String
A String is an ordered collection of bytes.
Strings don't specify an encoding.
Example usage of some common String methods:
actor Main
new create(env: Env) =>
try
// construct a new string
let str = "Hello"
// make an uppercased version
let str_upper = str.upper()
// make a reversed version
let str_reversed = str.reverse()
// add " world" to the end of our original string
let str_new = str.add(" world")
// count occurrences of letter "l"
let count = str_new.count("l")
// find first occurrence of letter "w"
let first_w = str_new.find("w")
// find first occurrence of letter "d"
let first_d = str_new.find("d")
// get substring capturing "world"
let substr = str_new.substring(first_w, first_d+1)
// clone substring
let substr_clone = substr.clone()
// print our substr
env.out.print(consume substr)
end
class val String is Seq[U8 val] ref, Comparable[String box] ref, Stringable box
Implements
- Seq[U8 val] ref
- Comparable[String box] ref
- Stringable box
Constructors
create
An empty string. Enough space for len bytes is reserved.
new ref create( len: USize val = 0) : String ref^
Parameters
- len: USize val = 0
Returns
- String ref^
from_array
Create a string from an array, reusing the underlying data pointer.
new val from_array( data: Array[U8 val] val) : String val^
Parameters
Returns
- String val^
from_iso_array
Create a string from an array, reusing the underlying data pointer
new iso from_iso_array( data: Array[U8 val] iso) : String iso^
Parameters
Returns
- String iso^
from_cpointer
Return a string from binary pointer data without making a copy. This must be done only with C-FFI functions that return pony_alloc'd character arrays. If a null pointer is given then an empty string is returned.
new ref from_cpointer( str: Pointer[U8 val] ref, len: USize val, alloc: USize val = 0) : String ref^
Parameters
Returns
- String ref^
from_cstring
Return a string from a pointer to a null-terminated cstring without making a copy. The data is not copied. This must be done only with C-FFI functions that return pony_alloc'd character arrays. The pointer is scanned for the first null byte, which will be interpreted as the null terminator. Note that the scan is unbounded; the pointed to data must be null-terminated within the allocated array to preserve memory safety. If a null pointer is given then an empty string is returned.
new ref from_cstring( str: Pointer[U8 val] ref) : String ref^
Parameters
Returns
- String ref^
copy_cpointer
Create a string by copying a fixed number of bytes from a pointer.
new ref copy_cpointer( str: Pointer[U8 val] box, len: USize val) : String ref^
Parameters
Returns
- String ref^
copy_cstring
Create a string by copying a null-terminated C string. Note that the scan is unbounded; the pointed to data must be null-terminated within the allocated array to preserve memory safety. If a null pointer is given then an empty string is returned.
new ref copy_cstring( str: Pointer[U8 val] box) : String ref^
Parameters
Returns
- String ref^
from_utf32
Create a UTF-8 string from a single UTF-32 code point.
new ref from_utf32( value: U32 val) : String ref^
Parameters
- value: U32 val
Returns
- String ref^
Public Functions
push_utf32
Push a UTF-32 code point.
fun ref push_utf32( value: U32 val) : None val
Parameters
- value: U32 val
Returns
- None val
cpointer
Returns a C compatible pointer to the underlying string allocation.
fun box cpointer( offset: USize val = 0) : Pointer[U8 val] tag
Parameters
- offset: USize val = 0
Returns
cstring
Returns a C compatible pointer to a null-terminated version of the string, safe to pass to an FFI function that doesn't accept a size argument, expecting a null-terminator. If the underlying string is already null terminated, this is returned; otherwise the string is copied into a new, null-terminated allocation.
fun box cstring() : Pointer[U8 val] tag
Returns
array
Returns an Array[U8] that reuses the underlying data pointer.
fun val array() : Array[U8 val] val
Returns
iso_array
Returns an Array[U8] iso that reuses the underlying data pointer.
fun iso iso_array() : Array[U8 val] iso^
Returns
size
Returns the length of the string data in bytes.
fun box size() : USize val
Returns
- USize val
codepoints
Returns the number of unicode code points in the string between the two offsets. Index range [from .. to) is half-open.
fun box codepoints( from: ISize val = 0, to: ISize val = call) : USize val
Parameters
Returns
- USize val
space
Returns the space available for data, not including the null terminator.
fun box space() : USize val
Returns
- USize val
reserve
Reserve space for len bytes. An additional byte will be reserved for the null terminator.
fun ref reserve( len: USize val) : None val
Parameters
- len: USize val
Returns
- None val
compact
Try to remove unused space, making it available for garbage collection. The request may be ignored. The string is returned to allow call chaining.
fun ref compact() : None val
Returns
- None val
recalc
Recalculates the string length. This is only needed if the string is changed via an FFI call. If a null terminator byte is not found within the allocated length, the size will not be changed.
fun ref recalc() : None val
Returns
- None val
truncate
Truncates the string at the minimum of len and space. Ensures there is a null terminator. Does not check for null terminators inside the string.
