Swift struct extension add initializer - swift

I'm trying to add an initializer to Range.
import Foundation
extension Range {
init(_ range: NSRange, in string: String) {
let lower = string.index(string.startIndex, offsetBy: range.location)
let upper = string.index(string.startIndex, offsetBy: NSMaxRange(range))
self.init(uncheckedBounds: (lower: lower, upper: upper))
}
}
But, the last line has a Swift compiler error.
Cannot convert value of type '(lower: String.Index, upper: String.Index)' (aka '(lower: String.CharacterView.Index, upper: String.CharacterView.Index)') to expected argument type '(lower: _, upper: _)'
How do I get it to compile?

The problem is even though String.Index does conform to Comparable protocol, you still need to specify the Range type you want to work with public struct Range<Bound> where Bound : Comparable {}
Note: As NSString uses UTF-16, check this and also in the link you've referred to, your initial code does not work correctly for characters consisting of more than one UTF-16 code point. The following is the updated working version for Swift 3.
extension Range where Bound == String.Index {
init(_ range: NSRange, in string: String) {
let lower16 = string.utf16.index(string.utf16.startIndex, offsetBy: range.location)
let upper16 = string.utf16.index(string.utf16.startIndex, offsetBy: NSMaxRange(range))
if let lower = lower16.samePosition(in: string),
let upper = upper16.samePosition(in: string) {
self.init(lower..<upper)
} else {
fatalError("init(range:in:) could not be implemented")
}
}
}
let string = "❄️Let it snow! ☃️"
let range1 = NSRange(location: 0, length: 1)
let r1 = Range<String.Index>(range1, in: string) // ❄️
let range2 = NSRange(location: 1, length: 2)
let r2 = Range<String.Index>(range2, in: string) // fatal error: init(range:in:) could not be implemented
To answer the OP's comment: The problem is an NSString object encodes a Unicode-compliant text string, represented as a sequence of UTF–16 code units. Unicode scalar values that make up a string’s contents can be up to 21 bits long. The longer scalar values may need two UInt16 values for storage.
Therefore, some letters like ❄️ takes up two UInt16 values in NSString but only one in String. As you pass an NSRange argument to the initializer, you may expect it to work correctly in NSString.
In my example, the results for r1 and r2 after you convert string to utf16 are '❄️' and a fatal error. Meanwhile, the results from your original solution are '❄️L' and 'Le', respectively. Hopefully, you see the difference.
In case you insist with the solution without converting to utf16, you can take a look at the Swift source code to make decision. In Swift 4, you will have the initializer as a built-in lib. The code is as follows.
extension Range where Bound == String.Index {
public init?(_ range: NSRange, in string: String) {
let u = string.utf16
guard range.location != NSNotFound,
let start = u.index(u.startIndex, offsetBy: range.location, limitedBy: u.endIndex),
let end = u.index(u.startIndex, offsetBy: range.location + range.length, limitedBy: u.endIndex),
let lowerBound = String.Index(start, within: string),
let upperBound = String.Index(end, within: string)
else { return nil }
self = lowerBound..<upperBound
}
}

You need to constrain your range initializer to where Bound is equal to String.Index, get your NSRange utf16 indexes and find the same position of the string index in your string as follow:
extension Range where Bound == String.Index {
init?(_ range: NSRange, in string: String) {
guard
let start = string.utf16.index(string.utf16.startIndex, offsetBy: range.location, limitedBy: string.utf16.endIndex),
let end = string.utf16.index(string.utf16.startIndex, offsetBy: range.location + range.length, limitedBy: string.utf16.endIndex),
let startIndex = start.samePosition(in: string),
let endIndex = end.samePosition(in: string)
else {
return nil
}
self = startIndex..<endIndex
}
}

The signature for that method requires a "Bound" type (at least in swift 4)
Since Bound is just an associated type of "Comparable" and String.Index conforms to it, you should just be able to cast it.
extension Range {
init(_ range: NSRange, in string: String) {
let lower : Bound = string.index(string.startIndex, offsetBy: range.location) as! Bound
let upper : Bound = string.index(string.startIndex, offsetBy: NSMaxRange(range)) as! Bound
self.init(uncheckedBounds: (lower: lower, upper: upper))
}
}
https://developer.apple.com/documentation/swift/rangeexpression/2894257-bound

