2015-06-09 13:01:42 +02:00
|
|
|
#----------------------------
|
|
|
|
# Concordia configuration file
|
|
|
|
#---------------------------
|
|
|
|
#
|
|
|
|
# File containing all html tags (one per line)
|
2017-04-28 13:49:30 +02:00
|
|
|
html_tags_path = "@RESOURCES_DIRECTORY@/tokenizer/html_tags.txt"
|
2015-06-09 13:01:42 +02:00
|
|
|
|
|
|
|
# File containing all symbols to be replaced by spaces
|
2017-04-28 13:49:30 +02:00
|
|
|
space_symbols_path = "@RESOURCES_DIRECTORY@/tokenizer/space_symbols.txt"
|
2015-06-09 13:01:42 +02:00
|
|
|
|
|
|
|
# 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
|
2017-04-28 13:49:30 +02:00
|
|
|
#stop_words_path = "@RESOURCES_DIRECTORY@/tokenizer/stop_words.txt"
|
2015-06-09 13:01:42 +02:00
|
|
|
|
|
|
|
# File containing regular expressions that match named entities
|
2017-04-28 13:49:30 +02:00
|
|
|
named_entities_path = "@RESOURCES_DIRECTORY@/tokenizer/named_entities.txt"
|
2015-06-09 13:01:42 +02:00
|
|
|
|
|
|
|
# File containing special symbols (one per line) to be removed
|
2017-04-28 13:49:30 +02:00
|
|
|
stop_symbols_path = "@RESOURCES_DIRECTORY@/tokenizer/stop_symbols.txt"
|
2015-06-09 13:01:42 +02:00
|
|
|
|
|
|
|
### eof
|