C++ Utilities  4.8.0
Common C++ classes and routines used by my applications such as argument parser, IO and conversion utilities
stringconversion.h
Go to the documentation of this file.
1 #ifndef CONVERSION_UTILITIES_STRINGCONVERSION_H
2 #define CONVERSION_UTILITIES_STRINGCONVERSION_H
3 
4 #include "./binaryconversion.h"
6 
7 #include "../misc/traits.h"
8 
9 #include <cstring>
10 #include <initializer_list>
11 #include <iomanip>
12 #include <list>
13 #include <memory>
14 #include <sstream>
15 #include <string>
16 #include <vector>
17 
18 namespace ConversionUtilities {
19 
28  void operator()(char *stringData)
29  {
30  std::free(stringData);
31  }
32 };
33 
37 typedef std::pair<std::unique_ptr<char[], StringDataDeleter>, std::size_t> StringData;
38 //typedef std::pair<std::unique_ptr<char>, std::size_t> StringData; // might work too
39 
41  const char *fromCharset, const char *toCharset, const char *inputBuffer, std::size_t inputBufferSize, float outputBufferSizeFactor = 1.0f);
42 CPP_UTILITIES_EXPORT StringData convertUtf8ToUtf16LE(const char *inputBuffer, std::size_t inputBufferSize);
43 CPP_UTILITIES_EXPORT StringData convertUtf16LEToUtf8(const char *inputBuffer, std::size_t inputBufferSize);
44 CPP_UTILITIES_EXPORT StringData convertUtf8ToUtf16BE(const char *inputBuffer, std::size_t inputBufferSize);
45 CPP_UTILITIES_EXPORT StringData convertUtf16BEToUtf8(const char *inputBuffer, std::size_t inputBufferSize);
46 CPP_UTILITIES_EXPORT StringData convertLatin1ToUtf8(const char *inputBuffer, std::size_t inputBufferSize);
47 CPP_UTILITIES_EXPORT StringData convertUtf8ToLatin1(const char *inputBuffer, std::size_t inputBufferSize);
48 
49 CPP_UTILITIES_EXPORT void truncateString(std::string &str, char terminationChar = '\0');
50 
64 template <class Container = std::initializer_list<std::string>>
65 typename Container::value_type joinStrings(const Container &strings,
66  const typename Container::value_type &delimiter = typename Container::value_type(), bool omitEmpty = false,
67  const typename Container::value_type &leftClosure = typename Container::value_type(),
68  const typename Container::value_type &rightClosure = typename Container::value_type())
69 {
70  typename Container::value_type res;
71  if (strings.size()) {
72  size_t entries = 0, size = 0;
73  for (const auto &str : strings) {
74  if (!omitEmpty || !str.empty()) {
75  size += str.size();
76  ++entries;
77  }
78  }
79  if (entries) {
80  size += (entries * leftClosure.size()) + (entries * rightClosure.size()) + ((entries - 1) * delimiter.size());
81  res.reserve(size);
82  for (const auto &str : strings) {
83  if (!omitEmpty || !str.empty()) {
84  if (!res.empty()) {
85  res.append(delimiter);
86  }
87  res.append(leftClosure);
88  res.append(str);
89  res.append(rightClosure);
90  }
91  }
92  }
93  }
94  return res;
95 }
96 
100 enum class EmptyPartsTreat {
101  Keep,
102  Omit,
103  Merge
104 };
105 
115 template <class Container = std::list<std::string>>
116 Container splitString(const typename Container::value_type &string, const typename Container::value_type &delimiter,
117  EmptyPartsTreat emptyPartsRole = EmptyPartsTreat::Keep, int maxParts = -1)
118 {
119  --maxParts;
120  Container res;
121  bool merge = false;
122  for (typename Container::value_type::size_type i = 0, end = string.size(), delimPos; i < end; i = delimPos + delimiter.size()) {
123  delimPos = string.find(delimiter, i);
124  if (!merge && maxParts >= 0 && res.size() == static_cast<typename Container::value_type::size_type>(maxParts)) {
125  if (delimPos == i && emptyPartsRole == EmptyPartsTreat::Merge) {
126  if (!res.empty()) {
127  merge = true;
128  continue;
129  }
130  }
131  delimPos = Container::value_type::npos;
132  }
133  if (delimPos == Container::value_type::npos) {
134  delimPos = string.size();
135  }
136  if (emptyPartsRole == EmptyPartsTreat::Keep || i != delimPos) {
137  if (merge) {
138  res.back().append(delimiter);
139  res.back().append(string.substr(i, delimPos - i));
140  merge = false;
141  } else {
142  res.emplace_back(string.substr(i, delimPos - i));
143  }
144  } else if (emptyPartsRole == EmptyPartsTreat::Merge) {
145  if (!res.empty()) {
