reworked regex directory structure to match boost requirements.

[SVN r9752]

example/snippets/credit_card_example.cpp

@@ -0,0 +1,69 @@
+/*
+ *
+ * Copyright (c) 1998-2000
+ * Dr John Maddock
+ *
+ * Permission to use, copy, modify, distribute and sell this software
+ * and its documentation for any purpose is hereby granted without fee,
+ * provided that the above copyright notice appear in all copies and
+ * that both that copyright notice and this permission notice appear
+ * in supporting documentation.  Dr John Maddock makes no representations
+ * about the suitability of this software for any purpose.
+ * It is provided "as is" without express or implied warranty.
+ *
+ */
+
+ /*
+  *   LOCATION:    see http://www.boost.org for most recent version.
+  *   FILE         credit_card_example.cpp
+  *   VERSION      3.00
+  *   DESCRIPTION: Credit card number formatting code.
+  */
+
+#include <string>
+#include <boost/regex.hpp>
+
+bool validate_card_format(const std::string& s)
+{
+   static const boost::regex e("(\\d{4}[- ]){3}\\d{4}");
+   return boost::regex_match(s, e);
+}
+
+const boost::regex e("\\A(\\d{3,4})[- ]?(\\d{4})[- ]?(\\d{4})[- ]?(\\d{4})\\z");
+const std::string machine_format("\\1\\2\\3\\4");
+const std::string human_format("\\1-\\2-\\3-\\4");
+
+std::string machine_readable_card_number(const std::string& s)
+{
+   return boost::regex_merge(s, e, machine_format, boost::match_default | boost::format_sed);
+}
+
+std::string human_readable_card_number(const std::string& s)
+{
+   return boost::regex_merge(s, e, human_format, boost::match_default | boost::format_sed);
+}
+
+#include <iostream>
+using namespace std;
+
+int main()
+{
+   string s[4] = { "0000111122223333", "0000 1111 2222 3333",
+                   "0000-1111-2222-3333", "000-1111-2222-3333", };
+   int i;
+   for(i = 0; i < 4; ++i)
+   {
+      cout << "validate_card_format(\"" << s[i] << "\") returned " << validate_card_format(s[i]) << endl;
+   }
+   for(i = 0; i < 4; ++i)
+   {
+      cout << "machine_readable_card_number(\"" << s[i] << "\") returned " << machine_readable_card_number(s[i]) << endl;
+   }
+   for(i = 0; i < 4; ++i)
+   {
+      cout << "human_readable_card_number(\"" << s[i] << "\") returned " << human_readable_card_number(s[i]) << endl;
+   }
+   return 0;
+}
+
+

example/snippets/partial_regex_grep.cpp

@@ -0,0 +1,82 @@
+
+#include <iostream>
+#include <fstream>
+#include <sstream>
+#include <string>
+#include <boost/regex.hpp>
+
+// match some kind of html tag:
+boost::regex e("<[^>]*>");
+// count how many:
+unsigned int tags = 0;
+// saved position of partial match:
+char* next_pos = 0;
+
+bool grep_callback(const boost::match_results<char*>& m)
+{
+   if(m[0].matched == false)
+   {
+      // save position and return:
+      next_pos = m[0].first;
+   }
+   else
+      ++tags;
+   return true;
+}
+
+void search(std::istream& is)
+{
+   char buf[4096];
+   next_pos = buf + sizeof(buf);
+   bool have_more = true;
+   while(have_more)
+   {
+      // how much do we copy forward from last try:
+      unsigned leftover = (buf + sizeof(buf)) - next_pos;
+      // and how much is left to fill:
+      unsigned size = next_pos - buf;
+      // copy forward whatever we have left:
+      memcpy(buf, next_pos, leftover);
+      // fill the rest from the stream:
+      unsigned read = is.readsome(buf + leftover, size);
+      // check to see if we've run out of text:
+      have_more = read == size;
+      // reset next_pos:
+      next_pos = buf + sizeof(buf);
+      // and then grep:
+      boost::regex_grep(grep_callback,
+                        buf,
+                        buf + read + leftover,
+                        e,
+                        boost::match_default | boost::match_partial);
+   }
+}
+
+int main(int argc, char* argv[])
+{
+   if(argc > 1)
+   {
+      for(unsigned int i = 1; i < argc; ++i)
+      {
+         std::ifstream fs(argv[i]);
+         if(fs.bad()) continue;
+         search(fs);
+      }
+   }
+   else
+   {
+      std::string one("<META NAME=\"keywords\" CONTENT=\"regex++, regular expressions, regular expression library, C++\">");
+      std::string what;
+      while(what.size() < 10000)
+      {
+         what.append(one);
+         what.append(13, ' ');
+      }
+      std::stringstream ss;
+      ss.str(what);
+      search(ss);
+   }
+   std::cout << "total tag count was " << tags << std::endl;
+   return 0;
+}
+

