Reduce buggy usage of the registry controlled domain service.

url/url_canon.h

 // Copyright 2013 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #ifndef URL_URL_CANON_H_
 #define URL_URL_CANON_H_
 
 #include <stdlib.h>
 #include <string.h>
 
@@ skipping 361 matching lines @@
 // definition of CanonHostInfo above for details.
 URL_EXPORT void CanonicalizeHostVerbose(const char* spec,
                                         const Component& host,
                                         CanonOutput* output,
                                         CanonHostInfo* host_info);
 URL_EXPORT void CanonicalizeHostVerbose(const base::char16* spec,
                                         const Component& host,
                                         CanonOutput* output,
                                         CanonHostInfo* host_info);
 
+// Canonicalizes a string according to the host canonicalization rules. Unlike
+// CanonicalizeHost, this will not check for IP addresses which can change the
+// meaning (and canonicalization) of the components. This means it is possible
+// to call this for sub-components of a host name without corruption.
+//
+// As an example, "01.02.03.04.com" is a canonical hostname. If you called
+// CanonicalizeHost on the substring "01.02.03.04" it will get "fixed" to
+// "1.2.3.4" which will produce an invalid host name when reassembled. This
+// is more common because all numbers by themselves are considered IP
+// addresses; so "5" canonicalizes to "0.0.0.5".
+//
+// Be careful: Because Punycode works on each dot-separated substring as a
+// unit, you should only pass this function substrings that represent complete
+// dot-separated subcomponents of the original host. Even if you has ASCII

[Peter Kasting, 2016/10/25 01:33:33]

Nit: has -> have

+// input, percent-escaped characters will have different meaning if split in

[Peter Kasting, 2016/10/25 01:33:33]

Nit: meaning -> meanings

+// the middle.
+//
+// Returns true if the host was valid. This function will treat a 0-length
+// host as valid (because it's designed to be used for substrings) while the
+// full version above will mark empty hosts as broken.
+URL_EXPORT bool CanonicalizeHostSubstring(const char* spec,
+                                          const Component& host,
+                                          CanonOutput* output);
+URL_EXPORT bool CanonicalizeHostSubstring(const base::char16* spec,
+                                          const Component& host,
+                                          CanonOutput* output);
+
 // IP addresses.
 //
 // Tries to interpret the given host name as an IPv4 or IPv6 address. If it is
 // an IP address, it will canonicalize it as such, appending it to |output|.
 // Additional status information is returned via the |*host_info| parameter.
 // See the definition of CanonHostInfo above for details.
 //
 // This is called AUTOMATICALLY from the host canonicalizer, which ensures that
 // the input is unescaped and name-prepped, etc. It should not normally be
 // necessary or wise to call this directly.
@@ skipping 491 matching lines @@
                                    bool base_is_file,
                                    const base::char16* relative_url,
                                    const Component& relative_component,
                                    CharsetConverter* query_converter,
                                    CanonOutput* output,
                                    Parsed* out_parsed);
 
 }  // namespace url
 
 #endif  // URL_URL_CANON_H_