Expresiones Regulares (std::regex)

Validación de email y filtrado de lista con filter + regex.test.

// Feature: regex.test — checks whether the string contains the pattern

// When to use: validate format (email, phone), filter a list by pattern.


use std::regex
use std::Array

// Zolo regexes use Lua patterns: `%d` means a digit.
print(regex.test("%d+", "abc123"))  // expected: true
print(regex.test("%d+", "abcdef"))  // expected: false

// Anchored — entire string must be only digits.

print(regex.test("^%d+$", "12345"))  // expected: true
print(regex.test("^%d+$", "12a45"))  // expected: false

// Simplified email (without {n,} quantifier: we use `+`).

let email_re = "^[a-zA-Z0-9._-]+@[a-zA-Z0-9.-]+%.[a-zA-Z]+$"
print(regex.test(email_re, "[email protected]"))  // expected: true

print(regex.test(email_re, "not an email"))  // expected: false


// Filter emails out of a list.

let inputs = ["[email protected]", "ops", "[email protected]"]
let valid = inputs.filter(|e| regex.test(email_re, e))
print(valid.len())  // expected: 2

Extracción de números y palabras; nums[0].text accede a la subcadena.

// Feature: regex.find_all — every match of the pattern
// When to use: extract tokens (numbers, IDs, hashtags) from text.

use std::regex

// Each match is a table with `text`, `start`, `stop`, `groups`.
// NOTE: Zolo's regex module uses LUA patterns (`%d`, `%a`, ...),
// not PCRE syntax (`\d`).
let text = "I have 3 apples, 12 pears and 100 grapes"
let nums = regex.find_all("%d+", text)
print(nums.len())  // expected: 3

// The `text` field carries the exact substring.
print(nums[0].text)  // expected: 3
print(nums[1].text)  // expected: 12
print(nums[2].text)  // expected: 100

// Extract words (alphanumeric tokens).
let words = regex.find_all("[a-z]+", "hello world zolo")
print(words.len())  // expected: 3
print(words[0].text)  // expected: hello
print(words[2].text)  // expected: zolo

// regex.count — shortcut that counts without collecting text.
print(regex.count("%d+", text))  // expected: 3

Enmascarar dígitos, normalizar espacios y cambiar etiquetas HTML por Markdown.

// Feature: regex.replace_all — replace every match
// When to use: anonymize data, strip noise, sanitize input.

use std::regex

// Mask every digit.
print(regex.replace_all("%d", "id-12345", "*"))

// expected: id-*****

// Collapse multiple spaces into a single one.
print(regex.replace_all(" +", "a    b   c", " "))

// expected: a b c

// Strip a numeric prefix.
print(regex.replace_all("^%d+ ?", "42 abc", ""))

// expected: abc

// Swap <b> tags for **.
print(regex.replace_all("<b>(.-)</b>", "hello <b>world</b>!", "**%1**"))
// expected: hello **world**!

División por espacios múltiples y por conjunto de delimitadores [,;|].

// Feature: regex.split — split a string by pattern

// When to use: split on multiple delimiters, varied whitespace.


use std::csv
use std::regex

// Split on any run of whitespace (1 or more).

let parts = regex.split("%s+", "one  two   three four")
print(parts.len())  // expected: 4

print(parts[0])  // expected: one

print(parts[3])  // expected: four


// Split on comma, semicolon, or pipe.

let csv = regex.split("[,;|]", "a,b;c|d,e")
print(csv.len())  // expected: 5

print(csv[0])  // expected: a

print(csv[4])  // expected: e


// When the pattern does not match, returns the whole string in a single-element array.

let single = regex.split(",", "abc")
print(single.len())  // expected: 1

print(single[0])  // expected: abc