example/snippets/partial_regex_match.cpp

@@ -0,0 +1,46 @@
+#include <string>
+#include <iostream>
+#include <boost/regex.hpp>
+
+boost::regex e("(\\d{3,4})[- ]?(\\d{4})[- ]?(\\d{4})[- ]?(\\d{4})");
+
+bool is_possible_card_number(const std::string& input)
+{
+   //
+   // return false for partial match, true for full match, or throw for
+   // impossible match based on what we have so far...
+   boost::match_results<std::string::const_iterator> what;
+   if(0 == boost::regex_match(input, what, e, boost::match_default | boost::match_partial))
+   {
+      // the input so far could not possibly be valid so reject it:
+      throw std::runtime_error("Invalid data entered - this could not possibly be a valid card number");
+   }
+   // OK so far so good, but have we finished?
+   if(what[0].matched)
+   {
+      // excellent, we have a result:
+      return true;
+   }
+   // what we have so far is only a partial match...
+   return false;
+}
+
+int main(int argc, char* argv[])
+{
+   try{
+      std::string input;
+      std::cin >> input;
+      if(is_possible_card_number(input))
+      {
+         std::cout << "Matched OK..." << std::endl;
+      }
+      else
+         std::cout << "Got a partial match..." << std::endl;
+   }
+   catch(const std::exception& e)
+   {
+      std::cout << e.what() << std::endl;
+   }
+   return 0;
+}
+

example/snippets/regex_grep_example_1.cpp

@@ -0,0 +1,107 @@
+/*
+ *
+ * Copyright (c) 1998-2000
+ * Dr John Maddock
+ *
+ * Permission to use, copy, modify, distribute and sell this software
+ * and its documentation for any purpose is hereby granted without fee,
+ * provided that the above copyright notice appear in all copies and
+ * that both that copyright notice and this permission notice appear
+ * in supporting documentation.  Dr John Maddock makes no representations
+ * about the suitability of this software for any purpose.
+ * It is provided "as is" without express or implied warranty.
+ *
+ */
+
+ /*
+  *   LOCATION:    see http://www.boost.org for most recent version.
+  *   FILE         regex_grep_example_1.cpp
+  *   VERSION      3.00
+  *   DESCRIPTION: regex_grep example 1: searches a cpp file for class definitions.
+  */
+
+#include <string>
+#include <map>
+#include <boost/regex.hpp>
+
+// purpose:
+// takes the contents of a file in the form of a string
+// and searches for all the C++ class definitions, storing
+// their locations in a map of strings/int's
+
+typedef std::map<std::string, int, std::less<std::string> > map_type;
+
+boost::regex expression("^(template[[:space:]]*<[^;:{]+>[[:space:]]*)?(class|struct)[[:space:]]*(\\<\\w+\\>([[:blank:]]*\\([^)]*\\))?[[:space:]]*)*(\\<\\w*\\>)[[:space:]]*(<[^;:{]+>)?[[:space:]]*(\\{|:[^;\\{()]*\\{)");
+
+class IndexClassesPred
+{
+   map_type& m;
+   std::string::const_iterator base;
+public:
+   IndexClassesPred(map_type& a, std::string::const_iterator b) : m(a), base(b) {}
+   bool operator()(const boost::match_results<std::string::const_iterator, boost::regex::allocator_type>& what)
+   {
+      // what[0] contains the whole string
+      // what[5] contains the class name.
+      // what[6] contains the template specialisation if any.
+      // add class name and position to map:
+      m[std::string(what[5].first, what[5].second) + std::string(what[6].first, what[6].second)] = 
+               what[5].first - base;
+      return true;
+   }
+};
+
+void IndexClasses(map_type& m, const std::string& file)
+{
+   std::string::const_iterator start, end;
+   start = file.begin();
+   end = file.end();
+   boost::regex_grep(IndexClassesPred(m, start), start, end, expression);
+}
+
+
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+
+void load_file(std::string& s, std::istream& is)
+{
+   s.erase();
+   s.reserve(is.rdbuf()->in_avail());
+   char c;
+   while(is.get(c))
+   {
+      if(s.capacity() == s.size())
+         s.reserve(s.capacity() * 3);
+      s.append(1, c);
+   }
+}
+
+int main(int argc, const char** argv)
+{
+   std::string text;
+   for(int i = 1; i < argc; ++i)
+   {
+      cout << "Processing file " << argv[i] << endl;
+      map_type m;
+      std::ifstream fs(argv[i]);
+      load_file(text, fs);
+      IndexClasses(m, text);
+      cout << m.size() << " matches found" << endl;
+      map_type::iterator c, d;
+      c = m.begin();
+      d = m.end();
+      while(c != d)
+      {
+         cout << "class \"" << (*c).first << "\" found at index: " << (*c).second << endl;
+         ++c;
+      }
+   }
+   return 0;
+}
+
+
+
+
+

