Not logged in.  Login/Logout/Register | List snippets | | Create snippet | Upload image | Upload data

70
LINES

< > BotCompany Repo | #1029009 // Instant Full-Text Snippet Search v3 [using double word index, skips texts > 100k chars]

JavaX source code (Dynamic Module) [tags: use-pretranspiled] - run with: Stefan's OS

Uses 911K of libraries. Click here for Pure Java version (8609L/43K).

1  
!7
2  
3  
sclass SearchResult {
4  
  S snippetID;
5  
  S title;
6  
  int occurrences;
7  
  
8  
  sS _fieldOrder = "snippetID title occurrences";
9  
}
10  
11  
cmodule FullTextSnippetSearch > DynTableWithInput2<SearchResult> {
12  
  switchable int maxResults = 1000;
13  
  switchable int maxTextLength = 100000;
14  
  transient S status;
15  
  
16  
  JComponent mainComponent() {
17  
    ret northAndCenterWithMargin(dm_rightAlignedLabel status(), super.mainComponent());
18  
  }
19  
  
20  
  start {
21  
    dontPersist();
22  
    thread { warmUp(); }
23  
  }
24  
  
25  
  void calc {
26  
    setList(search(input, true));
27  
  }
28  
  
29  
  void warmUp enter {
30  
    benchFor5Seconds(r { hijackPrint(r { search("this is cool", false) }) });
31  
  }
32  
  
33  
  L<SearchResult> search(S input, bool setStatus) {
34  
    S query = upper(input);
35  
    S index = dm_require("#1029008/SnippetsDoubleWordIndex");
36  
    Cl<S> preSnippetIDs = cast dm_call(index, 'snippetsContainingTextIC_preSearch, query);
37  
    print("Pre-search: " + (preSnippetIDs == null ? "-" : lstr(preSnippetIDs)));
38  
    
39  
    S mod = dm_require("#1028945/CacheAllSnippets");
40  
    SS data = cast dm_rcall getData(mod);
41  
    SS titles = cast dm_rcall getTitles(mod);
42  
    new L<SearchResult> out;
43  
    if (preSnippetIDs == null) preSnippetIDs = keys(data);
44  
    long nanos = 0;
45  
    if (nempty(query)) {
46  
      nanos = nanoTime();
47  
      fOr ping (S snippetID : preSnippetIDs) {
48  
        S text = data.get(snippetID);
49  
        continue if l(text) > maxTextLength;
50  
        S title = titles.get(snippetID);
51  
        int n = 
52  
          countOccurrencesIC(title, query)
53  
          + countOccurrences_optimizedForZero(text, query);
54  
        if (n > 0) {
55  
          new SearchResult r;
56  
          r.snippetID = snippetID;
57  
          r.title = title;
58  
          r.occurrences = n;
59  
          out.add(r);
60  
          if (l(out) >= maxResults) break;
61  
        }
62  
      }
63  
      nanos = max(nanoTime()-nanos, 0);
64  
    }
65  
    sortInPlaceByCalculatedFieldDesc(out, r -> r.occurrences);
66  
    if (setStatus)
67  
      setField(status := empty(query) ? " " : "Found " + addPlusToCount(maxResults, l(out), nSnippets(out) + " in " + formatDouble(nanoSecondsToMilliseconds(nanos), 3) + " ms"));
68  
    ret out;
69  
  }
70  
}

Author comment

Began life as a copy of #1028975

download  show line numbers  debug dex  old transpilations   

Travelled to 7 computer(s): bhatertpkbcr, mqqgnosmbjvj, pyentgdyhuwx, pzhvpgtvlbxg, tvejysmllsmz, vouqrxazstgt, xrpafgyirdlv

No comments. add comment

Snippet ID: #1029009
Snippet name: Instant Full-Text Snippet Search v3 [using double word index, skips texts > 100k chars]
Eternal ID of this version: #1029009/6
Text MD5: b4b2ab5bd7c9eaeb7867748ddc76140b
Transpilation MD5: 521202e26db77912e06bcb5a02d76ad4
Author: stefan
Category: javax
Type: JavaX source code (Dynamic Module)
Public (visible to everyone): Yes
Archived (hidden from active list): No
Created/modified: 2020-07-16 19:31:32
Source code size: 2176 bytes / 70 lines
Pitched / IR pitched: No / No
Views / Downloads: 210 / 310
Version history: 5 change(s)
Referenced in: [show references]