[pkg/ottl] parse uri string to url.* SemConv attributes

.chloggen/ottl_uri-parser.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: Introducing `Uri` converter parsing URI string into SemConv
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [32433]
+
+# (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: [user]

pkg/ottl/ottlfuncs/README.md

@@ -1292,6 +1292,44 @@ Examples:
 
 - `UnixSeconds(Time("02/04/2023", "%m/%d/%Y"))`
 
+### URI
+
+`URI(uri_string)`
+
+Parses a Uniform Resource Identifier (URI) string and extracts its components as an object.
+This URI object includes properties for the URI’s domain, path, fragment, port, query, scheme, user info, username, and password.
+
+`original`, `domain`, `scheme`, and `path` are always present. Other properties are present only if they have corresponding values.
+
+`uri_string` is a `string`.
+
+- `URI("http://www.example.com")`
+
+results in 
+```
+  "original": "http://www.example.com",
+  "scheme":   "http",
+  "domain":   "www.example.com",
+  "path":     "",
+```
+
+- `URI("http://myusername:[email protected]:80/foo.gif?key1=val1&key2=val2#fragment")`
+
+results in 
+```
+  "path":      "/foo.gif",
+  "fragment":  "fragment",
+  "extension": "gif",
+  "password":  "mypassword",
+  "original":  "http://myusername:[email protected]:80/foo.gif?key1=val1&key2=val2#fragment",
+  "scheme":    "http",
+  "port":      80,
+  "user_info": "myusername:mypassword",
+  "domain":    "www.example.com",
+  "query":     "key1=val1&key2=val2",
+  "username":  "myusername",
+```
+
 ### UUID
 
 `UUID()`

pkg/ottl/ottlfuncs/func_uri.go

@@ -0,0 +1,93 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package ottlfuncs // import "github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl/ottlfuncs"
+
+import (
+	"context"
+	"fmt"
+	"net/url"
+	"strconv"
+	"strings"
+
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl"
+)
+
+type URIArguments[K any] struct {
+	URI ottl.StringGetter[K]
+}
+
+func NewURIFactory[K any]() ottl.Factory[K] {
+	return ottl.NewFactory("URI", &URIArguments[K]{}, createURIFunction[K])
+}
+
+func createURIFunction[K any](_ ottl.FunctionContext, oArgs ottl.Arguments) (ottl.ExprFunc[K], error) {
+	args, ok := oArgs.(*URIArguments[K])
+	if !ok {
+		return nil, fmt.Errorf("URIFactory args must be of type *URIArguments[K]")
+	}
+
+	return URI(args.URI)
+}
+
+func URI[K any](uriSource ottl.StringGetter[K]) (ottl.ExprFunc[K], error) {
+	return func(ctx context.Context, tCtx K) (any, error) {
+		uriString, err := uriSource.Get(ctx, tCtx)
+		if err != nil {
+			return nil, err
+		}
+
+		if uriString == "" {
+			return nil, fmt.Errorf("uri cannot be nil")
+		}
+
+		uriParts := make(map[string]any)
+
+		parsedURI, err := url.Parse(uriString)
+		if err != nil {
+			return nil, err
+		}
+
+		// always present fields
+		uriParts["original"] = uriString
+		uriParts["domain"] = parsedURI.Hostname()
+		uriParts["scheme"] = parsedURI.Scheme
+		uriParts["path"] = parsedURI.Path
+
+		// optional fields included only if populated
+		if port := parsedURI.Port(); len(port) > 0 {
+			uriParts["port"], err = strconv.Atoi(port)
+			if err != nil {
+				return nil, err
+			}
+		}
+
+		if fragment := parsedURI.Fragment; len(fragment) > 0 {
+			uriParts["fragment"] = fragment
+		}
+
+		if parsedURI.User != nil {
+			uriParts["user_info"] = parsedURI.User.String()
+
+			if username := parsedURI.User.Username(); len(username) > 0 {
+				uriParts["username"] = username
+			}
+
+			if pwd, isSet := parsedURI.User.Password(); isSet {
+				uriParts["password"] = pwd
+			}
+		}
+
+		if query := parsedURI.RawQuery; len(query) > 0 {
+			uriParts["query"] = query
+		}
+
+		if periodIdx := strings.LastIndex(parsedURI.Path, "."); periodIdx != -1 {
+			if periodIdx < len(parsedURI.Path)-1 {
+				uriParts["extension"] = parsedURI.Path[periodIdx+1:]
+			}
+		}
+
+		return uriParts, nil
+	}, nil
+}

