yetangitu/recoll
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

describe new pdf handler configuration parameters + other comments

Browse source
This commit is contained in:
Jean-Francois Dockes 2016-04-11 13:56:22 +02:00
parent 7c177c5576
commit a077f4a10e
1 changed files with 21 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

27
src/sampleconf/recoll.conf
View file

@ -66,10 +66,15 @@ noContentSuffixes = .md5 .map \
loglevel = 3
logfilename = stderr
# The following can be used to set different values for logging by the
# indexer (recollindex). The default is to use loglevel/logfilename
#idxloglevel = 3
#idxlogfilename = stderr
# Specific versions of log file name and level for the indexing daemon. The
# default is to use the above values.
# daemloglevel = 3
# daemlogfilename = /dev/null
# default is to use the idx... values if set, else the log... values.
#daemloglevel = 3
#daemlogfilename = /dev/null
# Run directory for the indexing process. The filters sometimes leave
# garbage in the current directory, so it makes sense to have recollindex
@ -383,15 +388,25 @@ snippetMaxPosWalk = 1000000
# undetected). Perform a full index reset after changing this.
testmodifusemtime = 0
# Disable extended attributes conversion to metadata fields. This probably
# needs to be set if testmodifusemtime is set.
noxattrfields = 0
# Script used to heuristically check if we need to retry indexing files
# which previously failed. The default script checks the modified dates on
# /usr/bin and /usr/local/bin. A relative path will be looked up in the
# filters dirs, then in the path. Use an absolute path to do otherwise.
checkneedretryindexscript = rclcheckneedretry.sh
# Disable extended attributes conversion to metadata fields. This probably
# needs to be set if testmodifusemtime is set.
noxattrfields = 0
# Parameters for the PDF input script
# Attempt OCR of PDF files with no text content if both tesseract and
# pdftoppm are installed. The default is not to do it because OCR is so
# very slow
#pdfocr = 0
# Enable PDF attachment extraction, using pdftk (if available). This is
# normally disabled, because it does slow down PDF indexing a bit even if
# not one attachment is ever found.
#pdfattach = 0
# You could specify different parameters for a subdirectory like this:
#[~/hungariandocs/plain]