diff --git a/Makefile.am b/Makefile.am index d76361ccd..5b39e86b2 100644 --- a/Makefile.am +++ b/Makefile.am @@ -1,6 +1,6 @@ ## -*- coding: utf-8 -*- -## Copyright (C) 2011, 2012, 2013, 2014, 2015, 2016 Laboratoire de -## Recherche et Développement de l'Epita (LRDE). +## Copyright (C) 2011-2017 Laboratoire de Recherche et Développement +## de l'Epita (LRDE). ## Copyright (C) 2003, 2005 Laboratoire d'Informatique de Paris 6 (LIP6), ## département Systèmes Répartis Coopératifs (SRC), Université Pierre ## et Marie Curie. @@ -35,7 +35,7 @@ endif SUBDIRS = picosat buddy lib ltdl spot bin tests $(PYTHON_SUBDIR) doc \ $(NEVER_SUBDIRS) -UTF8 = utf8/doc/ReleaseNotes utf8/doc/utf8cpp.html utf8/utf8.h \ +UTF8 = utf8/README.md utf8/utf8.h \ utf8/utf8/checked.h utf8/utf8/core.h utf8/utf8/unchecked.h DEBIAN = \ diff --git a/utf8/README.md b/utf8/README.md new file mode 100644 index 000000000..d4369e85d --- /dev/null +++ b/utf8/README.md @@ -0,0 +1,1090 @@ +# UTF8-CPP: UTF-8 with C++ in a Portable Way + + +## Introduction + +Many C++ developers miss an easy and portable way of handling Unicode encoded strings. The original C++ Standard (known as C++98 or C++03) is Unicode agnostic. C++11 provides some support for Unicode on core language and library level: u8, u, and U character and string literals, char16_t and char32_t character types, u16string and u32string library classes, and codecvt support for conversions between Unicode encoding forms. In the meantime, developers use third party libraries like ICU, OS specific capabilities, or simply roll out their own solutions. + +In order to easily handle UTF-8 encoded Unicode strings, I came up with a small, C++98 compatible generic library. For anybody used to work with STL algorithms and iterators, it should be easy and natural to use. The code is freely available for any purpose - check out the license at the beginning of the utf8.h file. The library has been used a lot in the past ten years both in commercial and open-source projects and is considered feature-complete now. If you run into bugs or performance issues, please let me know and I'll do my best to address them. + +The purpose of this article is not to offer an introduction to Unicode in general, and UTF-8 in particular. If you are not familiar with Unicode, be sure to check out [Unicode Home Page](http://www.unicode.org/) or some other source of information for Unicode. Also, it is not my aim to advocate the use of UTF-8 encoded strings in C++ programs; if you want to handle UTF-8 encoded strings from C++, I am sure you have good reasons for it. + +## Examples of use + +### Introductionary Sample + +To illustrate the use of the library, let's start with a small but complete program that opens a file containing UTF-8 encoded text, reads it line by line, checks each line for invalid UTF-8 byte sequences, and converts it to UTF-16 encoding and back to UTF-8: + +```cpp +#include +#include +#include +#include +#include "utf8.h" +using namespace std; +int main(int argc, char** argv) +{ + if (argc != 2) { + cout << "\nUsage: docsample filename\n"; + return 0; + } + + const char* test_file_path = argv[1]; + // Open the test file (contains UTF-8 encoded text) + ifstream fs8(test_file_path); + if (!fs8.is_open()) { + cout << "Could not open " << test_file_path << endl; + return 0; + } + + unsigned line_count = 1; + string line; + // Play with all the lines in the file + while (getline(fs8, line)) { + // check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function) + string::iterator end_it = utf8::find_invalid(line.begin(), line.end()); + if (end_it != line.end()) { + cout << "Invalid UTF-8 encoding detected at line " << line_count << "\n"; + cout << "This part is fine: " << string(line.begin(), end_it) << "\n"; + } + + // Get the line length (at least for the valid part) + int length = utf8::distance(line.begin(), end_it); + cout << "Length of line " << line_count << " is " << length << "\n"; + + // Convert it to utf-16 + vector utf16line; + utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line)); + + // And back to utf-8 + string utf8line; + utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line)); + + // Confirm that the conversion went OK: + if (utf8line != string(line.begin(), end_it)) + cout << "Error in UTF-16 conversion at line: " << line_count << "\n"; + + line_count++; + } + return 0; +} +``` + +In the previous code sample, for each line we performed a detection of invalid UTF-8 sequences with `find_invalid`; the number of characters (more precisely - the number of Unicode code points, including the end of line and even BOM if there is one) in each line was determined with a use of `utf8::distance`; finally, we have converted each line to UTF-16 encoding with `utf8to16` and back to UTF-8 with `utf16to8`. + +### Checking if a file contains valid UTF-8 text + +Here is a function that checks whether the content of a file is valid UTF-8 encoded text without reading the content into the memory: + +```cpp +bool valid_utf8_file(const char* file_name) +{ + ifstream ifs(file_name); + if (!ifs) + return false; // even better, throw here + + istreambuf_iterator it(ifs.rdbuf()); + istreambuf_iterator eos; + + return utf8::is_valid(it, eos); +} +``` + +Because the function `utf8::is_valid()` works with input iterators, we were able to pass an `istreambuf_iterator` to it and read the content of the file directly without loading it to the memory first. + +Note that other functions that take input iterator arguments can be used in a similar way. For instance, to read the content of a UTF-8 encoded text file and convert the text to UTF-16, just do something like: + +```cpp + utf8::utf8to16(it, eos, back_inserter(u16string)); +``` + +### Ensure that a string contains valid UTF-8 text + +If we have some text that "probably" contains UTF-8 encoded text and we want to replace any invalid UTF-8 sequence with a replacement character, something like the following function may be used: + +```cpp +void fix_utf8_string(std::string& str) +{ + std::string temp; + utf8::replace_invalid(str.begin(), str.end(), back_inserter(temp)); + str = temp; +} +``` + +The function will replace any invalid UTF-8 sequence with a Unicode replacement character. There is an overloaded function that enables the caller to supply their own replacement character. + +## Reference + +### Functions From utf8 Namespace + +#### utf8::append + +Available in version 1.0 and later. + +Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence to a UTF-8 string. + +```cpp +template +octet_iterator append(uint32_t cp, octet_iterator result); +``` + +`octet_iterator`: an output iterator. +`cp`: a 32 bit integer representing a code point to append to the sequence. +`result`: an output iterator to the place in the sequence where to append the code point. +Return value: an iterator pointing to the place after the newly appended sequence. + +Example of use: + +```cpp +unsigned char u[5] = {0,0,0,0,0}; +unsigned char* end = append(0x0448, u); +assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0); +``` + +Note that `append` does not allocate any memory - it is the burden of the caller to make sure there is enough memory allocated for the operation. To make things more interesting, `append` can add anywhere between 1 and 4 octets to the sequence. In practice, you would most often want to use `std::back_inserter` to ensure that the necessary memory is allocated. + +In case of an invalid code point, a `utf8::invalid_code_point` exception is thrown. + +#### utf8::next + +Available in version 1.0 and later. + +Given the iterator to the beginning of the UTF-8 sequence, it returns the code point and moves the iterator to the next position. + +```cpp +template +uint32_t next(octet_iterator& it, octet_iterator end); +``` + +`octet_iterator`: an input iterator. +`it`: a reference to an iterator pointing to the beginning of an UTF-8 encoded code point. After the function returns, it is incremented to point to the beginning of the next code point. +`end`: end of the UTF-8 sequence to be processed. If `it` gets equal to `end` during the extraction of a code point, an `utf8::not_enough_room` exception is thrown. +Return value: the 32 bit representation of the processed UTF-8 code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars; +int cp = next(w, twochars + 6); +assert (cp == 0x65e5); +assert (w == twochars + 3); +``` + +This function is typically used to iterate through a UTF-8 encoded string. + +In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. + +#### utf8::peek_next + +Available in version 2.1 and later. + +Given the iterator to the beginning of the UTF-8 sequence, it returns the code point for the following sequence without changing the value of the iterator. + +```cpp +template +uint32_t peek_next(octet_iterator it, octet_iterator end); +``` + + +`octet_iterator`: an input iterator. +`it`: an iterator pointing to the beginning of an UTF-8 encoded code point. +`end`: end of the UTF-8 sequence to be processed. If `it` gets equal to `end` during the extraction of a code point, an `utf8::not_enough_room` exception is thrown. +Return value: the 32 bit representation of the processed UTF-8 code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars; +int cp = peek_next(w, twochars + 6); +assert (cp == 0x65e5); +assert (w == twochars); +``` + +In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. + +#### utf8::prior + +Available in version 1.02 and later. + +Given a reference to an iterator pointing to an octet in a UTF-8 sequence, it decreases the iterator until it hits the beginning of the previous UTF-8 encoded code point and returns the 32 bits representation of the code point. + +```cpp +template +uint32_t prior(octet_iterator& it, octet_iterator start); +``` + +`octet_iterator`: a bidirectional iterator. +`it`: a reference pointing to an octet within a UTF-8 encoded string. After the function returns, it is decremented to point to the beginning of the previous code point. +`start`: an iterator to the beginning of the sequence where the search for the beginning of a code point is performed. It is a safety measure to prevent passing the beginning of the string in the search for a UTF-8 lead octet. + Return value: the 32 bit representation of the previous code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +unsigned char* w = twochars + 3; +int cp = prior (w, twochars); +assert (cp == 0x65e5); +assert (w == twochars); +``` + +This function has two purposes: one is two iterate backwards through a UTF-8 encoded string. Note that it is usually a better idea to iterate forward instead, since `utf8::next` is faster. The second purpose is to find a beginning of a UTF-8 sequence if we have a random position within a string. Note that in that case `utf8::prior` may not detect an invalid UTF-8 sequence in some scenarios: for instance if there are superfluous trail octets, it will just skip them. + +`it` will typically point to the beginning of a code point, and `start` will point to the beginning of the string to ensure we don't go backwards too far. `it` is decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence beginning with that octet is decoded to a 32 bit representation and returned. + +In case `start` is reached before a UTF-8 lead octet is hit, or if an invalid UTF-8 sequence is started by the lead octet, an `invalid_utf8` exception is thrown. + +In case `start` equals `it`, a `not_enough_room` exception is thrown. + +#### utf8::previous + +Deprecated in version 1.02 and later. + +Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it decreases the iterator until it hits the beginning of the previous UTF-8 encoded code point and returns the 32 bits representation of the code point. + +```cpp +template +uint32_t previous(octet_iterator& it, octet_iterator pass_start); +``` + +`octet_iterator`: a random access iterator. +`it`: a reference pointing to an octet within a UTF-8 encoded string. After the function returns, it is decremented to point to the beginning of the previous code point. +`pass_start`: an iterator to the point in the sequence where the search for the beginning of a code point is aborted if no result was reached. It is a safety measure to prevent passing the beginning of the string in the search for a UTF-8 lead octet. +Return value: the 32 bit representation of the previous code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +unsigned char* w = twochars + 3; +int cp = previous (w, twochars - 1); +assert (cp == 0x65e5); +assert (w == twochars); +``` + + +`utf8::previous` is deprecated, and `utf8::prior` should be used instead, although the existing code can continue using this function. The problem is the parameter `pass_start` that points to the position just before the beginning of the sequence. Standard containers don't have the concept of "pass start" and the function can not be used with their iterators. + +`it` will typically point to the beginning of a code point, and `pass_start` will point to the octet just before the beginning of the string to ensure we don't go backwards too far. `it` is decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence beginning with that octet is decoded to a 32 bit representation and returned. + +In case `pass_start` is reached before a UTF-8 lead octet is hit, or if an invalid UTF-8 sequence is started by the lead octet, an `invalid_utf8` exception is thrown + +#### utf8::advance +Available in version 1.0 and later. + +Advances an iterator by the specified number of code points within an UTF-8 sequence. + +```cpp +template +void advance (octet_iterator& it, distance_type n, octet_iterator end); +``` + +`octet_iterator`: an input iterator. +`distance_type`: an integral type convertible to `octet_iterator`'s difference type. +`it`: a reference to an iterator pointing to the beginning of an UTF-8 encoded code point. After the function returns, it is incremented to point to the nth following code point. +`n`: a positive integer that shows how many code points we want to advance. +`end`: end of the UTF-8 sequence to be processed. If `it` gets equal to `end` during the extraction of a code point, an `utf8::not_enough_room` exception is thrown. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +unsigned char* w = twochars; +advance (w, 2, twochars + 6); +assert (w == twochars + 5); +``` + +This function works only "forward". In case of a negative `n`, there is no effect. + +In case of an invalid code point, a `utf8::invalid_code_point` exception is thrown. + +#### utf8::distance + +Available in version 1.0 and later. + +Given the iterators to two UTF-8 encoded code points in a seqence, returns the number of code points between them. + +```cpp +template +typename std::iterator_traits::difference_type distance (octet_iterator first, octet_iterator last); +``` + +`octet_iterator`: an input iterator. +`first`: an iterator to a beginning of a UTF-8 encoded code point. +`last`: an iterator to a "post-end" of the last UTF-8 encoded code point in the sequence we are trying to determine the length. It can be the beginning of a new code point, or not. + Return value the distance between the iterators, in code points. