...one of the most highly
regarded and expertly designed C++ library projects in the
world.
— Herb Sutter and Andrei
Alexandrescu, C++
Coding Standards
#include <boost/regex.hpp>
The template class basic_regex
encapsulates regular expression parsing and compilation. The class takes
two template parameters:
charT
: determines the
character type, i.e. either char
or wchar_t
; see charT
concept.
traits
: determines the
behavior of the character type, for example which character class names
are recognized. A default traits class is provided: regex_traits<charT>
. See also traits
concept.
For ease of use there are two typedefs that define the two standard basic_regex
instances, unless you want
to use custom traits classes or non-standard character types (for example
see unicode support),
you won't need to use anything other than these:
namespace boost{ template <class charT, class traits = regex_traits<charT> > class basic_regex; typedef basic_regex<char> regex; typedef basic_regex<wchar_t> wregex; }
The definition of basic_regex
follows: it is based very closely on class basic_string
,
and fulfils the requirements for a constant-container of charT
.
namespace boost{ template <class charT, class traits = regex_traits<charT> > class basic_regex { public: // types: typedef charT value_type; typedef implementation-specific const_iterator; typedef const_iterator iterator; typedef charT& reference; typedef const charT& const_reference; typedef std::ptrdiff_t difference_type; typedef std::size_t size_type; typedef regex_constants::syntax_option_type
flag_type; typedef typename traits::locale_type locale_type; // constants: // main option selection: static const regex_constants::syntax_option_type
normal = regex_constants::normal; static const regex_constants::syntax_option_type
ECMAScript = normal; static const regex_constants::syntax_option_type
JavaScript = normal; static const regex_constants::syntax_option_type
JScript = normal; static const regex_constants::syntax_option_type
basic = regex_constants::basic; static const regex_constants::syntax_option_type
extended = regex_constants::extended; static const regex_constants::syntax_option_type
awk = regex_constants::awk; static const regex_constants::syntax_option_type
grep = regex_constants::grep; static const regex_constants::syntax_option_type
egrep = regex_constants::egrep; static const regex_constants::syntax_option_type
sed = basic = regex_constants::sed; static const regex_constants::syntax_option_type
perl = regex_constants::perl; static const regex_constants::syntax_option_type
literal = regex_constants::literal; // modifiers specific to perl expressions: static const regex_constants::syntax_option_type
no_mod_m = regex_constants::no_mod_m; static const regex_constants::syntax_option_type
no_mod_s = regex_constants::no_mod_s; static const regex_constants::syntax_option_type
mod_s = regex_constants::mod_s; static const regex_constants::syntax_option_type
mod_x = regex_constants::mod_x; // modifiers specific to POSIX basic expressions: static const regex_constants::syntax_option_type
bk_plus_qm = regex_constants::bk_plus_qm; static const regex_constants::syntax_option_type
bk_vbar = regex_constants::bk_vbar static const regex_constants::syntax_option_type
no_char_classes = regex_constants::no_char_classes static const regex_constants::syntax_option_type
no_intervals = regex_constants::no_intervals // common modifiers: static const regex_constants::syntax_option_type
nosubs = regex_constants::nosubs; static const regex_constants::syntax_option_type
optimize = regex_constants::optimize; static const regex_constants::syntax_option_type
collate = regex_constants::collate; static const regex_constants::syntax_option_type
newline_alt = regex_constants::newline_alt; static const regex_constants::syntax_option_type
no_except = regex_constants::newline_alt; // construct/copy/destroy: explicit basic_regex (); explicit basic_regex(const charT* p, flag_type f = regex_constants::normal); basic_regex(const charT* p1, const charT* p2, flag_type f = regex_constants::normal); basic_regex(const charT* p, size_type len, flag_type f); basic_regex(const basic_regex&); template <class ST, class SA> explicit basic_regex(const basic_string<charT, ST, SA>& p, flag_type f = regex_constants::normal); template <class InputIterator> basic_regex(InputIterator first, InputIterator last, flag_type f = regex_constants::normal); ~basic_regex(); basic_regex& operator=(const basic_regex&); basic_regex& operator= (const charT* ptr); template <class ST, class SA> basic_regex& operator= (const basic_string<charT, ST, SA>& p); // iterators: std::pair<const_iterator, const_iterator> subexpression(size_type n) const; const_iterator