feat(parsers.binary): handle hex-encoded inputs (#12232)

plugins/parsers/binary/README.md

@@ -18,11 +18,14 @@ user-specified configurations.
   ## Do not error-out if none of the filter expressions below matches.
   # allow_no_match = false
 
-  ## Specify the endianess of the data.
+  ## Specify the endianness of the data.
   ## Available values are "be" (big-endian), "le" (little-endian) and "host",
-  ## where "host" means the same endianess as the machine running Telegraf.
+  ## where "host" means the same endianness as the machine running Telegraf.
   # endianess = "host"
 
+  ## Interpret input as string containing hex-encoded data.
+  # hex_encoding = false
+
   ## Multiple parsing sections are allowed
   [[inputs.file.binary]]
     ## Optional: Metric (measurement) name to use if not extracted from the data.
@@ -30,7 +33,7 @@ user-specified configurations.
 
     ## Definition of the message format and the extracted data.
     ## Please note that you need to define all elements of the data in the
-    ## correct order with the correct length as the data is parsed in the order 
+    ## correct order with the correct length as the data is parsed in the order
     ## given.
     ## An entry can have the following properties:
     ##  name        --  Name of the element (e.g. field or tag). Can be omitted
@@ -59,7 +62,7 @@ user-specified configurations.
       { name = "address", type = "uint16", assignment = "tag" },
       { name = "value",   type = "float64" },
       { type = "unix", assignment = "time" },
-    ]   
+    ]
 
     ## Optional: Filter evaluated before applying the configuration.
     ## This option can be used to mange multiple configuration specific for
@@ -101,14 +104,20 @@ By specifying `allow_no_match` you allow the parser to silently ignore data
 that does not match _any_ given configuration filter. This can be useful if
 you only want to collect a subset of the available messages.
 
-#### `endianess` (optional)
+#### `endianness` (optional)
 
-This specifies the endianess of the data. If not specified, the parser will
-fallback to the "host" endianess, assuming that the message and Telegraf
-machine share the same endianess.
+This specifies the endianness of the data. If not specified, the parser will
+fallback to the "host" endianness, assuming that the message and Telegraf
+machine share the same endianness.
 Alternatively, you can explicitly specify big-endian format (`"be"`) or
 little-endian format (`"le"`).
 
+#### `hex_encoding` (optional)
+
+If `true`, the input data is interpreted as a string containing hex-encoded
+data like `C0 C7 21 A9`. The value is _case insensitive_ and can handle spaces,
+however prefixes like `0x` or `x` are _not_ allowed.
+
 ### Non-byte aligned value extraction
 
 In both, `filter` and `entries` definitions, values can be extracted at non-byte

plugins/parsers/binary/parser.go

@@ -2,8 +2,10 @@ package binary
 
 import (
 	"encoding/binary"
+	"encoding/hex"
 	"errors"
 	"fmt"
+	"strings"
 	"time"
 
 	"github.com/influxdata/telegraf"
@@ -14,6 +16,7 @@ type Parser struct {
 	AllowNoMatch bool            `toml:"allow_no_match"`
 	Endianess    string          `toml:"endianess"`
 	Configs      []Config        `toml:"binary"`
+	HexEncoding  bool            `toml:"hex_encoding"`
 	Log          telegraf.Logger `toml:"-"`
 
 	metricName  string
@@ -47,9 +50,21 @@ func (p *Parser) Init() error {
 	return nil
 }
 
-func (p *Parser) Parse(buf []byte) ([]telegraf.Metric, error) {
+func (p *Parser) Parse(data []byte) ([]telegraf.Metric, error) {
 	t := time.Now()
 
+	// If the data is encoded in HEX, we need to decode it first
+	buf := data
+	if p.HexEncoding {
+		s := strings.ReplaceAll(string(data), " ", "")
+		s = strings.ReplaceAll(s, "\t", "")
+		var err error
+		buf, err = hex.DecodeString(s)
+		if err != nil {
+			return nil, fmt.Errorf("decoding hex failed: %w", err)
+		}
+	}
+
 	matches := 0
 	metrics := make([]telegraf.Metric, 0)
 	for i, cfg := range p.Configs {

plugins/parsers/binary/parser_test.go

@@ -3,6 +3,7 @@ package binary
 import (
 	"bytes"
 	"encoding/binary"
+	"encoding/hex"
 	"fmt"
 	"os"
 	"path/filepath"
@@ -1465,3 +1466,35 @@ func TestCases(t *testing.T) {
 		})
 	}
 }
+
+func TestHexEncoding(t *testing.T) {
+	testdata := []interface{}{
+		uint64(0x01020304050607),
+		uint64(0x08090A0B0C0D0E),
+		uint64(0x0F101213141516),
+		uint64(0x1718191A1B1C1D),
+		uint64(0x1E1F2021222324),
+	}
+
+	parser := &Parser{
+		Endianess:   "be",
+		HexEncoding: true,
+		Configs: []Config{
+			{
+				Entries: []Entry{dummyEntry},
+			},
+		},
+		Log:        testutil.Logger{Name: "parsers.binary"},
+		metricName: "binary",
+	}
+	require.NoError(t, parser.Init())
+
+	// Generate the binary data and encode it to HEX
+	data, err := generateBinary(testdata, binary.BigEndian)
+	require.NoError(t, err)
+	encoded := hex.EncodeToString(data)
+
+	metrics, err := parser.Parse([]byte(encoded))
+	require.NoError(t, err)
+	require.NotEmpty(t, metrics)
+}