mstoeck3/autopsy-flatpak
1
0
Fork 0
mirror of https://github.com/overcuriousity/autopsy-flatpak.git synced 2025-07-13 00:16:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixed language pack look up to happen once at class loading

Browse Source
This commit is contained in:
U-BASIS\dsmyda 2018-12-10 16:37:55 -05:00
parent ab86d88126
commit 9d15b5f571
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
Core/src/org/sleuthkit/autopsy/textextractors/TikaTextExtractor.java
View File

@ -120,6 +120,7 @@ final class TikaTextExtractor extends TextExtractor {
private static final String TESSERACT_DIR_NAME = "Tesseract-OCR"; //NON-NLS private static final String TESSERACT_DIR_NAME = "Tesseract-OCR"; //NON-NLS
private static final String TESSERACT_EXECUTABLE = "tesseract.exe"; //NON-NLS private static final String TESSERACT_EXECUTABLE = "tesseract.exe"; //NON-NLS
private static final File TESSERACT_PATH = locateTesseractExecutable(); private static final File TESSERACT_PATH = locateTesseractExecutable();
private static final String LANGUAGE_PACKS = getLanguagePacks();
private static final List<String> TIKA_SUPPORTED_TYPES private static final List<String> TIKA_SUPPORTED_TYPES
= new Tika().getParser().getSupportedTypes(new ParseContext()) = new Tika().getParser().getSupportedTypes(new ParseContext())
@ -177,8 +178,7 @@ final class TikaTextExtractor extends TextExtractor {
ocrConfig.setTesseractPath(tesseractFolder); ocrConfig.setTesseractPath(tesseractFolder);
// Tesseract expects language data packs to be in a subdirectory of tesseractFolder, in a folder called "tessdata". // Tesseract expects language data packs to be in a subdirectory of tesseractFolder, in a folder called "tessdata".
// If they are stored somewhere else, use ocrConfig.setTessdataPath(String tessdataPath) to point to them // If they are stored somewhere else, use ocrConfig.setTessdataPath(String tessdataPath) to point to them
System.out.println(getLanguagePacks()); ocrConfig.setLanguage(LANGUAGE_PACKS);
ocrConfig.setLanguage(getLanguagePacks());
parseContext.set(TesseractOCRConfig.class, ocrConfig); parseContext.set(TesseractOCRConfig.class, ocrConfig);
} }
@ -279,7 +279,7 @@ final class TikaTextExtractor extends TextExtractor {
* *
* @return String of all language packs available for Tesseract to use * @return String of all language packs available for Tesseract to use
*/ */
private String getLanguagePacks() { private static String getLanguagePacks() {
File languagePackRootDir = new File(TESSERACT_PATH.getParent(), "tessdata"); File languagePackRootDir = new File(TESSERACT_PATH.getParent(), "tessdata");
//Acceptable extensions for Tesseract-OCR version 3.05 language packs. //Acceptable extensions for Tesseract-OCR version 3.05 language packs.
//All extensions other than traineddata are associated with cube files that //All extensions other than traineddata are associated with cube files that