From 23f71d7727aa140c165fe34b008a1d6a7a6f12ff Mon Sep 17 00:00:00 2001 From: John Maddock Date: Mon, 3 Nov 2003 11:25:30 +0000 Subject: [PATCH] Changed regex_token_iterator to return a sub_match rather than a std::string (it's more efficient). [SVN r20613] --- doc/Attic/regex_token_iterator.html | 21 +++++----- doc/regex_token_iterator.html | 21 +++++----- include/boost/regex/config.hpp | 3 ++ .../boost/regex/v4/regex_token_iterator.hpp | 39 ++++++++++++++++++- 4 files changed, 62 insertions(+), 22 deletions(-) diff --git a/doc/Attic/regex_token_iterator.html b/doc/Attic/regex_token_iterator.html index abe9cb04..1cbd0b00 100644 --- a/doc/Attic/regex_token_iterator.html +++ b/doc/Attic/regex_token_iterator.html @@ -30,11 +30,12 @@

The template class regex_token_iterator is an iterator adapter; that is to say it represents a new view of an existing iterator sequence, by enumerating all the occurrences of a regular expression within that sequence, - and presenting one or more new strings for each match found. Each position - enumerated by the iterator is a string that represents what matched a - particular sub-expression within the regular expression. When class regex_token_iterator - is used to enumerate a single sub-expression with index -1, then the iterator - performs field splitting: that is to say it enumerates one string for each + and presenting one or more character sequence for each match found. Each + position enumerated by the iterator is a sub_match + object that represents what matched a particular sub-expression within the + regular expression. When class regex_token_iterator is used to + enumerate a single sub-expression with index -1, then the iterator performs + field splitting: that is to say it enumerates one character sequence for each section of the character container sequence that does not match the regular expression specified.

@@ -46,7 +47,8 @@ class regex_token_iterator
 {
 public:
    typedef          basic_regex<charT, traits, Allocator>                   regex_type;
-   typedef          basic_string<charT>                                     value_type;
+   typedef          sub_match                     
+             <BidirectionalIterator>                                     value_type;
    typedef typename iterator_traits<BidirectionalIterator>::difference_type difference_type;
    typedef          const value_type*                                       pointer;
    typedef          const value_type&                                       reference;
@@ -140,13 +142,13 @@ regex_token_iterator(BidirectionalIterator a, BidirectionalIterator b, const reg
          Effects: returns !(*this == that).

       
const value_type& operator*()const;

       

-         Effects: returns the current string being enumerated.

+         Effects: returns the current character sequence being enumerated.

       
const value_type* operator->()const;

       

          Effects: returns &(*this).

       
regex_token_iterator& operator++();

       

-         Effects: Moves on to the next string to be enumerated.

+         Effects: Moves on to the next character sequence to be enumerated.

       
Throws: std::runtime_error if the complexity of 
          matching the expression against an N character string begins to exceed O(N2), 
          or if the program runs out of stack space while matching the expression (if 
@@ -275,8 +277,7 @@ boost::regex e("<\\s*A\\s+[^>]*href\\s*=\\s*\"([^\"]*)
          24 Oct 2003 
          

       
© Copyright John Maddock 1998- 
-             
-            2003

+              2003

       
Use, modification and distribution are subject to 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)

diff --git a/doc/regex_token_iterator.html b/doc/regex_token_iterator.html
index abe9cb04..1cbd0b00 100644
--- a/doc/regex_token_iterator.html
+++ b/doc/regex_token_iterator.html
@@ -30,11 +30,12 @@
       
The template class regex_token_iterator is an iterator adapter; 
          that is to say it represents a new view of an existing iterator sequence, by 
          enumerating all the occurrences of a regular expression within that sequence, 
-         and presenting one or more new strings for each match found. Each position 
-         enumerated by the iterator is a string that represents what matched a 
-         particular sub-expression within the regular expression. When class regex_token_iterator
-         is used to enumerate a single sub-expression with index -1, then the iterator 
-         performs field splitting: that is to say it enumerates one string for each 
+         and presenting one or more character sequence for each match found. Each 
+         position enumerated by the iterator is a sub_match 
+         object that represents what matched a particular sub-expression within the 
+         regular expression. When class regex_token_iterator is used to 
+         enumerate a single sub-expression with index -1, then the iterator performs 
+         field splitting: that is to say it enumerates one character sequence for each 
          section of the character container sequence that does not match the regular 
          expression specified.

       
@@ -46,7 +47,8 @@ class regex_token_iterator
 {
 public:
    typedef          basic_regex<charT, traits, Allocator>                   regex_type;
-   typedef          basic_string<charT>                                     value_type;
+   typedef          sub_match                     
+             <BidirectionalIterator>                                     value_type;
    typedef typename iterator_traits<BidirectionalIterator>::difference_type difference_type;
    typedef          const value_type*                                       pointer;
    typedef          const value_type&                                       reference;
@@ -140,13 +142,13 @@ regex_token_iterator(BidirectionalIterator a, BidirectionalIterator b, const reg
          Effects: returns !(*this == that).

       
const value_type& operator*()const;

       

-         Effects: returns the current string being enumerated.