pkg/ottl/ottlfuncs/func_uri_test.go

@@ -0,0 +1,172 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package ottlfuncs
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl"
+)
+
+func TestURIParser(t *testing.T) {
+	testCases := []struct {
+		Name        string
+		Original    string
+		ExpectedMap map[string]any
+	}{
+		{
+			"complete example",
+			"http://myusername:[email protected]:80/foo.gif?key1=val1&key2=val2#fragment",
+			map[string]any{
+				"path":      "/foo.gif",
+				"fragment":  "fragment",
+				"extension": "gif",
+				"password":  "mypassword",
+				"original":  "http://myusername:[email protected]:80/foo.gif?key1=val1&key2=val2#fragment",
+				"scheme":    "http",
+				"port":      80,
+				"user_info": "myusername:mypassword",
+				"domain":    "www.example.com",
+				"query":     "key1=val1&key2=val2",
+				"username":  "myusername",
+			},
+		},
+		{
+			"simple example",
+			"http://www.example.com",
+			map[string]any{
+				"original": "http://www.example.com",
+				"scheme":   "http",
+				"domain":   "www.example.com",
+				"path":     "",
+			},
+		},
+		{
+			"custom port",
+			"http://www.example.com:77",
+			map[string]any{
+				"original": "http://www.example.com:77",
+				"scheme":   "http",
+				"domain":   "www.example.com",
+				"path":     "",
+				"port":     77,
+			},
+		},
+		{
+			"file",
+			"http://www.example.com:77/file.png",
+			map[string]any{
+				"original":  "http://www.example.com:77/file.png",
+				"scheme":    "http",
+				"domain":    "www.example.com",
+				"path":      "/file.png",
+				"port":      77,
+				"extension": "png",
+			},
+		},
+		{
+			"fragment",
+			"http://www.example.com:77/foo#bar",
+			map[string]any{
+				"original": "http://www.example.com:77/foo#bar",
+				"scheme":   "http",
+				"domain":   "www.example.com",
+				"path":     "/foo",
+				"port":     77,
+				"fragment": "bar",
+			},
+		},
+		{
+			"query example",
+			"https://www.example.com:77/foo?key=val",
+			map[string]any{
+				"original": "https://www.example.com:77/foo?key=val",
+				"scheme":   "https",
+				"domain":   "www.example.com",
+				"path":     "/foo",
+				"port":     77,
+				"query":    "key=val",
+			},
+		},
+		{
+			"user info",
+			"https://user:[email protected]:77/foo",
+			map[string]any{
+				"original":  "https://user:[email protected]:77/foo",
+				"scheme":    "https",
+				"domain":    "www.example.com",
+				"path":      "/foo",
+				"port":      77,
+				"user_info": "user:pw",
+				"username":  "user",
+				"password":  "pw",
+			},
+		},
+		{
+			"user info - no password",
+			"https://user:@www.example.com:77/foo",
+			map[string]any{
+				"original":  "https://user:@www.example.com:77/foo",
+				"scheme":    "https",
+				"domain":    "www.example.com",
+				"path":      "/foo",
+				"port":      77,
+				"user_info": "user:",
+				"username":  "user",
+				"password":  "",
+			},
+		},
+		{
+			"non-http scheme: ftp",
+			"ftp://ftp.is.co.za/rfc/rfc1808.txt",
+			map[string]any{
+				"original":  "ftp://ftp.is.co.za/rfc/rfc1808.txt",
+				"scheme":    "ftp",
+				"path":      "/rfc/rfc1808.txt",
+				"extension": "txt",
+				"domain":    "ftp.is.co.za",
+			},
+		},
+		{
+			"non-http scheme: telnet",
+			"telnet://192.0.2.16:80/",
+			map[string]any{
+				"original": "telnet://192.0.2.16:80/",
+				"scheme":   "telnet",
+				"path":     "/",
+				"port":     80,
+				"domain":   "192.0.2.16",
+			},
+		},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.Name, func(t *testing.T) {
+			source := &ottl.StandardStringGetter[any]{
+				Getter: func(_ context.Context, _ any) (any, error) {
+					return tc.Original, nil
+				},
+			}
+
+			exprFunc, err := URI(source)
+			require.NoError(t, err)
+
+			res, err := exprFunc(context.Background(), nil)
+			require.NoError(t, err)
+
+			resMap, ok := res.(map[string]any)
+			require.True(t, ok)
+
+			require.Equal(t, len(tc.ExpectedMap), len(resMap))
+			for k, v := range tc.ExpectedMap {
+				actualValue, found := resMap[k]
+				require.True(t, found, "key not found %q", k)
+				require.Equal(t, v, actualValue)
+			}
+		})
+	}
+}

pkg/ottl/ottlfuncs/functions.go

@@ -79,5 +79,6 @@ func converters[K any]() []ottl.Factory[K] {
 		NewUnixNanoFactory[K](),
 		NewUnixSecondsFactory[K](),
 		NewUUIDFactory[K](),
+		NewURIFactory[K](),
 	}
 }