string_util.cc 28 KB
Newer Older
gejun's avatar
gejun committed
1 2 3 4
// Copyright 2013 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.

5
#include "butil/strings/string_util.h"
gejun's avatar
gejun committed
6 7 8 9 10 11 12 13 14 15 16 17 18 19 20

#include <ctype.h>
#include <errno.h>
#include <math.h>
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>
#include <wchar.h>
#include <wctype.h>

#include <algorithm>
#include <vector>

21 22 23 24 25 26 27
#include "butil/basictypes.h"
#include "butil/logging.h"
#include "butil/memory/singleton.h"
#include "butil/strings/utf_string_conversion_utils.h"
#include "butil/strings/utf_string_conversions.h"
#include "butil/third_party/icu/icu_utf.h"
#include "butil/build_config.h"
gejun's avatar
gejun committed
28

29 30 31
// Remove when this entire file is in namespace butil.
using butil::char16;
using butil::string16;
gejun's avatar
gejun committed
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

namespace {

// Force the singleton used by EmptyString[16] to be a unique type. This
// prevents other code that might accidentally use Singleton<string> from
// getting our internal one.
struct EmptyStrings {
  EmptyStrings() {}
  const std::string s;
  const string16 s16;

  static EmptyStrings* GetInstance() {
    return Singleton<EmptyStrings>::get();
  }
};

// Used by ReplaceStringPlaceholders to track the position in the string of
// replaced parameters.
struct ReplacementOffset {
  ReplacementOffset(uintptr_t parameter, size_t offset)
      : parameter(parameter),
        offset(offset) {}

  // Index of the parameter.
  uintptr_t parameter;

  // Starting position in the string.
  size_t offset;
};

static bool CompareParameter(const ReplacementOffset& elem1,
                             const ReplacementOffset& elem2) {
  return elem1.parameter < elem2.parameter;
}

}  // namespace

69
namespace butil {
gejun's avatar
gejun committed
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

bool IsWprintfFormatPortable(const wchar_t* format) {
  for (const wchar_t* position = format; *position != '\0'; ++position) {
    if (*position == '%') {
      bool in_specification = true;
      bool modifier_l = false;
      while (in_specification) {
        // Eat up characters until reaching a known specifier.
        if (*++position == '\0') {
          // The format string ended in the middle of a specification.  Call
          // it portable because no unportable specifications were found.  The
          // string is equally broken on all platforms.
          return true;
        }

        if (*position == 'l') {
          // 'l' is the only thing that can save the 's' and 'c' specifiers.
          modifier_l = true;
        } else if (((*position == 's' || *position == 'c') && !modifier_l) ||
                   *position == 'S' || *position == 'C' || *position == 'F' ||
                   *position == 'D' || *position == 'O' || *position == 'U') {
          // Not portable.
          return false;
        }

        if (wcschr(L"diouxXeEfgGaAcspn%", *position)) {
          // Portable, keep scanning the rest of the format string.
          in_specification = false;
        }
      }
    }
  }

  return true;
}

const std::string& EmptyString() {
  return EmptyStrings::GetInstance()->s;
}

const string16& EmptyString16() {
  return EmptyStrings::GetInstance()->s16;
}

template<typename STR>
bool ReplaceCharsT(const STR& input,
                   const STR& replace_chars,
                   const STR& replace_with,
                   STR* output) {
  bool removed = false;
  size_t replace_length = replace_with.length();

  *output = input;

  size_t found = output->find_first_of(replace_chars);
  while (found != STR::npos) {
    removed = true;
    output->replace(found, 1, replace_with);
    found = output->find_first_of(replace_chars, found + replace_length);
  }

  return removed;
}

bool ReplaceChars(const string16& input,
135
                  const butil::StringPiece16& replace_chars,
gejun's avatar
gejun committed
136 137 138 139 140 141
                  const string16& replace_with,
                  string16* output) {
  return ReplaceCharsT(input, replace_chars.as_string(), replace_with, output);
}

bool ReplaceChars(const std::string& input,
142
                  const butil::StringPiece& replace_chars,
gejun's avatar
gejun committed
143 144 145 146 147 148
                  const std::string& replace_with,
                  std::string* output) {
  return ReplaceCharsT(input, replace_chars.as_string(), replace_with, output);
}

