More romanisation schemes

.gitignore

@@ -102,4 +102,6 @@ ENV/
 
 
 .idea/
-.vscode/
+.vscode/
+
+.DS_Store

Makefile

@@ -0,0 +1,2 @@
+test:
+	python3 -m unittest discover -v . "*Test.py"

pyhokchew/convert.py

@@ -1,6 +1,9 @@
-from .models.CikLinSyllable import CikLinSyllable
-from .models.FoochowRomanized import FoochowRomanizedSyllable
-
+from .models.historical.CikLinSyllable import CikLinSyllable
+from .models.historical.FoochowRomanized import FoochowRomanizedSyllable
+from .models.historical.HectorScheme import HectorSyllable
+from .models.concurrent.matsu import WuyixingSyllable
+from .models.concurrent.minjiang import MinjiangSyllable
+from .models.yngping.YngPingTwo import YngPingSyllable
 
 def foochow_romanized_to_ciklin(f):
     ciklin_syllable = CikLinSyllable(f.initial,f.final,f.tone)
@@ -18,3 +21,129 @@ def ciklin_to_foochow_romanized_string(cInitial, cFinal, cTone):
     :return: The converted Foochow Romanized string.
     """
     return ciklin_to_foochow_romanized(CikLinSyllable.from_ciklin_string(cInitial+cFinal,cTone)).get_string()
+
+def foochow_romanized_to_yngping(f: FoochowRomanizedSyllable):
+    INITIAL_MAPPING = ['l', 'b', 'g', 'k', 'd',
+                       'p', 't', 'z', 'n', 's',
+                       '' , 'm','ng','c', 'h']
+    FINAL_MAPPING  = [
+        #   1       2      3       4      5       7      8     FR
+        #  55       33    212     23     53      242     5     YP
+        ['ung',  'ung', 'oung', 'ouk', 'ung',  'oung', 'uk'],  # 春
+        ['ua',   'ua',  'ua',   'uah', 'ua',   'ua',   'uah'], # 花
+        ['yong', 'yong','yong', 'yok', 'yong', 'yong', 'yok'], # 香 
+        ['iu',   'iu',  'iu',   'iuh', 'iu',   'iu',   None],  # 秋
+        ['ang',  'ang', 'ang',  'ak',  'ang',  'ang',  'ak'],  # 山
+        ['ai',   'ai',  'ai',   'aih', 'ai',   'ai',   'aih'], # 開
+        ['a',    'a',   'a',    'ah',  'a',    'a',    'ah'],  # 嘉 
+        ['ing',  'ing', 'eing', 'eik', 'ing',  'eing', 'ik'],  # 賓
+        ['uang', 'uang','uang', 'uak', 'uang', 'uang', 'uak'], # 歡
+        ['o',    'o',   'o',    'oh',  'o',    'o',    'oh'],  # 歌
+        ['y',    'y',   'oey',  'oeyk','y',    'oey',  'yk'],  # 須
+        ['ui',   'ui',  'ui',   'uih', 'ui',   'ui',   None],  # 杯
+        ['u',    'u',   'ou',   'ouh', 'u',    'ou',   'uh'],  # 孤
+        ['eing', 'eing','aing', 'aik', 'eing', 'aing', 'eik'], # 燈
+        ['uong', 'uong','uong', 'uok', 'uong', 'uong', 'uok'], # 光
+        ['ui',   'ui',  'ui',   'uih', 'ui',   'ui',   'uih'], # 輝
+        ['iu',   'iu',  'iu',   'iuh', 'iu',   'iu',   None],  # 燒
+        ['yng',  'yng', 'oeyng','oeyk','yng',  'oeyng','yk'],  # 銀
+        ['oung', 'oung','aung', 'auk', 'oung', 'aung', 'ouk'], # 缸
+        ['i',    'i',   'ei',   'eih', 'i',    'ei',   'ih'],  # 之
+        ['oeyng','oeyng','oyng','oyk', 'oeyng','oyng', 'oeyk'],# 東
+        ['au',   'au',  'au',   'auh' ,'au',   'au',   'auh'], # 郊
+        ['uo',   'uo',  'uo',   'uoh', 'uo',   'uo',   'uoh'], # 過
