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.

Mercurial (b6d82b1a6b02)

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
/* 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 "mozilla/ArrayUtils.h"
#include "mozilla/TextUtils.h"
#include "mozilla/Utf8.h"

#include <cstring>

#include "jsfriendapi.h"

#include "js/CharacterEncoding.h"
#include "js/CompilationAndEvaluation.h"  // JS::CompileDontInflate
#include "js/SourceText.h"
#include "jsapi-tests/tests.h"
#include "vm/ErrorReporting.h"

using mozilla::ArrayEqual;
using mozilla::ArrayLength;
using mozilla::IsAsciiHexDigit;
using mozilla::Utf8Unit;

BEGIN_TEST(testUtf8BadBytes) {
  static const char badLeadingUnit[] = "var x = \x80";
  CHECK(testBadUtf8(
      badLeadingUnit, JSMSG_BAD_LEADING_UTF8_UNIT,
      [this](JS::ConstUTF8CharsZ message) {
        const char* chars = message.c_str();
        CHECK(startsWith(chars, "0x80"));
        CHECK(isBadLeadUnitMessage(chars));
        return true;
      },
      "0x80"));

  static const char badSecondInTwoByte[] = "var x = \xDF\x20";
  CHECK(testBadUtf8(
      badSecondInTwoByte, JSMSG_BAD_TRAILING_UTF8_UNIT,
      [this](JS::ConstUTF8CharsZ message) {
        const char* chars = message.c_str();
        CHECK(isBadTrailingBytesMessage(chars));
        CHECK(contains(chars, "0x20"));
        return true;
      },
      "0xDF 0x20"));

  static const char badSecondInThreeByte[] = "var x = \xEF\x17\xA7";
  CHECK(testBadUtf8(
      badSecondInThreeByte, JSMSG_BAD_TRAILING_UTF8_UNIT,
      [this](JS::ConstUTF8CharsZ message) {
        const char* chars = message.c_str();
        CHECK(isBadTrailingBytesMessage(chars));
        CHECK(contains(chars, "0x17"));
        return true;
      },
      // Validating stops with the first invalid code unit and
      // shouldn't go beyond that.
      "0xEF 0x17"));

  static const char lengthTwoTooShort[] = "var x = \xDF";
  CHECK(testBadUtf8(
      lengthTwoTooShort, JSMSG_NOT_ENOUGH_CODE_UNITS,
      [this](JS::ConstUTF8CharsZ message) {
        const char* chars = message.c_str();
        CHECK(isNotEnoughUnitsMessage(chars));
        CHECK(contains(chars, "0xDF"));
        CHECK(contains(chars, " 1 byte, but 0 bytes were present"));
        return true;
      },
      "0xDF"));

  static const char forbiddenHighSurrogate[] = "var x = \xED\xA2\x87";
  CHECK(testBadUtf8(
      forbiddenHighSurrogate, JSMSG_FORBIDDEN_UTF8_CODE_POINT,
      [this](JS::ConstUTF8CharsZ message) {
        const char* chars = message.c_str();
        CHECK(isSurrogateMessage(chars));
        CHECK(contains(chars, "0xD887"));
        return true;
      },
      "0xED 0xA2 0x87"));

  static const char forbiddenLowSurrogate[] = "var x = \xED\xB7\xAF";
  CHECK(testBadUtf8(
      forbiddenLowSurrogate, JSMSG_FORBIDDEN_UTF8_CODE_POINT,
      [this](JS::ConstUTF8CharsZ message) {
        const char* chars = message.c_str();
        CHECK(isSurrogateMessage(chars));
        CHECK(contains(chars, "0xDDEF"));
        return true;
      },
      "0xED 0xB7 0xAF"));

  static const char oneTooBig[] = "var x = \xF4\x90\x80\x80";
  CHECK(testBadUtf8(
      oneTooBig, JSMSG_FORBIDDEN_UTF8_CODE_POINT,
      [this](JS::ConstUTF8CharsZ message) {
        const char* chars = message.c_str();
        CHECK(isTooBigMessage(chars));
        CHECK(contains(chars, "0x110000"));
        return true;
      },
      "0xF4 0x90 0x80 0x80"));

  static const char notShortestFormZero[] = "var x = \xC0\x80";
  CHECK(testBadUtf8(
      notShortestFormZero, JSMSG_FORBIDDEN_UTF8_CODE_POINT,
      [this](JS::ConstUTF8CharsZ message) {
        const char* chars = message.c_str();
        CHECK(isNotShortestFormMessage(chars));
        CHECK(startsWith(chars, "0x0 isn't "));
        return true;
      },
      "0xC0 0x80"));

  static const char notShortestFormNonzero[] = "var x = \xE0\x87\x80";
  CHECK(testBadUtf8(
      notShortestFormNonzero, JSMSG_FORBIDDEN_UTF8_CODE_POINT,
      [this](JS::ConstUTF8CharsZ message) {
        const char* chars = message.c_str();
        CHECK(isNotShortestFormMessage(chars));
        CHECK(startsWith(chars, "0x1C0 isn't "));
        return true;
      },
      "0xE0 0x87 0x80"));

  return true;
}

static constexpr size_t LengthOfByte = ArrayLength("0xFF") - 1;

static bool startsWithByte(const char* str) {
  return str[0] == '0' && str[1] == 'x' && IsAsciiHexDigit(str[2]) &&
         IsAsciiHexDigit(str[3]);
}

static bool startsWith(const char* str, const char* prefix) {
  return std::strncmp(prefix, str, strlen(prefix)) == 0;
}

static bool contains(const char* str, const char* substr) {
  return std::strstr(str, substr) != nullptr;
}

static bool equals(const char* str, const char* expected) {
  return std::strcmp(str, expected) == 0;
}

