#----------------------------
# Concordia configuration file
#---------------------------
#

#-------------------------------------------------------------------------------
# The below set the paths for hashed index, markers array and word map files.
# If all the files pointed by these paths exist, Concordia reads them to its
# RAM index. When none of these files exist, a new empty index is created.
# However, if any of these files exist and any other is missing, the index
# is considered corrupt and Concordia does not start.

hashed_index_path = "@INDEX_DIRECTORY@/@HASHED_INDEX_FILE@"
markers_path = "@INDEX_DIRECTORY@/@MARKERS_FILE@"
word_map_path = "@INDEX_DIRECTORY@/@WORD_MAP_FILE@"

#-------------------------------------------------------------------------------
# The following settings control the sentence anonymizer mechanism. It is used to
# remove unnecessary symbols and possibly words from sentences added to index
# and search patterns. Anonymizer removes html tags, substitutes predefined symbols
# with a single space, removes stop words (if the option is enabled), as well as
# named entities and special symbols. All these have to be listed in files.

# File containing all html tags (one per line)
html_tags_path = "@RESOURCES_DIRECTORY@/anonymizer/html_tags.txt"

# File containing all symbols to be replaced by spaces
space_symbols_path = "@RESOURCES_DIRECTORY@/anonymizer/space_symbols.txt"

# If set to true, words from predefined list are removed
stop_words_enabled = "@STOP_WORDS_ENABLED@"

# If stop_words_enabled is true, set the path to the stop words file
#stop_words_path = "@RESOURCES_DIRECTORY@/anonymizer/stop_words.txt"

# File containing regular expressions that match named entities
named_entities_path = "@RESOURCES_DIRECTORY@/anonymizer/named_entities.txt"

# File containing special symbols (one per line) to be removed
stop_symbols_path = "@RESOURCES_DIRECTORY@/anonymizer/stop_symbols.txt"

### eof