faro.receiver: add sourcemap fetching from remote locations

CHANGELOG.md

@@ -37,6 +37,8 @@ Main (unreleased)
 
 - Add `truncate` stage for `loki.process` to truncate log entries, label values, and structured_metadata values. (@dehaansa)
 
+- `faro.receiver` can now fetch sourcemaps from remote locations. When multiple locations are configured, local on-disk paths will be checked before remote paths. (@Oxel40)
+
 ### Enhancements
 
 - Add support of `tls` in components `loki.source.(awsfirehose|gcplog|heroku|api)` and `prometheus.receive_http` and `pyroscope.receive_http`. (@fgouteroux)

docs/sources/reference/components/faro/faro.receiver.md

@@ -55,13 +55,13 @@ The following strings are valid log line formats:
 
 You can use the following blocks with `faro.receiver`:
 
-| Block                                        | Description                                          | Required |
-|----------------------------------------------|------------------------------------------------------|----------|
-| [`output`][output]                           | Configures where to send collected telemetry data.   | yes      |
-| [`server`][server]                           | Configures the HTTP server.                          | no       |
-| `server` >  [`rate_limiting`][rate_limiting] | Configures rate limiting for the HTTP server.        | no       |
-| [`sourcemaps`][sourcemaps]                   | Configures sourcemap retrieval.                      | no       |
-| `sourcemaps` >  [`location`][location]       | Configures on-disk location for sourcemap retrieval. | no       |
+| Block                                        | Description                                        | Required |
+|----------------------------------------------|----------------------------------------------------|----------|
+| [`output`][output]                           | Configures where to send collected telemetry data. | yes      |
+| [`server`][server]                           | Configures the HTTP server.                        | no       |
+| `server` >  [`rate_limiting`][rate_limiting] | Configures rate limiting for the HTTP server.      | no       |
+| [`sourcemaps`][sourcemaps]                   | Configures sourcemap retrieval.                    | no       |
+| `sourcemaps` >  [`location`][location]       | Configures the location for sourcemap retrieval.   | no       |
 
 The > symbol indicates deeper levels of nesting.
 For example, `sourcemaps` > `location` refers to a `location` block defined inside a `sourcemaps` block.
@@ -151,18 +151,18 @@ The `*` character indicates a wildcard.
 By default, sourcemap downloads are subject to a timeout of `"1s"`, specified by the `download_timeout` argument.
 Setting `download_timeout` to `"0s"` disables timeouts.
 
-To retrieve sourcemaps from disk instead of the network, specify one or more [`location` blocks][location].
+To retrieve sourcemaps from disk or another network location, specify one or more [`location` blocks][location].
 When `location` blocks are provided, they're checked first for sourcemaps before falling back to downloading.
 
 #### `location`
 
 The `location` block declares a location where sourcemaps are stored on the filesystem.
 You can specify the `location` block multiple times to declare multiple locations where sourcemaps are stored.
 
-| Name                   | Type     | Description                                         | Default | Required |
-|------------------------|----------|-----------------------------------------------------|---------|----------|
-| `minified_path_prefix` | `string` | The prefix of the minified path sent from browsers. |         | yes      |
-| `path`                 | `string` | The path on disk where sourcemaps are stored.       |         | yes      |
+| Name                   | Type     | Description                                               | Default | Required |
+|------------------------|----------|-----------------------------------------------------------|---------|----------|
+| `minified_path_prefix` | `string` | The prefix of the minified path sent from browsers.       |         | yes      |
+| `path`                 | `string` | The path on disk or base URL where sourcemaps are stored. |         | yes      |
 
 The `minified_path_prefix` argument determines the prefix of paths to JavaScript files, such as `http://example.com/`.
 The `path` argument then determines where to find the sourcemap for the file.
@@ -184,6 +184,35 @@ To look up the sourcemaps for a file hosted at `http://example.com/example.js`,
 Optionally, the value for the `path` argument may contain `{{ .Release }}` as a template value, such as `/var/my-app/{{ .Release }}/build`.
 The template value is replaced with the release value provided by the [Faro Web App SDK][faro-sdk].
 