+        ['e',    'e',   'a',    'ah',  'e',    'a',    'eh'],  # 西
+        ['yo',   'yo',  'yo',   'yoh', 'yo',   'yo',   'yoh'], # 橋
+        ['ie',   'ie',  'ie',   'ieh', 'ie',   'ie',   'ieh'], # 鷄
+        ['iang', 'iang','iang', 'iak', 'iang', 'iang', 'iak'], # 聲
+        ['oey',  'oey',  'oy',  'oyh', 'oey',  'oy',   'oeyh'],# 催
+        ['oe',   'oe',   'o',   'oeh', 'oe',   'o',    'oeh'], # 初
+        ['ieng', 'ieng','ieng', 'iek', 'ieng', 'ieng', 'iek'], # 天
+        ['ia',   'ia',  'ia',   'ieh', 'ia',   'ia',   'ieh'], # 奇
+        ['uai',  'uai', 'uai',  'uaih','uai',  'uai',  'uaih'],# 歪  
+        ['eu',   'eu',  'au',   'auh', 'eu',   'au',   'euh']  # 溝  
+    ]
+    FINAL_MAPPING_IO_UO = {
+        24: ['uo',   'uo',  'uo',   'uoh', 'uo',   'uo',   'uoh'],
+        2:  ['uong', 'uong','uong', 'uok', 'uong', 'uong', 'uok']
+    }
+    TONE_MAPPING = {
+        1: "55",
+        2: "33",
+        3: "212",
+        4: "23",
+        5: "53",
+        6: "33",
+        7: "242",
+        8: "5"
+    }
+    ypInitial = INITIAL_MAPPING[f.initial]
+    toneIndex = FoochowRomanizedSyllable.TONE_MAPPING[f.tone]
+    if ypInitial not in ['','g','k','h','ng'] and f.final in [2, 24]: #香 / 橋
+        # 漳泉亂 
+        ypFinal = FINAL_MAPPING_IO_UO[f.final][toneIndex]
+    else:
+        ypFinal = FINAL_MAPPING[f.final][toneIndex]
+    ypTone = TONE_MAPPING[f.tone]
+    return YngPingSyllable(ypInitial, ypFinal, ypTone)
+
+def hector_to_foochow_romanized(s):
+    h = HectorSyllable.from_string(s)
+    return FoochowRomanizedSyllable(h.initial,h.final,h.tone)
+
+def hector_to_foochow_romanized_string(s):
+    return hector_to_foochow_romanized(s).get_string()
+
+def hector_to_yngping(s):
+    f = hector_to_foochow_romanized(s)
+    return foochow_romanized_to_yngping(f).to_typing()
+
+def foochow_romanized_to_yngping_string(s, allow_omit_ingbing=False):
+    return foochow_romanized_to_yngping(FoochowRomanizedSyllable.from_string(s,allow_omit_ingbing)).to_typing()
+
+def wuyixing_to_yngping(s):
+    """從烏衣行轉換爲榕拼方案
+    """
+    wyx = WuyixingSyllable.from_string(s)
+    INITIAL_MAPPING = {
+        'p': 'b',
+        'ph':'p',
+        't' :'d',
+        'th':'t',
+        'ts': 'z',
+        'tsh': 'c',
+        'k':'g',
+        'kh':'k',
+    }
+
+    FINAL_MAPPING = {
+        # TODO: 榕拼無?
+        'ieu': 'iu'
+    }
+
+    return YngPingSyllable(
+        INITIAL_MAPPING[wyx.initial] if wyx.initial in INITIAL_MAPPING.keys() else wyx.initial,
+        FINAL_MAPPING[wyx.final] if wyx.final in FINAL_MAPPING.keys() else wyx.final, 
+        wyx.tone).to_typing()
+
+
+def minjiang_to_yngping(s):
+    """從閩江學院轉換爲榕拼方案
+    """
+    mj = MinjiangSyllable.from_string(s)
+
+    VOWEL_MAPPING = {
+        'ë': 'oe',
+        'ü': 'y'
+    }
+
+    final = mj.final
+    for v in VOWEL_MAPPING.keys():
+        nv = VOWEL_MAPPING[v]
+        final = final.replace(v,nv)
+
+    return YngPingSyllable(
+        mj.initial,
+        final,
+        mj.tone).to_typing()
+

