Google Tag Manager data layer events support

README.md

@@ -101,18 +101,19 @@ See [schema.json](schema.json) for a JSON Schema of the output.
 
 | Library | JavaScript/TypeScript | Python | Ruby | Go |
 |---------|:---------------------:|:------:|:----:|:--:|
-| Google Analytics  | ✅ | ❌ | ❌ | ❌ |
-| Segment           | ✅ | ✅ | ✅ | ✅ |
-| Mixpanel          | ✅ | ✅ | ✅ | ✅ |
-| Amplitude         | ✅ | ✅ | ❌ | ✅ |
-| Rudderstack       | ✅ | ✅ | ✳️ | ✳️ |
-| mParticle         | ✅ | ❌ | ❌ | ❌ |
-| PostHog           | ✅ | ✅ | ✅ | ✅ |
-| Pendo             | ✅ | ❌ | ❌ | ❌ |
-| Heap              | ✅ | ❌ | ❌ | ❌ |
-| Snowplow          | ✅ | ✅ | ✅ | ✅ |
-| Datadog RUM       | ✅ | ❌ | ❌ | ❌ |
-| Custom Function   | ✅ | ✅ | ✅ | ✅ |
+| Google Analytics   | ✅ | ❌ | ❌ | ❌ |
+| Google Tag Manager | ✅ | ❌ | ❌ | ❌ |
+| Segment            | ✅ | ✅ | ✅ | ✅ |
+| Mixpanel           | ✅ | ✅ | ✅ | ✅ |
+| Amplitude          | ✅ | ✅ | ❌ | ✅ |
+| Rudderstack        | ✅ | ✅ | ✳️ | ✳️ |
+| mParticle          | ✅ | ❌ | ❌ | ❌ |
+| PostHog            | ✅ | ✅ | ✅ | ✅ |
+| Pendo              | ✅ | ❌ | ❌ | ❌ |
+| Heap               | ✅ | ❌ | ❌ | ❌ |
+| Snowplow           | ✅ | ✅ | ✅ | ✅ |
+| Datadog RUM        | ✅ | ❌ | ❌ | ❌ |
+| Custom Function    | ✅ | ✅ | ✅ | ✅ |
 
 ✳️ Rudderstack's SDKs often use the same format as Segment, so Rudderstack events may be detected as Segment events.
 
