文字列とコンテナの総合演習

# CSV データの解析
line = "Alice,25,Beijing,Engineer"
fields = line.split(",")
print(fields)               # ['Alice', '25', 'Beijing', 'Engineer']

# 空白による分割（デフォルト）
text = "hello   world    python"
words = text.split()
print(words)                # ['hello', 'world', 'python']

# 分割数の制限
data = "2026-06-23-15-30-00"
parts = data.split("-", 3)
print(parts)                # ['2026', '06', '23', '15-30-00']

# 設定ファイルの解析をシミュレート
config_text = """
host=localhost
port=8080
debug=true
theme=dark
"""

# 行で分割 → 等号で分割 → 辞書に保存
config = {}
for line in config_text.strip().split("\n"):
    if "=" in line:
        key, value = line.split("=", 1)
        config[key.strip()] = value.strip()

print(config)
# {'host': 'localhost', 'port': '8080', 'debug': 'true', 'theme': 'dark'}

# 設定を読み取り
print(f"Current host: {config.get('host', 'localhost')}")
print(f"Current port: {config.get('port', '80')}")

{'host': 'localhost', 'port': '8080', 'debug': 'true', 'theme': 'dark'}
Current host: localhost
Current port: 8080

# 基本的な使い方
words = ["Hello", "World", "Python"]
sentence = " ".join(words)
print(sentence)             # Hello World Python

# カンマで結合
csv = ",".join(["Alice", "25", "Beijing"])
print(csv)                  # Alice,25,Beijing

# 改行で結合
lines = "\n".join(["First line", "Second line", "Third line"])
print(lines)

# ❌ 推奨しない — ループ内での文字列連結
result = ""
for i in range(1000):
    result += str(i) + ","
# これにより 1000 個の一時的な文字列オブジェクトが作成される

# ✅ 推奨 — リストに集めて join()
parts = [str(i) for i in range(1000)]
result = ",".join(parts)
# 1 回のマージで、はるかに効率的

# join + リスト内包表記でフォーマット済み表出力
headers = ["Name", "Age", "City"]
rows = [
    ["Alice", "25", "Beijing"],
    ["Bob", "30", "Shanghai"],
    ["Charlie", "22", "Guangzhou"],
]

# ヘッダー
print(" | ".join(headers))
print("-" * 25)

# データ行
for row in rows:
    print(" | ".join(row))

Name | Age | City
─────────────────────────
Alice | 25 | Beijing
Bob | 30 | Shanghai
Charlie | 22 | Guangzhou

# 文字列のソート — アルファベット順
text = "python"
sorted_chars = sorted(text)
print(sorted_chars)                 # ['h', 'n', 'o', 'p', 't', 'y']
print("".join(sorted_chars))        # hnopty — 再結合

# 辞書のソート — デフォルトでキーをソート
d = {"banana": 3, "apple": 5, "cherry": 2}
sorted_keys = sorted(d)
print(sorted_keys)                  # ['apple', 'banana', 'cherry']

# 値でソート
sorted_by_value = sorted(d.items(), key=lambda x: x[1])
print(sorted_by_value)              # [('cherry', 2), ('banana', 3), ('apple', 5)]

# セットのソート
s = {3, 1, 4, 1, 5, 9}
sorted_set = sorted(s)
print(sorted_set)                   # [1, 3, 4, 5, 9]

# ファイル名を数値部分でソート
files = ["file_10.txt", "file_2.txt", "file_1.txt", "file_20.txt"]

# 通常のソート — 文字列ソート、「10」は「2」より前に来る（'1' < '2' のため）
print(sorted(files))
# ['file_1.txt', 'file_10.txt', 'file_2.txt', 'file_20.txt']

# 数値部分でソート — 数値を抽出し int に変換してからソート
def extract_number(filename):
    num_str = filename.split("_")[1].split(".")[0]
    return int(num_str)

sorted_files = sorted(files, key=extract_number)
print(sorted_files)
# ['file_1.txt', 'file_2.txt', 'file_10.txt', 'file_20.txt']

fruits = ["apple", "banana", "orange"]

# enumerate なし — 不格好
for i in range(len(fruits)):
    print(f"{i + 1}. {fruits[i]}")

# enumerate あり — エレガント
for i, fruit in enumerate(fruits, 1):    # start=1 で 1 からカウント
    print(f"{i}. {fruit}")

names = ["Alice", "Bob", "Charlie"]
scores = [85, 92, 78]
cities = ["Beijing", "Shanghai", "Guangzhou"]

# 3 つのリストを同時に反復
for name, score, city in zip(names, scores, cities):
    print(f"{name}: {score} points, from {city}")

Alice: 85 points, from Beijing
Bob: 92 points, from Shanghai
Charlie: 78 points, from Guangzhou

# enumerate + zip を使って完全なレポートカードを生成
students = ["Alice", "Bob", "Charlie", "Diana"]
chinese = [85, 92, 78, 88]
math = [90, 85, 95, 80]
english = [78, 95, 82, 90]

print("=== Student Score Report ===")
print(f"{'Rank':<4}{'Name':<8}{'Chinese':<8}{'Math':<8}{'English':<8}{'Average':<8}")

# 平均を計算
averages = [(c + m + e) / 3 for c, m, e in zip(chinese, math, english)]

# 平均の降順でソート
data = list(zip(students, chinese, math, english, averages))
data.sort(key=lambda x: x[4], reverse=True)

# 出力
for rank, (name, c, m, e, avg) in enumerate(data, 1):
    print(f"{rank:<4}{name:<8}{c:<8}{m:<8}{e:<8}{avg:<8.1f}")

# シミュレートされたサーバーログ
log_data = """
2026-06-20 10:23:45 INFO  User 1001 logged in
2026-06-20 10:25:12 ERROR Database connection timeout
2026-06-20 10:26:30 INFO  User 1002 logged in
2026-06-20 10:27:45 WARN  Disk usage 85%
2026-06-20 10:28:10 ERROR User 1001 request timeout
2026-06-20 10:29:00 INFO  User 1001 logged out
"""

# 1. 行で分割
lines = log_data.strip().split("\n")

# 2. 各ログエントリを解析
parsed = []
for line in lines:
    parts = line.split()
    timestamp = f"{parts[0]} {parts[1]}"
    level = parts[2]
    message = " ".join(parts[3:])
    parsed.append({"time": timestamp, "level": level, "msg": message})

# 3. レベル別にカウント
level_count = {}
for entry in parsed:
    level = entry["level"]
    level_count[level] = level_count.get(level, 0) + 1

# 4. レベル順にソートして出力
print("=== Log Statistics ===")
for level, count in sorted(level_count.items()):
    print(f"{level}: {count} entries")

# 5. すべての ERROR を抽出
print("\n=== Error Details ===")
errors = [e for e in parsed if e["level"] == "ERROR"]
for e in errors:
    print(f"[{e['time']}] {e['msg']}")

=== Log Statistics ===
ERROR: 2 entries
INFO: 3 entries
WARN: 1 entry

=== Error Details ===
[2026-06-20 10:25:12] Database connection timeout
[2026-06-20 10:28:10] User 1001 request timeout