RhodeCode

/* -*- mode: C++; indent-tabs-mode: nil; -*-

 *

 * This file is a part of LEMON, a generic C++ optimization library.

 *

 * Copyright (C) 2003-2008

 * Egervary Jeno Kombinatorikus Optimalizalasi Kutatocsoport

 * (Egervary Research Group on Combinatorial Optimization, EGRES).

 *

 * Permission to use, modify and distribute this software is granted

 * provided that this copyright notice appears in all copies. For

 * precise terms see the accompanying LICENSE file.

 *

 * This software is provided "AS IS" with no warranty of any kind,

 * express or implied, and with no claim as to its suitability for any

 * purpose.

 *

 */

namespace lemon {

/*!

\page lgf-format LEMON Graph Format (LGF)

The \e LGF is a <em>column oriented</em>

file format for storing graphs and associated data like

node and edge maps.

Each line with \c '#' first non-whitespace

character is considered as a comment line.

Otherwise the file consists of sections starting with

a header line. The header lines starts with an \c '@' character followed by the

type of section. The standard section types are \c \@nodes, \c

\@arcs and \c \@edges

and \@attributes. Each header line may also have an optional

\e name, which can be use to distinguish the sections of the same

type.

The standard sections are column oriented, each line consists of

<em>token</em>s separated by whitespaces. A token can be \e plain or

\e quoted. A plain token is just a sequence of non-whitespace characters,

while a quoted token is a

character sequence surrounded by double quotes, and it can also

contain whitespaces and escape sequences.

The \c \@nodes section describes a set of nodes and associated

maps. The first is a header line, its columns are the names of the

maps appearing in the following lines.

One of the maps must be called \c

"label", which plays special role in the file.

The following

non-empty lines until the next section describes nodes of the

graph. Each line contains the values of the node maps

associated to the current node.

\code

 @nodes

 label  coordinates  size    title

 1      (10,20)      10      "First node"

 2      (80,80)      8       "Second node"

 3      (40,10)      10      "Third node"

\endcode

values. The source and target tokens must be node labels.

\code

 @arcs

         capacity

 1   2   16

 1   3   12

 2   3   18

\endcode

The \c \@edges is just a synonym of \c \@arcs. The \@arcs section can

also store the edge set of an undirected graph. In such case there is

a conventional method for store arc maps in the file, if two columns

can be regarded as the values of an arc map.

The \c \@attributes section contains key-value pairs, each line

consists of two tokens, an attribute name, and then an attribute

value. The value of the attribute could be also a label value of a

node or an edge, or even an edge label prefixed with \c '+' or \c '-',

which regards to the forward or backward directed arc of the

corresponding edge.

\code

 @attributes

 source 1

 target 3

 caption "LEMON test digraph"

\endcode

The \e LGF can contain extra sections, but there is no restriction on

the format of such sections.

*/

}

//  LocalWords:  whitespace whitespaces

/* -*- mode: C++; indent-tabs-mode: nil; -*-

 *

 * This file is a part of LEMON, a generic C++ optimization library.

 *

 * Egervary Jeno Kombinatorikus Optimalizalasi Kutatocsoport

 * (Egervary Research Group on Combinatorial Optimization, EGRES).

 *

 * Permission to use, modify and distribute this software is granted

 * provided that this copyright notice appears in all copies. For

 * precise terms see the accompanying LICENSE file.

 *

 * This software is provided "AS IS" with no warranty of any kind,

 * express or implied, and with no claim as to its suitability for any

 * purpose.

 *

 */

///\ingroup lemon_io

///\file

///\brief \ref lgf-format "LEMON Graph Format" reader.

#ifndef LEMON_LGF_READER_H

#define LEMON_LGF_READER_H

#include <iostream>

#include <fstream>

#include <sstream>

#include <set>

#include <map>

#include <lemon/core.h>

#include <lemon/lgf_writer.h>

#include <lemon/concept_check.h>

#include <lemon/concepts/maps.h>

namespace lemon {

  namespace _reader_bits {

    template <typename Value>

    struct DefaultConverter {

      Value operator()(const std::string& str) {

        std::istringstream is(str);

        Value value;

        if (!(is >> value)) {

          throw FormatError("Cannot read token");

        }

        char c;

        if (is >> std::ws >> c) {

          throw FormatError("Remaining characters in token");

        }

        return value;

      }

    };

    template <>

    struct DefaultConverter<std::string> {

      std::string operator()(const std::string& str) {

        return str;

      }

    };

    template <typename _Item>

    class MapStorageBase {

    public:

      typedef _Item Item;

    public:

      MapStorageBase() {}

      virtual ~MapStorageBase() {}

      virtual void set(const Item& item, const std::string& value) = 0;