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +size_t dist = utf8::distance(twochars, twochars + 5); +assert (dist == 2); +``` + +This function is used to find the length (in code points) of a UTF-8 encoded string. The reason it is called _distance_, rather than, say, _length_ is mainly because developers are used that _length_ is an O(1) function. Computing the length of an UTF-8 string is a linear operation, and it looked better to model it after `std::distance` algorithm. + +In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. If `last` does not point to the past-of-end of a UTF-8 seqence, a `utf8::not_enough_room` exception is thrown. + +#### utf8::utf16to8 + +Available in version 1.0 and later. + +Converts a UTF-16 encoded string to UTF-8. + +```cpp +template +octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result); +``` + +`u16bit_iterator`: an input iterator. +`octet_iterator`: an output iterator. +`start`: an iterator pointing to the beginning of the UTF-16 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-16 encoded string to convert. +`result`: an output iterator to the place in the UTF-8 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-8 string. + +Example of use: + +```cpp +unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; +vector utf8result; +utf16to8(utf16string, utf16string + 5, back_inserter(utf8result)); +assert (utf8result.size() == 10); +``` + +In case of invalid UTF-16 sequence, a `utf8::invalid_utf16` exception is thrown. + +#### utf8::utf8to16 + +Available in version 1.0 and later. + +Converts an UTF-8 encoded string to UTF-16 + +```cpp +template +u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result); +``` + +`octet_iterator`: an input iterator. +`u16bit_iterator`: an output iterator. +`start`: an iterator pointing to the beginning of the UTF-8 encoded string to convert. < br /> `end`: an iterator pointing to pass-the-end of the UTF-8 encoded string to convert. +`result`: an output iterator to the place in the UTF-16 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-16 string. + +Example of use: + +```cpp +char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; +vector utf16result; +utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result)); +assert (utf16result.size() == 4); +assert (utf16result[2] == 0xd834); +assert (utf16result[3] == 0xdd1e); +``` + +In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. If `end` does not point to the past-of-end of a UTF-8 seqence, a `utf8::not_enough_room` exception is thrown. + +#### utf8::utf32to8 + +Available in version 1.0 and later. + +Converts a UTF-32 encoded string to UTF-8. + +```cpp +template +octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result); +``` + +`octet_iterator`: an output iterator. +`u32bit_iterator`: an input iterator. +`start`: an iterator pointing to the beginning of the UTF-32 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-32 encoded string to convert. +`result`: an output iterator to the place in the UTF-8 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-8 string. + +Example of use: + +``` +int utf32string[] = {0x448, 0x65E5, 0x10346, 0}; +vector utf8result; +utf32to8(utf32string, utf32string + 3, back_inserter(utf8result)); +assert (utf8result.size() == 9); +``` + +In case of invalid UTF-32 string, a `utf8::invalid_code_point` exception is thrown. + +#### utf8::utf8to32 + +Available in version 1.0 and later. + +Converts a UTF-8 encoded string to UTF-32. + +```cpp +template +u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result); +``` + +`octet_iterator`: an input iterator. +`u32bit_iterator`: an output iterator. +`start`: an iterator pointing to the beginning of the UTF-8 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-8 encoded string to convert. +`result`: an output iterator to the place in the UTF-32 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-32 string. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +vector utf32result; +utf8to32(twochars, twochars + 5, back_inserter(utf32result)); +assert (utf32result.size() == 2); +``` + +In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. If `end` does not point to the past-of-end of a UTF-8 seqence, a `utf8::not_enough_room` exception is thrown. + +#### utf8::find_invalid + +Available in version 1.0 and later. + +Detects an invalid sequence within a UTF-8 string. + +```cpp +template +octet_iterator find_invalid(octet_iterator start, octet_iterator end); +``` + +`octet_iterator`: an input iterator. +`start`: an iterator pointing to the beginning of the UTF-8 string to test for validity. +`end`: an iterator pointing to pass-the-end of the UTF-8 string to test for validity. +Return value: an iterator pointing to the first invalid octet in the UTF-8 string. In case none were found, equals `end`. + +Example of use: + +```cpp +char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa"; +char* invalid = find_invalid(utf_invalid, utf_invalid + 6); +assert (invalid == utf_invalid + 5); +``` + +This function is typically used to make sure a UTF-8 string is valid before processing it with other functions. It is especially important to call it if before doing any of the _unchecked_ operations on it. + +#### utf8::is_valid + +Available in version 1.0 and later. + +Checks whether a sequence of octets is a valid UTF-8 string. + +```cpp +template +bool is_valid(octet_iterator start, octet_iterator end); +``` + +`octet_iterator`: an input iterator. +`start`: an iterator pointing to the beginning of the UTF-8 string to test for validity. +`end`: an iterator pointing to pass-the-end of the UTF-8 string to test for validity. +Return value: `true` if the sequence is a valid UTF-8 string; `false` if not. + +Example of use: + +```cpp +char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa"; +bool bvalid = is_valid(utf_invalid, utf_invalid + 6); +assert (bvalid == false); +``` + +`is_valid` is a shorthand for `find_invalid(start, end) == end;`. You may want to use it to make sure that a byte seqence is a valid UTF-8 string without the need to know where it fails if it is not valid. + +#### utf8::replace_invalid + +Available in version 2.0 and later. + +Replaces all invalid UTF-8 sequences within a string with a replacement marker. + +```cpp +template +output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement); +template +output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out); +``` + +`octet_iterator`: an input iterator. +`output_iterator`: an output iterator. +`start`: an iterator pointing to the beginning of the UTF-8 string to look for invalid UTF-8 sequences. +`end`: an iterator pointing to pass-the-end of the UTF-8 string to look for invalid UTF-8 sequences. +`out`: An output iterator to the range where the result of replacement is stored. +`replacement`: A Unicode code point for the replacement marker. The version without this parameter assumes the value `0xfffd` +Return value: An iterator pointing to the place after the UTF-8 string with replaced invalid sequences. + +Example of use: + +```cpp +char invalid_sequence[] = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"; +vector replace_invalid_result; +replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), back_inserter(replace_invalid_result), '?'); +bvalid = is_valid(replace_invalid_result.begin(), replace_invalid_result.end()); +assert (bvalid); +char* fixed_invalid_sequence = "a????z"; +assert (std::equal(replace_invalid_result.begin(), replace_invalid_result.end(), fixed_invalid_sequence)); +``` + +`replace_invalid` does not perform in-place replacement of invalid sequences. Rather, it produces a copy of the original string with the invalid sequences replaced with a replacement marker. Therefore, `out` must not be in the `[start, end]` range. + +If `end` does not point to the past-of-end of a UTF-8 sequence, a `utf8::not_enough_room` exception is thrown. + +#### utf8::starts_with_bom + +Available in version 2.3 and later. Relaces deprecated `is_bom()` function. + +Checks whether an octet sequence starts with a UTF-8 byte order mark (BOM) + +```cpp +template +bool starts_with_bom (octet_iterator it, octet_iterator end); +``` + +`octet_iterator`: an input iterator. +`it`: beginning of the octet sequence to check +`end`: pass-end of the sequence to check +Return value: `true` if the sequence starts with a UTF-8 byte order mark; `false` if not. + +Example of use: + +```cpp +unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf}; +bool bbom = starts_with_bom(byte_order_mark, byte_order_mark + sizeof(byte_order_mark)); +assert (bbom == true); +``` + +The typical use of this function is to check the first three bytes of a file. If they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8 encoded text. + +#### utf8::is_bom + +Available in version 1.0 and later. Deprecated in version 2.3\. `starts_with_bom()` should be used instead. + +Checks whether a sequence of three octets is a UTF-8 byte order mark (BOM) + +```cpp +template +bool is_bom (octet_iterator it); // Deprecated +``` + +`octet_iterator`: an input iterator. +`it`: beginning of the 3-octet sequence to check +Return value: `true` if the sequence is UTF-8 byte order mark; `false` if not. + +Example of use: + +```cpp +unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf}; +bool bbom = is_bom(byte_order_mark); +assert (bbom == true); +``` + +The typical use of this function is to check the first three bytes of a file. If they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8 encoded text. + +If a sequence is shorter than three bytes, an invalid iterator will be dereferenced. Therefore, this function is deprecated in favor of `starts_with_bom()`that takes the end of sequence as an argument. + +### Types From utf8 Namespace + +#### utf8::exception + +Available in version 2.3 and later. + +Base class for the exceptions thrown by UTF CPP library functions. + +```cpp +class exception : public std::exception {}; +``` + +Example of use: + +```cpp +try { + code_that_uses_utf_cpp_library(); +} +catch(const utf8::exception& utfcpp_ex) { + cerr << utfcpp_ex.what(); +} +``` + +#### utf8::invalid_code_point + +Available in version 1.0 and later. + +Thrown by UTF8 CPP functions such as `advance` and `next` if an UTF-8 sequence represents and invalid code point. + +```cpp +class invalid_code_point : public exception { +public: + uint32_t code_point() const; +}; +``` + +Member function `code_point()` can be used to determine the invalid code point that caused the exception to be thrown. + +#### utf8::invalid_utf8 + +Available in version 1.0 and later. + +Thrown by UTF8 CPP functions such as `next` and `prior` if an invalid UTF-8 sequence is detected during decoding. + +```cpp +class invalid_utf8 : public exception { +public: + uint8_t utf8_octet() const; +}; +``` + +Member function `utf8_octet()` can be used to determine the beginning of the byte sequence that caused the exception to be thrown. + +#### utf8::invalid_utf16 + +Available in version 1.0 and later. + +Thrown by UTF8 CPP function `utf16to8` if an invalid UTF-16 sequence is detected during decoding. + +```cpp +class invalid_utf16 : public exception { +public: + uint16_t utf16_word() const; +}; +``` + +Member function `utf16_word()` can be used to determine the UTF-16 code unit that caused the exception to be thrown. + +#### utf8::not_enough_room + +Available in version 1.0 and later. + +Thrown by UTF8 CPP functions such as `next` if the end of the decoded UTF-8 sequence was reached before the code point was decoded. + +```cpp +class not_enough_room : public exception {}; +``` + +#### utf8::iterator + +Available in version 2.0 and later. + +Adapts the underlying octet iterator to iterate over the sequence of code points, rather than raw octets. + +```cpp +template +class iterator; +``` + +##### Member functions + +`iterator();` the deafult constructor; the underlying octet_iterator is constructed with its default constructor. +`explicit iterator (const octet_iterator& octet_it, const octet_iterator& range_start, const octet_iterator& range_end);` a constructor that initializes the underlying octet_iterator with octet_it and sets the range in which the iterator is considered valid. +`octet_iterator base () const;` returns the underlying octet_iterator. +`uint32_t operator * () const;` decodes the utf-8 sequence the underlying octet_iterator is pointing to and returns the code point. +`bool operator == (const iterator& rhs) const;` returns `true` if the two underlaying iterators are equal. +`bool operator != (const iterator& rhs) const;` returns `true` if the two underlaying iterators are not equal. +`iterator& operator ++ ();` the prefix increment - moves the iterator to the next UTF-8 encoded code point. +`iterator operator ++ (int);` the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one. +`iterator& operator -- ();` the prefix decrement - moves the iterator to the previous UTF-8 encoded code point. +`iterator operator -- (int);` the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one. + +Example of use: + +```cpp +char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; +utf8::iterator it(threechars, threechars, threechars + 9); +utf8::iterator it2 = it; +assert (it2 == it); +assert (*it == 0x10346); +assert (*(++it) == 0x65e5); +assert ((*it++) == 0x65e5); +assert (*it == 0x0448); +assert (it != it2); +utf8::iterator endit (threechars + 9, threechars, threechars + 9); +assert (++it == endit); +assert (*(--it) == 0x0448); +assert ((*it--) == 0x0448); +assert (*it == 0x65e5); +assert (--it == utf8::iterator(threechars, threechars, threechars + 9)); +assert (*it == 0x10346); +``` + +The purpose of `utf8::iterator` adapter is to enable easy iteration as well as the use of STL algorithms with UTF-8 encoded strings. Increment and decrement operators are implemented in terms of `utf8::next()` and `utf8::prior()` functions. + +Note that `utf8::iterator` adapter is a checked iterator. It operates on the range specified in the constructor; any attempt to go out of that range will result in an exception. Even the comparison operators require both iterator object to be constructed against the same range - otherwise an exception is thrown. Typically, the range will be determined by sequence container functions `begin` and `end`, i.e.: + +```cpp +std::string s = "example"; +utf8::iterator