Related

Swift: How do I use String.Index to work with replaceSubrange

I can't figure out String.Index vs. Int
error is...
Instance method 'replaceSubrange(_:with:)' requires the types
'String.Index' and 'Int' be equivalent
func MID( destin: String, start_pos: Int, length: Int, source: String )
{
var destin_string = destin
let dest_index = Int( start_pos - 1 )
let dest_end_index = Int( dest_index + length )
destin_string.replaceSubrange( dest_index...dest_end_index, <<<<<< error
with: source )
}
The index type of String is not Int-compatible because a character can contain multiple bytes.
A workaround to convert Int indices to String.Index is NSRange which matches the startPos and length parameters and which can be reliably converted to Range<String.Index>.
By the way to modify the string inside the function and never use it makes no sense. A better way is an inout parameter
func MID(destin: inout String, startPos: Int, length: Int, source: String )
{
let nsRange = NSRange(location: startPos, length: length)
guard let range = Range(nsRange, in: destin) else { return }
destin.replaceSubrange(range, with: source)
}
The best way is to work with indices all the way and specially the function index(:offsetBy:)
Something like this
func MID(destin: String, start_pos: Int, length: Int, source: String ) -> String {
var destin_string = destin
let dest_index = destin.index(destin.startIndex, offsetBy: start_pos)
let dest_end_index = destin.index(destin.startIndex, offsetBy: start_pos + length)
destin_string.replaceSubrange( dest_index...dest_end_index,
with: source )
return destin_string
}
You might need to adjust some calculations depending on what this function is supposed to do.
Here is a variant of the above with what I consider a bit better naming and some basic error handling
func replace(in string: String, start: Int, length: Int, with replacement: String ) -> String {
if string.isEmpty || start >= string.count { return string }
var input = string
let startIndex = string.index(string.startIndex, offsetBy: start)
var endIndex = string.index(string.startIndex, offsetBy: start + length)
if endIndex >= string.endIndex { endIndex = string.endIndex }
input.replaceSubrange(startIndex..<endIndex, with: replacement)
return input
}
In Swift String is a collection with its own Index type, which doesn't coincide with Int type as per Swift's Array collection.
You'd better read the the official String documentation at the section "Manipulating Indices".
Anyway, in your case rather than that method you wrote, you'd better just write an helper in an extension to get the range of indices from a String instance and then use directly the replaceSubrange(_:with:) method.
Something like:
extension String {
func indicesRange(position: Int, length: Int) -> Range<String.Index>? {
assert(position >= 0 && length >= 0, "position and length must not be negative.")
guard
let start = index(startIndex, offsetBy: position, limitedBy: endIndex),
start < endIndex,
let end = index(start, offsetBy: length, limitedBy: endIndex),
end > start
else { return nil }
return start..<end
}
}
// usage assuming previously defined destination and source strings,
// as well as startPos and length non-negative Int values:
if let range = destination.indicesRange(position: startPos, length: length) {
destination.replaceSubrange(range, with: source)
}

Swift 5.1 Regex Bug

for the following code:
import Foundation
extension String {
var fullRange: NSRange {
return .init(self.startIndex ..< self.endIndex, in: self)
}
public subscript(range: Range<Int>) -> Self.SubSequence {
let st = self.index(self.startIndex, offsetBy: range.startIndex)
let ed = self.index(self.startIndex, offsetBy: range.endIndex)
let sub = self[st ..< ed]
return sub
}
func split(regex pattern: String) throws -> [String] {
let regex = try NSRegularExpression.init(pattern: pattern, options: [])
let fRange = self.fullRange
let match = regex.matches(in: self, options: [], range: fRange)
var list = [String]()
var start = 0
for m in match {
let r = m.range
let end = r.location
list.append(String(self[start ..< end]))
start = end + r.length
}
if start < self.count {
list.append(String(self[start ..< self.count]))
}
return list
}
}
print(try! "مرتفع جداً\nVery High".split(regex: "\n"))
the output should be :
["مرتفع جداً", "Very High"]
but instead it is:
["مرتفع جداً\n", "ery High"]
that because regex (for this case) matched the \n at the offset 10 instead of 9
is there any thing wrong in my code, or it is a bug in swift with regex !!
It's not a bug. You are trying to use Int indexes which is error-prone and strongly discouraged in an Unicode environment.
This is the equivalent of your code with the proper String.Index type and the dedicated API to convert NSRange to Range<String.Index> and vice versa. fullRange and subscript are obsolete.
I just left out the print line. startIndex and endIndex are properties of String
extension String {
func split(regex pattern: String) throws -> [String] {
let regex = try NSRegularExpression(pattern: pattern)
let matches = regex.matches(in: self, range: NSRange(startIndex..., in: self))
var list = [String]()
var start = startIndex
for match in matches {
let range = Range(match.range, in: self)!
let end = range.lowerBound
list.append(String(self[start..<end]))
start = range.upperBound
}
if start < endIndex {
list.append(String(self[start..<endIndex]))
}
return list
}
}
print(try! "مرتفع جداً\nVery High".split(regex: "\n"))
The result is ["مرتفع جداً", "Very High"]
I found the issue behind this bug?!
Swift Strings are so much weirder than any other language; since every character is 4 bytes length, then a single character (may, would, will, ..) contains 1 or 2 unicode characters (witch what happened in my case), so the solution is to subarray the unicodeScalars of the swift String instead of the string it self !!