+         Effects: returns the current character sequence being enumerated.

       
const value_type* operator->()const;

       

          Effects: returns &(*this).

       
regex_token_iterator& operator++();

       

-         Effects: Moves on to the next string to be enumerated.

+         Effects: Moves on to the next character sequence to be enumerated.

       
Throws: std::runtime_error if the complexity of 
          matching the expression against an N character string begins to exceed O(N2), 
          or if the program runs out of stack space while matching the expression (if 
@@ -275,8 +277,7 @@ boost::regex e("<\\s*A\\s+[^>]*href\\s*=\\s*\"([^\"]*)
          24 Oct 2003 
          

       
© Copyright John Maddock 1998- 
-             
-            2003

+              2003

       
Use, modification and distribution are subject to 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)

diff --git a/include/boost/regex/config.hpp b/include/boost/regex/config.hpp
index 991f1cba..a3aaf5f9 100644
--- a/include/boost/regex/config.hpp
+++ b/include/boost/regex/config.hpp
@@ -209,6 +209,9 @@ using std::distance;
 #  ifdef BOOST_REGEX_DYN_LINK
 #     define BOOST_DYN_LINK
 #  endif
+#ifdef BOOST_REGEX_DIAG
+#  define BOOST_LIB_DIAGNOSTIC
+#endif
 #  include 
 #endif
 
diff --git a/include/boost/regex/v4/regex_token_iterator.hpp b/include/boost/regex/v4/regex_token_iterator.hpp
index 90fa7c21..a5ed5f3d 100644
--- a/include/boost/regex/v4/regex_token_iterator.hpp
+++ b/include/boost/regex/v4/regex_token_iterator.hpp
@@ -44,6 +44,9 @@ namespace boost{
 #  pragma warning(disable:4700)
 #endif
 
+// testing
+#define TEST_BECKER_INTERFACE
+
 template  regex_type;
+#ifdef TEST_BECKER_INTERFACE
+   typedef sub_match      value_type;
+#else
    typedef std::basic_string              value_type;
+#endif
 
    match_results what;   // current match
    BidirectionalIterator                end;    // end of search area
    const regex_type*                    pre;    // the expression
    match_flag_type                      flags;  // match flags
-   std::basic_string             result; // the current string result
+   value_type                           result; // the current string result
    int                                  N;      // the current sub-expression being enumerated
    std::vector                     subs;   // the sub-expressions to enumerate
 
@@ -99,12 +106,22 @@ public:
       if(regex_search(first, end, what, *pre, flags) == true)
       {
          N = 0;
+#ifdef TEST_BECKER_INTERFACE
+         result = ((subs[N] == -1) ? what.prefix() : what[(int)subs[N]]);
+#else
          result = ((subs[N] == -1) ? value_type(what.prefix().str()) : value_type(what[(int)subs[N]].str()));
+#endif
          return true;
       }
       else if((subs[N] == -1) && (first != end))
       {
+#ifdef TEST_BECKER_INTERFACE
+         result.first = first;
+         result.second = end;
+         result.matched = true;
+#else
          result = value_type(first, end);
+#endif
          return true;
       }
       return false;
@@ -119,7 +136,7 @@ public:
          && (what[0].first == that.what[0].first) 
          && (what[0].second == that.what[0].second);
    }
-   const std::basic_string& get()
+   const value_type& get()
    { return result; }
    bool next()
    {
@@ -128,7 +145,11 @@ public:
       if(N+1 < (int)subs.size())
       {
          ++N;
+#ifdef TEST_BECKER_INTERFACE
+         result =((subs[N] == -1) ? what.prefix().first : what[subs[N]]);
+#else
          result =((subs[N] == -1) ? value_type(what.prefix().first, what.prefix().second) : value_type(what[subs[N]].first, what[subs[N]].second));
+#endif
          return true;
       }
       if(what.prefix().first != what[0].second)
@@ -137,13 +158,23 @@ public:
       if(regex_search(last_end, end, what, *pre, ((what[0].first == what[0].second) ? flags | regex_constants::match_not_initial_null : flags)))
       {
          N =0;
+#ifdef TEST_BECKER_INTERFACE
+         result =((subs[N] == -1) ? what.prefix() : what[subs[N]]);
+#else
          result =((subs[N] == -1) ? value_type(what.prefix().first, what.prefix().second) : value_type(what[subs[N]].first, what[subs[N]].second));
+#endif
          return true;
       }
       else if((last_end != end) && (subs[0] == -1))
       {
          N =-1;
+#ifdef TEST_BECKER_INTERFACE
+         result.first = last_end;
+         result.second = end;
+         result.matched = true;
+#else
          result = value_type(last_end, end);
+#endif
          return true;
       }
       return false;
@@ -161,7 +192,11 @@ private:
    typedef shared_ptr pimpl;
 public:
    typedef          basic_regex                   regex_type;
+#ifdef TEST_BECKER_INTERFACE
+   typedef          sub_match                        value_type;
+#else
    typedef          std::basic_string                                value_type;
+#endif
    typedef typename re_detail::regex_iterator_traits::difference_type 
                                                                             difference_type;
    typedef          const value_type*                                       pointer;