example/snippets/regex_grep_example_2.cpp

@@ -0,0 +1,99 @@
+/*
+ *
+ * Copyright (c) 1998-2000
+ * Dr John Maddock
+ *
+ * Permission to use, copy, modify, distribute and sell this software
+ * and its documentation for any purpose is hereby granted without fee,
+ * provided that the above copyright notice appear in all copies and
+ * that both that copyright notice and this permission notice appear
+ * in supporting documentation.  Dr John Maddock makes no representations
+ * about the suitability of this software for any purpose.
+ * It is provided "as is" without express or implied warranty.
+ *
+ */
+
+ /*
+  *   LOCATION:    see http://www.boost.org for most recent version.
+  *   FILE         regex_grep_example_2.cpp
+  *   VERSION      3.00
+  *   DESCRIPTION: regex_grep example 2: searches a cpp file for class definitions,
+  *                using a global callback function.
+  */
+
+#include <string>
+#include <map>
+#include <boost/regex.hpp>
+
+// purpose:
+// takes the contents of a file in the form of a string
+// and searches for all the C++ class definitions, storing
+// their locations in a map of strings/int's
+
+typedef std::map<std::string, int, std::less<std::string> > map_type;
+
+boost::regex expression("^(template[[:space:]]*<[^;:{]+>[[:space:]]*)?(class|struct)[[:space:]]*(\\<\\w+\\>([[:blank:]]*\\([^)]*\\))?[[:space:]]*)*(\\<\\w*\\>)[[:space:]]*(<[^;:{]+>)?[[:space:]]*(\\{|:[^;\\{()]*\\{)");
+map_type class_index;
+std::string::const_iterator base;
+
+bool grep_callback(const boost::match_results<std::string::const_iterator, boost::regex::allocator_type>& what)
+{
+   // what[0] contains the whole string
+   // what[5] contains the class name.
+   // what[6] contains the template specialisation if any.
+   // add class name and position to map:
+   class_index[std::string(what[5].first, what[5].second) + std::string(what[6].first, what[6].second)] = 
+               what[5].first - base;
+   return true;
+}
+
+void IndexClasses(const std::string& file)
+{
+   std::string::const_iterator start, end;
+   start = file.begin();
+   end = file.end();
+   base = start;
+   boost::regex_grep(grep_callback, start, end, expression);
+}
+
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+
+void load_file(std::string& s, std::istream& is)
+{
+   s.erase();
+   s.reserve(is.rdbuf()->in_avail());
+   char c;
+   while(is.get(c))
+   {
+      if(s.capacity() == s.size())
+         s.reserve(s.capacity() * 3);
+      s.append(1, c);
+   }
+}
+
+int main(int argc, const char** argv)
+{
+   std::string text;
+   for(int i = 1; i < argc; ++i)
+   {
+      cout << "Processing file " << argv[i] << endl;
+      std::ifstream fs(argv[i]);
+      load_file(text, fs);
+      IndexClasses(text);
+      cout << class_index.size() << " matches found" << endl;
+      map_type::iterator c, d;
+      c = class_index.begin();
+      d = class_index.end();
+      while(c != d)
+      {
+         cout << "class \"" << (*c).first << "\" found at index: " << (*c).second << endl;
+         ++c;
+      }
+      class_index.erase(class_index.begin(), class_index.end());
+   }
+   return 0;
+}
+

