pdf: ocr: small fixes, plus make pdfocr redefinable in subdirs

tests/config/recoll.conf

@@ -37,6 +37,9 @@ daemSkippedPaths =  \
     /home/dockes/projets/fulltext/testrecoll/config
 
 pdfextrameta = pdf:Producer dc:identifier
+[/home/dockes/projets/fulltext/testrecoll/pdf]
+pdfocr = 1
+pdfocrlang = eng
 
 unac_except_trans = åå Åå ää Ää öö Öö üü Üü ßss œoe Œoe æae ÆAE fifi flfl
 

tests/pdf/pdf.sh

@@ -12,6 +12,8 @@ initvariables $0
     # url is prefixed for the dc:identifier search to work
     recollq dc:identifier:10.12345/sampledoi
     recollq 'pdf:Producer:"GPL Ghostscript 9.18"'
+    recollq '"bubbleupnp server to simulate openhome"'
+    
 )  2> $mystderr | egrep -v '^Recoll query: ' > $mystdout
 
 diff -w ${myname}.txt $mystdout > $mydiffs 2>&1

tests/pdf/pdf.txt

@@ -1,3 +1,9 @@
-2 results 
+2 results
 application/pdf	[file:///home/dockes/projets/fulltext/testrecoll/pdf/ThinkingInPostScript.pdf]	[Thinking In PostScript]	846435	bytes	
 application/pdf	[file:///home/dockes/projets/fulltext/testrecoll/pdf/linux unicode.pdf]	[developerWorks: Linux | Unicode : Linux Unicode programming]	72669	bytes	
+1 results
+application/pdf	[10.12345/sampledoi]	[How to edit a recoll python script in order to extract data]	6426	bytes	
+1 results
+application/pdf	[10.12345/sampledoi]	[How to edit a recoll python script in order to extract data]	6426	bytes	
+1 results
+application/pdf	[file:///home/dockes/projets/fulltext/testrecoll/pdf/pdf-tesseract.pdf]	[pdf-tesseract.pdf]	226331	bytes