Väärin tulkittuja yhdyssanoja

Johdanto

Tällä sivulla on sanoja, jotka on jaettu yhdyssanoiksi eri tavalla kuin yleensä.

Kaksi sanaa yhdestä

Kolme sanaa yhdestä

Kaksi sanaa kahdesta

Kolme sanaa kahdesta

Neljä sanaa kahdesta

Ohjelma

Python-ohjelma, jolla sanat on etsitty. Vaatii sanalistat täältä.

MIN_WORD_LEN = 2

# no nouns or verbs; no acronyms either
EXCLUDE_WORDS = frozenset((
    "aa", "ah", "ai", "ani", "asti", "au", "av",
    "di",
    "eli",
    "ha", "haa", "hah", "he", "hei", "hi", "hoi", "hui", "hus", "hä", "hän",
    "in",
    "ja", "jee", "jo", "jos", "juu",
    "kai", "kait", "kap", "kas", "kii", "kis", "kop",
    "lainen",
    "ma", "mainen", "maisesti", "maisuus", "mar", "me", "mi", "moinen", "mut", "mä",
    "ne", "no", "noi", "noin", "nuo",
    "oh", "oi", "op", "ota",
    "pas", "per", "pois", "puh", "pus", "pöh",
    "ry",
    "sa", "se", "sen", "so", "soo", "sun", "sus", "sä",
    "taa", "tai", "te", "toi", "tse", "tuut", "tä", "tämä", "tää",
    "ula", "ups",
    "vai", "vau", "vek", "via", "vip", "viuh",
    "yh", "yht",
))

def get_words(filename):
    with open(filename, "rt", encoding="utf8") as handle:
        handle.seek(0)
        for line in handle:
            line = line.rstrip()
            if line:
                yield line

def split_in_two(word):
    # generate tuples of two strings
    for i in range(MIN_WORD_LEN, len(word) - MIN_WORD_LEN + 1):
        yield (word[:i], word[i:])

def split_in_three(word):
    # generate tuples of three strings
    for i in range(MIN_WORD_LEN, len(word) - MIN_WORD_LEN * 2 + 1):
        for j in range(i + MIN_WORD_LEN, len(word) - MIN_WORD_LEN + 1):
            yield (word[:i], word[i:j], word[j:])

def split_in_four(word):
    # generate tuples of four strings
    for i in range(MIN_WORD_LEN, len(word) - MIN_WORD_LEN * 3 + 1):
        for j in range(i + MIN_WORD_LEN, len(word) - MIN_WORD_LEN * 2 + 1):
            for k in range(j + MIN_WORD_LEN, len(word) - MIN_WORD_LEN + 1):
                yield (word[:i], word[i:j], word[j:k], word[k:])

def split_word(word, partCnt):
    if partCnt == 2:
        yield from split_in_two(word)
    elif partCnt == 3:
        yield from split_in_three(word)
    elif partCnt == 4:
        yield from split_in_four(word)
    else:
        sys.exit("Can only split in 2-4 parts.")

def main():
    allWords  = set(get_words("plaintext.txt")) - EXCLUDE_WORDS
    singles   = set(get_words("singles.txt"))   & allWords
    finals    = set(get_words("finals.txt"))    - EXCLUDE_WORDS
    nonfinals = set(get_words("nonfinals.txt")) - EXCLUDE_WORDS
    compounds = set(get_words("compounds.txt"))

    wordOrder = sorted(singles)
    for partCnt in range(2, 4 + 1):
        print(f"*** Non-compounds into {partCnt} parts ***")
        for word in wordOrder:
            for parts in split_word(word, partCnt):
                if (
                    all(p in singles or p in nonfinals for p in parts[:-1])
                    and (parts[-1] in singles or parts[-1] in finals)
                ):
                    print(f"{word:17}" + " = " + "-".join(parts))
        print()

    for srcPartCnt in range(2, 9 + 1):
        wordOrder = sorted(w for w in compounds if w.count("_") == srcPartCnt - 1)
        for dstPartCnt in range(2, 4 + 1):
            print(f"*** {srcPartCnt}-part compounds into {dstPartCnt} parts ***")
            for word in wordOrder:
                origWord = word.replace("_", "")
                for parts in split_word(origWord, dstPartCnt):
                    if (
                        all(p in singles or p in nonfinals for p in parts[:-1])
                        and (parts[-1] in singles or parts[-1] in finals)
                        and set(parts).isdisjoint(set(word.split("_")))
                    ):
                        print(f"{origWord:25}" + " = " + "-".join(parts))
            print()

main()