source: trunk/lib/BlameStats.cc @ 1194

// $Id: BlameStats.cc 1194 2010-10-03 23:39:12Z peter $

/*
  Copyright (C) 2005 Peter Johansson
  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 "BlameStats.h"

#include "Functor.h"
#include "SVNblame.h"
#include "SVNinfo.h"
#include "SVNlog.h"
#include "utility.h"
#include "Vector.h"

#include <algorithm>
#include <cassert>
#include <cstdlib>
#include <fstream>
#include <functional>
#include <iostream>
#include <iterator>
#include <map>
#include <numeric>
#include <string>
#include <sstream>
#include <unistd.h>
#include <utility>
#include <vector>


namespace theplu{
namespace svndigest{


  BlameStats::BlameStats(const std::string& path)
    : Stats(path)
  {
  }


  BlameStats::BlameStats(const BlameStats& other)
  : Stats(other)
  {
  }


  void BlameStats::do_parse(const std::string& path, svn_revnum_t first_rev)
  {
    // FIXME: using log from File object
    SVNlog log(path);
    typedef std::set<svn_revnum_t> RevSet;
    RevSet revs;
    std::transform(log.commits().begin(), log.commits().end(),
                   std::inserter(revs, revs.begin()), 
                   std::mem_fun_ref(&Commitment::revision));
    // we use a ParseVector here to be able to detect when people are
    // absent in a revision.
    std::vector<std::map<std::string, SparseVector> > data(4);
    for (RevSet::reverse_iterator rev_iter=revs.rbegin();
         rev_iter!=revs.rend() && *rev_iter>=first_rev; ++rev_iter){
      SVNblame svn_blame(path, *rev_iter);
      LineTypeParser parser(path);
      while (svn_blame.valid()) {
        int lt = parser.parse(svn_blame.line());
        assert(lt<data.size());
        SparseVector& vec = data[lt][svn_blame.author()];
        vec.set(*rev_iter, vec[*rev_iter] + 1);
        add_author(svn_blame.author());
        // I dont trust blame and log behave consistently (stop-on-copy).
        revs.insert(svn_blame.revision());
        svn_blame.next_line();
      }
    }

    // for count=zero we have not created an entry in SumVector and
    // value will be "value for previous rev". Therefore we need to
    // set the value to zero explicitely.
    if (stats_.size()<data.size())
      stats_.resize(data.size());
    for (int lt =0; lt<data.size(); ++lt) {
      // just to avoid long long lines
      typedef std::map<std::string,SparseVector>::const_iterator const_iterator;
      for (const_iterator av = data[lt].begin(); av!=data[lt].end(); ++av) {
        for (RevSet::const_reverse_iterator rev_iter=revs.rbegin(); 
             rev_iter!=revs.rend() && *rev_iter >= first_rev; ++rev_iter) {
          // FIXME: use Vector::iterator to avoid logN checkup
          stats_[lt][av->first].set(*rev_iter, data[lt][av->first][*rev_iter]);
        }
      }
    }
  }

}} // end of namespace svndigest and namespace theplu