i (s.begin(), s.begin(), s.end()); +``` + +### Functions From utf8::unchecked Namespace + +#### utf8::unchecked::append + +Available in version 1.0 and later. + +Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence to a UTF-8 string. + +```cpp +template +octet_iterator append(uint32_t cp, octet_iterator result); +``` + +`cp`: A 32 bit integer representing a code point to append to the sequence. +`result`: An output iterator to the place in the sequence where to append the code point. +Return value: An iterator pointing to the place after the newly appended sequence. + +Example of use: + +```cpp +unsigned char u[5] = {0,0,0,0,0}; +unsigned char* end = unchecked::append(0x0448, u); +assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0); +``` + +This is a faster but less safe version of `utf8::append`. It does not check for validity of the supplied code point, and may produce an invalid UTF-8 sequence. + +#### utf8::unchecked::next + +Available in version 1.0 and later. + +Given the iterator to the beginning of a UTF-8 sequence, it returns the code point and moves the iterator to the next position. + +```cpp +template +uint32_t next(octet_iterator& it); +``` + +`it`: a reference to an iterator pointing to the beginning of an UTF-8 encoded code point. After the function returns, it is incremented to point to the beginning of the next code point. + Return value: the 32 bit representation of the processed UTF-8 code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars; +int cp = unchecked::next(w); +assert (cp == 0x65e5); +assert (w == twochars + 3); +``` + +This is a faster but less safe version of `utf8::next`. It does not check for validity of the supplied UTF-8 sequence. + +#### utf8::unchecked::peek_next + +Available in version 2.1 and later. + +Given the iterator to the beginning of a UTF-8 sequence, it returns the code point. + +```cpp +template +uint32_t peek_next(octet_iterator it); +``` + +`it`: an iterator pointing to the beginning of an UTF-8 encoded code point. +Return value: the 32 bit representation of the processed UTF-8 code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars; +int cp = unchecked::peek_next(w); +assert (cp == 0x65e5); +assert (w == twochars); +``` + +This is a faster but less safe version of `utf8::peek_next`. It does not check for validity of the supplied UTF-8 sequence. + +#### utf8::unchecked::prior + +Available in version 1.02 and later. + +Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it decreases the iterator until it hits the beginning of the previous UTF-8 encoded code point and returns the 32 bits representation of the code point. + +```cpp +template +uint32_t prior(octet_iterator& it); +``` + +`it`: a reference pointing to an octet within a UTF-8 encoded string. After the function returns, it is decremented to point to the beginning of the previous code point. + Return value: the 32 bit representation of the previous code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars + 3; +int cp = unchecked::prior (w); +assert (cp == 0x65e5); +assert (w == twochars); +``` + +This is a faster but less safe version of `utf8::prior`. It does not check for validity of the supplied UTF-8 sequence and offers no boundary checking. + +#### utf8::unchecked::previous (deprecated, see utf8::unchecked::prior) + +Deprecated in version 1.02 and later. + +Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it decreases the iterator until it hits the beginning of the previous UTF-8 encoded code point and returns the 32 bits representation of the code point. + +```cpp +template +uint32_t previous(octet_iterator& it); +``` + +`it`: a reference pointing to an octet within a UTF-8 encoded string. After the function returns, it is decremented to point to the beginning of the previous code point. +Return value: the 32 bit representation of the previous code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars + 3; +int cp = unchecked::previous (w); +assert (cp == 0x65e5); +assert (w == twochars); +``` + +The reason this function is deprecated is just the consistency with the "checked" versions, where `prior` should be used instead of `previous`. In fact, `unchecked::previous` behaves exactly the same as `unchecked::prior` + +This is a faster but less safe version of `utf8::previous`. It does not check for validity of the supplied UTF-8 sequence and offers no boundary checking. + +#### utf8::unchecked::advance + +Available in version 1.0 and later. + +Advances an iterator by the specified number of code points within an UTF-8 sequence. + +```cpp +template +void advance (octet_iterator& it, distance_type n); +``` + +`it`: a reference to an iterator pointing to the beginning of an UTF-8 encoded code point. After the function returns, it is incremented to point to the nth following code point. +`n`: a positive integer that shows how many code points we want to advance. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars; +unchecked::advance (w, 2); +assert (w == twochars + 5); +``` + +This function works only "forward". In case of a negative `n`, there is no effect. + +This is a faster but less safe version of `utf8::advance`. It does not check for validity of the supplied UTF-8 sequence and offers no boundary checking. + +#### utf8::unchecked::distance + +Available in version 1.0 and later. + +Given the iterators to two UTF-8 encoded code points in a seqence, returns the number of code points between them. + +```cpp +template +typename std::iterator_traits::difference_type distance (octet_iterator first, octet_iterator last); +``` + +`first`: an iterator to a beginning of a UTF-8 encoded code point. +`last`: an iterator to a "post-end" of the last UTF-8 encoded code point in the sequence we are trying to determine the length. It can be the beginning of a new code point, or not. +Return value: the distance between the iterators, in code points. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +size_t dist = utf8::unchecked::distance(twochars, twochars + 5); +assert (dist == 2); +``` + +This is a faster but less safe version of `utf8::distance`. It does not check for validity of the supplied UTF-8 sequence. + +#### utf8::unchecked::utf16to8 + +Available in version 1.0 and later. + +Converts a UTF-16 encoded string to UTF-8. + +```cpp +template +octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result); +``` + +`start`: an iterator pointing to the beginning of the UTF-16 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-16 encoded string to convert. +`result`: an output iterator to the place in the UTF-8 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-8 string. + +Example of use: + +```cpp +unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; +vector utf8result; +unchecked::utf16to8(utf16string, utf16string + 5, back_inserter(utf8result)); +assert (utf8result.size() == 10); +``` + +This is a faster but less safe version of `utf8::utf16to8`. It does not check for validity of the supplied UTF-16 sequence. + +#### utf8::unchecked::utf8to16 + +Available in version 1.0 and later. + +Converts an UTF-8 encoded string to UTF-16 + +```cpp +template +u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result); +``` + +`start`: an iterator pointing to the beginning of the UTF-8 encoded string to convert. < br /> `end`: an iterator pointing to pass-the-end of the UTF-8 encoded string to convert. +`result`: an output iterator to the place in the UTF-16 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-16 string. + +Example of use: + +```cpp +char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; +vector utf16result; +unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result)); +assert (utf16result.size() == 4); +assert (utf16result[2] == 0xd834); +assert (utf16result[3] == 0xdd1e); +``` + +This is a faster but less safe version of `utf8::utf8to16`. It does not check for validity of the supplied UTF-8 sequence. + +#### utf8::unchecked::utf32to8 + +Available in version 1.0 and later. + +Converts a UTF-32 encoded string to UTF-8. + +```cpp +template +octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result); +``` + +`start`: an iterator pointing to the beginning of the UTF-32 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-32 encoded string to convert. +`result`: an output iterator to the place in the UTF-8 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-8 string. + +Example of use: + +```cpp +int utf32string[] = {0x448, 0x65e5, 0x10346, 0}; +vector utf8result; +utf32to8(utf32string, utf32string + 3, back_inserter(utf8result)); +assert (utf8result.size() == 9); +``` + +This is a faster but less safe version of `utf8::utf32to8`. It does not check for validity of the supplied UTF-32 sequence. + +#### utf8::unchecked::utf8to32 + +Available in version 1.0 and later. + +Converts a UTF-8 encoded string to UTF-32. + +```cpp +template +u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result); +``` + +`start`: an iterator pointing to the beginning of the UTF-8 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-8 encoded string to convert. +`result`: an output iterator to the place in the UTF-32 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-32 string. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +vector utf32result; +unchecked::utf8to32(twochars, twochars + 5, back_inserter(utf32result)); +assert (utf32result.size() == 2); +``` + +This is a faster but less safe version of `utf8::utf8to32`. It does not check for validity of the supplied UTF-8 sequence. + +### Types From utf8::unchecked Namespace + +#### utf8::iterator + +Available in version 2.0 and later. + +Adapts the underlying octet iterator to iterate over the sequence of code points, rather than raw octets. + +```cpp +template +class iterator; +``` + +##### Member functions + +`iterator();` the deafult constructor; the underlying octet_iterator is constructed with its default constructor. +`explicit iterator (const octet_iterator& octet_it);` a constructor that initializes the underlying octet_iterator with `octet_it` +`octet_iterator base () const;` returns the underlying octet_iterator. +`uint32_t operator * () const;` decodes the utf-8 sequence the underlying octet_iterator is pointing to and returns the code point. +`bool operator == (const iterator& rhs) const;` returns `true` if the two underlaying iterators are equal. +`bool operator != (const iterator& rhs) const;` returns `true` if the two underlaying iterators are not equal. +`iterator& operator ++ ();` the prefix increment - moves the iterator to the next UTF-8 encoded code point. +`iterator operator ++ (int);` the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one. +`iterator& operator -- ();` the prefix decrement - moves the iterator to the previous UTF-8 encoded code point. +`iterator operator -- (int);` the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one. + +Example of use: + +```cpp +char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; +utf8::unchecked::iterator un_it(threechars); +utf8::unchecked::iterator un_it2 = un_it; +assert (un_it2 == un_it); +assert (*un_it == 0x10346); +assert (*(++un_it) == 0x65e5); +assert ((*un_it++) == 0x65e5); +assert (*un_it == 0x0448); +assert (un_it != un_it2); +utf8::::unchecked::iterator un_endit (threechars + 9); +assert (++un_it == un_endit); +assert (*(--un_it) == 0x0448); +assert ((*un_it--) == 0x0448); +assert (*un_it == 0x65e5); +assert (--un_it == utf8::unchecked::iterator(threechars)); +assert (*un_it == 0x10346); +``` + +This is an unchecked version of `utf8::iterator`. It is faster in many cases, but offers no validity or range checks. + +## Points of interest + +#### Design goals and decisions + +The library was designed to be: + +1. Generic: for better or worse, there are many C++ string classes out there, and the library should work with as many of them as possible. +2. Portable: the library should be portable both accross different platforms and compilers. The only non-portable code is a small section that declares unsigned integers of different sizes: three typedefs. They can be changed by the users of the library if they don't match their platform. The default setting should work for Windows (both 32 and 64 bit), and most 32 bit and 64 bit Unix derivatives. At this point I don't plan to use any post C++03 features, so the library should work even with pretty old compilers. +3. Lightweight: follow the "pay only for what you use" guideline. +4. Unintrusive: avoid forcing any particular design or even programming style on the user. This is a library, not a framework. + +#### Alternatives + +In case you want to look into other means of working with UTF-8 strings from C++, here is the list of solutions I am aware of: + +1. [ICU Library](http://icu.sourceforge.net/). It is very powerful, complete, feature-rich, mature, and widely used. Also big, intrusive, non-generic, and doesn't play well with the Standard Library. I definitelly recommend looking at ICU even if you don't plan to use it. +2. C++11 language and library features. Still far from complete, and not easy to use. +3. [Glib::ustring](http://www.gtkmm.org/gtkmm2/docs/tutorial/html/ch03s04.html). A class specifically made to work with UTF-8 strings, and also feel like `std::string`. If you prefer to have yet another string class in your code, it may be worth a look. Be aware of the licensing issues, though. +4. Platform dependent solutions: Windows and POSIX have functions to convert strings from one encoding to another. That is only a subset of what my library offers, but if that is all you need it may be good enough. + +## Links + +1. [The Unicode Consortium](http://www.unicode.org/). +2. [ICU Library](http://icu.sourceforge.net/). +3. [UTF-8 at Wikipedia](http://en.wikipedia.org/wiki/UTF-8) +4. [UTF-8 and Unicode FAQ for Unix/Linux](http://www.cl.cam.ac.uk/~mgk25/unicode.html) diff --git a/utf8/doc/ReleaseNotes b/utf8/doc/ReleaseNotes deleted file mode 100644 index c0c01a3c6..000000000 --- a/utf8/doc/ReleaseNotes +++ /dev/null @@ -1,12 +0,0 @@ -utf8 cpp library -Release 2.3.1 - -A bug fix release. Special thanks to dalle and Ivan Sorokin who reported the bugs. - -Changes from version 2.3 -- Bug fix [3025042]: is_bom documentation issue. -- Bug fix [3083640]: is_code_point_valid incorrectly returns false. -- Bug fix [3167987]: prior moves it before start. -- Bug fix [3185087]: utf8::prior and utf8::previous documentation issue. - -Files included in the release: utf8.h, core.h, checked.h, unchecked.h, utf8cpp.html, ReleaseNotes diff --git a/utf8/doc/utf8cpp.html b/utf8/doc/utf8cpp.html deleted file mode 100644 index c0a89a27d..000000000 --- a/utf8/doc/utf8cpp.html +++ /dev/null @@ -1,1795 +0,0 @@ - - - - - - - - - UTF8-CPP: UTF-8 with C++ in a Portable Way - - - - -

