diff --git a/include/boost/algorithm/string_ref.hpp b/include/boost/algorithm/string_ref.hpp new file mode 100644 index 0000000..5847cb8 --- /dev/null +++ b/include/boost/algorithm/string_ref.hpp @@ -0,0 +1,397 @@ +/* + Copyright (c) Marshall Clow 2012-2012. + + Distributed under the Boost Software License, Version 1.0. (See accompanying + file LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt) + + For more information, see http://www.boost.org + + Based on the StringRef implementation in LLVM (http://llvm.org) and + N3422 by Jeffrey Yasskin + http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2012/n3442.html + +*/ + +#ifndef BOOST_STRING_REF_HPP +#define BOOST_STRING_REF_HPP + +#include + +#include +#include +#include +#include +#ifndef BOOST_NO_CXX11_HDR_INITIALIZER_LIST +#include +#endif + +namespace boost { + + namespace detail { + // A helper functor for when we don't have lambdas + template + class string_ref_traits_eq { + public: + string_ref_traits_eq ( charT ch ) : ch_(ch) {} + bool operator () ( charT val ) const { return traits::eq ( ch_, val ); } + charT ch_; + }; + } + + template class basic_string_ref; + typedef basic_string_ref > string_ref; + typedef basic_string_ref > wstring_ref; + +#ifndef BOOST_NO_CXX11_CHAR16_T + typedef basic_string_ref > u16string_ref; +#endif + +#ifndef BOOST_NO_CXX11_CHAR32_T + typedef basic_string_ref > u32string_ref; +#endif + + template + class basic_string_ref { + public: + // types + typedef charT value_type; + typedef const charT* pointer; + typedef const charT& reference; + typedef const charT& const_reference; + typedef pointer const_iterator; // impl-defined + typedef const_iterator iterator; + typedef std::reverse_iterator const_reverse_iterator; + typedef const_reverse_iterator reverse_iterator; + typedef size_t size_type; + typedef ptrdiff_t difference_type; + static BOOST_CONSTEXPR_OR_CONST size_type npos = size_type(-1); + + // construct/copy + BOOST_CONSTEXPR basic_string_ref () +#ifdef BOOST_NO_CXX11_NULLPTR + : ptr_(NULL), len_(0) {} +#else + : ptr_(nullptr), len_(0) {} +#endif + BOOST_CONSTEXPR basic_string_ref (const basic_string_ref &rhs) + : ptr_(rhs.ptr_), len_(rhs.len_) {} + + basic_string_ref& operator=(const basic_string_ref &rhs) { + ptr_ = rhs.ptr_; + len_ = rhs.len_; + return *this; + } + + basic_string_ref(const charT* str) + : ptr_(str), len_(std::strlen(str)) {} + + template + basic_string_ref(const std::basic_string& str) + : ptr_(str.data()), len_(str.length()) {} + + BOOST_CONSTEXPR basic_string_ref(const charT* str, size_type len) + : ptr_(str), len_(len) {} + +#ifndef BOOST_NO_CXX11_HDR_INITIALIZER_LIST +// !! How do I do this? Look how initializer_lists work! + basic_string_ref(std::initializer_list il); // TODO +#endif + +#ifndef BOOST_NO_CXX11_EXPLICIT_CONVERSION_OPERATORS + template + explicit operator std::basic_string() const { + return std::basic_string ( ptr_, len_ ); + } +#endif + + // iterators + BOOST_CONSTEXPR const_iterator begin() const { return ptr_; } + BOOST_CONSTEXPR const_iterator cbegin() const { return ptr_; } + BOOST_CONSTEXPR const_iterator end() const { return ptr_ + len_; } + BOOST_CONSTEXPR const_iterator cend() const { return ptr_ + len_; } + const_reverse_iterator rbegin() const { return const_reverse_iterator (end()); } + const_reverse_iterator crbegin() const { return const_reverse_iterator (end()); } + const_reverse_iterator rend() const { return const_reverse_iterator (begin()); } + const_reverse_iterator crend() const { return const_reverse_iterator (begin()); } + + // capacity + BOOST_CONSTEXPR size_type size() const { return len_; } + BOOST_CONSTEXPR size_type length() const { return len_; } + BOOST_CONSTEXPR size_type max_size() const { return len_; } + BOOST_CONSTEXPR bool empty() const { return len_ == 0; } + + // element access + BOOST_CONSTEXPR const charT& operator[](size_type pos) const { return ptr_[pos]; } + + const charT& at(size_t pos) const { + if ( pos >= len_ ) + throw std::out_of_range ( "boost::string_ref::at" ); + return ptr_[pos]; + } + + BOOST_CONSTEXPR const charT& front() const { return ptr_[0]; } + BOOST_CONSTEXPR const charT& back() const { return ptr_[len_-1]; } + BOOST_CONSTEXPR const charT* data() const { return ptr_; } + + // modifiers + void clear() { len_ = 0; } + void remove_prefix(size_type n) { + if ( n > len_ ) + n = len_; + ptr_ += n; + len_ -= n; + } + + void remove_suffix(size_type n) { + if ( n > len_ ) + n = len_; + len_ -= n; + } + + + // basic_string_ref string operations + BOOST_CONSTEXPR + basic_string_ref substr(size_type pos, size_type n=npos) const { +// if ( pos > size()) throw std::out_of_range ( "string_ref::substr" ); +// if ( n == npos || pos + n > size()) n = size () - pos; +// return basic_string_ref ( data() + pos, n ); + return pos > size() ? throw std::out_of_range ( "string_ref::substr" ) : + basic_string_ref ( data() + pos, n == npos || pos + n > size() ? size() - pos : n ); + } + + int compare(basic_string_ref x) const { + int cmp = std::memcmp ( ptr_, x.ptr_, std::min(len_, x.len_)); + return cmp != 0 ? cmp : ( len_ == x.len_ ? 0 : len_ < x.len_ ? -1 : 1 ); + } + + bool starts_with(charT c) const { return !empty() && front() == c; } + bool starts_with(basic_string_ref x) const { + return len_ >= x.len_ && std::memcmp ( ptr_, x.ptr_, x.len_ ) == 0; + } + + bool ends_with(charT c) const { return !empty() && back() == c; } + bool ends_with(basic_string_ref x) const { + return len_ >= x.len_ && std::memcmp ( ptr_ + len_ - x.len_, x.ptr_, x.len_ ) == 0; + } + + +// Have to use traits here + size_type find(basic_string_ref s) const { + const_iterator iter = std::find_if ( this->cbegin (), this->cend (), + s.cbegin (), s.cend (), traits::eq ); + return iter = this->cend () ? npos : std::distance ( this->cbegin (), iter ); + } + + size_type find(charT c) const { +#ifdef BOOST_NO_CXX11_LAMBDAS + const_iterator iter = std::find_if ( this->cbegin (), this->cend (), + detail::string_ref_traits_eq ( c )); +#else + const_iterator iter = std::find_if ( this->cbegin (), this->cend (), + [c] ( charT val ) { return traits::eq ( c, val ); } ); +#endif + return iter == this->cend () ? npos : std::distance ( this->cbegin (), iter ); + } + + size_type rfind(basic_string_ref s) const { + const_iterator iter = std::find_if ( this->crbegin (), this->crend (), + s.crbegin (), s.crend (), traits::eq ); + return iter == this->crend () ? npos : reverse_distance ( this->crbegin (), iter ); + } + + size_type rfind(charT c) const { +#ifdef BOOST_NO_CXX11_LAMBDAS + const_reverse_iterator iter = std::find_if ( this->crbegin (), this->crend (), + detail::string_ref_traits_eq ( c )); +#else + const_reverse_iterator iter = std::find_if ( this->crbegin (), this->crend (), + [c] ( charT val ) { return traits::eq ( c, val ); } ); +#endif + return iter == this->crend () ? npos : reverse_distance ( this->crbegin (), iter ); + } + + size_type find_first_of(basic_string_ref s) const { + const_iterator iter = std::find_first_of ( this->cbegin (), this->cend (), + s.cbegin (), s.cend (), traits::eq ); + return iter = this->cend () ? npos : std::distance ( this->cbegin (), iter ); + } + + size_type find_first_of(charT c) const { return find (c); } + size_type find_last_of (charT c) const { return rfind (c); } + + + size_type find_last_of(basic_string_ref s) const { + const_reverse_iterator iter = std::find_first_of ( this->crbegin (), this->crend (), + s.crbegin (), s.crend (), traits::eq ); + return iter = this->cend () ? npos : reverse_distance ( this->crbegin (), iter); + } + + size_type find_first_not_of(basic_string_ref s) const { + for ( const_reverse_iterator iter = this->cbegin (); iter != this->cend (); ++iter ) + if ( 0 == traits::find ( s->ptr_, s.len_, *iter )) + return std::distance ( this->cbegin (), iter ); + return npos; + } + + size_type find_first_not_of(charT c) const { + for ( const_iterator iter = this->cbegin (); iter != this->cend (); ++iter ) + if ( !traits::eq ( c, *iter )) + return std::distance ( this->cbegin (), iter ); + return npos; + } + + size_type find_last_not_of(basic_string_ref s) const { + for ( const_reverse_iterator iter = this->crbegin (); iter != this->crend (); ++iter ) + if ( 0 == traits::find ( s.ptr_, s.len_, *iter )) + return reverse_distance ( this->crbegin (), iter ); + return npos; + } + + size_type find_last_not_of(charT c) const { + for ( const_reverse_iterator iter = this->crbegin (); iter != this->crend (); ++iter ) + if ( !traits::eq ( c, *iter )) + return reverse_distance ( this->crbegin (), iter ); + return npos; + } + + private: + size_type reverse_distance ( reverse_iterator first, reverse_iterator last ) const { + return len_ - 1 + std::distance ( first, last ); + } + + const charT *ptr_; + std::size_t len_; + }; + + // Comparison operators + template + bool operator==(basic_string_ref x, basic_string_ref y) { + if ( x.size () != y.size ()) return false; + return x.compare(y) == 0; + } + + template + bool operator!=(basic_string_ref x, basic_string_ref y) { + if ( x.size () != y.size ()) return true; + return x.compare(y) != 0; + } + + template + bool operator<(basic_string_ref x, basic_string_ref y) { + return x.compare(y) < 0; + } + + template + bool operator>(basic_string_ref x, basic_string_ref y) { + return x.compare(y) > 0; + } + + template + bool operator<=(basic_string_ref x, basic_string_ref y) { + return x.compare(y) <= 0; + } + + template + bool operator>=(basic_string_ref x, basic_string_ref y) { + return x.compare(y) >= 0; + } + + + // Inserter + template + std::basic_ostream& + operator<<(std::basic_ostream& os, const basic_string_ref& str) { +#ifdef BOOST_NO_CXX11_RANGE_BASED_FOR + for ( typename basic_string_ref::const_iterator iter = str.begin (); iter != str.end (); ++iter ) + os << *iter; +#else + for ( charT x : str ) + os << x; +#endif + return os; + } + +#if 0 + // numeric conversions + // + // These are short-term implementations. + // In a production environment, I would rather avoid the copying. + // + int stoi (string_ref str, size_t* idx=0, int base=10) { + return std::stoi ( std::string(str), idx, base ); + } + + long stol (string_ref str, size_t* idx=0, int base=10) { + return std::stol ( std::string(str), idx, base ); + } + + unsigned long