from unscript import unscript, clean_text, clean_script, detect_script, ranges, in_range

# Most common use case: complete text cleaning for a specific script
text = "Hello @user! Check https://example.com 😊 مرحبا $123.45"
result = unscript("Latn", text, {"numbers": True, "symbols": True})
print(result)  # Output: "hello check $123.45"

# For general cleaning without script filtering
clean_result = clean_text(text)
print(clean_result)  # Output: "hello ! check مرحبا $123.45"

# For script filtering only (keeps original case, URLs, mentions)
script_result = clean_script("Latn", text, {"numbers": True, "symbols": True})
print(script_result)  # Output: "Hello @user Check https //example com 😊 $123.45"

# Multiple scripts: keep Latin OR Arabic
multi = clean_script(["Latn", "Arab"], "Hello مرحبا 你好")
print(multi)  # Output: "Hello مرحبا"

# Allow up to N words from other scripts (optionally restricted)
mix_cfg = {"max_foreign_words": 1, "foreign_scripts": ["Arab"]}
kept = clean_script("Latn", "Hello مرحبا 你好", mix_cfg)
print(kept)  # Output: "Hello مرحبا"

# For detecting script composition
detect_result = detect_script(text)
print(detect_result)  # Output: {'Latn': 71.43, 'Arab': 28.57}

# For checking individual characters against Unicode ranges
print(in_range('ا', ranges.Arab))    # True - Arabic character
print(in_range('A', ranges.Latn))    # True - Latin character
print(in_range('5', ranges.numbers)) # True - Digit character

# Check multiple ranges (OR logic)
print(in_range('5', ranges.Arab, ranges.numbers))  # True - character is a number

from unscript import unscript

# Basic usage with Latin script
text1 = "Hello @user! Check https://example.com 😊 مرحبا"
result1 = unscript("Latn", text1)
print(result1)
# Expected output: "hello check"

# Arabic script with punctuation
text2 = "مرحبا @user بالعالم! https://example.com"
result2 = unscript("Arab", text2, {"punctuation": True})
print(result2)
# Expected output: "مرحبا بالعالم!"

# Latin script with numbers and symbols
text3 = "Price: $123.45 @user!"
result3 = unscript("Latn", text3, {"numbers": True, "symbols": True})
print(result3)
# Expected output: "price $123.45"

# Preserve case
text4 = "HELLO @user WORLD!"
result4 = unscript("Latn", text4, lowercase=False)
print(result4)
# Expected output: "HELLO WORLD"

from unscript import clean_text

text1 = "Hello world! This is a test @user #python https://example.com 😊 coooooolllll"
cleaned_text1 = clean_text(text1)
print(cleaned_text1)
# Expected output: "hello world! this is a test cooll"

text2 = "Price is $123.45 @user"
cleaned_text2 = clean_text(text2)
print(cleaned_text2)
# Expected output: "price is $123.45"

# Preserve case
text3 = "Hello WORLD @user"
cleaned_text3 = clean_text(text3, lowercase=False)
print(cleaned_text3)
# Expected output: "Hello WORLD"

from unscript import clean_script

# Example 1: Latin script, no numbers or punctuation
text_latin = "Hello World! 123 مرحبا"
cleaned_latin = clean_script("Latn", text_latin)
print(cleaned_latin)
# Expected output: "Hello World"

# Example 2: Arabic script, with numbers
text_arabic = "مرحبا بالعالم 123! Hello"
cleaned_arabic = clean_script("Arab", text_arabic, {"numbers": True})
print(cleaned_arabic)
# Expected output: "مرحبا بالعالم 123"

# Example 3: Chinese script, with punctuation
text_chinese = "你好。世界！This is a test."
cleaned_chinese = clean_script("Hans", text_chinese, {"punctuation": True})
print(cleaned_chinese)
# Expected output: "你好。世界！"

# Example 5: Multiple scripts OR logic
text_multi = "Hello مرحبا 你好"
print(clean_script(["Latn", "Arab"], text_multi))
# Expected output: "Hello مرحبا"

# Example 6: Allow N words from other scripts
text_mix = "Hello مرحبا 你好 test"
print(clean_script("Latn", text_mix, {"max_foreign_words": 2}))
# Expected output: "Hello مرحبا 你好 test"
print(clean_script("Latn", text_mix, {"max_foreign_words": 1, "foreign_scripts": "Arab"}))
# Expected output: "Hello مرحبا test"

