Utility functions for Text
values.
A Text
value represents human-readable text as a sequence of characters of type Char
.
let text = "Hello!";
let size = text.size(); // 6
let iter = text.chars(); // iterator ('H', 'e', 'l', 'l', 'o', '!')
let concat = text # " 👋"; // "Hello! 👋"
The "mo:base/Text"
module defines additional operations on Text
values.
Import the module from the base library:
import Text "mo:base/Text";
Note: Text
values are represented as ropes of UTF-8 character sequences with O(1) concatenation.
type Text = Prim.Types.Text
The type corresponding to primitive Text
values.
let hello = "Hello!";
let emoji = "👋";
let concat = hello # " " # emoji; // "Hello! 👋"
let fromChar : (c : Char) -> Text
Converts the given Char
to a Text
value.
let text = Text.fromChar('A'); // "A"
func toIter(t : Text) : Iter.Iter<Char>
Iterates over each Char
value in the given Text
.
Equivalent to calling the t.chars()
method where t
is a Text
value.
import { print } "mo:base/Debug";
for (c in Text.toIter("abc")) {
print(debug_show c);
}
func toArray(t : Text) : [Char]
Creates a new Array
containing characters of the given Text
.
Equivalent to Iter.toArray(t.chars())
.
assert Text.toArray("Café") == ['C', 'a', 'f', 'é'];
Runtime: O(t.size()) Space: O(t.size())
func toVarArray(t : Text) : [var Char]
Creates a new mutable Array
containing characters of the given Text
.
Equivalent to Iter.toArrayMut(t.chars())
.
assert Text.toVarArray("Café") == [var 'C', 'a', 'f', 'é'];
Runtime: O(t.size()) Space: O(t.size())
func fromIter(cs : Iter.Iter<Char>) : Text
Creates a Text
value from a Char
iterator.
let text = Text.fromIter(['a', 'b', 'c'].vals()); // "abc"
func size(t : Text) : Nat
Returns the number of characters in the given Text
.
Equivalent to calling t.size()
where t
is a Text
value.
let size = Text.size("abc"); // 3
func hash(t : Text) : Hash.Hash
Returns a hash obtained by using the djb2
algorithm (more details).
let hash = Text.hash("abc");
Note: this algorithm is intended for use in data structures rather than as a cryptographic hash function.
func concat(t1 : Text, t2 : Text) : Text
Returns t1 # t2
, where #
is the Text
concatenation operator.
let a = "Hello";
let b = "There";
let together = a # b; // "HelloThere"
let withSpace = a # " " # b; // "Hello There"
let togetherAgain = Text.concat(a, b); // "HelloThere"
func equal(t1 : Text, t2 : Text) : Bool
Returns t1 == t2
.
func notEqual(t1 : Text, t2 : Text) : Bool
Returns t1 != t2
.
func less(t1 : Text, t2 : Text) : Bool
Returns t1 < t2
.
func lessOrEqual(t1 : Text, t2 : Text) : Bool
Returns t1 <= t2
.
func greater(t1 : Text, t2 : Text) : Bool
Returns t1 > t2
.
func greaterOrEqual(t1 : Text, t2 : Text) : Bool
Returns t1 >= t2
.
func compare(t1 : Text, t2 : Text) : {#less; #equal; #greater}
Compares t1
and t2
lexicographically.
import { print } "mo:base/Debug";
print(debug_show Text.compare("abc", "abc")); // #equal
print(debug_show Text.compare("abc", "def")); // #less
print(debug_show Text.compare("abc", "ABC")); // #greater
func join(sep : Text, ts : Iter.Iter<Text>) : Text
Join an iterator of Text
values with a given delimiter.
let joined = Text.join(", ", ["a", "b", "c"].vals()); // "a, b, c"
func map(t : Text, f : Char -> Char) : Text
Applies a function to each character in a Text
value, returning the concatenated Char
results.
// Replace all occurrences of '?' with '!'
let result = Text.map("Motoko?", func(c) {
if (c == '?') '!'
else c
});
func translate(t : Text, f : Char -> Text) : Text
Returns the result of applying f
to each character in ts
, concatenating the intermediate text values.
// Replace all occurrences of '?' with "!!"
let result = Text.translate("Motoko?", func(c) {
if (c == '?') "!!"
else Text.fromChar(c)
}); // "Motoko!!"
type Pattern = {#char : Char; #text : Text; #predicate : (Char -> Bool)}
A pattern p
describes a sequence of characters. A pattern has one of the following forms:
#char c
matches the single character sequence,c
.#text t
matches multi-character text sequencet
.#predicate p
matches any single character sequencec
satisfying predicatep(c)
.