begin() const; const_iterator end() const; // capacity: size_type size() const; size_type max_size() const; bool empty() const; size_type mark_count()const; // // modifiers: basic_regex& assign(const basic_regex& that); basic_regex& assign(const charT* ptr, flag_type f = regex_constants::normal); basic_regex& assign(const charT* ptr, unsigned int len, flag_type f); template <class string_traits, class A> basic_regex& assign(const basic_string<charT, string_traits, A>& s, flag_type f = regex_constants::normal); template <class InputIterator> basic_regex& assign(InputIterator first, InputIterator last, flag_type f = regex_constants::normal); // const operations: flag_type flags() const; int status()const; basic_string<charT> str() const; int compare(basic_regex&) const; // locale: locale_type imbue(locale_type loc); locale_type getloc() const; // swap void swap(basic_regex&) throw(); }; template <class charT, class traits> bool operator == (const basic_regex<charT, traits>& lhs, const basic_regex<charT, traits>& rhs); template <class charT, class traits> bool operator != (const basic_regex<charT, traits>& lhs, const basic_regex<charT, traits>& rhs); template <class charT, class traits> bool operator < (const basic_regex<charT, traits>& lhs, const basic_regex<charT, traits>& rhs); template <class charT, class traits> bool operator <= (const basic_regex<charT, traits>& lhs, const basic_regex<charT, traits>& rhs); template <class charT, class traits> bool operator >= (const basic_regex<charT, traits>& lhs, const basic_regex<charT, traits>& rhs); template <class charT, class traits> bool operator > (const basic_regex<charT, traits>& lhs, const basic_regex<charT, traits>& rhs); template <class charT, class io_traits, class re_traits> basic_ostream<charT, io_traits>& operator << (basic_ostream<charT, io_traits>& os, const basic_regex<charT, re_traits>& e); template <class charT, class traits> void swap(basic_regex<charT, traits>& e1, basic_regex<charT, traits>& e2); typedef basic_regex<char> regex; typedef basic_regex<wchar_t> wregex; } // namespace boost
Class basic_regex
has the
following public members:
// main option selection: static const regex_constants::syntax_option_type
normal = regex_constants::normal; static const regex_constants::syntax_option_type
ECMAScript = normal; static const regex_constants::syntax_option_type
JavaScript = normal; static const regex_constants::syntax_option_type
JScript = normal; static const regex_constants::syntax_option_type
basic = regex_constants::basic; static const regex_constants::syntax_option_type
extended = regex_constants::extended; static const regex_constants::syntax_option_type
awk = regex_constants::awk; static const regex_constants::syntax_option_type
grep = regex_constants::grep; static const regex_constants::syntax_option_type
egrep = regex_constants::egrep; static const regex_constants::syntax_option_type
sed = regex_constants::sed; static const regex_constants::syntax_option_type
perl = regex_constants::perl; static const regex_constants::syntax_option_type
literal = regex_constants::literal; // modifiers specific to perl expressions: static const regex_constants::syntax_option_type
no_mod_m = regex_constants::no_mod_m; static const regex_constants::syntax_option_type
no_mod_s = regex_constants::no_mod_s; static const regex_constants::syntax_option_type
mod_s = regex_constants::mod_s; static const regex_constants::syntax_option_type
mod_x = regex_constants::mod_x; // modifiers specific to POSIX basic expressions: static const regex_constants::syntax_option_type
bk_plus_qm = regex_constants::bk_plus_qm; static const regex_constants::syntax_option_type
bk_vbar = regex_constants::bk_vbar static const regex_constants::syntax_option_type
no_char_classes = regex_constants::no_char_classes static const regex_constants::syntax_option_type
no_intervals = regex_constants::no_intervals // common modifiers: static const regex_constants::syntax_option_type
nosubs = regex_constants::nosubs; static const regex_constants::syntax_option_type
optimize = regex_constants::optimize; static const regex_constants::syntax_option_type
collate = regex_constants::collate; static const regex_constants::syntax_option_type
newline_alt = regex_constants::newline_alt;
The meaning of these options is documented in the syntax_option_type
section.
The static constant members are provided as synonyms for the constants declared
in namespace boost::regex_constants
; for each constant of type
syntax_option_type
declared in namespace boost::regex_constants
then a constant with the same name, type and value is declared within the
scope of basic_regex.
basic_regex();
Effects: Constructs an object of class
basic_regex
.
