DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Header

Mercurial (f1252cfec7a1)

VCS Links

Line Code
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */

#include "nsHTMLTags.h"
#include "nsCRT.h"
#include "nsDataHashtable.h"
#include "nsReadableUtils.h"
#include "nsString.h"
#include "nsUnicharUtils.h"
#include "mozilla/HashFunctions.h"
#include <algorithm>

using namespace mozilla;

// static array of unicode tag names
#define HTML_TAG(_tag, _classname, _interfacename) (u"" #_tag),
#define HTML_OTHER(_tag)
const char16_t* const nsHTMLTags::sTagNames[] = {
#include "nsHTMLTagList.h"
};
#undef HTML_TAG
#undef HTML_OTHER

int32_t nsHTMLTags::gTableRefCount;
nsHTMLTags::TagStringHash* nsHTMLTags::gTagTable;
nsHTMLTags::TagAtomHash* nsHTMLTags::gTagAtomTable;

#define NS_HTMLTAG_NAME_MAX_LENGTH 10

// static
nsresult nsHTMLTags::AddRefTable(void) {
  if (gTableRefCount++ == 0) {
    NS_ASSERTION(!gTagTable && !gTagAtomTable, "pre existing hash!");

    gTagTable = new TagStringHash(64);
    gTagAtomTable = new TagAtomHash(64);

    // Fill in gTagTable with the above static char16_t strings as
    // keys and the value of the corresponding enum as the value in
    // the table.

    for (int32_t i = 0; i < NS_HTML_TAG_MAX; ++i) {
      const char16_t* tagName = sTagNames[i];
      const nsHTMLTag tagValue = static_cast<nsHTMLTag>(i + 1);

      // We use AssignLiteral here to avoid a string copy. This is okay
      // because this is truly static data.
      nsString tmp;
      tmp.AssignLiteral(tagName, nsString::char_traits::length(tagName));
      gTagTable->Put(tmp, tagValue);

      // All the HTML tag names are static atoms within nsGkAtoms, and they are
      // registered before this code is reached.
      nsStaticAtom* atom = NS_GetStaticAtom(tmp);
      MOZ_ASSERT(atom);
      gTagAtomTable->Put(atom, tagValue);
    }

#ifdef DEBUG
    // Check all tagNames are lowercase, and that NS_HTMLTAG_NAME_MAX_LENGTH is
    // correct.
    uint32_t maxTagNameLength = 0;
    for (int i = 0; i < NS_HTML_TAG_MAX; ++i) {
      const char16_t* tagName = sTagNames[i];

      nsAutoString lowerTagName(tagName);
      ToLowerCase(lowerTagName);
      MOZ_ASSERT(lowerTagName.Equals(tagName));

      maxTagNameLength = std::max(NS_strlen(tagName), maxTagNameLength);
    }

    MOZ_ASSERT(maxTagNameLength == NS_HTMLTAG_NAME_MAX_LENGTH);
#endif
  }

  return NS_OK;
}

// static
void nsHTMLTags::ReleaseTable(void) {
  if (0 == --gTableRefCount) {
    delete gTagTable;
    delete gTagAtomTable;
    gTagTable = nullptr;
    gTagAtomTable = nullptr;
  }
}

// static
nsHTMLTag nsHTMLTags::StringTagToId(const nsAString& aTagName) {
  uint32_t length = aTagName.Length();

  if (length > NS_HTMLTAG_NAME_MAX_LENGTH) {
    return eHTMLTag_userdefined;
  }

  // Setup a stack allocated string buffer with the appropriate length.
  nsAutoString lowerCase;
  lowerCase.SetLength(length);

  // Operate on the raw buffers to avoid bounds checks.
  auto src = aTagName.BeginReading();
  auto dst = lowerCase.BeginWriting();

  // Fast lowercasing-while-copying of ASCII characters into a
  // nsString buffer.

  for (uint32_t i = 0; i < length; i++) {
    char16_t c = src[i];

    if (c <= 'Z' && c >= 'A') {
      c |= 0x20;  // Lowercase the ASCII character.
    }

    dst[i] = c;  // Copy ASCII character.
  }

  return CaseSensitiveStringTagToId(lowerCase);
}

#ifdef DEBUG
void nsHTMLTags::TestTagTable() {
  const char16_t* tag;
  nsHTMLTag id;
  RefPtr<nsAtom> atom;

  nsHTMLTags::AddRefTable();
  // Make sure we can find everything we are supposed to
  for (int i = 0; i < NS_HTML_TAG_MAX; ++i) {
    tag = sTagNames[i];
    const nsAString& tagString = nsDependentString(tag);
    id = StringTagToId(tagString);
    NS_ASSERTION(id != eHTMLTag_userdefined, "can't find tag id");

    nsAutoString uname(tagString);
    ToUpperCase(uname);
    NS_ASSERTION(id == StringTagToId(uname), "wrong id");

    NS_ASSERTION(id == CaseSensitiveStringTagToId(tagString), "wrong id");

    atom = NS_Atomize(tag);
    NS_ASSERTION(id == CaseSensitiveAtomTagToId(atom), "wrong id");
  }

  // Make sure we don't find things that aren't there
  id = StringTagToId(NS_LITERAL_STRING("@"));
  NS_ASSERTION(id == eHTMLTag_userdefined, "found @");
  id = StringTagToId(NS_LITERAL_STRING("zzzzz"));
  NS_ASSERTION(id == eHTMLTag_userdefined, "found zzzzz");

  atom = NS_Atomize("@");
  id = CaseSensitiveAtomTagToId(atom);
  NS_ASSERTION(id == eHTMLTag_userdefined, "found @");
  atom = NS_Atomize("zzzzz");
  id = CaseSensitiveAtomTagToId(atom);
  NS_ASSERTION(id == eHTMLTag_userdefined, "found zzzzz");

  ReleaseTable();
}

#endif  // DEBUG