TheAnachronism/docspell
1
0
Fork 0
mirror of https://github.com/TheAnachronism/docspell.git synced 2025-06-22 02:18:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make the text length limit optional

Browse Source
This commit is contained in:
Eike Kettner
2021-01-22 22:56:51 +01:00
parent 8dd1672c8c
commit c7e850116f
5 changed files with 35 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
modules/joex/src/main/resources/reference.conf
View File

@ -269,9 +269,13 @@ docspell.joex {
# All text to analyse must fit into RAM. A large document may take
# too much heap. Also, most important information is at the
# beginning of a document, so in most cases the first two pages
# should suffice. Default is 8000, which are about 2-3 pages (just
# a rough guess, of course).
max-length = 8000
# should suffice. Default is 5000, which are about 2 pages (just a
# rough guess, of course). For my data, more than 80% of the
# documents are less than 5000 characters.
#
# This values applies to nlp and the classifier. If this value is
# <= 0, the limit is disabled.
max-length = 5000
# A working directory for the analyser to store temporary/working
# files.
@ -363,6 +367,10 @@ docspell.joex {
# If concerned with memory consumption, this restricts the
# number of items to consider. More are better for training. A
# negative value or zero means to train on all items.
#
# This limit and `text-analysis.max-length` define how much
# memory is required. On weaker hardware, it is advised to play
# with these values.
item-count = 600
# These settings are used to configure the classifier. If