note = "  Table 4: two FLAT whites, one croissant  "
print(repr(note))
print(repr(note.strip()))
print(note.strip().lower().replace("flat whites", "lattes"))

words = note.split()
print(len(words), "words:", words)
print("Shouty words:", [w for w in words if w.isupper()])
print("croissant" in note, note.count("o"))
print(note.strip().title())
print(note.strip().startswith("Table"), note.find("croissant"))

drink = "Latte"
price = 3.5
print(f"{drink} costs {price}")
print(f"{drink} costs ${price:.2f}")
print(f"[{drink:10}]")
print(f"[{price:10}]")

print(f"[{drink:<10}]  left")
print(f"[{drink:>10}]  right")
print(f"[{drink:^10}]  centre")
print(f"[{drink:*^10}]  centre, padded with *")

menu = {"Espresso": 2.2, "Flat white": 3.4, "Hot chocolate": 3.95, "Tea": 1.8}
print(f"{'Item':<15}{'Price':>8}")
print("-" * 23)
for item, cost in menu.items():
    print(f"{item:<15}{cost:>8.2f}")

width = 30
print(f"{' Cafe Menu ':=^{width}}")
for item, cost in menu.items():
    print(f"{item:.<{width - 6}}${cost:>5.2f}")
print("=" * width)

steps = 8432
goal = 10000
print(f"{steps=}")
print(f"{goal - steps=}")
print(f"{steps / goal=:.1%}")

name = "  Zoe "
print(f"Hello {name}!")
print(f"Hello {name!r}!")
print(f"Hello {name.strip()!r}!")

playlist = [("Morning Run", 215), ("Slow Jam", 368), ("Cooldown", 74)]
for number, (song, seconds) in enumerate(playlist, start=1):
    mins, secs = divmod(seconds, 60)
    print(f"{number:>2}. {song:<12}{mins:>2}:{secs:02d}")
total_secs = sum(s for _, s in playlist)
print(f"    {'Total':<12}{total_secs // 60:>2}:{total_secs % 60:02d}")

total = 1234567.891
print(f"{total}")
print(f"{total:.2f}")
print(f"{total:,.2f}")
print(f"{total:_.0f}")
print(f"{total:.3e}")

rate = 0.0768
print(f"{rate}")
print(f"{rate:%}")
print(f"{rate:.1%}")
print(f"{0.5:.0%} off all pastries after 4pm")

for change in [12.5, -3.4, 0]:
    print(f"Weight change: {change:+.1f} kg")

for order_no in [7, 42, 315]:
    print(f"Order #{order_no:05d}")

budget = {"Rent": 950, "Food": 310.5, "Travel": 86.2, "Fun": 120}
total = sum(budget.values())
for item, cost in budget.items():
    print(f"{item:<8}${cost:>8,.2f}  {cost / total:>6.1%}")
print(f"{'Total':<8}${total:>8,.2f}  {1:>6.0%}")

price_text = "3.50"
print(f"${price_text:.2f}")

price_text = "3.50"
print(f"${float(price_text):.2f}")
print(f"${float(price_text) * 3:.2f} for three")

print(f"{0.256:.0%}")
print(f"{7:03d}")

from datetime import datetime, date

booking = datetime(2026, 3, 14, 19, 30)
print(f"{booking}")
print(f"{booking:%d/%m/%Y}")
print(f"{booking:%A %d %B %Y at %H:%M}")

print(f"{booking:%I:%M %p}")
print(f"{booking:%a %d %b}")
print(f"Day {booking:%j} of the year")

classes = [date(2026, 3, 16), date(2026, 3, 18), date(2026, 3, 21)]
for day in classes:
    kind = "weekend" if day.weekday() >= 5 else "weekday"
    print(f"{day:%a %d %b}  Spin class  ({kind})")