- UTF8-CPP: UTF-8 with C++ in a Portable Way -

-

- The Sourceforge project page -

- -

- Introduction -

-

- Many C++ developers miss an easy and portable way of handling Unicode encoded - strings. The original C++ Standard (known as C++98 or C++03) is Unicode agnostic, - and while some work is being done to introduce Unicode to the next incarnation - called C++0x, for the moment nothing of the sort is available. In the meantime, - developers use third party libraries like ICU, OS specific capabilities, or simply - roll out their own solutions. -

-

- In order to easily handle UTF-8 encoded Unicode strings, I came up with a small - generic library. For anybody used to work with STL algorithms and iterators, it should be - easy and natural to use. The code is freely available for any purpose - check out - the license at the beginning of the utf8.h file. If you run into - bugs or performance issues, please let me know and I'll do my best to address them. -

-

- The purpose of this article is not to offer an introduction to Unicode in general, - and UTF-8 in particular. If you are not familiar with Unicode, be sure to check out - Unicode Home Page or some other source of - information for Unicode. Also, it is not my aim to advocate the use of UTF-8 - encoded strings in C++ programs; if you want to handle UTF-8 encoded strings from - C++, I am sure you have good reasons for it. -

-

- Examples of use -

-

- Introductionary Sample -

-

- To illustrate the use of the library, let's start with a small but complete program - that opens a file containing UTF-8 encoded text, reads it line by line, checks each line - for invalid UTF-8 byte sequences, and converts it to UTF-16 encoding and back to UTF-8: -

-
-#include <fstream>
-#include <iostream>
-#include <string>
-#include <vector>
-#include "utf8.h"
-using namespace std;
-int main(int argc, char** argv)
-{
-    if (argc != 2) {
-        cout << "\nUsage: docsample filename\n";
-        return 0;
-    }
-
-    const char* test_file_path = argv[1];
-    // Open the test file (contains UTF-8 encoded text)
-    ifstream fs8(test_file_path);
-    if (!fs8.is_open()) {
-    cout << "Could not open " << test_file_path << endl;
-    return 0;
-    }
-
-    unsigned line_count = 1;
-    string line;
-    // Play with all the lines in the file
-    while (getline(fs8, line)) {
-       // check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function)
-        string::iterator end_it = utf8::find_invalid(line.begin(), line.end());
-        if (end_it != line.end()) {
-            cout << "Invalid UTF-8 encoding detected at line " << line_count << "\n";
-            cout << "This part is fine: " << string(line.begin(), end_it) << "\n";
-        }
-
-        // Get the line length (at least for the valid part)
-        int length = utf8::distance(line.begin(), end_it);
-        cout << "Length of line " << line_count << " is " << length <<  "\n";
-
-        // Convert it to utf-16
-        vector<unsigned short> utf16line;
-        utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line));
-
-        // And back to utf-8
-        string utf8line; 
-        utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line));
-
-        // Confirm that the conversion went OK:
-        if (utf8line != string(line.begin(), end_it))
-            cout << "Error in UTF-16 conversion at line: " << line_count << "\n";        
-
-        line_count++;
-    }
-    return 0;
-}
-
-

- In the previous code sample, for each line we performed - a detection of invalid UTF-8 sequences with find_invalid; the number - of characters (more precisely - the number of Unicode code points, including the end - of line and even BOM if there is one) in each line was - determined with a use of utf8::distance; finally, we have converted - each line to UTF-16 encoding with utf8to16 and back to UTF-8 with - utf16to8. -

-

Checking if a file contains valid UTF-8 text

-

-Here is a function that checks whether the content of a file is valid UTF-8 encoded text without -reading the content into the memory: -

-
    
-bool valid_utf8_file(iconst char* file_name)
-{
-    ifstream ifs(file_name);
-    if (!ifs)
-        return false; // even better, throw here
-
-    istreambuf_iterator<char> it(ifs.rdbuf());
-    istreambuf_iterator<char> eos;
-
-    return utf8::is_valid(it, eos);
-}
-
-

-Because the function utf8::is_valid() works with input iterators, we were able -to pass an istreambuf_iterator to it and read the content of the file directly -without loading it to the memory first.

-

-Note that other functions that take input iterator arguments can be used in a similar way. For -instance, to read the content of a UTF-8 encoded text file and convert the text to UTF-16, just -do something like: -

-
-    utf8::utf8to16(it, eos, back_inserter(u16string));
-
-

Ensure that a string contains valid UTF-8 text

-

-If we have some text that "probably" contains UTF-8 encoded text and we want to -replace any invalid UTF-8 sequence with a replacement character, something like -the following function may be used: -

-
-void fix_utf8_string(std::string& str)
-{
-    std::string temp;
-    utf8::replace_invalid(str.begin(), str.end(), back_inserter(temp));
-    str = temp;
-}
-
-

The function will replace any invalid UTF-8 sequence with a Unicode replacement character. -There is an overloaded function that enables the caller to supply their own replacement character. -

-

- Reference -

-

- Functions From utf8 Namespace -

-

- utf8::append -

-

- Available in version 1.0 and later. -

-

- Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence - to a UTF-8 string. -

-
-template <typename octet_iterator>
-octet_iterator append(uint32_t cp, octet_iterator result);
-   
-
-

- octet_iterator: an output iterator.
- cp: a 32 bit integer representing a code point to append to the - sequence.
- result: an output iterator to the place in the sequence where to - append the code point.
- Return value: an iterator pointing to the place - after the newly appended sequence. -

-

- Example of use: -

-
-unsigned char u[5] = {0,0,0,0,0};
-unsigned char* end = append(0x0448, u);
-assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0);
-
-

- Note that append does not allocate any memory - it is the burden of - the caller to make sure there is enough memory allocated for the operation. To make - things more interesting, append can add anywhere between 1 and 4 - octets to the sequence. In practice, you would most often want to use - std::back_inserter to ensure that the necessary memory is allocated. -

-

- In case of an invalid code point, a utf8::invalid_code_point exception - is thrown. -

-

- utf8::next -

-

- Available in version 1.0 and later. -

-

- Given the iterator to the beginning of the UTF-8 sequence, it returns the code - point and moves the iterator to the next position. -

-
-template <typename octet_iterator> 
-uint32_t next(octet_iterator& it, octet_iterator end);
-   
-
-

- octet_iterator: an input iterator.
- it: a reference to an iterator pointing to the beginning of an UTF-8 - encoded code point. After the function returns, it is incremented to point to the - beginning of the next code point.
- end: end of the UTF-8 sequence to be processed. If it - gets equal to end during the extraction of a code point, an - utf8::not_enough_room exception is thrown.
- Return value: the 32 bit representation of the - processed UTF-8 code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-char* w = twochars;
-int cp = next(w, twochars + 6);
-assert (cp == 0x65e5);
-assert (w == twochars + 3);
-
-

- This function is typically used to iterate through a UTF-8 encoded string. -

-

- In case of an invalid UTF-8 seqence, a utf8::invalid_utf8 exception is - thrown. -

-

- utf8::peek_next -

-

- Available in version 2.1 and later. -

-

- Given the iterator to the beginning of the UTF-8 sequence, it returns the code - point for the following sequence without changing the value of the iterator. -

-
-template <typename octet_iterator> 
-uint32_t peek_next(octet_iterator it, octet_iterator end);
-   
-
-

- octet_iterator: an input iterator.
- it: an iterator pointing to the beginning of an UTF-8 - encoded code point.
- end: end of the UTF-8 sequence to be processed. If it - gets equal to end during the extraction of a code point, an - utf8::not_enough_room exception is thrown.
- Return value: the 32 bit representation of the - processed UTF-8 code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-char* w = twochars;
-int cp = peek_next(w, twochars + 6);
-assert (cp == 0x65e5);
-assert (w == twochars);
-
-

- In case of an invalid UTF-8 seqence, a utf8::invalid_utf8 exception is - thrown. -

-

- utf8::prior -

-

- Available in version 1.02 and later. -

-

- Given a reference to an iterator pointing to an octet in a UTF-8 sequence, it - decreases the iterator until it hits the beginning of the previous UTF-8 encoded - code point and returns the 32 bits representation of the code point. -

-
-template <typename octet_iterator> 
-uint32_t prior(octet_iterator& it, octet_iterator start);
-   
-
-

- octet_iterator: a bidirectional iterator.
- it: a reference pointing to an octet within a UTF-8 encoded string. - After the function returns, it is decremented to point to the beginning of the - previous code point.
- start: an iterator to the beginning of the sequence where the search - for the beginning of a code point is performed. It is a - safety measure to prevent passing the beginning of the string in the search for a - UTF-8 lead octet.
- Return value: the 32 bit representation of the - previous code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-unsigned char* w = twochars + 3;
-int cp = prior (w, twochars);
-assert (cp == 0x65e5);
-assert (w == twochars);
-
-

- This function has two purposes: one is two iterate backwards through a UTF-8 - encoded string. Note that it is usually a better idea to iterate forward instead, - since utf8::next is faster. The second purpose is to find a beginning - of a UTF-8 sequence if we have a random position within a string. Note that in that - case utf8::prior may not detect an invalid UTF-8 sequence in some scenarios: - for instance if there are superfluous trail octets, it will just skip them. -

-

- it will typically point to the beginning of - a code point, and start will point to the - beginning of the string to ensure we don't go backwards too far. it is - decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence - beginning with that octet is decoded to a 32 bit representation and returned. -

-

- In case start is reached before a UTF-8 lead octet is hit, or if an - invalid UTF-8 sequence is started by the lead octet, an invalid_utf8 - exception is thrown. -

-

In case start equals it, a not_enough_room - exception is thrown. -

- utf8::previous -

-

- Deprecated in version 1.02 and later. -

-

- Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it - decreases the iterator until it hits the beginning of the previous UTF-8 encoded - code point and returns the 32 bits representation of the code point. -

-
-template <typename octet_iterator> 
-uint32_t previous(octet_iterator& it, octet_iterator pass_start);
-   
-
-

- octet_iterator: a random access iterator.
- it: a reference pointing to an octet within a UTF-8 encoded string. - After the function returns, it is decremented to point to the beginning of the - previous code point.
- pass_start: an iterator to the point in the sequence where the search - for the beginning of a code point is aborted if no result was reached. It is a - safety measure to prevent passing the beginning of the string in the search for a - UTF-8 lead octet.
- Return value: the 32 bit representation of the - previous code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-unsigned char* w = twochars + 3;
-int cp = previous (w, twochars - 1);
-assert (cp == 0x65e5);
-assert (w == twochars);
-
-

- utf8::previous is deprecated, and utf8::prior should - be used instead, although the existing code can continue using this function. - The problem is the parameter pass_start that points to the position - just before the beginning of the sequence. Standard containers don't have the - concept of "pass start" and the function can not be used with their iterators. -

-

- it will typically point to the beginning of - a code point, and pass_start will point to the octet just before the - beginning of the string to ensure we don't go backwards too far. it is - decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence - beginning with that octet is decoded to a 32 bit representation and returned. -

-

- In case pass_start is reached before a UTF-8 lead octet is hit, or if an - invalid UTF-8 sequence is started by the lead octet, an invalid_utf8 - exception is thrown -

-

- utf8::advance -

-

- Available in version 1.0 and later. -

-

- Advances an iterator by the specified number of code points within an UTF-8 - sequence. -

-
-template <typename octet_iterator, typename distance_type> 
-void advance (octet_iterator& it, distance_type n, octet_iterator end);
-   
-
-

- octet_iterator: an input iterator.
- distance_type: an integral type convertible to octet_iterator's difference type.
- it: a reference to an iterator pointing to the beginning of an UTF-8 - encoded code point. After the function returns, it is incremented to point to the - nth following code point.
- n: a positive integer that shows how many code points we want to - advance.
- end: end of the UTF-8 sequence to be processed. If it - gets equal to end during the extraction of a code point, an - utf8::not_enough_room exception is thrown.
-