@@ -130,6 +131,24 @@ See [schema.json](schema.json) for a JSON Schema of the output.
   ```
 </details>
 
+<details>
+  <summary>Google Tag Manager</summary>
+
+  **JavaScript/TypeScript**
+  ```js
+  dataLayer.push({
+    event: '<event_name>',
+    '<property_name>': '<property_value>'
+  });
+
+  // Or via window
+  window.dataLayer.push({
+    event: '<event_name>',
+    '<property_name>': '<property_value>'
+  });
+  ```
+</details>
+
 <details>
   <summary>Segment</summary>
 

schema.json

@@ -68,6 +68,7 @@
                       "heap",
                       "snowplow",
                       "datadog",
+                      "gtm",
                       "custom",
                       "unknown"
                     ],

src/analyze/javascript/constants.js

@@ -81,6 +81,12 @@ const ANALYTICS_PROVIDERS = {
     objectNames: ['datadogRum', 'DD_RUM'],
     methodName: 'addAction',
     type: 'member'
+  },
+  GOOGLE_TAG_MANAGER: {
+    name: 'gtm',
+    objectNames: ['dataLayer'],
+    methodName: 'push',
+    type: 'member'
   }
 };
 

src/analyze/javascript/extractors/event-extractor.js

@@ -20,6 +20,7 @@ const EXTRACTION_STRATEGIES = {
   googleanalytics: extractGoogleAnalyticsEvent,
   snowplow: extractSnowplowEvent,
   mparticle: extractMparticleEvent,
+  gtm: extractGTMEvent,
   custom: extractCustomEvent,
   default: extractDefaultEvent
 };
@@ -105,6 +106,43 @@ function extractMparticleEvent(node, constantMap) {
   return { eventName, propertiesNode };
 }
 
+/**
+ * Extracts Google Tag Manager event data
+ * @param {Object} node - CallExpression node
+ * @param {Object} constantMap - Collected constant map
+ * @returns {EventData}
+ */
+function extractGTMEvent(node, constantMap) {
+  if (!node.arguments || node.arguments.length === 0) {
+    return { eventName: null, propertiesNode: null };
+  }
+
+  // dataLayer.push({ event: 'event_name', property1: 'value1', property2: 'value2' })
+  const firstArg = node.arguments[0];
+
+  if (firstArg.type !== NODE_TYPES.OBJECT_EXPRESSION) {
+    return { eventName: null, propertiesNode: null };
+  }
+
+  // Find the 'event' property
+  const eventProperty = findPropertyByKey(firstArg, 'event');
+  if (!eventProperty) {
+    return { eventName: null, propertiesNode: null };
+  }
+
+  const eventName = getStringValue(eventProperty.value, constantMap);
+
+  // Create a modified properties node without the 'event' property
+  const modifiedPropertiesNode = {
+    ...firstArg,
+    properties: firstArg.properties.filter(prop => 
+      prop.key && (prop.key.name !== 'event' && prop.key.value !== 'event')
+    )
+  };
+
+  return { eventName, propertiesNode: modifiedPropertiesNode };
+}
+
 /**
  * Default event extraction for standard providers
  * @param {Object} node - CallExpression node

src/analyze/typescript/constants.js

@@ -81,6 +81,12 @@ const ANALYTICS_PROVIDERS = {
     objectNames: ['datadogRum', 'DD_RUM'],
     methodName: 'addAction',
     type: 'member'
+  },
+  GOOGLE_TAG_MANAGER: {
+    name: 'gtm',
+    objectNames: ['dataLayer'],
+    methodName: 'push',
+    type: 'member'
   }
 };
 

src/analyze/typescript/extractors/event-extractor.js

@@ -21,6 +21,7 @@ const EXTRACTION_STRATEGIES = {
   googleanalytics: extractGoogleAnalyticsEvent,
   snowplow: extractSnowplowEvent,
   mparticle: extractMparticleEvent,
+  gtm: extractGTMEvent,
   custom: extractCustomEvent,
   default: extractDefaultEvent
 };
@@ -126,6 +127,60 @@ function extractMparticleEvent(node, checker, sourceFile) {
   return { eventName, propertiesNode };
 }
 
+/**
+ * Extracts Google Tag Manager event data
+ * @param {Object} node - CallExpression node
+ * @param {Object} checker - TypeScript type checker
+ * @param {Object} sourceFile - TypeScript source file
+ * @returns {EventData}
+ */
+function extractGTMEvent(node, checker, sourceFile) {
+  if (!node.arguments || node.arguments.length === 0) {
+    return { eventName: null, propertiesNode: null };
+  }
+
+  // dataLayer.push({ event: 'event_name', property1: 'value1', property2: 'value2' })
+  const firstArg = node.arguments[0];
+
+  if (!ts.isObjectLiteralExpression(firstArg)) {
+    return { eventName: null, propertiesNode: null };
+  }
+
+  // Find the 'event' property
+  const eventProperty = findPropertyByKey(firstArg, 'event');
+  if (!eventProperty) {
+    return { eventName: null, propertiesNode: null };
+  }
+
+  const eventName = getStringValue(eventProperty.initializer, checker, sourceFile);
+
+  // Create a modified properties node without the 'event' property
+  const modifiedProperties = firstArg.properties.filter(prop => {
+    if (ts.isPropertyAssignment(prop) && prop.name) {
+      if (ts.isIdentifier(prop.name)) {
+        return prop.name.escapedText !== 'event';
+      }