order = [("Flat white", 2, 3.40), ("Croissant", 1, 2.75), ("Banana bread", 3, 2.95)]
for item, qty, unit in order:
    print(f"{qty}x {item:<14}@ ${unit:.2f} = ${qty * unit:>5.2f}")

def receipt(order, when, discount=0.0, width=32):
    lines = [f"{' THE DAILY GRIND ':*^{width}}", f"{when:%d %b %Y  %H:%M}".center(width)]
    subtotal = 0
    for item, qty, unit in order:
        subtotal += qty * unit
        lines.append(f"{qty}x {item:<{width - 10}}${qty * unit:>6.2f}")
    lines.append("-" * width)
    if discount:
        lines.append(f"{'Discount ' + format(discount, '.0%'):<{width - 8}}-${subtotal * discount:>6.2f}")
    lines.append(f"{'TOTAL':<{width - 7}}${subtotal * (1 - discount):>6.2f}")
    return lines

print(len(receipt(order, booking)), "lines ready")

print("\n".join(receipt(order, booking)))

print("\n".join(receipt(order, datetime(2026, 3, 15, 8, 5), discount=0.1)))

import string

print(string.ascii_lowercase)
print(string.ascii_uppercase)
print(string.digits)
print(string.punctuation)
print(len(string.ascii_letters), "letters,", len(string.punctuation), "punctuation marks")

review = "Great coffee!!! Friendly staff, but... the Wi-Fi? Terrible :("
no_punct = "".join(ch for ch in review if ch not in string.punctuation)
print(no_punct)
print(string.capwords("the daily grind cafe"))

code = "AB12-cd34"
allowed = string.ascii_letters + string.digits + "-"
print(all(ch in allowed for ch in code))
print(sum(ch.isdigit() for ch in code), "digits")

import textwrap

blurb = ("Our beans are roasted every Tuesday in small batches, then rested for "
         "three days so the flavours settle before they reach your cup.")
print(textwrap.fill(blurb, width=40))
print()
print(textwrap.fill(blurb, width=60))

for line in textwrap.wrap(blurb, width=30):
    print(f"| {line:<30} |")

print(textwrap.shorten(blurb, width=50, placeholder="..."))
print(textwrap.indent(textwrap.fill(blurb, 36), "> "))

message = """
    Hi Sam,
        Your order is ready for collection.
    Thanks!
"""
print(textwrap.dedent(message).strip())

pasted = "\u201cBest\u201d caf\u00e9 in town\u2026 isn\u2019t it?"
fixes = str.maketrans({"\u201c": '"', "\u201d": '"', "\u2019": "'", "\u2026": "..."})
print(pasted)
print(pasted.translate(fixes))

import re

text = "Order 4471 shipped. Order 4472 is delayed."
match = re.search(r"\d+", text)
print(match)
print(match.group(), match.start(), match.end())

print(re.findall(r"\d+", text))
print(re.findall(r"Order \d+", text))
print(re.findall(r"\d+", "No numbers here"))

sample = "Room 7B!"
shortcuts = {r"\d": "a digit", r"\w": "letter/digit/_", r"\s": "whitespace", r".": "any character"}
for pat, meaning in shortcuts.items():
    print(f"{pat:<4}{meaning:<16}{re.findall(pat, sample)}")

flight = "Gate 7, flight 123, seat 4567"
for pat in [r"\d", r"\d+", r"\d{3}", r"\d{2,4}"]:
    print(f"{pat:<8}", re.findall(pat, flight))
print(re.findall(r"colou?r", "colour or color? Colour!"))

