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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530
|
#include "esmreader.hpp"
#include "readerscache.hpp"
#include <components/esm3/cellid.hpp>
#include <components/esm3/loadcell.hpp>
#include <components/files/conversion.hpp>
#include <components/files/openfile.hpp>
#include <components/misc/strings/algorithm.hpp>
#include <filesystem>
#include <fstream>
#include <sstream>
#include <stdexcept>
namespace ESM
{
ESM_Context ESMReader::getContext()
{
// Update the file position before returning
mCtx.filePos = mEsm->tellg();
return mCtx;
}
ESMReader::ESMReader()
: mRecordFlags(0)
, mBuffer(50 * 1024)
, mEncoder(nullptr)
, mFileSize(0)
{
clearCtx();
mCtx.index = 0;
}
void ESMReader::restoreContext(const ESM_Context& rc)
{
// Reopen the file if necessary
if (mCtx.filename != rc.filename)
openRaw(rc.filename);
// Copy the data
mCtx = rc;
// Make sure we seek to the right place
mEsm->seekg(mCtx.filePos);
}
void ESMReader::close()
{
mEsm.reset();
clearCtx();
mHeader.blank();
}
void ESMReader::clearCtx()
{
mCtx.filename.clear();
mCtx.leftFile = 0;
mCtx.leftRec = 0;
mCtx.leftSub = 0;
mCtx.subCached = false;
mCtx.recName.clear();
mCtx.subName.clear();
}
void ESMReader::resolveParentFileIndices(ReadersCache& readers)
{
mCtx.parentFileIndices.clear();
for (const Header::MasterData& mast : getGameFiles())
{
const std::string& fname = mast.name;
int index = getIndex();
for (int i = 0; i < getIndex(); i++)
{
if (readers.getFileSize(static_cast<std::size_t>(i)) == 0)
continue; // Content file in non-ESM format
const auto fnamecandidate
= Files::pathToUnicodeString(readers.getName(static_cast<std::size_t>(i)).filename());
if (Misc::StringUtils::ciEqual(fname, fnamecandidate))
{
index = i;
break;
}
}
mCtx.parentFileIndices.push_back(index);
}
}
bool ESMReader::applyContentFileMapping(FormId& id)
{
if (mContentFileMapping && id.hasContentFile())
{
auto iter = mContentFileMapping->find(id.mContentFile);
if (iter == mContentFileMapping->end())
return false;
id.mContentFile = iter->second;
}
return true;
}
ESM::RefId ESMReader::getCellId()
{
if (mHeader.mFormatVersion <= ESM::MaxUseEsmCellIdFormatVersion)
{
ESM::CellId cellId;
cellId.load(*this);
if (cellId.mPaged)
{
return ESM::RefId::esm3ExteriorCell(cellId.mIndex.mX, cellId.mIndex.mY);
}
else
{
return ESM::RefId::stringRefId(cellId.mWorldspace);
}
}
return getHNRefId("NAME");
}
void ESMReader::openRaw(std::unique_ptr<std::istream>&& stream, const std::filesystem::path& name)
{
close();
mEsm = std::move(stream);
mCtx.filename = name;
mEsm->seekg(0, mEsm->end);
mCtx.leftFile = mFileSize = mEsm->tellg();
mEsm->seekg(0, mEsm->beg);
}
void ESMReader::openRaw(const std::filesystem::path& filename)
{
openRaw(Files::openBinaryInputFileStream(filename), filename);
}
void ESMReader::open(std::unique_ptr<std::istream>&& stream, const std::filesystem::path& name)
{
openRaw(std::move(stream), name);
if (getRecName() != "TES3")
fail("Not a valid Morrowind file");
getRecHeader();
mHeader.load(*this);
}
void ESMReader::open(const std::filesystem::path& file)
{
open(Files::openBinaryInputFileStream(file), file);
}
std::string ESMReader::getHNOString(NAME name)
{
if (isNextSub(name))
return getHString();
return {};
}
ESM::RefId ESMReader::getHNORefId(NAME name)
{
if (isNextSub(name))
return getRefId();
return ESM::RefId();
}
void ESMReader::skipHNORefId(NAME name)
{
if (isNextSub(name))
skipHRefId();
}
std::string ESMReader::getHNString(NAME name)
{
getSubNameIs(name);
return getHString();
}
RefId ESMReader::getHNRefId(NAME name)
{
getSubNameIs(name);
return getRefId();
}
std::string ESMReader::getHString()
{
return std::string(getHStringView());
}
std::string_view ESMReader::getHStringView()
{
getSubHeader();
if (mHeader.mFormatVersion > MaxStringRefIdFormatVersion)
return getStringView(mCtx.leftSub);
// Hack to make MultiMark.esp load. Zero-length strings do not
// occur in any of the official mods, but MultiMark makes use of
// them. For some reason, they break the rules, and contain a byte
// (value 0) even if the header says there is no data. If
// Morrowind accepts it, so should we.
