Uses 911K of libraries. Click here for Pure Java version (8609L/43K).
!7 sclass SearchResult { S snippetID; S title; int occurrences; sS _fieldOrder = "snippetID title occurrences"; } 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 query = upper(input); S index = dm_require("#1029008/SnippetsDoubleWordIndex"); Cl<S> preSnippetIDs = cast dm_call(index, 'snippetsContainingTextIC_preSearch, query); print("Pre-search: " + (preSnippetIDs == null ? "-" : lstr(preSnippetIDs))); S mod = dm_require("#1028945/CacheAllSnippets"); SS data = cast dm_rcall getData(mod); SS titles = cast dm_rcall getTitles(mod); new L<SearchResult> out; if (preSnippetIDs == null) preSnippetIDs = keys(data); long nanos = 0; if (nempty(query)) { nanos = nanoTime(); fOr ping (S snippetID : preSnippetIDs) { S text = data.get(snippetID); continue if l(text) > maxTextLength; S title = titles.get(snippetID); int n = countOccurrencesIC(title, query) + countOccurrences_optimizedForZero(text, query); if (n > 0) { new SearchResult r; r.snippetID = snippetID; r.title = title; r.occurrences = n; out.add(r); if (l(out) >= maxResults) break; } } nanos = max(nanoTime()-nanos, 0); } sortInPlaceByCalculatedFieldDesc(out, r -> r.occurrences); if (setStatus) setField(status := empty(query) ? " " : "Found " + addPlusToCount(maxResults, l(out), nSnippets(out) + " in " + formatDouble(nanoSecondsToMilliseconds(nanos), 3) + " ms")); ret out; } }
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: | 211 / 310 |
Version history: | 5 change(s) |
Referenced in: | #1029014 - Instant Full-Text Snippet Search v4 [using deep double word index, OK] |