# Import the required libraries
import re
from collections import Counter

# The (mini)corpus for initial development originally comes from Wikipedia thanks to http://lukelindemann.com/wiki_corpus.html
path_corpus = "Sundanese.txt"

def words(text): return re.findall(r'\w+', text.lower())

WORDS = Counter(words(open(path_corpus, encoding='utf8').read()))

def P(word, N=sum(WORDS.values())): 
    "Probability of `word`."
    return WORDS[word] / N

def correction(word): 
    "Most probable spelling correction for word."
    return max(candidates(word), key=P)

# Candidate model
def candidates(word): 
    "Generate possible spelling corrections for word."
    return (known([word]) or known(edits1(word)) or known(edits2(word)) or [word])

# Error model
def known(words): 
    "The subset of `words` that appear in the dictionary of WORDS."
    return set(w for w in words if w in WORDS)

def edits1(word):
    "All edits that are one edit away from `word`."
    letters    = 'abcdefghijklmnopqrstuvwxyz'
    splits     = [(word[:i], word[i:])    for i in range(len(word) + 1)]
    deletes    = [L + R[1:]               for L, R in splits if R]
    transposes = [L + R[1] + R[0] + R[2:] for L, R in splits if len(R)>1]
    replaces   = [L + c + R[1:]           for L, R in splits if R for c in letters]
    inserts    = [L + c + R               for L, R in splits for c in letters]
    return set(deletes + transposes + replaces + inserts)

def edits2(word): 
    "All edits that are two edits away from `word`."
    return (e2 for e1 in edits1(word) for e2 in edits1(e1))

# Create a Gradio app
import gradio as gr

def correct_sentence(sentence):
    # Split the sentence into words
    words = re.findall(r'\b[\w\']+\b', sentence)
    
    # Correct the spelling of each word
    corrected_words = []
    for word in words:
        corrected_word = correction(word)
        corrected_words.append(corrected_word)
    
    # Join the corrected words into a sentence
    corrected_sentence = ' '.join(corrected_words)
    
    return corrected_sentence

app = gr.Interface(correct_sentence, [gr.inputs.Textbox()], gr.outputs.Textbox(),
                    examples=["anying, kuer jangarr sirah sok hayanh dahar nu lada hasuem."],
                    title="Sundanese spell-checker app",
                    description="This app check the Sundanese spell based on the probabilty theory.")
app.launch()