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 (b6057e17f856)

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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364
/* 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 "nsEscape.h"
#include "nsString.h"
#include "nsIURI.h"
#include "nsNetUtil.h"
#include "nsUrlClassifierUtils.h"
#include "nsTArray.h"
#include "nsReadableUtils.h"
#include "plbase64.h"
#include "prprf.h"

static char int_to_hex_digit(int32_t i)
{
  NS_ASSERTION((i >= 0) && (i <= 15), "int too big in int_to_hex_digit");
  return static_cast<char>(((i < 10) ? (i + '0') : ((i - 10) + 'A')));
}

static bool
IsDecimal(const nsACString & num)
{
  for (uint32_t i = 0; i < num.Length(); i++) {
    if (!isdigit(num[i])) {
      return false;
    }
  }

  return true;
}

static bool
IsHex(const nsACString & num)
{
  if (num.Length() < 3) {
    return false;
  }

  if (num[0] != '0' || !(num[1] == 'x' || num[1] == 'X')) {
    return false;
  }

  for (uint32_t i = 2; i < num.Length(); i++) {
    if (!isxdigit(num[i])) {
      return false;
    }
  }

  return true;
}

static bool
IsOctal(const nsACString & num)
{
  if (num.Length() < 2) {
    return false;
  }

  if (num[0] != '0') {
    return false;
  }

  for (uint32_t i = 1; i < num.Length(); i++) {
    if (!isdigit(num[i]) || num[i] == '8' || num[i] == '9') {
      return false;
    }
  }

  return true;
}

nsUrlClassifierUtils::nsUrlClassifierUtils() : mEscapeCharmap(nullptr)
{
}

nsresult
nsUrlClassifierUtils::Init()
{
  // Everything but alpha numerics, - and .
  mEscapeCharmap = new Charmap(0xffffffff, 0xfc009fff, 0xf8000001, 0xf8000001,
                               0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff);
  if (!mEscapeCharmap)
    return NS_ERROR_OUT_OF_MEMORY;
  return NS_OK;
}

NS_IMPL_ISUPPORTS(nsUrlClassifierUtils, nsIUrlClassifierUtils)

/////////////////////////////////////////////////////////////////////////////
// nsIUrlClassifierUtils

NS_IMETHODIMP
nsUrlClassifierUtils::GetKeyForURI(nsIURI * uri, nsACString & _retval)
{
  nsCOMPtr<nsIURI> innerURI = NS_GetInnermostURI(uri);
  if (!innerURI)
    innerURI = uri;

  nsAutoCString host;
  innerURI->GetAsciiHost(host);

  if (host.IsEmpty()) {
    return NS_ERROR_MALFORMED_URI;
  }

  nsresult rv = CanonicalizeHostname(host, _retval);
  NS_ENSURE_SUCCESS(rv, rv);

  nsAutoCString path;
  rv = innerURI->GetPath(path);
  NS_ENSURE_SUCCESS(rv, rv);

  // strip out anchors
  int32_t ref = path.FindChar('#');
  if (ref != kNotFound)
    path.SetLength(ref);

  nsAutoCString temp;
  rv = CanonicalizePath(path, temp);
  NS_ENSURE_SUCCESS(rv, rv);

  _retval.Append(temp);

  return NS_OK;
}

/////////////////////////////////////////////////////////////////////////////
// non-interface methods

nsresult
nsUrlClassifierUtils::CanonicalizeHostname(const nsACString & hostname,
                                           nsACString & _retval)
{
  nsAutoCString unescaped;
  if (!NS_UnescapeURL(PromiseFlatCString(hostname).get(),
                      PromiseFlatCString(hostname).Length(),
                      0, unescaped)) {
    unescaped.Assign(hostname);
  }

  nsAutoCString cleaned;
  CleanupHostname(unescaped, cleaned);

  nsAutoCString temp;
  ParseIPAddress(cleaned, temp);
  if (!temp.IsEmpty()) {
    cleaned.Assign(temp);
  }

  ToLowerCase(cleaned);
  SpecialEncode(cleaned, false, _retval);

  return NS_OK;
}


nsresult
nsUrlClassifierUtils::CanonicalizePath(const nsACString & path,
                                       nsACString & _retval)
{
  _retval.Truncate();

  nsAutoCString decodedPath(path);
  nsAutoCString temp;
  while (NS_UnescapeURL(decodedPath.get(), decodedPath.Length(), 0, temp)) {
    decodedPath.Assign(temp);
    temp.Truncate();
  }

  SpecialEncode(decodedPath, true, _retval);
  // XXX: lowercase the path?

  return NS_OK;
}

void
nsUrlClassifierUtils::CleanupHostname(const nsACString & hostname,
                                      nsACString & _retval)
{
  _retval.Truncate();

  const char* curChar = hostname.BeginReading();
  const char* end = hostname.EndReading();
  char lastChar = '\0';
  while (curChar != end) {
    unsigned char c = static_cast<unsigned char>(*curChar);
    if (c == '.' && (lastChar == '\0' || lastChar == '.')) {
      // skip
    } else {
      _retval.Append(*curChar);
    }
    lastChar = c;
    ++curChar;
  }

