public static string FormatKnGraphIndexesForPrinting(KnowledgeGraph graph)
{
StringBuilder sb = new StringBuilder();
foreach (KnowledgeGraphNode node in graph.KnGraph)
{
sb.Append(node.Index + ": ");
foreach (KnowledgeGraphNode neighbor in node.Neighbors)
{
sb.Append(neighbor.Index + ", ");
}
sb.AppendLine();
}
return(sb.ToString());
}
public static string FormatKnGraphLabelsForPrinting(KnowledgeGraph graph)
{
// we'll use DFS to print the names according to the graph and with indentation
List <bool> visited = new List <bool>();
graph.KnGraph.ForEach(x => visited.Add(false));
StringBuilder sb = new StringBuilder();
foreach (KnowledgeGraphNode node in graph.KnGraph)
{
if (!visited[node.Index])
{
DFSRecursive(graph, visited, node, 0, ref sb);
}
}
return(sb.ToString());
}
public static string FormatKnGraphIndexAndLabelsForPrinting(KnowledgeGraph graph)
{
StringBuilder sb = new StringBuilder();
foreach (KnowledgeGraphNode node in graph.KnGraph)
{
sb.AppendLine(node.OriginalGraphType + "-" + node.Index + ": " + node.HtmlName + ": " + node.Label + ", " + node.LinkToPage);
sb.Append(node.Index + ": ");
foreach (KnowledgeGraphNode neighbor in node.Neighbors)
{
sb.Append(neighbor.Index + ", ");
}
sb.AppendLine();
}
return(sb.ToString());
}
private static void DFSRecursive(KnowledgeGraph graph, List <bool> visited, KnowledgeGraphNode currentNode, int level, ref StringBuilder sb)
{
sb.Append(currentNode.Label);
sb.AppendLine();
visited[currentNode.Index] = true;
level++;
foreach (KnowledgeGraphNode neighbor in graph.KnGraph[currentNode.Index].Neighbors)
{
if (!visited[neighbor.Index])
{
PrintLevelSpaces(level, ref sb);
DFSRecursive(graph, visited, neighbor, level, ref sb);
}
}
level--;
}
public static void DownloadAllPagesInKnGraph()
{
KnowledgeGraph knowledgeGraph = WKGE.ExtractKnGraphFromUris(WKGE.WikipediaPagesToParse);
// Download the html files
SaveUriToHtmlFile(WKGE.GetWikipediaListOfAlgorithmsPageUri(), "../../../DownloadedHtmlPages/listOfAlgos.html");
SaveUriToHtmlFile(WKGE.GetWikipediaListOfDataStructuresPageUri(), "../../../DownloadedHtmlPages/listOfDataStructures.html");
// Download the content of each link in the nodes of the kn graph
foreach (KnowledgeGraphNode node in knowledgeGraph.KnGraph.Where(x => x.LinkToPage != null))
{
string filePath = GetFilePathFromNodeLinkTopage(node.LinkToPage);
if (!File.Exists(filePath))
{
SaveUriPageContentToTxtFile(node.LinkToPage, filePath);
Console.WriteLine("Wrote file with name " + Path.GetFileName(filePath));
}
else
{
Console.WriteLine("!!! ALREADYEXISTS !!! " + filePath);
}
}
}
private static void AddEdgeToKnowledgeGraph(ref KnowledgeGraph graph, int nodeIndex, KnowledgeGraphNode nodeToAdd)
{
graph.KnGraph[nodeIndex].Neighbors.Add(new KnowledgeGraphNode(nodeToAdd));
}
private static Dictionary <string, KnowledgeGraphNode> GetUniqueDataStructureNodes(KnowledgeGraph graph)
{
List <KnowledgeGraphNode> dataStructureNodesWithDuplicates = graph.KnGraph.Where(n => n.OriginalGraphType == OriginalGraphType.DataStructuresKnGraph).ToList();
Dictionary <string, KnowledgeGraphNode> result = new Dictionary <string, KnowledgeGraphNode>();
foreach (KnowledgeGraphNode node in dataStructureNodesWithDuplicates)
{
string nodeLabel = node.Label.ToLowerInvariant();
if (!result.ContainsKey(nodeLabel))
{
result.Add(nodeLabel, node);
}
}
return(result);
}
public static List <WordCountByNodeIndex> GetDataStructureWordCountsFromGraph(KnowledgeGraph knowledgeGraph)
{
// compute the list of DS words
List <string> dataStructureWords = Utilities.GetDataStructureWordsFromGraph(knowledgeGraph);
List <WordCountByNodeIndex> result = new List <WordCountByNodeIndex>();
// foreach node in the graph which has a link to page and downloaded file for that link, get the ds word count
knowledgeGraph.KnGraph
.Where(node => node.OriginalGraphType == OriginalGraphType.AlgorithmsKnGraph && node.LinkToPage != null && File.Exists(Utilities.GetFilePathFromNodeLinkTopage(node.LinkToPage))).ToList()
.ForEach(node =>
{
// make empty ds words dictionary for this node
Dictionary <string, int> dsWordsCountDictForOneNode = new Dictionary <string, int>();
dataStructureWords.ForEach(dsWord =>
{
dsWordsCountDictForOneNode.Add(dsWord, 0);
});
// get file content and count the ds words in it
string fileContent = File.ReadAllText(Utilities.GetFilePathFromNodeLinkTopage(node.LinkToPage));
string[] fileContentWords = fileContent.Split(' ');
foreach (string word in fileContentWords)
{
if (dsWordsCountDictForOneNode.ContainsKey(word))
{
dsWordsCountDictForOneNode[word]++;
}
}
// remove words with 0 count from words count dictionary
dsWordsCountDictForOneNode = dsWordsCountDictForOneNode.Where(x => x.Value > 0).ToDictionary(y => y.Key, y => y.Value);
// only add it to the list if there is at least one ds word
if (dsWordsCountDictForOneNode.Any())
{
WordCountByNodeIndex wordCountForNode = new WordCountByNodeIndex()
{
Index = node.Index,
WordsCount = new Dictionary <string, int>(dsWordsCountDictForOneNode)
};
result.Add(wordCountForNode);
}
});
return(result);
}