bool RemoveChars(const string16& input,
149
                 const butil::StringPiece16& remove_chars,
gejun's avatar
gejun committed
150 151 152 153 154
                 string16* output) {
  return ReplaceChars(input, remove_chars.as_string(), string16(), output);
}

bool RemoveChars(const std::string& input,
155
                 const butil::StringPiece& remove_chars,
gejun's avatar
gejun committed
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
                 std::string* output) {
  return ReplaceChars(input, remove_chars.as_string(), std::string(), output);
}

template<typename STR>
TrimPositions TrimStringT(const STR& input,
                          const STR& trim_chars,
                          TrimPositions positions,
                          STR* output) {
  // Find the edges of leading/trailing whitespace as desired.
  const size_t last_char = input.length() - 1;
  const size_t first_good_char = (positions & TRIM_LEADING) ?
      input.find_first_not_of(trim_chars) : 0;
  const size_t last_good_char = (positions & TRIM_TRAILING) ?
      input.find_last_not_of(trim_chars) : last_char;

  // When the string was all whitespace, report that we stripped off whitespace
  // from whichever position the caller was interested in.  For empty input, we
  // stripped no whitespace, but we still need to clear |output|.
  if (input.empty() ||
      (first_good_char == STR::npos) || (last_good_char == STR::npos)) {
    bool input_was_empty = input.empty();  // in case output == &input
    output->clear();
    return input_was_empty ? TRIM_NONE : positions;
  }

  // Trim the whitespace.
  *output =
      input.substr(first_good_char, last_good_char - first_good_char + 1);

  // Return where we trimmed from.
  return static_cast<TrimPositions>(
      ((first_good_char == 0) ? TRIM_NONE : TRIM_LEADING) |
      ((last_good_char == last_char) ? TRIM_NONE : TRIM_TRAILING));
}

bool TrimString(const string16& input,
193
                const butil::StringPiece16& trim_chars,
gejun's avatar
gejun committed
194 195 196 197 198 199
                string16* output) {
  return TrimStringT(input, trim_chars.as_string(), TRIM_ALL, output) !=
      TRIM_NONE;
}

bool TrimString(const std::string& input,
200
                const butil::StringPiece& trim_chars,
gejun's avatar
gejun committed
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
                std::string* output) {
  return TrimStringT(input, trim_chars.as_string(), TRIM_ALL, output) !=
      TRIM_NONE;
}

void TruncateUTF8ToByteSize(const std::string& input,
                            const size_t byte_size,
                            std::string* output) {
  DCHECK(output);
  if (byte_size > input.length()) {
    *output = input;
    return;
  }
  DCHECK_LE(byte_size, static_cast<uint32_t>(kint32max));
  // Note: This cast is necessary because CBU8_NEXT uses int32s.
  int32_t truncation_length = static_cast<int32_t>(byte_size);
  int32_t char_index = truncation_length - 1;
  const char* data = input.data();

  // Using CBU8, we will move backwards from the truncation point
  // to the beginning of the string looking for a valid UTF8
  // character.  Once a full UTF8 character is found, we will
  // truncate the string to the end of that character.
  while (char_index >= 0) {
    int32_t prev = char_index;
    uint32_t code_point = 0;
    CBU8_NEXT(data, char_index, truncation_length, code_point);
    if (!IsValidCharacter(code_point) ||
        !IsValidCodepoint(code_point)) {
      char_index = prev - 1;
    } else {
      break;
    }
  }

  if (char_index >= 0 )
    *output = input.substr(0, char_index);
  else
    output->clear();
}

TrimPositions TrimWhitespace(const string16& input,
                             TrimPositions positions,
                             string16* output) {
245
  return TrimStringT(input, butil::string16(kWhitespaceUTF16), positions,
gejun's avatar
gejun committed
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
                     output);
}

TrimPositions TrimWhitespaceASCII(const std::string& input,
                                  TrimPositions positions,
                                  std::string* output) {
  return TrimStringT(input, std::string(kWhitespaceASCII), positions, output);
}