Swift String Range - Is there easier way to define string ranges?

I consider if there are some easier ways to define string ranges I tried to use some function that need ranges and swift ranges seems to be incredibly unreadable and long.
title.startIndex..<title.index(title.startIndex, offsetBy: 1)
and just to say I want to search only in [0,1) characters of this string
label.text = title.replacingOccurrences(of: "\n", with: "", options: .caseInsensitive, range: title.startIndex..<title.index(title.startIndex, offsetBy: 1) )
There isn't really a concise way to specify a String range.
You could make it a bit nicer with an extension:
extension StringProtocol {
func range(_ ir: Range<Int>) -> Range<String.Index> {
return self.index(self.startIndex, offsetBy: ir.lowerBound) ..< self.index(self.startIndex, offsetBy: ir.upperBound)
}
}
Then
title.startIndex..<title.index(title.startIndex, offsetBy: 1)
becomes
title.range(0..<1)
Note: Be careful to specify a valid range, or this will crash, just like if you had used an offset beyond the end of your string in your example.
The problem is that replacingOccurrencesOf is an Cocoa Objective-C NSString method, so you end up with type impedance mismatch between the String notion of a Range and the NSString notion of an NSRange. The simplest solution is to stay in the NSString world:
label.text = (title as NSString).replacingOccurrences(
of: "\n", with: "", options: .caseInsensitive,
range: NSRange(location: 0, length: 2))
Otherwise I agree with vacawama's idea of an extension:
extension String {
func range(_ start:Int, _ count:Int) -> Range<String.Index> {
let i = self.index(start >= 0 ?
self.startIndex :
self.endIndex, offsetBy: start)
let j = self.index(i, offsetBy: count)
return i..<j
}
func nsRange(_ start:Int, _ count:Int) -> NSRange {
return NSRange(self.range(start,count), in:self)
}
}
Then you can say
label.text = title.replacingOccurrences(
of: "\n", with: "", options: .caseInsensitive,
range: title.range(0,2))

How to find Multiple NSRange for a string from full string iOS swift

let fullString = "Hello world, there are \(string(07)) continents and \(string(195)) countries."
let range = [NSMakeRange(24,2), NSMakeRange(40,3)]
Need to find the NSRange for numbers in the entire full string and there is a possibility that both numbers can be same. Currently hard coding like shown above, the message can be dynamic where hard coding values will be problematic.
I have split the strings and try to fetch NSRange since there is a possibility of same value. like stringOne and stringTwo.
func findNSMakeRange(initialString:String, fromString: String) {
let fullStringRange = fromString.startIndex..<fromString.endIndex
fromString.enumerateSubstrings(in: fullStringRange, options: NSString.EnumerationOptions.byWords) { (substring, substringRange, enclosingRange, stop) -> () in
let start = distance(fromString.startIndex, substringRange.startIndex)
let length = distance(substringRange.startIndex, substringRange.endIndex)
let range = NSMakeRange(start, length)
if (substring == initialString) {
print(substring, range)
}
})
}
Receiving errors like Cannot invoke distance with an argument list of type (String.Index, String.Index)
Anyone have any better solution ?
You say that you want to iterate through NSRange matches in a string so that you can apply a bold attribute to the relevant substrings.
In Swift 5.7 and later, you can use the new Regex:
string.ranges(of: /\d+/)
.map { NSRange($0, in: string) }
.forEach {
attributedString.setAttributes(attributes, range: $0)
}
Or if you find the traditional regular expressions too cryptic, you can import RegexBuilder, and you can use the new regex DSL:
string.ranges(of: Regex { OneOrMore(.digit) })
.map { NSRange($0, in: string) }
.forEach {
attributedString.setAttributes(attributes, range: $0)
}
In Swift versions prior to 5.7, one would use NSRegularExpression. E.g.:
let range = NSRange(location: 0, length: string.count)
try! NSRegularExpression(pattern: "\\d+").enumerateMatches(in: string, range: range) { result, _, _ in
guard let range = result?.range else { return }
attributedString.setAttributes(attributes, range: range)
}
Personally, before Swift 5.7, I found it useful to have a method to return an array of Swift ranges, i.e. [Range<String.Index>]:
extension StringProtocol {
func ranges<T: StringProtocol>(of string: T, options: String.CompareOptions = []) -> [Range<Index>] {
var ranges: [Range<Index>] = []
var start: Index = startIndex
while let range = range(of: string, options: options, range: start ..< endIndex) {
ranges.append(range)
if !range.isEmpty {
start = range.upperBound // if not empty, resume search at upper bound
} else if range.lowerBound < endIndex {
start = index(after: range.lowerBound) // if empty and not at end, resume search at next character
} else {
break // if empty and at end, then quit
}
}
return ranges
}
}
Then you can use it like so:
let string = "Hello world, there are 09 continents and 195 countries."
let ranges = string.ranges(of: "[0-9]+", options: .regularExpression)
And then you can map the Range to NSRange. Going back to the original example, if you wanted to make these numbers bold in some attributed string:
string.ranges(of: "[0-9]+", options: .regularExpression)
.map { NSRange($0, in: string) }
.forEach { attributedString.setAttributes(boldAttributes, range: $0) }
Resources:
Swift 5.7 and later:
WWDC 2022 video Meet Swift Regex
WWDC 2022 video Swift Regex: Beyond the basics
Hacking With Swift: Regular Expressions
Swift before 5.7:
Hacking With Swift: How to use regular expressions in Swift
NSHipster: Regular Expressions in Swift