if (mCtx.leftSub == 0 && hasMoreSubs() && !mEsm->peek())
{
// Skip the following zero byte
mCtx.leftRec--;
char c;
getT(c);
return std::string_view();
}
return getStringView(mCtx.leftSub);
}
RefId ESMReader::getRefId()
{
if (mHeader.mFormatVersion <= MaxStringRefIdFormatVersion)
return ESM::RefId::stringRefId(getHStringView());
getSubHeader();
return getRefIdImpl(mCtx.leftSub);
}
void ESMReader::skipHString()
{
getSubHeader();
// Hack to make MultiMark.esp load. Zero-length strings do not
// occur in any of the official mods, but MultiMark makes use of
// them. For some reason, they break the rules, and contain a byte
// (value 0) even if the header says there is no data. If
// Morrowind accepts it, so should we.
if (mHeader.mFormatVersion <= MaxStringRefIdFormatVersion && mCtx.leftSub == 0 && hasMoreSubs()
&& !mEsm->peek())
{
// Skip the following zero byte
mCtx.leftRec--;
skipT<char>();
return;
}
skip(mCtx.leftSub);
}
void ESMReader::skipHRefId()
{
skipHString();
}
FormId ESMReader::getFormId(bool wide, NAME tag)
{
FormId res;
if (wide)
getHNT(tag, res.mIndex, res.mContentFile);
else
getHNT(res.mIndex, tag);
return res;
}
// Get the next subrecord name and check if it matches the parameter
void ESMReader::getSubNameIs(NAME name)
{
getSubName();
if (mCtx.subName != name)
fail("Expected subrecord " + name.toString() + " but got " + mCtx.subName.toString());
}
bool ESMReader::isNextSub(NAME name)
{
if (!hasMoreSubs())
return false;
getSubName();
// If the name didn't match, then mark the it as 'cached' so it's
// available for the next call to getSubName.
mCtx.subCached = (mCtx.subName != name);
// If subCached is false, then subName == name.
return !mCtx.subCached;
}
bool ESMReader::peekNextSub(NAME name)
{
if (!hasMoreSubs())
return false;
getSubName();
mCtx.subCached = true;
return mCtx.subName == name;
}
// Read subrecord name. This gets called a LOT, so I've optimized it
// slightly.
void ESMReader::getSubName()
{
// If the name has already been read, do nothing
if (mCtx.subCached)
{
mCtx.subCached = false;
return;
}
// reading the subrecord data anyway.
const std::size_t subNameSize = decltype(mCtx.subName)::sCapacity;
getExact(mCtx.subName.mData, subNameSize);
mCtx.leftRec -= static_cast<std::uint32_t>(subNameSize);
}
void ESMReader::skipHSub()
{
getSubHeader();
skip(mCtx.leftSub);
}
void ESMReader::skipHSubSize(std::size_t size)
{
skipHSub();
if (mCtx.leftSub != size)
reportSubSizeMismatch(mCtx.leftSub, size);
}
void ESMReader::skipHSubUntil(NAME name)
{
while (hasMoreSubs() && !isNextSub(name))
{
mCtx.subCached = false;
skipHSub();
}
if (hasMoreSubs())
mCtx.subCached = true;
}
void ESMReader::getSubHeader()
{
if (mCtx.leftRec < static_cast<std::streamsize>(sizeof(mCtx.leftSub)))
fail("End of record while reading sub-record header: " + std::to_string(mCtx.leftRec) + " < "
+ std::to_string(sizeof(mCtx.leftSub)));
// Get subrecord size
getUint(mCtx.leftSub);
mCtx.leftRec -= sizeof(mCtx.leftSub);
// Adjust number of record bytes left; may go negative
mCtx.leftRec -= mCtx.leftSub;
}
NAME ESMReader::getRecName()
{
if (!hasMoreRecs())
fail("No more records, getRecName() failed");
if (hasMoreSubs())
fail("Previous record contains unread bytes");
// We went out of the previous record's bounds. Backtrack.
if (mCtx.leftRec < 0)
mEsm->seekg(mCtx.leftRec, std::ios::cur);
getName(mCtx.recName);
mCtx.leftFile -= decltype(mCtx.recName)::sCapacity;
// Make sure we don't carry over any old cached subrecord
// names. This can happen in some cases when we skip parts of a
// record.