example/snippets/regex_grep_example_3.cpp

@@ -0,0 +1,118 @@
+/*
+ *
+ * Copyright (c) 1998-2000
+ * Dr John Maddock
+ *
+ * Permission to use, copy, modify, distribute and sell this software
+ * and its documentation for any purpose is hereby granted without fee,
+ * provided that the above copyright notice appear in all copies and
+ * that both that copyright notice and this permission notice appear
+ * in supporting documentation.  Dr John Maddock makes no representations
+ * about the suitability of this software for any purpose.
+ * It is provided "as is" without express or implied warranty.
+ *
+ */
+
+ /*
+  *   LOCATION:    see http://www.boost.org for most recent version.
+  *   FILE         regex_grep_example_3.cpp
+  *   VERSION      3.00
+  *   DESCRIPTION: regex_grep example 3: searches a cpp file for class definitions,
+  *                using a bound member function callback.
+  */
+
+#include <string>
+#include <map>
+#include <boost/regex.hpp>
+#include <functional>
+
+// purpose:
+// takes the contents of a file in the form of a string
+// and searches for all the C++ class definitions, storing
+// their locations in a map of strings/int's
+
+typedef std::map<std::string, int, std::less<std::string> > map_type;
+
+class class_index
+{
+   boost::regex expression;
+   map_type index;
+   std::string::const_iterator base;
+
+   bool grep_callback(boost::match_results<std::string::const_iterator, boost::regex::allocator_type> what);
+public:
+   map_type& get_map() { return index; }
+   void IndexClasses(const std::string& file);
+   class_index()
+      : index(),
+        expression("^(template[[:space:]]*<[^;:{]+>[[:space:]]*)?(class|struct)[[:space:]]*(\\<\\w+\\>([[:blank:]]*\\([^)]*\\))?[[:space:]]*)*(\\<\\w*\\>)[[:space:]]*(<[^;:{]+>)?[[:space:]]*(\\{|:[^;\\{()]*\\{)")
+        {}
+};
+
+bool class_index::grep_callback(boost::match_results<std::string::const_iterator, boost::regex::allocator_type> what)
+{
+   // what[0] contains the whole string
+   // what[5] contains the class name.
+   // what[6] contains the template specialisation if any.
+   // add class name and position to map:
+   index[std::string(what[5].first, what[5].second) + std::string(what[6].first, what[6].second)] =
+               what[5].first - base;
+   return true;
+}
+
+void class_index::IndexClasses(const std::string& file)
+{
+   std::string::const_iterator start, end;
+   start = file.begin();
+   end = file.end();
+   base = start;
+   boost::regex_grep(std::bind1st(std::mem_fun(&class_index::grep_callback), this),
+            start,
+            end,
+            expression);
+}
+
+
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+
+void load_file(std::string& s, std::istream& is)
+{
+   s.erase();
+   s.reserve(is.rdbuf()->in_avail());
+   char c;
+   while(is.get(c))
+   {
+      if(s.capacity() == s.size())
+         s.reserve(s.capacity() * 3);
+      s.append(1, c);
+   }
+}
+
+int main(int argc, const char** argv)
+{
+   std::string text;
+   for(int i = 1; i < argc; ++i)
+   {
+      cout << "Processing file " << argv[i] << endl;
+      std::ifstream fs(argv[i]);
+      load_file(text, fs);
+      class_index i;
+      i.IndexClasses(text);
+      cout << i.get_map().size() << " matches found" << endl;
+      map_type::iterator c, d;
+      c = i.get_map().begin();
+      d = i.get_map().end();
+      while(c != d)
+      {
+         cout << "class \"" << (*c).first << "\" found at index: " << (*c).second << endl;
+         ++c;
+      }
+   }
+   return 0;
+}
+
+
+