// This function is only for backward-compatibility.
// To be removed when all callers are updated.
TrimPositions TrimWhitespace(const std::string& input,
                             TrimPositions positions,
                             std::string* output) {
  return TrimWhitespaceASCII(input, positions, output);
}

template<typename STR>
STR CollapseWhitespaceT(const STR& text,
                        bool trim_sequences_with_line_breaks) {
  STR result;
  result.resize(text.size());

  // Set flags to pretend we're already in a trimmed whitespace sequence, so we
  // will trim any leading whitespace.
  bool in_whitespace = true;
  bool already_trimmed = true;

  int chars_written = 0;
  for (typename STR::const_iterator i(text.begin()); i != text.end(); ++i) {
    if (IsWhitespace(*i)) {
      if (!in_whitespace) {
        // Reduce all whitespace sequences to a single space.
        in_whitespace = true;
        result[chars_written++] = L' ';
      }
      if (trim_sequences_with_line_breaks && !already_trimmed &&
          ((*i == '\n') || (*i == '\r'))) {
        // Whitespace sequences containing CR or LF are eliminated entirely.
        already_trimmed = true;
        --chars_written;
      }
    } else {
      // Non-whitespace chracters are copied straight across.
      in_whitespace = false;
      already_trimmed = false;
      result[chars_written++] = *i;
    }
  }

  if (in_whitespace && !already_trimmed) {
    // Any trailing whitespace is eliminated.
    --chars_written;
  }

  result.resize(chars_written);
  return result;
}

string16 CollapseWhitespace(const string16& text,
                            bool trim_sequences_with_line_breaks) {
  return CollapseWhitespaceT(text, trim_sequences_with_line_breaks);
}

std::string CollapseWhitespaceASCII(const std::string& text,
                                    bool trim_sequences_with_line_breaks) {
  return CollapseWhitespaceT(text, trim_sequences_with_line_breaks);
}

bool ContainsOnlyChars(const StringPiece& input,
                       const StringPiece& characters) {
  return input.find_first_not_of(characters) == StringPiece::npos;
}

bool ContainsOnlyChars(const StringPiece16& input,
                       const StringPiece16& characters) {
  return input.find_first_not_of(characters) == StringPiece16::npos;
}

template<class STR>
static bool DoIsStringASCII(const STR& str) {
  for (size_t i = 0; i < str.length(); i++) {
    typename ToUnsigned<typename STR::value_type>::Unsigned c = str[i];
    if (c > 0x7F)
      return false;
  }
  return true;
}

bool IsStringASCII(const StringPiece& str) {
  return DoIsStringASCII(str);
}

bool IsStringASCII(const string16& str) {
  return DoIsStringASCII(str);
}

bool IsStringUTF8(const std::string& str) {
  const char *src = str.data();
  int32_t src_len = static_cast<int32_t>(str.length());
  int32_t char_index = 0;

  while (char_index < src_len) {
    int32_t code_point;
    CBU8_NEXT(src, char_index, src_len, code_point);
    if (!IsValidCharacter(code_point))
      return false;
  }
  return true;
}

357
}  // namespace butil
gejun's avatar
gejun committed
358 359 360 361 362 363

template<typename Iter>
static inline bool DoLowerCaseEqualsASCII(Iter a_begin,
                                          Iter a_end,
                                          const char* b) {
  for (Iter it = a_begin; it != a_end; ++it, ++b) {
364
    if (!*b || butil::ToLowerASCII(*it) != *b)
gejun's avatar
gejun committed
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
      return false;
  }
  return *b == 0;
}

// Front-ends for LowerCaseEqualsASCII.
bool LowerCaseEqualsASCII(const std::string& a, const char* b) {
  return DoLowerCaseEqualsASCII(a.begin(), a.end(), b);
}

bool LowerCaseEqualsASCII(const string16& a, const char* b) {
  return DoLowerCaseEqualsASCII(a.begin(), a.end(), b);
}

bool LowerCaseEqualsASCII(std::string::const_iterator a_begin,
                          std::string::const_iterator a_end,
                          const char* b) {
  return DoLowerCaseEqualsASCII(a_begin, a_end, b);
}

bool LowerCaseEqualsASCII(string16::const_iterator a_begin,
                          string16::const_iterator a_end,
                          const char* b) {
  return DoLowerCaseEqualsASCII(a_begin, a_end, b);
}