static bool isBadLeadUnitMessage(const char* str) {
  return startsWithByte(str) &&
         equals(str + LengthOfByte,
                " byte doesn't begin a valid UTF-8 code point");
}

static bool isBadTrailingBytesMessage(const char* str) {
  return startsWith(str, "bad trailing UTF-8 byte ");
}

static bool isNotEnoughUnitsMessage(const char* str) {
  return startsWithByte(str) &&
         startsWith(str + LengthOfByte, " byte in UTF-8 must be followed by ");
}

static bool isForbiddenCodePointMessage(const char* str) {
  return contains(str, "isn't a valid code point because");
}

static bool isSurrogateMessage(const char* str) {
  return isForbiddenCodePointMessage(str) &&
         contains(str, " it's a UTF-16 surrogate");
}

static bool isTooBigMessage(const char* str) {
  return isForbiddenCodePointMessage(str) &&
         contains(str, "the maximum code point is U+10FFFF");
}

static bool isNotShortestFormMessage(const char* str) {
  return isForbiddenCodePointMessage(str) &&
         contains(str, "it wasn't encoded in shortest possible form");
}

template <size_t N, typename TestMessage>
bool testBadUtf8(const char (&chars)[N], unsigned errorNumber,
                 TestMessage testMessage, const char* badBytes) {
  JS::Rooted<JSScript*> script(cx);
  {
    JS::CompileOptions options(cx);

    JS::SourceText<mozilla::Utf8Unit> srcBuf;
    CHECK(srcBuf.init(cx, chars, N - 1, JS::SourceOwnership::Borrowed));

    script = JS::CompileDontInflate(cx, options, srcBuf);
    CHECK(!script);
  }

  JS::RootedValue exn(cx);
  CHECK(JS_GetPendingException(cx, &exn));
  JS_ClearPendingException(cx);

  js::ErrorReport report(cx);
  CHECK(report.init(cx, exn, js::ErrorReport::WithSideEffects));

  const auto* errorReport = report.report();

  CHECK(errorReport->errorNumber == errorNumber);

  CHECK(testMessage(errorReport->message()));

  {
    const auto& notes = errorReport->notes;
    CHECK(notes != nullptr);

    auto iter = notes->begin();
    CHECK(iter != notes->end());

    const char* noteMessage = (*iter)->message().c_str();

    // The prefix ought always be the same.
    static const char expectedPrefix[] =
        "the code units comprising this invalid code point were: ";
    constexpr size_t expectedPrefixLen = ArrayLength(expectedPrefix) - 1;

    CHECK(startsWith(noteMessage, expectedPrefix));

    // The end of the prefix is the bad bytes.
    CHECK(equals(noteMessage + expectedPrefixLen, badBytes));

    ++iter;
    CHECK(iter == notes->end());
  }

  static const char16_t expectedContext[] = u"var x = ";
  constexpr size_t expectedContextLen = ArrayLength(expectedContext) - 1;

  const char16_t* lineOfContext = errorReport->linebuf();
  size_t lineOfContextLength = errorReport->linebufLength();

  CHECK(lineOfContext[lineOfContextLength] == '\0');
  CHECK(lineOfContextLength == expectedContextLen);

  CHECK(std::memcmp(lineOfContext, expectedContext,
                    expectedContextLen * sizeof(char16_t)) == 0);

  return true;
}
END_TEST(testUtf8BadBytes)

BEGIN_TEST(testMultiUnitUtf8InWindow) {
  static const char firstInWindowIsMultiUnit[] =
      "\xCF\x80\xCF\x80 = 6.283185307; @ bad starts HERE:\x80\xFF\xFF";
  CHECK(testContext(firstInWindowIsMultiUnit,
                    u"ππ = 6.283185307; @ bad starts HERE:"));

  static const char atTokenOffsetIsMulti[] = "var z = 💯";
  CHECK(testContext(atTokenOffsetIsMulti, u"var z = 💯"));

  static const char afterTokenOffsetIsMulti[] = "var z = @💯💯💯X";
  CHECK(testContext(afterTokenOffsetIsMulti, u"var z = @💯💯💯X"));

  static const char atEndIsMulti[] = "var z = @@💯💯💯";
  CHECK(testContext(atEndIsMulti, u"var z = @@💯💯💯"));

  return true;
}

template <size_t N, size_t ContextLenWithNull>
bool testContext(const char (&chars)[N],
                 const char16_t (&expectedContext)[ContextLenWithNull]) {
  JS::Rooted<JSScript*> script(cx);
  {
    JS::CompileOptions options(cx);

    JS::SourceText<mozilla::Utf8Unit> srcBuf;
    CHECK(srcBuf.init(cx, chars, N - 1, JS::SourceOwnership::Borrowed));

    script = JS::CompileDontInflate(cx, options, srcBuf);
    CHECK(!script);
  }

  JS::RootedValue exn(cx);
  CHECK(JS_GetPendingException(cx, &exn));
  JS_ClearPendingException(cx);

  js::ErrorReport report(cx);
  CHECK(report.init(cx, exn, js::ErrorReport::WithSideEffects));

  const auto* errorReport = report.report();

  CHECK(errorReport->errorNumber == JSMSG_ILLEGAL_CHARACTER);

  const char16_t* lineOfContext = errorReport->linebuf();
  size_t lineOfContextLength = errorReport->linebufLength();

  CHECK(lineOfContext[lineOfContextLength] == '\0');
  CHECK(lineOfContextLength == ContextLenWithNull - 1);

  CHECK(ArrayEqual(lineOfContext, expectedContext, ContextLenWithNull));

  return true;
}
END_TEST(testMultiUnitUtf8InWindow)