example/snippets/regex_grep_example_4.cpp

@@ -0,0 +1,121 @@
+/*
+ *
+ * Copyright (c) 1998-2000
+ * Dr John Maddock
+ *
+ * Permission to use, copy, modify, distribute and sell this software
+ * and its documentation for any purpose is hereby granted without fee,
+ * provided that the above copyright notice appear in all copies and
+ * that both that copyright notice and this permission notice appear
+ * in supporting documentation.  Dr John Maddock makes no representations
+ * about the suitability of this software for any purpose.
+ * It is provided "as is" without express or implied warranty.
+ *
+ */
+
+ /*
+  *   LOCATION:    see http://www.boost.org for most recent version.
+  *   FILE         regex_grep_example_4.cpp
+  *   VERSION      3.00
+  *   DESCRIPTION: regex_grep example 4: searches a cpp file for class definitions,
+  *                using a C++ Builder closure as a callback.
+  */
+
+#include <string>
+#include <map>
+#include <boost/regex.hpp>
+#include <functional>
+
+// purpose:
+// takes the contents of a file in the form of a string
+// and searches for all the C++ class definitions, storing
+// their locations in a map of strings/int's
+
+typedef std::map<std::string, int, std::less<std::string> > map_type;
+
+class class_index
+{
+   boost::regex expression;
+   map_type index;
+   std::string::const_iterator base;
+   typedef boost::match_results<std::string::const_iterator, boost::regex::allocator_type> arg_type;
+
+   bool grep_callback(const boost::match_results<std::string::const_iterator, boost::regex::allocator_type>& what);
+public:
+   map_type& get_map() { return index; }
+   typedef bool (__closure* grep_callback_type)(const arg_type&);
+   void IndexClasses(const std::string& file);
+   class_index()
+      : index(),
+        expression("^(template[[:space:]]*<[^;:{]+>[[:space:]]*)?(class|struct)[[:space:]]*(\\<\\w+\\>([[:blank:]]*\\([^)]*\\))?[[:space:]]*)*(\\<\\w*\\>)[[:space:]]*(<[^;:{]+>)?[[:space:]]*(\\{|:[^;\\{()]*\\{)")
+        {}
+};
+
+bool class_index::grep_callback(const boost::match_results<std::string::const_iterator, boost::regex::allocator_type>& what)
+{
+   // what[0] contains the whole string
+   // what[5] contains the class name.
+   // what[6] contains the template specialisation if any.
+   // add class name and position to map:
+   index[std::string(what[5].first, what[5].second) + std::string(what[6].first, what[6].second)] =
+               what[5].first - base;
+   return true;
+}
+
+void class_index::IndexClasses(const std::string& file)
+{
+   std::string::const_iterator start, end;
+   start = file.begin();
+   end = file.end();
+   base = start;
+   class_index::grep_callback_type cl = &(this->grep_callback);
+   boost::regex_grep(cl,
+            start,
+            end,
+            expression);
+}
+
+
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+
+void load_file(std::string& s, std::istream& is)
+{
+   s.erase();
+   s.reserve(is.rdbuf()->in_avail());
+   char c;
+   while(is.get(c))
+   {
+      if(s.capacity() == s.size())
+         s.reserve(s.capacity() * 3);
+      s.append(1, c);
+   }
+}
+
+int main(int argc, const char** argv)
+{
+   std::string text;
+   for(int i = 1; i < argc; ++i)
+   {
+      cout << "Processing file " << argv[i] << endl;
+      std::ifstream fs(argv[i]);
+      load_file(text, fs);
+      class_index i;
+      i.IndexClasses(text);
+      cout << i.get_map().size() << " matches found" << endl;
+      map_type::iterator c, d;
+      c = i.get_map().begin();
+      d = i.get_map().end();
+      while(c != d)
+      {
+         cout << "class \"" << (*c).first << "\" found at index: " << (*c).second << endl;
+         ++c;
+      }
+   }
+   return 0;
+}
+
+
+

example/snippets/regex_match_example.cpp

@@ -0,0 +1,100 @@
+/*
+ *
+ * Copyright (c) 1998-2000
+ * Dr John Maddock
+ *
+ * Permission to use, copy, modify, distribute and sell this software
+ * and its documentation for any purpose is hereby granted without fee,
+ * provided that the above copyright notice appear in all copies and
+ * that both that copyright notice and this permission notice appear
+ * in supporting documentation.  Dr John Maddock makes no representations
+ * about the suitability of this software for any purpose.
+ * It is provided "as is" without express or implied warranty.
+ *
+ */
+
+ /*
+  *   LOCATION:    see http://www.boost.org for most recent version.
+  *   FILE         regex_match_example.cpp
+  *   VERSION      3.00
+  *   DESCRIPTION: ftp based regex_match example.
+  */
+  
+#include <cstdlib>
+#include <boost/regex.hpp>
+#include <string>
+#include <iostream>
+
+using namespace std;
+using namespace boost;
+
+regex expression("^([0-9]+)(\\-| |$)(.*)$");
+
+// process_ftp:
+// on success returns the ftp response code, and fills
+// msg with the ftp response message.
+int process_ftp(const char* response, std::string* msg)
+{
+   cmatch what;
+   if(regex_match(response, what, expression))
+   {
+      // what[0] contains the whole string
+      // what[1] contains the response code
+      // what[2] contains the separator character
+      // what[3] contains the text message.
+      if(msg)
+         msg->assign(what[3].first, what[3].second);
+      return atoi(what[1].first);
+   }
+   // failure did not match
+   if(msg)
+      msg->erase();
+   return -1;
+}
+
+#if defined(BOOST_MSVC) || (defined(__BORLANDC__) && (__BORLANDC__ == 0x550))
+//
+// problem with std::getline under MSVC6sp3
+istream& getline(istream& is, std::string& s)
+{
+   s.erase();
+   char c = is.get();
+   while(c != '\n')
+   {
+      s.append(1, c);
+      c = is.get();
+   }
+   return is;
+}
+#endif
+
+int main()
+{
+  std::string in, out;
+  while(true)
+  {
+  cout << "enter test string" << endl;
+  getline(cin, in);
+  if(in == "quit")
+     break;
+  int result;
+  result = process_ftp(in.c_str(), &out);
+  if(result != -1)
+  {
+     cout << "Match found:" << endl;
+     cout << "Response code: " << result << endl;
+     cout << "Message text: " << out << endl;
+  }
+  else
+  {
+     cout << "Match not found" << endl;
+  }
+  cout << endl;
+  }
+  return 0;
+}
+
+
+
+
+