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-unsigned char* w = twochars;
-advance (w, 2, twochars + 6);
-assert (w == twochars + 5);
-
-

- This function works only "forward". In case of a negative n, there is - no effect. -

-

- In case of an invalid code point, a utf8::invalid_code_point exception - is thrown. -

-

- utf8::distance -

-

- Available in version 1.0 and later. -

-

- Given the iterators to two UTF-8 encoded code points in a seqence, returns the - number of code points between them. -

-
-template <typename octet_iterator> 
-typename std::iterator_traits<octet_iterator>::difference_type distance (octet_iterator first, octet_iterator last);
-   
-
-

- octet_iterator: an input iterator.
- first: an iterator to a beginning of a UTF-8 encoded code point.
- last: an iterator to a "post-end" of the last UTF-8 encoded code - point in the sequence we are trying to determine the length. It can be the - beginning of a new code point, or not.
- Return value the distance between the iterators, - in code points. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-size_t dist = utf8::distance(twochars, twochars + 5);
-assert (dist == 2);
-
-

- This function is used to find the length (in code points) of a UTF-8 encoded - string. The reason it is called distance, rather than, say, - length is mainly because developers are used that length is an - O(1) function. Computing the length of an UTF-8 string is a linear operation, and - it looked better to model it after std::distance algorithm. -

-

- In case of an invalid UTF-8 seqence, a utf8::invalid_utf8 exception is - thrown. If last does not point to the past-of-end of a UTF-8 seqence, - a utf8::not_enough_room exception is thrown. -

-

- utf8::utf16to8 -

-

- Available in version 1.0 and later. -

-

- Converts a UTF-16 encoded string to UTF-8. -

-
-template <typename u16bit_iterator, typename octet_iterator>
-octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result);
-   
-
-

- u16bit_iterator: an input iterator.
- octet_iterator: an output iterator.
- start: an iterator pointing to the beginning of the UTF-16 encoded - string to convert.
- end: an iterator pointing to pass-the-end of the UTF-16 encoded - string to convert.
- result: an output iterator to the place in the UTF-8 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-8 string. -

-

- Example of use: -

-
-unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
-vector<unsigned char> utf8result;
-utf16to8(utf16string, utf16string + 5, back_inserter(utf8result));
-assert (utf8result.size() == 10);    
-
-

- In case of invalid UTF-16 sequence, a utf8::invalid_utf16 exception is - thrown. -

-

- utf8::utf8to16 -

-

- Available in version 1.0 and later. -

-

- Converts an UTF-8 encoded string to UTF-16 -

-
-template <typename u16bit_iterator, typename octet_iterator>
-u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result);
-   
-
-

- octet_iterator: an input iterator.
- u16bit_iterator: an output iterator.
- start: an iterator pointing to the beginning of the UTF-8 encoded - string to convert. < br /> end: an iterator pointing to - pass-the-end of the UTF-8 encoded string to convert.
- result: an output iterator to the place in the UTF-16 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-16 string. -

-

- Example of use: -

-
-char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
-vector <unsigned short> utf16result;
-utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result));
-assert (utf16result.size() == 4);
-assert (utf16result[2] == 0xd834);
-assert (utf16result[3] == 0xdd1e);
-
-

- In case of an invalid UTF-8 seqence, a utf8::invalid_utf8 exception is - thrown. If end does not point to the past-of-end of a UTF-8 seqence, a - utf8::not_enough_room exception is thrown. -

-

- utf8::utf32to8 -

-

- Available in version 1.0 and later. -

-

- Converts a UTF-32 encoded string to UTF-8. -

-
-template <typename octet_iterator, typename u32bit_iterator>
-octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result);
-   
-
-

- octet_iterator: an output iterator.
- u32bit_iterator: an input iterator.
- start: an iterator pointing to the beginning of the UTF-32 encoded - string to convert.
- end: an iterator pointing to pass-the-end of the UTF-32 encoded - string to convert.
- result: an output iterator to the place in the UTF-8 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-8 string. -

-

- Example of use: -

-
-int utf32string[] = {0x448, 0x65E5, 0x10346, 0};
-vector<unsigned char> utf8result;
-utf32to8(utf32string, utf32string + 3, back_inserter(utf8result));
-assert (utf8result.size() == 9);
-
-

- In case of invalid UTF-32 string, a utf8::invalid_code_point exception - is thrown. -

-

- utf8::utf8to32 -

-

- Available in version 1.0 and later. -

-

- Converts a UTF-8 encoded string to UTF-32. -

-
-template <typename octet_iterator, typename u32bit_iterator>
-u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result);
-   
-
-

- octet_iterator: an input iterator.
- u32bit_iterator: an output iterator.
- start: an iterator pointing to the beginning of the UTF-8 encoded - string to convert.
- end: an iterator pointing to pass-the-end of the UTF-8 encoded string - to convert.
- result: an output iterator to the place in the UTF-32 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-32 string. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-vector<int> utf32result;
-utf8to32(twochars, twochars + 5, back_inserter(utf32result));
-assert (utf32result.size() == 2);
-
-

- In case of an invalid UTF-8 seqence, a utf8::invalid_utf8 exception is - thrown. If end does not point to the past-of-end of a UTF-8 seqence, a - utf8::not_enough_room exception is thrown. -

-

- utf8::find_invalid -

-

- Available in version 1.0 and later. -

-

- Detects an invalid sequence within a UTF-8 string. -

-
-template <typename octet_iterator> 
-octet_iterator find_invalid(octet_iterator start, octet_iterator end);
-
-

- octet_iterator: an input iterator.
- start: an iterator pointing to the beginning of the UTF-8 string to - test for validity.
- end: an iterator pointing to pass-the-end of the UTF-8 string to test - for validity.
- Return value: an iterator pointing to the first - invalid octet in the UTF-8 string. In case none were found, equals - end. -

-

- Example of use: -

-
-char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa";
-char* invalid = find_invalid(utf_invalid, utf_invalid + 6);
-assert (invalid == utf_invalid + 5);
-
-

- This function is typically used to make sure a UTF-8 string is valid before - processing it with other functions. It is especially important to call it if before - doing any of the unchecked operations on it. -

-

- utf8::is_valid -

-

- Available in version 1.0 and later. -

-

- Checks whether a sequence of octets is a valid UTF-8 string. -

-
-template <typename octet_iterator> 
-bool is_valid(octet_iterator start, octet_iterator end);
-   
-
-

- octet_iterator: an input iterator.
- start: an iterator pointing to the beginning of the UTF-8 string to - test for validity.
- end: an iterator pointing to pass-the-end of the UTF-8 string to test - for validity.
- Return value: true if the sequence - is a valid UTF-8 string; false if not. -

- Example of use: -
-char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa";
-bool bvalid = is_valid(utf_invalid, utf_invalid + 6);
-assert (bvalid == false);
-
-

- is_valid is a shorthand for find_invalid(start, end) == - end;. You may want to use it to make sure that a byte seqence is a valid - UTF-8 string without the need to know where it fails if it is not valid. -

-

- utf8::replace_invalid -

-

- Available in version 2.0 and later. -

-

- Replaces all invalid UTF-8 sequences within a string with a replacement marker. -

-
-template <typename octet_iterator, typename output_iterator>
-output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement);
-template <typename octet_iterator, typename output_iterator>
-output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out);
-   
-
-

- octet_iterator: an input iterator.
- output_iterator: an output iterator.
- start: an iterator pointing to the beginning of the UTF-8 string to - look for invalid UTF-8 sequences.
- end: an iterator pointing to pass-the-end of the UTF-8 string to look - for invalid UTF-8 sequences.
- out: An output iterator to the range where the result of replacement - is stored.
- replacement: A Unicode code point for the replacement marker. The - version without this parameter assumes the value 0xfffd
- Return value: An iterator pointing to the place - after the UTF-8 string with replaced invalid sequences. -

-

- Example of use: -

-
-char invalid_sequence[] = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z";
-vector<char> replace_invalid_result;
-replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), back_inserter(replace_invalid_result), '?');
-bvalid = is_valid(replace_invalid_result.begin(), replace_invalid_result.end());
-assert (bvalid);
-char* fixed_invalid_sequence = "a????z";
-assert (std::equal(replace_invalid_result.begin(), replace_invalid_result.end(), fixed_invalid_sequence));
-
-

- replace_invalid does not perform in-place replacement of invalid - sequences. Rather, it produces a copy of the original string with the invalid - sequences replaced with a replacement marker. Therefore, out must not - be in the [start, end] range. -

-

- If end does not point to the past-of-end of a UTF-8 sequence, a - utf8::not_enough_room exception is thrown. -

-

- utf8::starts_with_bom -

-

- Available in version 2.3 and later. Relaces deprecated is_bom() function. -

-

- Checks whether an octet sequence starts with a UTF-8 byte order mark (BOM) -

-
-template <typename octet_iterator> 
-bool starts_with_bom (octet_iterator it, octet_iterator end);
-
-

- octet_iterator: an input iterator.
- it: beginning of the octet sequence to check
- end: pass-end of the sequence to check
- Return value: true if the sequence - starts with a UTF-8 byte order mark; false if not. -

-

- Example of use: -

-
-unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf};
-bool bbom = starts_with_bom(byte_order_mark, byte_order_mark + sizeof(byte_order_mark));
-assert (bbom == true);
-
-

- The typical use of this function is to check the first three bytes of a file. If - they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8 - encoded text. -

-

- utf8::is_bom -

-

- Available in version 1.0 and later. Deprecated in version 2.3. starts_with_bom() should be used - instead. -

-

- Checks whether a sequence of three octets is a UTF-8 byte order mark (BOM) -

-
-template <typename octet_iterator> 
-bool is_bom (octet_iterator it);  // Deprecated
-
-

- octet_iterator: an input iterator.
- it: beginning of the 3-octet sequence to check
- Return value: true if the sequence - is UTF-8 byte order mark; false if not. -

-

- Example of use: -

-
-unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf};
-bool bbom = is_bom(byte_order_mark);
-assert (bbom == true);
-
-

- The typical use of this function is to check the first three bytes of a file. If - they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8 - encoded text. -

-

- If a sequence is - shorter than three bytes, an invalid iterator will be dereferenced. Therefore, this function is deprecated - in favor of starts_with_bom()that takes the end of sequence as an argument. -

-

- Types From utf8 Namespace -

-

utf8::exception -

-

- Available in version 2.3 and later. -

-

- Base class for the exceptions thrown by UTF CPP library functions. -

-
-class exception : public std::exception {};
-
-

- Example of use: -

-
-try {
-  code_that_uses_utf_cpp_library();
-}
-catch(const utf8::exception& utfcpp_ex) {
-  cerr << utfcpp_ex.what();
-}
-
- -

utf8::invalid_code_point -

-

- Available in version 1.0 and later. -

-

- Thrown by UTF8 CPP functions such as advance and next if an UTF-8 sequence represents and invalid code point. -

- -
-class invalid_code_point : public exception {
-public: 
-    uint32_t code_point() const;
-};
-
-
-

- Member function code_point() can be used to determine the invalid code point that - caused the exception to be thrown. -

-

utf8::invalid_utf8 -

-

- Available in version 1.0 and later. -

-

- Thrown by UTF8 CPP functions such as next and prior if an invalid UTF-8 sequence - is detected during decoding. -

- -
-class invalid_utf8 : public exception {
-public: 
-    uint8_t utf8_octet() const;
-};
-
- -

- Member function utf8_octet() can be used to determine the beginning of the byte - sequence that caused the exception to be thrown. -

- -

utf8::invalid_utf16 -

-

- Available in version 1.0 and later. -

-

- Thrown by UTF8 CPP function utf16to8 if an invalid UTF-16 sequence - is detected during decoding. -

- -
-class invalid_utf16 : public exception {
-public: 
-    uint16_t utf16_word() const;
-};
-
- -

- Member function utf16_word() can be used to determine the UTF-16 code unit - that caused the exception to be thrown. -

-

utf8::not_enough_room -

-

- Available in version 1.0 and later. -

-

- Thrown by UTF8 CPP functions such as next if the end of the decoded UTF-8 sequence - was reached before the code point was decoded. -

- -
-class not_enough_room : public exception {};
-
-

- utf8::iterator -

-

- Available in version 2.0 and later. -

-

- Adapts the underlying octet iterator to iterate over the sequence of code points, - rather than raw octets. -