Note that memory is not freed by this operation.
fun ref truncate( len: USize val) : None val
Parameters
- len: USize val
Returns
- None val
trim_in_place
Trim the string to a portion of itself, covering from until to. Unlike slice, the operation does not allocate a new string nor copy elements.
fun ref trim_in_place( from: USize val = 0, to: USize val = call) : None val
Parameters
Returns
- None val
trim
Return a shared portion of this string, covering from until to. Both the original and the new string are immutable, as they share memory. The operation does not allocate a new string pointer nor copy elements.
fun val trim( from: USize val = 0, to: USize val = call) : String val
Parameters
Returns
- String val
chop
Chops the string in half at the split point requested and returns both the left and right portions. The original string is trimmed in place and returned as the left portion. If the split point is larger than the string, the left portion is the original string and the right portion is a new empty string. Both strings are isolated and mutable, as they do not share memory. The operation does not allocate a new string pointer nor copy elements.
fun iso chop( split_point: USize val) : (String iso^ , String iso^)
Parameters
- split_point: USize val
Returns
unchop
Unchops two iso strings to return the original string they were chopped from. Both input strings are isolated and mutable and were originally chopped from a single string. This function checks that they are indeed two strings chopped from the same original string and can be unchopped before doing the unchopping and returning the unchopped string. If the two strings cannot be unchopped it returns both strings without modifying them. The operation does not allocate a new string pointer nor copy elements.
fun iso unchop( b: String iso) : ((String iso^ , String iso^) | String iso^)
Parameters
- b: String iso
Returns
is_null_terminated
Return true if the string is null-terminated and safe to pass to an FFI function that doesn't accept a size argument, expecting a null-terminator. This method checks that there is a null byte just after the final position of populated bytes in the string, but does not check for other null bytes which may be present earlier in the content of the string. If you need a null-terminated copy of this string, use the clone method.
fun box is_null_terminated() : Bool val
Returns
- Bool val
utf32
Return a UTF32 representation of the character at the given offset and the number of bytes needed to encode that character. If the offset does not point to the beginning of a valid UTF8 encoding, return 0xFFFD (the unicode replacement character) and a length of one. Raise an error if the offset is out of bounds.
fun box utf32( offset: ISize val) : (U32 val , U8 val) ?
Parameters
- offset: ISize val
Returns
apply
Returns the i-th byte. Raise an error if the index is out of bounds.
fun box apply( i: USize val) : U8 val ?
Parameters
- i: USize val
Returns
- U8 val ?
update
Change the i-th byte. Raise an error if the index is out of bounds.
fun ref update( i: USize val, value: U8 val) : U8 val ?
Parameters
Returns
- U8 val ?
at_offset
Returns the byte at the given offset. Raise an error if the offset is out of bounds.
fun box at_offset( offset: ISize val) : U8 val ?
Parameters
- offset: ISize val
Returns
- U8 val ?
update_offset
Changes a byte in the string, returning the previous byte at that offset. Raise an error if the offset is out of bounds.
fun ref update_offset( offset: ISize val, value: U8 val) : U8 val ?
Parameters
Returns
- U8 val ?
clone
Returns a copy of the string. The resulting string is null-terminated even if the original is not.
fun box clone() : String iso^
Returns
- String iso^
repeat_str
Returns a copy of the string repeated num times with an optional separator added inbetween repeats.
fun box repeat_str( num: USize val = 1, sep: String val = "") : String iso^
Parameters
Returns
- String iso^
mul
Returns a copy of the string repeated num times.
fun box mul( num: USize val) : String iso^
Parameters
- num: USize val
Returns
- String iso^
find
Return the index of the n-th instance of s in the string starting from the beginning. Raise an error if there is no n-th occurrence of s or s is empty.
fun box find( s: String box, offset: ISize val = 0, nth: USize val = 0) : ISize val ?
