Phonetic Data

from myspellchecker.text.phonetic_data import (
    PHONETIC_GROUPS,
    VISUAL_SIMILAR,
    TONAL_GROUPS,
    COLLOQUIAL_SUBSTITUTIONS,
)

# Check phonetic group for a consonant
labial_consonants = PHONETIC_GROUPS["p"]  # ["ပ", "ဖ", "ဗ", "ဘ"]

# Check visual similarity
similar_to_i = VISUAL_SIMILAR["ိ"]  # {"ီ"}

VISUAL_SIMILAR = {
    "ိ": {"ီ"},   # short i vs long ii
    "ု": {"ူ"},   # short u vs long uu
    "ာ": {"ါ"},   # different aa marks
    "ျ": {"ြ"},   # ya-yit vs ya-pin
    "န": {"ည"},   # na vs nya
    "င": {"ည", "ဉ"},  # nga vs nya variants
    "ရ": {"ယ"},   # ra vs ya
    "ယ": {"ရ"},   # ya vs ra (bidirectional)
    "သ": {"ဿ"},   # sa vs great sa
    "ဿ": {"သ"},   # great sa vs sa (bidirectional)
    "ပ": {"ဗ"},   # pa vs ba
    "ဗ": {"ပ"},   # ba vs pa (bidirectional)
    "ည": {"ဉ"},   # nya vs archaic nya
    "ဉ": {"ည"},   # archaic nya vs nya (bidirectional)
    # Aspirated vs unaspirated pairs
    "က": {"ခ"}, "ခ": {"က"},
    "ဂ": {"ဃ"}, "ဃ": {"ဂ"},
    "စ": {"ဆ"}, "ဆ": {"စ"},
    "တ": {"ထ"}, "ထ": {"တ"},
    "ဒ": {"ဓ"}, "ဓ": {"ဒ"},
    "ဖ": {"ဘ"}, "ဘ": {"ဖ"},
    # Retroflex pairs
    "ဋ": {"ဌ"}, "ဌ": {"ဋ"},
    "ဍ": {"ဎ"}, "ဎ": {"ဍ"},
    # LA variants
    "လ": {"ဠ"}, "ဠ": {"လ"},
    # Medial confusions
    "ွ": {"ှ"}, "ှ": {"ွ"},
}

# Both directions are mapped for most pairs
VISUAL_SIMILAR["ရ"] = {"ယ"}
VISUAL_SIMILAR["ယ"] = {"ရ"}

TONAL_GROUPS = {
    # Vowel 'a' variants
    "ာ": ["ာ", "့", "း", "ား", ""],

    # Vowel 'i' variants
    "ိ": ["ိ", "ီ", "ိ့", "ီး"],
    "ီ": ["ိ", "ီ", "ိ့", "ီး"],

    # Vowel 'u' variants
    "ု": ["ု", "ူ", "ု့", "ူး"],
    "ူ": ["ု", "ူ", "ု့", "ူး"],

    # Vowel 'e' variants
    "ေ": ["ေ", "ေ့", "ေး"],
    "ဲ": ["ဲ", "ဲ့"],

    # Tone marks
    "့": ["", "း"],  # Dot Below -> empty or Visarga
    "း": ["", "့"],  # Visarga -> empty or Dot Below
}

COLLOQUIAL_SUBSTITUTIONS = {
    "အုန်း": {"ဦး"},  # Coconut -> Particle
    "အုံး": {"ဦး"},   # Pillow -> Particle
}

from myspellchecker.text.phonetic import PhoneticHasher
from myspellchecker.text.phonetic_data import PHONETIC_GROUPS

class PhoneticHasher:
    def __init__(self):
        # Build reverse mapping from char to group
        self.char_to_group = {}
        for group, chars in PHONETIC_GROUPS.items():
            for char in chars:
                self.char_to_group[char] = group

    def hash(self, word: str) -> str:
        """Generate phonetic hash."""
        result = []
        for char in word:
            if char in self.char_to_group:
                result.append(self.char_to_group[char])
            else:
                result.append(char)
        return "".join(result)

from myspellchecker.text.phonetic_data import VISUAL_SIMILAR

def find_visual_variants(word: str) -> List[str]:
    """Generate visually similar variants of a word."""
    variants = []
    for i, char in enumerate(word):
        if char in VISUAL_SIMILAR:
            for similar in VISUAL_SIMILAR[char]:
                variant = word[:i] + similar + word[i+1:]
                variants.append(variant)
    return variants

# Example
variants = find_visual_variants("ကိုယ်")
# ["ကီုယ်"] - short i replaced with long ii

from myspellchecker.text.phonetic_data import TONAL_GROUPS

def generate_tonal_variants(word: str) -> List[str]:
    """Generate tonal variants of a word."""
    variants = [word]
    for i, char in enumerate(word):
        if char in TONAL_GROUPS:
            for variant_char in TONAL_GROUPS[char]:
                if variant_char != char:
                    variant = word[:i] + variant_char + word[i+1:]
                    variants.append(variant)
    return variants

# Example
variants = generate_tonal_variants("လာ")
# ["လာ", "လာ့", "လား", ...]

from myspellchecker.text.phonetic_data import (
    PHONETIC_GROUPS,            # Phonetic similarity groups
    VISUAL_SIMILAR,             # Visual confusability mapping
    MYANMAR_SUBSTITUTION_COSTS, # Weighted edit distance costs
    TONAL_GROUPS,               # Tonal variant mappings
    COLLOQUIAL_SUBSTITUTIONS,   # Colloquial -> standard mappings
    is_colloquial_variant,      # Check if word is colloquial
    get_standard_forms,         # Get standard forms for colloquial
    get_colloquial_variants,    # Get colloquial variants for standard
)