_CURSTD_DUP_NO_VALUE          0x00001000u
+#define	WT_CURSTD_HS_READ_ALL		0x00002000u
+#define	WT_CURSTD_HS_READ_COMMITTED	0x00004000u
+#define	WT_CURSTD_IGNORE_TOMBSTONE	0x00008000u
+#define	WT_CURSTD_JOINED		0x00010000u
+#define	WT_CURSTD_KEY_EXT		0x00020000u /* Key points out of tree. */
+#define	WT_CURSTD_KEY_INT		0x00040000u /* Key points into tree. */
+#define	WT_CURSTD_KEY_ONLY		0x00080000u
+#define	WT_CURSTD_META_INUSE		0x00100000u
+#define	WT_CURSTD_OPEN			0x00200000u
+#define	WT_CURSTD_OVERWRITE		0x00400000u
+#define	WT_CURSTD_PREFIX_SEARCH		0x00800000u
+#define	WT_CURSTD_RAW			0x01000000u
+#define	WT_CURSTD_RAW_SEARCH		0x02000000u
+#define	WT_CURSTD_VALUE_EXT		0x04000000u /* Value points out of tree. */
+#define	WT_CURSTD_VALUE_INT		0x08000000u /* Value points into tree. */
+#define WT_CURSTD_VERSION_CURSOR	0x10000000u /* Version cursor. */
 /* AUTOMATIC FLAG VALUE GENERATION STOP 32 */
 #define	WT_CURSTD_KEY_SET	(WT_CURSTD_KEY_EXT | WT_CURSTD_KEY_INT)
 #define	WT_CURSTD_VALUE_SET	(WT_CURSTD_VALUE_EXT | WT_CURSTD_VALUE_INT)
diff --git a/src/third_party/wiredtiger/test/suite/test_cursor20.py b/src/third_party/wiredtiger/test/suite/test_cursor20.py
new file mode 100644
index 00000000000..3ff29695e7f
--- /dev/null
+++ b/src/third_party/wiredtiger/test/suite/test_cursor20.py
@@ -0,0 +1,66 @@
+#!/usr/bin/env python
+#
+# Public Domain 2014-present MongoDB, Inc.
+# Public Domain 2008-2014 WiredTiger, Inc.
+#
+# This is free and unencumbered software released into the public domain.
+#
+# Anyone is free to copy, modify, publish, use, compile, sell, or
+# distribute this software, either in source code form or as a compiled
+# binary, for any purpose, commercial or non-commercial, and by any
+# means.
+#
+# In jurisdictions that recognize copyright laws, the author or authors
+# of this software dedicate any and all copyright interest in the
+# software to the public domain. We make this dedication for the benefit
+# of the public at large and to the detriment of our heirs and
+# successors. We intend this dedication to be an overt act of
+# relinquishment in perpetuity of all present and future rights to this
+# software under copyright law.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+# IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+# test_cursor18.py
+#   Test dupicate key return values.
+
+from suite_subprocess import suite_subprocess
+from wtdataset import SimpleDataSet
+import wiredtiger, wttest
+from wtscenario import make_scenarios
+
+class test_cursor18(wttest.WiredTigerTestCase, suite_subprocess):
+    format_values = [
+        ('row', dict(key_format = 'S', value_format='S')),
+        ('var', dict(key_format = 'r', value_format='S')),
+        ('fix', dict(key_format = 'r', value_format='8t')),
+    ]
+    reopen = [
+        ('in-memory', dict(reopen=False)),
+        ('on-disk', dict(reopen=True)),
+    ]
+    scenarios = make_scenarios(format_values, reopen)
+
+    def test_dup_key(self):
+        uri = 'table:dup_key'
+        ds = SimpleDataSet(self, uri, 100,
+            key_format=self.key_format, value_format=self.value_format)
+        ds.populate()
+
+        if self.reopen:
+            self.reopen_conn()
+
+        c = self.session.open_cursor(uri, None, 'overwrite=false')
+        c.set_key(ds.key(10))
+        c.set_value(ds.value(20))
+        self.assertRaisesHavingMessage(
+            wiredtiger.WiredTigerError, lambda:c.insert(), '/WT_DUPLICATE_KEY/')
+        self.assertEqual(c.get_value(), ds.value(10))
+
+if __name__ == '__main__':
+    wttest.run()