字串處理技術與演算法實作

def Champernowne_Word(n):
    d = 0
    p_i = 0
    p_n = 0
    w = 9
    while n >= p_i + w * (d + 1):
        p_i += w * (d + 1)
        d += 1
        p_n += w
        w *= 10
    p = (n - p_i) // (d + 1)
    num = p_n + p + 1
    return str(num)[(n - p_i) % (d + 1)]

def combine_strings_into_one(first_word, second_word):
    vowels = 'aeiou'
    
    # 提取 first_word 中的連續母音索引
    first_vowel_groups = []
    for i in range(len(first_word)):
        if first_word[i] in vowels:
            if i > 0 and first_word[i-1] in vowels:
                first_vowel_groups[-1].append(i)
            else:
                first_vowel_groups.append([i])
                
    # 提取 second_word 中的連續母音索引
    second_vowel_groups = []
    for i in range(len(second_word)):
        if second_word[i] in vowels:
            if i > 0 and second_word[i-1] in vowels:
                second_vowel_groups[-1].append(i)
            else:
                second_vowel_groups.append([i])
    
    # 決定 first_word 的保留部分
    if len(first_vowel_groups) == 0:
        fw_segment = first_word
    elif len(first_vowel_groups) == 1:
        fw_segment = first_word[:first_vowel_groups[0][0]]
    else:
        fw_segment = first_word[:first_vowel_groups[-2][0]]
        
    # 決定 second_word 的保留部分，從第一個母音開始
    sw_segment = second_word[second_vowel_groups[0][0]:]
    
    return fw_segment + sw_segment

def keyword_distance():
    # 定義 QWERTY 鍵盤佈局
    top = {c: (0, i) for (i, c) in enumerate("qwertyuiop")}
    mid = {c: (1, i) for (i, c) in enumerate("asdfghjkl")}
    bot = {c: (2, i) for (i, c) in enumerate("zxcvbnm")}
    keys = {**top, **mid, **bot}
    dist = {}
    lows = "abcdefghijklmnopqrstuvwxyz"
    
    # 計算任意兩個字母之間的距離
    for cc1 in lows:
        for cc2 in lows:
            (r1, c1) = keys[cc1]
            (r2, c2) = keys[cc2]
            dist[(cc1, cc2)] = (abs(r2 - r1) + abs(c2 - c1)) ** 2
    return dist

dist = keyword_distance()

def ds(c1, c2):
    # 傳回兩個字母之間的預先計算距離
    return dist[(c1, c2)]

def autocorrect_word(words, word):
    # 提取與輸入單字長度相同的單字
    dists = {x.strip(): 0 for x in words if len(x) == len(word)}
    
    for w in dists.keys():
        storage = []
        for i in range(len(word)):
            # 計算當前單字與輸入單字之間的距離
            storage.append(ds(w[i], word[i]))
        dists[w] = sum(storage)
    
    # 傳回距離最小的單字
    return min(dists, key=dists.get)

def correct_verb_form_in_spanish(verb, subject, tense):
    di = {}
    
    if verb[-2:] == 'ar':
        if tense == 'presente':
            di = {
                'yo': 'o', 'tú': 'as', 'él': 'a', 'ella': 'a', 'usted': 'a',
                'nosotros': 'amos', 'nosotras': 'amos', 'vosotros': 'áis', 'vosotras': 'áis',
                'ellos': 'an', 'ellas': 'an', 'ustedes': 'an'
            }
        elif tense == 'pretérito':
            di = {
                'yo': 'é', 'tú': 'aste', 'él': 'ó', 'ella': 'ó', 'usted': 'ó',
                'nosotros': 'amos', 'nosotras': 'amos', 'vosotros': 'asteis', 'vosotras': 'asteis',
                'ellos': 'aron', 'ellas': 'aron', 'ustedes': 'aron'
            }
        elif tense == 'imperfecto':
            di = {
                'yo': 'aba', 'tú': 'abas', # ... 其他主語對應的字尾
            }
    
    # 根據主語傳回正確的動詞形式
    return verb[:-2] + di.get(subject, '')

def spanish_verb_conjugation(verb, tense, subject):
    if verb[-2:] == 'ar':
        if tense == 'presente':
            di = {'yo': 'o', 'tú': 'as', 'él': 'a', 'ella': 'a', 'usted': 'a',
                  'nosotros': 'amos', 'nosotras': 'amos', 'vosotros': 'áis',
                  'vosotras': 'áis', 'ellos': 'an', 'ellas': 'an', 'ustedes': 'an'}
        elif tense == 'pretérito':
            di = {'yo': 'é', 'tú': 'aste', 'él': 'ó', 'ella': 'ó', 'usted': 'ó',
                  'nosotros': 'amos', 'nosotras': 'amos', 'vosotros': 'asteis',
                  'vosotras': 'asteis', 'ellos': 'aron', 'ellas': 'aron', 'ustedes': 'aron'}
        elif tense == 'imperfecto':
            di = {'yo': 'aba', 'tú': 'abas', 'él': 'aba', 'ella': 'aba', 'usted': 'aba',
                  'nosotros': 'ábamos', 'nosotras': 'ábamos', 'vosotros': 'abais',
                  'vosotras': 'abais', 'ellos': 'aban', 'ellas': 'aban', 'ustedes': 'aban'}
        elif tense == 'futuro':
            di = {'yo': 'é', 'tú': 'ás', 'él': 'á', 'ella': 'á', 'usted': 'á',
                  'nosotros': 'emos', '-nosotras': 'emos', '-vosotros': '-éis',
                  '-vosotras': '-éis', '-ellos': '-án', '-ellas': '-án', '-ustedes': '-án'}
            return verb + di[subject]
        return verb[:-2] + di[subject]

    elif verb[-2:] == 'er':
        # 類別似的邏輯適用於 -er 動詞
        pass

    elif verb[-2:] == 'ir':
        # 類別似的邏輯適用於 -ir 動詞
        pass

def subsequent_letters(words, letters):
    len_let = len(letters)
    ST = []
    for term in words:
        if len(term) >= len_let:
            indterm = list(term)
            counter = 0
            CurrentIndex = -1
            for let in letters:
                if let in indterm[CurrentIndex+1:]:
                    indexlet = indterm.index(let, CurrentIndex+1)
                    CurrentIndex = indexlet
                    counter += 1
            if counter == len_let:
                ST.append(term)
    return ST