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 248 matching lines @@
   // 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 split within quoted text

[Sebastian Noack, 2016/02/17 15:24:37]

Nit: This code has bee ncopied from cssProperties.js, however this comment isn't
accurrate in the context here. Perhaps "touch" instead of "split"?

[kzar, 2016/02/17 15:35:03]

Done.

-      sep = "";             // e.g. [attr=","]
+    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 < "0" && chr != "-" ||
-               chr > "9" && chr < "A" ||
-               chr > "Z" && chr != "_" && chr < "a" ||
-               chr > "z" && chr < "\x80") // look for the end of the ID
+      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 = "";

[Sebastian Noack, 2016/02/17 15:24:37]

Concatenating strings in a loop is expensive. You usually would use an array and
join it afterwards.

[kzar, 2016/02/17 15:35:04]

Done.

-  let position = 0;
-  for (let ID of positions)

[Sebastian Noack, 2016/02/17 15:24:37]

Nit: The variable shouldn't start with uppercase. "position" or "pos" seems to
be a better name here anyway.

[kzar, 2016/02/17 15:35:04]

Done.

-  {
-    newSelector += selector.substring(position, ID.start);
-    newSelector += '[id=' + selector.substring(ID.start + 1, ID.end) + ']';
-    position = ID.end;
-  }
-  newSelector += selector.substring(position);
-
-  return newSelector;
+  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 42 matching lines @@
     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);