  // cut off trailing dots
  while (_retval.Length() > 0 && _retval[_retval.Length() - 1] == '.') {
    _retval.SetLength(_retval.Length() - 1);
  }
}

void
nsUrlClassifierUtils::ParseIPAddress(const nsACString & host,
                                     nsACString & _retval)
{
  _retval.Truncate();
  nsACString::const_iterator iter, end;
  host.BeginReading(iter);
  host.EndReading(end);

  if (host.Length() <= 15) {
    // The Windows resolver allows a 4-part dotted decimal IP address to
    // have a space followed by any old rubbish, so long as the total length
    // of the string doesn't get above 15 characters. So, "10.192.95.89 xy"
    // is resolved to 10.192.95.89.
    // If the string length is greater than 15 characters, e.g.
    // "10.192.95.89 xy.wildcard.example.com", it will be resolved through
    // DNS.

    if (FindCharInReadable(' ', iter, end)) {
      end = iter;
    }
  }

  for (host.BeginReading(iter); iter != end; iter++) {
    if (!(isxdigit(*iter) || *iter == 'x' || *iter == 'X' || *iter == '.')) {
      // not an IP
      return;
    }
  }

  host.BeginReading(iter);
  nsTArray<nsCString> parts;
  ParseString(PromiseFlatCString(Substring(iter, end)), '.', parts);
  if (parts.Length() > 4) {
    return;
  }

  // If any potentially-octal numbers (start with 0 but not hex) have
  // non-octal digits, no part of the ip can be in octal
  // XXX: this came from the old javascript implementation, is it really
  // supposed to be like this?
  bool allowOctal = true;
  uint32_t i;

  for (i = 0; i < parts.Length(); i++) {
    const nsCString& part = parts[i];
    if (part[0] == '0') {
      for (uint32_t j = 1; j < part.Length(); j++) {
        if (part[j] == 'x') {
          break;
        }
        if (part[j] == '8' || part[j] == '9') {
          allowOctal = false;
          break;
        }
      }
    }
  }

  for (i = 0; i < parts.Length(); i++) {
    nsAutoCString canonical;

    if (i == parts.Length() - 1) {
      CanonicalNum(parts[i], 5 - parts.Length(), allowOctal, canonical);
    } else {
      CanonicalNum(parts[i], 1, allowOctal, canonical);
    }

    if (canonical.IsEmpty()) {
      _retval.Truncate();
      return;
    }

    if (_retval.IsEmpty()) {
      _retval.Assign(canonical);
    } else {
      _retval.Append('.');
      _retval.Append(canonical);
    }
  }
  return;
}

void
nsUrlClassifierUtils::CanonicalNum(const nsACString& num,
                                   uint32_t bytes,
                                   bool allowOctal,
                                   nsACString& _retval)
{
  _retval.Truncate();

  if (num.Length() < 1) {
    return;
  }

  uint32_t val;
  if (allowOctal && IsOctal(num)) {
    if (PR_sscanf(PromiseFlatCString(num).get(), "%o", &val) != 1) {
      return;
    }
  } else if (IsDecimal(num)) {
    if (PR_sscanf(PromiseFlatCString(num).get(), "%u", &val) != 1) {
      return;
    }
  } else if (IsHex(num)) {
  if (PR_sscanf(PromiseFlatCString(num).get(), num[1] == 'X' ? "0X%x" : "0x%x",
                &val) != 1) {
      return;
    }
  } else {
    return;
  }

  while (bytes--) {
    char buf[20];
    PR_snprintf(buf, sizeof(buf), "%u", val & 0xff);
    if (_retval.IsEmpty()) {
      _retval.Assign(buf);
    } else {
      _retval = nsDependentCString(buf) + NS_LITERAL_CSTRING(".") + _retval;
    }
    val >>= 8;
  }
}

// This function will encode all "special" characters in typical url
// encoding, that is %hh where h is a valid hex digit.  It will also fold
// any duplicated slashes.
bool
nsUrlClassifierUtils::SpecialEncode(const nsACString & url,
                                    bool foldSlashes,
                                    nsACString & _retval)
{
  bool changed = false;
  const char* curChar = url.BeginReading();
  const char* end = url.EndReading();

  unsigned char lastChar = '\0';
  while (curChar != end) {
    unsigned char c = static_cast<unsigned char>(*curChar);
    if (ShouldURLEscape(c)) {
      _retval.Append('%');
      _retval.Append(int_to_hex_digit(c / 16));
      _retval.Append(int_to_hex_digit(c % 16));

      changed = true;
    } else if (foldSlashes && (c == '/' && lastChar == '/')) {
      // skip
    } else {
      _retval.Append(*curChar);
    }
    lastChar = c;
    curChar++;
  }
  return changed;
}

bool
nsUrlClassifierUtils::ShouldURLEscape(const unsigned char c) const
{
  return c <= 32 || c == '%' || c >=127;
}