1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
# -*- coding: utf-8 -*-
"""Turns the numbers in a transcription into words, so it can be compared
with the script (which spells everything out)."""
import re
U = ["cero", "uno", "dos", "tres", "cuatro", "cinco", "seis", "siete", "ocho", "nueve",
"diez", "once", "doce", "trece", "catorce", "quince", "dieciseis", "diecisiete",
"dieciocho", "diecinueve", "veinte", "veintiuno", "veintidos", "veintitres",
"veinticuatro", "veinticinco", "veintiseis", "veintisiete", "veintiocho", "veintinueve"]
D = {3: "treinta", 4: "cuarenta", 5: "cincuenta", 6: "sesenta",
7: "setenta", 8: "ochenta", 9: "noventa"}
C = {1: "ciento", 2: "doscientos", 3: "trescientos", 4: "cuatrocientos", 5: "quinientos",
6: "seiscientos", 7: "setecientos", 8: "ochocientos", 9: "novecientos"}
def _lt1000(n):
if n < 30:
return U[n]
if n < 100:
d, u = divmod(n, 10)
return D[d] + (" y " + U[u] if u else "")
if n == 100:
return "cien"
c, r = divmod(n, 100)
return C[c] + (" " + _lt1000(r) if r else "")
def spell_int(n):
if n < 1000:
return _lt1000(n)
if n < 1000000:
m, r = divmod(n, 1000)
pre_frames = "mil" if m == 1 else _lt1000(m) + " mil"
return pre_frames + (" " + _lt1000(r) if r else "")
m, r = divmod(n, 1000000)
pre_frames = "un millon" if m == 1 else _lt1000(m) + " millones"
return pre_frames + (" " + spell_int(r) if r else "")
def _tok(m):
s = m.group(0)
s = re.sub(r"\.(?=\d{3}\b)", "", s) # 384.000 -> 384000
if "," in s:
a, b = s.split(",", 1)
whole = spell_int(int(a or 0))
dec = " ".join(U[int(c)] for c in b if c.isdigit())
return f"{whole} coma {dec}"
if "." in s: # 0.5 English style
a, b = s.split(".", 1)
return f"{spell_int(int(a or 0))} coma " + " ".join(U[int(c)] for c in b if c.isdigit())
return spell_int(int(s))
def expand(text):
t = text.replace("%", " por ciento ").replace("º", "")
t = re.sub(r"\d+(?:[.,]\d+)*", _tok, t)
return re.sub(r"\s+", " ", t).strip()
|
