init

resource/datasets/__init__.py

@@ -0,0 +1,141 @@
+import difflib
+import os
+import typing
+import urllib.request
+
+import simplejson as json
+
+
+class FuzzyDict(dict):
+    """Provides a dictionary that performs fuzzy lookup"""
+
+    def __init__(self, cutoff: float = 0.6):
+        """Construct a new FuzzyDict instance
+
+        items is an dictionary to copy items from (optional)
+        cutoff is the match ratio below which matches should not be considered
+        cutoff needs to be a float between 0 and 1 (where zero is no match
+        and 1 is a perfect match)"""
+        super(FuzzyDict, self).__init__()
+        self.cutoff = cutoff
+
+        # short wrapper around some super (dict) methods
+        self._dict_contains = lambda key: super(FuzzyDict, self).__contains__(key)
+        self._dict_getitem = lambda key: super(FuzzyDict, self).__getitem__(key)
+
+    def _search(self, lookfor: typing.Any, stop_on_first: bool = False):
+        """Returns the value whose key best matches lookfor
+
+        if stop_on_first is True then the method returns as soon
+        as it finds the first item
+        """
+
+        # if the item is in the dictionary then just return it
+        if self._dict_contains(lookfor):
+            return True, lookfor, self._dict_getitem(lookfor), 1
+
+        # set up the fuzzy matching tool
+        ratio_calc = difflib.SequenceMatcher()
+        ratio_calc.set_seq1(lookfor)
+
+        # test each key in the dictionary
+        best_ratio = 0
+        best_match = None
+        best_key = None
+        for key in self:
+            # if the current key is not a string
+            # then we just skip it
+            try:
+                # set up the SequenceMatcher with other text
+                ratio_calc.set_seq2(key)
+            except TypeError:
+                continue
+
+            # we get an error here if the item to look for is not a
+            # string - if it cannot be fuzzy matched and we are here
+            # this it is definitely not in the dictionary
+            try:
+                # calculate the match value
+                ratio = ratio_calc.ratio()
+            except TypeError:
+                break
+
+            # if this is the best ratio so far - save it and the value
+            if ratio > best_ratio:
+                best_ratio = ratio
+                best_key = key
+                best_match = self._dict_getitem(key)
+
+            if stop_on_first and ratio >= self.cutoff:
+                break
+
+        return best_ratio >= self.cutoff, best_key, best_match, best_ratio
+
+    def __contains__(self, item: typing.Any):
+        if self._search(item, True)[0]:
+            return True
+        else:
+            return False
+