Table 1. basic_regex default construction postconditions
Element |
Value |
---|---|
|
|
|
|
|
|
basic_regex(const charT* p, flag_type f = regex_constants::normal);
Requires: p shall not be a null pointer.
Throws: bad_expression
if p
is not a valid regular expression, unless the flag no_except
is set in f.
Effects: Constructs an object of class
basic_regex
;
the object's internal finite state machine is constructed from the regular
expression contained in the null-terminated string p,
and interpreted according to the option
flags specified in f.
Table 2. Postconditions for basic_regex construction
Element |
Value |
---|---|
|
|
|
|
|
|
|
f |
|
The number of marked sub-expressions within the expression. |
basic_regex(const charT* p1, const charT* p2, flag_type f = regex_constants::normal);
Requires: p1 and p2
are not null pointers, p1 < p2
.
Throws: bad_expression if [p1,p2) is not
a valid regular expression, unless the flag no_except
is set in f.
Effects: Constructs an object of class
basic_regex
;
the object's internal finite state machine is constructed from the regular
expression contained in the sequence of characters [p1,p2), and interpreted
according the option flags
specified in f.
Table 3. Postconditions for basic_regex construction
Element |
Value |
---|---|
|
|
|
|
|
|
|
f |
|
The number of marked sub-expressions within the expression. |
basic_regex(const charT* p, size_type len, flag_type f);
Requires: p shall not
be a null pointer, len <
max_size()
.
Throws: bad_expression
if p
is not a valid regular expression, unless the flag no_except
is set in f.
Effects: Constructs an object of class
basic_regex
;
the object's internal finite state machine is constructed from the regular
expression contained in the sequence of characters [p, p+len), and interpreted
according the option flags specified in f.
Table 4. Postconditions for basic_regex construction
Element |
Value |
---|---|
|
|
|
len |
|
|
|
f |
|
The number of marked sub-expressions within the expression. |
basic_regex(const basic_regex& e);
Effects: Constructs an object of class
basic_regex
as a copy of the object e.
template <class ST, class SA> basic_regex(const basic_string<charT, ST, SA>& s, flag_type f = regex_constants::normal);
Throws: bad_expression
if s
is not a valid regular expression, unless the flag no_except
is set in f.
Effects: Constructs an object of class
basic_regex
;
the object's internal finite state machine is constructed from the regular
expression contained in the string s, and interpreted
according to the option
flags specified in f.
Table 5. Postconditions for basic_regex construction
Element |
Value |
---|---|
|
|
|
|
|
s |
|
f |
|
The number of marked sub-expressions within the expression. |
template <class ForwardIterator> basic_regex(ForwardIterator first, ForwardIterator last, flag_type f = regex_constants::normal);
Throws: bad_expression
if the sequence [first,
last) is not a valid regular expression, unless the flag no_except
is set in f.
Effects: Constructs an object of class
basic_regex
;
the object's internal finite state machine is constructed from the regular
expression contained in the sequence of characters [first, last), and interpreted
according to the option
flags specified in f.
Table 6. Postconditions for basic_regex construction
Element |
Value |
---|---|
|
|
|
|
|
|
|
f |
|
The number of marked sub-expressions within the expression. |
basic_regex& operator=(const basic_regex& e);
Effects: Returns the result of assign(e.str(), e.flags())
.
basic_regex& operator=(const charT* ptr);
Requires: p shall not be a null pointer.
Effects: Returns the result of assign(ptr)
.
template <class ST, class SA> basic_regex& operator=(const basic_string<charT, ST, SA>& p);
Effects: Returns the result of assign(p)
.
std::pair<const_iterator, const_iterator> subexpression(size_type n) const;
Effects: Returns a pair of iterators denoting
the location of marked subexpression n within the original
regular expression string. The returned iterators are relative to begin()
and end()
.
