Issue 3584 - Work around WebKit uppercase ID matching bug

abp2blocklist.js

 "use strict";
 
 let readline = require("readline");
 let punycode = require("punycode");
 let tldjs = require("tldjs");
 let filterClasses = require("./adblockplus.js");
 
 let typeMap = filterClasses.RegExpFilter.typeMap;
 
 const selectorLimit = 5000;
@@ skipping 236 matching lines @@
           return true;
 
     for (let name of Object.getOwnPropertyNames(obj))
       if (hasNonASCI(obj[name]))
         return true;
   }
 
   return false;
 }
 
+function convertIDSelectorsToAttributeSelectors(selector)
+{
+  // First we figure out where all the IDs are
+  let sep = "";
+  let start = null;
+  let positions = [];
+  for (let i = 0; i < selector.length; i++)
+  {
+    let chr = selector[i];
+
+    if (chr == "\\")        // ignore escaped characters
+      i++;
+    else if (chr == sep)    // don't match IDs within quoted text
+      sep = "";             // e.g. [attr="#Hello"]
+    else if (sep == "")
+    {
+      if (chr == '"' || chr == "'")
+        sep = chr;
+      else if (start == null)  // look for the start of an ID
+      {
+        if (chr == "#")
+          start = i;
+      }
+      else if (chr != "-" && chr != "_" &&
+               (chr < "0" ||
+                chr > "9" && chr < "A" ||
+                chr > "Z" && chr < "a" ||
+                chr > "z" && chr < "\x80")) // look for the end of the ID
+      {
+        positions.push({start: start, end: i});
+        start = null;
+      }
+    }
+  }
+  if (start != null)
+    positions.push({start: start, end: selector.length});
+
+  // Now replace them all with the [id="someID"] form
+  let newSelector = [];
+  let i = 0;
+  for (let pos of positions)
+  {
+    newSelector.push(selector.substring(i, pos.start));
+    newSelector.push('[id=' + selector.substring(pos.start + 1, pos.end) + ']');
+    i = pos.end;
+  }
+  newSelector.push(selector.substring(i));
+
+  return newSelector.join("");
+}
+
 function logRules()
 {
   let rules = [];
 
   function addRule(rule)
   {
     if (!hasNonASCI(rule))
       rules.push(rule);
   }
 
@@ skipping 13 matching lines @@
       group.push(result.selector);
       groupedElemhideFilters.set(matchDomain, group);
     }
   }
 
   groupedElemhideFilters.forEach((selectors, matchDomain) =>
   {
     while (selectors.length)
     {
       let selector = selectors.splice(0, selectorLimit).join(", ");
+
+      // As of Safari 9.0 element IDs are matched as lowercase. We work around
+      // this by converting to the attribute format [id="elementID"]
+      selector = convertIDSelectorsToAttributeSelectors(selector);
+
       addRule({
         trigger: {"url-filter": matchDomain},
         action: {type: "css-display-none",
                  selector: selector}
       });
-
-      // FIXME - Hack to work around WebKit bug whereby element IDs are

[Sebastian Noack, 2016/02/17 08:04:28]

I feel that this won't be just a temporary workaround. The earliest this will
get fixed is the next Safari major release, leaving some devices behind. So that
we cannot get rid of this workaround any time soon. So it seems more appropriate
to say "as of Safari 9.0" instead of "FIXME".

[kzar, 2016/02/17 13:45:26]

Done.

-      //         converted to lowercase before being matched.
-      let lowercaseSelector = selector.replace(
-        /#[\w-]+/g, match => match.toLowerCase()

[Sebastian Noack, 2016/02/17 08:04:28]

ID selectors can have escaped special chars, e.g #foo\:bar. ID selectors can
also use non-ascii characters (which aren't matched by \w) without escaping.

[kzar, 2016/02/17 13:45:26]

Acknowledged.

-      );
-      if (lowercaseSelector != selector)
-        addRule({

[Sebastian Noack, 2016/02/17 08:04:28]

Ideally, we merge the lowercase variants with the other selectors rather than
adding another rule.

[kzar, 2016/02/17 13:45:26]

Acknowledged.

-          trigger: {"url-filter": matchDomain},
-          action: {type: "css-display-none",
-                   selector: lowercaseSelector}
-        });
     }
   });
 
   for (let filter of elemhideExceptions)
     addRule(convertFilter(filter, "ignore-previous-rules", false));
 
   for (let filter of requestFilters)
     addRule(convertFilter(filter, "block", true));
   for (let filter of requestExceptions)
     addRule(convertFilter(filter, "ignore-previous-rules", true));
 
   console.log(JSON.stringify(rules, null, "\t"));
 }
 
 let rl = readline.createInterface({input: process.stdin, terminal: false});
 rl.on("line", parseFilter);
 rl.on("close", logRules);