+    def __getitem__(self, lookfor: typing.Any):
+        matched, key, item, ratio = self._search(lookfor)
+
+        if not matched:
+            raise KeyError(
+                "'%s'. closest match: '%s' with ratio %.3f"
+                % (str(lookfor), str(key), ratio)
+            )
+
+        return item
+
+
+__HERE = os.path.abspath(os.path.dirname(__file__))
+with open(os.path.join(__HERE, "map_filename.json"), "r", encoding="utf8") as f:
+    FILENAMES: FuzzyDict = FuzzyDict()
+    for k, v in json.load(f).items():
+        FILENAMES[k] = v
+
+with open(os.path.join(__HERE, "city_coordinates.json"), "r", encoding="utf8") as f:
+    COORDINATES: FuzzyDict = FuzzyDict()
+    for k, v in json.load(f).items():
+        COORDINATES[k] = v
+
+EXTRA = {}
+
+
+def register_url(asset_url: str):
+    if asset_url:
+        registry = asset_url + "/registry.json"
+        try:
+            contents = urllib.request.urlopen(registry).read()
+            contents = json.loads(contents)
+        except Exception as e:
+            raise e
+        files = {}
+        pinyin_names = set()
+        for name, pinyin in contents["PINYIN_MAP"].items():
+            file_name = contents["FILE_MAP"][pinyin]
+            files[name] = [file_name, "js"]
+            pinyin_names.add(pinyin)
+
+        for key, file_name in contents["FILE_MAP"].items():
+            if key not in pinyin_names:
+                # English names
+                files[key] = [file_name, "js"]
+
+        js_folder_name = contents["JS_FOLDER"]
+        if js_folder_name == "/":
+            js_file_prefix = f"{asset_url}/"
+        else:
+            js_file_prefix = f"{asset_url}/{js_folder_name}/"
+        EXTRA[js_file_prefix] = files
+
+
+def register_files(asset_files: dict):
+    if asset_files:
+        FILENAMES.update(asset_files)
+
+
+def register_coords(coords: dict):
+    if coords:
+        COORDINATES.update(coords)

resource/datasets/countries_regions_db.json

@@ -0,0 +1,218 @@
+{
+  "蒲隆地": "BI",
+  "圣卢西亚": "LC",
+  "巴巴多斯": "BB",
+  "安道尔": "AD",
+  "利比里亚": "LR",
+  "吉尔吉斯斯坦": "KG",
+  "阿曼": "OM",
+  "利比亚": "LY",
+  "根西": "GG",
+  "南非": "ZA",
+  "阿塞拜疆": "AZ",
+  "巴拉圭": "PY",
+  "匈牙利": "HU",
+  "巴勒斯坦": "PS",
+  "泰国": "TH",
+  "黎巴嫩": "LB",
+  "英属维尔京群岛": "VG",
+  "特立尼达和多巴哥": "TT",
+  "巴基斯坦": "PK",
+  "加拿大": "CA",
+  "保加利亚": "BG",
+  "马来西亚": "MY",
+  "叙利亚": "SY",
+  "毛里塔尼亚": "MR",
+  "白俄罗斯": "BY",
+  "秘鲁": "PE",
+  "摩洛哥": "MA",
+  "莱索托": "LS",
+  "法罗群岛": "FO",
+  "圣基茨和尼维斯": "KN",
+  "阿根廷": "AR",
+  "委内瑞拉": "VE",
+  "塞舌尔": "SC",
+  "英属印度洋领地": "IO",
+  "瓦努阿图": "VU",
+  "纳米比亚": "NA",
+  "马拉维": "MW",
+  "克罗地亚": "HR",
+  "玻利维亚": "BO",
+  "塞内加尔": "SN",
+  "希腊": "GR",
+  "蒙古": "MN",
+  "东帝汶": "TL",
+  "新加坡": "SG",
+  "意大利": "IT",
+  "皮特凱恩群島": "PN",
+  "芬兰": "FI",
+  "圭亚那": "GY",
+  "福克兰群岛": "FK",
