Homophones Detection

from myspellchecker.core.homophones import HomophoneChecker

checker = HomophoneChecker()

# Get homophones for a word
homophones = checker.get_homophones("ကား")
print(homophones)  # {"ကာ"}

# Check if word has homophones
has_homophones = checker.has_homophone("ကား")
print(has_homophones)  # True

# Use custom homophone map
custom_map = {
    "ကား": {"ကာ"},
    "ကာ": {"ကား"},
    "သာ": {"သား"},
    "သား": {"သာ"}
}

checker = HomophoneChecker(homophone_map=custom_map)

# Load from grammar config
checker = HomophoneChecker(config_path="/path/to/config")

# Or use default config (loads from rules/homophones.yaml)
checker = HomophoneChecker()

from myspellchecker.core.validation_strategies.homophone_strategy import (
    HomophoneValidationStrategy
)

strategy = HomophoneValidationStrategy(
    homophone_checker=checker,
    provider=ngram_provider,
    confidence=0.80,
    improvement_ratio=5.0,   # Require 5x better probability
    min_probability=0.001    # Minimum threshold to prevent false positives
)

# When current word has zero probability (unseen n-gram):
# - Without threshold: ANY positive probability triggers suggestion
# - With threshold: Only probabilities >= min_probability trigger suggestion

# Example with min_probability=0.001:
# Homophone with prob 0.01   → suggested (0.01 >= 0.001)
# Homophone with prob 0.0001 → NOT suggested (0.0001 < 0.001)

# "ကား သွား" (went by car) vs "ကာ သွား" (shield went — nonsensical)
# Context suggests "ကား" (car) is the correct word here

words = ["ကာ", "သွား", "တယ်"]
context = ValidationContext(
    sentence="ကာ သွား တယ်",
    words=words,
    word_positions=[0, 3, 8]  # Unicode code point offsets
)

errors = strategy.validate(context)
# May suggest "ကား" instead of "ကာ" based on context

from myspellchecker import SpellChecker
from myspellchecker.core.config import SpellCheckerConfig
from myspellchecker.providers import SQLiteProvider

config = SpellCheckerConfig(
    use_context_checker=True  # Enables homophone detection
)

provider = SQLiteProvider(database_path="path/to/dictionary.db")
checker = SpellChecker(config=config, provider=provider)
result = checker.check("ကာ သွား တယ်")

# Homophone errors have type "homophone_error"
for error in result.errors:
    if error.error_type == "homophone_error":
        print(f"{error.text} → {error.suggestions[0]}")

version: "1.1.0"
category: "homophones"

homophones:
  # Each entry maps a word to its homophones (simple list format)
  "ကား": ["ကာ"]            # car vs protect/shield
  "ကာ": ["ကား"]
  "ကျောင်း": ["ကြောင်း"]  # school vs reason
  "ကြောင်း": ["ကျောင်း"]
  "ကံ": ["ကန်", "ကင်"]    # luck vs kick vs (rare)
  "ကန်": ["ကံ", "ကင်"]