[pkg/ottl] parse uri string to url.* SemConv attributes (open-telemet…

…ry#32906)

**Description:** 
This ottl converter converts uri string into SemConv attributes.
Instead of using regex it uses `uri.Parse` providing nicer shorthand.

**Link to tracking Issue:** open-telemetry#32433

**Testing:** unit test added

**Documentation:** readme updated with:

### 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 are
present only if they have corresponding values.

`uri_string` is a `string`.

- `Uri("http:https://www.example.com")`

results in 
```
  "original": "http:https://www.example.com",
  "scheme":   "http",
  "domain":   "www.example.com",
  "path":     "",
```

-
`Uri("http:https://myusername:mypassword@www.example.com:80/foo.gif?key1=val1&key2=val2#fragment")`

results in 
```
  "path":      "/foo.gif",
  "fragment":  "fragment",
  "extension": "gif",
  "password":  "mypassword",
  "original":  "http:https://myusername:mypassword@www.example.com: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",
```

---------

Co-authored-by: Tiffany Hrabusa <[email protected]>
Co-authored-by: Evan Bradley <[email protected]>

.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]

connector/countconnector/go.mod

@@ -49,6 +49,7 @@ require (
  github.com/prometheus/procfs v0.15.0 // indirect
  go.opentelemetry.io/collector v0.102.2-0.20240611143128-7dfb57b9ad1c // indirect
  go.opentelemetry.io/collector/config/configtelemetry v0.102.2-0.20240611143128-7dfb57b9ad1c // indirect
+ go.opentelemetry.io/collector/semconv v0.102.2-0.20240611143128-7dfb57b9ad1c // indirect
  go.opentelemetry.io/otel v1.27.0 // indirect
  go.opentelemetry.io/otel/exporters/prometheus v0.49.0 // indirect
  go.opentelemetry.io/otel/sdk v1.27.0 // indirect

connector/routingconnector/go.mod

@@ -44,6 +44,7 @@ require (
  github.com/prometheus/procfs v0.15.0 // indirect
  go.opentelemetry.io/collector v0.102.2-0.20240611143128-7dfb57b9ad1c // indirect
  go.opentelemetry.io/collector/config/configtelemetry v0.102.2-0.20240611143128-7dfb57b9ad1c // indirect
+ go.opentelemetry.io/collector/semconv v0.102.2-0.20240611143128-7dfb57b9ad1c // indirect
  go.opentelemetry.io/otel v1.27.0 // indirect
  go.opentelemetry.io/otel/exporters/prometheus v0.49.0 // indirect
  go.opentelemetry.io/otel/sdk v1.27.0 // indirect

exporter/honeycombmarkerexporter/go.mod

@@ -13,6 +13,7 @@ require (
  go.opentelemetry.io/collector/confmap v0.102.2-0.20240611143128-7dfb57b9ad1c
  go.opentelemetry.io/collector/exporter v0.102.2-0.20240611143128-7dfb57b9ad1c
  go.opentelemetry.io/collector/pdata v1.9.1-0.20240611143128-7dfb57b9ad1c
+ go.opentelemetry.io/collector/semconv v0.102.2-0.20240611143128-7dfb57b9ad1c // indirect
  go.opentelemetry.io/otel/metric v1.27.0
  go.opentelemetry.io/otel/trace v1.27.0
  go.uber.org/goleak v1.3.0