pyhokchew/models/concurrent/matsu.py

@@ -0,0 +1,107 @@
+
+from ...utils import normalise
+
+WYX_CONSONANTS = ['p', 'ph', 'm', 't', 'th', 'n', 'l', 'ts', 'tsh', 's', 'k', 'kh', 'ng', 'h']
+
+WYX_VOWELS = ['a', 'o', 'e', 'oe', 'i', 'u', 'y']
+
+WYX_CODAS = ['ng', 'h', 'k', '']
+
+WYX_INITIALS = WYX_CONSONANTS + ['']
+
+
+# Tones
+# 55	
+# 53	s
+# 33	f
+# 212	v
+# 242	x
+# 23	z
+# 5	
+
+class WuyixingSyllable:
+    """烏衣行馬祖話輸入法的拼音方案
+    """
+
+    def __init__(self, initial, final, tone):
+        """
+        """
+        if initial not in set(WYX_INITIALS):
+            raise Exception('Unknown initial: %s' % initial)
+        self.initial = initial
+        self.final = final
+        self.tone = tone
+
+    def __str__(self):
+        return 'WuyixingSyllable Initial=%s Final=%s Tone=%s' % (self.initial, self.final, self.tone)
+
+    def __repr__(self):
+        return self.__str__()
+
+    @classmethod
+    def from_string(cls, s):
+        s = normalise(s).strip().lower()
+
+        # 需要先 match 較長的
+        sorted_initials = sorted(WYX_INITIALS, reverse=True, key=lambda x: len(x))
+        initial = None
+        for i in sorted_initials:
+            if s.startswith(i):
+                initial = i
+                s = s[len(i):]
+                break
+
+        if initial is None:
+            raise Exception('No matching initial')
+
+        rime = None
+        sorted_vowels = sorted(WYX_VOWELS, reverse=True, key=lambda x: len(x))
+
+        while True:
+            found = False
+            for v in sorted_vowels:
+                if s.startswith(v):
+                    rime = v if rime is None else rime + v
+                    s = s[len(v):]
+                    found = True                
+                    break
+            if not found:
+                break
+
+        if rime is None:
+            raise Exception('No matching final')
+
+        coda = None
+
+        for c in WYX_CODAS:
+            if s.startswith(c):
+                coda = c
+                s = s[len(c):]
+                break
+
+        if coda is None:
+            raise Exception('No matching final')
+
+        # the rest is the tone
+        tone = None
+        if s == "":
+            if coda in ['h', 'k']:
+                tone = "5"
+            else:
+                tone = "55"
+        elif s == "s":
+            tone = "53"
+        elif s == "f":
+            tone = "33"
+        elif s == "v":
+            tone = "212"
+        elif s == "x":
+            tone = "242"
+        elif s == "z":
+            if coda in ['h', 'k']:
+                tone = "23"
+
+        if tone is None:
+            raise Exception('No matching tone.')
+
+        return WuyixingSyllable(initial, rime+coda, tone)

pyhokchew/models/concurrent/minjiang.py

@@ -0,0 +1,109 @@
+from ...utils import normalise
+
+MJ_CONSONANTS = ['b', 'p', 'm', 'd', 't', 'n', 'l', 'z', 'c', 's', 'g', 'k', 'ng', 'h']
+
+MJ_VOWELS = ['a', 'o', 'e', 'ë', 'i', 'u', 'ü']
+
+MJ_CODAS = ['ng', 'h', 'k', '']
+
+MJ_INITIALS = MJ_CONSONANTS + ['']
+
+TONE_MAPPINGS = {
+    "1": "55",
+    "2": "53",
+    "3": "33",
+    "4": "212",
+    "5": "242",
+    "6": "23",
+    "7": "5"
+}
+
+MJ_TONES = list(TONE_MAPPINGS.keys())
+
+def normalise_mj(s):
+    # 正規化閩江學院的奇怪字符
+    s = normalise(s).strip().lower()
+    s = s.replace('ɑ','a').replace('ê','e').replace('ɡ','g')
+    return s
+
+# Tones
+# 55	1
+# 53	2
+# 33	3
+# 212	4
+# 242	5
+# 23	6
+# 5	    7
+
+class MinjiangSyllable:
+    """閩江學院的拼音方案
+    """
+
+    def __init__(self, initial, final, tone):
+        """
+        """
+        if initial not in set(MJ_INITIALS):
+            raise Exception('Unknown initial: %s' % initial)
+        self.initial = initial
+        self.final = final
+        self.tone = tone
+
+    def __str__(self):
+        return 'MinjiangSyllable Initial=%s Final=%s Tone=%s' % (self.initial, self.final, self.tone)
+
+    def __repr__(self):
+        return self.__str__()
+
+    @classmethod
+    def from_string(cls, s):
+        s = normalise_mj(s)
+
+        # 需要先 match 較長的
+        sorted_initials = sorted(MJ_INITIALS, reverse=True, key=lambda x: len(x))
+        initial = None
+        for i in sorted_initials:
+            if s.startswith(i):
+                initial = i
+                s = s[len(i):]
+                break
+
+        if initial is None:
+            raise Exception('No matching initial')
+
+        rime = None
+        sorted_vowels = sorted(MJ_VOWELS, reverse=True, key=lambda x: len(x))
+
+        while True:
+            found = False
+            for v in sorted_vowels:
+                if s.startswith(v):
+                    rime = v if rime is None else rime + v
+                    s = s[len(v):]
+                    found = True                
+                    break
+            if not found:
+                break
+
+        if rime is None:
+            raise Exception('No matching final')
+
+        coda = None
+
+        for c in MJ_CODAS:
+            if s.startswith(c):
+                coda = c
+                s = s[len(c):]
+                break
+
+        if coda is None:
+            raise Exception('No matching final')
+
+        # the rest is the tone
+        tone = None
+        if s in MJ_TONES:
+            tone = TONE_MAPPINGS[s]
+
+        if tone is None:
+            raise Exception('No matching tone.')
+
+        return MinjiangSyllable(initial, rime+coda, tone)