Issue 5062 - [emscripten] Allow generation of custom bindings code

compiled/filter/RegExpFilter.cpp

 /*
  * This file is part of Adblock Plus <https://adblockplus.org/>,
  * Copyright (C) 2006-2017 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/>.
  */
 
+#include <cctype>
 #include <climits>
+#include <cstdio>
+#include <stdexcept>
+#include <iterator>
 
 #include <emscripten.h>
 
 #include "RegExpFilter.h"
 #include "../StringScanner.h"
 #include "../StringMap.h"
 
 namespace
 {
   enum
@@ skipping 310 matching lines @@
     done = scanner.done();
     if (scanner.next() == u'|')
     {
       if (scanner.position() > start)
         AddSitekey(DependentString(sitekeys, start, scanner.position() - start));
       start = scanner.position() + 1;
     }
   }
 }
 
-void RegExpFilter::InitJSTypes()
+void RegExpFilter::GenerateCustomBindings()
 {
-  EM_ASM(exports.RegExpFilter.typeMap = {};);
-  for (auto it = typeMap.begin(); it != typeMap.end(); ++it)
-    EM_ASM_ARGS(exports.RegExpFilter.typeMap[readString($0).replace("-", "_").toUpperCase()] = $1, &(it->first), it->second);
+  printf("exports.RegExpFilter.typeMap = {\n");
+
+  OwnedString type;
+  char type_cstr[256];
+  for (const auto& it : typeMap)
+  {
+    type = it.first;
+    auto len = type.length();
+    if (len >= std::end(type_cstr) - std::begin(type_cstr))
+      throw std::runtime_error("Value size too large for the buffer");

[sergei, 2017/04/04 14:49:31]

Well, if you touch this code then I would recommend to get rid of at least
"type_cstr" variable and optionally "OwnedString type" variable, use std::string
instead of "char type_cstr[256];" and move it into the scope of loop.

something like this:

for (const auto& typeEntry : typeMap) {
  std::string type(typeEntry.first.length(), '\0');
  for (int i = 0; i < typeEntry.first.length(); ++i) {
    type[i] = typeEntry.first[i] == '-' ? '_' : toupper(typeEntry.first[i]);
  }
  printf("  %s: %i,\n", type.c_str(), it.second);
}

[Wladimir Palant, 2017/04/04 15:41:48]

Done.

+    for (int i = 0; i < len; i++)
+    {
+      if (type[i] == '-')
+        type_cstr[i] = '_';
+      else
+        type_cstr[i] = toupper(type[i]);
+    }
+    type_cstr[len] = 0;
+    printf("  %s: %i,\n", type_cstr, it.second);
+  }
+  printf("};\n");
 }
 
 RegExpFilter::DomainMap* RegExpFilter::GetDomains() const
 {
   if (!mData.DomainsParsingDone())
   {
     ParseDomains(mData.GetDomainsSource(mText), u'|');
     mData.SetDomainsParsingDone();
   }
   return ActiveFilter::GetDomains();
@@ skipping 20 matching lines @@
     return false;
   }
 
   if (!mData.RegExpParsingDone())
   {
     const OwnedString pattern(mData.GetRegExpSource(mText));
     mData.SetRegExp(GenerateRegExp(RegExpFromSource(pattern), mData.mMatchCase));
   }
   return EM_ASM_INT(return regexps.test($0, $1), mData.mRegexpId, &location);
 }