    };

    template <typename _Item, typename _Map,

              typename _Converter = DefaultConverter<typename _Map::Value> >

    class MapStorage : public MapStorageBase<_Item> {

    public:

      typedef _Map Map;

      typedef _Converter Converter;

      typedef _Item Item;

    private:

      Map& _map;

      Converter _converter;

    public:

      MapStorage(Map& map, const Converter& converter = Converter())

        : _map(map), _converter(converter) {}

      virtual ~MapStorage() {}

      virtual void set(const Item& item ,const std::string& value) {

        _map.set(item, _converter(value));

      }

        std::string map;

        int index = 0;

        while (_reader_bits::readToken(line, map)) {

          if (maps.find(map) != maps.end()) {

            std::ostringstream msg;

            msg << "Multiple occurence of node map: " << map;

            throw FormatError(msg.str());

          }

          maps.insert(std::make_pair(map, index));

          ++index;

        }

        for (int i = 0; i < static_cast<int>(_node_maps.size()); ++i) {

          std::map<std::string, int>::iterator jt =

            maps.find(_node_maps[i].first);

          if (jt == maps.end()) {

            std::ostringstream msg;

            msg << "Map not found: " << _node_maps[i].first;

            throw FormatError(msg.str());

          }

          map_index[i] = jt->second;

        }

        {

          std::map<std::string, int>::iterator jt = maps.find("label");

          if (jt != maps.end()) {

            label_index = jt->second;

          } else {

            label_index = -1;

          }

        }

        map_num = maps.size();

      }

      while (readLine() && line >> c && c != '@') {

        line.putback(c);

        std::vector<std::string> tokens(map_num);

        for (int i = 0; i < map_num; ++i) {

          if (!_reader_bits::readToken(line, tokens[i])) {

            std::ostringstream msg;

            msg << "Column not found (" << i + 1 << ")";

            throw FormatError(msg.str());

          }

        }

        if (line >> std::ws >> c)

          throw FormatError("Extra character at the end of line");

        Node n;

        if (!_use_nodes) {

          n = _digraph.addNode();

          if (label_index != -1)

            _node_index.insert(std::make_pair(tokens[label_index], n));

        } else {

          if (label_index == -1)

            throw FormatError("Label map not found");

          typename std::map<std::string, Node>::iterator it =

            _node_index.find(tokens[label_index]);

          if (it == _node_index.end()) {

            std::ostringstream msg;

            msg << "Node with label not found: " << tokens[label_index];

            throw FormatError(msg.str());

          }

          n = it->second;

        }

        for (int i = 0; i < static_cast<int>(_node_maps.size()); ++i) {

          _node_maps[i].second->set(n, tokens[map_index[i]]);

        }

      }

      if (readSuccess()) {

        line.putback(c);

      }

    }

    void readArcs() {

      std::vector<int> map_index(_arc_maps.size());

      int map_num, label_index;

      char c;

      if (!readLine() || !(line >> c) || c == '@') {

        if (readSuccess() && line) line.putback(c);

        if (!_arc_maps.empty())

          throw FormatError("Cannot find map names");

        return;

      }

      line.putback(c);

      {

        std::map<std::string, int> maps;

        std::string map;

        int index = 0;

        while (_reader_bits::readToken(line, map)) {

          if (maps.find(map) != maps.end()) {

            std::ostringstream msg;

            msg << "Multiple occurence of arc map: " << map;

            throw FormatError(msg.str());

          }

          maps.insert(std::make_pair(map, index));

          ++index;

        }

        for (int i = 0; i < static_cast<int>(_arc_maps.size()); ++i) {

          std::map<std::string, int>::iterator jt =

            maps.find(_arc_maps[i].first);

          if (jt == maps.end()) {

            std::ostringstream msg;

            msg << "Map not found: " << _arc_maps[i].first;

            throw FormatError(msg.str());

          }

          map_index[i] = jt->second;

        }

        {

          std::map<std::string, int>::iterator jt = maps.find("label");

          if (jt != maps.end()) {

            label_index = jt->second;

          } else {

            label_index = -1;

          }

        }

        map_num = maps.size();

      }

      while (readLine() && line >> c && c != '@') {

        line.putback(c);

        std::string source_token;

        std::string target_token;

        if (!_reader_bits::readToken(line, source_token))

          throw FormatError("Source not found");

        if (!_reader_bits::readToken(line, target_token))

          throw FormatError("Target not found");

        std::vector<std::string> tokens(map_num);

        for (int i = 0; i < map_num; ++i) {

          if (!_reader_bits::readToken(line, tokens[i])) {

            std::ostringstream msg;

            msg << "Column not found (" << i + 1 << ")";

            throw FormatError(msg.str());

          }

        }

        if (line >> std::ws >> c)

          throw FormatError("Extra character at the end of line");

