[pkg/ottl] Add ParseKeyValue function (open-telemetry#31035)

**Description:** <Describe what has changed.>
Adds a `ParseKeyValue` converter function that parses out key values
pairs into a `pcommon.Map`. It takes a `StringGetter` target argument
and 2 optional arguments for the pair delimiter and key value delimiter.
This is an adaptation of the Stanza Key Value Parser operator to provide
feature parity.

Given the following input string `"k1=v1 k2=v2 k3=v3"`, the function
would return the following map:
```
{ "k1": "v1", "k2": "v2", "k3": "v3" }
```

**Link to tracking Issue:** <Issue number if applicable>
Closes open-telemetry#30998 

**Testing:** <Describe what testing was performed and which tests were
added.>
Added unit tests and e2e test.

**Documentation:** <Describe the documentation added.>
Added function documentation.

.chloggen/pkg-ottl-add-parse-key-value-function.yaml

@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: pkg/ottl
+
+# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Add `ParseKeyValue` function for parsing key value pairs from a target string
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [30998]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: []

internal/coreinternal/parseutils/doc.go

@@ -0,0 +1,4 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package parseutils // import "github.com/open-telemetry/opentelemetry-collector-contrib/internal/coreinternal/parseutils"

internal/coreinternal/parseutils/package_test.go

@@ -0,0 +1,14 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package parseutils
+
+import (
+ "testing"
+
+ "go.uber.org/goleak"
+)
+
+func TestMain(m *testing.M) {
+ goleak.VerifyTestMain(m)
+}

internal/coreinternal/parseutils/parser.go

@@ -0,0 +1,73 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package parseutils // import "github.com/open-telemetry/opentelemetry-collector-contrib/internal/coreinternal/parseutils"
+
+import (
+ "fmt"
+ "strings"
+
+ "go.uber.org/multierr"
+)
+
+// SplitString will split the input on the delimiter and return the resulting slice while respecting quotes. Outer quotes are stripped.
+// Use in place of `strings.Split` when quotes need to be respected.
+// Requires `delimiter` not be an empty string
+func SplitString(input, delimiter string) ([]string, error) {
+ var result []string
+ current := ""
+ delimiterLength := len(delimiter)
+ quoteChar := "" // "" means we are not in quotes
+
+ for i := 0; i < len(input); i++ {
+ if quoteChar == "" && i+delimiterLength <= len(input) && input[i:i+delimiterLength] == delimiter { // delimiter
+ if current == "" { // leading || trailing delimiter; ignore
+ i += delimiterLength - 1
+ continue
+ }
+ result = append(result, current)
+ current = ""
+ i += delimiterLength - 1
+ continue
+ }
+
+ if quoteChar == "" && (input[i] == '"' || input[i] == '\'') { // start of quote
+ quoteChar = string(input[i])
+ continue
+ }
+ if string(input[i]) == quoteChar { // end of quote
+ quoteChar = ""
+ continue
+ }
+
+ current += string(input[i])
+ }
+
+ if quoteChar != "" { // check for closed quotes
+ return nil, fmt.Errorf("never reached the end of a quoted value")
+ }
+ if current != "" { // avoid adding empty value bc of a trailing delimiter
+ return append(result, current), nil
+ }
+
+ return result, nil
+}
+
+// ParseKeyValuePairs will split each string in `pairs` on the `delimiter` into a key and value string that get added to a map and returned.
+func ParseKeyValuePairs(pairs []string, delimiter string) (map[string]any, error) {
+ parsed := make(map[string]any)
+ var err error
+ for _, p := range pairs {
+ pair := strings.SplitN(p, delimiter, 2)
+ if len(pair) != 2 {
+ err = multierr.Append(err, fmt.Errorf("cannot split %q into 2 items, got %d item(s)", p, len(pair)))
+ continue
+ }
+
+ key := strings.TrimSpace(pair[0])
+ value := strings.TrimSpace(pair[1])
+
+ parsed[key] = value
+ }
+ return parsed, err
+}

