PageRenderTime 30ms CodeModel.GetById 12ms RepoModel.GetById 0ms app.codeStats 0ms

/new_backend/abdelrahmanrustom-searchengine-ac46608ebeab/searches/commands/SearchByTagsCommand.java

https://bitbucket.org/abdelrahmanrustom/searchengine
Java | 151 lines | 105 code | 19 blank | 27 comment | 14 complexity | 699f497d5d21a088e966f4cd2d681f90 MD5 | raw file
  1. import com.google.gson.Gson;
  2. import com.google.gson.JsonObject;
  3. import com.mongodb.MongoClient;
  4. import com.mongodb.MongoClientURI;
  5. import com.mongodb.client.MongoCollection;
  6. import com.mongodb.client.MongoDatabase;
  7. import org.apache.http.HttpHost;
  8. import org.bson.Document;
  9. import org.elasticsearch.action.ActionListener;
  10. import org.elasticsearch.action.search.SearchRequest;
  11. import org.elasticsearch.action.search.SearchRequestBuilder;
  12. import org.elasticsearch.action.search.SearchResponse;
  13. import org.elasticsearch.client.RestClient;
  14. import org.elasticsearch.client.RestHighLevelClient;
  15. import org.elasticsearch.common.document.DocumentField;
  16. import org.elasticsearch.index.query.BoolQueryBuilder;
  17. import org.elasticsearch.index.query.QueryBuilder;
  18. import org.elasticsearch.index.query.QueryBuilders;
  19. import org.elasticsearch.search.SearchHit;
  20. import org.elasticsearch.search.SearchHits;
  21. import org.elasticsearch.search.builder.SearchSourceBuilder;
  22. import org.tartarus.snowball.ext.PorterStemmer;
  23. import java.io.IOException;
  24. import java.io.StringReader;
  25. import java.util.*;
  26. import java.util.concurrent.Callable;
  27. //https://github.com/harryaskham/Twitter-L-LDA/blob/master/util/Stopwords.java
  28. import static org.elasticsearch.index.query.QueryBuilders.*;
  29. public class SearchByTagsCommand implements Callable<String> {
  30. String q;
  31. int resultType = 0, page_no = 1, category = -1;
  32. PorterStemmer porterStemmer = new PorterStemmer();
  33. final RestHighLevelClient client = new RestHighLevelClient(
  34. RestClient.builder(
  35. new HttpHost("localhost", 9200, "http"),
  36. new HttpHost("localhost", 9201, "http")));
  37. private static final MongoClient mongoClient = new
  38. MongoClient(new MongoClientURI("mongodb://localhost:27017"));
  39. private static final MongoDatabase database = mongoClient.getDatabase("history");
  40. private static final MongoCollection<Document> collection = database.getCollection("user_history");
  41. private static String[] stopwords = {"a", "as", "able", "about", "above", "according", "accordingly", "across", "actually", "after", "afterwards", "again", "against", "aint", "all", "allow", "allows", "almost", "alone", "along", "already", "also", "although", "always", "am", "among", "amongst", "an", "and", "another", "any", "anybody", "anyhow", "anyone", "anything", "anyway", "anyways", "anywhere", "apart", "appear", "appreciate", "appropriate", "are", "arent", "around", "as", "aside", "ask", "asking", "associated", "at", "available", "away", "awfully", "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", "behind", "being", "believe", "below", "beside", "besides", "best", "better", "between", "beyond", "both", "brief", "but", "by", "cmon", "cs", "came", "can", "cant", "cannot", "cant", "cause", "causes", "certain", "certainly", "changes", "clearly", "co", "com", "come", "comes", "concerning", "consequently", "consider", "considering", "contain", "containing", "contains", "corresponding", "could", "couldnt", "course", "currently", "definitely", "described", "despite", "did", "didnt", "different", "do", "does", "doesnt", "doing", "dont", "done", "down", "downwards", "during", "each", "edu", "eg", "eight", "either