// TODO(port): Resolve wchar_t/iterator issues that require OS_ANDROID here.
#if !defined(OS_ANDROID)
bool LowerCaseEqualsASCII(const char* a_begin,
                          const char* a_end,
                          const char* b) {
  return DoLowerCaseEqualsASCII(a_begin, a_end, b);
}

bool LowerCaseEqualsASCII(const char16* a_begin,
                          const char16* a_end,
                          const char* b) {
  return DoLowerCaseEqualsASCII(a_begin, a_end, b);
}

#endif  // !defined(OS_ANDROID)

407
bool EqualsASCII(const string16& a, const butil::StringPiece& b) {
gejun's avatar
gejun committed
408 409 410 411 412 413 414 415 416 417 418
  if (a.length() != b.length())
    return false;
  return std::equal(b.begin(), b.end(), a.begin());
}

bool StartsWithASCII(const std::string& str,
                     const std::string& search,
                     bool case_sensitive) {
  if (case_sensitive)
    return str.compare(0, search.length(), search) == 0;
  else
419
    return butil::strncasecmp(str.c_str(), search.c_str(), search.length()) == 0;
gejun's avatar
gejun committed
420 421 422 423 424 425 426 427 428 429
}

template <typename STR>
bool StartsWithT(const STR& str, const STR& search, bool case_sensitive) {
  if (case_sensitive) {
    return str.compare(0, search.length(), search) == 0;
  } else {
    if (search.size() > str.size())
      return false;
    return std::equal(search.begin(), search.end(), str.begin(),
430
                      butil::CaseInsensitiveCompare<typename STR::value_type>());
gejun's avatar
gejun committed
431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448
  }
}

bool StartsWith(const string16& str, const string16& search,
                bool case_sensitive) {
  return StartsWithT(str, search, case_sensitive);
}

template <typename STR>
bool EndsWithT(const STR& str, const STR& search, bool case_sensitive) {
  size_t str_length = str.length();
  size_t search_length = search.length();
  if (search_length > str_length)
    return false;
  if (case_sensitive)
    return str.compare(str_length - search_length, search_length, search) == 0;
  return std::equal(search.begin(), search.end(),
                    str.begin() + (str_length - search_length),
449
                    butil::CaseInsensitiveCompare<typename STR::value_type>());
gejun's avatar
gejun committed
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
}

bool EndsWith(const std::string& str, const std::string& search,
              bool case_sensitive) {
  return EndsWithT(str, search, case_sensitive);
}

bool EndsWith(const string16& str, const string16& search,
              bool case_sensitive) {
  return EndsWithT(str, search, case_sensitive);
}

static const char* const kByteStringsUnlocalized[] = {
  " B",
  " kB",
  " MB",
  " GB",
  " TB",
  " PB"
};

string16 FormatBytesUnlocalized(int64_t bytes) {
  double unit_amount = static_cast<double>(bytes);
  size_t dimension = 0;
  const int kKilo = 1024;
  while (unit_amount >= kKilo &&
         dimension < arraysize(kByteStringsUnlocalized) - 1) {
    unit_amount /= kKilo;
    dimension++;
  }

  char buf[64];
  if (bytes != 0 && dimension > 0 && unit_amount < 100) {
483
    butil::snprintf(buf, arraysize(buf), "%.1lf%s", unit_amount,
gejun's avatar
gejun committed
484 485
                   kByteStringsUnlocalized[dimension]);
  } else {
486
    butil::snprintf(buf, arraysize(buf), "%.0lf%s", unit_amount,
gejun's avatar
gejun committed
487 488 489
                   kByteStringsUnlocalized[dimension]);
  }

490
  return butil::ASCIIToUTF16(buf);
gejun's avatar
gejun committed
491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578
}

template<class StringType>
void DoReplaceSubstringsAfterOffset(StringType* str,
                                    size_t start_offset,
                                    const StringType& find_this,
                                    const StringType& replace_with,
                                    bool replace_all) {
  if ((start_offset == StringType::npos) || (start_offset >= str->length()))
    return;

