Issue 6538, 6781 - Implement support for snippet filters

lib/filterClasses.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
@@ skipping 66 matching lines @@
   }
 };
 
 /**
  * Cache for known filters, maps string representation to filter objects.
  * @type {Map.<string,Filter>}
  */
 Filter.knownFilters = new Map();
 
 /**
- * Regular expression that script filters should match
+ * Regular expression that content filters should match
  * @type {RegExp}
  */
-Filter.scriptRegExp = /^([^/*|@"!]*?)#([@?$])?#(.+)$/;
+Filter.contentRegExp = /^([^/*|@"!]*?)#([@?$])?#(.+)$/;
 /**
  * Regular expression that RegExp filters specified as RegExps should match
  * @type {RegExp}
  */
 Filter.regexpRegExp = /^(@@)?\/.*\/(?:\$~?[\w-]+(?:=[^,\s]+)?(?:,~?[\w-]+(?:=[^,\s]+)?)*)?$/;
 /**
  * Regular expression that options on a RegExp filter should match
  * @type {RegExp}
  */
 Filter.optionsRegExp = /\$(~?[\w-]+(?:=[^,]+)?(?:,~?[\w-]+(?:=[^,]+)?)*)$/;
 /**
  * Regular expression that matches an invalid Content Security Policy
  * @type {RegExp}
  */
 Filter.invalidCSPRegExp = /(;|^) ?(base-uri|referrer|report-to|report-uri|upgrade-insecure-requests)\b/i;
 
 /**
  * Creates a filter of correct type from its text representation - does the
  * basic parsing and calls the right constructor then.
  *
  * @param {string} text   as in Filter()
  * @return {Filter}
  */
 Filter.fromText = function(text)
 {
   let filter = Filter.knownFilters.get(text);
   if (filter)
     return filter;
 
-  let match = text.includes("#") ? Filter.scriptRegExp.exec(text) : null;
+  let match = text.includes("#") ? Filter.contentRegExp.exec(text) : null;
   if (match)
   {
     let propsMatch;
     if (!match[2] &&
         (propsMatch = /\[-abp-properties=(["'])([^"']+)\1\]/.exec(match[3])))
     {
       // This is legacy CSS properties syntax, convert to current syntax
       let prefix = match[3].substr(0, propsMatch.index);
       let expression = propsMatch[2];
       let suffix = match[3].substr(propsMatch.index + propsMatch[0].length);
       return Filter.fromText(`${match[1]}#?#` +
           `${prefix}:-abp-properties(${expression})${suffix}`);
     }
 
-    if (match[2] == "$")
-      filter = new SnippetFilter(text, match[1], match[3]);
-    else
-      filter = ElemHideBase.fromText(text, match[1], match[2], match[3]);
+    filter = ContentFilter.fromText(text, match[1], match[2], match[3]);
   }
   else if (text[0] == "!")
     filter = new CommentFilter(text);
   else
     filter = RegExpFilter.fromText(text);
 
   Filter.knownFilters.set(filter.text, filter);
   return filter;
 };
 
@@ skipping 29 matching lines @@
   if (!text)
     return text;
 
   // Remove line breaks, tabs etc
   text = text.replace(/[^\S ]+/g, "");
 
   // Don't remove spaces inside comments
   if (/^ *!/.test(text))
     return text.trim();
 
-  // Special treatment for script filters, right side is allowed to contain
+  // Special treatment for content filters, right side is allowed to contain
   // spaces
-  if (Filter.scriptRegExp.test(text))
-  {
-    let [, domains, separator, script] = /^(.*?)(#[@?$]?#?)(.*)$/.exec(text);
-    return domains.replace(/ +/g, "") + separator + script.trim();
+  if (Filter.contentRegExp.test(text))
+  {
+    let [, domains, separator, body] = /^(.*?)(#[@?$]?#?)(.*)$/.exec(text);
+    return domains.replace(/ +/g, "") + separator + body.trim();
   }
 
   // For most regexp filters we strip all spaces, but $csp filter options
   // are allowed to contain single (non trailing) spaces.
   let strippedText = text.replace(/ +/g, "");
   if (!strippedText.includes("$") || !/\bcsp=/i.test(strippedText))
     return strippedText;
 
   let optionsMatch = Filter.optionsRegExp.exec(strippedText);
   if (!optionsMatch)
@@ skipping 190 matching lines @@
    */
   domainSourceIsLowerCase: false,
 
