ApplicationSettings: app_name: "Neahttadigisánit" app_meta_title: "Neahttadigisánit" short_name: "vada" default_locale: "yrk" default_pair: ["yrk", "fin"] mobile_default_pair: false locales_available: - yrk - fi - en meta_description: > Free online, mobile friendly dictionaries for Nenets meta_keywords: > nenets, nenetsi, mobile, dictionary, free, russian admins_to_email: - "rueter.jack@gmail.com" - "trond.trosterud@uit.no" Tools: xfst_lookup: &LOOKUP '/usr/bin/lookup' opt: &OPT '/opt/smi/' Morphology: yrk: tool: *LOOKUP file: [*OPT, '/yrk/bin/analyser-dict-gt-desc.xfst'] inverse_file: [*OPT, '/yrk/bin/generator-dict-gt-norm.xfst'] format: 'xfst' options: compoundBoundary: "+Use/Circ#" derivationMarker: "+Der" tagsep: '+' inverse_tagsep: '+' fin: tool: *LOOKUP file: [*OPT, '/fin/bin/analyser-dict-gt-desc.xfst'] inverse_file: [*OPT, '/fin/bin/generator-dict-gt-norm.xfst'] format: 'xfst' options: compoundBoundary: "+Use/Circ#" derivationMarker: "+Der" tagsep: '+' inverse_tagsep: '+' Languages: - iso: yrk minority_lang: true - iso: eng - iso: fin - iso: rus Dictionaries: - source: yrk target: eng path: 'dicts/yrk-all.xml' - source: yrk target: fin path: 'dicts/yrk-all.xml' - source: fin target: yrk path: 'dicts/finyrk.xml' ReaderConfig: yrk: multiword_lookups: false # multiword_list: # # File format-- plain text, but line coments allowed: # # Use %WORD% as a marker for any word these may co-occur with, i.e., if # # the user clicks on a %WORD%, then search for these environments too. # file: "configs/language_specific_rules/reader/hdn_multiwords.txt" # NB: this is JavaScript format, since it will be sent to the reader via # config. It must also be stored as a string. # # JavaScript is problematic with unicode, and \w in a regex ends up meaning # just the ASCII range, thus it's necessary to be very explicit. # # Also this example shows how to include periods and apostrophes in # word unit detection. # # http://regexpal.com/ # # apostrophes don't yet want to work on a word boundary, but also # http://nvinder.ru/rubric/yalumd uses different characters. word_regex: | [\u00C0-\u1FFF\u2C00-\uD7FF\w\"\'’’]+ word_regex_opts: "g"