C＃查找搜索结果显示的相关文档片段
在开发搜索我正在构建的网站时，我决定采用廉价而快捷的方式使用Microsoft Sql Server的全文搜索引擎，而不是像Lucene.Net那样更强大的东西。
不过，我希望拥有的功能之一是google-esque相关文档片段。我很快发现确定“相关”片段比我意识到的更难。
我想根据找到的文本中的搜索词密度选择片段。所以，基本上，我需要在文本中找到最密集的搜索词。通道是一些任意数量的字符（比如200 - 但它确实无关紧要）。
我的第一个想法是在循环中使用.IndexOf（）并构建一个术语距离数组（从先前找到的术语中减去找到的术语的索引），然后......什么？将任意两个，任意三个，任意四个，任何五个顺序数组元素相加，并使用具有最小和的那个（因此，搜索项之间的最小距离）。
这看起来很混乱。
有没有一种既定的，更好的，更明显的方式来做到这一点，而不是我想出来的？
没有找到相关结果
已邀请:
7 个回复
拟蓬
告耸
public static string SelectKeywordSnippets(string StringToSnip, string[] Keywords, int SnippetLength) { string snippedString = ""; List<int> keywordLocations = new List<int>(); //Get the locations of all keywords for (int i = 0; i < Keywords.Count(); i++) keywordLocations.AddRange(SharedTools.IndexOfAll(StringToSnip, Keywords[i], StringComparison.CurrentCultureIgnoreCase)); //Sort locations keywordLocations.Sort(); //Remove locations which are closer to each other than the SnippetLength if (keywordLocations.Count > 1) { bool found = true; while (found) { found = false; for (int i = keywordLocations.Count - 1; i > 0; i--) if (keywordLocations[i] - keywordLocations[i - 1] < SnippetLength / 2) { keywordLocations[i - 1] = (keywordLocations[i] + keywordLocations[i - 1]) / 2; keywordLocations.RemoveAt(i); found = true; } } } //Make the snippets if (keywordLocations.Count > 0 && keywordLocations[0] - SnippetLength / 2 > 0) snippedString = "... "; foreach (int i in keywordLocations) { int stringStart = Math.Max(0, i - SnippetLength / 2); int stringEnd = Math.Min(i + SnippetLength / 2, StringToSnip.Length); int stringLength = Math.Min(stringEnd - stringStart, StringToSnip.Length - stringStart); snippedString += StringToSnip.Substring(stringStart, stringLength); if (stringEnd < StringToSnip.Length) snippedString += " ... "; if (snippedString.Length > 200) break; } return snippedString; }private static List<int> IndexOfAll(string haystack, string needle, StringComparison Comparison) { int pos; int offset = 0; int length = needle.Length; List<int> positions = new List<int>(); while ((pos = haystack.IndexOf(needle, offset, Comparison)) != -1) { positions.Add(pos); offset = pos + length; } return positions; }亲奋漏
畦桨存灯
public class Highlighter { private class Packet { public string Sentence; public double Density; public int Offset; } public static string FindSnippet(string text, string query, int maxLength) { if (maxLength < 0) { throw new ArgumentException("maxLength"); } var words = query.Split(' ').Where(w => !string.IsNullOrWhiteSpace(w)).Select(word => word.ToLower()).ToLookup(s => s); var sentences = text.Split('.'); var i = 0; var packets = sentences.Select(sentence => new Packet { Sentence = sentence, Density = ComputeDensity(words, sentence), Offset = i++ }).OrderByDescending(packet => packet.Density); var list = new SortedList<int, string>(); int length = 0; foreach (var packet in packets) { if (length >= maxLength || packet.Density == 0) { break; } string sentence = packet.Sentence; list.Add(packet.Offset, sentence.Substring(0, Math.Min(sentence.Length, maxLength - length))); length += packet.Sentence.Length; } var sb = new List<string>(); int previous = -1; foreach (var item in list) { var offset = item.Key; var sentence = item.Value; if (previous != -1 && offset - previous != 1) { sb.Add("."); } previous = offset; sb.Add(Highlight(sentence, words)); } return String.Join(".", sb); } private static string Highlight(string sentence, ILookup<string, string> words) { var sb = new List<string>(); var ff = true; foreach (var word in sentence.Split(' ')) { var token = word.ToLower(); if (ff && words.Contains(token)) { sb.Add("[[HIGHLIGHT]]"); ff = !ff; } if (!ff && !string.IsNullOrWhiteSpace(token) && !words.Contains(token)) { sb.Add("[[ENDHIGHLIGHT]]"); ff = !ff; } sb.Add(word); } if (!ff) { sb.Add("[[ENDHIGHLIGHT]]"); } return String.Join(" ", sb); } private static double ComputeDensity(ILookup<string, string> words, string sentence) { if (string.IsNullOrEmpty(sentence) || words.Count == 0) { return 0; } int numerator = 0; int denominator = 0; foreach(var word in sentence.Split(' ').Select(w => w.ToLower())) { if (words.Contains(word)) { numerator++; } denominator++; } if (denominator != 0) { return (double)numerator / denominator; } else { return 0; } } }搁手
private static string FindRelevantSnippets(string infoText, string[] searchTerms) { List<int> termLocations = new List<int>(); foreach (string term in searchTerms) { int termStart = infoText.IndexOf(term); while (termStart > 0) { termLocations.Add(termStart); termStart = infoText.IndexOf(term, termStart + 1); } } if (termLocations.Count == 0) { if (infoText.Length > 250) return infoText.Substring(0, 250); else return infoText; } termLocations.Sort(); List<int> termDistances = new List<int>(); for (int i = 0; i < termLocations.Count; i++) { if (i == 0) { termDistances.Add(0); continue; } termDistances.Add(termLocations[i] - termLocations[i - 1]); } int smallestSum = int.MaxValue; int smallestSumIndex = 0; for (int i = 0; i < termDistances.Count; i++) { int sum = termDistances.Skip(i).Take(5).Sum(); if (sum < smallestSum) { smallestSum = sum; smallestSumIndex = i; } } int start = Math.Max(termLocations[smallestSumIndex] - 128, 0); int len = Math.Min(smallestSum, infoText.Length - start); len = Math.Min(len, 250); return infoText.Substring(start, len); }臀博
赣借
即可。这样做的好处是你知道片段是从开始/结束/中间获取的，所以你可以添加一些装饰，如，如果你希望在片段开始/结束。 性能 设置为的将找到最佳片段，但一次将窗口移动1个字符。将此值设置得更高可加快执行速度。 调整 你可以随心所欲地锻炼。在这个例子中，我已经完成了以支持更长的单词。private static int GetSnippetStartPoint(string documentText, string originalQuery, int snippetLength) { // Normalise document text documentText = documentText.Trim(); if (string.IsNullOrWhiteSpace(documentText)) return 0; // Return 0 if entire doc fits in snippet if (documentText.Length <= snippetLength) return 0; // Break query down into words var wordsInQuery = new HashSet<string>(); { var queryWords = originalQuery.Split(' '); foreach (var word in queryWords) { var normalisedWord = word.Trim().ToLower(); if (string.IsNullOrWhiteSpace(normalisedWord)) continue; if (wordsInQuery.Contains(normalisedWord)) continue; wordsInQuery.Add(normalisedWord); } } // Create moving window to get maximum trues var windowStart = 0; double maxScore = 0; var maxWindowStart = 0; // Higher number less accurate but faster const int resolution = 5; while (true) { var text = documentText.Substring(windowStart, snippetLength); // Get score of this chunk // This isn't perfect, as window moves in steps of resolution first and last words will be partial. // Could probably be improved to iterate words and not characters. var words = text.Split(' ').Select(c => c.Trim().ToLower()); double score = 0; foreach (var word in words) { if (wordsInQuery.Contains(word)) { // The longer the word, the more important. // Can simply replace with score += 1 for simpler model. score += Math.Pow(word.Length, 2); } } if (score > maxScore) { maxScore = score; maxWindowStart = windowStart; } // Setup next iteration windowStart += resolution; // Window end passed document end if (windowStart + snippetLength >= documentText.Length) { break; } } return maxWindowStart; }，你的权重soundex匹配少于完全匹配。