        Arc a;

        if (!_use_arcs) {

          typename NodeIndex::iterator it;

          it = _node_index.find(source_token);

          if (it == _node_index.end()) {

            std::ostringstream msg;

            msg << "Item not found: " << source_token;

            throw FormatError(msg.str());

          }

          Node source = it->second;

          it = _node_index.find(target_token);

          if (it == _node_index.end()) {

            std::ostringstream msg;

            msg << "Item not found: " << target_token;

            throw FormatError(msg.str());

          }

          Node target = it->second;

          a = _digraph.addArc(source, target);

          if (label_index != -1)

            _arc_index.insert(std::make_pair(tokens[label_index], a));

        } else {

          if (label_index == -1)

            throw FormatError("Label map not found");

          typename std::map<std::string, Arc>::iterator it =

            _arc_index.find(tokens[label_index]);

          if (it == _arc_index.end()) {

            std::ostringstream msg;

            msg << "Arc with label not found: " << tokens[label_index];

            throw FormatError(msg.str());

          }

          a = it->second;

        }

        for (int i = 0; i < static_cast<int>(_arc_maps.size()); ++i) {

          _arc_maps[i].second->set(a, tokens[map_index[i]]);

        }

      }

        std::string map;

        int index = 0;

        while (_reader_bits::readToken(line, map)) {

          if (maps.find(map) != maps.end()) {

            std::ostringstream msg;

            msg << "Multiple occurence of node map: " << map;

            throw FormatError(msg.str());

          }

          maps.insert(std::make_pair(map, index));

          ++index;

        }

        for (int i = 0; i < static_cast<int>(_node_maps.size()); ++i) {

          std::map<std::string, int>::iterator jt =

            maps.find(_node_maps[i].first);

          if (jt == maps.end()) {

            std::ostringstream msg;

            msg << "Map not found: " << _node_maps[i].first;

            throw FormatError(msg.str());

          }

          map_index[i] = jt->second;

        }

        {

          std::map<std::string, int>::iterator jt = maps.find("label");

          if (jt != maps.end()) {

            label_index = jt->second;

          } else {

            label_index = -1;

          }

        }

        map_num = maps.size();

      }

      while (readLine() && line >> c && c != '@') {

        line.putback(c);

        std::vector<std::string> tokens(map_num);

        for (int i = 0; i < map_num; ++i) {

          if (!_reader_bits::readToken(line, tokens[i])) {

            std::ostringstream msg;

            msg << "Column not found (" << i + 1 << ")";

            throw FormatError(msg.str());

          }

        }

        if (line >> std::ws >> c)

          throw FormatError("Extra character at the end of line");

        Node n;

        if (!_use_nodes) {

          n = _graph.addNode();

          if (label_index != -1)

            _node_index.insert(std::make_pair(tokens[label_index], n));

        } else {

          if (label_index == -1)

            throw FormatError("Label map not found");

          typename std::map<std::string, Node>::iterator it =

            _node_index.find(tokens[label_index]);

          if (it == _node_index.end()) {

            std::ostringstream msg;

            msg << "Node with label not found: " << tokens[label_index];

            throw FormatError(msg.str());

          }

          n = it->second;

        }

        for (int i = 0; i < static_cast<int>(_node_maps.size()); ++i) {

          _node_maps[i].second->set(n, tokens[map_index[i]]);

        }

      }

      if (readSuccess()) {

        line.putback(c);

      }

    }

    void readEdges() {

      std::vector<int> map_index(_edge_maps.size());

      int map_num, label_index;

      char c;

      if (!readLine() || !(line >> c) || c == '@') {

        if (readSuccess() && line) line.putback(c);

        if (!_edge_maps.empty())

          throw FormatError("Cannot find map names");

        return;

      }

      line.putback(c);

      {

        std::map<std::string, int> maps;

        std::string map;

        int index = 0;

        while (_reader_bits::readToken(line, map)) {

          if (maps.find(map) != maps.end()) {

            std::ostringstream msg;

            msg << "Multiple occurence of edge map: " << map;

            throw FormatError(msg.str());

          }

          maps.insert(std::make_pair(map, index));

          ++index;

        }

        for (int i = 0; i < static_cast<int>(_edge_maps.size()); ++i) {

          std::map<std::string, int>::iterator jt =

            maps.find(_edge_maps[i].first);

          if (jt == maps.end()) {

            std::ostringstream msg;

            msg << "Map not found: " << _edge_maps[i].first;

            throw FormatError(msg.str());

          }

          map_index[i] = jt->second;

        }

        {

          std::map<std::string, int>::iterator jt = maps.find("label");

          if (jt != maps.end()) {

            label_index = jt->second;

          } else {

            label_index = -1;

          }

        }

        map_num = maps.size();

