Pygame--解决中文输入问题（一）

拼音分词：

提示：解决pygame无法输入中文。

• 实现自动分词

---

拼音分词：

        (一)、建立字典树

   

class Node:
    def __init__(self):
        self.children = {}
        self.is_end_of_pinyin = False

class PinyinDictTree:
    def __init__(self):
        self.root = Node()

    def insert(self, pinyin):
        node = self.root
        for i in range(len(pinyin)):
            if pinyin[i] not in node.children:
                node.children[pinyin[i]] = Node()
            node = node.children[pinyin[i]]
        node.is_end_of_pinyin = True

    def search(self, pinyin):
        node = self.root
        for i in range(len(pinyin)):
            if pinyin[i] not in node.children:
                return False
            node = node.children[pinyin[i]]
        return node.is_end_of_pinyin

(二)、构建字典树

        将所有声母与声母后面可以拼接的韵母进行组合。

def Construction_Dictionary():
    pinyin_tree = PinyinDictTree()
    special_cases = ['ao', 'ai', 'a', 'er', 'an', 'o', 'ang']
    pinyin_dict = {
        'b':['a', 'o', 'e', 'i', 'ia', 'ie', 'iao', 'iu', 'ian', 'in', 'iang', 'ing', 'u', 'ua', 'uo', 'uai', 'ui',
              'uan', 'uang', 've', 'ai'],
        'p': ['a', 'o', 'e', 'i', 'ia', 'ie', 'iao', 'ou', 'an', 'ang', 'eng', 'i', 'in', 'ing', 'u', 'uan', 'uo',
              'uai', 'ui', 'uan', 'uang', 've'],
        'm': ['a', 'o', 'e', 'i', 'ia', 'ie', 'iao', 'ou', 'an', 'ang', 'eng', 'i', 'in', 'ing', 'u', 'uan', 'ua', 'ui',
              'uan', 'uang'],
        'f': ['a', 'o', 'e', 'ei', 'ou', 'an', 'en', 'ang', 'eng', 'u', 'iu'],
        'd': ['a', 'e', 'i', 'ia', 'ie', 'iao', 'ou', 'an', 'ang', 'eng', 'i', 'iu', 'ra', 'ian', 'iang', 'ing', 'u',
              'ua', 'uo', 'uai', 'ui', 'uan', 'uang'],
        't': ['a', 'e', 'i', 'ia', 'ie', 'iao', 'iou', 'ai', 'ui', 'an', 'ang', 'eng', 'ian', 'iang', 'ing', 'u', 'uan',
              'uang', 've'],
        'n': ['a', 'e', 'i', 'ia', 'ie', 'iao', 'iu', 'ian', 'in', 'iang', 'ing', 'u', 'uan', 'uang', 've', 'v'],
        'l': ['a', 'o', 'e', 'ai', 'ei', 'ia', 'iao', 'ian', 'iang', 'ing', 'u', 'uan', 'uang', 'uo', 've', 'i'],
        'g': ['a', 'e', 'ai', 'ei', 'ui', 'ao', 'ou', 'an', 'ang', 'eng', 'er', 'i', 'ua', 'uo', 'uai', 'ui', 'uan',
              'uang','on','ong'],
        'k': ['a', 'e', 'ai', 'ei', 'ou', 'an', 'ang', 'u', 'ua', 'uo', 'uai', 'ui', 'uan', 'uang'],
        'h': ['a', 'e', 'ai', 'ei', 'ao', 'ou', 'an', 'ang', 'i', 'ia', 'ie', 'iao', 'iu', 'u', 'ua', 'uo', 'uai', 'ui',
              'uan', 'uang', 'ua'],
        'j': ['i', 'ia', 'ie', 'iao', 'iu', 'ian', 'in', 'iang', 'ing', 'u', 'uan', 'uang'],
        'q': ['i', 'ia', 'ie', 'iao', 'iu', 'ian', 'iang', 'ing', 'u', 'uan', 'uang'],
        'x': ['i', 'ia', 'ie', 'iao', 'iu', 'ian', 'iang', 'ing', 'u', 'uan', 'uang', 've'],
        'zh': ['a', 'e', 'ai', 'ei', 'ao', 'ou', 'an', 'ang', 've', 'i', 'ua', 'uo', 'uai', 'ui', 'uan', 'uang','en','eng'],
        'ch': ['a', 'e', 'ai', 'ei', 'ao', 'ou', 'an', 'ang', 've', 'u', 'ua', 'uo', 'uai', 'ui', 'uan', 'uang', 'en', 'eng'],
        'sh': ['a', 'e', 'i', 'ou', 'an', 'ang', 've', 'u', 'ua', 'uo', 'uai', 'ui', 'uan', 'uang','en','eng'],
        'r': ['e', 'i', 'en', 'eng', 'i', 'ian', 'iang', 'u', 'ua'],
        'z': ['a', 'e', 'i', 'iu', 'an', 'ang', 'u', 'ua', 'uo', 'ui', 'uan', 'uang', 'i', 'ie'],
        'c': ['a', 'e', 'i', 'i', 'ou', 'an', 'ang', 'u', 'uo', 'ui', 'uan', 'uang'],
        's': ['a', 'e', 'i', 'i', 'ou', 'an', 'ang', 'eng', 'i', 'ong', 'u', 'ong', 'ong', 'ong', 'ong'],
        'y': ['a', 'ao', 'e', 'i', 'in', 'ing', 'i', 'o', 'ong', 'in', 'ing', 'in', 'ing', 'u', 'uan', 'ue', 'un', 'uan', 'uen', 'un'],
        'w': ['a', 'ai', 'an', 'ang', 'ei', 'en', 'eng', 'o', 'u', 'ei', 'en', 'eng']
    }
    for special in special_cases:
        pinyin_tree.insert(special)
    for shengmu,yunmu in pinyin_dict.items():
        if 'a' in yunmu and 'i' in yunmu:
            for i in ['i','o']:
                yunmu.append('a'+i)
        for y in yunmu:
            pinyin_tree.insert(shengmu  + y)
    return pinyin_tree

（三）、通过PinyinDictTree的search方法进行分词。

        

def find_last_true_index(lst):
    last_true_index = -1

    for i, val in enumerate(lst):
        if val:
            last_true_index = i
    return last_true_index

def pinyin_format(tree, pinyin):
    x = pinyin
    resault = []
    while True:
        flag = []
        s = ''
        for i in x:
            s += i
            r = tree.search(s)
            flag.append(r)
        y = find_last_true_index(flag)
        p = x[:y+1]
        if y == -1:
            resault.append(x[::])
            break
        if x[:2] in ['zh', 'ch', 'sh']:
            if x[2:4] in ['ia', 'ie', 'in',] or x[2:5] in ['iao', 'ian',]or x[2:6] in [ 'iang']:
                resault.append(x[:3])
                x = x[3:]
            elif x[2:4] in ['en','on','an']:
                if x[4:5] == 'g' and len(x) != 5:
                    if x[5:6] == 'g':
                        resault.append(p)
                        x = x[y + 1:]
                    else:
                        resault.append(x[:y+1])
                        x = x[y+1:]
                else:
                    resault.append(x[:y+1])
                    x = x[y+1:]
            else:
                resault.append(p)
                x = x[y + 1:]
        else:
            resault.append(p)
            x = x[y+1:]
        if not x:
            break
    return resault

解析拼音可以使用Pinyin2Hanzi,具体解析内容下一期更新。。。。