"""
Урок 61. Практикум 15 — весь код примеров одним файлом.

Источник: subjects/python-fundamentals/course/lessons/61-practice-15/examples.html
Файл собран автоматически (tools/build_lesson_examples.py): правьте страницу урока.
Запуск: python lesson-61.py
"""



# ====================================================================
# Пример 1. re.compile + findall — база всех текстовых заданий
# ====================================================================
import re

text = "Order #123, code: ABC-42, id: 007"
number_re = re.compile(r"\d+")
print(number_re.findall(text))
# ['123', '42', '007']


# ====================================================================
# Пример 2. Очистка строки: re.sub(r"\D", "", ...)
# ====================================================================
import re

raw = "+49 157 1234-5678"
clean = re.sub(r"\D", "", raw)
print(clean)
# 4915712345678


# ====================================================================
# Пример 3. Собираем шаблон немецкого номера по частям
# ====================================================================
import re

phone_re = re.compile(r"(?:\+49|0049)[\s\-]*1[5-7](?:[\s\-]*\d){7,9}")
sample = "Call +49 157 12345678 or 0049-160-9876543 or +49 89 123456 (landline)"
print(phone_re.findall(sample))
# ['+49 157 12345678', '0049-160-9876543']


# ====================================================================
# Пример 4. Валидация после regex — фильтр первого приближения
# ====================================================================
def clean_and_validate(raw_match: str) -> str | None:
    digits = re.sub(r"\D", "", raw_match)
    if digits.startswith("0049"):
        digits = digits[4:]
    elif digits.startswith("49"):
        digits = digits[2:]
    if digits[:2] not in ("15", "16", "17"):
        return None
    if not (10 <= len(digits) <= 12):
        return None
    return f"+49{digits}"

candidates = phone_re.findall(sample)
valid = [n for n in (clean_and_validate(c) for c in candidates) if n]
print(valid)
# ['+4915712345678', '+491609876543']


# ====================================================================
# Пример 5. Границы слова в email: почему нельзя жадный класс символов
# ====================================================================
local = r"[a-zA-Z0-9_](?:[a-zA-Z0-9._]*[a-zA-Z0-9_])?"
email_re = re.compile(rf"\b{local}@[a-zA-Z0-9.-]+\.[a-zA-Z]{{2,3}}\b")
sample_emails = "ok: user.name@sub.domain.com, bad: .user@example.com, bad2: user.@example.com"
print(email_re.findall(sample_emails))
# ['user.name@sub.domain.com', 'user@example.com']


# ====================================================================
# Пример 6. Номер карты: повторяющаяся группа (?:\d{4}[- ]?){3}\d{4}
# ====================================================================
card_re = re.compile(r"\b(?:\d{4}[- ]?){3}\d{4}\b")
sample_cards = "1234 5678 9012 3456 and 1234--5678--9012--3456 and 1234567812345678"
print(card_re.findall(sample_cards))
# ['1234 5678 9012 3456', '1234567812345678']


# ====================================================================
# Пример 7. JSON туда и обратно через pathlib
# ====================================================================
import json
from pathlib import Path

students = [
    {"name": "Alice", "subject": "Math", "grade": 90, "date": "12-03-2025"},
    {"name": "Alice", "subject": "Math", "grade": 70, "date": "20-04-2025"},
]
json_path = Path("students.json")
json_path.write_text(json.dumps(students, indent=2, ensure_ascii=False), encoding="utf-8")

loaded = json.loads(json_path.read_text(encoding="utf-8"))
print(loaded[0])
# {'name': 'Alice', 'subject': 'Math', 'grade': 90, 'date': '12-03-2025'}


# ====================================================================
# Пример 8. Дата → квартал: datetime.strptime и своя функция
# ====================================================================
from datetime import datetime

def get_quarter(date_str: str) -> str | None:
    month = datetime.strptime(date_str, "%d-%m-%Y").month
    if 1 <= month <= 3:
        return "Q1"
    if 4 <= month <= 5:
        return "Q2"
    if 9 <= month <= 12:
        return "Q3"
    return None  # летние месяцы пропускаем

for date_str in ("12-03-2025", "20-04-2025", "06-09-2025"):
    print(date_str, "->", get_quarter(date_str))
# 12-03-2025 -> Q1
# 20-04-2025 -> Q2
# 06-09-2025 -> Q3


# ====================================================================
# Пример 9. Группировка без if: defaultdict(lambda: defaultdict(list))
# ====================================================================
from collections import defaultdict

entries = [
    {"name": "Alice", "grade": 90, "date": "12-03-2025"},
    {"name": "Alice", "grade": 70, "date": "20-04-2025"},
    {"name": "Alice", "grade": 80, "date": "06-09-2025"},
]

by_quarter: defaultdict[str, list[int]] = defaultdict(list)
for row in entries:
    quarter = get_quarter(row["date"])
    if quarter:
        by_quarter[quarter].append(row["grade"])

report = {q: round(sum(v) / len(v), 2) for q, v in by_quarter.items()}
print(report)
# {'Q1': 90.0, 'Q2': 70.0, 'Q3': 80.0}


# ====================================================================
# Пример 10. Генератор + regex: лениво читаем файл и сразу фильтруем
# ====================================================================
from pathlib import Path

def emails_from_file(path: Path):
    with path.open(encoding="utf-8") as file:
        for line in file:
            for match in email_re.finditer(line):
                yield match.group()

contacts = Path("contacts.txt")
contacts.write_text(
    "Alice - alice@example.com\nnot an email line\nBob - bob.work@company.org\n",
    encoding="utf-8",
)
print(list(emails_from_file(contacts)))
# ['alice@example.com', 'bob.work@company.org']