print(re.findall(r"[aeiou]", "espresso"))
print(re.findall(r"[A-Z]\w+", "Meet Ada and Ben at Bristol Temple Meads"))
print(re.findall(r"\bcat\b", "cat catalogue bobcat cat."))
print(re.findall(r"[^0-9 ]+", "Bus 42 to 7 Dials"))
print(re.search(r"^Hello", "Hello there") is not None, re.search(r"^Hello", "Oh, Hello") is not None)

print(re.match(r"\d+", "42 lattes"))
print(re.match(r"\d+", "lattes 42"))
print(re.fullmatch(r"\d+", "42"))
print(re.fullmatch(r"\d+", "42a"))

order_text = "1x Latte (large) $3.50, 2x Latte (small) $2.90"
print(re.findall(r"Latte \((\w+)\)", order_text))
literal = re.escape("(large) $3.50")
print(literal)
print(re.search(literal, order_text) is not None)

m = re.search(r"\d{5}", "No order number here")
print(m.group())

m = re.search(r"\d{5}", "No order number here")
if m:
    print("Found", m.group())
else:
    print("No match, so search returned", m)

line = "Flight BA2490 departs 14:35 from gate 22"
m = re.search(r"(\d{2}):(\d{2})", line)
print(m.group(0), m.group(1), m.group(2))
print(m.groups())

hours = int(m.group(1))
minutes = int(m.group(2))
print(f"{hours * 60 + minutes} minutes after midnight")

schedule = "Yoga 07:30, Spin 12:15, Boxing 18:45"
pairs = re.findall(r"(\w+) (\d{2}:\d{2})", schedule)
print(pairs)
for gym_class, time in pairs:
    print(f"{gym_class:<8}{time}")

flight_re = r"(?P<airline>[A-Z]{2})(?P<number>\d{3,4})"
m = re.search(flight_re, line)
print(m.group("airline"), m.group("number"))
print(m.groupdict())

tickets = "BA2490 to Rome, EZ812 to Nice, FR33 to Oslo"
for m in re.finditer(flight_re, tickets):
    print(f"{m['airline']} flight {m['number']} found at position {m.start()}")

dates = "Booked 14/03/2026, paid 02/04/2026"
for day, month, year in re.findall(r"(\d{2})/(\d{2})/(\d{4})", dates):
    print(f"{year}-{month}-{day}")

for booking_ref in ["Table for 4 at 19:30", "Table for 2", "table for 12 at 20:00"]:
    m = re.search(r"[Tt]able for (\d+)(?: at (\d{2}:\d{2}))?", booking_ref)
    people, time = m.groups()
    print(f"{people:>2} people, time: {time or 'not given'}")

print(re.findall(r"(\w+)@(\w+)", "ann@cafe and bo@gym"))

re.search(r"(\d+", "Table 12")

print(re.search(r"(\d+)", "Table 12").group(1))
print(re.search(r"\(\d+\)", "Table (12)").group())

messy = "Too    many     spaces   here"
print(re.sub(r"\s+", " ", messy))
print(re.sub(r"\d", "#", "Card 4929 1234 5678 9012"))

card = "Card 4929 1234 5678 9012"
print(re.sub(r"\d{4} \d{4} \d{4} (\d{4})", r"**** **** **** \1", card))
print(re.sub(r"(?P<d>\d{2})/(?P<m>\d{2})/(?P<y>\d{4})", r"\g<y>-\g<m>-\g<d>", dates))

def tidy_price(m):
    return f"${float(m.group(1)):.2f}"

print(re.sub(r"\$([\d.]+)", tidy_price, "Tea $2, cake $3.5, lunch $12.25"))

print(re.split(r"[,;|]\s*", "milk, eggs;bread|butter,  jam"))
print(re.split(r",\s*|\s+and\s+", "tea, coffee and cake"))
print(re.split(r"\s*\|\s*", "2026-03-02 |  Ada |note"))

shout = "WOW. Wow! wow?"
print(re.findall(r"wow", shout))
print(re.findall(r"wow", shout, flags=re.IGNORECASE))

log = "ok: fine\nERROR: disk full\nok: fine\nERROR: out of milk"
print(re.findall(r"^ERROR: (.+)$", log, flags=re.MULTILINE))

time_re = re.compile(r"""
    (?P<hour>[01]\d|2[0-3])    # 00 to 23
    :
    (?P<minute>[0-5]\d)        # 00 to 59
""", re.VERBOSE)

for t in ["09:30", "23:59", "24:00", "7:5"]:
    print(f"{t:<6}", "valid" if time_re.fullmatch(t) else "invalid")

opening = "Open 08:00 to 17:30, late night Friday 21:00"
print(time_re.findall(opening))
print(time_re.sub("--:--", opening))

