Пример #1
0
  @Override
  public void prepare(ResponseBuilder rb) throws IOException {
    SolrParams params = rb.req.getParams();
    if (params.getBool(TermsParams.TERMS, false)) {
      rb.doTerms = true;
    }

    // TODO: temporary... this should go in a different component.
    String shards = params.get(ShardParams.SHARDS);
    if (shards != null) {
      if (params.get(ShardParams.SHARDS_QT) == null) {
        throw new SolrException(
            SolrException.ErrorCode.BAD_REQUEST, "No shards.qt parameter specified");
      }
      List<String> lst = StrUtils.splitSmart(shards, ",", true);
      rb.shards = lst.toArray(new String[lst.size()]);
    }
  }
Пример #2
0
  @Override
  public void process(ResponseBuilder rb) throws IOException {
    SolrParams params = rb.req.getParams();
    if (!params.getBool(TermsParams.TERMS, false)) return;

    String[] fields = params.getParams(TermsParams.TERMS_FIELD);

    NamedList<Object> termsResult = new SimpleOrderedMap<>();
    rb.rsp.add("terms", termsResult);

    if (fields == null || fields.length == 0) return;

    int limit = params.getInt(TermsParams.TERMS_LIMIT, 10);
    if (limit < 0) {
      limit = Integer.MAX_VALUE;
    }

    String lowerStr = params.get(TermsParams.TERMS_LOWER);
    String upperStr = params.get(TermsParams.TERMS_UPPER);
    boolean upperIncl = params.getBool(TermsParams.TERMS_UPPER_INCLUSIVE, false);
    boolean lowerIncl = params.getBool(TermsParams.TERMS_LOWER_INCLUSIVE, true);
    boolean sort =
        !TermsParams.TERMS_SORT_INDEX.equals(
            params.get(TermsParams.TERMS_SORT, TermsParams.TERMS_SORT_COUNT));
    int freqmin = params.getInt(TermsParams.TERMS_MINCOUNT, 1);
    int freqmax = params.getInt(TermsParams.TERMS_MAXCOUNT, UNLIMITED_MAX_COUNT);
    if (freqmax < 0) {
      freqmax = Integer.MAX_VALUE;
    }
    String prefix = params.get(TermsParams.TERMS_PREFIX_STR);
    String regexp = params.get(TermsParams.TERMS_REGEXP_STR);
    Pattern pattern = regexp != null ? Pattern.compile(regexp, resolveRegexpFlags(params)) : null;

    boolean raw = params.getBool(TermsParams.TERMS_RAW, false);

    final AtomicReader indexReader = rb.req.getSearcher().getAtomicReader();
    Fields lfields = indexReader.fields();

    for (String field : fields) {
      NamedList<Integer> fieldTerms = new NamedList<>();
      termsResult.add(field, fieldTerms);

      Terms terms = lfields == null ? null : lfields.terms(field);
      if (terms == null) {
        // no terms for this field
        continue;
      }

      FieldType ft = raw ? null : rb.req.getSchema().getFieldTypeNoEx(field);
      if (ft == null) ft = new StrField();

      // prefix must currently be text
      BytesRef prefixBytes = prefix == null ? null : new BytesRef(prefix);

      BytesRef upperBytes = null;
      if (upperStr != null) {
        upperBytes = new BytesRef();
        ft.readableToIndexed(upperStr, upperBytes);
      }

      BytesRef lowerBytes;
      if (lowerStr == null) {
        // If no lower bound was specified, use the prefix
        lowerBytes = prefixBytes;
      } else {
        lowerBytes = new BytesRef();
        if (raw) {
          // TODO: how to handle binary? perhaps we don't for "raw"... or if the field exists
          // perhaps we detect if the FieldType is non-character and expect hex if so?
          lowerBytes = new BytesRef(lowerStr);
        } else {
          lowerBytes = new BytesRef();
          ft.readableToIndexed(lowerStr, lowerBytes);
        }
      }

      TermsEnum termsEnum = terms.iterator(null);
      BytesRef term = null;

      if (lowerBytes != null) {
        if (termsEnum.seekCeil(lowerBytes) == TermsEnum.SeekStatus.END) {
          termsEnum = null;
        } else {
          term = termsEnum.term();
          // Only advance the enum if we are excluding the lower bound and the lower Term actually
          // matches
          if (lowerIncl == false && term.equals(lowerBytes)) {
            term = termsEnum.next();
          }
        }
      } else {
        // position termsEnum on first term
        term = termsEnum.next();
      }

      int i = 0;
      BoundedTreeSet<CountPair<BytesRef, Integer>> queue =
          (sort ? new BoundedTreeSet<CountPair<BytesRef, Integer>>(limit) : null);
      CharsRef external = new CharsRef();
      while (term != null && (i < limit || sort)) {
        boolean externalized = false; // did we fill in "external" yet for this term?