  DCHECK(!find_this.empty());
  for (size_t offs(str->find(find_this, start_offset));
      offs != StringType::npos; offs = str->find(find_this, offs)) {
    str->replace(offs, find_this.length(), replace_with);
    offs += replace_with.length();

    if (!replace_all)
      break;
  }
}

void ReplaceFirstSubstringAfterOffset(string16* str,
                                      size_t start_offset,
                                      const string16& find_this,
                                      const string16& replace_with) {
  DoReplaceSubstringsAfterOffset(str, start_offset, find_this, replace_with,
                                 false);  // replace first instance
}

void ReplaceFirstSubstringAfterOffset(std::string* str,
                                      size_t start_offset,
                                      const std::string& find_this,
                                      const std::string& replace_with) {
  DoReplaceSubstringsAfterOffset(str, start_offset, find_this, replace_with,
                                 false);  // replace first instance
}

void ReplaceSubstringsAfterOffset(string16* str,
                                  size_t start_offset,
                                  const string16& find_this,
                                  const string16& replace_with) {
  DoReplaceSubstringsAfterOffset(str, start_offset, find_this, replace_with,
                                 true);  // replace all instances
}

void ReplaceSubstringsAfterOffset(std::string* str,
                                  size_t start_offset,
                                  const std::string& find_this,
                                  const std::string& replace_with) {
  DoReplaceSubstringsAfterOffset(str, start_offset, find_this, replace_with,
                                 true);  // replace all instances
}


template<typename STR>
static size_t TokenizeT(const STR& str,
                        const STR& delimiters,
                        std::vector<STR>* tokens) {
  tokens->clear();

  size_t start = str.find_first_not_of(delimiters);
  while (start != STR::npos) {
    size_t end = str.find_first_of(delimiters, start + 1);
    if (end == STR::npos) {
      tokens->push_back(str.substr(start));
      break;
    } else {
      tokens->push_back(str.substr(start, end - start));
      start = str.find_first_not_of(delimiters, end + 1);
    }
  }

  return tokens->size();
}

size_t Tokenize(const string16& str,
                const string16& delimiters,
                std::vector<string16>* tokens) {
  return TokenizeT(str, delimiters, tokens);
}

size_t Tokenize(const std::string& str,
                const std::string& delimiters,
                std::vector<std::string>* tokens) {
  return TokenizeT(str, delimiters, tokens);
}

579 580 581
size_t Tokenize(const butil::StringPiece& str,
                const butil::StringPiece& delimiters,
                std::vector<butil::StringPiece>* tokens) {
gejun's avatar
gejun committed
582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687
  return TokenizeT(str, delimiters, tokens);
}

template<typename STR>
static STR JoinStringT(const std::vector<STR>& parts, const STR& sep) {
  if (parts.empty())
    return STR();

  STR result(parts[0]);
  typename std::vector<STR>::const_iterator iter = parts.begin();
  ++iter;

  for (; iter != parts.end(); ++iter) {
    result += sep;
    result += *iter;
  }

  return result;
}

std::string JoinString(const std::vector<std::string>& parts, char sep) {
  return JoinStringT(parts, std::string(1, sep));
}

string16 JoinString(const std::vector<string16>& parts, char16 sep) {
  return JoinStringT(parts, string16(1, sep));
}

std::string JoinString(const std::vector<std::string>& parts,
                       const std::string& separator) {
  return JoinStringT(parts, separator);
}

string16 JoinString(const std::vector<string16>& parts,
                    const string16& separator) {
  return JoinStringT(parts, separator);
}

template<class FormatStringType, class OutStringType>
OutStringType DoReplaceStringPlaceholders(const FormatStringType& format_string,
    const std::vector<OutStringType>& subst, std::vector<size_t>* offsets) {
  size_t substitutions = subst.size();

  size_t sub_length = 0;
  for (typename std::vector<OutStringType>::const_iterator iter = subst.begin();
       iter != subst.end(); ++iter) {
    sub_length += iter->length();
  }

