From 1fc0ac1eb0dccf4c9fe28cf2cab0159b1f4591ca Mon Sep 17 00:00:00 2001
From: tallison <tallison@apache.org>
Date: Thu, 14 Nov 2024 13:58:59 -0500
Subject: [PATCH] improve serialization

(cherry picked from commit 3a8990d4d6a25f359962ce8a1a8b5e5d22486a93)
---
 .../java/org/apache/tika/parser/ocr/TesseractOCRConfig.java    | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRConfig.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRConfig.java
index ec021643cf..f802b26f5f 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRConfig.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRConfig.java
@@ -199,6 +199,9 @@ public String getPageSeparator() {
      * @param pageSeparator
      */
     public void setPageSeparator(String pageSeparator) {
+        if (pageSeparator.isBlank()) {
+            return;
+        }
         Matcher m = ALLOWABLE_PAGE_SEPARATORS_PATTERN.matcher(pageSeparator);
         if (!m.find()) {
             throw new IllegalArgumentException(pageSeparator + " contains illegal characters.\n" +