rclpdf: restore pdfextrametafix function and add test

This commit is contained in:
Jean-Francois Dockes
2019-09-04 09:38:11 +02:00
parent c1d593b104
commit 2e801812fe
4 changed files with 56 additions and 9 deletions
+23
View File
@@ -0,0 +1,23 @@
import sys
import re
class MetaFixer(object):
def __init__(self):
pass
def metafix(self, nm, txt):
#print("Metafixer: mfix: nm [%s] txt [%s]" % (nm, txt), file=sys.stderr)
if nm == 'pdf:Producer':
txt += " metafixerunique"
elif nm == 'someothername':
# do something else
pass
elif nm == 'stillanother':
# etc.
pass
return txt
def wrapup(self, metaheaders):
#print("Metafixer: wrapup: %s" % metaheaders, file=sys.stderr)
pass
+2
View File
@@ -39,6 +39,8 @@ daemSkippedPaths = \
unac_except_trans = åå Åå ää Ää öö Öö üü Üü ßss œoe Œoe æae ÆAE fifi flfl
pdfextrameta = pdf:Producer dc:identifier
pdfextrametafix = /home/dockes/projets/fulltext/recoll/tests/config/pdfemf.py
[/home/dockes/projets/fulltext/testrecoll/pdf]
pdfocr = 1
pdfocrlang = eng
+1 -1
View File
@@ -11,7 +11,7 @@ initvariables $0
# defaults field file, and this can't be overruled afaics, so
# url is prefixed for the dc:identifier search to work
recollq dc:identifier:10.12345/sampledoi
recollq 'pdf:Producer:"GPL Ghostscript 9.18"'
recollq 'pdf:Producer:"GPL Ghostscript 9.18" metafixerunique'
recollq '"bubbleupnp server to simulate openhome"'
) 2> $mystderr | egrep -v '^Recoll query: ' > $mystdout