From f6cfcf783b55cc0a206d9436799acf81116fbb46 Mon Sep 17 00:00:00 2001
From: Diego Pino Navarro <DiegoPino@users.noreply.github.com>
Date: Sun, 28 Nov 2021 17:03:55 -0500
Subject: [PATCH] Fixes OCR Highlight 0.7 dislike for empty <w> tags

---
 .../OcrPostProcessor.php                        | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/src/Plugin/StrawberryRunnersPostProcessor/OcrPostProcessor.php b/src/Plugin/StrawberryRunnersPostProcessor/OcrPostProcessor.php
index 4bf8a30..84ed48f 100644
--- a/src/Plugin/StrawberryRunnersPostProcessor/OcrPostProcessor.php
+++ b/src/Plugin/StrawberryRunnersPostProcessor/OcrPostProcessor.php
@@ -573,13 +573,16 @@ protected function hOCRtoMiniOCR($output, $pageid) {
                 $miniocr->text(' ');
               }
               $notFirstWord = TRUE;
-              $miniocr->startElement("w");
-              $miniocr->writeAttribute("x", $l . ' ' . $t . ' ' . $w . ' ' . $h);
-              $miniocr->text($text);
-              // Only assume we have at least one word for <w> tags
-              // Since lines? could end empty?
-              $atleastone_word = TRUE;
-              $miniocr->endElement();
+              // New OCR Highlight does not like empty <w> tags at all
+              if (strlen(trim($text)) > 0) {
+                $miniocr->startElement("w");
+                $miniocr->writeAttribute("x", $l . ' ' . $t . ' ' . $w . ' ' . $h);
+                $miniocr->text($text);
+                // Only assume we have at least one word for <w> tags
+                // Since lines? could end empty?
+                $atleastone_word = TRUE;
+                $miniocr->endElement();
+              }
             }
           }
           $miniocr->endElement();