Python入門ガイド: Unicode、正規表現、バイナリデータの扱い方【データ操作マスター！】

# Unicode文字列の操作例
unicode_str = "こんにちは、世界！"
print(len(unicode_str))
print(unicode_str.upper())
print(unicode_str.encode("utf-8"))

# UTF-8エンコーディングの例
utf8_str = "Hello, 世界！"
encoded_str = utf8_str.encode("utf-8")
print(encoded_str)

# 文字列のエンコーディング
text = "こんにちは"
encoded_text = text.encode("utf-8")
print(encoded_text)

# 文字列のデコーディング
encoded_text = b'\xe3\x81\x93\xe3\x82\x93\xe3\x81\xab\xe3\x81\xa1\xe3\x81\xaf'
decoded_text = encoded_text.decode("utf-8")
print(decoded_text)

# HTMLエンティティの変換
import html

text = "<p>This is a paragraph.</p>"
encoded_text = html.escape(text)
print(encoded_text)

# 文字列の正規化
text = "caf\u00e9"
normalized_text = unicodedata.normalize("NFC", text)
print(normalized_text)

import re

pattern = r"abc"
text = "abcdefg"

match = re.match(pattern, text)
if match:
    print("Match found:", match.group())
else:
    print("No match")

import re

pattern = r"world"
text = "Hello, world!"

match = re.search(pattern, text)
if match:
    print("Match found:", match.group())
else:
    print("No match")

import re

pattern = r"\d+"
text = "Today is 2022-01-01."

matches = re.findall(pattern, text)
print("Matches:", matches)

import re

pattern = r"[.,]"
text = "Hello, world. How are you?"

split = re.split(pattern, text)
print("Split result:", split)

import re

pattern = r"apple"
text = "I have an apple. Do you like apple?"

replaced_text = re.sub(pattern, "orange", text)
print("Replaced text:", replaced_text)

import re

pattern = r"\d+\w*\s?"
text = "123 apple 456 banana"

matches = re.findall(pattern, text)
print("Matches:", matches)

import re

pattern = r"gr(a|e)y"
text1 = "gray"
text2 = "grey"

match1 = re.search(pattern, text1)
match2 = re.search(pattern, text2)

if match1:
    print("Match found in text1:", match1.group())

if match2:
    print("Match found in text2:", match2.group())

import re

pattern = r"(Mr|Mrs|Ms)\. (\w+)"
text = "Mr. Smith, Mrs. Johnson, Ms. Davis"

matches = re.findall(pattern, text)
for match in matches:
    title, name = match
    print("Title:", title)
    print("Name:", name)

# bytesとbytearrayの使い方
data = b"\x48\x65\x6c\x6c\x6f"
print("bytes:", data)

mutable_data = bytearray(b"\x48\x65\x6c\x6c\x6f")
mutable_data[0] = 0x42
print("mutable_data:", mutable_data)

import struct

data = struct.pack("I", 12345)
print("Packed data:", data)

unpacked_data = struct.unpack("I", data)
print("Unpacked data:", unpacked_data[0])

import binascii

text = "Hello, world!"
encoded_data = binascii.b2a_hex(text.encode("utf-8"))
print("Encoded data:", encoded_data)

decoded_data = binascii.a2b_hex(encoded_data).decode("utf-8")
print("Decoded data:", decoded_data)

import struct
import binascii

def analyze_binary_file(file_path):
    try:
        with open(file_path, "rb") as file:
            # ファイルの先頭からヘッダー情報を読み取る
            header_data = file.read(16)

            # ファイルタイプを解析
            file_type = header_data[:4].decode("utf-8")

            # ファイルサイズを解析
            file_size = struct.unpack("I", header_data[4:8])[0]

            # バージョン情報を解析
            version = struct.unpack("H", header_data[8:10])[0]

            # ヘッダー情報の表示
            print("File Path:", file_path)
            print("File Type:", file_type)
            print("File Size:", file_size)
            print("Version:", version)

    except FileNotFoundError:
        print("File not found.")

    except Exception as e:
        print("An error occurred:", str(e))

# 使用例
file_path = "sample.bin"
analyze_binary_file(file_path)