internal/coreinternal/parseutils/parser_test.go

@@ -0,0 +1,276 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package parseutils
+
+import (
+ "fmt"
+ "testing"
+
+ "github.com/stretchr/testify/assert"
+)
+
+func Test_SplitString(t *testing.T) {
+ testCases := []struct {
+ name string
+ input string
+ delimiter string
+ expected []string
+ expectedErr error
+ }{
+ {
+ name: "simple",
+ input: "a b c",
+ delimiter: " ",
+ expected: []string{
+ "a",
+ "b",
+ "c",
+ },
+ },
+ {
+ name: "single quotes",
+ input: "a 'b c d'",
+ delimiter: " ",
+ expected: []string{
+ "a",
+ "b c d",
+ },
+ },
+ {
+ name: "double quotes",
+ input: `a " b c " d`,
+ delimiter: " ",
+ expected: []string{
+ "a",
+ " b c ",
+ "d",
+ },
+ },
+ {
+ name: "multi-char delimiter",
+ input: "abc!@! def !@! g",
+ delimiter: "!@!",
+ expected: []string{
+ "abc",
+ " def ",
+ " g",
+ },
+ },
+ {
+ name: "leading and trailing delimiters",
+ input: " name=ottl func=key_value hello=world ",
+ delimiter: " ",
+ expected: []string{
+ "name=ottl",
+ "func=key_value",
+ "hello=world",
+ },
+ },
+ {
+ name: "embedded double quotes in single quoted value",
+ input: `ab c='this is a "co ol" value'`,
+ delimiter: " ",
+ expected: []string{
+ "ab",
+ `c=this is a "co ol" value`,
+ },
+ },
+ {
+ name: "embedded double quotes end single quoted value",
+ input: `ab c='this is a "co ol"'`,
+ delimiter: " ",
+ expected: []string{
+ "ab",
+ `c=this is a "co ol"`,
+ },
+ },
+ {
+ name: "quoted values include whitespace",
+ input: `name=" ottl " func=" key_ value"`,
+ delimiter: " ",
+ expected: []string{
+ "name= ottl ",
+ "func= key_ value",
+ },
+ },
+ {
+ name: "delimiter longer than input",
+ input: "abc",
+ delimiter: "aaaa",
+ expected: []string{
+ "abc",
+ },
+ },
+ {
+ name: "delimiter not found",
+ input: "a b c",
+ delimiter: "!",
+ expected: []string{
+ "a b c",
+ },
+ },
+ {
+ name: "newlines in input",
+ input: `a
+b
+c`,
+ delimiter: " ",
+ expected: []string{
+ "a\nb\nc",
+ },
+ },
+ {
+ name: "newline delimiter",
+ input: `a b c
+d e f
+g 
+h`,
+ delimiter: "\n",
+ expected: []string{
+ "a b c",
+ "d e f",
+ "g ",
+ "h",
+ },
+ },
+ {
+ name: "empty input",
+ input: "",
+ delimiter: " ",
+ expected: nil,
+ },
+ {
+ name: "equal input and delimiter",
+ input: "abc",
+ delimiter: "abc",
+ expected: nil,
+ },
+ {
+ name: "unclosed quotes",
+ input: "a 'b c",
+ delimiter: " ",
+ expectedErr: fmt.Errorf("never reached the end of a quoted value"),
+ },
+ {
+ name: "mismatched quotes",
+ input: `a 'b c' "d '`,
+ delimiter: " ",
+ expectedErr: fmt.Errorf("never reached the end of a quoted value"),
+ },
+ {
+ name: "tab delimiters",
+ input: "a b c",
+ delimiter: "\t",
+ expected: []string{
+ "a",
+ "b",
+ "c",
+ },
+ },
+ }
+
+ for _, tc := range testCases {
+ t.Run(tc.name, func(t *testing.T) {
+ result, err := SplitString(tc.input, tc.delimiter)
+
+ if tc.expectedErr == nil {
+ assert.NoError(t, err)
+ assert.Equal(t, tc.expected, result)
+ } else {
+ assert.EqualError(t, err, tc.expectedErr.Error())
+ assert.Nil(t, result)
+ }
+ })
+ }
+}
+
+func Test_ParseKeyValuePairs(t *testing.T) {
+ testCases := []struct {
+ name string
+ pairs []string
+ delimiter string
+ expected map[string]any
+ expectedErr error
+ }{
+ {
+ name: "multiple delimiters",
+ pairs: []string{"a==b", "c=d=", "e=f"},
+ delimiter: "=",
+ expected: map[string]any{
+ "a": "=b",
+ "c": "d=",
+ "e": "f",
+ },
+ },
+ {
+ name: "no delimiter found",
+ pairs: []string{"ab"},
+ delimiter: "=",
+ expectedErr: fmt.Errorf("cannot split \"ab\" into 2 items, got 1 item(s)"),
+ },
+ {
+ name: "no delimiter found 2x",
+ pairs: []string{"ab", "cd"},
+ delimiter: "=",
+ expectedErr: fmt.Errorf("cannot split \"ab\" into 2 items, got 1 item(s); cannot split \"cd\" into 2 items, got 1 item(s)"),
+ },
+ {
+ name: "empty pairs",
+ pairs: []string{},
+ delimiter: "=",
+ expected: map[string]any{},
+ },
+ {
+ name: "empty pair string",
+ pairs: []string{""},
+ delimiter: "=",
+ expectedErr: fmt.Errorf("cannot split \"\" into 2 items, got 1 item(s)"),
+ },
+ {
+ name: "empty delimiter",
+ pairs: []string{"a=b", "c=d"},
+ delimiter: "",
+ expected: map[string]any{
+ "a": "=b",
+ "c": "=d",
+ },
+ },
+ {
+ name: "empty pairs & delimiter",
+ pairs: []string{},
+ delimiter: "",
+ expected: map[string]any{},
+ },
+ {
+ name: "early delimiter",
+ pairs: []string{"=a=b"},
+ delimiter: "=",
+ expected: map[string]any{
+ "": "a=b",
+ },
+ },
+ {
+ name: "weird spacing",
+ pairs: []string{" a= b ", " c = d "},
+ delimiter: "=",
+ expected: map[string]any{
+ "a": "b",
+ "c": "d",
+ },
+ },
+ }
+
+ for _, tc := range testCases {
+ t.Run(tc.name, func(t *testing.T) {
+ result, err := ParseKeyValuePairs(tc.pairs, tc.delimiter)
+
+ if tc.expectedErr == nil {
+ assert.NoError(t, err)
+ assert.Equal(t, tc.expected, result)
+ } else {
+ assert.EqualError(t, err, tc.expectedErr.Error())
+ }
+ })
+ }
+}