+      if (ts.isStringLiteral(prop.name)) {
+        return prop.name.text !== 'event';
+      }
+    }
+    return true;
+  });
+
+  // Create a synthetic object literal with the filtered properties
+  const modifiedPropertiesNode = ts.factory.createObjectLiteralExpression(modifiedProperties);
+
+  // Copy source positions for proper analysis
+  if (firstArg.pos !== undefined) {
+    modifiedPropertiesNode.pos = firstArg.pos;
+  }
+  if (firstArg.end !== undefined) {
+    modifiedPropertiesNode.end = firstArg.end;
+  }
+
+  return { eventName, propertiesNode: modifiedPropertiesNode };
+}
+
 /**
  * Custom extraction
  * @param {Object} node - CallExpression node

tests/analyzeJavaScript.test.js

@@ -16,7 +16,7 @@ test.describe('analyzeJsFile', () => {
     // Sort events by line number for consistent ordering
     events.sort((a, b) => a.line - b.line);
 
-    assert.strictEqual(events.length, 15);
+    assert.strictEqual(events.length, 19);
 
     // Test Google Analytics event
     const gaEvent = events.find(e => e.eventName === 'purchase' && e.source === 'googleanalytics');
@@ -232,7 +232,7 @@ test.describe('analyzeJsFile', () => {
     const events = analyzeJsFile(testFilePath, null);
 
     // Should find all events except the custom one
-    assert.strictEqual(events.length, 14);
+    assert.strictEqual(events.length, 18);
     assert.strictEqual(events.find(e => e.source === 'custom'), undefined);
   });
 

tests/analyzeTypeScript.test.js

@@ -37,7 +37,7 @@ test.describe('analyzeTsFile', () => {
     // Sort events by line number for consistent ordering
     events.sort((a, b) => a.line - b.line);
 
-    assert.strictEqual(events.length, 23);
+    assert.strictEqual(events.length, 25);
 
     // Test Google Analytics event
     const gaEvent = events.find(e => e.eventName === 'order_completed' && e.source === 'googleanalytics');
@@ -405,7 +405,7 @@ test.describe('analyzeTsFile', () => {
     const events = analyzeTsFile(testFilePath, program, null);
 
     // Should find all events except the custom ones
-    assert.strictEqual(events.length, 16);
+    assert.strictEqual(events.length, 18);
     assert.strictEqual(events.find(e => e.source === 'custom'), undefined);
   });
 

tests/fixtures/javascript/main.js

@@ -211,3 +211,51 @@ mixpanel.track(TRACKING_EVENTS_FROZEN.ECOMMERCE_PURCHASE, {
   total: 99.99,
   items: ['sku_1', 'sku_2']
 });
+
+// -----------------------------------------------------------------------------
+// Google Tag Manager (GTM) tracking examples
+// -----------------------------------------------------------------------------
+
+// GTM example 1: window.dataLayer.push
+window.dataLayer.push({
+  'event': 'formSubmission',
+  'formId': 'contactForm',
+  'formLocation': 'footer'
+});
+
+// GTM example 2: dataLayer.push (without window)
+dataLayer.push({
+  'event': 'userRegistration',
+  'userId': 'user123',
+  'source': 'organic',
+  'plan': 'premium'
+});
+
+// GTM example 3: complex properties
+window.dataLayer.push({
+  'event': 'ecommerce_purchase',
+  'transactionId': 'txn_123',
+  'value': 99.99,
+  'currency': 'USD',
+  'items': [
+    {
+      'item_id': 'sku_001',
+      'item_name': 'Product A',
+      'price': 49.99
+    },
+    {
+      'item_id': 'sku_002', 
+      'item_name': 'Product B',
+      'price': 50.00
+    }
+  ]
+});
+
+function gtmTestFunction() {
+  // GTM example 4: inside a function
+  dataLayer.push({
+    'event': 'buttonClick',
+    'buttonText': 'Subscribe Now',
+    'location': 'header'
+  });
+}

tests/fixtures/javascript/tracking-schema-javascript.yaml

@@ -316,3 +316,55 @@ events:
         type: string
       success:
         type: boolean
+  formSubmission:
+    implementations:
+      - path: main.js
+        line: 220
+        function: global
+        destination: gtm
+    properties:
+      formId:
+        type: string
+      formLocation:
+        type: string
+  userRegistration:
+    implementations:
+      - path: main.js
+        line: 227
+        function: global
+        destination: gtm
+    properties:
+      userId:
+        type: string
+      source:
+        type: string
+      plan:
+        type: string
+  ecommerce_purchase:
+    implementations:
+      - path: main.js
+        line: 235
+        function: global
+        destination: gtm
+    properties:
+      transactionId:
+        type: string
+      value:
+        type: number
+      currency:
+        type: string
+      items:
+        type: array
+        items:
+          type: object
+  buttonClick:
+    implementations:
+      - path: main.js
+        line: 256
+        function: gtmTestFunction
+        destination: gtm
+    properties:
+      buttonText:
+        type: string
+      location:
+        type: string