You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2018/05/25 14:44:53 UTC
[tika] 01/02: allow more flexibility for OCR variations in a
PDFParser test
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch branch_1x
in repository https://gitbox.apache.org/repos/asf/tika.git
commit ac736936126b77fe9479b8ea78e799899545cf86
Author: tballison <ta...@mitre.org>
AuthorDate: Fri May 25 10:31:21 2018 -0400
allow more flexibility for OCR variations in a PDFParser test
---
.../test/java/org/apache/tika/parser/pdf/PDFParserTest.java | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
index 537a7ff..3e4f293 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
@@ -1252,11 +1252,14 @@ public class PDFParserTest extends TikaTest {
assertContains("Needle", xmlResult.xml);
if (! strategy.equals(PDFParserConfig.OCR_STRATEGY.NO_OCR)) {
// Tesseract may see the t in haystack as a ! some times...
- String div = "<div class=\"ocr\">pdf_hays";
- if (xmlResult.xml.contains(div+"!ack")) {
- assertContains(div+"!ack", xmlResult.xml);
+ //or it might see dehayslack...
+ //TODO: figure out how to make this test less hacky
+ String div = "<div class=\"ocr\">";
+ if (xmlResult.xml.contains(div+"pdf_hays!ack")) {
+ } else if (xmlResult.xml.contains(div+"pdf_haystack")) {
+ } else if (xmlResult.xml.contains(div+"dehayslack")) {
} else {
- assertContains(div+"tack", xmlResult.xml);
+ fail("couldn't find acceptable variants of haystack");
}
} else {
assertNotContained("<div class=\"ocr\">pdf_haystack", xmlResult.xml);
--
To stop receiving notification emails like this one, please contact
tallison@apache.org.