EMAIL = re.compile(r"[\w.+-]+@[\w-]+(?:\.[\w-]+)+")
for e in ["ada@example.com", "ben.smith+gym@mail.co.uk", "no-at-sign.com", "eve@site", "a b@x.com"]:
    print(f"{e:<26}{'ok' if EMAIL.fullmatch(e) else 'rejected'}")

print(EMAIL.search("Reply to ada@example.com today").group())

PHONE = re.compile(r"(?:\+44\s?|0)7\d{3}\s?\d{6}")
for p in ["07700 900123", "07700900123", "+44 7700 900123", "0161 496 0000", "07700 9001"]:
    print(f"{p:<18}{'ok' if PHONE.fullmatch(p) else 'rejected'}")

found = PHONE.findall("Call 07700 900111 or 07700900222 after 6pm")
print("Inside a sentence:", found)

def tidy_phone(raw):
    digits = re.sub(r"\D", "", raw)
    if digits.startswith("44"):
        digits = "0" + digits[2:]
    return f"{digits[:5]} {digits[5:]}"

for p in ["+44 7700 900123", "07700-900-123", "(07700) 900 123"]:
    print(f"{p:<18} -> {tidy_phone(p)}")

POSTCODE = re.compile(r"[A-Z]{1,2}\d[A-Z\d]? ?\d[A-Z]{2}", re.IGNORECASE)
for pc in ["SW1A 1AA", "M1 1AE", "b33 8th", "LS1 4AP", "12345", "EC1A1BB"]:
    print(f"{pc:<10}{'ok' if POSTCODE.fullmatch(pc) else 'rejected'}")

def tidy_postcode(raw):
    squashed = re.sub(r"\s", "", raw).upper()
    return f"{squashed[:-3]} {squashed[-3:]}"

print([tidy_postcode(pc) for pc in ["b33 8th", "EC1A1BB", " m1   1ae "]])

CHECKS = {"email": EMAIL, "phone": PHONE, "postcode": POSTCODE}

def ask_valid(kind):
    while True:
        answer = input(f"Your {kind}: ").strip()
        if CHECKS[kind].fullmatch(answer):
            return answer
        print(f"  That doesn't look like a valid {kind}, please try again.")

print("Checks ready for:", ", ".join(CHECKS))

profile = {}  # ask_valid asks for input()
for kind in CHECKS:
    profile[kind] = ask_valid(kind)
print(profile)

profile["phone"] = tidy_phone(profile["phone"])
profile["postcode"] = tidy_postcode(profile["postcode"])
print(f"{' NEW MEMBER ':=^34}")
for kind, value in profile.items():
    print(f"{kind.title():<10}{value:>24}")
print("=" * 34)

word = "caf\u00e9"
data = word.encode("utf-8")
print(len(word), "characters")
print(data, len(data), "bytes")

for ch in "a\u00e9\u20ac":
    print(ch, ord(ch), ch.encode("utf-8"))
print(chr(233), chr(8364))
print("\N{LATIN SMALL LETTER E WITH ACUTE}" == "\u00e9", "\u00e9".encode("latin-1"), "\u00e9".encode("utf-8"))

print(data.decode("utf-8"))
print(data.decode("latin-1"), " <- wrong dictionary, scrambled text")

data.decode("ascii")

print(data.decode("utf-8"))
print(data.decode("ascii", errors="replace"))