Requires: The expression must have been
compiled with the syntax_option_type
save_subexpression_location
set. Argument n must be in within the range 0 <= n
< mark_count()
.
const_iterator begin() const;
Effects: Returns a starting iterator to a sequence of characters representing the regular expression.
const_iterator end() const;
Effects: Returns termination iterator to a sequence of characters representing the regular expression.
size_type size() const;
Effects: Returns the length of the sequence of characters representing the regular expression.
size_type max_size() const;
Effects: Returns the maximum length of the sequence of characters representing the regular expression.
bool empty() const;
Effects: Returns true if the object does not contain a valid regular expression, otherwise false.
size_type mark_count() const;
Effects: Returns the number of marked sub-expressions within the regular expression.
basic_regex& assign(const basic_regex& that);
Effects: Returns assign(that.str(), that.flags())
.
basic_regex& assign(const charT* ptr, flag_type f = regex_constants::normal);
Effects: Returns assign(string_type(ptr), f)
.
basic_regex& assign(const charT* ptr, unsigned int len, flag_type f);
Effects: Returns assign(string_type(ptr, len), f)
.
template <class string_traits, class A> basic_regex& assign(const basic_string<charT, string_traits, A>& s, flag_type f = regex_constants::normal);
Throws: bad_expression
if s
is not a valid regular expression, unless the flag no_except
is set in f.
Returns: *this.
Effects: Assigns the regular expression contained in the string s, interpreted according the option flags specified in f.
Table 7. Postconditions for basic_regex::assign
Element |
Value |
---|---|
|
|
|
|
|
s |
|
f |
|
The number of marked sub-expressions within the expression. |
template <class InputIterator> basic_regex& assign(InputIterator first, InputIterator last, flag_type f = regex_constants::normal);
Requires: The type InputIterator
corresponds to the Input Iterator requirements
(24.1.1).
Effects: Returns assign(string_type(first, last), f)
.
flag_type flags() const;
Effects: Returns a copy of the regular
expression syntax flags that were passed to the object's constructor,
or the last call to assign
.
int status() const;
Effects: Returns zero if the expression contains a valid regular expression, otherwise an error code. This member function is retained for use in environments that cannot use exception handling.
basic_string<charT> str() const;
Effects: Returns a copy of the character sequence passed to the object's constructor, or the last call to assign.
int compare(basic_regex& e)const;
Effects: If flags() == e.flags()
then returns str().compare(e.str())
,
otherwise returns flags()
- e.flags()
.
locale_type imbue(locale_type l);
Effects: Returns the result of traits_inst.imbue(l)
where
traits_inst
is a (default
initialized) instance of the template parameter traits
stored within the object. Calls to imbue
invalidate any currently contained regular expression.
Postcondition: empty() == true
.
locale_type getloc() const;
Effects: Returns the result of traits_inst.getloc()
where traits_inst
is a (default
initialized) instance of the template parameter traits stored within the
object.
void swap(basic_regex& e) throw();
Effects: Swaps the contents of the two regular expressions.
Postcondition: *this
contains the regular expression that
was in e, e contains the regular
expression that was in *this
.
Complexity: constant time.
Note | |
---|---|
Comparisons between |
template <class charT, class traits> bool operator == (const basic_regex<charT, traits>& lhs, const basic_regex<charT, traits>& rhs);
Effects: Returns lhs.compare(rhs)
== 0
.
template <class charT, class traits> bool operator != (const basic_regex<charT, traits>& lhs, const basic_regex<charT, traits>& rhs);
Effects: Returns lhs.compare(rhs)
!= 0
.
template <class charT, class traits> bool operator < (const basic_regex<charT, traits>& lhs, const basic_regex<charT, traits>& rhs);
Effects: Returns lhs.compare(rhs)
< 0
.
template <class charT, class traits> bool operator <= (const basic_regex<charT, traits>& lhs, const basic_regex<charT, traits>& rhs);
Effects: Returns lhs.compare(rhs)
<= 0
.
template <class charT, class traits> bool operator >= (const basic_regex<charT, traits>& lhs, const basic_regex<charT, traits>& rhs);
Effects: Returns lhs.compare(rhs)
>= 0
.
template <class charT, class traits> bool operator > (const basic_regex<charT, traits>& lhs, const basic_regex<charT, traits>& rhs);
Effects: Returns lhs.compare(rhs)
> 0
.
Note | |
---|---|
The basic_regex stream inserter is provided on an experimental basis, and outputs the textual representation of the expression to the stream. |
template <class charT, class io_traits, class re_traits> basic_ostream<charT, io_traits>& operator << (basic_ostream<charT, io_traits>& os const basic_regex<charT, re_traits>& e);
Effects: Returns (os << e.str())
.
template <class charT, class traits> void swap(basic_regex<charT, traits>& lhs, basic_regex<charT, traits>& rhs);
Effects: calls lhs.swap(rhs)
.