+  "毛里求斯": "MU",
+  "马其顿": "MK",
+  "新西兰": "NZ",
+  "波斯尼亚-黑塞哥维那": "BA",
+  "吐瓦鲁": "TV",
+  "以色列": "IL",
+  "塞尔维亚": "RS",
+  "密克罗尼西亚联邦": "FM",
+  "斯洛文尼亚": "SI",
+  "阿富汗": "AF",
+  "科威特": "KW",
+  "英国": "GB",
+  "汤加": "TO",
+  "贝宁": "BJ",
+  "撒拉威阿拉伯民主共和国": "",
+  "海地": "HT",
+  "格鲁吉亚": "GE",
+  "安提瓜和巴布达": "AG",
+  "刚果金": "CD",
+  "澳大利亚": "AU",
+  "史瓦济兰": "SZ",
+  "马达加斯加": "MG",
+  "哥伦比亚": "CO",
+  "多米尼加共和国": "DO",
+  "爱沙尼亚": "EE",
+  "哥斯达黎加": "CR",
+  "塞浦路斯": "CY",
+  "沙特阿拉伯": "SA",
+  "南苏丹": "SS",
+  "荷兰": "NL",
+  "圣马力诺": "SM",
+  "罗马尼亚": "RO",
+  "智利": "CL",
+  "几内亚比索": "GW",
+  "尼加拉瓜": "NI",
+  "特克斯和凯科斯群岛": "TC",
+  "珊瑚海群岛领地": "",
+  "泽西": "JE",
+  "奥地利": "AT",
+  "蒙特塞拉特": "MS",
+  "纽埃": "NU",
+  "圣文森特和格林纳丁斯": "VC",
+  "伯利兹": "BZ",
+  "斯洛伐克": "SK",
+  "哈萨克斯坦": "KZ",
+  "直布罗陀": "GI",
+  "柬埔寨": "KH",
+  "立陶宛": "LT",
+  "中非共和国": "CF",
+  "瑞典": "SE",
+  "爱尔兰": "IE",
+  "赤道几内亚": "GQ",
+  "亚美尼亚": "AM",
+  "捷克": "CZ",
+  "冈比亚": "GM",
+  "格陵兰": "GL",
+  "科索沃": "",
+  "印度": "IN",
+  "多哥": "TG",
+  "挪威": "NO",
+  "土耳其": "TR",
+  "拉脱维亚": "LV",
+  "佛得角": "CV",
+  "乌兹别克斯坦": "UZ",
+  "肯尼亚": "KE",
+  "博茨瓦纳": "BW",
+  "加蓬": "GA",
+  "塔吉克斯坦": "TJ",
+  "尼日尔": "NE",
+  "布基纳法索": "BF",
+  "安圭拉": "AI",
+  "老挝": "LA",
+  "阿尔巴尼亚": "AL",
+  "厄瓜多尔": "EC",
+  "葡萄牙": "PT",
+  "乍得": "TD",
+  "南乔治亚和南桑威奇群岛": "GS",
+  "几内亚": "GN",
+  "冰岛": "IS",
+  "托克劳": "TK",
+  "摩纳哥": "MC",
+  "埃及": "EG",
+  "马绍尔群岛": "MH",
+  "巴拿马": "PA",
+  "巴林": "BH",
+  "苏里南": "SR",
+  "帕劳": "PW",
+  "尼日利亚": "NG",
+  "加纳": "GH",
+  "牙买加": "JM",
+  "巴哈马": "BS",
+  "波兰": "PL",
+  "土库曼": "TM",
+  "古巴": "CU",
+  "吉布提": "DJ",
+  "马恩岛": "IM",
+  "巴布亚新几内亚": "PG",
+  "文莱": "BN",
+  "摩尔多瓦": "MD",
+  "开曼群岛": "KY",
+  "安哥拉": "AO",
+  "乌克兰": "UA",
+  "喀麦隆": "CM",
+  "萨尔瓦多": "SV",
+  "萨摩亚": "WS",
+  "黑山": "ME",
+  "孟加拉国": "BD",
+  "韩国": "KR",
+  "苏丹": "SD",
+  "厄立特里亚": "ER",
+  "库克群岛": "CK",
+  "马里": "ML",
+  "伊朗": "IR",
+  "伊拉克": "IQ",
+  "日本": "JP",
+  "突尼斯": "TN",
+  "津巴布韦": "ZW",
+  "菲律宾": "PH",
+  "约旦": "JO",
+  "埃塞俄比亚": "ET",
+  "德国": "DE",
+  "巴西": "BR",
+  "卢旺达": "RW",
+  "洪都拉斯": "HN",
+  "梵蒂冈": "VA",
+  "基里巴斯": "KI",
+  "阿拉伯联合酋长国": "AE",
+  "墨西哥": "MX",
+  "塞拉利昂": "SL",
+  "所罗门群岛": "SB",
+  "斯里兰卡": "LK",
+  "俄罗斯": "RU",
+  "法国": "FR",
+  "危地马拉": "GT",
+  "越南": "VN",
+  "坦桑尼亚": "TZ",
+  "比利时": "BE",
+  "丹麦": "DK",
+  "索马里": "SO",
+  "美国": "US",
+  "马尔代夫": "MV",
+  "列支敦士登": "LI",
+  "科摩罗": "KM",
+  "百慕达群岛": "BM",
+  "不丹": "BT",
+  "朝鲜": "KP",
+  "莫桑比克": "MZ",
+  "印度尼西亚, 印尼": "ID",
+  "也门": "YE",
+  "刚果-布拉柴维尔": "CG",
+  "乌拉圭": "UY",
+  "圣赫勒拿-阿森松和特里斯坦-达库尼亚": "SH",
+  "尼泊尔": "NP",
+  "多米尼克": "DM",
+  "马耳他": "MT",
+  "阿尔及利亚": "DZ",
+  "卡塔尔": "QA",
+  "赞比亚": "ZM",
+  "缅甸": "MM",
+  "卢森堡": "LU",
+  "斐济": "FJ",
+  "西班牙": "ES",
+  "乌干达": "UG",
+  "中国": "CN",
+  "中国香港": "HK",
+  "中国台湾": "TW",
+  "china": "CN"
+}