        // stop if the prefix doesn't match
        if (prefixBytes != null && !StringHelper.startsWith(term, prefixBytes)) break;

        if (pattern != null) {
          // indexed text or external text?
          // TODO: support "raw" mode?
          ft.indexedToReadable(term, external);
          externalized = true;
          if (!pattern.matcher(external).matches()) {
            term = termsEnum.next();
            continue;
          }
        }

        if (upperBytes != null) {
          int upperCmp = term.compareTo(upperBytes);
          // if we are past the upper term, or equal to it (when don't include upper) then stop.
          if (upperCmp > 0 || (upperCmp == 0 && !upperIncl)) break;
        }

        // This is a good term in the range.  Check if mincount/maxcount conditions are satisfied.
        int docFreq = termsEnum.docFreq();
        if (docFreq >= freqmin && docFreq <= freqmax) {
          // add the term to the list
          if (sort) {
            queue.add(new CountPair<>(BytesRef.deepCopyOf(term), docFreq));
          } else {

            // TODO: handle raw somehow
            if (!externalized) {
              ft.indexedToReadable(term, external);
            }
            fieldTerms.add(external.toString(), docFreq);
            i++;
          }
        }

        term = termsEnum.next();
      }

      if (sort) {
        for (CountPair<BytesRef, Integer> item : queue) {
          if (i >= limit) break;
          ft.indexedToReadable(item.key, external);
          fieldTerms.add(external.toString(), item.val);
          i++;
        }
      }
    }
  }
Пример #3
0
  @Override
  public void process(ResponseBuilder rb) throws IOException {
    SolrParams params = rb.req.getParams();
    if (params.getBool(TermsParams.TERMS, false)) {
      String lowerStr = params.get(TermsParams.TERMS_LOWER, null);
      String[] fields = params.getParams(TermsParams.TERMS_FIELD);
      if (fields != null && fields.length > 0) {
        NamedList terms = new SimpleOrderedMap();
        rb.rsp.add("terms", terms);
        int limit = params.getInt(TermsParams.TERMS_LIMIT, 10);
        if (limit < 0) {
          limit = Integer.MAX_VALUE;
        }
        String upperStr = params.get(TermsParams.TERMS_UPPER);
        boolean upperIncl = params.getBool(TermsParams.TERMS_UPPER_INCLUSIVE, false);
        boolean lowerIncl = params.getBool(TermsParams.TERMS_LOWER_INCLUSIVE, true);
        boolean sort =
            !TermsParams.TERMS_SORT_INDEX.equals(
                params.get(TermsParams.TERMS_SORT, TermsParams.TERMS_SORT_COUNT));
        int freqmin = params.getInt(TermsParams.TERMS_MINCOUNT, 1); // initialize freqmin
        int freqmax =
            params.getInt(TermsParams.TERMS_MAXCOUNT, UNLIMITED_MAX_COUNT); // initialize freqmax
        if (freqmax < 0) {
          freqmax = Integer.MAX_VALUE;
        }
        String prefix = params.get(TermsParams.TERMS_PREFIX_STR);
        String regexp = params.get(TermsParams.TERMS_REGEXP_STR);
        Pattern pattern =
            regexp != null ? Pattern.compile(regexp, resolveRegexpFlags(params)) : null;

        boolean raw = params.getBool(TermsParams.TERMS_RAW, false);
        for (int j = 0; j < fields.length; j++) {
          String field = StringHelper.intern(fields[j]);
          FieldType ft = raw ? null : rb.req.getSchema().getFieldTypeNoEx(field);
          if (ft == null) ft = new StrField();

          // If no lower bound was specified, use the prefix
          String lower = lowerStr == null ? prefix : (raw ? lowerStr : ft.toInternal(lowerStr));
          if (lower == null) lower = "";
          String upper = upperStr == null ? null : (raw ? upperStr : ft.toInternal(upperStr));

          Term lowerTerm = new Term(field, lower);
          Term upperTerm = upper == null ? null : new Term(field, upper);

          TermEnum termEnum =
              rb.req
                  .getSearcher()
                  .getReader()
                  .terms(lowerTerm); // this will be positioned ready to go
          int i = 0;
          BoundedTreeSet<CountPair<String, Integer>> queue =
              (sort ? new BoundedTreeSet<CountPair<String, Integer>>(limit) : null);
          NamedList fieldTerms = new NamedList();
          terms.add(field, fieldTerms);
          Term lowerTestTerm = termEnum.term();