example/snippets/regex_merge_example.cpp

@@ -0,0 +1,131 @@
+/*
+ *
+ * Copyright (c) 1998-2000
+ * Dr John Maddock
+ *
+ * Permission to use, copy, modify, distribute and sell this software
+ * and its documentation for any purpose is hereby granted without fee,
+ * provided that the above copyright notice appear in all copies and
+ * that both that copyright notice and this permission notice appear
+ * in supporting documentation.  Dr John Maddock makes no representations
+ * about the suitability of this software for any purpose.
+ * It is provided "as is" without express or implied warranty.
+ *
+ */
+
+ /*
+  *   LOCATION:    see http://www.boost.org for most recent version.
+  *   FILE         regex_merge_example.cpp
+  *   VERSION      3.00
+  *   DESCRIPTION: regex_merge example:
+  *                converts a C++ file to syntax highlighted HTML.
+  */
+
+#include <iostream>
+#include <fstream>
+#include <sstream>
+#include <string>
+#include <iterator>
+#include <boost/regex.hpp>
+#include <fstream>
+#include <iostream>
+
+// purpose:
+// takes the contents of a file and transform to
+// syntax highlighted code in html format
+
+boost::regex e1, e2;
+extern const char* expression_text;
+extern const char* format_string;
+extern const char* pre_expression;
+extern const char* pre_format;
+extern const char* header_text;
+extern const char* footer_text;
+
+void load_file(std::string& s, std::istream& is)
+{
+   s.erase();
+   s.reserve(is.rdbuf()->in_avail());
+   char c;
+   while(is.get(c))
+   {
+      if(s.capacity() == s.size())
+         s.reserve(s.capacity() * 3);
+      s.append(1, c);
+   }
+}
+
+int main(int argc, const char** argv)
+{
+   e1.set_expression(expression_text);
+   e2.set_expression(pre_expression);
+   for(int i = 1; i < argc; ++i)
+   {
+      std::cout << "Processing file " << argv[i] << std::endl;
+      std::ifstream fs(argv[i]);
+      std::string in;
+      load_file(in, fs);
+      std::string out_name = std::string(argv[i]) + std::string(".htm");
+      std::ofstream os(out_name.c_str());
+      os << header_text;
+      // strip '<' and '>' first by outputting to a
+      // temporary string stream
+      std::ostringstream t(std::ios::out | std::ios::binary);
+      std::ostream_iterator<char, char> oi(t);
+      boost::regex_merge(oi, in.begin(), in.end(), e2, pre_format);
+      // then output to final output stream
+      // adding syntax highlighting:
+      std::string s(t.str());
+      std::ostream_iterator<char, char> out(os);
+      boost::regex_merge(out, s.begin(), s.end(), e1, format_string);
+      os << footer_text;
+   }
+   return 0;
+}
+
+extern const char* pre_expression = "(<)|(>)|\\r";
+extern const char* pre_format = "(?1&lt;)(?2&gt;)";
+
+
+const char* expression_text = // preprocessor directives: index 1
+                              "(^[[:blank:]]*#(?:[^\\\\\\n]|\\\\[^\\n[:punct:][:word:]]*[\\n[:punct:][:word:]])*)|"
+                              // comment: index 2
+                              "(//[^\\n]*|/\\*.*?\\*/)|"
+                              // literals: index 3
+                              "\\<([+-]?(?:(?:0x[[:xdigit:]]+)|(?:(?:[[:digit:]]*\\.)?[[:digit:]]+(?:[eE][+-]?[[:digit:]]+)?))u?(?:(?:int(?:8|16|32|64))|L)?)\\>|"
+                              // string literals: index 4
+                              "('(?:[^\\\\']|\\\\.)*'|\"(?:[^\\\\\"]|\\\\.)*\")|"
+                              // keywords: index 5
+                              "\\<(__asm|__cdecl|__declspec|__export|__far16|__fastcall|__fortran|__import"
+                              "|__pascal|__rtti|__stdcall|_asm|_cdecl|__except|_export|_far16|_fastcall"
+                              "|__finally|_fortran|_import|_pascal|_stdcall|__thread|__try|asm|auto|bool"
+                              "|break|case|catch|cdecl|char|class|const|const_cast|continue|default|delete"
+                              "|do|double|dynamic_cast|else|enum|explicit|extern|false|float|for|friend|goto"
+                              "|if|inline|int|long|mutable|namespace|new|operator|pascal|private|protected"
+                              "|public|register|reinterpret_cast|return|short|signed|sizeof|static|static_cast"
+                              "|struct|switch|template|this|throw|true|try|typedef|typeid|typename|union|unsigned"
+                              "|using|virtual|void|volatile|wchar_t|while)\\>"
+                              ;
+
+const char* format_string = "(?1<font color=\"#008040\">$&</font>)"
+                            "(?2<I><font color=\"#000080\">$&</font></I>)"
+                            "(?3<font color=\"#0000A0\">$&</font>)"
+                            "(?4<font color=\"#0000FF\">$&</font>)"
+                            "(?5<B>$&</B>)";
+
+const char* header_text = "<HTML>\n<HEAD>\n"
+                          "<TITLE>Auto-generated html formated source</TITLE>\n"
+                          "<META HTTP-EQUIV=\"Content-Type\" CONTENT=\"text/html; charset=windows-1252\">\n"
+                          "</HEAD>\n"
+                          "<BODY LINK=\"#0000ff\" VLINK=\"#800080\" BGCOLOR=\"#ffffff\">\n"
+                          "<P> </P>\n<PRE>";
+
+const char* footer_text = "</PRE>\n</BODY>\n\n";
+
+
+
+
+
+
+
+

