Added regex iterator examples and docs, recovering from cvs repository crash...

[SVN r18361]

example/snippets/regex_iterator_example.cpp

@@ -0,0 +1,115 @@
+/*
+ *
+ * Copyright (c) 2003
+ * 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_iterator_example_2.cpp
+  *   VERSION      see <boost/version.hpp>
+  *   DESCRIPTION: regex_iterator example 2: searches a cpp file for class definitions,
+  *                using global data.
+  */
+
+#include <string>
+#include <map>
+#include <fstream>
+#include <iostream>
+#include <boost/regex.hpp>
+
+using namespace std;
+
+// 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, std::string::difference_type, std::less<std::string> > map_type;
+
+const char* re = 
+   // possibly leading whitespace:   
+   "^[[:space:]]*" 
+   // possible template declaration:
+   "(template[[:space:]]*<[^;:{]+>[[:space:]]*)?"
+   // class or struct:
+   "(class|struct)[[:space:]]*" 
+   // leading declspec macros etc:
+   "("
+      "\\<\\w+\\>"
+      "("
+         "[[:blank:]]*\\([^)]*\\)"
+      ")?"
+      "[[:space:]]*"
+   ")*" 
+   // the class name
+   "(\\<\\w*\\>)[[:space:]]*" 
+   // template specialisation parameters
+   "(<[^;:{]+>)?[[:space:]]*"
+   // terminate in { or :
+   "(\\{|:[^;\\{()]*\\{)";
+
+
+boost::regex expression(re);
+map_type class_index;
+
+bool regex_callback(const boost::match_results<std::string::const_iterator>& 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[what[5].str() + what[6].str()] = what.position(5);
+   return true;
+}
+
+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);
+      // construct our iterators:
+      boost::regex_iterator<std::string::const_iterator> m1(text.begin(), text.end(), expression);
+      boost::regex_iterator<std::string::const_iterator> m2;
+      std::for_each(m1, m2, &regex_callback);
+      // copy results:
+      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_merge_example.cpp

@@ -73,12 +73,12 @@ int main(int argc, const char** argv)
       // temporary string stream
       std::ostringstream t(std::ios::out | std::ios::binary);
       std::ostream_iterator<char> oi(t);
-      boost::regex_merge(oi, in.begin(), in.end(), e2, pre_format);
+      boost::regex_merge(oi, in.begin(), in.end(), e2, pre_format, boost::match_default | boost::format_all);
       // then output to final output stream
       // adding syntax highlighting:
       std::string s(t.str());
       std::ostream_iterator<char> out(os);
-      boost::regex_merge(out, s.begin(), s.end(), e1, format_string);
+      boost::regex_merge(out, s.begin(), s.end(), e1, format_string, boost::match_default | boost::format_all);
       os << footer_text;
    }
    }

example/snippets/regex_replace_example.cpp

@@ -73,12 +73,12 @@ int main(int argc, const char** argv)
       // temporary string stream
       std::ostringstream t(std::ios::out | std::ios::binary);
       std::ostream_iterator<char> oi(t);
-      boost::regex_replace(oi, in.begin(), in.end(), e2, pre_format);
+      boost::regex_replace(oi, in.begin(), in.end(), e2, pre_format, boost::match_default | boost::format_all);
       // then output to final output stream
       // adding syntax highlighting:
       std::string s(t.str());
       std::ostream_iterator<char> out(os);
-      boost::regex_replace(out, s.begin(), s.end(), e1, format_string);
+      boost::regex_replace(out, s.begin(), s.end(), e1, format_string, boost::match_default | boost::format_all);
       os << footer_text;
    }
    }
@@ -135,3 +135,4 @@ const char* footer_text = "</PRE>\n</BODY>\n\n";
 
 
 
+

example/snippets/regex_token_iterator_example_1.cpp

@@ -0,0 +1,75 @@
+/*
+ *
+ * Copyright (c) 12003
+ * 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_token_iterator_example_1.cpp
+  *   VERSION      see <boost/version.hpp>
+  *   DESCRIPTION: regex_token_iterator example: split a string into tokens.
+  */
+
+
+#include <boost/regex.hpp>
+
+#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(int argc)
+{
+   string s;
+   do{
+      if(argc == 1)
+      {
+         cout << "Enter text to split (or \"quit\" to exit): ";
+         getline(cin, s);
+         if(s == "quit") break;
+      }
+      else
+         s = "This is a string of tokens";
+
+      boost::regex re("\\s+");
+      boost::regex_token_iterator<std::string::const_iterator> i(s.begin(), s.end(), re, -1);
+      boost::regex_token_iterator<std::string::const_iterator> j;
+
+      unsigned count = 0;
+      while(i != j)
+      {
+         cout << *i++ << endl;
+         count++;
+      }
+      cout << "There were " << count << " tokens found." << endl;
+
+   }while(argc == 1);
+   return 0;
+}
+

example/snippets/regex_token_iterator_example_2.cpp

@@ -0,0 +1,92 @@
+/*
+ *
+ * Copyright (c) 2003
+ * 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_token_iterator_example_2.cpp
+  *   VERSION      see <boost/version.hpp>
+  *   DESCRIPTION: regex_token_iterator example: spit out linked URL's.
+  */
+
+
+#include <fstream>
+#include <iostream>
+#include <iterator>
+#include <boost/regex.hpp>
+
+boost::regex e("<\\s*A\\s+[^>]*href\\s*=\\s*\"([^\"]*)\"",
+               boost::regex::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;
+   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_token_iterator<std::string::const_iterator>
+         i(s.begin(), s.end(), e, 1);
+      boost::regex_token_iterator<std::string::const_iterator> j;
+      while(i != j)
+      {
+         std::cout << *i++ << std::endl;
+      }
+   }
+   //
+   // alternative method:
+   // test the array-literal constructor, and split out the whole
+   // match as well as $1....
+   //
+   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);
+      const int subs[] = {1, 0,};
+      boost::regex_token_iterator<std::string::const_iterator>
+         i(s.begin(), s.end(), e, subs);
+      boost::regex_token_iterator<std::string::const_iterator> j;
+      while(i != j)
+      {
+         std::cout << *i++ << std::endl;
+      }
+   }
+
+   return 0;
+}
+
+