mCtx.subCached = false;
return mCtx.recName;
}
void ESMReader::skipRecord()
{
skip(mCtx.leftRec);
mCtx.leftRec = 0;
mCtx.subCached = false;
}
void ESMReader::getRecHeader(uint32_t& flags)
{
if (mCtx.leftFile < static_cast<std::streamsize>(3 * sizeof(uint32_t)))
fail("End of file while reading record header");
std::uint32_t leftRec = 0;
getUint(leftRec);
mCtx.leftRec = static_cast<std::streamsize>(leftRec);
getUint(flags); // This header entry is always zero
getUint(flags);
mCtx.leftFile -= 3 * sizeof(uint32_t);
// Check that sizes add up
if (mCtx.leftFile < mCtx.leftRec)
reportSubSizeMismatch(mCtx.leftFile, mCtx.leftRec);
// Adjust number of bytes mCtx.left in file
mCtx.leftFile -= mCtx.leftRec;
}
/*************************************************************************
*
* Lowest level data reading and misc methods
*
*************************************************************************/
std::string ESMReader::getMaybeFixedStringSize(std::size_t size)
{
if (mHeader.mFormatVersion > MaxLimitedSizeStringsFormatVersion)
{
StringSizeType storedSize = 0;
getT(storedSize);
if (storedSize > mCtx.leftSub)
fail("String does not fit subrecord (" + std::to_string(storedSize) + " > "
+ std::to_string(mCtx.leftSub) + ")");
size = static_cast<std::size_t>(storedSize);
}
return std::string(getStringView(size));
}
RefId ESMReader::getMaybeFixedRefIdSize(std::size_t size)
{
if (mHeader.mFormatVersion <= MaxStringRefIdFormatVersion)
return RefId::stringRefId(getMaybeFixedStringSize(size));
return getRefIdImpl(mCtx.leftSub);
}
std::string_view ESMReader::getStringView(std::size_t size)
{
if (mBuffer.size() <= size)
// Add some extra padding to reduce the chance of having to resize
// again later.
mBuffer.resize(3 * size);
// And make sure the string is zero terminated
mBuffer[size] = 0;
// read ESM data
char* ptr = mBuffer.data();
getExact(ptr, size);
size = strnlen(ptr, size);
// Convert to UTF8 and return
if (mEncoder != nullptr)
return mEncoder->getUtf8(std::string_view(ptr, size));
return std::string_view(ptr, size);
}
RefId ESMReader::getRefId(std::size_t size)
{
if (mHeader.mFormatVersion <= MaxStringRefIdFormatVersion)
return ESM::RefId::stringRefId(getStringView(size));
return getRefIdImpl(size);
}
RefId ESMReader::getRefIdImpl(std::size_t size)
{
RefIdType refIdType = RefIdType::Empty;
getT(refIdType);
switch (refIdType)
{
case RefIdType::Empty:
return RefId();
case RefIdType::SizedString:
{
const std::size_t minSize = sizeof(refIdType) + sizeof(StringSizeType);
if (size < minSize)
fail("Requested RefId record size is too small (" + std::to_string(size) + " < "
+ std::to_string(minSize) + ")");
StringSizeType storedSize = 0;
getT(storedSize);
const std::size_t maxSize = size - minSize;
if (storedSize > maxSize)
fail("RefId string does not fit subrecord size (" + std::to_string(storedSize) + " > "
+ std::to_string(maxSize) + ")");
return RefId::stringRefId(getStringView(storedSize));
}
case RefIdType::UnsizedString:
if (size < sizeof(refIdType))
fail("Requested RefId record size is too small (" + std::to_string(size) + " < "
+ std::to_string(sizeof(refIdType)) + ")");
return RefId::stringRefId(getStringView(size - sizeof(refIdType)));
case RefIdType::FormId:
{
FormId formId{};
getT(formId.mIndex);
getT(formId.mContentFile);
if (applyContentFileMapping(formId))
return RefId(formId);
else
return RefId(); // content file was removed from load order
}
case RefIdType::Generated:
{
std::uint64_t generated{};
getT(generated);
return RefId::generated(generated);
}
case RefIdType::Index:
{
RecNameInts recordType{};
getExact(&recordType, sizeof(std::uint32_t));
std::uint32_t index{};
getT(index);
return RefId::index(recordType, index);
}
case RefIdType::ESM3ExteriorCell:
{
int32_t x, y;
getT(x);
getT(y);
return RefId::esm3ExteriorCell(x, y);
}
}
fail("Unsupported RefIdType: " + std::to_string(static_cast<unsigned>(refIdType)));
}
[[noreturn]] void ESMReader::fail(std::string_view msg)
{
std::stringstream ss;
ss << "ESM Error: " << msg;
ss << "\n File: " << Files::pathToUnicodeString(mCtx.filename);
ss << "\n Record: " << mCtx.recName.toStringView();
ss << "\n Subrecord: " << mCtx.subName.toStringView();
if (mEsm.get())
ss << "\n Offset: 0x" << std::hex << mEsm->tellg();
throw std::runtime_error(ss.str());
}
}
|