!7

sclass SearchResult {
  S snippetID;
  S title;
  int occurrences;
  
  sS _fieldOrder = "snippetID title";
}

cmodule FullTextSnippetSearch > DynTableWithInput2<SearchResult> {
  switchable int maxResults = 1000;
  switchable int maxTextLength = 100000;
  transient S status;
  
  JComponent mainComponent() {
    ret northAndCenterWithMargin(dm_rightAlignedLabel status(), super.mainComponent());
  }
  
  start {
    dontPersist();
    //thread { warmUp(); }
  }
  
  void calc {
    setList(search(input, true));
  }
  
  void warmUp enter {
    benchFor5Seconds(r { hijackPrint(r { search("this is cool", false) }) });
  }
  
  L<SearchResult> search(S input, bool setStatus) {
    S mod = dm_require("#1028945/CacheAllSnippets");
    SS data = cast dm_rcall getData(mod);
    SS titles = cast dm_rcall getTitles(mod);
    
    S index = dm_require("#1029043/SnippetsDeepWordPairIndex");
    long nanos = nanoTime();
    
    S query = upper(input);
    Iterable</*virtual Pair<S, Cl<S>>*/O> pre = cast dm_call(index, 'snippetPreSearch_withPositions, query);
    long nanos1 = nanoTime()-nanos;

    new L<SearchResult> out;
    if (pre == null) {
      if (setStatus) print("No pres");
      pre = mapI(keys(data), snippetID -> pair(snippetID, null));
    }
    int badPres = 0;
    if (nempty(query)) {
      fOr ping (O entry : pre) {
        Pair<S, Cl<Int>> p = quickImportPair(entry);
        S snippetID = p.a;
        Cl<Int> positions = p.b;
        S text = data.get(snippetID);
        continue if l(text) > maxTextLength;
        int n = 0;
        if (positions == null)
          n = countOccurrences(text, query);
        else
          for (int i : positions)
            if (regionMatches(text, i, query, 0, l(query)))
              ++n;
            else
              ++badPres;
        bool found = n > 0;
        if (found) {
          S title = titles.get(snippetID);
          new SearchResult r;
          r.snippetID = snippetID;
          r.title = title;
          r.occurrences = n;
          out.add(r);
          if (l(out) >= maxResults) break;
        }
      }
    }
    //sortInPlaceByCalculatedFieldDesc(out, r -> r.occurrences);
    nanos = max(nanoTime()-nanos, 0);
    if (setStatus) {
      print("Bad pres: " + badPres);
      setField(status := empty(query) ? " " : "Found " + addPlusToCount(maxResults, l(out), nSnippets(out) + " in "
        + formatDouble(nanoSecondsToMilliseconds(nanos1), 3)
        + " / " + formatDouble(nanoSecondsToMilliseconds(nanos), 3)
        + " ms"));
    }
    ret out;
  }
}

Began life as a copy of #1029035