From fe86fa9e1fd9df4203733e272697a7074c3b2fb4 Mon Sep 17 00:00:00 2001
From: Jean-Francois Dockes <jf@dockes.org>
Date: Fri, 28 Feb 2020 14:38:02 +0100
Subject: [PATCH] ocr: compat: make a non-existant ocrprogs config variable
 equivalent to "tesseract"

---
 src/filters/rclocr.py      |  6 +++++-
 src/sampleconf/recoll.conf | 11 +++++++----
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/src/filters/rclocr.py b/src/filters/rclocr.py
index 9bcb1635..40f4d26a 100755
--- a/src/filters/rclocr.py
+++ b/src/filters/rclocr.py
@@ -81,9 +81,13 @@ if incache:
 # Retrieve configured OCR program names and try to load the
 # corresponding module
 ocrprogs = config.getConfParam("ocrprogs")
+if ocrprogs is None:
+    # Compat: the previous version has no ocrprogs variable, but would do
+    # tesseract by default. Use "ocrprogs = " for a really empty list
+    ocrprogs = "tesseract"
 if not ocrprogs:
     _deb("No ocrprogs variable in recoll configuration")
-    sys.exit(1)
+    sys.exit(0)
 
 #_deb("ocrprogs: %s" % ocrprogs)
 
diff --git a/src/sampleconf/recoll.conf b/src/sampleconf/recoll.conf
index a72e1f42..32af0f6d 100644
--- a/src/sampleconf/recoll.conf
+++ b/src/sampleconf/recoll.conf
@@ -905,7 +905,7 @@ snippetMaxPosWalk = 1000000
 #
 # <brief>Attempt OCR of PDF files with no text content.</brief>
 # <descr>This can be defined in subdirectories. The default is off because
-# OCR is so very slow. Will only do anything if ocrprogs is defined.</descr>
+# OCR is so very slow.</descr>
 # </var>
 #pdfocr = 0
 
@@ -946,10 +946,13 @@ snippetMaxPosWalk = 1000000
 # <brief>OCR modules to try.</brief>
 # <descr>The top OCR script will try to load the corresponding modules in
 # order and use the first which reports being capable of performing OCR on
-# the input file. Modules for tesseract and ABBYY FineReader are present in
-# the standard distribution.</descr>
+# the input file. Modules for tesseract (tesseract) and ABBYY FineReader
+# (abbyy) are present in the standard distribution. For compatibility with
+# the previous version, if this is not defined at all, the default value is
+# "tesseract". Use an explicit empty value if needed. A value of "abbyy
+# tesseract" will try everything.</descr>
 # </var>
-#ocrprogs = abbyy tesseract
+#ocrprogs = tesseract
 
 # <var name="ocrcachedir" type="dfn">
 # <brief>Location for caching OCR data.</brief>