from pathlib import Path

folder = Path("lesson_files")
folder.mkdir(exist_ok=True)
menu_file = folder / "menu.txt"
menu_file.write_text("Cr\u00e8me br\u00fbl\u00e9e $5\nJalape\u00f1o toastie $6\n", encoding="utf-8")
text = menu_file.read_text(encoding="utf-8")
print(text, menu_file.stat().st_size, "bytes for", len(text), "characters")

print("Stra\u00dfe".lower(), "|", "Stra\u00dfe".casefold())
print("STRASSE".lower() == "Stra\u00dfe".lower())
print("STRASSE".casefold() == "Stra\u00dfe".casefold())

import unicodedata

a = "caf\u00e9"
b = "cafe\u0301"
print(a, b, a == b, len(a), len(b))
for ch in b[-2:]:
    print(repr(ch), unicodedata.name(ch))

nfc = unicodedata.normalize("NFC", b)
print(nfc == a, len(nfc))
nfd = unicodedata.normalize("NFD", a)
print(nfd == b, len(nfd))

def strip_accents(text):
    pieces = unicodedata.normalize("NFD", text)
    return "".join(ch for ch in pieces if not unicodedata.combining(ch))

for person in ["Zo\u00eb", "Jos\u00e9", "Ren\u00e9e", "\u0141ukasz"]:
    print(f"{person:<8} -> {strip_accents(person)}")

def same_name(x, y):
    return strip_accents(x).casefold() == strip_accents(y).casefold()

members = ["Jos\u00e9", "Zo\u00eb Nakamura", "Ren\u00e9e", "Ben"]
query = input("Search members: ")
print([m for m in members if same_name(query, m.split()[0])])

for ch in "$5 \u00d1!":
    print(f"{ch!r:<5}{unicodedata.category(ch):<4}{unicodedata.name(ch)}")

print(len("caf\u00e9"), "characters,", len("caf\u00e9".encode("utf-8")), "bytes: \u00e9 needs two bytes in UTF-8")

raw_notes = """2026-03-02 | ada  LOVELACE | Rang re order #A1042, email ADA.L@Example.com, mobile 07700 900123. Wants refund!!!
2026-03-03 | jos\u00e9 garc\u00eda | order a1043 & A1044 not arrived... contact jose.garcia@mail.co.uk / +44 7700 900456
2026-03-03 | Ben   Okafor | Cake was squashed :( call (07700) 900-789 , postcode m1 1ae. Order A1045
2026-03-04 | ZO\u00cb NAKAMURA | email zoe@cafe-fans.org ,no phone given. order #A1046 lovely!!
2026-03-05 | sam lee | email sam@@typo.com ?? phone 0770 090   no order number"""

notes_file = folder / "customer_notes.txt"
notes_file.write_text(raw_notes, encoding="utf-8")
print(f"Saved {len(raw_notes.splitlines())} notes ({notes_file.stat().st_size:,} bytes)")

rows = []
for line in notes_file.read_text(encoding="utf-8").splitlines():
    when, who, note = re.split(r"\s*\|\s*", line)
    rows.append({"date": date.fromisoformat(when), "name": who, "note": note})
print(rows[1])

FIND_EMAIL = re.compile(r"[\w.+-]+@[\w-]+(?:\.[\w-]+)+")
FIND_PHONE = re.compile(r"(?:\+44\s?|\(?0)7\d{3}\)?[\s-]?\d{3}[\s-]?\d{3}")
FIND_ORDER = re.compile(r"\bA\d{4}\b", re.IGNORECASE)
FIND_POSTCODE = re.compile(r"\b[A-Z]{1,2}\d[A-Z\d]? ?\d[A-Z]{2}\b", re.IGNORECASE)
URGENT = re.compile(r"refund|not arrived|squashed|complain", re.IGNORECASE)
print(FIND_PHONE.findall(raw_notes))