          // Only advance the enum if we are excluding the lower bound and the lower Term actually
          // matches
          if (lowerTestTerm != null
              && lowerIncl == false
              && lowerTestTerm.field() == field // intern'd comparison
              && lowerTestTerm.text().equals(lower)) {
            termEnum.next();
          }

          while (i < limit || sort) {

            Term theTerm = termEnum.term();

            // check for a different field, or the end of the index.
            if (theTerm == null || field != theTerm.field()) // intern'd comparison
            break;

            String indexedText = theTerm.text();

            // stop if the prefix doesn't match
            if (prefix != null && !indexedText.startsWith(prefix)) break;

            if (pattern != null && !pattern.matcher(indexedText).matches()) {
              termEnum.next();
              continue;
            }

            if (upperTerm != null) {
              int upperCmp = theTerm.compareTo(upperTerm);
              // if we are past the upper term, or equal to it (when don't include upper) then stop.
              if (upperCmp > 0 || (upperCmp == 0 && !upperIncl)) break;
            }

            // This is a good term in the range.  Check if mincount/maxcount conditions are
            // satisfied.
            int docFreq = termEnum.docFreq();
            if (docFreq >= freqmin && docFreq <= freqmax) {
              // add the term to the list
              String label = raw ? indexedText : ft.indexedToReadable(indexedText);
              if (sort) {
                queue.add(new CountPair<String, Integer>(label, docFreq));
              } else {
                fieldTerms.add(label, docFreq);
                i++;
              }
            }

            termEnum.next();
          }

          termEnum.close();

          if (sort) {
            for (CountPair<String, Integer> item : queue) {
              if (i < limit) {
                fieldTerms.add(item.key, item.val);
                i++;
              } else {
                break;
              }
            }
          }
        }
      } else {
        throw new SolrException(
            SolrException.ErrorCode.BAD_REQUEST, "No terms.fl parameter specified");
      }
    }
  }
Пример #4
0
  @Override
  public void prepare(ResponseBuilder rb) throws IOException {

    SolrQueryRequest req = rb.req;
    SolrParams params = req.getParams();
    if (!params.getBool(COMPONENT_NAME, true)) {
      return;
    }
    SolrQueryResponse rsp = rb.rsp;

    // Set field flags
    String fl = params.get(CommonParams.FL);
    int fieldFlags = 0;
    if (fl != null) {
      fieldFlags |= SolrPluginUtils.setReturnFields(fl, rsp);
    }
    rb.setFieldFlags(fieldFlags);

    String defType = params.get(QueryParsing.DEFTYPE, QParserPlugin.DEFAULT_QTYPE);

    // get it from the response builder to give a different component a chance
    // to set it.
    String queryString = rb.getQueryString();
    if (queryString == null) {
      // this is the normal way it's set.
      queryString = params.get(CommonParams.Q);
      rb.setQueryString(queryString);
    }

    try {
      QParser parser = QParser.getParser(rb.getQueryString(), defType, req);
      Query q = parser.getQuery();
      if (q == null) {
        // normalize a null query to a query that matches nothing
        q = new BooleanQuery();
      }
      rb.setQuery(q);
      rb.setSortSpec(parser.getSort(true));
      rb.setQparser(parser);

      String[] fqs = req.getParams().getParams(CommonParams.FQ);
      if (fqs != null && fqs.length != 0) {
        List<Query> filters = rb.getFilters();
        if (filters == null) {
          filters = new ArrayList<Query>();
          rb.setFilters(filters);
        }
        for (String fq : fqs) {
          if (fq != null && fq.trim().length() != 0) {
            QParser fqp = QParser.getParser(fq, null, req);
            filters.add(fqp.getQuery());
          }
        }
      }
    } catch (ParseException e) {
      throw new SolrException(SolrException.ErrorCode.BAD_REQUEST, e);
    }

    // TODO: temporary... this should go in a different component.
    String shards = params.get(ShardParams.SHARDS);
    if (shards != null) {
      List<String> lst = StrUtils.splitSmart(shards, ",", true);
      rb.shards = lst.toArray(new String[lst.size()]);
    }
    String shards_rows = params.get(ShardParams.SHARDS_ROWS);
    if (shards_rows != null) {
      rb.shards_rows = Integer.parseInt(shards_rows);
    }
    String shards_start = params.get(ShardParams.SHARDS_START);
    if (shards_start != null) {
      rb.shards_start = Integer.parseInt(shards_start);
    }
  }
Пример #5
0
  /** Actually run the query */
  @Override
  public void process(ResponseBuilder rb) throws IOException {
    SolrQueryRequest req = rb.req;
    SolrQueryResponse rsp = rb.rsp;
    SolrParams params = req.getParams();
    if (!params.getBool(COMPONENT_NAME, true)) {
      return;
    }
    SolrIndexSearcher searcher = req.getSearcher();

    if (rb.getQueryCommand().getOffset() < 0) {
      throw new SolrException(
          SolrException.ErrorCode.BAD_REQUEST, "'start' parameter cannot be negative");
    }