# Example 4: Devanagari script, with punctuation
text_devanagari = "नमस्ते। यह है॥ 987"
cleaned_devanagari = clean_script("Deva", text_devanagari, {"punctuation": True})
print(cleaned_devanagari)
# Expected output: "नमस्ते। यह है॥"

from unscript import ranges

# Access script ranges
arabic_ranges = ranges.Arab
print(len(arabic_ranges))  # Number of Unicode ranges for Arabic script

# Access category ranges  
number_ranges = ranges.numbers
punctuation_ranges = ranges.punctuation

# Alternative access through organized objects
latin_ranges = ranges.scripts.Latn
symbol_ranges = ranges.categories.symbols

# List all available ranges
print(ranges.list_scripts())    # ['Arab', 'Armn', 'Beng', 'Brai', ...]
print(ranges.list_categories()) # ['numbers', 'punctuation', 'spaces', 'symbols']

# Get information about a range
info = ranges.get_range_info('Arab')
print(info['type'])         # 'script'
print(info['range_count'])  # Number of Unicode ranges

from unscript import ranges, in_range

# Check if character is in a single range
print(in_range('ا', ranges.Arab))      # True - Arabic character
print(in_range('A', ranges.Latn))      # True - Latin character  
print(in_range('5', ranges.numbers))   # True - Digit character
print(in_range('!', ranges.punctuation)) # True - Punctuation

# Check multiple ranges (OR logic)
print(in_range('5', ranges.Arab, ranges.numbers))  # True - in numbers
print(in_range('ا', ranges.Arab, ranges.numbers))  # True - in Arabic
print(in_range('A', ranges.Arab, ranges.numbers))  # False - in neither

# Mix script and category ranges
print(in_range('!', ranges.Latn, ranges.punctuation))  # True - punctuation
print(in_range('A', ranges.Latn, ranges.punctuation))  # True - Latin
print(in_range('你', ranges.Latn, ranges.punctuation)) # False - Chinese

# Advanced filtering example
text = "Hello مرحبا 123!"
latin_or_arabic = [char for char in text if in_range(char, ranges.Latn, ranges.Arab)]
print(''.join(latin_or_arabic))  # "Helloمرحبا"

# Check if character is Arabic OR a digit
is_arabic_or_digit = lambda c: in_range(c, ranges.Arab, ranges.numbers)
print(is_arabic_or_digit('ا'))  # True
print(is_arabic_or_digit('5'))  # True
print(is_arabic_or_digit('A'))  # False

from unscript import ranges, in_range

# Filter multilingual text by script
def filter_by_scripts(text, *script_ranges):
    """Keep only characters from specified scripts."""
    return ''.join(char for char in text 
                  if in_range(char, *script_ranges) or char.isspace())

# Example usage
mixed_text = "Hello مرحبا 你好 123!"
latin_arabic = filter_by_scripts(mixed_text, ranges.Latn, ranges.Arab)
print(latin_arabic)  # "Hello مرحبا   !"

# Content validation
def is_script_compliant(text, script_range, allow_numbers=True, allow_punctuation=True):
    """Check if text only contains allowed character types."""
    allowed_ranges = [script_range]
    if allow_numbers:
        allowed_ranges.append(ranges.numbers)
    if allow_punctuation:
        allowed_ranges.append(ranges.punctuation)
    
    for char in text:
        if char.isspace():
            continue
        if not in_range(char, *allowed_ranges):
            return False
    return True

# Example usage
arabic_text = "مرحبا بالعالم 123!"
print(is_script_compliant(arabic_text, ranges.Arab))  # True

latin_text = "Hello World 你好!"  # Contains Chinese
print(is_script_compliant(latin_text, ranges.Latn))   # False

from unscript import detect_script

# Basic usage - only script percentages
text1 = "Hello World!"
result1 = detect_script(text1)
print(result1)
# Expected output: {'Latn': 100.0}

# Mixed scripts
text2 = "Hello مرحبا 你好"
result2 = detect_script(text2)
print(result2)
# Expected output: {'Latn': 41.67, 'Arab': 41.67, 'Hans': 16.67}

# Including categories for detailed analysis
text3 = "Hello مرحبا 123!"
result3 = detect_script(text3, include_categories=True)
print(result3)
# Expected output: {'Latn': 41.67, 'Arab': 25.0, 'spaces': 16.67, 'punctuation': 8.33, 'numbers': 8.33}