How does String substring work in Swift

I've been updating some of my old code and answers with Swift 3 but when I got to Swift Strings and Indexing with substrings things got confusing.
Specifically I was trying the following:
let str = "Hello, playground"
let prefixRange = str.startIndex..<str.startIndex.advancedBy(5)
let prefix = str.substringWithRange(prefixRange)
where the second line was giving me the following error
Value of type 'String' has no member 'substringWithRange'
I see that String does have the following methods now:
str.substring(to: String.Index)
str.substring(from: String.Index)
str.substring(with: Range<String.Index>)
These were really confusing me at first so I started playing around index and range. This is a followup question and answer for substring. I am adding an answer below to show how they are used.
All of the following examples use
var str = "Hello, playground"
Swift 4
Strings got a pretty big overhaul in Swift 4. When you get some substring from a String now, you get a Substring type back rather than a String. Why is this? Strings are value types in Swift. That means if you use one String to make a new one, then it has to be copied over. This is good for stability (no one else is going to change it without your knowledge) but bad for efficiency.
A Substring, on the other hand, is a reference back to the original String from which it came. Here is an image from the documentation illustrating that.
No copying is needed so it is much more efficient to use. However, imagine you got a ten character Substring from a million character String. Because the Substring is referencing the String, the system would have to hold on to the entire String for as long as the Substring is around. Thus, whenever you are done manipulating your Substring, convert it to a String.
let myString = String(mySubstring)
This will copy just the substring over and the memory holding old String can be reclaimed. Substrings (as a type) are meant to be short lived.
Another big improvement in Swift 4 is that Strings are Collections (again). That means that whatever you can do to a Collection, you can do to a String (use subscripts, iterate over the characters, filter, etc).
The following examples show how to get a substring in Swift.
Getting substrings
You can get a substring from a string by using subscripts or a number of other methods (for example, prefix, suffix, split). You still need to use String.Index and not an Int index for the range, though. (See my other answer if you need help with that.)
Beginning of a string
You can use a subscript (note the Swift 4 one-sided range):
let index = str.index(str.startIndex, offsetBy: 5)
let mySubstring = str[..<index] // Hello
or prefix:
let index = str.index(str.startIndex, offsetBy: 5)
let mySubstring = str.prefix(upTo: index) // Hello
or even easier:
let mySubstring = str.prefix(5) // Hello
End of a string
Using subscripts:
let index = str.index(str.endIndex, offsetBy: -10)
let mySubstring = str[index...] // playground
or suffix:
let index = str.index(str.endIndex, offsetBy: -10)
let mySubstring = str.suffix(from: index) // playground
or even easier:
let mySubstring = str.suffix(10) // playground
Note that when using the suffix(from: index) I had to count back from the end by using -10. That is not necessary when just using suffix(x), which just takes the last x characters of a String.
Range in a string
Again we simply use subscripts here.
let start = str.index(str.startIndex, offsetBy: 7)
let end = str.index(str.endIndex, offsetBy: -6)
let range = start..<end
let mySubstring = str[range] // play
Converting Substring to String
Don't forget, when you are ready to save your substring, you should convert it to a String so that the old string's memory can be cleaned up.
let myString = String(mySubstring)
Using an Int index extension?
I'm hesitant to use an Int based index extension after reading the article Strings in Swift 3 by Airspeed Velocity and Ole Begemann. Although in Swift 4, Strings are collections, the Swift team purposely hasn't used Int indexes. It is still String.Index. This has to do with Swift Characters being composed of varying numbers of Unicode codepoints. The actual index has to be uniquely calculated for every string.
I have to say, I hope the Swift team finds a way to abstract away String.Index in the future. But until then, I am choosing to use their API. It helps me to remember that String manipulations are not just simple Int index lookups.
