Day 10: 檔案、路徑與編碼

count = 0
with open("notes.txt", encoding="utf-8") as f:
for line in f:
if line.strip():
count += 1
print(count, f.closed)
輸出：3 True。追蹤：迴圈依序取得 'alpha\n'、'beta\n'、'gamma\n'（若檔案沒有結尾換行符號則為 'gamma'）；strip() 之後每一行都非空，所以 count 達到 3，最後一行結尾的換行符號不會產生第四行。print 在 with 區塊結束之後才執行，此時 f 已關閉，所以 f.closed 為 True。

練習腳本的觀察輸出（因為夾具是私有的，在每台機器上都相同）：

[project] exit=0
cwd is project: True
exists: True
lines: 3
[outside] exit=1
cwd is project: False
exists: False
FileNotFoundError: [Errno 2] No such file or directory: 'data/notes.txt'

診斷：檔案存在（cwd 為 project 時 exists: True），但第二次執行的 cwd 不同（cwd is project: False），所以相對路徑解析為並不存在的 outside/data/notes.txt。原因是工作目錄，而不是檔案遺失。最小修復：用 BASE = Path(__file__).resolve().parent 把路徑錨定到腳本，並開啟 BASE / "data" / "notes.txt"；計數那一行保持不變。下面的完整參考程式把錨定版 reader 寫入一個新夾具，從兩個資料夾分別執行，然後刪除資料檔以展示另一種原因：當錨定路徑本身不存在時，任何程式修改都沒用，還原夾具才能解決。

import subprocess
import sys
import tempfile
from pathlib import Path
FIXED = (
    "from pathlib import Path\n"
    "BASE = Path(__file__).resolve().parent\n"
    "with open(BASE / 'data' / 'notes.txt', encoding='utf-8') as f:\n"
    "    print('lines:', sum(1 for line in f if line.strip()))\n"
)

def run(script, cwd):
    done = subprocess.run([sys.executable, str(script)],
                          cwd=cwd, capture_output=True, text=True)
    if done.returncode == 0:
        return f"exit=0 {done.stdout.strip()}"
    last = done.stderr.strip().splitlines()[-1]
    return f"exit={done.returncode} {last.split(':')[0]}"

with tempfile.TemporaryDirectory() as tmp:
    root = Path(tmp).resolve()
    project = root / "project"
    outside = root / "outside"
    notes = project / "data" / "notes.txt"
    notes.parent.mkdir(parents=True)
    outside.mkdir()
    notes.write_text("alpha\nbeta\ngamma\n", encoding="utf-8")
    reader = project / "reader.py"
    reader.write_text(FIXED, encoding="utf-8")
    print("anchored, from outside:", run(reader, outside))
    print("anchored, from project:", run(reader, project))
    notes.unlink()
    print("fixture deleted, anchored path exists:", notes.exists())
    print("anchored, from project:", run(reader, project))
    notes.write_text("alpha\nbeta\ngamma\n", encoding="utf-8")
    print("fixture restored:", run(reader, outside))

預期輸出：

anchored, from outside: exit=0 lines: 3
anchored, from project: exit=0 lines: 3
fixture deleted, anchored path exists: False
anchored, from project: exit=1 FileNotFoundError
fixture restored: exit=0 lines: 3

預測與觀察輸出：

{'ana': 7, 'cy': 5} [2]

第 2 行（bo,x9）在 try 內拋出 ValueError，所以它的行號進入 skipped，continue 跳過了指派；第 1 行和第 3 行執行到 scores[name] = score。try 只包住 int(raw)，所以 open() 失敗或拆行程式碼裡的 bug 仍會以 traceback 暴露出來，而不會被悄悄算作壞行。enumerate(f, 1) 給實體行編號，所以空行也會讓行號前進。解碼問題是另一類失敗，下面的程式把它與 ValueError 對比：

data = "café".encode("latin-1")
print(data)
try:
    data.decode("utf-8")
except UnicodeDecodeError as exc:
    print(type(exc).__name__ + ":", exc)
print(data.decode("latin-1") == "café")
print(b"plain ascii".decode("utf-8") == b"plain ascii".decode("latin-1"))
both = b"caf\xc3\xa9"
as_utf8 = both.decode("utf-8")
as_latin1 = both.decode("latin-1")
print(as_utf8 == "café", as_latin1 == "café", len(as_utf8), len(as_latin1))

預期輸出：

b'caf\xe9'
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe9 in position 3: unexpected end of data
True
True
True True 4 5

b'caf\xe9' 是 Latin-1 編碼的 café，不是有效的 UTF-8，所以按 UTF-8 解碼會拋出 UnicodeDecodeError；修復方法是宣告真實編碼（這裡是 encoding="latin-1"）。純 ASCII 在兩種編碼下解碼結果相同，而 b'caf\xc3\xa9' 在兩種編碼下都能解碼成功，卻得到不同的文字（café 是 4 個字元，café 是 5 個字元），所以解碼成功並不能證明宣告的編碼正確。相較之下，ValueError 表示文字解碼正常，但某一行的值無效。

附有自足夾具測試的參考實作（請在記錄了你獨立完成的嘗試之後，再拿它與自己的版本比較）：

import tempfile
from pathlib import Path

def summarize_scores(path):
    result = {"scores": {}, "skipped": [], "missing": False}
    try:
        f = open(path, encoding="utf-8")
    except FileNotFoundError:
        result["missing"] = True
        return result
    with f:
        for lineno, line in enumerate(f, 1):
            line = line.strip()
            if not line:
                continue
            name, sep, raw = line.rpartition(",")
            try:
                score = int(raw)
            except ValueError:
                score = None
            if not sep or not name or score is None:
                result["skipped"].append(lineno)
                continue
            best = result["scores"].get(name)
            if best is None or score > best:
                result["scores"][name] = score
    return result

with tempfile.TemporaryDirectory() as tmp:
    base = Path(tmp)
    (base / "s1.txt").write_text("ana,7\nbo,9\nana,8\n", encoding="utf-8")
    (base / "s2.txt").write_text("ana,7\nbo,x9\ncy,5\n", encoding="utf-8")
    print(summarize_scores(base / "s1.txt"))
    print(summarize_scores(base / "s2.txt"))
    print(summarize_scores(base / "missing.txt"))

預期輸出：

{'scores': {'ana': 8, 'bo': 9}, 'skipped': [], 'missing': False}
{'scores': {'ana': 7, 'cy': 5}, 'skipped': [2], 'missing': False}
{'scores': {}, 'skipped': [], 'missing': True}

為什麼這樣寫：FileNotFoundError 處理器裡只有 open()，所以只有檔案遺失才會把 missing 設為 True，其他錯誤照常暴露。with f: 區塊在每條路徑上都會關閉檔案。ValueError 處理器裡只有 int(raw)；沒有逗號、名字為空或分數不是整數的行會被跳過，並記錄其從 1 開始的行號。每個名字的最高分透過與已存值比較來保留，所以 ana 最終是 8。