#!/usr/bin/python3

import sys, os

cn_syllables = {"a","ai","an","ang","ao","ba","bai","ban","bang","bao","bei","ben","beng","bi","bian","biao","bie","bin","bing","bo",
    "bu","ca","cai","can","cang","cao","ce","cen","ceng","cha","chai","chan","chang","chao","che","chen","cheng","chi","chong","chou",
    "chu","chua","chuai","chuan","chuang","chui","chun","chuo","ci","cong","cou","cu","cuan","cui","cun","cuo","da","dai","dan","dang",
    "dao","de","dei","den","deng","di","dian","diang","diao","die","ding","diu","dong","dou","du","duan","dui","dun","duo","e",
    "ei","en","eng","er","fa","fan","fang","fei","fen","feng","fo","fou","fu","ga","gai","gan","gang","gao","ge","gei",
    "gen","geng","gong","gou","gu","gua","guai","guan","guang","gui","gun","guo","ha","hai","han","hang","hao","he","hei","hen",
    "heng","hong","hou","hu","hua","huai","huan","huang","hui","hun","huo","ji","jia","jian","jiang","jiao","jie","jin","jing","jiong",
    "jiu","ju","juan","jue","jun","ka","kai","kan","kang","kao","ke","kei","ken","keng","kong","kou","ku","kua","kuai","kuan",
    "kuang","kui","kun","kuo","la","lai","lan","lang","lao","le","lei","leng","li","lia","lian","liang","liao","lie","lin","ling",
    "liu","lo","long","lou","lu","lü","luan","lüe","lun","luo","ma","mai","man","mang","mao","me","mei","men",
    "meng","mi","mian","miao","mie","min","ming","miu","mo","mou","mu","na","nai","nan","nang","nao","ne","nei","nen","neng",
    "ni","nia","nian","niang","niao","nie","nin","ning","niu","nong","nou","nu","nü","nuan","nüe","nun","nuo","o","ou","pa",
    "pai","pan","pang","pao","pei","pen","peng","pi","pian","piao","pie","pin","ping","po","pou","pu","qi","qia","qian","qiang",
    "qiao","qie","qin","qing","qiong","qiu","qu","quan","que","qun","ran","rang","rao","re","ren","reng","ri","rong","rou","ru",
    "ruan","rui","run","ruo","sa","sai","san","sang","sao","se","sei","sen","seng","sha","shai","shan","shang","shao","she","shei",
    "shen","sheng","shi","shong","shou","shu","shua","shuai","shuan","shuang","shui","shun","shuo","si","song","sou","su","suan","sui","sun",
    "suo","ta","tai","tan","tang","tao","te","teng","ti","tian","tiao","tie","ting","tong","tou","tu","tuan","tui","tun","tuo",
    "wa","wai","wan","wang","wei","wen","weng","wo","wu","xi","xia","xian","xiang","xiao","xie","xin","xing","xiong","xiu","xu",
    "xuan","xue","xun","ya","yai","yan","yang","yao","ye","yi","yin","ying","yo","yong","you","yu","yuan","yue","yun","za",
    "zai","zan","zang","zao","ze","zei","zen","zeng","zha","zhai","zhan","zhang","zhao","zhe","zhei","zhen","zheng","zhi","zhong","zhou",
    "zhu","zhua","zhuai","zhuan","zhuang","zhui","zhun","zhuo","zi","zong","zou","zu","zuan","zui","zun","zuo",
     "lv", "lve", "nv", "nve" } # for convenience, v == ü

def print_usage():
    print("Usage: "+sys.argv[0]+" [-1n] <syllable>[<tone>] [<syllable>[<tone>]...]")
    print("Examples:\n\t"+sys.argv[0]+" zhi\n\t"+sys.argv[0]+" shi4\n\t"+sys.argv[0]+" -1 qi1 ji1\n\t"+sys.argv[0]+" -i 1-50,6500")
    print("Add -1 for single mode (no column)")
    print("Add -s for silent mode (no line numbers, pinyin or headers)")
    print("Add -p for hide pinyin mode (no pinyin)")
    print("Add -n for hide numbers mode (no line numbers)")
    print("Add -a search for characters in both section 1 (frequent) AND section 2 (common). Default is only section 1.")
    print("Add -i <index> shows a character based on its index, can use multiple indexes separated with , or ranges with -")