  OutStringType formatted;
  formatted.reserve(format_string.length() + sub_length);

  std::vector<ReplacementOffset> r_offsets;
  for (typename FormatStringType::const_iterator i = format_string.begin();
       i != format_string.end(); ++i) {
    if ('$' == *i) {
      if (i + 1 != format_string.end()) {
        ++i;
        DCHECK('$' == *i || '1' <= *i) << "Invalid placeholder: " << *i;
        if ('$' == *i) {
          while (i != format_string.end() && '$' == *i) {
            formatted.push_back('$');
            ++i;
          }
          --i;
        } else {
          uintptr_t index = 0;
          while (i != format_string.end() && '0' <= *i && *i <= '9') {
            index *= 10;
            index += *i - '0';
            ++i;
          }
          --i;
          index -= 1;
          if (offsets) {
            ReplacementOffset r_offset(index,
                static_cast<int>(formatted.size()));
            r_offsets.insert(std::lower_bound(r_offsets.begin(),
                                              r_offsets.end(),
                                              r_offset,
                                              &CompareParameter),
                             r_offset);
          }
          if (index < substitutions)
            formatted.append(subst.at(index));
        }
      }
    } else {
      formatted.push_back(*i);
    }
  }
  if (offsets) {
    for (std::vector<ReplacementOffset>::const_iterator i = r_offsets.begin();
         i != r_offsets.end(); ++i) {
      offsets->push_back(i->offset);
    }
  }
  return formatted;
}

string16 ReplaceStringPlaceholders(const string16& format_string,
                                   const std::vector<string16>& subst,
                                   std::vector<size_t>* offsets) {
  return DoReplaceStringPlaceholders(format_string, subst, offsets);
}

688
std::string ReplaceStringPlaceholders(const butil::StringPiece& format_string,
gejun's avatar
gejun committed
689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849
                                      const std::vector<std::string>& subst,
                                      std::vector<size_t>* offsets) {
  return DoReplaceStringPlaceholders(format_string, subst, offsets);
}

string16 ReplaceStringPlaceholders(const string16& format_string,
                                   const string16& a,
                                   size_t* offset) {
  std::vector<size_t> offsets;
  std::vector<string16> subst;
  subst.push_back(a);
  string16 result = ReplaceStringPlaceholders(format_string, subst, &offsets);

  DCHECK_EQ(1U, offsets.size());
  if (offset)
    *offset = offsets[0];
  return result;
}

static bool IsWildcard(base_icu::UChar32 character) {
  return character == '*' || character == '?';
}

// Move the strings pointers to the point where they start to differ.
template <typename CHAR, typename NEXT>
static void EatSameChars(const CHAR** pattern, const CHAR* pattern_end,
                         const CHAR** string, const CHAR* string_end,
                         NEXT next) {
  const CHAR* escape = NULL;
  while (*pattern != pattern_end && *string != string_end) {
    if (!escape && IsWildcard(**pattern)) {
      // We don't want to match wildcard here, except if it's escaped.
      return;
    }

    // Check if the escapement char is found. If so, skip it and move to the
    // next character.
    if (!escape && **pattern == '\\') {
      escape = *pattern;
      next(pattern, pattern_end);
      continue;
    }

    // Check if the chars match, if so, increment the ptrs.
    const CHAR* pattern_next = *pattern;
    const CHAR* string_next = *string;
    base_icu::UChar32 pattern_char = next(&pattern_next, pattern_end);
    if (pattern_char == next(&string_next, string_end) &&
        pattern_char != (base_icu::UChar32) CBU_SENTINEL) {
      *pattern = pattern_next;
      *string = string_next;
    } else {
      // Uh ho, it did not match, we are done. If the last char was an
      // escapement, that means that it was an error to advance the ptr here,
      // let's put it back where it was. This also mean that the MatchPattern
      // function will return false because if we can't match an escape char
      // here, then no one will.
      if (escape) {
        *pattern = escape;
      }
      return;
    }

    escape = NULL;
  }
}

template <typename CHAR, typename NEXT>
static void EatWildcard(const CHAR** pattern, const CHAR* end, NEXT next) {
  while (*pattern != end) {
    if (!IsWildcard(**pattern))
      return;
    next(pattern, end);
  }
}

template <typename CHAR, typename NEXT>
static bool MatchPatternT(const CHAR* eval, const CHAR* eval_end,
                          const CHAR* pattern, const CHAR* pattern_end,
                          int depth,
                          NEXT next) {
  const int kMaxDepth = 16;
  if (depth > kMaxDepth)
    return false;