   /**
    * Map containing domains that this filter should match on/not match
    * on or null if the filter should match on all domains
    * @type {?Map.<string,boolean>}
    */
   get domains()
   {
+    let prop = Object.getOwnPropertyDescriptor(this, "_domains");
+    if (prop)
+    {
+      let {value} = prop;
+      return typeof value == "string" ?
+               new Map([[value, true], ["", false]]) : value;
+    }
+
     let domains = null;
 
     if (this.domainSource)
     {
       let source = this.domainSource;
       if (!this.domainSourceIsLowerCase)
       {
         // RegExpFilter already have lowercase domains
         source = source.toLowerCase();
       }
       let list = source.split(this.domainSeparator);
       if (list.length == 1 && list[0][0] != "~")
       {
         // Fast track for the common one-domain scenario
-        domains = new Map([["", false], [list[0], true]]);
+        domains = list[0];
       }
       else
       {
         let hasIncludes = false;
         for (let i = 0; i < list.length; i++)
         {
           let domain = list[i];
           if (domain == "")
             continue;
 
@@ skipping 14 matching lines @@
 
           domains.set(domain, include);
         }
         if (domains)
           domains.set("", !hasIncludes);
       }
 
       this.domainSource = null;
     }
 
-    Object.defineProperty(this, "domains", {value: domains, enumerable: true});
+    Object.defineProperty(this, "_domains", {value: domains});
     return this.domains;
   },
 
   /**
    * Array containing public keys of websites that this filter should apply to
    * @type {?string[]}
    */
   sitekeys: null,
 
   /**
@@ skipping 517 matching lines @@
   RegExpFilter.call(this, text, regexpSource, contentType, matchCase, domains,
                     thirdParty, sitekeys);
 }
 exports.WhitelistFilter = WhitelistFilter;
 
 WhitelistFilter.prototype = extend(RegExpFilter, {
   type: "whitelist"
 });
 
 /**
- * Base class for script filters
+ * Base class for content filters
  * @param {string} text see {@link Filter Filter()}
  * @param {string} [domains] Host names or domains the filter should be
  *                           restricted to
- * @param {string} script    Script that should be executed
+ * @param {string} body      The body of the filter
  * @constructor
  * @augments ActiveFilter
  */
-function ScriptFilter(text, domains, script)

[hub, 2018/06/22 20:45:39]

I'm not convinced with the renaming to "ScriptFilter". I'd prefer somnething
like "ContentFilter" since we are manipulating the content and it is run by the
content script.

But this is just a personal preference.

[Manish Jethani, 2018/06/23 18:24:08]

That sounds reasonable to me.

Done.

+function ContentFilter(text, domains, body)
 {
   ActiveFilter.call(this, text, domains || null);
 
-  this.script = script;
-}
-exports.ScriptFilter = ScriptFilter;
-
-ScriptFilter.prototype = extend(ActiveFilter, {
+  this.body = body;
+}
+exports.ContentFilter = ContentFilter;
+
+ContentFilter.prototype = extend(ActiveFilter, {
   /**
    * @see ActiveFilter.domainSeparator
    */
   domainSeparator: ",",
 
   /**
-   * Script that should be executed
+   * The body of the filter
    * @type {string}
    */
-  script: null
-});
-
-/*
- * Base class for element hiding filters
- * @param {string} text see {@link Filter Filter()}
- * @param {string} [domains] see {@link ScriptFilter ScriptFilter()}
- * @param {string} selector  CSS selector for the HTML elements that should be
- *                           hidden
- * @constructor
- * @augments ScriptFilter
- */
-function ElemHideBase(text, domains, selector)
-{
-  ScriptFilter.call(this, text, domains, selector);
-
-  // Braces are being escaped to prevent CSS rule injection.
-  this.selector = this.script.replace("{", "\\7B ").replace("}", "\\7D ");
-}
-exports.ElemHideBase = ElemHideBase;
-
-ElemHideBase.prototype = extend(ScriptFilter, {
-  /**
-   * CSS selector for the HTML elements that should be hidden
-   * @type {string}
-   */
-  selector: null
-});
-
-/**
- * Creates an element hiding filter from a pre-parsed text representation
+  body: null
+});
+
+/**
+ * Creates a content filter from a pre-parsed text representation
  *
  * @param {string} text         same as in Filter()
  * @param {string} [domains]
  *   domains part of the text representation
  * @param {string} [type]
-*    rule type, either empty or @ (exception) or ? (emulation rule)
- * @param {string} selector     raw CSS selector
+ *   rule type, either:
+ *     <li>"" for an element hiding filter</li>

[Manish Jethani, 2018/07/11 13:04:26]

Using just "-" doesn't work in the HTML version, but we can use <li> instead.