-
-template <typename octet_iterator>
-class iterator;
-
- -
Member functions
-
-
iterator();
the deafult constructor; the underlying octet_iterator is - constructed with its default constructor. -
explicit iterator (const octet_iterator& octet_it, - const octet_iterator& range_start, - const octet_iterator& range_end);
a constructor - that initializes the underlying octet_iterator with octet_it - and sets the range in which the iterator is considered valid. -
octet_iterator base () const;
returns the - underlying octet_iterator. -
uint32_t operator * () const;
decodes the utf-8 sequence - the underlying octet_iterator is pointing to and returns the code point. -
bool operator == (const iterator& rhs) - const;
returns true - if the two underlaying iterators are equal. -
bool operator != (const iterator& rhs) - const;
returns true - if the two underlaying iterators are not equal. -
iterator& operator ++ ();
the prefix increment - moves - the iterator to the next UTF-8 encoded code point. -
iterator operator ++ (int);
- the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one. -
iterator& operator -- ();
the prefix decrement - moves - the iterator to the previous UTF-8 encoded code point. -
iterator operator -- (int);
- the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one. -
-

- Example of use: -

-
-char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
-utf8::iterator<char*> it(threechars, threechars, threechars + 9);
-utf8::iterator<char*> it2 = it;
-assert (it2 == it);
-assert (*it == 0x10346);
-assert (*(++it) == 0x65e5);
-assert ((*it++) == 0x65e5);
-assert (*it == 0x0448);
-assert (it != it2);
-utf8::iterator<char*> endit (threechars + 9, threechars, threechars + 9);  
-assert (++it == endit);
-assert (*(--it) == 0x0448);
-assert ((*it--) == 0x0448);
-assert (*it == 0x65e5);
-assert (--it == utf8::iterator<char*>(threechars, threechars, threechars + 9));
-assert (*it == 0x10346);
-
-

- The purpose of utf8::iterator adapter is to enable easy iteration as well as the use of STL - algorithms with UTF-8 encoded strings. Increment and decrement operators are implemented in terms of - utf8::next() and utf8::prior() functions. -

-

- Note that utf8::iterator adapter is a checked iterator. It operates on the range specified in - the constructor; any attempt to go out of that range will result in an exception. Even the comparison operators - require both iterator object to be constructed against the same range - otherwise an exception is thrown. Typically, - the range will be determined by sequence container functions begin and end, i.e.: -

-
-std::string s = "example";
-utf8::iterator i (s.begin(), s.begin(), s.end());
-
-

- Functions From utf8::unchecked Namespace -

-

- utf8::unchecked::append -

-

- Available in version 1.0 and later. -

-

- Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence - to a UTF-8 string. -

-
-template <typename octet_iterator>
-octet_iterator append(uint32_t cp, octet_iterator result);
-   
-
-

- cp: A 32 bit integer representing a code point to append to the - sequence.
- result: An output iterator to the place in the sequence where to - append the code point.
- Return value: An iterator pointing to the place - after the newly appended sequence. -

-

- Example of use: -

-
-unsigned char u[5] = {0,0,0,0,0};
-unsigned char* end = unchecked::append(0x0448, u);
-assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0);
-
-

- This is a faster but less safe version of utf8::append. It does not - check for validity of the supplied code point, and may produce an invalid UTF-8 - sequence. -

-

- utf8::unchecked::next -

-

- Available in version 1.0 and later. -

-

- Given the iterator to the beginning of a UTF-8 sequence, it returns the code point - and moves the iterator to the next position. -

-
-template <typename octet_iterator>
-uint32_t next(octet_iterator& it);
-   
-
-

- it: a reference to an iterator pointing to the beginning of an UTF-8 - encoded code point. After the function returns, it is incremented to point to the - beginning of the next code point.
- Return value: the 32 bit representation of the - processed UTF-8 code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-char* w = twochars;
-int cp = unchecked::next(w);
-assert (cp == 0x65e5);
-assert (w == twochars + 3);
-
-

- This is a faster but less safe version of utf8::next. It does not - check for validity of the supplied UTF-8 sequence. -

-

- utf8::unchecked::peek_next -

-

- Available in version 2.1 and later. -

-

- Given the iterator to the beginning of a UTF-8 sequence, it returns the code point. -

-
-template <typename octet_iterator>
-uint32_t peek_next(octet_iterator it);
-   
-
-

- it: an iterator pointing to the beginning of an UTF-8 - encoded code point.
- Return value: the 32 bit representation of the - processed UTF-8 code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-char* w = twochars;
-int cp = unchecked::peek_next(w);
-assert (cp == 0x65e5);
-assert (w == twochars);
-
-

- This is a faster but less safe version of utf8::peek_next. It does not - check for validity of the supplied UTF-8 sequence. -

-

- utf8::unchecked::prior -

-

- Available in version 1.02 and later. -

-

- Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it - decreases the iterator until it hits the beginning of the previous UTF-8 encoded - code point and returns the 32 bits representation of the code point. -

-
-template <typename octet_iterator>
-uint32_t prior(octet_iterator& it);
-   
-
-

- it: a reference pointing to an octet within a UTF-8 encoded string. - After the function returns, it is decremented to point to the beginning of the - previous code point.
- Return value: the 32 bit representation of the - previous code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-char* w = twochars + 3;
-int cp = unchecked::prior (w);
-assert (cp == 0x65e5);
-assert (w == twochars);
-
-

- This is a faster but less safe version of utf8::prior. It does not - check for validity of the supplied UTF-8 sequence and offers no boundary checking. -

-

- utf8::unchecked::previous (deprecated, see utf8::unchecked::prior) -

-

- Deprecated in version 1.02 and later. -

-

- Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it - decreases the iterator until it hits the beginning of the previous UTF-8 encoded - code point and returns the 32 bits representation of the code point. -

-
-template <typename octet_iterator>
-uint32_t previous(octet_iterator& it);
-   
-
-

- it: a reference pointing to an octet within a UTF-8 encoded string. - After the function returns, it is decremented to point to the beginning of the - previous code point.
- Return value: the 32 bit representation of the - previous code point. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-char* w = twochars + 3;
-int cp = unchecked::previous (w);
-assert (cp == 0x65e5);
-assert (w == twochars);
-
-

- The reason this function is deprecated is just the consistency with the "checked" - versions, where prior should be used instead of previous. - In fact, unchecked::previous behaves exactly the same as - unchecked::prior -

-

- This is a faster but less safe version of utf8::previous. It does not - check for validity of the supplied UTF-8 sequence and offers no boundary checking. -

-

- utf8::unchecked::advance -

-

- Available in version 1.0 and later. -

-

- Advances an iterator by the specified number of code points within an UTF-8 - sequence. -

-
-template <typename octet_iterator, typename distance_type>
-void advance (octet_iterator& it, distance_type n);
-   
-
-

- it: a reference to an iterator pointing to the beginning of an UTF-8 - encoded code point. After the function returns, it is incremented to point to the - nth following code point.
- n: a positive integer that shows how many code points we want to - advance.
-

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-char* w = twochars;
-unchecked::advance (w, 2);
-assert (w == twochars + 5);
-
-

- This function works only "forward". In case of a negative n, there is - no effect. -

-

- This is a faster but less safe version of utf8::advance. It does not - check for validity of the supplied UTF-8 sequence and offers no boundary checking. -

-

- utf8::unchecked::distance -

-

- Available in version 1.0 and later. -

-

- Given the iterators to two UTF-8 encoded code points in a seqence, returns the - number of code points between them. -

-
-template <typename octet_iterator>
-typename std::iterator_traits<octet_iterator>::difference_type distance (octet_iterator first, octet_iterator last);
-
-

- first: an iterator to a beginning of a UTF-8 encoded code point.
- last: an iterator to a "post-end" of the last UTF-8 encoded code - point in the sequence we are trying to determine the length. It can be the - beginning of a new code point, or not.
- Return value the distance between the iterators, - in code points. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-size_t dist = utf8::unchecked::distance(twochars, twochars + 5);
-assert (dist == 2);
-
-

- This is a faster but less safe version of utf8::distance. It does not - check for validity of the supplied UTF-8 sequence. -

-

- utf8::unchecked::utf16to8 -

-

- Available in version 1.0 and later. -

-

- Converts a UTF-16 encoded string to UTF-8. -

-
-template <typename u16bit_iterator, typename octet_iterator>
-octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result);
-   
-
-

- start: an iterator pointing to the beginning of the UTF-16 encoded - string to convert.
- end: an iterator pointing to pass-the-end of the UTF-16 encoded - string to convert.
- result: an output iterator to the place in the UTF-8 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-8 string. -

-

- Example of use: -

-
-unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
-vector<unsigned char> utf8result;
-unchecked::utf16to8(utf16string, utf16string + 5, back_inserter(utf8result));
-assert (utf8result.size() == 10);    
-
-

- This is a faster but less safe version of utf8::utf16to8. It does not - check for validity of the supplied UTF-16 sequence. -

-

- utf8::unchecked::utf8to16 -

-

- Available in version 1.0 and later. -

-

- Converts an UTF-8 encoded string to UTF-16 -

-
-template <typename u16bit_iterator, typename octet_iterator>
-u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result);
-   
-
-

- start: an iterator pointing to the beginning of the UTF-8 encoded - string to convert. < br /> end: an iterator pointing to - pass-the-end of the UTF-8 encoded string to convert.
- result: an output iterator to the place in the UTF-16 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-16 string. -

-

- Example of use: -

-
-char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e";
-vector <unsigned short> utf16result;
-unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result));
-assert (utf16result.size() == 4);
-assert (utf16result[2] == 0xd834);
-assert (utf16result[3] == 0xdd1e);
-
-

- This is a faster but less safe version of utf8::utf8to16. It does not - check for validity of the supplied UTF-8 sequence. -

-

- utf8::unchecked::utf32to8 -

-

- Available in version 1.0 and later. -

-

- Converts a UTF-32 encoded string to UTF-8. -

-
-template <typename octet_iterator, typename u32bit_iterator>
-octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result);
-   
-
-

- start: an iterator pointing to the beginning of the UTF-32 encoded - string to convert.
- end: an iterator pointing to pass-the-end of the UTF-32 encoded - string to convert.
- result: an output iterator to the place in the UTF-8 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-8 string. -

-

- Example of use: -

-
-int utf32string[] = {0x448, 0x65e5, 0x10346, 0};
-vector<unsigned char> utf8result;
-utf32to8(utf32string, utf32string + 3, back_inserter(utf8result));
-assert (utf8result.size() == 9);
-
-

- This is a faster but less safe version of utf8::utf32to8. It does not - check for validity of the supplied UTF-32 sequence. -

-

- utf8::unchecked::utf8to32 -

-

- Available in version 1.0 and later. -

-

- Converts a UTF-8 encoded string to UTF-32. -

-
-template <typename octet_iterator, typename u32bit_iterator>
-u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result);
-   
-
-

- start: an iterator pointing to the beginning of the UTF-8 encoded - string to convert.
- end: an iterator pointing to pass-the-end of the UTF-8 encoded string - to convert.
- result: an output iterator to the place in the UTF-32 string where to - append the result of conversion.
- Return value: An iterator pointing to the place - after the appended UTF-32 string. -

-

- Example of use: -

-
-char* twochars = "\xe6\x97\xa5\xd1\x88";
-vector<int> utf32result;
-unchecked::utf8to32(twochars, twochars + 5, back_inserter(utf32result));
-assert (utf32result.size() == 2);
-
-

- This is a faster but less safe version of utf8::utf8to32. It does not - check for validity of the supplied UTF-8 sequence. -

-

- Types From utf8::unchecked Namespace -

-

- utf8::iterator -

-

- Available in version 2.0 and later. -

-

- Adapts the underlying octet iterator to iterate over the sequence of code points, - rather than raw octets. -

-
-template <typename octet_iterator>
-class iterator;
-
- -
Member functions
-
-
iterator();
the deafult constructor; the underlying octet_iterator is - constructed with its default constructor. -
explicit iterator (const octet_iterator& octet_it); -
a constructor - that initializes the underlying octet_iterator with octet_it -
octet_iterator base () const;
returns the - underlying octet_iterator. -
uint32_t operator * () const;
decodes the utf-8 sequence - the underlying octet_iterator is pointing to and returns the code point. -
bool operator == (const iterator& rhs) - const;
returns true - if the two underlaying iterators are equal. -
bool operator != (const iterator& rhs) - const;
returns true - if the two underlaying iterators are not equal. -
iterator& operator ++ ();
the prefix increment - moves - the iterator to the next UTF-8 encoded code point. -
iterator operator ++ (int);
- the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one. -
iterator& operator -- ();
the prefix decrement - moves - the iterator to the previous UTF-8 encoded code point. -
iterator operator -- (int);
- the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one. -
-