  // Eat all the matching chars.
  EatSameChars(&pattern, pattern_end, &eval, eval_end, next);

  // If the string is empty, then the pattern must be empty too, or contains
  // only wildcards.
  if (eval == eval_end) {
    EatWildcard(&pattern, pattern_end, next);
    return pattern == pattern_end;
  }

  // Pattern is empty but not string, this is not a match.
  if (pattern == pattern_end)
    return false;

  // If this is a question mark, then we need to compare the rest with
  // the current string or the string with one character eaten.
  const CHAR* next_pattern = pattern;
  next(&next_pattern, pattern_end);
  if (pattern[0] == '?') {
    if (MatchPatternT(eval, eval_end, next_pattern, pattern_end,
                      depth + 1, next))
      return true;
    const CHAR* next_eval = eval;
    next(&next_eval, eval_end);
    if (MatchPatternT(next_eval, eval_end, next_pattern, pattern_end,
                      depth + 1, next))
      return true;
  }

  // This is a *, try to match all the possible substrings with the remainder
  // of the pattern.
  if (pattern[0] == '*') {
    // Collapse duplicate wild cards (********** into *) so that the
    // method does not recurse unnecessarily. http://crbug.com/52839
    EatWildcard(&next_pattern, pattern_end, next);

    while (eval != eval_end) {
      if (MatchPatternT(eval, eval_end, next_pattern, pattern_end,
                        depth + 1, next))
        return true;
      eval++;
    }

    // We reached the end of the string, let see if the pattern contains only
    // wildcards.
    if (eval == eval_end) {
      EatWildcard(&pattern, pattern_end, next);
      if (pattern != pattern_end)
        return false;
      return true;
    }
  }

  return false;
}

struct NextCharUTF8 {
  base_icu::UChar32 operator()(const char** p, const char* end) {
    base_icu::UChar32 c;
    int offset = 0;
    CBU8_NEXT(*p, offset, end - *p, c);
    *p += offset;
    return c;
  }
};

struct NextCharUTF16 {
  base_icu::UChar32 operator()(const char16** p, const char16* end) {
    base_icu::UChar32 c;
    int offset = 0;
    CBU16_NEXT(*p, offset, end - *p, c);
    *p += offset;
    return c;
  }
};

850 851
bool MatchPattern(const butil::StringPiece& eval,
                  const butil::StringPiece& pattern) {
gejun's avatar
gejun committed
852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886
  return MatchPatternT(eval.data(), eval.data() + eval.size(),
                       pattern.data(), pattern.data() + pattern.size(),
                       0, NextCharUTF8());
}

bool MatchPattern(const string16& eval, const string16& pattern) {
  return MatchPatternT(eval.c_str(), eval.c_str() + eval.size(),
                       pattern.c_str(), pattern.c_str() + pattern.size(),
                       0, NextCharUTF16());
}

// The following code is compatible with the OpenBSD lcpy interface.  See:
//   http://www.gratisoft.us/todd/papers/strlcpy.html
//   ftp://ftp.openbsd.org/pub/OpenBSD/src/lib/libc/string/{wcs,str}lcpy.c

namespace {

template <typename CHAR>
size_t lcpyT(CHAR* dst, const CHAR* src, size_t dst_size) {
  for (size_t i = 0; i < dst_size; ++i) {
    if ((dst[i] = src[i]) == 0)  // We hit and copied the terminating NULL.
      return i;
  }

  // We were left off at dst_size.  We over copied 1 byte.  Null terminate.
  if (dst_size != 0)
    dst[dst_size - 1] = 0;

  // Count the rest of the |src|, and return it's length in characters.
  while (src[dst_size]) ++dst_size;
  return dst_size;
}

}  // namespace

887
size_t butil::strlcpy(char* dst, const char* src, size_t dst_size) {
gejun's avatar
gejun committed
888 889
  return lcpyT<char>(dst, src, dst_size);
}
890
size_t butil::wcslcpy(wchar_t* dst, const wchar_t* src, size_t dst_size) {
gejun's avatar
gejun committed
891 892
  return lcpyT<wchar_t>(dst, src, dst_size);
}