"""
Урок 60. Регулярные выражения — весь код примеров одним файлом.

Источник: subjects/python-fundamentals/course/lessons/60-regular-expressions/examples.html
Файл собран автоматически (tools/build_lesson_examples.py): правьте страницу урока.
Запуск: python lesson-60.py
"""



# ====================================================================
# Пример 1. Поиск всех чисел
# ====================================================================
# regex_01_findall.py
import re


def extract_numbers(text: str) -> list[str]:
    return re.findall(r"\d+", text)


if __name__ == "__main__":
    sample = "Python 3.9, Java 17, C++ 14"
    print(extract_numbers(sample))  # ['3', '9', '17', '14']


# ====================================================================
# Пример 2. Почему важен r"..."
# ====================================================================
# regex_02_raw_string.py
import re


# С r: ищем цифры
print(re.findall(r"\d+", "Price: 123"))  # ['123']

# Без r: Python превращает \d в обычную букву d
print(re.findall("\d+", "Price: 123"))   # []


# ====================================================================
# Пример 3. Классы символов
# ====================================================================
# regex_03_char_classes.py
import re


text = "\tPython 3.12, Java 17, C++ 14!\n"
print("Цифры:", re.findall(r"\d", text))
print("Двузначные:", re.findall(r"\d\d", text))
print("Буквы/цифры/_:", re.findall(r"\w", text))
print("Пробелы:", re.findall(r"\s", text))
print("Всё кроме \n:", re.findall(r".", text))


# ====================================================================
# Пример 4. Квантификаторы
# ====================================================================
# regex_04_quantifiers.py
import re


text = """
Orders: ID123, ID4567, ID89
Numbers: 123-45-67, 321-45-67
Prices: 100$, 199.50$, 99.99€, 0.49€, .99€
Files: report.txt, report2.txt, report10.txt
"""
print("ID-коды:", re.findall(r"ID\d{2,}", text))
print("Телефоны:", re.findall(r"\d{3}-\d{2}-\d{2}", text))
print("Цены:", re.findall(r"\d+\.\d+", text))
print("Файлы:", re.findall(r"report\d*\.txt", text))


# ====================================================================
# Пример 5. Жадные и ленивые квантификаторы
# ====================================================================
# regex_05_greedy_lazy.py
import re


text = "<div>Hello</div><div>World</div>"
greedy = re.findall(r"<.*>", text)
lazy = re.findall(r"<.*?>", text)
print("Жадно:", greedy)
print("Лениво:", lazy)


# ====================================================================
# Пример 6. Якоря
# ====================================================================
# regex_06_anchors.py
import re


text = "Hello world! Welcome to world"
print(re.findall(r"^\w+", text))   # ['Hello']
print(re.findall(r"\w+$", text))   # ['world']

text2 = "category wildcat education _cat_ catalog"
print(re.findall(r"\bcat\w*", text2))   # ['cat', 'catalog']


# ====================================================================
# Пример 7. re.search vs re.match
# ====================================================================
# regex_07_search_match.py
import re


text = "ID12345 is confirmed. ID23456 is confirmed"

match_search = re.search(r"ID\d+", text)
print("search:", match_search.group() if match_search else None)  # ID12345

match_match = re.match(r"ID\d+", text)
print("match:", match_match.group() if match_match else None)    # ID12345

# Тот же шаблон, но текст начинается не с ID
print(re.match(r"ID\d+", "Confirmed: ID12345"))  # None


# ====================================================================
# Пример 7a. re.finditer
# ====================================================================
# regex_07a_finditer.py
import re


text = "Order ID: 12345, Invoice No: 67890, Ref: ABC9876"
for match in re.finditer(r"\d+", text):
    print(f"{match.group():>8} at {match.span()}")


# ====================================================================
# Пример 8. Группы и негруппирующие скобки
# ====================================================================
# regex_08_groups.py
import re


text = "Order ID: 12345, Invoice No: 67890"
match = re.search(r"Order ID: (\d+), Invoice No: (\d+)", text)
if match:
    print(f"Order: {match.group(1)}, Invoice: {match.group(2)}")

# Негруппирующие скобки: валюта не попадает в результат
amounts = re.findall(r"(?:USD|EUR|GBP) (\d+)", "USD 100, EUR 200, GBP 300")
print(amounts)  # ['100', '200', '300']


# ====================================================================
# Пример 9. re.sub и re.split
# ====================================================================
# regex_09_sub_split.py
import re


raw = "apple,   banana ,  orange ,grape"
clean = re.sub(r"\s*,\s*", ", ", raw)
print(clean)

# Разделить по запятым, точкам, пробелам и переводам строк
words = re.split(r"[,\.\s]+", "Python is popular. It is used in web, data, and automation.")
print([w for w in words if w])


# ====================================================================
# Пример 10. Компиляция шаблона
# ====================================================================
# regex_10_compile.py
import re


texts = [
    "Order ID: 12345, Invoice No: 67890",
    "Shipment ID: 54321, Tracking No: 98765",
]
number_pattern = re.compile(r"\d+")

for text in texts:
    matches = number_pattern.findall(text)
    print(matches)


# ====================================================================
# Пример 11. Флаги
# ====================================================================
# regex_11_flags.py
import re


# Регистронезависимый поиск
print(re.search(r"python", "Python is fun", re.IGNORECASE).group())

# DOTALL: точка совпадает с переводом строки
text = "line1\nline2"
print(re.findall(r".*", text, re.DOTALL))

# MULTILINE: ^/$ для каждой строки
multiline = "Start one\nStart two\nEnd here"
print(re.findall(r"^Start", multiline, re.MULTILINE))