146  merge = true;
147  }
148  }
149  }
150  return res;
151 }
152 
156 template <typename StringType> bool startsWith(const StringType &str, const StringType &phrase)
157 {
158  if (str.size() < phrase.size()) {
159  return false;
160  }
161  for (auto stri = str.cbegin(), strend = str.cend(), phrasei = phrase.cbegin(), phraseend = phrase.cend(); stri != strend; ++stri, ++phrasei) {
162  if (phrasei == phraseend) {
163  return true;
164  } else if (*stri != *phrasei) {
165  return false;
166  }
167  }
168  return false;
169 }
170 
174 template <typename StringType> bool startsWith(const StringType &str, const typename StringType::value_type *phrase)
175 {
176  for (auto stri = str.cbegin(), strend = str.cend(); stri != strend; ++stri, ++phrase) {
177  if (!*phrase) {
178  return true;
179  } else if (*stri != *phrase) {
180  return false;
181  }
182  }
183  return false;
184 }
185 
190 template <typename StringType> bool containsSubstrings(const StringType &str, std::initializer_list<StringType> substrings)
191 {
192  typename StringType::size_type currentPos = 0;
193  for (const auto &substr : substrings) {
194  if ((currentPos = str.find(substr, currentPos)) == StringType::npos) {
195  return false;
196  }
197  currentPos += substr.size();
198  }
199  return true;
200 }
201 
206 template <typename StringType>
207 bool containsSubstrings(const StringType &str, std::initializer_list<const typename StringType::value_type *> substrings)
208 {
209  typename StringType::size_type currentPos = 0;
210  for (const auto *substr : substrings) {
211  if ((currentPos = str.find(substr, currentPos)) == StringType::npos) {
212  return false;
213  }
214  currentPos += std::strlen(substr);
215  }
216  return true;
217 }
218 
222 template <typename StringType> void findAndReplace(StringType &str, const StringType &find, const StringType &replace)
223 {
224  for (typename StringType::size_type i = 0; (i = str.find(find, i)) != StringType::npos; i += replace.size()) {
225  str.replace(i, find.size(), replace);
226  }
227 }
228 
235 template <typename CharType> CharType digitToChar(CharType digit)
236 {
237  CharType res;
238  if (digit <= 9) {
239  res = digit + '0';
240  } else {
241  res = digit + 'A' - 10;
242  }
243  return res;
244 }
245 
252 template <typename IntegralType, class StringType = std::string,
254 StringType numberToString(IntegralType number, typename StringType::value_type base = 10)
255 {
256  std::size_t resSize = 0;
257  for (auto n = number; n; n /= base, ++resSize)
258  ;
259  StringType res;
260  res.reserve(resSize);
261  do {
262  res.insert(res.begin(), digitToChar<typename StringType::value_type>(number % base));
263  number /= base;
264  } while (number);
265  return res;
266 }
267 
274 template <typename IntegralType, class StringType = std::string, Traits::EnableIf<std::is_integral<IntegralType>, std::is_signed<IntegralType>>...>
275 StringType numberToString(IntegralType number, typename StringType::value_type base = 10)
276 {
277  const bool negative = number < 0;
278  std::size_t resSize;
279  if (negative) {
280  number = -number, resSize = 1;
281  } else {
282  resSize = 0;
283  }
284  for (auto n = number; n; n /= base, ++resSize)
285  ;
286  StringType res;
287  res.reserve(resSize);
288  do {
289  res.insert(res.begin(), digitToChar<typename StringType::value_type>(number % base));
290  number /= base;
291  } while (number);
292  if (negative) {
293  res.insert(res.begin(), '-');
294  }
295  return res;
296 }
297 
306 template <typename FloatingType, class StringType = std::string, Traits::EnableIf<std::is_floating_point<FloatingType>>...>
307 StringType numberToString(FloatingType number, typename StringType::value_type base = 10)
308 {
309  std::basic_stringstream<typename StringType::value_type> ss;
310  ss << std::setbase(base) << number;
311  return ss.str();
312 }
313 
318 template <typename CharType> CharType charToDigit(CharType character, CharType base)
319 {
320  CharType res;
321  if (character >= '0' && character <= '9') {
322  res = character - '0';
323  } else if (character >= 'a' && character <= 'z') {
324  res = character - 'a' + 10;
325  } else if (character >= 'A' && character <= 'Z') {
