# 安装必要的DataStructures包（如果未安装
import Pkg; Pkg.add("DataStructures")

# 使用数据结构包方便字符频率计算
using DataStructures

# 从一到九十的数字的文本表示的字典
const textnumbers = Dict(
    "single" => 1, "one" => 1, "two" => 2, "three" => 3, "four" => 4,
    "five" => 5, "six" => 6, "seven" => 7, "eight" => 8, "nine" => 9,
    "ten" => 10, "eleven" => 11, "twelve" => 12, "thirteen" => 13,
    "fourteen" => 14, "fifteen" => 15, "sixteen" => 16,
    "seventeen" => 17, "eighteen" => 18, "nineteen" => 19,
    "twenty" => 20, "thirty" => 30, "forty" => 40, "fifty" => 50,
    "sixty" => 60, "seventy" => 70, "eighty" => 80, "ninety" => 90
)

"""
    phrasetointeger(txt)

将文本数字转换为数值。
Пример: "twenty five" => 25
"""
function phrasetointeger(txt)
    words = split(txt, r"\W+")      # 将字符串拆分为单独的单词，不包括标点符号
    n = 0                           # 数字累加器
    for w in words                  # 通过所有的话
        n += get(textnumbers, w, 0) # 如果这个词在字典中，请添加其含义。
        w == "hundred" && (n *= 100) # 如果这个词是一百，我们乘以100。
    end
    return n                        # 返回总数值
end

"""
    isautogram(txt, countpunctuation; verbose = true)

该函数检查txt字符串是否是有效的自动标记。
争论:
-txt：需要检查的文本
-countpunctuation：是否计算标点符号（true/false）
-verbose：是否显示错误消息
"""
function isautogram(txt, countpunctuation; verbose = true)
    # 我们将整个文本减少为小写字母
    s = lowercase(txt)
    
    # 我们计算每个字符的出现次数
    charcounts = counter(s)

    # 要检查引用的字符字典
    stillneedmention = Dict(
        p[1] => isletter(p[1]) || p[1] != ' ' && countpunctuation ? p[2] : 0
        for p in charcounts
    )

    # 在解析之前对字符串进行一点格式化
    s = " " * replace(s, r"^\.(?:employs|composed|contains)" => "")

    # 用逗号和冒号将字符串拆分为描述字符的标记
    for mention in split(s, r"\s*,|:\s*")
        mention = replace(mention, r" and$" => "")  # 删除行尾的"和"字
        spos = findlast(isspace, mention)           # 我们找到最后一个空格-然后会有符号的单词。

        if spos === nothing continue end            # 如果你还没有找到它，跳过它。

        # 提取文本的数字部分（直到最后一个空格）
        numfromtext = phrasetointeger(mention[begin:spos-1])
        numfromtext == 0 && continue  # 如果数字为0，我们继续

        # 提取字符串中表示字符的部分
        c = mention[begin+spos:end]

        if c == "letters"
            # 检查字母总数
            if numfromtext != count(isletter, txt)
                verbose && println("The total letter count (should be $(count(isletter, txt))) is incorrect.")
                return false
            end
            continue
        end

        # 我们根据描述定义符号
        ch = contains(c, "comma") ? ',' : 
             contains(c, "apostrophe") ? '\'' : 
             contains(c, "hyphen") ? '-' : Char(c[1])

        # 检查提到的字符的数量
        if charcounts[ch] == numfromtext
            stillneedmention[ch] = 0  # 将其标记为已验证
        else
            verbose && println("The count of $ch in the phrase is incorrect.")
            return false
        end
    end

    # 我们检查是否有任何字符被遗忘。
    for p in stillneedmention
        if p[2] > 0
            verbose && println("The letter and count $p was not mentioned in the counts in the phrase.")
            return false
        end
    end

    return true  # 如果所有内容都被检查并匹配，则自动图是正确的。
end

# 一组测试线-自动图和非自动图
for (i, t) in enumerate([
    ("This sentence employs two a's, two c's, two d's, twenty-eight e's, five f's, three g's, eight h's, eleven i's, three l's, two m's, thirteen n's, nine o's, two p's, five r's, twenty-five s's, twenty-three t's, six v's, ten w's, two x's, five y's, and one z.", false),
    ("This sentence employs two a's, two c's, two d's, twenty eight e's, five f's, three g's, eight h's, eleven i's, three l's, two m's, thirteen n's, nine o's, two p's, five r's, twenty five s's, twenty three t's, six v's, ten w's, two x's, five y's, and one z.", false),
    ("This pangram contains four as, one b, two cs, one d, thirty es, six fs, five gs, seven hs, eleven is, one j, one k, two ls, two ms, eighteen ns, fifteen os, two ps, one q, five rs, twenty-seven ss, eighteen ts, two us, seven vs, eight ws, two xs, three ys, & one z.", false),
    ("This sentence contains one hundred and ninety-seven letters: four a's, one b, three c's, five d's, thirty-four e's, seven f's, one g, six h's, twelve i's, three l's, twenty-six n's, ten o's, ten r's, twenty-nine s's, nineteen t's, six u's, seven v's, four w's, four x's, five y's, and one z.", false),
    ("Thirteen e's, five f's, two g's, five h's, eight i's, two l's, three n's, six o's, six r's, twenty s's, twelve t's, three u's, four v's, six w's, four x's, two y's.", false),
    ("Fifteen e's, seven f's, four g's, six h's, eight i's, four n's, five o's, six r's, eighteen s's, eight t's, four u's, three v's, two w's, three x's.", true),
    ("Sixteen e's, five f's, three g's, six h's, nine i's, five n's, four o's, six r's, eighteen s's, eight t's, three u's, three v's, two w's, four z's.", false),
   ])
    
    # 我们检查每一行
    println("Test phrase $i is", isautogram(t[1], t[2]) ? " " : " not ", "a valid autogram.\n")
end