source: trunk/lib/LineTypeParser.cc @ 1267

// $Id: LineTypeParser.cc 1267 2010-11-02 03:56:19Z peter $

/*
  Copyright (C) 2006, 2007, 2008 Jari Häkkinen, Peter Johansson
  Copyright (C) 2009, 2010 Peter Johansson

  This file is part of svndigest, http://dev.thep.lu.se/svndigest

  svndigest is free software; you can redistribute it and/or modify it
  under the terms of the GNU General Public License as published by
  the Free Software Foundation; either version 3 of the License, or
  (at your option) any later version.

  svndigest is distributed in the hope that it will be useful, but
  WITHOUT ANY WARRANTY; without even the implied warranty of
  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  General Public License for more details.

  You should have received a copy of the GNU General Public License
  along with svndigest. If not, see <http://www.gnu.org/licenses/>.
*/

#include "LineTypeParser.h"
#include "Configuration.h"
#include "utility.h"

#include <algorithm>
#include <cassert>
#include <functional>
#include <fstream>
#include <iostream>
#include <string>
#include <utility>
#include <vector>

namespace theplu{
namespace svndigest{


  LineTypeParser::LineTypeParser(std::string path)
    : mode_(0), post_copyright_(false), copyright_found_(false)
  {
    codon_ = Configuration::instance().codon(file_name(path)); 
  }


  LineTypeParser::line_type LineTypeParser::parse(std::string line)
  {
    if (!post_copyright_) {
      if (copyright_found_) {
        // check if line is end of copyright statement, i.e. contains
        // no alphanumerical character (except in copyright_prefix).
        post_copyright_ = true;
        for (size_t i=0; i<line.size()&&post_copyright_; ++i)
          if (isalnum(line[i]) && 
              !(i<copyright_prefix_.size() && copyright_prefix_[i]==line[i])){
            post_copyright_ = false;
            block_ += line + "\n";
          }
        if (post_copyright_)
          end_line_ = type_.size()+1;
      }
      else {
        // check whether copyright starts on this line
        std::string::iterator i =
          search(line.begin(), line.end(),
                 Configuration::instance().copyright_string());
        if (i!=line.end()) {
          start_line_ = type_.size()+1;
          copyright_prefix_ = line.substr(0, distance(line.begin(), i));
          copyright_found_ = true;
          block_ = line+"\n";
        }
      }
    }
    // we are in copyright block
    if (copyright_found_ && !post_copyright_)
      type_.push_back(LineTypeParser::copyright);

    else if (codon_)
      type_.push_back(code_mode(line));
    else
      type_.push_back(text_mode(line));
    return type_.back();
                      
  }


  LineTypeParser::line_type LineTypeParser::code_mode(const std::string& str)
  {
    // mode zero means we are currently not in a comment
    // if mode!=0 comment is closed by codon[mode-1].second -> mode=0
    // if codon[x-1].start is found and x >= mode -> mode=x 
    line_type lt=other;
    {
      for (std::string::const_iterator iter=str.begin();iter!=str.end();++iter){
        for (size_t i=mode_; i<codon_->size(); ++i) {
          if ( iter==str.begin() && (*codon_)[i].first[0] == '\n' && 
               match_begin(iter, str.end(), (*codon_)[i].first.substr(1)) ) {
            iter += (*codon_)[i].first.size()-1;
            mode_ = i+1;
            break;
          }
          if (match_begin(iter, str.end(), (*codon_)[i].first)) {
            iter += (*codon_)[i].first.size();
            mode_ = i+1;
            break;
          }
        }
        if (iter==str.end())
          break;
        assert(mode_==0 || mode_-1<(*codon_).size());
        if (mode_ && match_begin(iter,str.end(), (*codon_)[mode_-1].second)){
          iter += (*codon_)[mode_-1].second.size();
          mode_=0;
          if (iter==str.end())
            break;
        }
        else if (!mode_ && isgraph(*iter))
          lt=code;
        else if (mode_ && lt!=code && isalnum(*iter))
          lt=comment;
      }
      if (mode_ && (*codon_)[mode_-1].second==std::string("\n"))
        mode_=0;
    }
    return lt;
  }


  LineTypeParser::line_type LineTypeParser::text_mode(const std::string& str)
  {
    for (std::string::const_iterator iter=str.begin(); iter!=str.end(); ++iter)
      if (isalnum(*iter))
        return comment;
    return other;
  }


}} // end of namespace svndigest and namespace theplu