I'm really frustrated at Swift's String access model: everything has to be an Index. All I want is to access the i-th character of the string using Int, not the clumsy index and advancing (which happens to change with every major release). So I made an extension to String:
extension String {
func index(from: Int) -> Index {
return self.index(startIndex, offsetBy: from)
}
func substring(from: Int) -> String {
let fromIndex = index(from: from)
return String(self[fromIndex...])
}
func substring(to: Int) -> String {
let toIndex = index(from: to)
return String(self[..<toIndex])
}
func substring(with r: Range<Int>) -> String {
let startIndex = index(from: r.lowerBound)
let endIndex = index(from: r.upperBound)
return String(self[startIndex..<endIndex])
}
}
let str = "Hello, playground"
print(str.substring(from: 7)) // playground
print(str.substring(to: 5)) // Hello
print(str.substring(with: 7..<11)) // play
Swift 5 Extension:
extension String {
subscript(_ range: CountableRange<Int>) -> String {
let start = index(startIndex, offsetBy: max(0, range.lowerBound))
let end = index(start, offsetBy: min(self.count - range.lowerBound,
range.upperBound - range.lowerBound))
return String(self[start..<end])
}
subscript(_ range: CountablePartialRangeFrom<Int>) -> String {
let start = index(startIndex, offsetBy: max(0, range.lowerBound))
return String(self[start...])
}
}
Usage:
let s = "hello"
s[0..<3] // "hel"
s[3...] // "lo"
Or unicode:
let s = "😎🤣😋"
s[0..<1] // "😎"
Swift 4 & 5:
extension String {
subscript(_ i: Int) -> String {
let idx1 = index(startIndex, offsetBy: i)
let idx2 = index(idx1, offsetBy: 1)
return String(self[idx1..<idx2])
}
subscript (r: Range<Int>) -> String {
let start = index(startIndex, offsetBy: r.lowerBound)
let end = index(startIndex, offsetBy: r.upperBound)
return String(self[start ..< end])
}
subscript (r: CountableClosedRange<Int>) -> String {
let startIndex = self.index(self.startIndex, offsetBy: r.lowerBound)
let endIndex = self.index(startIndex, offsetBy: r.upperBound - r.lowerBound)
return String(self[startIndex...endIndex])
}
}
How to use it:
"abcde"[0] --> "a"
"abcde"[0...2] --> "abc"
"abcde"[2..<4] --> "cd"
Swift 4
In swift 4 String conforms to Collection. Instead of substring, we should now use a subscript. So if you want to cut out only the word "play" from "Hello, playground", you could do it like this:
var str = "Hello, playground"
let start = str.index(str.startIndex, offsetBy: 7)
let end = str.index(str.endIndex, offsetBy: -6)
let result = str[start..<end] // The result is of type Substring
It is interesting to know, that doing so will give you a Substring instead of a String. This is fast and efficient as Substring shares its storage with the original String. However sharing memory this way can also easily lead to memory leaks.
This is why you should copy the result into a new String, once you want to clean up the original String. You can do this using the normal constructor:
let newString = String(result)
You can find more information on the new Substring class in the [Apple documentation].1
So, if you for example get a Range as the result of an NSRegularExpression, you could use the following extension:
extension String {
subscript(_ range: NSRange) -> String {
let start = self.index(self.startIndex, offsetBy: range.lowerBound)
let end = self.index(self.startIndex, offsetBy: range.upperBound)
let subString = self[start..<end]
return String(subString)
}
}
Came across this fairly short and simple way of achieving this.
var str = "Hello, World"
let arrStr = Array(str)
print(arrStr[0..<5]) //["H", "e", "l", "l", "o"]
print(arrStr[7..<12]) //["W", "o", "r", "l", "d"]
print(String(arrStr[0..<5])) //Hello
print(String(arrStr[7..<12])) //World
Here's a function that returns substring of a given substring when start and end indices are provided. For complete reference you can visit the links given below.
func substring(string: String, fromIndex: Int, toIndex: Int) -> String? {
if fromIndex < toIndex && toIndex < string.count /*use string.characters.count for swift3*/{
let startIndex = string.index(string.startIndex, offsetBy: fromIndex)
let endIndex = string.index(string.startIndex, offsetBy: toIndex)
return String(string[startIndex..<endIndex])
}else{
return nil
}
}