# With minimum threshold to filter out minor scripts
text4 = "Hello World! مرحبا"
result4 = detect_script(text4, min_threshold=10.0)
print(result4)
# Expected output: {'Latn': 77.78, 'Arab': 22.22}

from unscript import detect_script_detailed

text = "Hi! 你好"
result = detect_script_detailed(text)

print(result['summary'])
# Expected output: {'Latn': 40.0, 'Hans': 40.0, 'punctuation': 20.0}

print(result['total_chars'])
# Expected output: 5

print(result['script_chars'])
# Expected output: {'Latn': ['H', 'i'], 'Hans': ['你', '好']}

print(result['category_chars'])
# Expected output: {'punctuation': ['!']}

from unscript import get_dominant_script

# Clear majority
text1 = "Hello world! This is a long English sentence."
result1 = get_dominant_script(text1)
print(result1)
# Expected output: "Latn"

# Mixed text with no clear dominant script
text2 = "Hello مرحبا 你好"
result2 = get_dominant_script(text2)
print(result2)
# Expected output: None

# Custom threshold
text3 = "Hello مرحبا"
result3 = get_dominant_script(text3, min_percentage=20.0)
print(result3)
# Expected output: "Latn" (since Latin has >20%)

from unscript import is_script_mixed

# Mixed scripts
text1 = "Hello مرحبا"
result1 = is_script_mixed(text1)
print(result1)
# Expected output: True

# Single script
text2 = "Hello world!"
result2 = is_script_mixed(text2)
print(result2)
# Expected output: False

# Custom threshold
text3 = "Hello World مرحبا"  # ~75% Latin, ~25% Arabic
result3 = is_script_mixed(text3, threshold=30.0)
print(result3)
# Expected output: False (Arabic doesn't meet 30% threshold)

from unscript import unscript, detect_script

# Clean text for specific language models
arabic_text = unscript("Arab", "مرحبا @user! تحقق من https://example.com 😊")
print(arabic_text)  # "مرحبا تحقق من"

# Detect script composition for language routing
mixed_text = "Hello مرحبا 你好"
scripts = detect_script(mixed_text)
if scripts.get("Arab", 0) > 30:
    # Route to Arabic NLP pipeline
    process_arabic(mixed_text)

from unscript import is_script_mixed, get_dominant_script

# Validate content language
user_input = "User's multilingual text"
if is_script_mixed(user_input):
    print("Please use a single language")
else:
    dominant = get_dominant_script(user_input)
    print(f"Detected language script: {dominant}")

from unscript import detect_script_detailed

# Analyze document composition
document = "Large multilingual document..."
analysis = detect_script_detailed(document)
print(f"Total characters: {analysis['total_chars']}")
print(f"Script distribution: {analysis['summary']}")
print(f"Scripts found: {list(analysis['script_chars'].keys())}")

from unscript import ranges, in_range

# Advanced content filtering
def filter_content(text, allowed_scripts=None, allow_digits=True, allow_punctuation=True):
    """Filter text to only include specific character types."""
    if allowed_scripts is None:
        allowed_scripts = [ranges.Latn]  # Default to Latin
    
    extra_ranges = []
    if allow_digits:
        extra_ranges.append(ranges.numbers)
    if allow_punctuation:
        extra_ranges.append(ranges.punctuation)
    
    filtered_chars = []
    for char in text:
        if char.isspace():  # Always allow spaces
            filtered_chars.append(char)
        elif in_range(char, *(allowed_scripts + extra_ranges)):
            filtered_chars.append(char)
        else:
            filtered_chars.append(' ')  # Replace unwanted chars with space
    
    return ''.join(filtered_chars).strip()

# Example usage
multilingual_text = "Hello مرحبا 你好 123! Welcome to unscript."

# Keep only Latin + numbers + punctuation
latin_only = filter_content(multilingual_text, [ranges.Latn])
print(latin_only)  # "Hello     123! Welcome to unscript."

# Keep Arabic + Latin + numbers
arabic_latin = filter_content(multilingual_text, [ranges.Arab, ranges.Latn])
print(arabic_latin)  # "Hello مرحبا   123! Welcome to unscript."

# Input validation for forms
def validate_script_input(text, script_range, max_other_script_ratio=0.1):
    """Validate that text is primarily in the expected script."""
    script_chars = sum(1 for char in text if in_range(char, script_range))
    total_chars = len([char for char in text if not char.isspace()])
    
    if total_chars == 0:
        return True
    
    script_ratio = script_chars / total_chars
    return script_ratio >= (1 - max_other_script_ratio)

# Examples
arabic_form_input = "مرحبا بك في موقعنا"
print(validate_script_input(arabic_form_input, ranges.Arab))  # True

mixed_input = "مرحبا hello world"  # Mixed Arabic and Latin
print(validate_script_input(mixed_input, ranges.Arab))       # False