Python File Handling

# Manual close (not recommended — easy to forget)
f = open("data.txt", "r", encoding="utf-8")
content = f.read()
f.close()

# Recommended: with statement closes the file automatically
with open("data.txt", "r", encoding="utf-8") as f:
    content = f.read()
    print(content)
# f.close() is called automatically when the with block exits

# Write to a file
with open("log.txt", "w", encoding="utf-8") as f:
    f.write("Line one\n")
    f.write("Line two\n")

# Append to a file
with open("log.txt", "a", encoding="utf-8") as f:
    f.write("Line three\n")

# Open two files simultaneously (read source, write destination)
with open("source.txt", "r", encoding="utf-8") as src, \
     open("dest.txt", "w", encoding="utf-8") as dst:
    dst.write(src.read())

with open("data.txt", "r", encoding="utf-8") as f:
    # Read the entire file into a string at once
    content = f.read()

    # Read one line (including the trailing \n)
    line = f.readline()

    # Read all lines and return a list
    lines = f.readlines()  # ['Line one\n', 'Line two\n', ...]

# Recommended: iterate line by line (does not load the whole file; suitable for large files)
with open("large.txt", "r", encoding="utf-8") as f:
    for line in f:
        print(line.rstrip())  # rstrip() removes the trailing newline

# Copy a binary file
with open("photo.jpg", "rb") as src, open("copy.jpg", "wb") as dst:
    while True:
        chunk = src.read(4096)   # Read 4 KB at a time
        if not chunk:
            break
        dst.write(chunk)

# More concise alternative
import shutil
shutil.copyfile("photo.jpg", "copy.jpg")

# Read a UTF-8 file
with open("utf8.txt", "r", encoding="utf-8") as f:
    print(f.read())

# Read a legacy GBK-encoded file
with open("gbk.txt", "r", encoding="gbk") as f:
    content = f.read()

# Specify encoding when writing
with open("output.txt", "w", encoding="utf-8") as f:
    f.write("Hello, World!\n")

# Error handling for bytes that cannot be decoded
with open("mixed.txt", "r", encoding="utf-8", errors="ignore") as f:
    content = f.read()   # Skip bytes that cannot be decoded

# errors="replace": replace undecodable bytes with ?
with open("mixed.txt", "r", encoding="utf-8", errors="replace") as f:
    content = f.read()

with open("data.txt", "rb") as f:
    # tell(): return the current pointer position (in bytes)
    print(f.tell())    # 0

    f.read(5)
    print(f.tell())    # 5

    # seek(offset, whence)
    f.seek(0)          # Move to the beginning (equivalent to f.seek(0, 0))
    f.seek(0, 2)       # Move to the end (whence=2 means relative to the end)
    print(f.tell())    # Total file size in bytes

    f.seek(-3, 2)      # Move 3 bytes back from the end
    print(f.read().decode("utf-8"))   # Last 3 bytes of content

from pathlib import Path

# Create path objects
data_dir = Path("data")
config = Path("/etc/app/config.yaml")

# Path joining (/ operator)
log_file = data_dir / "logs" / "app.log"

# Path attributes
p = Path("/home/user/docs/readme.txt")
print(p.name)     # readme.txt
print(p.stem)     # readme
print(p.suffix)   # .txt
print(p.parent)   # /home/user/docs

# Existence checks
print(p.exists())   # Whether the path exists
print(p.is_file())  # Whether it is a file
print(p.is_dir())   # Whether it is a directory

# Convenient read/write (manages open/close automatically)
output = Path("output.txt")
output.write_text("Hello, World!", encoding="utf-8")
text = output.read_text(encoding="utf-8")

# Create directories (parents=True creates intermediate directories)
Path("a/b/c").mkdir(parents=True, exist_ok=True)

# Delete
output.unlink(missing_ok=True)    # Delete a file
Path("empty_dir").rmdir()         # Delete an empty directory

# Iterate over a directory
for f in Path(".").iterdir():
    if f.is_file():
        print(f.name)

# Glob pattern matching
for py in Path("src").glob("**/*.py"):  # Recursive search
    print(py)

from pathlib import Path

# Approach 1: Read everything into memory, modify, then write back (suitable for small files)
path = Path("db.txt")
content = path.read_text(encoding="utf-8")
path.write_text(content.replace("old_value", "new_value"), encoding="utf-8")

# Approach 2: Read line by line and write to a temp file (suitable for large files)
import shutil, os

src = Path("db.txt")
tmp = Path(".db.txt.swap")

with src.open("r", encoding="utf-8") as r, \
     tmp.open("w", encoding="utf-8") as w:
    for line in r:
        w.write(line.replace("old_value", "new_value"))

tmp.replace(src)   # Atomic replacement (equivalent to os.replace)

import time
from pathlib import Path

def tail_log(path: Path) -> None:
    """Similar to tail -f: continuously output new lines appended to a log file."""
    with path.open("rb") as f:
        f.seek(0, 2)   # Jump to the end of the file
        while True:
            line = f.readline()
            if line:
                print(line.decode("utf-8"), end="")
            else:
                time.sleep(0.5)

# tail_log(Path("access.log"))