@crawlee/utils 3.17.1-beta.51 → 3.17.1-beta.53

package/internals/social.js

@@ -10,7 +10,10 @@ const tslib_1 = require("tslib");
 const cheerio = tslib_1.__importStar(require("cheerio"));
 const cheerio_1 = require("./cheerio");
 // Regex inspired by https://zapier.com/blog/extract-links-email-phone-regex/
-const EMAIL_REGEX_STRING = '(?:[a-z0-9!#$%&\'*+/=?^_`{|}~-]+(?:\\.[a-z0-9!#$%&\'*+/=?^_`{|}~-]+)*|"(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21\x23-\x5b\x5d-\x7f]|\\\\[\x01-\x09\x0b\x0c\x0e-\x7f])*")@(?:(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9])?|\\[(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?|[a-z0-9-]*[a-z0-9]:(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21-\x5a\x53-\x7f]|\\\\[\x01-\x09\x0b\x0c\x0e-\x7f])+)\\])';
+// The dot-atom local part and domain labels use RFC 5321 length bounds ({1,64}, {0,62})
+// instead of unbounded quantifiers to avoid quadratic backtracking (ReDoS) on long
+// dotted or hyphenated inputs, e.g. text scraped by parseHandlesFromHtml().
+const EMAIL_REGEX_STRING = '(?:[a-z0-9!#$%&\'*+/=?^_`{|}~-]{1,64}(?:\\.[a-z0-9!#$%&\'*+/=?^_`{|}~-]{1,64}){0,32}|"(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21\x23-\x5b\x5d-\x7f]|\\\\[\x01-\x09\x0b\x0c\x0e-\x7f])*")@(?:(?:[a-z0-9](?:[a-z0-9-]{0,62}[a-z0-9])?\\.)+[a-z0-9](?:[a-z0-9-]{0,62}[a-z0-9])?|\\[(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?|[a-z0-9-]*[a-z0-9]:(?:[\x01-\x08\x0b\x0c\x0e-\x1f\x21-\x5a\x53-\x7f]|\\\\[\x01-\x09\x0b\x0c\x0e-\x7f])+)\\])';
 /**
  * Regular expression to exactly match a single email address.
  * It has the following form: `/^...$/i`.

package/internals/systemInfoV2/cpu-info.js

@@ -51,6 +51,7 @@ function getCurrentCpuTicks() {
     }, { idle: 0, total: 0 });
     const idleTicksDelta = ticks.idle - previousTicks.idle;
     const totalTicksDelta = ticks.total - previousTicks.total;
+    Object.assign(previousTicks, ticks);
     return totalTicksDelta ? 1 - idleTicksDelta / totalTicksDelta : 0;
 }
 /**

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@crawlee/utils",
-    "version": "3.17.1-beta.51",
+    "version": "3.17.1-beta.53",
     "description": "A set of shared utilities that can be used by crawlers",
     "engines": {
         "node": ">=16.0.0"
@@ -49,7 +49,7 @@
     "dependencies": {
         "@apify/log": "^2.4.0",
         "@apify/ps-tree": "^1.2.0",
-        "@crawlee/types": "3.17.1-beta.51",
+        "@crawlee/types": "3.17.1-beta.53",
         "@types/sax": "^1.2.7",
         "cheerio": "1.0.0-rc.12",
         "file-type": "^21.3.1",
@@ -70,5 +70,5 @@
             }
         }
     },
-    "gitHead": "5185ab2c00a7fce4eaecb7e16c172b6077779a64"
+    "gitHead": "59a0d19d96e7402cd8d0edd8b90ad4f5abc8f7db"
 }