326  res = character - 'A' + 10;
327  } else {
328  throw ConversionException("The string is no valid number");
329  }
330  if (res >= base) {
331  throw ConversionException("The string is no valid number");
332  }
333  return res;
334 }
335 
343 template <typename IntegralType, class StringType, Traits::EnableIf<std::is_integral<IntegralType>, Traits::Not<std::is_signed<IntegralType>>>...>
344 IntegralType stringToNumber(const StringType &string, typename StringType::value_type base = 10)
345 {
346  IntegralType result = 0;
347  for (const auto &c : string) {
348  if (c == ' ') {
349  continue;
350  }
351  result *= base;
352  result += charToDigit<typename StringType::value_type>(c, base);
353  }
354  return result;
355 }
356 
364 template <typename IntegralType, class StringType, Traits::EnableIf<std::is_integral<IntegralType>, std::is_signed<IntegralType>>...>
365 IntegralType stringToNumber(const StringType &string, typename StringType::value_type base = 10)
366 {
367  auto i = string.begin();
368  auto end = string.end();
369  if (i == end) {
370  return 0;
371  }
372  const bool negative = (*i == '-');
373  if (negative) {
374  ++i;
375  }
376  IntegralType result = 0;
377  for (; i != end; ++i) {
378  if (*i == ' ') {
379  continue;
380  }
381  result *= base;
382  result += charToDigit<typename StringType::value_type>(*i, base);
383  }
384  return negative ? -result : result;
385 }
386 
396 template <typename FloatingType, class StringType, Traits::EnableIf<std::is_floating_point<FloatingType>>...>
397 FloatingType stringToNumber(const StringType &string, typename StringType::value_type base = 10)
398 {
399  std::basic_stringstream<typename StringType::value_type> ss;
400  ss << std::setbase(base) << string;
401  FloatingType result;
402  if ((ss >> result) && ss.eof()) {
403  return result;
404  } else {
405  throw ConversionException("The string is no valid number.");
406  }
407 }
408 
416 template <typename IntegralType, class CharType, Traits::EnableIf<std::is_integral<IntegralType>, Traits::Not<std::is_signed<IntegralType>>>...>
417 IntegralType stringToNumber(const CharType *string, unsigned char base = 10)
418 {
419  IntegralType result = 0;
420  for (; *string; ++string) {
421  if (*string == ' ') {
422  continue;
423  }
424  result *= base;
425  result += charToDigit<CharType>(*string, base);
426  }
427  return result;
428 }
429 
437 template <typename IntegralType, class CharType, Traits::EnableIf<std::is_integral<IntegralType>, std::is_signed<IntegralType>>...>
438 IntegralType stringToNumber(const CharType *string, unsigned char base = 10)
439 {
440  if (!*string) {
441  return 0;
442  }
443  const bool negative = (*string == '-');
444  if (negative) {
445  ++string;
446  }
447  IntegralType result = 0;
448  for (; *string; ++string) {
449  if (*string == ' ') {
450  continue;
451  }
452  result *= base;
453  result += charToDigit<CharType>(*string, base);
454  }
455  return negative ? -result : result;
456 }
457 
467 template <typename T> std::string interpretIntegerAsString(T integer, int startOffset = 0)
468 {
469  char buffer[sizeof(T)];
470  ConversionUtilities::BE::getBytes(integer, buffer);
471  return std::string(buffer + startOffset, sizeof(T) - startOffset);
472 }
473 
474 CPP_UTILITIES_EXPORT std::string dataSizeToString(uint64 sizeInByte, bool includeByte = false);
475 CPP_UTILITIES_EXPORT std::string bitrateToString(double speedInKbitsPerSecond, bool useByteInsteadOfBits = false);
476 CPP_UTILITIES_EXPORT std::string encodeBase64(const byte *data, uint32 dataSize);
477 CPP_UTILITIES_EXPORT std::pair<std::unique_ptr<byte[]>, uint32> decodeBase64(const char *encodedStr, const uint32 strSize);
478 }
479 
480 #endif // CONVERSION_UTILITIES_STRINGCONVERSION_H
CPP_UTILITIES_EXPORT StringData convertUtf8ToUtf16LE(const char *inputBuffer, std::size_t inputBufferSize)
Converts the specified UTF-8 string to UTF-16 (little-endian).
bool startsWith(const StringType &str, const StringType &phrase)
Returns whether str starts with phrase.
void operator()(char *stringData)
Deletes the specified stringData with std::free(), because the memory has been allocated using std::m...