    // -1 as flag if not set.
    long timeAllowed = (long) params.getInt(CommonParams.TIME_ALLOWED, -1);

    // Optional: This could also be implemented by the top-level searcher sending
    // a filter that lists the ids... that would be transparent to
    // the request handler, but would be more expensive (and would preserve score
    // too if desired).
    String ids = params.get(ShardParams.IDS);
    if (ids != null) {
      SchemaField idField = req.getSchema().getUniqueKeyField();
      List<String> idArr = StrUtils.splitSmart(ids, ",", true);
      int[] luceneIds = new int[idArr.size()];
      int docs = 0;
      for (int i = 0; i < idArr.size(); i++) {
        int id =
            req.getSearcher()
                .getFirstMatch(
                    new Term(idField.getName(), idField.getType().toInternal(idArr.get(i))));
        if (id >= 0) luceneIds[docs++] = id;
      }

      DocListAndSet res = new DocListAndSet();
      res.docList = new DocSlice(0, docs, luceneIds, null, docs, 0);
      if (rb.isNeedDocSet()) {
        List<Query> queries = new ArrayList<Query>();
        queries.add(rb.getQuery());
        List<Query> filters = rb.getFilters();
        if (filters != null) queries.addAll(filters);
        res.docSet = searcher.getDocSet(queries);
      }
      rb.setResults(res);
      rsp.add("response", rb.getResults().docList);
      return;
    }

    SolrIndexSearcher.QueryCommand cmd = rb.getQueryCommand();
    cmd.setTimeAllowed(timeAllowed);
    SolrIndexSearcher.QueryResult result = new SolrIndexSearcher.QueryResult();

    //
    // grouping / field collapsing
    //
    boolean doGroup = params.getBool(GroupParams.GROUP, false);
    if (doGroup) {
      try {
        cmd.groupCommands = new ArrayList<Grouping.Command>();

        String[] fields = params.getParams(GroupParams.GROUP_FIELD);
        String[] funcs = params.getParams(GroupParams.GROUP_FUNC);
        String[] queries = params.getParams(GroupParams.GROUP_QUERY);
        String groupSortStr = params.get(GroupParams.GROUP_SORT);
        Sort groupSort =
            groupSortStr != null ? QueryParsing.parseSort(groupSortStr, req.getSchema()) : null;

        int limitDefault = cmd.getLen(); // this is normally from "rows"
        int docsPerGroupDefault = params.getInt(GroupParams.GROUP_LIMIT, 1);

        // temporary: implement all group-by-field as group-by-func
        if (funcs == null) {
          funcs = fields;
        } else if (fields != null) {
          // catenate functions and fields
          String[] both = new String[fields.length + funcs.length];
          System.arraycopy(fields, 0, both, 0, fields.length);
          System.arraycopy(funcs, 0, both, fields.length, funcs.length);
          funcs = both;
        }

        if (funcs != null) {
          for (String groupByStr : funcs) {
            QParser parser = QParser.getParser(groupByStr, "func", rb.req);
            Query q = parser.getQuery();
            Grouping.CommandFunc gc = new Grouping.CommandFunc();
            gc.groupSort = groupSort;

            if (q instanceof FunctionQuery) {
              gc.groupBy = ((FunctionQuery) q).getValueSource();
            } else {
              gc.groupBy = new QueryValueSource(q, 0.0f);
            }
            gc.key = groupByStr;
            gc.groupLimit = limitDefault;
            gc.docsPerGroup = docsPerGroupDefault;

            cmd.groupCommands.add(gc);
          }
        }

        if (cmd.groupCommands.size() == 0) cmd.groupCommands = null;

        if (cmd.groupCommands != null) {
          if (rb.doHighlights || rb.isDebug()) {
            // we need a single list of the returned docs
            cmd.setFlags(SolrIndexSearcher.GET_DOCLIST);
          }

          searcher.search(result, cmd);
          rb.setResult(result);
          rsp.add("grouped", result.groupedResults);
          // TODO: get "hits" a different way to log
          return;
        }
      } catch (ParseException e) {
        throw new SolrException(SolrException.ErrorCode.BAD_REQUEST, e);
      }
    }

    // normal search result
    searcher.search(result, cmd);
    rb.setResult(result);

    rsp.add("response", rb.getResults().docList);
    rsp.getToLog().add("hits", rb.getResults().docList.matches());

    doFieldSortValues(rb, searcher);
    doPrefetch(rb);
  }