# Words by the Numbers 3, Exercise 3: how far apart the language profiles are.
TRAIN = {
    "English": (
        "The old harbour was quiet in the early morning, and the fishermen were "
        "already mending their nets on the stone quay. A cold wind came in from "
        "the sea, carrying the smell of salt and tar, while the children of the "
        "village walked slowly to school with their books under their arms. "
        "Nobody spoke much, for the week had been long and the weather had been "
        "hard on everyone who worked on the water."
    ),
    "French": (
        "Le vieux port était calme au petit matin, et les pêcheurs réparaient "
        "déjà leurs filets sur le quai de pierre. Un vent froid venait de la mer, "
        "apportant l'odeur du sel et du goudron, pendant que les enfants du "
        "village marchaient lentement vers l'école, leurs livres sous le bras. "
        "Personne ne parlait beaucoup, car la semaine avait été longue et le "
        "temps avait été dur pour tous ceux qui travaillaient sur l'eau."
    ),
    "German": (
        "Der alte Hafen war am frühen Morgen still, und die Fischer flickten "
        "schon ihre Netze am steinernen Kai. Ein kalter Wind kam vom Meer und "
        "brachte den Geruch von Salz und Teer mit, während die Kinder des Dorfes "
        "langsam zur Schule gingen, ihre Bücher unter dem Arm. Niemand sprach "
        "viel, denn die Woche war lang gewesen und das Wetter hatte allen "
        "zugesetzt, die auf dem Wasser arbeiteten."
    ),
    "Spanish": (
        "El viejo puerto estaba tranquilo a primera hora de la mañana, y los "
        "pescadores ya remendaban sus redes en el muelle de piedra. Un viento "
        "frío llegaba del mar, trayendo el olor a sal y alquitrán, mientras los "
        "niños del pueblo caminaban despacio hacia la escuela con los libros "
        "bajo el brazo. Nadie hablaba mucho, porque la semana había sido larga "
        "y el tiempo había sido duro para todos los que trabajaban en el agua."
    ),
    "Italian": (
        "Il vecchio porto era tranquillo di primo mattino, e i pescatori "
        "rammendavano già le loro reti sulla banchina di pietra. Un vento freddo "
        "veniva dal mare, portando l'odore di sale e di catrame, mentre i "
        "bambini del villaggio camminavano lentamente verso la scuola con i "
        "libri sotto il braccio. Nessuno parlava molto, perché la settimana era "
        "stata lunga e il tempo era stato duro per tutti quelli che lavoravano "
        "sull'acqua."
    ),
}
TEST = {
    "English": (
        "She opened the window and listened to the rain falling on the roof of "
        "the little house, thinking about the letter that had arrived the day "
        "before and what she should write in answer to it."
    ),
    "French": (
        "Elle ouvrit la fenêtre et écouta la pluie qui tombait sur le toit de la "
        "petite maison, en pensant à la lettre qui était arrivée la veille et à "
        "ce qu'elle devait écrire en réponse."
    ),
    "German": (
        "Sie öffnete das Fenster und hörte dem Regen zu, der auf das Dach des "
        "kleinen Hauses fiel, und dachte an den Brief, der am Tag zuvor "
        "angekommen war, und was sie darauf antworten sollte."
    ),
    "Spanish": (
        "Ella abrió la ventana y escuchó la lluvia que caía sobre el tejado de "
        "la casita, pensando en la carta que había llegado el día anterior y en "
        "lo que debía escribir como respuesta."
    ),
    "Italian": (
        "Lei aprì la finestra e ascoltò la pioggia che cadeva sul tetto della "
        "piccola casa, pensando alla lettera che era arrivata il giorno prima e "
        "a cosa dovesse scrivere in risposta."
    ),
}

import string
import unicodedata
from collections import Counter
from itertools import combinations
from pydoc_data.topics import topics

ALPHA = string.ascii_lowercase

def profile(text):
    decomposed = unicodedata.normalize("NFD", text.lower())
    letters = [ch for ch in decomposed if ch in ALPHA]
    counts = Counter(letters)
    return [counts[ch] / len(letters) for ch in ALPHA]

def distance(p, q):
    return sum(abs(a - b) for a, b in zip(p, q))

profiles = {lang: profile(text) for lang, text in TRAIN.items()}
pairs = sorted(
    (distance(profiles[a], profiles[b]), a, b) for a, b in combinations(profiles, 2)
)
print("closest pairs:")
for d, a, b in pairs[:3]:
    print(f"  {a:8} {b:8} {d:.3f}")
print("furthest pair:", pairs[-1][1], pairs[-1][2], f"{pairs[-1][0]:.3f}")

# A different kind of English: the Python reference documentation.
docs = profile(" ".join(topics.values()))
print("story English vs doc English:", f"{distance(profiles['English'], docs):.3f}")
for lang in ("French", "German", "Spanish", "Italian"):
    print(f"doc English vs {lang}:", f"{distance(docs, profiles[lang]):.3f}")

# Output when run (Python 3.14; the documentation-text figures depend on the Python version):
# closest pairs:
#   Spanish  Italian  0.310
#   English  German   0.350
#   French   Italian  0.372
# furthest pair: German Spanish 0.607
# story English vs doc English: 0.347
# doc English vs French: 0.393
# doc English vs German: 0.412
# doc English vs Spanish: 0.449
# doc English vs Italian: 0.403