CPP_UTILITIES_EXPORT std::string encodeBase64(const byte *data, uint32 dataSize)
Encodes the specified data to Base64.
IntegralType stringToNumber(const StringType &string, typename StringType::value_type base=10)
Converts the given string to a number assuming string uses the specified base.
bool containsSubstrings(const StringType &str, std::initializer_list< StringType > substrings)
Returns whether str contains the specified substrings.
The ConversionException class is thrown by the various conversion functions of this library when a co...
CPP_UTILITIES_EXPORT StringData convertUtf16BEToUtf8(const char *inputBuffer, std::size_t inputBufferSize)
Converts the specified UTF-16 (big-endian) string to UTF-8.
CPP_UTILITIES_EXPORT void truncateString(std::string &str, char terminationChar='\0')
Truncates all characters after the first occurrence of the specified terminationChar and the terminat...
StringType numberToString(IntegralType number, typename StringType::value_type base=10)
Converts the given number to its equivalent string representation using the specified base...
std::uint64_t uint64
unsigned 64-bit integer
Definition: types.h:49
The StringDataDeleter struct deletes the data of a StringData instance.
typename std::enable_if< All< Condition... >::value, Detail::Enabler >::type EnableIf
Definition: traits.h:33
std::string interpretIntegerAsString(T integer, int startOffset=0)
Interprets the given integer at the specified position as std::string using the specified byte order...
CPP_UTILITIES_EXPORT StringData convertUtf8ToUtf16BE(const char *inputBuffer, std::size_t inputBufferSize)
Converts the specified UTF-8 string to UTF-16 (big-endian).
EmptyPartsTreat
Specifies the role of empty parts when splitting strings.
CPP_UTILITIES_EXPORT StringData convertUtf8ToLatin1(const char *inputBuffer, std::size_t inputBufferSize)
Converts the specified UTF-8 string to Latin-1.
void findAndReplace(StringType &str, const StringType &find, const StringType &replace)
Replaces all occurences of find with relpace in the specified str.
Contains several functions providing conversions between different data types.
std::uint32_t uint32
unsigned 32-bit integer
Definition: types.h:44
std::pair< std::unique_ptr< char[], StringDataDeleter >, std::size_t > StringData
Type used to return string encoding conversion result.
CPP_UTILITIES_EXPORT StringData convertUtf16LEToUtf8(const char *inputBuffer, std::size_t inputBufferSize)
Converts the specified UTF-16 (little-endian) string to UTF-8.
CharType charToDigit(CharType character, CharType base)
Returns number/digit of the specified character representation using the specified base...
Container::value_type joinStrings(const Container &strings, const typename Container::value_type &delimiter=typename Container::value_type(), bool omitEmpty=false, const typename Container::value_type &leftClosure=typename Container::value_type(), const typename Container::value_type &rightClosure=typename Container::value_type())
Joins the given strings using the specified delimiter.
CPP_UTILITIES_EXPORT StringData convertString(const char *fromCharset, const char *toCharset, const char *inputBuffer, std::size_t inputBufferSize, float outputBufferSizeFactor=1.0f)
Converts the specified string from one character set to another.
CharType digitToChar(CharType digit)
Returns the character representation of the specified digit.
std::uint8_t byte
unsigned byte
Definition: types.h:14
CPP_UTILITIES_EXPORT StringData convertLatin1ToUtf8(const char *inputBuffer, std::size_t inputBufferSize)
Converts the specified Latin-1 string to UTF-8.
Container splitString(const typename Container::value_type &string, const typename Container::value_type &delimiter, EmptyPartsTreat emptyPartsRole=EmptyPartsTreat::Keep, int maxParts=-1)
Splits the given string at the specified delimiter.
CPP_UTILITIES_EXPORT std::string dataSizeToString(uint64 sizeInByte, bool includeByte=false)
Converts the specified data size in byte to its equivalent std::string representation.
#define CPP_UTILITIES_EXPORT
Marks the symbol to be exported by the c++utilities library.
CPP_UTILITIES_EXPORT std::pair< std::unique_ptr< byte[]>, uint32 > decodeBase64(const char *encodedStr, const uint32 strSize)
Decodes the specified Base64 encoded string.
CPP_UTILITIES_EXPORT std::string bitrateToString(double speedInKbitsPerSecond, bool useByteInsteadOfBits=false)
Converts the specified bitrate in kbit/s to its equivalent std::string representation.