From 6f41b01ce74488f68c85da5ad1cc2aa86cf695af Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Dani=C3=ABl=20van=20Eeden?= <git@myname.nl>
Date: Thu, 21 Nov 2024 13:09:54 +0100
Subject: [PATCH] replication: Support GTID tag in PreviousGTIDsEvent

Issue: closes #845

The `PreviousGTIDsEvent` / `PREVIOUS_GTIDS_LOG_EVENT` has changed to
work with tagged GTIDs.

First the `uuidCount` has changed, it encodes the GTID format. Here
format 1 is tagged and format 0 is untagged.

Then each entry may have a tag. If there is a tag then the uuid itself
isn't printed but the tag is appended to the last entry.

Examples:

`896e7882-18fe-11ef-ab88-22222d34d411:1-3`

regular format, compatible with both formats

`896e7882-18fe-11ef-ab88-22222d34d411:1-4:aaaa:1`

tagged format.

Combination of

- `896e7882-18fe-11ef-ab88-22222d34d411:1-4`
- `896e7882-18fe-11ef-ab88-22222d34d411:aaaa:1`

`896e7882-18fe-11ef-ab88-22222d34d411:1-4:aaaa:1:abc:1-3:bbbbb:1:bbbbbb:1:x:1,896e7882-18fe-11ef-ab88-22222d34d412:1-2`

Combination of:
```
896e7882-18fe-11ef-ab88-22222d34d411:1-4
                                    :aaaa:1
                                    :abc:1-3
                                    :bbbbb:1
                                    :bbbbbb:1
                                    :x:1,
896e7882-18fe-11ef-ab88-22222d34d412:1-2
```

Please also see: `mysqlbinlog --read-from-remote-server --hexdump $binlogfile` to see how MySQL encodes/decodes this.

See also:
- https://dev.mysql.com/doc/refman/8.4/en/replication-gtids-concepts.html
---
 replication/event.go | 57 ++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 53 insertions(+), 4 deletions(-)

diff --git a/replication/event.go b/replication/event.go
index 6fb614f61..599a336b2 100644
--- a/replication/event.go
+++ b/replication/event.go
@@ -229,15 +229,59 @@ type PreviousGTIDsEvent struct {
 	GTIDSets string
 }
 
+type GtidFormat int
+
+const (
+	GtidFormatClassic = iota
+	GtidFormatTagged
+)
+
+func decodeSid(data []byte) (format GtidFormat, sidnr uint64) {
+	if data[7] == 1 {
+		format = GtidFormatTagged
+	}
+
+	if format == GtidFormatTagged {
+		sid_mask := []byte{0, 255, 255, 255, 255, 255, 255, 0}
+
+		// Apply the mask
+		for i, _ := range data[:8] {
+			data[i] &= sid_mask[i]
+		}
+		data = append(data, 0)
+
+		// sidnr
+		sidnr = binary.LittleEndian.Uint64(data[1:])
+		return
+	}
+	sidnr = binary.LittleEndian.Uint64(data)
+	return
+}
+
 func (e *PreviousGTIDsEvent) Decode(data []byte) error {
 	pos := 0
-	uuidCount := binary.LittleEndian.Uint16(data[pos : pos+8])
+
+	gtidinfo := make([]byte, 8)
+	copy(gtidinfo, data[:8])
+	format, uuidCount := decodeSid(gtidinfo)
 	pos += 8
 
 	previousGTIDSets := make([]string, uuidCount)
-	for i := range previousGTIDSets {
+	currentSetnr := 0
+	for _ = range previousGTIDSets {
 		uuid := e.decodeUuid(data[pos : pos+16])
 		pos += 16
+		isTag := false
+		var tag string
+		if format == GtidFormatTagged {
+			tagLength := int(data[pos]) / 2
+			pos += 1
+			if tagLength > 0 {
+				isTag = true
+				tag = string(data[pos : pos+tagLength])
+				pos += tagLength
+			}
+		}
 		sliceCount := binary.LittleEndian.Uint16(data[pos : pos+8])
 		pos += 8
 		intervals := make([]string, sliceCount)
@@ -254,9 +298,14 @@ func (e *PreviousGTIDsEvent) Decode(data []byte) error {
 			}
 			intervals[i] = interval
 		}
-		previousGTIDSets[i] = fmt.Sprintf("%s:%s", uuid, strings.Join(intervals, ":"))
+		if isTag {
+			previousGTIDSets[currentSetnr-1] += fmt.Sprintf(":%s:%s", tag, strings.Join(intervals, ":"))
+		} else {
+			previousGTIDSets[currentSetnr] = fmt.Sprintf("%s:%s", uuid, strings.Join(intervals, ":"))
+			currentSetnr += 1
+		}
 	}
-	e.GTIDSets = strings.Join(previousGTIDSets, ",")
+	e.GTIDSets = strings.Join(previousGTIDSets[:currentSetnr], ",")
 	return nil
 }