url_formatter: Update comments for clarity.

components/url_formatter/url_formatter_unittest.cc

 // Copyright 2015 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.
 
 #include "components/url_formatter/url_formatter.h"
 
 #include <stddef.h>
 #include <string.h>
 
 #include <vector>
 
 #include "base/macros.h"
 #include "base/strings/string_number_conversions.h"
 #include "base/strings/stringprintf.h"
 #include "base/strings/utf_string_conversions.h"
 #include "testing/gtest/include/gtest/gtest.h"
 #include "url/gurl.h"
 
 
 namespace url_formatter {
 
 namespace {
 
 using base::WideToUTF16;
 using base::ASCIIToUTF16;
 
 const size_t kNpos = base::string16::npos;
 
 struct IDNTestCase {
+  // The IDNA/Punycode version of the domain (plain ASCII).
   const char* const input;
+  // The equivalent Unicode version of the domain. Even if we expect the domain
+  // to be displayed in Punycode, this should still contain the Unicode
+  // equivalent (see |unicode_allowed|).
   const wchar_t* unicode_output;
+  // Whether we expect the domain to be displayed decoded as a Unicode string
+  // (true) or in its Punycode form (false).
   const bool unicode_allowed;
 };
 
+// These cases can be generated with the following simple Python function:
+// import codecs
+// def make_case(case_name, unicode_domain, unicode_allowed=True):
+//   idna_input = codecs.encode(unicode_domain, 'idna').decode('ascii')
+//   unicode_output = 'L' + (ascii(unicode_domain)
+//                           .replace("'", '"')
+//                           .replace('\\u', '\\x'))
+//   print('  // %s' % case_name)
+//   print('  {"%s", %s, %s},' %
+//         (idna_input, unicode_output, repr(unicode_allowed).lower()))

[Peter Kasting, 2017/02/06 21:54:14]

You said this didn't warrant a separate tool, but it honestly seems like the
better route would be to just go ahead and check this script in in a tools
directory, then have the comment note that it can be used?  I dunno.

+
 const IDNTestCase idn_cases[] = {
   // No IDN
   {"www.google.com", L"www.google.com", true},
   {"www.google.com.", L"www.google.com.", true},
   {".", L".", true},
   {"", L"", true},
   // IDN
   // Hanzi (Traditional Chinese)
   {"xn--1lq90ic7f1rc.cn", L"\x5317\x4eac\x5927\x5b78.cn", true},
   // Hanzi ('video' in Simplified Chinese
@@ skipping 876 matching lines @@
     0, kNpos, kNpos, kNpos, kNpos, kNpos, kNpos, 0, kNpos, kNpos, kNpos, kNpos,
     0, 1, 2, 3, 4, 5, 6, 7
   };
   CheckAdjustedOffsets("http://user@foo.com/", kFormatUrlOmitAll,
                        net::UnescapeRule::NORMAL, omit_all_offsets);
 }
 
 }  // namespace
 
 }  // namespace url_formatter