def extract(note):
    return {
        "emails": [e.lower() for e in FIND_EMAIL.findall(note)],
        "phones": [tidy_phone(p) for p in FIND_PHONE.findall(note)],
        "orders": [o.upper() for o in FIND_ORDER.findall(note)],
        "postcodes": [tidy_postcode(p) for p in FIND_POSTCODE.findall(note)],
        "urgent": bool(URGENT.search(note)),
    }

print(extract(rows[2]["note"]))

def clean_name(name):
    return re.sub(r"\s+", " ", name).strip().title()

for row in rows:
    print(f"{row['name']!r:<18} -> {clean_name(row['name'])}")

def clean_note(note):
    note = re.sub(r":\(|:\)", "", note)
    note = re.sub(r"([!?.])\1+", r"\1", note)
    note = re.sub(r"\s+([,.!?])", r"\1", note)
    note = re.sub(r",(?=\S)", ", ", note)
    return re.sub(r"\s+", " ", note).strip()

print(clean_note(rows[2]["note"]))
print(clean_note(rows[3]["note"]))

records = []
for row in rows:
    record = {"date": row["date"], "name": clean_name(row["name"]), "note": clean_note(row["note"])}
    record.update(extract(row["note"]))
    records.append(record)
print(len(records), "records, keys:", list(records[0]))

def report_card(r, width=60):
    flag = "  [URGENT]" if r["urgent"] else ""
    print(f"{r['date']:%a %d %b}  {r['name']}{flag}")
    print(f"   Email : {', '.join(r['emails']) or '-'}")
    print(f"   Phone : {', '.join(r['phones']) or '-'}")
    print(f"   Orders: {', '.join(r['orders']) or '-'}")
    if r["postcodes"]:
        print(f"   Post  : {', '.join(r['postcodes'])}")
    print(textwrap.indent(textwrap.fill(r["note"], width - 3), "   > "))

report_card(records[0])

print(f"{' CUSTOMER NOTES REPORT ':=^60}")
for r in records[1:]:
    report_card(r)
    print("-" * 60)

def yes_no(items):
    return "yes" if items else "no"

print(f"{'Customer':<16}{'Orders':>7}{'Email':>7}{'Phone':>7}  Postcode")
for r in records:
    print(f"{r['name']:<16}{len(r['orders']):>7}{yes_no(r['emails']):>7}{yes_no(r['phones']):>7}  "
          f"{', '.join(r['postcodes']) or '-'}")

total = len(records)
counts = {
    "with an email": sum(1 for r in records if r["emails"]),
    "with a phone": sum(1 for r in records if r["phones"]),
    "flagged urgent": sum(r["urgent"] for r in records),
}
for label, n in counts.items():
    print(f"Notes {label:<15}{n:>2} of {total}  ({n / total:.0%})")

all_orders = sorted({o for r in records for o in r["orders"]})
print(f"{len(all_orders)} order IDs:", ", ".join(all_orders))
follow_up = [r["name"] for r in records if not (r["emails"] or r["phones"])]
print("Need contact details:", follow_up)

lines = [f"{r['date']:%Y-%m-%d} | {r['name']:<14} | {', '.join(r['orders']) or '-':<12} | "
         f"{', '.join(r['emails'] + r['phones']) or 'NO CONTACT'}" for r in records]
report_file = folder / "notes_report.txt"
report_file.write_text("\n".join(lines) + "\n", encoding="utf-8")
print(report_file.read_text(encoding="utf-8"))

def urgent_then_date(r):
    return (not r["urgent"], r["date"])

for r in sorted(records, key=urgent_then_date):
    label = "URGENT" if r["urgent"] else "ok"
    print(f"{label:<7}{r['date']:%d %b}  {r['name']:<14}{textwrap.shorten(r['note'], 32, placeholder='...')}")

key = strip_accents("Zoe Nakamura").casefold()
match = [r for r in records if strip_accents(r["name"]).casefold() == key]
print(f"Searched without accents, found: {match[0]['name']} ({match[0]['emails'][0]})")