Pythonで文字列が数字/英字/空白か判定する方法まとめ

# 3つの数字判定メソッドの違いを確認するデモ
tests = ["123", "１２３", "²", "①", "Ⅳ", "⅕", "3.14", "-42", ""]

for s in tests:
    # reprで見分けやすく表示
    print(f"{repr(s):>6} -> isdecimal:{s.isdecimal():5}  isdigit:{s.isdigit():5}  isnumeric:{s.isnumeric():5}")

# isalphaの挙動を確認
samples = ["Hello", "ＡＢＣ", "Café", "こんにちは", "Hello123", ""]
for s in samples:
    print(f"{s!r:>10} -> isalpha: {s.isalpha()}")

# isspaceの挙動を確認
spaces = [" ", "\t\n", "　", " a "]
for s in spaces:
    print(repr(s), "-> isspace:", s.isspace())

# isasciiの確認
vals = ["ABC", "１２３", "Café", " "]
for s in vals:
    print(f"{s!r:>8} -> isascii: {s.isascii()}")

# よくある誤判定パターンの動作確認
cases = ["123,456", "Hello!", "-42", "3.14", "", " \t", " "]
for s in cases:
    print(f"{s!r:>8} -> isdecimal:{s.isdecimal():5} isalpha:{s.isalpha():5} isspace:{s.isspace():5}")

# 用途に応じて使い分けできる関数群
def is_decimal_digits(s: str) -> bool:
    """10進数字(0〜9と全角0〜9)のみ"""
    return len(s) > 0 and s.isdecimal()

def is_digit_chars(s: str) -> bool:
    """数字として数えられる文字も含める(例: ²)"""
    return len(s) > 0 and s.isdigit()

def is_numeric_chars(s: str) -> bool:
    """数値として解釈できる文字全般(例: ①, Ⅳ, ⅕ を含む)"""
    return len(s) > 0 and s.isnumeric()

tests = ["123", "１２３", "²", "①", "Ⅳ", "⅕", "3.14", ""]
for s in tests:
    print(f"{s!r:>6} dec:{is_decimal_digits(s):5}  dig:{is_digit_chars(s):5}  num:{is_numeric_chars(s):5}")

def is_alpha_unicode(s: str) -> bool:
    """Unicodeの文字だけ(ひらがな・漢字・全角英字・ラテン拡張などもOK)"""
    return len(s) > 0 and s.isalpha()

def is_alpha_ascii(s: str) -> bool:
    """ASCIIの英字だけ(A〜Z, a〜z)"""
    return len(s) > 0 and s.isascii() and s.isalpha()

samples = ["Hello", "ＡＢＣ", "Café", "こんにちは", "Hello123", ""]
for s in samples:
    print(f"{s!r:>10} uni:{is_alpha_unicode(s):5} ascii:{is_alpha_ascii(s):5}")

def is_only_whitespace(s: str) -> bool:
    """空白(タブや改行、全角スペース含む)のみか"""
    return len(s) > 0 and s.isspace()

tests = [" ", "\t\n", "　", "", " a "]
for s in tests:
    print(f"{s!r:>6} -> {is_only_whitespace(s)}")

# 各文字の種別を判定して表示
def char_kind(ch: str) -> str:
    # 1文字の性質をわかりやすく分類
    if ch.isdecimal():
        return "decimal"
    if ch.isdigit():
        return "digit"
    if ch.isnumeric():
        return "numeric"
    if ch.isalpha():
        return "alpha"
    if ch.isspace():
        return "space"
    return "other"

s = "A1 ²①Ⅳ-Ω　"
for i, ch in enumerate(s):
    # reprで全角スペースなども視認しやすく
    print(f"index={i:2}: {repr(ch):>4} -> {char_kind(ch)}")

import re

# ASCIIの英数字と空白(タブ・改行なども含む)のみ
pat_ascii_alnum_space = re.compile(r'(?:[A-Za-z0-9]|\s)+\Z', flags=re.ASCII)

# 半角スペースだけを空白とみなす場合は、\sの代わりにスペース1個を使う
pat_ascii_alnum_space_only_space = re.compile(r'(?:[A-Za-z0-9]| )+\Z')

tests = [
    "Hello World",     # OK
    "Line1\nLine2",    # OK(ASCIIの改行含む)
    "ABC123\tXYZ",     # OK(タブ含む)
    "ＡＢＣ",           # NG(全角)
    "Café",            # NG(éは非ASCII)
    "Hello-World",     # NG(ハイフンは許可外)
]

for s in tests:
    ok1 = bool(pat_ascii_alnum_space.fullmatch(s))
    ok2 = bool(pat_ascii_alnum_space_only_space.fullmatch(s))
    print(f"{s!r:>14} -> ASCII空白含む: {ok1}, 半角スペースのみ空白: {ok2}")

# 数値の真偽は「パースできるか」で判定するのが堅実
def is_int_value(s: str) -> bool:
    try:
        int(s)  # 先頭や末尾の空白は許可されません
        return True
    except ValueError:
        return False

tests = ["42", "-42", " 42", "3.0", "3.14", "Ⅳ"]  # Ⅳは数値風だがintは失敗
for s in tests:
    print(f"{s!r:>4} -> int判定: {is_int_value(s)}")

import unicodedata

samples = ["①", "Ⅳ", "²", "ＡＢＣ"]
for s in samples:
    nfkD = unicodedata.normalize("NFKD", s)
    nfkC = unicodedata.normalize("NFKC", s)
    print(f"{s!r} -> NFKD:{nfkD!r}  NFKC:{nfkC!r}")