Here's a link to the blog post that I have created to deal with string manipulation in swift.
String manipulation in swift (Covers swift 4 as well)
Or you can see this gist on github
I had the same initial reaction. I too was frustrated at how syntax and objects change so drastically in every major release.
However, I realized from experience how I always eventually suffer the consequences of trying to fight "change" like dealing with multi-byte characters which is inevitable if you're looking at a global audience.
So I decided to recognize and respect the efforts exerted by Apple engineers and do my part by understanding their mindset when they came up with this "horrific" approach.
Instead of creating extensions which is just a workaround to make your life easier (I'm not saying they're wrong or expensive), why not figure out how Strings are now designed to work.
For instance, I had this code which was working on Swift 2.2:
let rString = cString.substringToIndex(2)
let gString = (cString.substringFromIndex(2) as NSString).substringToIndex(2)
let bString = (cString.substringFromIndex(4) as NSString).substringToIndex(2)
and after giving up trying to get the same approach working e.g. using Substrings, I finally understood the concept of treating Strings as a bidirectional collection for which I ended up with this version of the same code:
let rString = String(cString.characters.prefix(2))
cString = String(cString.characters.dropFirst(2))
let gString = String(cString.characters.prefix(2))
cString = String(cString.characters.dropFirst(2))
let bString = String(cString.characters.prefix(2))
I hope this contributes...
I'm quite mechanical thinking. Here are the basics...
Swift 4
Swift 5
let t = "abracadabra"
let start1 = t.index(t.startIndex, offsetBy:0)
let end1 = t.index(t.endIndex, offsetBy:-5)
let start2 = t.index(t.endIndex, offsetBy:-5)
let end2 = t.index(t.endIndex, offsetBy:0)
let t2 = t[start1 ..< end1]
let t3 = t[start2 ..< end2]
//or a shorter form
let t4 = t[..<end1]
let t5 = t[start2...]
print("\(t2) \(t3) \(t)")
print("\(t4) \(t5) \(t)")
// result:
// abraca dabra abracadabra
The result is a substring, meaning that it is a part of the original string. To get a full blown separate string just use e.g.
String(t3)
String(t4)
This is what I use:
let mid = t.index(t.endIndex, offsetBy:-5)
let firstHalf = t[..<mid]
let secondHalf = t[mid...]
I am new in Swift 3, but looking the String (index) syntax for analogy I think that index is like a "pointer" constrained to string and Int can help as an independent object. Using the base + offset syntax , then we can get the i-th character from string with the code bellow:
let s = "abcdefghi"
let i = 2
print (s[s.index(s.startIndex, offsetBy:i)])
// print c
For a range of characters ( indexes) from string using String (range) syntax we can get from i-th to f-th characters with the code bellow:
let f = 6
print (s[s.index(s.startIndex, offsetBy:i )..<s.index(s.startIndex, offsetBy:f+1 )])
//print cdefg
For a substring (range) from a string using String.substring (range) we can get the substring using the code bellow:
print (s.substring (with:s.index(s.startIndex, offsetBy:i )..<s.index(s.startIndex, offsetBy:f+1 ) ) )
//print cdefg
Notes:
The i-th and f-th begin with 0.
To f-th, I use offsetBY: f + 1, because the range of subscription use ..< (half-open operator), not include the f-th position.
Of course must include validate errors like invalid index.
Same frustration, this should not be that hard...
I compiled this example of getting positions for substring(s) from larger text:
//
// Play with finding substrings returning an array of the non-unique words and positions in text
//
//
import UIKit
let Bigstring = "Why is it so hard to find substrings in Swift3"
let searchStrs : Array<String>? = ["Why", "substrings", "Swift3"]
FindSubString(inputStr: Bigstring, subStrings: searchStrs)
func FindSubString(inputStr : String, subStrings: Array<String>?) -> Array<(String, Int, Int)> {
var resultArray : Array<(String, Int, Int)> = []
for i: Int in 0...(subStrings?.count)!-1 {
if inputStr.contains((subStrings?[i])!) {
let range: Range<String.Index> = inputStr.range(of: subStrings![i])!
let lPos = inputStr.distance(from: inputStr.startIndex, to: range.lowerBound)
let uPos = inputStr.distance(from: inputStr.startIndex, to: range.upperBound)
let element = ((subStrings?[i])! as String, lPos, uPos)
