texts_details.py

# Basic info about the text that should be processed

input_texts_details = [
    {
        "input_filename": "ludove_rozpravky.txt",
        "full_name": "Pavol Dobsinsky - Ludove rozpravky",
        "output_prefix_name": "dobsinsky_ludove_rozpravky",
        "language": "sk"
    },
    {
        "input_filename": "krasa_obycajnosti.txt",
        "full_name": "Palea Ulla - Krasa Obycajnosti",
        "output_prefix_name": "ulla_krasa_obycajnosti",
        "language": "sk"
    },
    {
        "input_filename": "essentia_mortem.txt",
        "full_name": "Peter Stec - Esentia Mortem",
        "output_prefix_name": "stec_essentia_mortem",
        "language": "sk"
    },
    {
        "input_filename": "uvod_do_klinickej_psychologie.txt",
        "full_name": "Monika Hricova - Uvod do klinickej psychologie",
        "output_prefix_name": "hricova_uvod_do_klinickej_psychologie",
        "language": "sk"
    },
    {
        "input_filename": "deti_vyhorlatu.txt",
        "full_name": "Brandon McYntire - Deti Vyhorlatu",
        "output_prefix_name": "mcyntire_deti_vyhorlatu",
        "language": "sk"
    },
    {
        "input_filename": "vedecka_komunikacia_manazment_vyskumnych_udajov.txt",
        "full_name": "Vedecka komunikacia a manazment vyskumnych udajov",
        "output_prefix_name": "vedecka_komunikacia_manazment_vyskumnych_udajov",
        "language": "sk"
    },
    {
        "input_filename": "never_the_twain_shall_meet.txt",
        "full_name": "Peter B. Kyne - Never the twain shall meet",
        "output_prefix_name": "never_the_twain_shall_meet",
        "language": "en"
    },
    {
        "input_filename": "on_the_origin_of_species.txt",
        "full_name": "Charles Darwin - On the origin of species",
        "output_prefix_name": "on_the_origin_of_species",
        "language": "en"
    },
    {
        "input_filename": "together.txt",
        "full_name": "Norman Douglas - Together",
        "output_prefix_name": "together",
        "language": "en"
    },
    {
        "input_filename": "oliver_october.txt",
        "full_name": "George Barr McCutcheon - Oliver October",
        "output_prefix_name": "oliver_october",
        "language": "en"
    },
    {
        "input_filename": "corpus_slk.txt",
        "full_name": "Korpus textov Ministerstva kultúry Slovenskej republiky",
        "output_prefix_name": "corpus_slk",
        "language": "sk"
    },
    {
        "input_filename": "collection_historicky_casopis.txt",
        "full_name": "Kolekcia volnepristupnych clankov z castopisu Historicky casopis",
        "output_prefix_name": "collection_historicky_casopis",
        "language": "sk"
    },
    {
        "input_filename": "collection_UPJS_free_books.txt",
        "full_name": "Kolekcia volnepristupnych knih z kniznice UPJS.",
        "output_prefix_name": "collection_UPJS_free_books",
        "language": "sk"
    },
    # this is not free book, so though I own it and analysed it, I can't push any part of it to github
    # {
    #     "input_filename": "obycajne_zazraky.txt",
    #     "full_name": "Samuel Kovacik - Obycajne Zazraky.",
    #     "output_prefix_name": "obycajne_zazraky",
    #     "language": "sk"
    # },
    {
        "input_filename": "dom_v_strani.txt",
        "full_name": "M. Kukucin - Dom v strani",
        "output_prefix_name": "dom_v_strani",
        "language": "sk"
    },
]