- Example of use: -

-
-char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88";
-utf8::unchecked::iterator<char*> un_it(threechars);
-utf8::unchecked::iterator<char*> un_it2 = un_it;
-assert (un_it2 == un_it);
-assert (*un_it == 0x10346);
-assert (*(++un_it) == 0x65e5);
-assert ((*un_it++) == 0x65e5);
-assert (*un_it == 0x0448);
-assert (un_it != un_it2);
-utf8::::unchecked::iterator<char*> un_endit (threechars + 9);  
-assert (++un_it == un_endit);
-assert (*(--un_it) == 0x0448);
-assert ((*un_it--) == 0x0448);
-assert (*un_it == 0x65e5);
-assert (--un_it == utf8::unchecked::iterator<char*>(threechars));
-assert (*un_it == 0x10346);
-
-

- This is an unchecked version of utf8::iterator. It is faster in many cases, but offers - no validity or range checks. -

-

- Points of interest -

-

- Design goals and decisions -

-

- The library was designed to be: -

-
    -
  1. - Generic: for better or worse, there are many C++ string classes out there, and - the library should work with as many of them as possible. -
    2. -
  2. - Portable: the library should be portable both accross different platforms and - compilers. The only non-portable code is a small section that declares unsigned - integers of different sizes: three typedefs. They can be changed by the users of - the library if they don't match their platform. The default setting should work - for Windows (both 32 and 64 bit), and most 32 bit and 64 bit Unix derivatives. -
    3. -
  3. - Lightweight: follow the "pay only for what you use" guidline. -
    4. -
  4. - Unintrusive: avoid forcing any particular design or even programming style on the - user. This is a library, not a framework. -
    5. -
-

- Alternatives -

-

- In case you want to look into other means of working with UTF-8 strings from C++, - here is the list of solutions I am aware of: -

-
    -
  1. - ICU Library. It is very powerful, - complete, feature-rich, mature, and widely used. Also big, intrusive, - non-generic, and doesn't play well with the Standard Library. I definitelly - recommend looking at ICU even if you don't plan to use it. -
    2. -
  2. - Glib::ustring. - A class specifically made to work with UTF-8 strings, and also feel like - std::string. If you prefer to have yet another string class in your - code, it may be worth a look. Be aware of the licensing issues, though. -
    3. -
  3. - Platform dependent solutions: Windows and POSIX have functions to convert strings - from one encoding to another. That is only a subset of what my library offers, - but if that is all you need it may be good enough, especially given the fact that - these functions are mature and tested in production. -
    4. -
-

- Conclusion -

-

- Until Unicode becomes officially recognized by the C++ Standard Library, we need to - use other means to work with UTF-8 strings. Template functions I describe in this - article may be a good step in this direction. -