A match for p
is any sequence of characters matching the pattern p
.
let charPattern = #char 'A';
let textPattern = #text "phrase";
let predicatePattern : Text.Pattern = #predicate (func(c) { c == 'A' or c == 'B' }); // matches "A" or "B"
func split(t : Text, p : Pattern) : Iter.Iter<Text>
Splits the input Text
with the specified Pattern
.
Two fields are separated by exactly one match.
let words = Text.split("This is a sentence.", #char ' ');
Text.join("|", words) // "This|is|a|sentence."
func tokens(t : Text, p : Pattern) : Iter.Iter<Text>
Returns a sequence of tokens from the input Text
delimited by the specified Pattern
, derived from start to end.
A "token" is a non-empty maximal subsequence of t
not containing a match for pattern p
.
Two tokens may be separated by one or more matches of p
.
let tokens = Text.tokens("this needs\n an example", #predicate (func(c) { c == ' ' or c == '\n' }));
Text.join("|", tokens) // "this|needs|an|example"
func contains(t : Text, p : Pattern) : Bool
Returns true
if the input Text
contains a match for the specified Pattern
.
Text.contains("Motoko", #text "oto") // true
func startsWith(t : Text, p : Pattern) : Bool
Returns true
if the input Text
starts with a prefix matching the specified Pattern
.
Text.startsWith("Motoko", #text "Mo") // true
func endsWith(t : Text, p : Pattern) : Bool
Returns true
if the input Text
ends with a suffix matching the specified Pattern
.
Text.endsWith("Motoko", #char 'o') // true
func replace(t : Text, p : Pattern, r : Text) : Text
Returns the input text t
with all matches of pattern p
replaced by text r
.
let result = Text.replace("abcabc", #char 'a', "A"); // "AbcAbc"
func stripStart(t : Text, p : Pattern) : ?Text
Strips one occurrence of the given Pattern
from the beginning of the input Text
.
If you want to remove multiple instances of the pattern, use Text.trimStart()
instead.
// Try to strip a nonexistent character
let none = Text.stripStart("abc", #char '-'); // null
// Strip just one '-'
let one = Text.stripStart("--abc", #char '-'); // ?"-abc"
func stripEnd(t : Text, p : Pattern) : ?Text
Strips one occurrence of the given Pattern
from the end of the input Text
.
If you want to remove multiple instances of the pattern, use Text.trimEnd()
instead.
// Try to strip a nonexistent character
let none = Text.stripEnd("xyz", #char '-'); // null
// Strip just one '-'
let one = Text.stripEnd("xyz--", #char '-'); // ?"xyz-"
func trimStart(t : Text, p : Pattern) : Text
Trims the given Pattern
from the start of the input Text
.
If you only want to remove a single instance of the pattern, use Text.stripStart()
instead.
let trimmed = Text.trimStart("---abc", #char '-'); // "abc"
func trimEnd(t : Text, p : Pattern) : Text
Trims the given Pattern
from the end of the input Text
.
If you only want to remove a single instance of the pattern, use Text.stripEnd()
instead.
let trimmed = Text.trimEnd("xyz---", #char '-'); // "xyz"
func trim(t : Text, p : Pattern) : Text
Trims the given Pattern
from both the start and end of the input Text
.
let trimmed = Text.trim("---abcxyz---", #char '-'); // "abcxyz"
func compareWith(t1 : Text, t2 : Text, cmp : (Char, Char) -> {#less; #equal; #greater}) : {#less; #equal; #greater}
Compares t1
and t2
using the provided character-wise comparison function.
import Char "mo:base/Char";
Text.compareWith("abc", "ABC", func(c1, c2) { Char.compare(c1, c2) }) // #greater
let encodeUtf8 : Text -> Blob
Returns a UTF-8 encoded Blob
from the given Text
.
let blob = Text.encodeUtf8("Hello");
let decodeUtf8 : Blob -> ?Text
Tries to decode the given Blob
as UTF-8.
Returns null
if the blob is not valid UTF-8.
let text = Text.decodeUtf8("\48\65\6C\6C\6F"); // ?"Hello"
let toLowercase : Text -> Text
Returns the text argument in lowercase. WARNING: Unicode compliant only when compiled, not interpreted.
let text = Text.toLowercase("Good Day"); // ?"good day"
let toUppercase : Text -> Text
Returns the text argument in uppercase. Unicode compliant. WARNING: Unicode compliant only when compiled, not interpreted.
let text = Text.toUppercase("Good Day"); // ?"GOOD DAY"