Pythonのファイル操作 — 正しい読み書きの方法

# ❌ Manual close — works until it doesn't
f = open('app.log')
data = f.read()   # if this raises an exception...
f.close()         # ...this line never runs. File handle leaks.

# ✅ Context manager — close() is guaranteed
with open('app.log') as f:
    data = f.read()
# file is closed here, no matter what happened inside the block

from pathlib import Path

def load_config(path: str) -> dict:
    """Read a key=value config file, ignoring comments and blank lines."""
    config = {}
    with open(path, encoding='utf-8') as f:
        for line in f:
            line = line.strip()
            if not line or line.startswith('#'):
                continue
            if '=' not in line:
                continue
            key, _, value = line.partition('=')
            config[key.strip()] = value.strip()
    return config

# Usage
settings = load_config('config/app.conf')
db_host = settings.get('DB_HOST', 'localhost')

import datetime

LOG_FILE = 'logs/pipeline.log'

def log_event(level: str, message: str) -> None:
    timestamp = datetime.datetime.utcnow().isoformat() + 'Z'
    line = f"[{timestamp}] {level.upper()}: {message}\n"
    with open(LOG_FILE, 'a', encoding='utf-8') as f:
        f.write(line)

log_event('info', 'Pipeline started')
log_event('warning', 'Retrying connection to database')
log_event('error', 'Failed to parse row 4821 — skipping')

# ❌ Platform-dependent — works on Linux, corrupts on Windows
with open('customers.csv') as f:
    data = f.read()

# ✅ Explicit UTF-8 — same behavior on every platform
with open('customers.csv', encoding='utf-8') as f:
    data = f.read()

# For files exported from Excel on Windows — may have a BOM (byte order mark)
# utf-8-sig strips the BOM automatically on read
with open('export.csv', encoding='utf-8-sig') as f:
    data = f.read()

from pathlib import Path

# Build a path relative to the current script — works on Windows and Unix
base_dir = Path(__file__).parent
data_dir = base_dir / 'data'
input_file = data_dir / 'records.csv'

# Check existence before opening
if not input_file.exists():
    raise FileNotFoundError(f"Input file not found: {input_file}")

# Create a directory (including parents) without error if it already exists
output_dir = base_dir / 'output' / 'reports'
output_dir.mkdir(parents=True, exist_ok=True)

# Iterate over all JSON files in a directory
for json_file in data_dir.glob('*.json'):
    print(json_file.name)       # just the filename: 'records.json'
    print(json_file.stem)       # filename without extension: 'records'
    print(json_file.suffix)     # extension: '.json'
    print(json_file.parent)     # parent directory as a Path

# The / operator builds paths — no os.path.join needed
report_path = output_dir / f"report_{input_file.stem}.txt"

from pathlib import Path
from collections import Counter

def count_error_levels(log_path: str) -> dict:
    """
    Process a large log file line by line.
    Memory usage stays roughly constant regardless of file size.
    """
    counts = Counter()
    with open(log_path, encoding='utf-8') as f:
        for line in f:
            # Each line is fetched from disk as needed — not loaded all at once
            if ' ERROR ' in line:
                counts['error'] += 1
            elif ' WARN ' in line:
                counts['warning'] += 1
            elif ' INFO ' in line:
                counts['info'] += 1
    return dict(counts)

results = count_error_levels('/var/log/app/server.log')
print(f"Errors: {results.get('error', 0)}, Warnings: {results.get('warning', 0)}")

import json
import csv
from pathlib import Path

# --- JSON ---
# Reading
with open('config/settings.json', encoding='utf-8') as f:
    settings = json.load(f)            # parsed directly from the file object

# Writing (indent=2 gives readable output)
with open('output/results.json', 'w', encoding='utf-8') as f:
    json.dump(results, f, indent=2, ensure_ascii=False)

# --- CSV ---
# Reading
with open('data/customers.csv', encoding='utf-8-sig', newline='') as f:
    reader = csv.DictReader(f)         # each row is a dict keyed by header
    for row in reader:
        process_customer(row['email'], row['plan'])

# Writing
fieldnames = ['id', 'email', 'plan', 'created_at']
with open('output/export.csv', 'w', encoding='utf-8', newline='') as f:
    writer = csv.DictWriter(f, fieldnames=fieldnames)
    writer.writeheader()
    for record in records:
        writer.writerow(record)

import json
from pathlib import Path

def load_json_config(path: str) -> dict:
    """
    Load a JSON config file with explicit error handling.
    Returns the parsed config or raises with a clear message.
    """
    config_path = Path(path)

    try:
        with open(config_path, encoding='utf-8') as f:
            return json.load(f)

    except FileNotFoundError:
        raise FileNotFoundError(
            f"Config file not found: {config_path.resolve()}\n"
            f"Create it or set CONFIG_PATH to the correct location."
        )

    except PermissionError:
        raise PermissionError(
            f"No read permission on {config_path.resolve()}\n"
            f"Check file ownership and mode (chmod 644 on Linux)."
        )

    except UnicodeDecodeError as e:
        raise ValueError(
            f"Encoding error reading {config_path}: {e}\n"
            f"Try opening with encoding='utf-8-sig' if the file came from Windows."
        )

    except json.JSONDecodeError as e:
        raise ValueError(
            f"Invalid JSON in {config_path} at line {e.lineno}, col {e.colno}: {e.msg}"
        )