Parameters
Returns
- ISize val ?
rfind
Return the index of n-th instance of s in the string starting from the end. The offset represents the highest index to included in the search. Raise an error if there is no n-th occurrence of s or s is empty.
fun box rfind( s: String box, offset: ISize val = call, nth: USize val = 0) : ISize val ?
Parameters
Returns
- ISize val ?
contains
Returns true if contains s as a substring, false otherwise.
fun box contains( s: String box, offset: ISize val = 0, nth: USize val = 0) : Bool val
Parameters
Returns
- Bool val
count
Counts the non-overlapping occurrences of s in the string.
fun box count( s: String box, offset: ISize val = 0) : USize val
Parameters
Returns
- USize val
at
Returns true if the substring s is present at the given offset.
fun box at( s: String box, offset: ISize val = 0) : Bool val
Parameters
Returns
- Bool val
delete
Delete len bytes at the supplied offset, compacting the string in place.
fun ref delete( offset: ISize val, len: USize val = 1) : None val
Parameters
Returns
- None val
substring
Returns a substring. Index range [from .. to) is half-open. Returns an empty string if nothing is in the range.
Note that this operation allocates a new string to be returned. For similar operations that don't allocate a new string, see trim and trim_in_place.
fun box substring( from: ISize val, to: ISize val = call) : String iso^
Parameters
Returns
- String iso^
lower
Returns a lower case version of the string.
fun box lower() : String iso^
Returns
- String iso^
lower_in_place
Transforms the string to lower case. Currently only knows ASCII case.
fun ref lower_in_place() : None val
Returns
- None val
upper
Returns an upper case version of the string. Currently only knows ASCII case.
fun box upper() : String iso^
Returns
- String iso^
upper_in_place
Transforms the string to upper case.
fun ref upper_in_place() : None val
Returns
- None val
reverse
Returns a reversed version of the string.
fun box reverse() : String iso^
Returns
- String iso^
reverse_in_place
Reverses the byte order in the string. This needs to be changed to handle UTF-8 correctly.
fun ref reverse_in_place() : None val
Returns
- None val
push
Add a byte to the end of the string.
fun ref push( value: U8 val) : None val
Parameters
- value: U8 val
Returns
- None val
pop
Remove a byte from the end of the string.
fun ref pop() : U8 val ?
Returns
- U8 val ?
unshift
Adds a byte to the beginning of the string.
fun ref unshift( value: U8 val) : None val
Parameters
- value: U8 val
Returns
- None val
shift
Removes a byte from the beginning of the string.
fun ref shift() : U8 val ?
Returns
- U8 val ?
append
Append the elements from a sequence, starting from the given offset.
fun ref append( seq: ReadSeq[U8 val] box, offset: USize val = 0, len: USize val = call) : None val
Parameters
Returns
- None val
concat
Add len iterated bytes to the end of the string, starting from the given offset.
fun ref concat( iter: Iterator[U8 val] ref, offset: USize val = 0, len: USize val = call) : None val
Parameters
Returns
- None val
clear
Truncate the string to zero length.
fun ref clear() : None val
Returns
- None val
insert
Returns a version of the string with the given string inserted at the given offset.
fun box insert( offset: ISize val, that: String val) : String iso^
Parameters
Returns
- String iso^
insert_in_place
Inserts the given string at the given offset. Appends the string if the offset is out of bounds.
fun ref insert_in_place( offset: ISize val, that: String box) : None val
Parameters
Returns
- None val
insert_byte
Inserts a byte at the given offset. Appends if the offset is out of bounds.
fun ref insert_byte( offset: ISize val, value: U8 val) : None val
Parameters
Returns
- None val
cut
Returns a version of the string with the given range deleted. Index range [from .. to) is half-open.
fun box cut( from: ISize val, to: ISize val = call) : String iso^
Parameters
Returns
- String iso^
cut_in_place
Cuts the given range out of the string. Index range [from .. to) is half-open.
fun ref cut_in_place( from: ISize val, to: ISize val = call) : None val
Parameters
Returns
- None val
remove
Remove all instances of s from the string. Returns the count of removed instances.
fun ref remove( s: String box) : USize val
Parameters
- s: String box
Returns
- USize val
replace
Replace up to n occurrences of from in this with to. If n is 0, all occurrences will be replaced. Returns the count of replaced occurrences.
fun ref replace( from: String box, to: String box, n: USize val = 0) : USize val
Parameters
Returns
- USize val
split_by
Split the string into an array of strings that are delimited by delim in the original string. If n > 0, then the split count is limited to n.
