implemented proper limitation and error reporting in case of truncation for term and query expansions

This commit is contained in:
Jean-Francois Dockes
2012-10-05 12:36:19 +02:00
parent bfd111ecaa
commit c9f6612c10
13 changed files with 217 additions and 105 deletions
+11 -12
View File
@@ -103,6 +103,17 @@ indexstemminglanguages = english
# Actually, this seems a reasonable default for all until someone protests.
unac_except_trans = åå Åå ää Ää öö Öö üü Üü ßss œoe Œoe æae ÆAE fifi flfl
# Maximum expansion count for a single term (ie: when using wildcards).
# We used to not limit this at all (except for filenames where the limit
# was too low at 1000), but it is unreasonable with a big index.
# Default 10 000
maxTermExpand = 10000
# Maximum number of clauses we add to a single Xapian query. In some cases,
# the result of term expansion can be multiplicative, and we want to avoid
# eating all the memory. Default 100 000
maxXapianClauses = 100000
# Where to store the database (directory). This may be an absolute path,
# else it is taken as relative to the configuration directory (-c argument
# or $RECOLL_CONFDIR).
@@ -132,18 +143,6 @@ filtersdir = @prefix@/share/recoll/filters
# want to change the icons displayed in the result list
iconsdir = @prefix@/share/recoll/images
# A list of characters, encoded in UTF-8, which should be handled specially
# when converting text to unaccented lowercase. For example, in Swedish,
# the letter a with diaeresis has full alphabet citizenship and should not
# be turned into an a. Each element in the space-separated list has the
# special character as first element and the translation following
# (multiple chars allowed. The handling of both the lowercase and
# upper-case versions of a character should be specified, as appartenance
# to the list will turn-off both standard accent and case
# processing. ** Changing the list implies a full reindex **
# Example for Swedish:
# unac_except_trans = åå Åå ää Ää öö Öö
# Should we use the system's 'file -i' command as a final step in file type
# identification ? This may be useful, but will usually cause the
# indexation of many bogus 'text' files