Infinite Trailing dots in IPv4 addrs at the end

Even though WHATWG only mentions the last empty octet to be a warning (https://url.spec.whatwg.org/#ipv4-empty-part), but I don't think something like "http://127.0.0.1.../" should be marked as Too Many Parts (https://url.spec.whatwg.org/#ipv4-too-many-parts).

Browsers' URL Parsers that I tested do ignore the last dot characters as well.

I'm not sure if this needs to be merged or not, but if I were writing WHATWG I either wouldn't have let the last dot be valid at all, or multiple dots would be okay too; I also wouldn't allow hex/octal IPv4 addresses either, so what do I know!!

Thanks.

src/checkers.cpp

@@ -10,14 +10,17 @@ ada_really_inline ada_constexpr bool is_ipv4(std::string_view view) noexcept {
   // with 'x' or a lowercase hex character.
   // Most of the time, this will be false so this simple check will save a lot
   // of effort.
-  char last_char = view.back();
   // If the address ends with a dot, we need to prune it (special case).
-  if (last_char == '.') {
+  char last_char{};
+  for (;;) {
+    last_char = view.back();
+    if (last_char != '.') {
+      break;
+    }
     view.remove_suffix(1);
     if (view.empty()) {
       return false;
     }
-    last_char = view.back();
   }
   bool possible_ipv4 = (last_char >= '0' && last_char <= '9') ||
                        (last_char >= 'a' && last_char <= 'f') ||

src/url.cpp

@@ -24,7 +24,7 @@ bool url::parse_opaque_host(std::string_view input) {
 
 bool url::parse_ipv4(std::string_view input) {
   ada_log("parse_ipv4 ", input, "[", input.size(), " bytes]");
-  if (input.back() == '.') {
+  while (!input.empty() && input.back() == '.') {
     input.remove_suffix(1);
   }
   size_t digit_count{0};

src/url_aggregator.cpp

@@ -858,10 +858,20 @@ bool url_aggregator::parse_ipv4(std::string_view input) {
           " bytes], overlaps with buffer: ",
           helpers::overlaps(input, buffer) ? "yes" : "no");
   ADA_ASSERT_TRUE(validate());
-  const bool trailing_dot = (input.back() == '.');
-  if (trailing_dot) {
-    input.remove_suffix(1);
+
+  // remove all of the last empty dots at the end:
+  bool trailing_dot = false;
+  for (;;) {
+    if (input.back() == '.') {
+      trailing_dot = true;
+      input.remove_suffix(1);
+      if (!input.empty()) {
+        continue;
+      }
+    }
+    break;
   }
+
   size_t digit_count{0};
   int pure_decimal_count = 0;  // entries that are decimal
   uint64_t ipv4{0};

tests/basic_tests.cpp

@@ -396,3 +396,53 @@ TYPED_TEST(basic_tests, nodejs_50235) {
   ASSERT_EQ(out->get_href(), "http://test.com:5/path?param=1");
   SUCCEED();
 }
+
+TYPED_TEST(basic_tests, LocalIPv4Addr) {
+  constexpr std::array<std::string_view, 17 * 2> strs{
+      "https://127.0.0.1/",
+      "https://0x7F.1/",
+      "https://0x7f000001",
+      "https://0x0000000007F.0X1",
+      "https://127.0.0x0.1",
+      "https://127.0X0.0x0.1",
+      "https://127.0X0.0x0.0x1",
+      "https://127.0.0x0.0x00000000000000000000000000000000000001",
+      "https://0x7F.0x00000000000000000000000001",
+      "https://0x000000000000000007F.0x00000000000000000000000001",
+      "https://0x000000000000000007F.0.0x00000000000000000000000001",
+      "https://0x7f.0.0.0x1",
+      "https://0x7F.0.0x000.0x1",
+      "https://2130706433",
+      "https://127.1",
+      "https://127.0x00.1",
+      "https://127.0x000000000000000.0.1",
+
+      // with dots at the end:
+      "https://127.0.0.1...../",
+      "https://0x7F.1..../",
+      "https://0x7f000001.",
+      "https://0x0000000007F.0X1...",
+      "https://127.0.0x0.1............",
+      "https://127.0X0.0x0.1.............",
+      "https://127.0X0.0x0.0x1..",
+      "https://127.0.0x0.0x00000000000000000000000000000000000000001....",
+      "https://0x7F.0x00000000000000000000000001.",
+      "https://0x000000000000000007F.0x00000000000000000000000001...",
+      "https://0x000000000000000007F.0.0x00000000000000000000000001.....",
+      "https://0x7f.0.0.0x1..........",
+      "https://0x7F.0.0x000.0x1..............................................",
+      "https://2130706433.................",
+      "https://127.1............",
+      "https://127.0x00.1........................",
+      "https://127.0x000000000000000.0.1................",
+  };
+
+  for (auto const str : strs) {
+    auto out = ada::parse<TypeParam>(str);
+    EXPECT_TRUE(out) << str;
+    if (out) {
+      EXPECT_EQ(out->get_href(), "https://127.0.0.1/") << str;
+      EXPECT_EQ(out->get_hostname(), "127.0.0.1") << str;
+    }
+  }
+}