- -
    -
  1. - The Unicode Consortium. -
    2. -
  2. - ICU Library. -
    3. -
  3. - UTF-8 at Wikipedia -
    4. -
  4. - UTF-8 and Unicode FAQ for - Unix/Linux -
    5. -
- - diff --git a/utf8/utf8.h b/utf8/utf8.h index 4e4451403..82b13f59f 100644 --- a/utf8/utf8.h +++ b/utf8/utf8.h @@ -1,34 +1,34 @@ -// Copyright 2006 Nemanja Trifunovic - -/* -Permission is hereby granted, free of charge, to any person or organization -obtaining a copy of the software and accompanying documentation covered by -this license (the "Software") to use, reproduce, display, distribute, -execute, and transmit the Software, and to prepare derivative works of the -Software, and to permit third-parties to whom the Software is furnished to -do so, all subject to the following: - -The copyright notices in the Software and this entire statement, including -the above license grant, this restriction and the following disclaimer, -must be included in all copies of the Software, in whole or in part, and -all derivative works of the Software, unless such copies or derivative -works are solely in the form of machine-executable object code generated by -a source language processor. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT -SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE -FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, -ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER -DEALINGS IN THE SOFTWARE. -*/ - - -#ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 -#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 - -#include "utf8/checked.h" -#include "utf8/unchecked.h" - -#endif // header guard +// Copyright 2006 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "utf8/checked.h" +#include "utf8/unchecked.h" + +#endif // header guard diff --git a/utf8/utf8/checked.h b/utf8/utf8/checked.h index 9cb8d2c7f..2aef5838d 100644 --- a/utf8/utf8/checked.h +++ b/utf8/utf8/checked.h @@ -1,4 +1,4 @@ -// Copyright 2006 Nemanja Trifunovic +// Copyright 2006-2016 Nemanja Trifunovic /* Permission is hereby granted, free of charge, to any person or organization @@ -34,14 +34,14 @@ DEALINGS IN THE SOFTWARE. namespace utf8 { // Base for the exceptions that may be thrown from the library - class exception : public std::exception { + class exception : public ::std::exception { }; // Exceptions that may be thrown from the library functions. class invalid_code_point : public exception { uint32_t cp; public: - invalid_code_point(uint32_t cp) : cp(cp) {} + invalid_code_point(uint32_t codepoint) : cp(codepoint) {} virtual const char* what() const throw() { return "Invalid code point"; } uint32_t code_point() const {return cp;} }; @@ -69,48 +69,10 @@ namespace utf8 /// The library API - functions intended to be called by the users - template - output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement) - { - while (start != end) { - octet_iterator sequence_start = start; - internal::utf_error err_code = internal::validate_next(start, end); - switch (err_code) { - case internal::UTF8_OK : - for (octet_iterator it = sequence_start; it != start; ++it) - *out++ = *it; - break; - case internal::NOT_ENOUGH_ROOM: - throw not_enough_room(); - case internal::INVALID_LEAD: - append (replacement, out); - ++start; - break; - case internal::INCOMPLETE_SEQUENCE: - case internal::OVERLONG_SEQUENCE: - case internal::INVALID_CODE_POINT: - append (replacement, out); - ++start; - // just one replacement mark for the sequence - while (internal::is_trail(*start) && start != end) - ++start; - break; - } - } - return out; - } - - template - inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out) - { - static const uint32_t replacement_marker = internal::mask16(0xfffd); - return replace_invalid(start, end, out, replacement_marker); - } - template octet_iterator append(uint32_t cp, octet_iterator result) { - if (!internal::is_code_point_valid(cp)) + if (!utf8::internal::is_code_point_valid(cp)) throw invalid_code_point(cp); if (cp < 0x80) // one octet @@ -124,7 +86,7 @@ namespace utf8 *(result++) = static_cast(((cp >> 6) & 0x3f) | 0x80); *(result++) = static_cast((cp & 0x3f) | 0x80); } - else { // four octets + else { // four octets *(result++) = static_cast((cp >> 18) | 0xf0); *(result++) = static_cast(((cp >> 12) & 0x3f) | 0x80); *(result++) = static_cast(((cp >> 6) & 0x3f) | 0x80); @@ -133,11 +95,49 @@ namespace utf8 return result; } + template + output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement) + { + while (start != end) { + octet_iterator sequence_start = start; + internal::utf_error err_code = utf8::internal::validate_next(start, end); + switch (err_code) { + case internal::UTF8_OK : + for (octet_iterator it = sequence_start; it != start; ++it) + *out++ = *it; + break; + case internal::NOT_ENOUGH_ROOM: + throw not_enough_room(); + case internal::INVALID_LEAD: + out = utf8::append (replacement, out); + ++start; + break; + case internal::INCOMPLETE_SEQUENCE: + case internal::OVERLONG_SEQUENCE: + case internal::INVALID_CODE_POINT: + out = utf8::append (replacement, out); + ++start; + // just one replacement mark for the sequence + while (start != end && utf8::internal::is_trail(*start)) + ++start; + break; + } + } + return out; + } + + template + inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out) + { + static const uint32_t replacement_marker = utf8::internal::mask16(0xfffd); + return utf8::replace_invalid(start, end, out, replacement_marker); + } + template uint32_t next(octet_iterator& it, octet_iterator end) { uint32_t cp = 0; - internal::utf_error err_code = internal::validate_next(it, end, &cp); + internal::utf_error err_code = utf8::internal::validate_next(it, end, cp); switch (err_code) { case internal::UTF8_OK : break; @@ -156,22 +156,22 @@ namespace utf8 template uint32_t peek_next(octet_iterator it, octet_iterator end) { - return next(it, end); + return utf8::next(it, end); } template uint32_t prior(octet_iterator& it, octet_iterator start) - { + { // can't do much if it == start - if (it == start) + if (it == start) throw not_enough_room(); - octet_iterator end = it; + octet_iterator end = it; // Go back until we hit either a lead octet or start - while (internal::is_trail(*(--it))) + while (utf8::internal::is_trail(*(--it))) if (it == start) throw invalid_utf8(*it); // error - no lead byte in the sequence - return peek_next(it, end); + return utf8::peek_next(it, end); } /// Deprecated in versions that include "prior" @@ -179,18 +179,18 @@ namespace utf8 uint32_t previous(octet_iterator& it, octet_iterator pass_start) { octet_iterator end = it; - while (internal::is_trail(*(--it))) + while (utf8::internal::is_trail(*(--it))) if (it == pass_start) throw invalid_utf8(*it); // error - no lead byte in the sequence octet_iterator temp = it; - return next(temp, end); + return utf8::next(temp, end); } template void advance (octet_iterator& it, distance_type n, octet_iterator end) { for (distance_type i = 0; i < n; ++i) - next(it, end); + utf8::next(it, end); } template @@ -199,7 +199,7 @@ namespace utf8 { typename std::iterator_traits::difference_type dist; for (dist = 0; first < last; ++dist) - next(first, last); + utf8::next(first, last); return dist; } @@ -207,12 +207,12 @@ namespace utf8 octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result) { while (start != end) { - uint32_t cp = internal::mask16(*start++); + uint32_t cp = utf8::internal::mask16(*start++); // Take care of surrogate pairs first - if (internal::is_lead_surrogate(cp)) { + if (utf8::internal::is_lead_surrogate(cp)) { if (start != end) { - uint32_t trail_surrogate = internal::mask16(*start++); - if (internal::is_trail_surrogate(trail_surrogate)) + uint32_t trail_surrogate = utf8::internal::mask16(*start++); + if (utf8::internal::is_trail_surrogate(trail_surrogate)) cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; else throw invalid_utf16(static_cast(trail_surrogate)); @@ -222,10 +222,10 @@ namespace utf8 } // Lone trail surrogate - else if (internal::is_trail_surrogate(cp)) + else if (utf8::internal::is_trail_surrogate(cp)) throw invalid_utf16(static_cast(cp)); - result = append(cp, result); + result = utf8::append(cp, result); } return result; } @@ -233,8 +233,8 @@ namespace utf8 template u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) { - while (start != end) { - uint32_t cp = next(start, end); + while (start < end) { + uint32_t cp = utf8::next(start, end); if (cp > 0xffff) { //make a surrogate pair *result++ = static_cast((cp >> 10) + internal::LEAD_OFFSET); *result++ = static_cast((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); @@ -249,7 +249,7 @@ namespace utf8 octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) { while (start != end) - result = append(*(start++), result); + result = utf8::append(*(start++), result); return result; } @@ -257,8 +257,8 @@ namespace utf8 template u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) { - while (start != end) - (*result++) = next(start, end); + while (start < end) + (*result++) = utf8::next(start, end); return result; } @@ -270,11 +270,11 @@ namespace utf8 octet_iterator range_start; octet_iterator range_end; public: - iterator () {}; + iterator () {} explicit iterator (const octet_iterator& octet_it, - const octet_iterator& range_start, - const octet_iterator& range_end) : - it(octet_it), range_start(range_start), range_end(range_end) + const octet_iterator& rangestart, + const octet_iterator& rangeend) : + it(octet_it), range_start(rangestart), range_end(rangeend) { if (it < range_start || it > range_end) throw std::out_of_range("Invalid utf-8 iterator position"); @@ -284,7 +284,7 @@ namespace utf8 uint32_t operator * () const { octet_iterator temp = it; - return next(temp, range_end); + return utf8::next(temp, range_end); } bool operator == (const iterator& rhs) const { @@ -298,24 +298,24 @@ namespace utf8 } iterator& operator ++ () { - next(it, range_end); + utf8::next(it, range_end); return *this; } iterator operator ++ (int) { iterator temp = *this; - next(it, range_end); + utf8::next(it, range_end); return temp; } iterator& operator -- () { - prior(it, range_start); + utf8::prior(it, range_start); return *this; } iterator operator -- (int) { iterator temp = *this; - prior(it, range_start); + utf8::prior(it, range_start); return temp; } }; // class iterator diff --git a/utf8/utf8/core.h b/utf8/utf8/core.h index 336973171..ae0f367db 100644 --- a/utf8/utf8/core.h +++ b/utf8/utf8/core.h @@ -68,7 +68,7 @@ namespace internal template inline bool is_trail(octet_type oc) { - return ((mask8(oc) >> 6) == 0x2); + return ((utf8::internal::mask8(oc) >> 6) == 0x2); } template @@ -92,14 +92,14 @@ namespace internal template inline bool is_code_point_valid(u32 cp) { - return (cp <= CODE_POINT_MAX && !is_surrogate(cp)); + return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp)); } template inline typename std::iterator_traits::difference_type sequence_length(octet_iterator lead_it) { - uint8_t lead = mask8(*lead_it); + uint8_t lead = utf8::internal::mask8(*lead_it); if (lead < 0x80) return 1; else if ((lead >> 5) == 0x6) @@ -116,15 +116,15 @@ namespace internal inline bool is_overlong_sequence(uint32_t cp, octet_difference_type length) { if (cp < 0x80) { - if (length != 1) + if (length != 1) return true; } else if (cp < 0x800) { - if (length != 2) + if (length != 2) return true; } else if (cp < 0x10000) { - if (length != 3) + if (length != 3) return true; } @@ -133,124 +133,98 @@ namespace internal enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT}; + /// Helper for get_sequence_x + template + utf_error increase_safely(octet_iterator& it, octet_iterator end) + { + if (++it == end) + return NOT_ENOUGH_ROOM; + + if (!utf8::internal::is_trail(*it)) + return INCOMPLETE_SEQUENCE; + + return UTF8_OK; + } + + #define UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(IT, END) {utf_error ret = increase_safely(IT, END); if (ret != UTF8_OK) return ret;} + /// get_sequence_x functions decode utf-8 sequences of the length x - template - utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t* code_point) + utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t& code_point) { - if (it != end) { - if (code_point) - *code_point = mask8(*it); - return UTF8_OK; - } - return NOT_ENOUGH_ROOM; + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + return UTF8_OK; } template - utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t* code_point) + utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t& code_point) { - utf_error ret_code = NOT_ENOUGH_ROOM; + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); - if (it != end) { - uint32_t cp = mask8(*it); - if (++it != end) { - if (is_trail(*it)) { - cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f); + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) - if (code_point) - *code_point = cp; - ret_code = UTF8_OK; - } - else - ret_code = INCOMPLETE_SEQUENCE; - } - else - ret_code = NOT_ENOUGH_ROOM; - } + code_point = ((code_point << 6) & 0x7ff) + ((*it) & 0x3f); - return ret_code; + return UTF8_OK; } template - utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t* code_point) + utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t& code_point) { - utf_error ret_code = NOT_ENOUGH_ROOM; + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); - if (it != end) { - uint32_t cp = mask8(*it); - if (++it != end) { - if (is_trail(*it)) { - cp = ((cp << 12) & 0xffff) + ((mask8(*it) << 6) & 0xfff); - if (++it != end) { - if (is_trail(*it)) { - cp += (*it) & 0x3f; + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) - if (code_point) - *code_point = cp; - ret_code = UTF8_OK; - } - else - ret_code = INCOMPLETE_SEQUENCE; - } - else - ret_code = NOT_ENOUGH_ROOM; - } - else - ret_code = INCOMPLETE_SEQUENCE; - } - else - ret_code = NOT_ENOUGH_ROOM; - } + code_point = ((code_point << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff); - return ret_code; + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (*it) & 0x3f; + + return UTF8_OK; } template - utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t* code_point) + utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t& code_point) { - utf_error ret_code = NOT_ENOUGH_ROOM; + if (it == end) + return NOT_ENOUGH_ROOM; - if (it != end) { - uint32_t cp = mask8(*it); - if (++it != end) { - if (is_trail(*it)) { - cp = ((cp << 18) & 0x1fffff) + ((mask8(*it) << 12) & 0x3ffff); - if (++it != end) { - if (is_trail(*it)) { - cp += (mask8(*it) << 6) & 0xfff; - if (++it != end) { - if (is_trail(*it)) { - cp += (*it) & 0x3f; + code_point = utf8::internal::mask8(*it); - if (code_point) - *code_point = cp; - ret_code = UTF8_OK; - } - else - ret_code = INCOMPLETE_SEQUENCE; - } - else - ret_code = NOT_ENOUGH_ROOM; - } - else - ret_code = INCOMPLETE_SEQUENCE; - } - else - ret_code = NOT_ENOUGH_ROOM; - } - else - ret_code = INCOMPLETE_SEQUENCE; - } - else - ret_code = NOT_ENOUGH_ROOM; - } + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) - return ret_code; + code_point = ((code_point << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (utf8::internal::mask8(*it) << 6) & 0xfff; + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (*it) & 0x3f; + + return UTF8_OK; } + #undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR + template - utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t* code_point) + utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t& code_point) { + if (it == end) + return NOT_ENOUGH_ROOM; + // Save the original value of it so we can go back in case of failure // Of course, it does not make much sense with i.e. stream iterators octet_iterator original_it = it; @@ -258,41 +232,40 @@ namespace internal uint32_t cp = 0; // Determine the sequence length based on the lead octet typedef typename std::iterator_traits::difference_type octet_difference_type; - octet_difference_type length = sequence_length(it); - if (length == 0) - return INVALID_LEAD; + const octet_difference_type length = utf8::internal::sequence_length(it); - // Now that we have a valid sequence length, get trail octets and calculate the code point + // Get trail octets and calculate the code point utf_error err = UTF8_OK; switch (length) { + case 0: + return INVALID_LEAD; case 1: - err = get_sequence_1(it, end, &cp); + err = utf8::internal::get_sequence_1(it, end, cp); break; case 2: - err = get_sequence_2(it, end, &cp); + err = utf8::internal::get_sequence_2(it, end, cp); break; case 3: - err = get_sequence_3(it, end, &cp); + err = utf8::internal::get_sequence_3(it, end, cp); break; case 4: - err = get_sequence_4(it, end, &cp); + err = utf8::internal::get_sequence_4(it, end, cp); break; } if (err == UTF8_OK) { // Decoding succeeded. Now, security checks... - if (is_code_point_valid(cp)) { - if (!is_overlong_sequence(cp, length)){ + if (utf8::internal::is_code_point_valid(cp)) { + if (!utf8::internal::is_overlong_sequence(cp, length)){ // Passed! Return here. - if (code_point) - *code_point = cp; + code_point = cp; ++it; return UTF8_OK; } else err = OVERLONG_SEQUENCE; } - else + else err = INVALID_CODE_POINT; } @@ -303,7 +276,8 @@ namespace internal template inline utf_error validate_next(octet_iterator& it, octet_iterator end) { - return validate_next(it, end, nullptr); + uint32_t ignored; + return utf8::internal::validate_next(it, end, ignored); } } // namespace internal @@ -318,7 +292,7 @@ namespace internal { octet_iterator result = start; while (result != end) { - internal::utf_error err_code = internal::validate_next(result, end); + utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end); if (err_code != internal::UTF8_OK) return result; } @@ -328,29 +302,31 @@ namespace internal template inline bool is_valid(octet_iterator start, octet_iterator end) { - return (find_invalid(start, end) == end); + return (utf8::find_invalid(start, end) == end); } template inline bool starts_with_bom (octet_iterator it, octet_iterator end) { return ( - ((it != end) && (internal::mask8(*it++)) == bom[0]) && - ((it != end) && (internal::mask8(*it++)) == bom[1]) && - ((it != end) && (internal::mask8(*it)) == bom[2]) + ((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) && + ((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) && + ((it != end) && (utf8::internal::mask8(*it)) == bom[2]) ); } - - //Deprecated in release 2.3 + + //Deprecated in release 2.3 template inline bool is_bom (octet_iterator it) { return ( - (internal::mask8(*it++)) == bom[0] && - (internal::mask8(*it++)) == bom[1] && - (internal::mask8(*it)) == bom[2] + (utf8::internal::mask8(*it++)) == bom[0] && + (utf8::internal::mask8(*it++)) == bom[1] && + (utf8::internal::mask8(*it)) == bom[2] ); } } // namespace utf8 #endif // header guard + + diff --git a/utf8/utf8/unchecked.h b/utf8/utf8/unchecked.h index 2f3eb4d1d..cb2427166 100644 --- a/utf8/utf8/unchecked.h +++ b/utf8/utf8/unchecked.h @@ -60,7 +60,7 @@ namespace utf8 template uint32_t next(octet_iterator& it) { - uint32_t cp = internal::mask8(*it); + uint32_t cp = utf8::internal::mask8(*it); typename std::iterator_traits::difference_type length = utf8::internal::sequence_length(it); switch (length) { case 1: @@ -71,15 +71,15 @@ namespace utf8 break; case 3: ++it; - cp = ((cp << 12) & 0xffff) + ((internal::mask8(*it) << 6) & 0xfff); + cp = ((cp << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff); ++it; cp += (*it) & 0x3f; break; case 4: ++it; - cp = ((cp << 18) & 0x1fffff) + ((internal::mask8(*it) << 12) & 0x3ffff); + cp = ((cp << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff); ++it; - cp += (internal::mask8(*it) << 6) & 0xfff; + cp += (utf8::internal::mask8(*it) << 6) & 0xfff; ++it; cp += (*it) & 0x3f; break; @@ -91,29 +91,29 @@ namespace utf8 template uint32_t peek_next(octet_iterator it) { - return next(it); + return utf8::unchecked::next(it); } template uint32_t prior(octet_iterator& it) { - while (internal::is_trail(*(--it))) ; + while (utf8::internal::is_trail(*(--it))) ; octet_iterator temp = it; - return next(temp); + return utf8::unchecked::next(temp); } // Deprecated in versions that include prior, but only for the sake of consistency (see utf8::previous) template inline uint32_t previous(octet_iterator& it) { - return prior(it); + return utf8::unchecked::prior(it); } template void advance (octet_iterator& it, distance_type n) { for (distance_type i = 0; i < n; ++i) - next(it); + utf8::unchecked::next(it); } template @@ -122,7 +122,7 @@ namespace utf8 { typename std::iterator_traits::difference_type dist; for (dist = 0; first < last; ++dist) - next(first); + utf8::unchecked::next(first); return dist; } @@ -130,13 +130,13 @@ namespace utf8 octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result) { while (start != end) { - uint32_t cp = internal::mask16(*start++); + uint32_t cp = utf8::internal::mask16(*start++); // Take care of surrogate pairs first - if (internal::is_lead_surrogate(cp)) { - uint32_t trail_surrogate = internal::mask16(*start++); + if (utf8::internal::is_lead_surrogate(cp)) { + uint32_t trail_surrogate = utf8::internal::mask16(*start++); cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; } - result = append(cp, result); + result = utf8::unchecked::append(cp, result); } return result; } @@ -145,7 +145,7 @@ namespace utf8 u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) { while (start < end) { - uint32_t cp = next(start); + uint32_t cp = utf8::unchecked::next(start); if (cp > 0xffff) { //make a surrogate pair *result++ = static_cast((cp >> 10) + internal::LEAD_OFFSET); *result++ = static_cast((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); @@ -160,7 +160,7 @@ namespace utf8 octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) { while (start != end) - result = append(*(start++), result); + result = utf8::unchecked::append(*(start++), result); return result; } @@ -169,7 +169,7 @@ namespace utf8 u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) { while (start < end) - (*result++) = next(start); + (*result++) = utf8::unchecked::next(start); return result; } @@ -179,14 +179,14 @@ namespace utf8 class iterator : public std::iterator { octet_iterator it; public: - iterator () {}; + iterator () {} explicit iterator (const octet_iterator& octet_it): it(octet_it) {} // the default "big three" are OK octet_iterator base () const { return it; } uint32_t operator * () const { octet_iterator temp = it; - return next(temp); + return utf8::unchecked::next(temp); } bool operator == (const iterator& rhs) const { @@ -198,24 +198,24 @@ namespace utf8 } iterator& operator ++ () { - std::advance(it, internal::sequence_length(it)); + ::std::advance(it, utf8::internal::sequence_length(it)); return *this; } iterator operator ++ (int) { iterator temp = *this; - std::advance(it, internal::sequence_length(it)); + ::std::advance(it, utf8::internal::sequence_length(it)); return temp; } iterator& operator -- () { - prior(it); + utf8::unchecked::prior(it); return *this; } iterator operator -- (int) { iterator temp = *this; - prior(it); + utf8::unchecked::prior(it); return temp; } }; // class iterator