", "else", "elsewhere", "enough", "entirely", "especially", "et", "etc", "even", "ever", "every", "everybody", "everyone", "everything", "everywhere", "ex", "exactly", "example", "except", "far", "few", "ff", "fifth", "first", "five", "followed", "following", "follows", "for", "former", "formerly", "forth", "four", "from", "further", "furthermore", "get", "gets", "getting", "given", "gives", "go", "goes", "going", "gone", "got", "gotten", "greetings", "had", "hadnt", "happens", "hardly", "has", "hasnt", "have", "havent", "having", "he", "hes", "hello", "help", "hence", "her", "here", "heres", "hereafter", "hereby", "herein", "hereupon", "hers", "herself", "hi", "him", "himself", "his", "hither", "hopefully", "how", "howbeit", "however", "i", "id", "ill", "im", "ive", "ie", "if", "ignored", "immediate", "in", "inasmuch", "inc", "indeed", "indicate", "indicated", "indicates", "inner", "insofar", "instead", "into", "inward", "is", "isnt", "it", "itd", "itll", "its", "its", "itself", "just", "keep", "keeps", "kept", "know", "knows", "known", "last", "lately", "later", "latter", "latterly", "least", "less", "lest", "let", "lets", "like", "liked", "likely", "little", "look", "looking", "looks", "ltd", "mainly", "many", "may", "maybe", "me", "mean", "meanwhile", "merely", "might", "more", "moreover", "most", "mostly", "much", "must", "my", "myself", "name", "namely", "nd", "near", "nearly", "necessary", "need", "needs", "neither", "never", "nevertheless", "new", "next", "nine", "no", "nobody", "non", "none", "noone", "nor", "normally", "not", "nothing", "novel", "now", "nowhere", "obviously", "of", "off", "often", "oh", "ok", "okay", "old", "on", "once", "one", "ones", "only", "onto", "or", "other", "others", "otherwise", "ought", "our", "ours", "ourselves", "out", "outside", "over", "overall", "own", "particular", "particularly", "per", "perhaps", "placed", "please", "plus", "possible", "presumably", "probably", "provides", "que", "quite", "qv", "rather", "rd", "re", "really", "reasonably", "regarding", "regardless", "regards", "relatively", "respectively", "right", "said", "same", "saw", "say", "saying", "says", "second", "secondly", "see", "seeing", "seem", "seemed", "seeming", "seems", "seen", "self", "selves", "sensible", "sent", "serious", "seriously", "seven", "several", "shall", "she", "should", "shouldnt", "since", "six", "so", "some", "somebody", "somehow", "someone", "something", "sometime", "sometimes", "somewhat", "somewhere", "soon", "sorry", "specified", "specify", "specifying", "still", "sub", "such", "sup", "sure", "ts", "take", "taken", "tell", "tends", "th", "than", "thank", "thanks", "thanx", "that", "thats", "thats", "the", "their", "theirs", "them", "themselves", "then", "thence", "there", "theres", "thereafter", "thereby", "therefore", "therein", "theres", "thereupon", "these", "they", "theyd", "theyll", "theyre", "theyve", "think", "third", "this", "thorough", "thoroughly", "those", "though", "three", "through", "throughout", "thru", "thus", "to", "together", "too", "took", "toward", "towards", "tried", "tries", "truly", "try", "trying", "twice", "two", "un", "under", "unfortunately", "unless", "unlikely", "until", "unto", "up", "upon", "us", "use", "used", "useful", "uses", "using", "usually", "value", "various", "very", "via", "viz", "vs", "want", "wants", "was", "wasnt", "way", "we", "wed", "well", "were", "weve", "welcome", "well", "went", "were", "werent", "what", "whats", "whatever", "when", "whence", "whenever", "where", "wheres", "whereafter", "whereas", "whereby", "wherein", "whereupon", "wherever", "whether", "which", "while", "whither", "who", "whos", "whoever", "whole", "whom", "whose", "why", "will", "willing", "wish", "with", "within", "without", "wont", "wonder", "would", "would", "wouldnt", "yes", "yet", "you", "youd", "youll", "youre", "youve", "your", "yours", "yourself", "yourselves", "zero"};