      }

      while (readLine() && line >> c && c != '@') {

        line.putback(c);

        std::string source_token;

        std::string target_token;

        if (!_reader_bits::readToken(line, source_token))

          throw FormatError("Node u not found");

        if (!_reader_bits::readToken(line, target_token))

          throw FormatError("Node v not found");

        std::vector<std::string> tokens(map_num);

        for (int i = 0; i < map_num; ++i) {

          if (!_reader_bits::readToken(line, tokens[i])) {

            std::ostringstream msg;

            msg << "Column not found (" << i + 1 << ")";

            throw FormatError(msg.str());

          }

        }

        if (line >> std::ws >> c)

          throw FormatError("Extra character at the end of line");

        Edge e;

        if (!_use_edges) {

          typename NodeIndex::iterator it;

          it = _node_index.find(source_token);

          if (it == _node_index.end()) {

            std::ostringstream msg;

            msg << "Item not found: " << source_token;

            throw FormatError(msg.str());

          }

          Node source = it->second;

          it = _node_index.find(target_token);

          if (it == _node_index.end()) {

            std::ostringstream msg;

            msg << "Item not found: " << target_token;

            throw FormatError(msg.str());

          }

          Node target = it->second;

          e = _graph.addEdge(source, target);

          if (label_index != -1)

            _edge_index.insert(std::make_pair(tokens[label_index], e));

        } else {

          if (label_index == -1)

            throw FormatError("Label map not found");

          typename std::map<std::string, Edge>::iterator it =

            _edge_index.find(tokens[label_index]);

          if (it == _edge_index.end()) {

            std::ostringstream msg;

            msg << "Edge with label not found: " << tokens[label_index];

            throw FormatError(msg.str());

          }

          e = it->second;

        }

        for (int i = 0; i < static_cast<int>(_edge_maps.size()); ++i) {

          _edge_maps[i].second->set(e, tokens[map_index[i]]);

        }

      }

INCLUDE_DIRECTORIES(

  ${CMAKE_SOURCE_DIR}

  ${PROJECT_BINARY_DIR}

)

LINK_DIRECTORIES(${CMAKE_BINARY_DIR}/lemon)

SET(TESTS

  bfs_test

  counter_test

  dfs_test

  digraph_test

  dijkstra_test

  dim_test

  error_test

  graph_copy_test

  graph_test

  graph_utils_test

  heap_test

  kruskal_test

  maps_test

  random_test

  path_test

  time_measure_test

  unionfind_test)

FOREACH(TEST_NAME ${TESTS})

  ADD_EXECUTABLE(${TEST_NAME} ${TEST_NAME}.cc)

  TARGET_LINK_LIBRARIES(${TEST_NAME} lemon)

  ADD_TEST(${TEST_NAME} ${TEST_NAME})

ENDFOREACH(TEST_NAME)

EXTRA_DIST += \

	test/CMakeLists.txt

noinst_HEADERS += \

	test/graph_test.h \

        test/test_tools.h

check_PROGRAMS += \

	test/bfs_test \

        test/counter_test \

	test/dfs_test \

	test/digraph_test \

	test/dijkstra_test \

        test/dim_test \

	test/error_test \

	test/graph_copy_test \

	test/graph_test \

	test/graph_utils_test \

	test/heap_test \

	test/kruskal_test \

        test/maps_test \

        test/random_test \

        test/path_test \

        test/test_tools_fail \

        test/test_tools_pass \

        test/time_measure_test \

	test/unionfind_test

TESTS += $(check_PROGRAMS)

XFAIL_TESTS += test/test_tools_fail$(EXEEXT)

test_bfs_test_SOURCES = test/bfs_test.cc

test_counter_test_SOURCES = test/counter_test.cc

test_dfs_test_SOURCES = test/dfs_test.cc

test_digraph_test_SOURCES = test/digraph_test.cc

test_dijkstra_test_SOURCES = test/dijkstra_test.cc

test_dim_test_SOURCES = test/dim_test.cc

test_error_test_SOURCES = test/error_test.cc

test_graph_copy_test_SOURCES = test/graph_copy_test.cc

test_graph_test_SOURCES = test/graph_test.cc

test_graph_utils_test_SOURCES = test/graph_utils_test.cc

test_heap_test_SOURCES = test/heap_test.cc

test_kruskal_test_SOURCES = test/kruskal_test.cc

test_maps_test_SOURCES = test/maps_test.cc

test_path_test_SOURCES = test/path_test.cc

test_random_test_SOURCES = test/random_test.cc

test_test_tools_fail_SOURCES = test/test_tools_fail.cc

test_test_tools_pass_SOURCES = test/test_tools_pass.cc

test_time_measure_test_SOURCES = test/time_measure_test.cc

test_unionfind_test_SOURCES = test/unionfind_test.cc