stoul (string_ref str, size_t* idx=0, int base=10) { + return std::stoul ( std::string(str), idx, base ); + } + + long long stoll (string_ref str, size_t* idx=0, int base=10) { + return std::stoll ( std::string(str), idx, base ); + } + + unsigned long long stoull (string_ref str, size_t* idx=0, int base=10) { + return std::stoull ( std::string(str), idx, base ); + } + + float stof (string_ref str, size_t* idx=0) { + return std::stof ( std::string(str), idx ); + } + + double stod (string_ref str, size_t* idx=0) { + return std::stod ( std::string(str), idx ); + } + + long double stold (string_ref str, size_t* idx=0) { + return std::stold ( std::string(str), idx ); + } + + int stoi (wstring_ref str, size_t* idx=0, int base=10) { + return std::stoi ( std::wstring(str), idx, base ); + } + + long stol (wstring_ref str, size_t* idx=0, int base=10) { + return std::stol ( std::wstring(str), idx, base ); + } + + unsigned long stoul (wstring_ref str, size_t* idx=0, int base=10) { + return std::stoul ( std::wstring(str), idx, base ); + } + + long long stoll (wstring_ref str, size_t* idx=0, int base=10) { + return std::stoll ( std::wstring(str), idx, base ); + } + + unsigned long long stoull (wstring_ref str, size_t* idx=0, int base=10) { + return std::stoull ( std::wstring(str), idx, base ); + } + + float stof (wstring_ref str, size_t* idx=0) { + return std::stof ( std::wstring(str), idx ); + } + + double stod (wstring_ref str, size_t* idx=0) { + return std::stod ( std::wstring(str), idx ); + } + + long double stold (wstring_ref str, size_t* idx=0) { + return std::stold ( std::wstring(str), idx ); + } +#endif + +} + +#if 0 +namespace std { + // Hashing + template<> struct hash; + template<> struct hash; + template<> struct hash; + template<> struct hash; +} +#endif + +#endif \ No newline at end of file diff --git a/test/Jamfile.v2 b/test/Jamfile.v2 index 1d13cec..e60610f 100755 --- a/test/Jamfile.v2 +++ b/test/Jamfile.v2 @@ -48,6 +48,10 @@ import testing ; [ run hex_test4.cpp : : : : hex_test4 ] [ compile-fail hex_fail1.cpp ] +# StringRef tests + [ run string_ref_test1.cpp : : : : string_ref_test1 ] + [ run string_ref_test2.cpp : : : : string_ref_test2 ] + # Wrapper tests [ run wrapper_test1.cpp : : : : wrapper_test1 ] ; diff --git a/test/string_ref_test1.cpp b/test/string_ref_test1.cpp new file mode 100644 index 0000000..0d3abf5 --- /dev/null +++ b/test/string_ref_test1.cpp @@ -0,0 +1,66 @@ +/* + Copyright (c) Marshall Clow 2012-2012. + + Distributed under the Boost Software License, Version 1.0. (See accompanying + file LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt) + + For more information, see http://www.boost.org +*/ + +#include +#include +#include + +#include + + +#include + +typedef boost::string_ref string_ref; + +// Should be equal +void interop ( const std::string &str, string_ref ref ) { +// BOOST_CHECK ( str == ref ); + BOOST_CHECK ( str.size () == ref.size ()); + BOOST_CHECK ( std::equal ( str.begin (), str.end (), ref.begin ())); + } + +void substr ( const std::string &str ) { + const size_t sz = str.size (); + string_ref ref ( str ); + +// Substrings at the end + for ( size_t i = 0; i <= sz; ++ i ) + interop ( str.substr ( i ), ref.substr ( i )); + +// Substrings at the beginning + for ( size_t i = 0; i <= sz; ++ i ) + interop ( str.substr ( 0, i ), ref.substr ( 0, i )); + +// All possible substrings + for ( size_t i = 0; i < sz; ++i ) + for ( size_t j = i; j < sz; ++j ) + interop ( str.substr ( i, j ), ref.substr ( i, j )); + } + +const char *test_strings [] = { + "", + "1", + "ABCDEFGHIJKLMNOPQRSTUVWXYZ", + "0123456789", + NULL + }; + +int test_main( int , char* [] ) { + + const char **p = &test_strings[0]; + + while ( *p != NULL ) { + interop ( *p, *p ); + substr ( *p ); + + p++; + } + + return 0; + } diff --git a/test/string_ref_test2.cpp b/test/string_ref_test2.cpp new file mode 100644 index 0000000..249dbb6 --- /dev/null +++ b/test/string_ref_test2.cpp @@ -0,0 +1,139 @@ +/* + Copyright (c) Marshall Clow 2012-2012. + + Distributed under the Boost Software License, Version 1.0. (See accompanying + file LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt) + + For more information, see http://www.boost.org +*/ + +#include + +#include + +#include + +typedef boost::string_ref string_ref; + +void ends_with ( const char *arg ) { + string_ref sr ( arg ); + string_ref sr2 ( arg ); + const char *p = arg; + + while ( !*p ) { + BOOST_CHECK ( sr.ends_with ( p )); + ++p; + } + + while ( !sr2.empty ()) { + BOOST_CHECK ( sr.ends_with ( sr2 )); + sr2.remove_prefix (1); + } + + sr2 = arg; + while ( !sr2.empty ()) { + BOOST_CHECK ( sr.ends_with ( sr2 )); + sr2.remove_prefix (1); + } + + BOOST_CHECK ( sr.ends_with ( string_ref ())); + } + +void starts_with ( const char *arg ) { + string_ref sr ( arg ); + string_ref sr2 ( arg ); + const char *p = arg + std::strlen ( arg ) - 1; + while ( p >= arg ) { + std::string foo ( arg, p + 1 ); + BOOST_CHECK ( sr.starts_with ( foo )); + --p; + } + + while ( !sr2.empty ()) { + BOOST_CHECK ( sr.starts_with ( sr2 )); + sr2.remove_suffix (1); + } + + BOOST_CHECK ( sr.starts_with ( string_ref ())); + } + +void reverse ( const char *arg ) { +// Round trip + string_ref sr1 ( arg ); + std::string string1 ( sr1.rbegin (), sr1.rend ()); + string_ref sr2 ( string1 ); + std::string string2 ( sr2.rbegin (), sr2.rend ()); + + BOOST_CHECK ( std::equal ( sr2.rbegin (), sr2.rend (), arg )); + BOOST_CHECK ( string2 == arg ); + BOOST_CHECK ( std::equal ( sr1.begin (), sr1.end (), string2.begin ())); + } + + +void find ( const char *arg ) { + string_ref sr1 ( arg ); + const char *p = arg; + +// Find everything at the start + while ( !sr1.empty ()) { + string_ref::size_type pos = sr1.find(*p); + BOOST_CHECK ( pos == 0 ); + sr1.remove_prefix (1); + ++p; + } + +// Find everything at the end + sr1 = arg; + p = arg + strlen ( arg ) - 1; + while ( !sr1.empty ()) { + string_ref::size_type pos = sr1.rfind(*p); + BOOST_CHECK ( pos == sr1.size () - 1 ); + sr1.remove_suffix (1); + --p; + } + +// Find everything at the start + sr1 = arg; + p = arg; + while ( !sr1.empty ()) { + string_ref::size_type pos = sr1.find_first_of(*p); + BOOST_CHECK ( pos == 0 ); + sr1.remove_prefix (1); + ++p; + } + + +// Find everything at the end + sr1 = arg; + p = arg + strlen ( arg ) - 1; + while ( !sr1.empty ()) { + string_ref::size_type pos = sr1.find_last_of(*p); + BOOST_CHECK ( pos == sr1.size () - 1 ); + sr1.remove_suffix (1); + --p; + } + } + +const char *test_strings [] = { + "", + "0", + "abc", + "adsfadadiaef;alkdg;aljt;j agl;sjrl;tjs;lga;lretj;srg[w349u5209dsfadfasdfasdfadsf", + "abc\0asdfadsfasf", + NULL + }; + +int test_main( int , char* [] ) { + const char **p = &test_strings[0]; + + while ( *p != NULL ) { + starts_with ( *p ); + ends_with ( *p ); + reverse ( *p ); + find ( *p ); + + p++; + } + + return 0; + }