if len(sys.argv) < 2:
    print_usage()
    sys.exit(1)

class Query:
    query_search = 1
    query_index = 2

    def __init__(self, query_type, query_string):
        self.query_type = query_type
        self.query_string = query_string

def index_queries(index_str):
    result = []
    for index_range in index_str.split(","):
        r = index_range.partition("-")
        if r[2] == "" and r[0].isdigit():
            result += [Query(Query.query_index, r[0])]
        elif r[0].isdigit() and r[2].isdigit():
            result += [Query(Query.query_index, r[0] + "," + r[2])]
        else:
            print(sys.argv[0]+" Error: option -i requires a set of comma separated indexes containing numbers(50) or ranges(1-50). Ex \"1,50-100,102-103,6500\". Argument \""+index+"\" is not correct.")
            return None
    return result

queries = []

singlemode = False
silentmode = False
hide_pinyinmode = False
hide_numbersmode = False
search_allmode = False
searching_for_index = False
for arg in sys.argv[1:]:
    if searching_for_index == True:
        searching_for_index = False
        qs = index_queries(arg)
        if qs is None:
            sys.exit(1)
        queries += qs
        continue
    if arg == "":
        print(sys.argv[0]+" Error: empty argument given")
        sys.exit(1)
    if arg[0] == "-":
        for opt in arg[1:]:
            if opt == "1":
                singlemode = True
            elif opt == "s":
                silentmode = True
            elif opt == "p":
                hide_pinyinmode = True
            elif opt == "n":
                hide_numbersmode = True
            elif opt == "a":
                search_allmode = True
            elif opt == "i":
                index = arg.partition("i")[2]
                if index == "":
                    searching_for_index = True
                    continue
                qs = index_queries(index)
                if qs is None:
                    sys.exit(1)
                queries += qs
                break
            else:
                print(sys.argv[0]+" Error: unknown option -"+opt+" given in "+arg)
                sys.exit(1)
    else:
        tone = '[1-5]'
        lastchr = arg[len(arg)-1]
        if lastchr.isdigit():
            syl = arg[:len(arg)-1]
            tone = lastchr
        else:
            syl = arg
        if syl not in cn_syllables:
            print(sys.argv[0] + ": Syllable "+arg+" does not exist in the Chinese language")
            sys.exit(1)
        loc_v = syl.find("v")
        if loc_v != -1:
            syl = syl[:loc_v] + "ü" + syl[loc_v+1:]
        queries += [Query(Query.query_search, syl + tone)]

if len(queries) == 0:
    print_usage()
    sys.exit(1)

grepopts = "-w"
end = ""

if silentmode or hide_pinyinmode:
    end += " | cut -d, -f1"

if not silentmode and not hide_numbersmode:
    grepopts += "n"

if not singlemode:
    end += " | column"

hanzi_file_full = "$HOME/Documents/Chinees/char-lists/hanzi-pinyin.csv"
hanzi_file_top3500 = "$HOME/Documents/Chinees/char-lists/hanzi-pinyin.csv.top3500"

if search_allmode:
    hanzi_file = hanzi_file_full
else:
    hanzi_file = hanzi_file_top3500

for query in queries:
    if query.query_type == Query.query_search:
        if not silentmode:
            print(query.query_string, flush=True)
        os.system("grep "+grepopts+" '"+query.query_string+"' " + hanzi_file + end)
    elif query.query_type == Query.query_index:
        os.system("sed -n "+query.query_string+"p " + hanzi_file_full + end)
    else:
        print(sys.argv[0] + " Error: unknown query type")
        sys.exit(1)