  42. private static Set<String> stopWordSet = new HashSet<String>(Arrays.asList(stopwords));
  43. public SearchByTagsCommand(int category){
  44. this.category = category;
  45. }
  46. public SearchByTagsCommand(String q, int resultType, int page_no, int category){
  47. this.q = q;
  48. this.resultType = resultType;
  49. this.page_no = page_no;
  50. this.category = category;
  51. }
  52. private static boolean isStopword(String word) {
  53. if(word.length() < 2) return true;
  54. if(word.charAt(0) >= '0' && word.charAt(0) <= '9') return true; //remove numbers, "25th", etc
  55. if(stopWordSet.contains(word)) return true;
  56. else return false;
  57. }
  58. private String removeStopWordsAndStem(String[] string) {
  59. String result = "";
  60. for(String word : string) {
  61. if(word.isEmpty()) continue;
  62. if(isStopword(word)) continue; //remove stopwords
  63. porterStemmer.setCurrent(word);
  64. porterStemmer.stem();
  65. result += (porterStemmer.getCurrent()+" ");
  66. }
  67. return result;
  68. }
  69. // TODO: max number of pages = 20
  70. public String call(){
  71. final String[] res = {null};
  72. SearchRequest searchRequest = new SearchRequest("webpages");
  73. SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
  74. searchSourceBuilder.from(10*page_no);
  75. searchSourceBuilder.from(10*page_no - 1);
  76. BoolQueryBuilder tmp = QueryBuilders.boolQuery()
  77. .must(QueryBuilders.matchQuery("category",
  78. category))
  79. .should(QueryBuilders.matchQuery("keywords", q));
  80. if(resultType == 1)
  81. tmp = tmp.filter(QueryBuilders.termQuery("has_imgs", true));
  82. if(resultType == 1)
  83. tmp = tmp.filter(QueryBuilders.termQuery("has_vids", true));
  84. searchSourceBuilder.query(tmp);
  85. searchRequest.source(searchSourceBuilder);
  86. Map<String, Object> resJson = new HashMap<>();
  87. if(page_no > 20){
  88. return "{\"error\": \"Maximum number of pages exceeded\"}";
  89. }
  90. try {
  91. SearchHits hits = client.search(searchRequest).getHits();
  92. ArrayList<String> json_search_responses = new ArrayList<>();
  93. for(SearchHit hit: hits){
  94. json_search_responses.add(hit.getSourceAsString());
  95. }
  96. // System.out.println(json_search_responses);
  97. resJson.put("results", json_search_responses);
  98. Gson json = new Gson();
  99. res[0] = json.toJson(resJson);
  100. // System.out.println(res[0]);
  101. return res[0];
  102. } catch (IOException e) {
  103. resJson.put("error", e.toString());
  104. Gson json = new Gson();
  105. res[0] = json.toJson(resJson);
  106. return res[0];
  107. }
  108. // client.searchAsync(searchRequest, new ActionListener<SearchResponse>() {
  109. // @Override
  110. // public void onResponse(SearchResponse searchResponse) {
  111. // SearchHits hits = searchResponse.getHits();
  112. // ArrayList<String> json_search_responses = new ArrayList<>();
  113. // for(SearchHit hit: hits){
  114. // json_search_responses.add(hit.getSourceAsString());
  115. // }
  116. // System.out.println(json_search_responses);
  117. // resJson.put("results", json_search_responses);
  118. // Gson json = new Gson();
  119. // res[0] = json.toJson(resJson);
  120. // }
  121. //
  122. // @Override
  123. // public void onFailure(Exception e) {
  124. // resJson.put("error", e.toString());
  125. // Gson json = new Gson();
  126. // res[0] = json.toJson(resJson);
  127. // }
  128. // });
  129. // while (!(res[0] == null));
  130. // return res[0];
  131. }
  132. }