import uicu

# Get character information
char = uicu.Char('€')
print(char.name)         # 'EURO SIGN'
print(char.category)     # 'Sc' (Currency Symbol)
print(char.script)       # 'Zyyy' (Common)
print(char.block)        # 'Currency Symbols'

# Direct function access
print(uicu.name('你'))    # 'CJK UNIFIED IDEOGRAPH-4F60'
print(uicu.script('A'))   # 'Latn'

# Note: Multi-codepoint strings (like flag emojis) need special handling
# char = uicu.Char('🎉')  # ✅ Works: Party popper (single codepoint)
# char = uicu.Char('🇺🇸')  # ❌ Fails: US flag (two codepoints)

import uicu

# Create a locale-specific collator
collator = uicu.Collator('de-DE')  # German collation rules

# Sort strings according to locale
words = ['Müller', 'Mueller', 'Mahler']
sorted_words = collator.sort(words)
print(sorted_words)  # German-specific ordering

# Numeric sorting
numeric_collator = uicu.Collator('en-US', numeric=True)
items = ['item10', 'item2', 'item1']
print(numeric_collator.sort(items))  # ['item1', 'item2', 'item10']

# Direct comparison
print(uicu.compare('café', 'cafe', 'en-US'))  # 1 (café > cafe)

import uicu

# Break text into user-perceived characters (grapheme clusters)
text = "👨‍👩‍👧‍👦"  # Family emoji
print(list(uicu.graphemes(text)))  # ['👨‍👩‍👧‍👦'] - single grapheme!

# Word segmentation
text = "Hello, world! How are you?"
words = list(uicu.words(text))
print(words)  # ['Hello', 'world', 'How', 'are', 'you']

# Sentence segmentation
text = "Dr. Smith went to N.Y.C. yesterday. He's busy!"
sentences = list(uicu.sentences(text))
print(sentences)  # Handles abbreviations correctly

# Language-specific segmentation
thai_text = "สวัสดีครับ"
thai_words = list(uicu.words(thai_text, locale='th-TH'))

import uicu

# Convert between scripts
trans = uicu.Transliterator('Greek-Latin')
print(trans.transliterate('Ελληνικά'))  # 'Ellēniká'

# Remove accents
trans = uicu.Transliterator('Latin-ASCII')
print(trans.transliterate('café résumé'))  # 'cafe resume'

# Chain transformations
trans = uicu.Transliterator('Any-Latin; Latin-ASCII; Lower')
print(trans.transliterate('北京'))  # 'bei jing'

# Case transformations
upper = uicu.Transliterator('Upper')
print(upper.transliterate('hello'))  # 'HELLO'

import uicu

# Create and inspect locales
locale = uicu.Locale('zh-Hant-TW')
print(locale.language)     # 'zh'
print(locale.script)       # 'Hant'
print(locale.region)       # 'TW'
print(locale.display_name) # 'Chinese (Traditional, Taiwan)'

# Get system default locale
default = uicu.get_default_locale()
print(default.language_tag)  # e.g., 'en-US'

# List available locales
locales = uicu.get_available_locales()
print(f"Available locales: {len(locales)}")  # 700+ locales

# Create locale-specific services
formatter = locale.get_datetime_formatter(date_style='long', time_style='short')
# Date/time formatting with locale-specific patterns

# Primary strength - ignores case and accents
collator = uicu.Collator('en-US', strength='primary')
print(collator.compare('café', 'CAFE'))  # 0 (equal)

# Secondary strength - considers accents but not case
collator = uicu.Collator('en-US', strength='secondary')
print(collator.compare('café', 'CAFÉ'))  # 0 (equal)
print(collator.compare('café', 'cafe'))  # 1 (café > cafe)

# Tertiary strength (default) - considers case
collator = uicu.Collator('en-US', strength='tertiary')
print(collator.compare('café', 'Café'))  # 1 (café > Café)

# Create reusable segmenters for better performance
word_segmenter = uicu.WordSegmenter('en-US')
sentences = [
    "This is a test.",
    "Another sentence here.",
    "And one more!"
]

for sentence in sentences:
    words = list(word_segmenter.segment(sentence))
    print(f"{len(words)} words: {words}")

# Detect the primary script in text
print(uicu.detect_script('Hello'))      # 'Latn'
print(uicu.detect_script('你好'))        # 'Hani'
print(uicu.detect_script('مرحبا'))      # 'Arab'
print(uicu.detect_script('Привет'))     # 'Cyrl'