internal/coreinternal/parseutils/uri.go

@@ -0,0 +1,164 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package parseutils // import "github.com/open-telemetry/opentelemetry-collector-contrib/internal/coreinternal/parseutils"
+
+import (
+ "net/url"
+ "strconv"
+ "strings"
+
+ semconv "go.opentelemetry.io/collector/semconv/v1.25.0"
+)
+
+const (
+ // replace once conventions includes these
+ AttributeURLUserInfo = "url.user_info"
+ AttributeURLUsername = "url.username"
+ AttributeURLPassword = "url.password"
+)
+
+// parseURI takes an absolute or relative uri and returns the parsed values.
+func ParseURI(value string, semconvCompliant bool) (map[string]any, error) {
+ m := make(map[string]any)
+
+ if strings.HasPrefix(value, "?") {
+ // remove the query string '?' prefix before parsing
+ v, err := url.ParseQuery(value[1:])
+ if err != nil {
+ return nil, err
+ }
+ return queryToMap(v, m), nil
+ }
+
+ var x *url.URL
+ var err error
+ var mappingFn func(*url.URL, map[string]any) (map[string]any, error)
+
+ if semconvCompliant {
+ mappingFn = urlToSemconvMap
+ x, err = url.Parse(value)
+ if err != nil {
+ return nil, err
+ }
+ } else {
+ x, err = url.ParseRequestURI(value)
+ if err != nil {
+ return nil, err
+ }
+
+ mappingFn = urlToMap
+ }
+ return mappingFn(x, m)
+}
+
+// urlToMap converts a url.URL to a map, excludes any values that are not set.
+func urlToSemconvMap(parsedURI *url.URL, m map[string]any) (map[string]any, error) {
+ m[semconv.AttributeURLOriginal] = parsedURI.String()
+ m[semconv.AttributeURLDomain] = parsedURI.Hostname()
+ m[semconv.AttributeURLScheme] = parsedURI.Scheme
+ m[semconv.AttributeURLPath] = parsedURI.Path
+
+ if portString := parsedURI.Port(); len(portString) > 0 {
+ port, err := strconv.Atoi(portString)
+ if err != nil {
+ return nil, err
+ }
+ m[semconv.AttributeURLPort] = port
+ }
+
+ if fragment := parsedURI.Fragment; len(fragment) > 0 {
+ m[semconv.AttributeURLFragment] = fragment
+ }
+
+ if parsedURI.User != nil {
+ m[AttributeURLUserInfo] = parsedURI.User.String()
+
+ if username := parsedURI.User.Username(); len(username) > 0 {
+ m[AttributeURLUsername] = username
+ }
+
+ if pwd, isSet := parsedURI.User.Password(); isSet {
+ m[AttributeURLPassword] = pwd
+ }
+ }
+
+ if query := parsedURI.RawQuery; len(query) > 0 {
+ m[semconv.AttributeURLQuery] = query
+ }
+
+ if periodIdx := strings.LastIndex(parsedURI.Path, "."); periodIdx != -1 {
+ if periodIdx < len(parsedURI.Path)-1 {
+ m[semconv.AttributeURLExtension] = parsedURI.Path[periodIdx+1:]
+ }
+ }
+
+ return m, nil
+}
+
+// urlToMap converts a url.URL to a map, excludes any values that are not set.
+func urlToMap(p *url.URL, m map[string]any) (map[string]any, error) {
+ scheme := p.Scheme
+ if scheme != "" {
+ m["scheme"] = scheme
+ }
+
+ user := p.User.Username()
+ if user != "" {
+ m["user"] = user
+ }
+
+ host := p.Hostname()
+ if host != "" {
+ m["host"] = host
+ }
+
+ port := p.Port()
+ if port != "" {
+ m["port"] = port
+ }
+
+ path := p.EscapedPath()
+ if path != "" {
+ m["path"] = path
+ }
+
+ return queryToMap(p.Query(), m), nil
+}
+
+// queryToMap converts a query string url.Values to a map.
+func queryToMap(query url.Values, m map[string]any) map[string]any {
+ // no-op if query is empty, do not create the key m["query"]
+ if len(query) == 0 {
+ return m
+ }
+
+ /* 'parameter' will represent url.Values
+ map[string]any{
+ "parameter-a": []any{
+ "a",
+ "b",
+ },
+ "parameter-b": []any{
+ "x",
+ "y",
+ },
+ }
+ */
+ parameters := map[string]any{}
+ for param, values := range query {
+ parameters[param] = queryParamValuesToMap(values)
+ }
+ m["query"] = parameters
+ return m
+}
+
+// queryParamValuesToMap takes query string parameter values and
+// returns an []interface populated with the values
+func queryParamValuesToMap(values []string) []any {
+ v := make([]any, len(values))
+ for i, value := range values {
+ v[i] = value
+ }
+ return v
+}