From 94d0f77f56bb9123c4c33c97125e76e7bdb73159 Mon Sep 17 00:00:00 2001
From: Stefan Weil <sw@weilnetz.de>
Date: Fri, 1 Nov 2019 21:43:26 +0100
Subject: [PATCH] Don't create an empty lstmf file

If Tesseract cannot find text in the input image, it should not write
an empty lstmf file. This problem was reported in issue #2741.

Signed-off-by: Stefan Weil <sw@weilnetz.de>
---
 src/ccmain/linerec.cpp | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/src/ccmain/linerec.cpp b/src/ccmain/linerec.cpp
index 7c01590cc4..0f4599dd1b 100644
--- a/src/ccmain/linerec.cpp
+++ b/src/ccmain/linerec.cpp
@@ -61,6 +61,10 @@ void Tesseract::TrainLineRecognizer(const STRING& input_imagename,
     return;
   }
   TrainFromBoxes(boxes, texts, block_list, &images);
+  if (images.NumPages() <= 0) {
+    tprintf("Failed to read pages from %s\n", input_imagename.c_str());
+    return;
+  }
   images.Shuffle();
   if (!images.SaveDocument(lstmf_name.c_str(), nullptr)) {
     tprintf("Failed to write training data to %s!\n", lstmf_name.c_str());