Example:
let original: String = "<b><span>Hello!</span></b>"
let delimiter: String = "><"
let split_array: Array[String] = original.split_by(delimiter)
env.out.print("OUTPUT:")
for value in split_array.values() do
env.out.print(value)
end
// OUTPUT:
// <b
// span>Hello!</span
// b>
Adjacent delimiters result in a zero length entry in the array. For example, "1CutCut2".split_by("Cut") => ["1", "", "2"].
An empty delimiter results in an array that contains a single element equal to the whole string.
If you want to split the string with each individual character of delim, use split.
fun box split_by( delim: String val, n: USize val = call) : Array[String val] iso^
Parameters
Returns
split
Split the string into an array of strings with any character in the delimiter string. By default, the string is split with whitespace characters. If n > 0, then the split count is limited to n.
Example:
let original: String = "name,job;department"
let delimiter: String = ".,;"
let split_array: Array[String] = original.split(delimiter)
env.out.print("OUTPUT:")
for value in split_array.values() do
env.out.print(value)
end
// OUTPUT:
// name
// job
// department
Adjacent delimiters result in a zero length entry in the array. For example, "1,,2".split(",") => ["1", "", "2"].
If you want to split the string with the entire delimiter string delim, use split_by.
fun box split( delim: String val = " ", n: USize val = 0) : Array[String val] iso^
Parameters
Returns
strip
Remove all leading and trailing characters from the string that are in s.
fun ref strip( s: String box = " ") : None val
Parameters
- s: String box = " "
Returns
- None val
rstrip
Remove all trailing characters within the string that are in s. By default, trailing whitespace is removed.
fun ref rstrip( s: String box = " ") : None val
Parameters
- s: String box = " "
Returns
- None val
lstrip
Remove all leading characters within the string that are in s. By default, leading whitespace is removed.
fun ref lstrip( s: String box = " ") : None val
Parameters
- s: String box = " "
Returns
- None val
add
Return a string that is a concatenation of this and that.
fun box add( that: String box) : String val
Parameters
- that: String box
Returns
- String val
join
Return a string that is a concatenation of the strings in data, using this as a separator.
fun box join( data: Iterator[Stringable box] ref) : String iso^
Parameters
- data: Iterator[Stringable box] ref
Returns
- String iso^
compare
Lexically compare two strings.
fun box compare( that: String box) : (Less val | Equal val | Greater val)
Parameters
- that: String box
Returns
compare_sub
Lexically compare at most n bytes of the substring of this starting at offset with the substring of that starting at that_offset. The comparison is case sensitive unless ignore_case is true.
If the substring of this is a proper prefix of the substring of that, then this is Less than that. Likewise, if that is a proper prefix of this, then this is Greater than that.
Both offset and that_offset can be negative, in which case the offsets are computed from the end of the string.
If n + offset is greater than the length of this, or n + that_offset is greater than the length of that, then the number of positions compared will be reduced to the length of the longest substring.
Needs to be made UTF-8 safe.
fun box compare_sub( that: String box, n: USize val, offset: ISize val = 0, that_offset: ISize val = 0, ignore_case: Bool val = false) : (Less val | Equal val | Greater val)
Parameters
- that: String box
- n: USize val
- offset: ISize val = 0
- that_offset: ISize val = 0
- ignore_case: Bool val = false
Returns
eq
Returns true if the two strings have the same contents.
fun box eq( that: String box) : Bool val
Parameters
- that: String box
Returns
- Bool val
lt
Returns true if this is lexically less than that. Needs to be made UTF-8 safe.
fun box lt( that: String box) : Bool val
Parameters
- that: String box
Returns
- Bool val
le
Returns true if this is lexically less than or equal to that. Needs to be made UTF-8 safe.
fun box le( that: String box) : Bool val
Parameters
- that: String box
Returns
- Bool val
offset_to_index
fun box offset_to_index( i: ISize val) : USize val
Parameters
- i: ISize val
Returns
- USize val
bool
fun box bool() : Bool val ?
Returns
- Bool val ?
i8
fun box i8( base: U8 val = 0) : I8 val ?
Parameters
- base: U8 val = 0
Returns
- I8 val ?
i16
fun box i16( base: U8 val = 0) : I16 val ?
Parameters
- base: U8 val = 0
Returns
- I16 val ?
i32
fun box i32( base: U8 val = 0) : I32 val ?
