feat(rum): categorize transactions based on current url

packages/rum-core/src/common/slugify.js

@@ -0,0 +1,98 @@
+/**
+ * MIT License
+ *
+ * Copyright (c) 2017-present, Elasticsearch BV
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ *
+ */
+
+import Url from './url'
+
+/**
+ * Converts URL path tree in to slug based on tree depth
+ */
+export default function slugifyUrl(urlStr, depth = 2) {
+  const parsedUrl = new Url(urlStr)
+  const { query, path } = parsedUrl
+  const pathParts = path.substring(1).split('/')
+
+  const redactString = ':id'
+  const end = '**'
+  const specialCharsRegex = /\W|_/g
+  const digitsRegex = /[0-9]/g
+  const lowerCaseRegex = /[a-z]/g
+  const upperCaseRegex = /[A-Z]/g
+
+  const redactedParts = []
+  let redactedBefore = false
+
+  for (let index = 0; index < pathParts.length; index++) {
+    const part = pathParts[index]
+
+    if (redactedBefore || index > depth - 1) {
+      if (part) {
+        redactedParts.push(end)
+      }
+      break
+    }
+
+    const numberOfSpecialChars = (part.match(specialCharsRegex) || []).length
+    if (numberOfSpecialChars >= 2) {
+      redactedParts.push(redactString)
+      redactedBefore = true
+      continue
+    }
+
+    const numberOfDigits = (part.match(digitsRegex) || []).length
+    if (
+      numberOfDigits > 3 ||
+      (part.length > 3 && numberOfDigits / part.length >= 0.3)
+    ) {
+      redactedParts.push(redactString)
+      redactedBefore = true
+      continue
+    }
+
+    const numberofUpperCase = (part.match(upperCaseRegex) || []).length
+    const numberofLowerCase = (part.match(lowerCaseRegex) || []).length
+    const lowerCaseRate = numberofLowerCase / part.length
+    const upperCaseRate = numberofUpperCase / part.length
+    if (
+      part.length > 5 &&
+      ((upperCaseRate > 0.3 && upperCaseRate < 0.6) ||
+        (lowerCaseRate > 0.3 && lowerCaseRate < 0.6))
+    ) {
+      redactedParts.push(redactString)
+      redactedBefore = true
+      continue
+    }
+
+    part && redactedParts.push(part)
+  }
+
+  const redacted =
+    '/' +
+    (redactedParts.length >= 2
+      ? redactedParts.join('/')
+      : redactedParts.join('')) +
+    (query ? '?{query}' : '')
+
+  return redacted
+}

packages/rum-core/src/common/url.js

@@ -78,7 +78,7 @@ const RULES = [
 ]
 const PROTOCOL_REGEX = /^([a-z][a-z0-9.+-]*:)?(\/\/)?([\S\s]*)/i
 
-class Url {
+export default class Url {
   constructor(url) {
     let { protocol, address, slashes } = this.extractProtocol(url || '')
     const relative = !protocol && !slashes
@@ -215,5 +215,3 @@ class Url {
     }
   }
 }
-
-export default Url

packages/rum-core/src/performance-monitoring/transaction-service.js

@@ -48,6 +48,7 @@ import {
 } from '../common/constants'
 import { addTransactionContext } from '../common/context'
 import { __DEV__, state } from '../state'
+import slugifyUrl from '../common/slugify'
 
 class TransactionService {
   constructor(logger, config) {
@@ -240,7 +241,7 @@ class TransactionService {
         if (lastHiddenStart >= tr._start) {
           if (__DEV__) {
             this._logger.debug(
-              `transaction(${tr.id}, ${tr.name}, ${tr.type}) was discarded! The page was hidden during the transaction!`
+              `transaction(${tr.id}, ${name}, ${type}) was discarded! The page was hidden during the transaction!`
             )
           }
           return
@@ -274,6 +275,13 @@ class TransactionService {
             tr.spans.push(createTotalBlockingTimeSpan(metrics.tbt))
           }
         }
+        /**
+         * Categorize the transaction based on the current location
+         */
+        if (tr.name === NAME_UNKNOWN) {
+          tr.name = slugifyUrl(window.location.href)
+        }
+
         captureNavigation(tr)
 
         /**

packages/rum-core/test/common/slugify.spec.js

@@ -0,0 +1,68 @@
+/**
+ * MIT License
+ *
+ * Copyright (c) 2017-present, Elasticsearch BV
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ *
+ */
+
+import slugifyUrl from '../../src/common/slugify'
+
+describe('Slug URL', () => {
+  const validate = (before, after, depth) => {
+    expect(slugifyUrl(before, depth)).toBe(after)
+  }
+
+  it('accept depth parameter', () => {
+    validate('/a/b/c/d', '/a/b/**')
+    validate('/a/b/c/d', '/a/**', 1)
+  })
+
+  it('handle trailing slash', () => {
+    validate('/a/', '/a')
+    validate('/a', '/a')
+    validate('/', '/')
+  })
+
+  it('handle query param', () => {
+    validate('/a/b/?id=hello', '/a/b?{query}')
+    validate('/?foo=bar&bar=baz', '/?{query}')
+  })
+
+  it('redact digits', () => {
+    validate('/a/123', '/a/123')
+    validate('/a/12312bcdd23', '/a/:id')
+    validate('/a/B00I8BIC9E', '/a/:id')
+    // uuid
+    validate('/a/786c1883-dc0b-495f-a16b-6c53fb20b272', '/a/:id')
+  })
+
+  it('redact special characters', () => {
+    validate('/a-b-c-d', '/:id')
+    validate('/a~b-c', '/:id')
+    validate('/a~b-c/d/e/f', '/:id/**')
+    validate('/b%c%d-ef', '/:id')
+  })
+
+  it('react mix of lower-uppercase characters', () => {
+    validate('/abcDEF', '/:id')
+    validate('/a1W9FtW5DnkyP3Bucng4aLvqT/edit', '/:id/**')
+  })
+})