Issue 6538, 6781 - Implement script parsing for snippets

lib/snippets.js

 /*
  * This file is part of Adblock Plus <https://adblockplus.org/>,
  * Copyright (C) 2006-present eyeo GmbH
  *
  * Adblock Plus is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 3 as
  * published by the Free Software Foundation.
  *
  * Adblock Plus is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
  * along with Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 "use strict";
 
 /**
  * @fileOverview Snippets implementation.
  */
 
 const {Filter} = require("./filterClasses");
 
+const singleCharacterEscapes = new Map([
+  ["n", "\n"], ["r", "\r"], ["t", "\t"]
+]);
+
 let filters = new Set();
 
 /**
  * Container for snippet filters
  * @class
  */
 let Snippets = {
   /**
    * Removes all known filters
    */
@@ skipping 32 matching lines @@
     {
       let filter = Filter.fromText(text);
       if (filter.isActiveOnDomain(domain))
         result.push(filter.script);
     }
     return result;
   }
 };
 
 exports.Snippets = Snippets;
+
+/**
+ * Parses a script and returns a list of all its commands and their arguments
+ * @param {string} script
+ * @return {Array.<string[]>}
+ */
+function parseScript(script)
+{
+  let tree = [];
+
+  // Whether the next character should be treated as an escape sequence.

[kzar, 2018/07/12 10:30:37]

I don't these new comments add much, and they are kind of patronising. I'd
prefer to remove them.

[Manish Jethani, 2018/07/12 10:57:49]

Well I'm glad you think so, because I don't like to repeat the logic in the
comments, it's harder to maintain (the comments need to be kept up to date).

Done.

+  let escape = false;
+
+  // Whether we are within a quoted sequence.
+  let withinQuotes = false;
+
+  // The Unicode code point following a "\u"
+  let unicodeEscape = null;
+
+  let call = [];
+  let argument = "";
+
+  // The terminating semicolon for the last command is optional; we add one
+  // here to make our loop consistent.
+  for (let character of script.trim() + ";")
+  {
+    if (unicodeEscape != null)
+    {
+      unicodeEscape += character;
+
+      if (unicodeEscape.length == 4)
+      {
+        // Consider the Unicode escape only if it parses as a valid code point.
+        let codePoint = parseInt(unicodeEscape, 16);
+        if (!isNaN(codePoint))
+          argument += String.fromCodePoint(codePoint);
+
+        unicodeEscape = null;
+      }
+    }
+    else if (escape)
+    {
+      escape = false;
+
+      if (character == "u")
+        unicodeEscape = "";
+      else
+        argument += singleCharacterEscapes.get(character) || character;
+    }
+    else if (character == "\\")
+    {
+      escape = true;
+    }
+    else if (character == "'")
+    {
+      withinQuotes = !withinQuotes;

[kzar, 2018/07/12 10:30:37]

Nice, I think this variable name is an improvement.

+    }
+    // Normally a semicolon or a whitespace character marks the end of an
+    // argument, but within quotes these characters are taken literally and
+    // included in the argument.
+    else if (withinQuotes || character != ";" && !/\s/u.test(character))
+    {
+      argument += character;
+    }
+    else
+    {
+      if (argument)
+      {
+        call.push(argument);
+        argument = "";
+      }
+
+      if (character == ";" && call.length > 0)
+      {
+        tree.push(call);
+        call = [];
+      }
+    }
+  }
+
+  return tree;
+}
+
+exports.parseScript = parseScript;