We should really switch to Markdown in the comments.

[kzar, 2018/07/11 17:17:52]

Acknowledged.

+ *     <li>"@" for an element hiding exception filter</li>
+ *     <li>"?" for an element hiding emulation filter</li>
+ *     <li>"$" for a snippet filter</li>
+ * @param {string} body
+ *   body part of the text representation, either a CSS selector or a snippet
+ *   script
  * @return {ElemHideFilter|ElemHideException|
- *          ElemHideEmulationFilter|InvalidFilter}
- */
-ElemHideBase.fromText = function(text, domains, type, selector)
-{
-  // We don't allow ElemHide filters which have any empty domains.
-  // Note: The ElemHide.prototype.domainSeparator is duplicated here, if that
-  // changes this must be changed too.
+ *          ElemHideEmulationFilter|SnippetFilter|InvalidFilter}
+ */
+ContentFilter.fromText = function(text, domains, type, body)
+{
+  // We don't allow content filters which have any empty domains.
+  // Note: The ContentFilter.prototype.domainSeparator is duplicated here, if
+  // that changes this must be changed too.
   if (domains && /(^|,)~?(,|$)/.test(domains))
     return new InvalidFilter(text, "filter_invalid_domain");
 
   if (type == "@")
-    return new ElemHideException(text, domains, selector);
+    return new ElemHideException(text, domains, body);
+
+  if (type == "$")
+    return new SnippetFilter(text, domains, body);
 
   if (type == "?")
   {
     // Element hiding emulation filters are inefficient so we need to make sure
     // that they're only applied if they specify active domains
     if (!/,[^~][^,.]*\.[^,]/.test("," + domains))
       return new InvalidFilter(text, "filter_elemhideemulation_nodomain");
 
-    return new ElemHideEmulationFilter(text, domains, selector);
-  }
-
-  return new ElemHideFilter(text, domains, selector);
+    return new ElemHideEmulationFilter(text, domains, body);
+  }
+
+  return new ElemHideFilter(text, domains, body);
 };
+
+/**
+ * Base class for element hiding filters
+ * @param {string} text see {@link Filter Filter()}
+ * @param {string} [domains] see {@link ContentFilter ContentFilter()}
+ * @param {string} selector  CSS selector for the HTML elements that should be
+ *                           hidden
+ * @constructor
+ * @augments ContentFilter
+ */
+function ElemHideBase(text, domains, selector)
+{
+  ContentFilter.call(this, text, domains, selector);
+}
+exports.ElemHideBase = ElemHideBase;
+
+ElemHideBase.prototype = extend(ContentFilter, {
+  /**
+   * CSS selector for the HTML elements that should be hidden
+   * @type {string}
+   */
+  get selector()
+  {
+    // Braces are being escaped to prevent CSS rule injection.
+    return this.body.replace("{", "\\7B ").replace("}", "\\7D ");
+  }
+});
 
 /**
  * Class for element hiding filters
  * @param {string} text see {@link Filter Filter()}
  * @param {string} [domains]  see {@link ElemHideBase ElemHideBase()}
  * @param {string} selector see {@link ElemHideBase ElemHideBase()}
  * @constructor
  * @augments ElemHideBase
  */
 function ElemHideFilter(text, domains, selector)
@@ skipping 38 matching lines @@
 }
 exports.ElemHideEmulationFilter = ElemHideEmulationFilter;
 
 ElemHideEmulationFilter.prototype = extend(ElemHideBase, {
   type: "elemhideemulation"
 });
 
 /**
  * Class for snippet filters
  * @param {string} text see Filter()
- * @param {string} [domains] see ScriptFilter()
+ * @param {string} [domains] see ContentFilter()
  * @param {string} script    Script that should be executed
  * @constructor
- * @augments ScriptFilter
+ * @augments ContentFilter
  */
 function SnippetFilter(text, domains, script)
 {
-  ScriptFilter.call(this, text, domains, script);
+  ContentFilter.call(this, text, domains, script);
 }
 exports.SnippetFilter = SnippetFilter;
 
-SnippetFilter.prototype = extend(ScriptFilter, {
-  type: "snippet"
-});
+SnippetFilter.prototype = extend(ContentFilter, {
+  type: "snippet",
+
+  /**
+   * Script that should be executed
+   * @type {string}
+   */
+  get script()
+  {
+    return this.body;
+  }
+});