resultArray.append(element)
}
}
for words in resultArray {
print(words)
}
return resultArray
}
returns
("Why", 0, 3)
("substrings", 26, 36)
("Swift3", 40, 46)
Swift 4+
extension String {
func take(_ n: Int) -> String {
guard n >= 0 else {
fatalError("n should never negative")
}
let index = self.index(self.startIndex, offsetBy: min(n, self.count))
return String(self[..<index])
}
}
Returns a subsequence of the first n characters, or the entire string if the string is shorter. (inspired by: https://kotlinlang.org/api/latest/jvm/stdlib/kotlin.text/take.html)
Example:
let text = "Hello, World!"
let substring = text.take(5) //Hello
I created an simple function like this:
func sliceString(str: String, start: Int, end: Int) -> String {
let data = Array(str)
return String(data[start..<end])
}
you can use it in following way
print(sliceString(str: "0123456789", start: 0, end: 3)) // -> prints 012
Swift 5
// imagine, need make substring from 2, length 3
let s = "abcdef"
let subs = s.suffix(s.count-2).prefix(3)
// now subs = "cde"
Swift 4
extension String {
subscript(_ i: Int) -> String {
let idx1 = index(startIndex, offsetBy: i)
let idx2 = index(idx1, offsetBy: 1)
return String(self[idx1..<idx2])
}
}
let s = "hello"
s[0] // h
s[1] // e
s[2] // l
s[3] // l
s[4] // o
I created a simple extension for this (Swift 3)
extension String {
func substring(location: Int, length: Int) -> String? {
guard characters.count >= location + length else { return nil }
let start = index(startIndex, offsetBy: location)
let end = index(startIndex, offsetBy: location + length)
return substring(with: start..<end)
}
}
Heres a more generic implementation:
This technique still uses index to keep with Swift's standards, and imply a full Character.
extension String
{
func subString <R> (_ range: R) -> String? where R : RangeExpression, String.Index == R.Bound
{
return String(self[range])
}
func index(at: Int) -> Index
{
return self.index(self.startIndex, offsetBy: at)
}
}
To sub string from the 3rd character:
let item = "Fred looks funny"
item.subString(item.index(at: 2)...) // "ed looks funny"
I've used camel subString to indicate it returns a String and not a Substring.
Building on the above I needed to split a string at a non-printing character dropping the non-printing character. I developed two methods:
var str = "abc\u{1A}12345sdf"
let range1: Range<String.Index> = str.range(of: "\u{1A}")!
let index1: Int = str.distance(from: str.startIndex, to: range1.lowerBound)
let start = str.index(str.startIndex, offsetBy: index1)
let end = str.index(str.endIndex, offsetBy: -0)
let result = str[start..<end] // The result is of type Substring
let firstStr = str[str.startIndex..<range1.lowerBound]
which I put together using some of the answers above.
Because a String is a collection I then did the following:
var fString = String()
for (n,c) in str.enumerated(){
*if c == "\u{1A}" {
print(fString);
let lString = str.dropFirst(n + 1)
print(lString)
break
}
fString += String(c)
}*
Which for me was more intuitive. Which one is best? I have no way of telling
They both work with Swift 5
var str = "VEGANISM"
print (str[str.index(str.startIndex, offsetBy:2)..<str.index(str.endIndex, offsetBy: -1)] )
//Output-> GANIS
Here, str.startIndex and str.endIndex is the starting index and ending index of your string.
Here as the offsetBy in startIndex = 2 -> str.index(str.startIndex, offsetBy:2) therefore the trimmed string will have starting from index 2 (i.e. from second character) and offsetBy in endIndex = -1 -> str.index(str.endIndex, offsetBy: -1) i.e. 1 character is being trimmed from the end.
var str = "VEGANISM"
print (str[str.index(str.startIndex, offsetBy:0)..<str.index(str.endIndex, offsetBy: 0)] )
//Output-> VEGANISM
As the offsetBy value = 0 on both sides i.e., str.index(str.startIndex, offsetBy:0) and str.index(str.endIndex, offsetBy: 0) therefore, the complete string is being printed
Swift 4
"Substring" (https://developer.apple.com/documentation/swift/substring):
let greeting = "Hi there! It's nice to meet you! 👋"
let endOfSentence = greeting.index(of: "!")!
let firstSentence = greeting[...endOfSentence]
// firstSentence == "Hi there!"
Example of extension String:
private typealias HowDoYouLikeThatElonMusk = String
private extension HowDoYouLikeThatElonMusk {
subscript(_ from: Character?, _ to: Character?, _ include: Bool) -> String? {