example/snippets/regex_search_example.cpp

@@ -0,0 +1,106 @@
+/*
+ *
+ * Copyright (c) 1998-2000
+ * Dr John Maddock
+ *
+ * Permission to use, copy, modify, distribute and sell this software
+ * and its documentation for any purpose is hereby granted without fee,
+ * provided that the above copyright notice appear in all copies and
+ * that both that copyright notice and this permission notice appear
+ * in supporting documentation.  Dr John Maddock makes no representations
+ * about the suitability of this software for any purpose.
+ * It is provided "as is" without express or implied warranty.
+ *
+ */
+
+ /*
+  *   LOCATION:    see http://www.boost.org for most recent version.
+  *   FILE         regex_search_example.cpp
+  *   VERSION      3.00
+  *   DESCRIPTION: regex_search example: searches a cpp file for class definitions.
+  */
+  
+#include <string>
+#include <map>
+#include <boost/regex.hpp>
+
+// purpose:
+// takes the contents of a file in the form of a string
+// and searches for all the C++ class definitions, storing
+// their locations in a map of strings/int's
+
+typedef std::map<std::string, int, std::less<std::string> > map_type;
+
+boost::regex expression("^(template[[:space:]]*<[^;:{]+>[[:space:]]*)?(class|struct)[[:space:]]*(\\<\\w+\\>([[:blank:]]*\\([^)]*\\))?[[:space:]]*)*(\\<\\w*\\>)[[:space:]]*(<[^;:{]+>)?[[:space:]]*(\\{|:[^;\\{()]*\\{)");
+
+void IndexClasses(map_type& m, const std::string& file)
+{
+   std::string::const_iterator start, end;
+   start = file.begin();
+   end = file.end();   
+   boost::match_results<std::string::const_iterator> what;
+   unsigned int flags = boost::match_default;
+   while(boost::regex_search(start, end, what, expression, flags))   
+   {
+      // what[0] contains the whole string
+      // what[5] contains the class name.
+      // what[6] contains the template specialisation if any.
+      // add class name and position to map:
+      m[std::string(what[5].first, what[5].second) + std::string(what[6].first, what[6].second)] = 
+               what[5].first - file.begin();      
+      // update search position:
+      start = what[0].second;      
+      // update flags:
+      flags |= boost::match_prev_avail;
+      flags |= boost::match_not_bob;
+   }
+}
+
+
+#include <iostream>
+#include <fstream>
+
+using namespace std;
+
+void load_file(std::string& s, std::istream& is)
+{
+   s.erase();
+   s.reserve(is.rdbuf()->in_avail());
+   char c;
+   while(is.get(c))
+   {
+      if(s.capacity() == s.size())
+         s.reserve(s.capacity() * 3);
+      s.append(1, c);
+   }
+}
+
+int main(int argc, const char** argv)
+{
+   std::string text;
+   for(int i = 1; i < argc; ++i)
+   {
+      cout << "Processing file " << argv[i] << endl;
+      map_type m;
+      std::ifstream fs(argv[i]);
+      load_file(text, fs);
+      IndexClasses(m, text);
+      cout << m.size() << " matches found" << endl;
+      map_type::iterator c, d;
+      c = m.begin();
+      d = m.end();
+      while(c != d)
+      {
+         cout << "class \"" << (*c).first << "\" found at index: " << (*c).second << endl;
+         ++c;
+      }
+   }
+   return 0;
+}
+
+
+
+
+
+
+