+When you specify a remote location, the procedure for retrieving the sourcemaps is the same as for a location block with a local path, except that the component retrieves the sourcemap from a remote HTTP server.
+
+ In the following example, the `faro.receiver` sends a GET request to `http://foo.com/blob/sourcemaps/example.js.map` and retrieves the sourcemap for a file hosted at
+`http://example.com/example.js`.
+
+You can specify multiple location blocks. For example:
+
+```alloy
+location {
+    path                 = "http://foo.com/blob/sourcemaps/"
+    minified_path_prefix = "http://example.com/"
+}
+
+```alloy
+location {
+    path                 = "/var/my-app/build"
+    minified_path_prefix = "http://example.com/"
+}
+location {
+    path                 = "http://foo.com/blob/sourcemaps/"
+    minified_path_prefix = "http://example.com/"
+}
+```
+
+The `faro.receiver` component searches through all locations for the sourcemap files.
+Local on-disk paths take precedence over remote paths.
+For a file hosted at `http://example.com/example.js`, the `faro.receiver` first checks
+the path `/var/my-app/build/example.js.map`, and then tries to retrieve `http://foo.com/blob/sourcemaps/example.js.map`.
+
 ## Exported fields
 
 `faro.receiver` doesn't export any fields.

internal/component/faro/receiver/sourcemaps.go

@@ -185,14 +185,30 @@ func (store *sourceMapsStoreImpl) GetSourceMap(sourceURL string, release string)
 func (store *sourceMapsStoreImpl) getSourceMapContent(sourceURL string, release string) (content []byte, sourceMapURL string, err error) {
 	// Attempt to find the source map in the filesystem first.
 	for _, loc := range store.locs {
+		if hasHttpPrefix(loc.Path) {
+			continue
+		}
+
 		content, sourceMapURL, err = store.getSourceMapFromFileSystem(sourceURL, release, loc)
 		if content != nil || err != nil {
 			return content, sourceMapURL, err
 		}
 	}
 
+	// Attempt to find the source map in the remote locations.
+	for _, loc := range store.locs {
+		if !(hasHttpPrefix(loc.Path)) {
+			continue
+		}
+
+		content, sourceMapURL, err = store.getSourceMapFromRemote(sourceURL, release, loc)
+		if content != nil || err != nil {
+			return content, sourceMapURL, err
+		}
+	}
+
 	// Attempt to download the sourcemap if enabled.
-	if strings.HasPrefix(sourceURL, "http") && urlMatchesOrigins(sourceURL, store.args.DownloadFromOrigins) && store.args.Download {
+	if store.args.Download && hasHttpPrefix(sourceURL) && urlMatchesOrigins(sourceURL, store.args.DownloadFromOrigins) {
 		return store.downloadSourceMapContent(sourceURL)
 	}
 	return nil, "", nil
@@ -242,6 +258,34 @@ func (store *sourceMapsStoreImpl) getSourceMapFromFileSystem(sourceURL string, r
 	return content, sourceURL, err
 }
 
+func (store *sourceMapsStoreImpl) getSourceMapFromRemote(sourceURL string, release string, loc *sourcemapFileLocation) (content []byte, sourceMapURL string, err error) {
+	if len(sourceURL) == 0 || !strings.HasPrefix(sourceURL, loc.MinifiedPathPrefix) || strings.HasSuffix(sourceURL, "/") {
+		return nil, "", nil
+	}
+
+	var rootPath bytes.Buffer
+
+	err = loc.pathTemplate.Execute(&rootPath, struct{ Release string }{Release: cleanFilePathPart(release)})
+	if err != nil {
+		return nil, "", err
+	}
+
+	subPath := strings.TrimPrefix(strings.Split(sourceURL, "?")[0], loc.MinifiedPathPrefix) + ".map"
+	mapURL, err := url.JoinPath(rootPath.String(), subPath)
+	if err != nil {
+		level.Debug(store.log).Log("msg", "failed to construct sourcemap url for remote location", "base_path", rootPath, "sub_path", subPath, "err", err)
+		return nil, "", err
+	}
+
+	content, err = store.downloadFileContents(mapURL)
+	if err != nil {
+		level.Debug(store.log).Log("msg", "failed to download sourcemap file from remote location", "url", mapURL, "err", err)
+		return nil, "", err
+	}
+
+	return content, sourceURL, err
+}
+
 func (store *sourceMapsStoreImpl) downloadSourceMapContent(sourceURL string) (content []byte, resolvedSourceMapURL string, err error) {
 	level.Debug(store.log).Log("msg", "attempting to download source file", "url", sourceURL)
 
@@ -341,6 +385,10 @@ func urlMatchesOrigins(URL string, origins []string) bool {
 	return false
 }
 
+func hasHttpPrefix(URL string) bool {
+	return strings.HasPrefix(URL, "http://") || strings.HasPrefix(URL, "https://")
+}
+
 func cleanFilePathPart(x string) string {
 	return strings.TrimLeft(strings.ReplaceAll(strings.ReplaceAll(x, "\\", ""), "/", ""), ".")
 }