if let _from: Character = from, let _to: Character = to {
let dynamicSourceForEnd: String = (_from == _to ? String(self.reversed()) : self)
guard let startOfSentence: String.Index = self.index(of: _from),
let endOfSentence: String.Index = dynamicSourceForEnd.index(of: _to) else {
return nil
}
let result: String = String(self[startOfSentence...endOfSentence])
if include == false {
guard result.count > 2 else {
return nil
}
return String(result[result.index(result.startIndex, offsetBy: 1)..<result.index(result.endIndex, offsetBy: -1)])
}
return result
} else if let _from: Character = from {
guard let startOfSentence: String.Index = self.index(of: _from) else {
return nil
}
let result: String = String(self[startOfSentence...])
if include == false {
guard result.count > 1 else {
return nil
}
return String(result[result.index(result.startIndex, offsetBy: 1)...])
}
return result
} else if let _to: Character = to {
guard let endOfSentence: String.Index = self.index(of: _to) else {
return nil
}
let result: String = String(self[...endOfSentence])
if include == false {
guard result.count > 1 else {
return nil
}
return String(result[..<result.index(result.endIndex, offsetBy: -1)])
}
return result
}
return nil
}
}
example of using the extension String:
let source = ">>>01234..56789<<<"
// include = true
var from = source["3", nil, true] // "34..56789<<<"
var to = source[nil, "6", true] // ">>>01234..56"
var fromTo = source["3", "6", true] // "34..56"
let notFound = source["a", nil, true] // nil
// include = false
from = source["3", nil, false] // "4..56789<<<"
to = source[nil, "6", false] // ">>>01234..5"
fromTo = source["3", "6", false] // "4..5"
let outOfBounds = source[".", ".", false] // nil
let str = "Hello, playground"
let hello = str[nil, ",", false] // "Hello"
The specificity of String has mostly been addressed in other answers. To paraphrase: String has a specific Index which is not of type Int because string elements do not have the same size in the general case. Hence, String does not conform to RandomAccessCollection and accessing a specific index implies the traversal of the collection, which is not an O(1) operation.
Many answers have proposed workarounds for using ranges, but they can lead to inefficient code as they use String methods (index(from:), index(:offsetBy:), ...) that are not O(1).
To access string elements like in an array you should use an Array:
let array = Array("Hello, world!")
let letter = array[5]
This is a trade-off, the array creation is an O(n) operation but array accesses are then O(1). You can convert back to a String when you want with String(array).
Swift 5 Solution High Performance
let fromIndex = s.index(s.startIndex, offsetBy: fromIndex)
let toIndex = s.index(s.startIndex, offsetBy: toIndex)
I used this approach to get the substring from a fromIndex to toIndex for a Leetcode problem and it timed-out it seems like this is quite in-efficient and slow and was causing the timeout.
A faster pure Swift way to get this is done is:
let fromIndex = String.Index(utf16Offset:fromIndex, in: s)
let toIndex = String.Index(utf16Offset: toIndex, in: s)
Tons of answers already, but here's a Swift 5 extension that works like substring in most other languages. length is optional, indexes are capped, and invalid selections result in an empty string (not an error or nil):
extension String {
func substring(_ location: Int, _ length: Int? = nil) -> String {
let start = min(max(0, location), self.count)
let limitedLength = min(self.count - start, length ?? Int.max)
let from = index(startIndex, offsetBy: start)
let to = index(startIndex, offsetBy: start + limitedLength)
return String(self[from..<to])
}
}
Swift 5
let desiredIndex: Int = 7
let substring = str[String.Index(encodedOffset: desiredIndex)...]
This substring variable will give you the result.
Simply here Int is converted to Index and then you can split the strings. Unless you will get errors.
Who ever was responsible for strings in Swift made a total mess of it, and it is definitely one of the worst features of the language.
A simple work-around is the implement a function like this (or make it an extension function):
func substring(str: String, start: Int, end : Int) -> String
{
let startIndex = str.index(str.startIndex, offsetBy: start)
let endIndex = str.index(str.startIndex, offsetBy: end)
return String(str[startIndex..<endIndex])
}