Skip to content

Commit

Permalink
'#1182: add tesseract lang dict for French, update config comment & test
Browse files Browse the repository at this point in the history
  • Loading branch information
lfcnassif committed May 15, 2024
1 parent f3dbf36 commit fef3474
Show file tree
Hide file tree
Showing 3 changed files with 3 additions and 3 deletions.
2 changes: 1 addition & 1 deletion iped-app/pom.xml
Original file line number Diff line number Diff line change
Expand Up @@ -315,7 +315,7 @@
<artifactItem>
<groupId>tesseract</groupId>
<artifactId>tesseract-zip</artifactId>
<version>5.3.2-24-g3922</version>
<version>5.3.2-24-g3922_1</version>
<type>zip</type>
<overWrite>false</overWrite>
<outputDirectory>${tools.dir}</outputDirectory>
Expand Down
2 changes: 1 addition & 1 deletion iped-app/resources/config/conf/OCRConfig.txt
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
# You can use the parameter -ocr "bookmark_name" to restrict the OCR to a specific bookmark (just works when creating reports from cmd line).

# Dictionary language to be used for OCR. You can specify multiple languages e.g. por+eng but you will pay an important processing cost.
# Languages supported: eng, por, ita, deu, spa
# Languages supported: eng, por, ita, deu, spa, fra
OCRLanguage = por

# Skip known files found in the hash lookup database.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ public class OCRParserTest {
@BeforeClass
public static void setUpTool() throws IOException {
if (osName.startsWith("windows")) {
String repoPath = "tesseract/tesseract-zip/5.3.2-24-g3922/tesseract-zip-5.3.2-24-g3922.zip";
String repoPath = "tesseract/tesseract-zip/5.3.2-24-g3922_1/tesseract-zip-5.3.2-24-g3922_1.zip";
RepoToolDownloader.unzipFromUrl(repoPath, testRoot + "/tmp_tools/");
System.setProperty(OCRParser.TOOL_PATH_PROP, testRoot + "/tmp_tools/tesseract/");
}
Expand Down

0 comments on commit fef3474

Please sign in to comment.