config.yml

# Configuration file

# Title: contains information that helps you identify the search
title: 'My document search'

# Strategies: this section contains parameters that guide the processing of the files
strategies:
  # List your strategies here. Multiple strategies are allowed. Name your strategies as you wish!
  my_strategy_01: 
    # processed_directory: the folder where to be processed files are looked for and hopefully found
    processed_directory: '/path/to/your_directory'
    # file_selection_pattern: a regex pattern selecting the files to be processed
    file_name_pattern: 'regex_pattern_identifying_your_file in /path/to/your_directory'
    # file_format
    # currently only 'pdf', 'docx', and 'txt' are supported
    file_format: 'pdf'
    # terms
    terms:
      # Choose names for the terms and associate each with a regex pattern or, alternatively,
      # two regex patterns surrounding '@@@', which serves as a divider.
      # In the former case (i.e. only one regex pattern, no divider) matches to the regex are returned.
      # In the latter case (i.e. divider present) the one or two regex patterns are converted
      # to groups surrounding a central "match-all" (.*) pattern. Only matches to the "match-all"-group
      # are returned.
      # Further options can be appended after the string '===' (three equal signs)
      #   m   multiline           should pattern matching be performed over multiple lines? (default=off)
      #   l   linebreak to space  in case of m: should line breaks be converted to space? (default=off)
      #   c   crop to length      should length be cropped? (default=off)
      #   ?   optional term       is the term optional? (default=off, e.g. term is required)
      # The further options are given thus: e.g. "regex1@@@regex2===mlc(100)?" would mean 
      #   - multiline: yes,
      #   - linebreak to space: yes
      #   - crop to 100 characters
      #   - term is optional (i.e. not required, thus will be ignored if 'move_to_directory' is set)
      my_first_term: 'regex1'
      my_second_term: 'regex2@@@regex3'
      my_third_term: '@@@regex'
      my_fourth_term: 'regex@@@'
    # export format
    # currently, the following formats are supported: csv, xlsx, html, json
    export_format: 'xlsx'
    # export path
    export_path: '/path/to/your/file.xlsx'
    # 
    # O P T I O N A L   K E Y S
    #
    # # optional, for csv, set export_csv_divider (defaults to ;)
    # export_csv_divider: ';'
    #
    # # optional: if all *required terms* are found, optionally move to specified directory
    # move_to_directory: '/path/to/another_directory'
    #
    # # optional: file_content_pattern - a regex pattern that has to return a match in the file contents
    # # this can be used to further restrict the selection of processed files 
    # file_content_pattern: '.*'
    #