example/snippets/regex_split_example_1.cpp

@@ -0,0 +1,73 @@
+/*
+ *
+ * Copyright (c) 1998-2000
+ * Dr John Maddock
+ *
+ * Permission to use, copy, modify, distribute and sell this software
+ * and its documentation for any purpose is hereby granted without fee,
+ * provided that the above copyright notice appear in all copies and
+ * that both that copyright notice and this permission notice appear
+ * in supporting documentation.  Dr John Maddock makes no representations
+ * about the suitability of this software for any purpose.
+ * It is provided "as is" without express or implied warranty.
+ *
+ */
+
+ /*
+  *   LOCATION:    see http://www.boost.org for most recent version.
+  *   FILE         regex_split_example_1.cpp
+  *   VERSION      3.00
+  *   DESCRIPTION: regex_split example: split a string into tokens.
+  */
+
+
+#include <list>
+#include <boost/regex.hpp>
+
+
+unsigned tokenise(std::list<std::string>& l, std::string& s)
+{
+   return boost::regex_split(std::back_inserter(l), s);
+}
+
+#include <iostream>
+using namespace std;
+
+
+#if defined(BOOST_MSVC) || (defined(__BORLANDC__) && (__BORLANDC__ == 0x550))
+//
+// problem with std::getline under MSVC6sp3
+istream& getline(istream& is, std::string& s)
+{
+   s.erase();
+   char c = is.get();
+   while(c != '\n')
+   {
+      s.append(1, c);
+      c = is.get();
+   }
+   return is;
+}
+#endif
+
+
+int main()
+{
+   string s;
+   list<string> l;
+   do{
+      cout << "Enter text to split (or \"quit\" to exit): ";
+      getline(cin, s);
+      if(s == "quit") break;
+      unsigned result = tokenise(l, s);
+      cout << result << " tokens found" << endl;
+      cout << "The remaining text is: \"" << s << "\"" << endl;
+      while(l.size())
+      {
+         s = *(l.begin());
+         l.pop_front();
+         cout << s << endl;
+      }
+   }while(true);
+   return 0;
+}

example/snippets/regex_split_example_2.cpp

@@ -0,0 +1,85 @@
+/*
+ *
+ * Copyright (c) 1998-2000
+ * Dr John Maddock
+ *
+ * Permission to use, copy, modify, distribute and sell this software
+ * and its documentation for any purpose is hereby granted without fee,
+ * provided that the above copyright notice appear in all copies and
+ * that both that copyright notice and this permission notice appear
+ * in supporting documentation.  Dr John Maddock makes no representations
+ * about the suitability of this software for any purpose.
+ * It is provided "as is" without express or implied warranty.
+ *
+ */
+
+ /*
+  *   LOCATION:    see http://www.boost.org for most recent version.
+  *   FILE         regex_split_example_2.cpp
+  *   VERSION      3.00
+  *   DESCRIPTION: regex_split example: spit out linked URL's.
+  */
+
+
+#include <list>
+#include <fstream>
+#include <iostream>
+#include <boost/regex.hpp>
+
+boost::regex e("<\\s*A\\s+[^>]*href\\s*=\\s*\"([^\"]*)\"",
+               boost::regbase::normal | boost::regbase::icase);
+
+void load_file(std::string& s, std::istream& is)
+{
+   s.erase();
+   //
+   // attempt to grow string buffer to match file size,
+   // this doesn't always work...
+   s.reserve(is.rdbuf()->in_avail());
+   char c;
+   while(is.get(c))
+   {
+      // use logarithmic growth stategy, in case
+      // in_avail (above) returned zero:
+      if(s.capacity() == s.size())
+         s.reserve(s.capacity() * 3);
+      s.append(1, c);
+   }
+}
+
+int main(int argc, char** argv)
+{
+   std::string s;
+   std::list<std::string> l;
+	int i;
+   for(i = 1; i < argc; ++i)
+   {
+      std::cout << "Findings URL's in " << argv[i] << ":" << std::endl;
+      s.erase();
+      std::ifstream is(argv[i]);
+      load_file(s, is);
+      boost::regex_split(std::back_inserter(l), s, e);
+      while(l.size())
+      {
+         s = *(l.begin());
+         l.pop_front();
+         std::cout << s << std::endl;
+      }
+   }
+   //
+   // alternative method:
+   // split one match at a time and output direct to
+   // cout via ostream_iterator<std::string>....
+   //
+   for(i = 1; i < argc; ++i)
+   {
+      std::cout << "Findings URL's in " << argv[i] << ":" << std::endl;
+      s.erase();
+      std::ifstream is(argv[i]);
+      load_file(s, is);
+      while(boost::regex_split(std::ostream_iterator<std::string>(std::cout), s, e, boost::match_default, 1)) std::cout << std::endl;
+   }
+
+   return 0;
+}
+