Parameters
- base: U8 val = 0
Returns
- I32 val ?
i64
fun box i64( base: U8 val = 0) : I64 val ?
Parameters
- base: U8 val = 0
Returns
- I64 val ?
i128
fun box i128( base: U8 val = 0) : I128 val ?
Parameters
- base: U8 val = 0
Returns
- I128 val ?
ilong
fun box ilong( base: U8 val = 0) : ILong val ?
Parameters
- base: U8 val = 0
Returns
- ILong val ?
isize
fun box isize( base: U8 val = 0) : ISize val ?
Parameters
- base: U8 val = 0
Returns
- ISize val ?
u8
fun box u8( base: U8 val = 0) : U8 val ?
Parameters
- base: U8 val = 0
Returns
- U8 val ?
u16
fun box u16( base: U8 val = 0) : U16 val ?
Parameters
- base: U8 val = 0
Returns
- U16 val ?
u32
fun box u32( base: U8 val = 0) : U32 val ?
Parameters
- base: U8 val = 0
Returns
- U32 val ?
u64
fun box u64( base: U8 val = 0) : U64 val ?
Parameters
- base: U8 val = 0
Returns
- U64 val ?
u128
fun box u128( base: U8 val = 0) : U128 val ?
Parameters
- base: U8 val = 0
Returns
- U128 val ?
ulong
fun box ulong( base: U8 val = 0) : ULong val ?
Parameters
- base: U8 val = 0
Returns
- ULong val ?
usize
fun box usize( base: U8 val = 0) : USize val ?
Parameters
- base: U8 val = 0
Returns
- USize val ?
read_int[A: ((I8 val | I16 val | I32 val | I64 val | I128 val | ILong val | ISize val | U8 val | U16 val | U32 val | U64 val | U128 val | ULong val | USize val) & Integer[A] val)]
Read an integer from the specified location in this string. The integer value read and the number of bytes consumed are reported. The base parameter specifies the base to use, 0 indicates using the prefix, if any, to detect base 2, 10 or 16. If no integer is found at the specified location, then (0, 0) is returned, since no characters have been used. An integer out of range for the target type throws an error. A leading minus is allowed for signed integer types. Underscore characters are allowed throughout the integer and are ignored.
fun box read_int[A: ((I8 val | I16 val | I32 val |
I64 val | I128 val | ILong val |
ISize val | U8 val | U16 val |
U32 val | U64 val | U128 val |
ULong val | USize val) & Integer[A] val)](
offset: ISize val = 0,
base: U8 val = 0)
: (A , USize val) ?
Parameters
Returns
- (A , USize val) ?
f32
Convert this string starting at the given offset to a 32-bit floating point number (F32).
This method errors if this string cannot be parsed to a float, if the result would over- or underflow, the offset exceeds the size of this string or there are leftover characters in the string after conversion.
Examples:
"1.5".f32()? == F32(1.5) "1.19208e-07".f32()? == F32(1.19208e-07) "NaN".f32()?.nan() == true
fun box f32( offset: ISize val = 0) : F32 val ?
Parameters
- offset: ISize val = 0
Returns
- F32 val ?
f64
Convert this string starting at the given offset to a 64-bit floating point number (F64).
This method errors if this string cannot be parsed to a float, if the result would over- or underflow, the offset exceeds the size of this string or there are leftover characters in the string after conversion.
Examples:
"1.5".f64()? == F64(1.5) "1.19208e-07".f64()? == F64(1.19208e-07) "Inf".f64()?.infinite() == true
fun box f64( offset: ISize val = 0) : F64 val ?
Parameters
- offset: ISize val = 0
Returns
- F64 val ?
hash
fun box hash() : USize val
Returns
- USize val
hash64
fun box hash64() : U64 val
Returns
- U64 val
string
fun box string() : String iso^
Returns
- String iso^
values
Return an iterator over the bytes in the string.
fun box values() : StringBytes ref^
Returns
- StringBytes ref^
runes
Return an iterator over the codepoints in the string.
fun box runes() : StringRunes ref^
Returns
- StringRunes ref^
ge
fun box ge( that: String box) : Bool val
Parameters
- that: String box
Returns
- Bool val
gt
fun box gt( that: String box) : Bool val
Parameters
- that: String box
Returns
- Bool val
ne
fun box ne( that: String box) : Bool val
Parameters
- that: String box
Returns
- Bool val
© 2016-2020, The Pony Developers
© 2014-2015, Causality Ltd.
Licensed under the BSD 2-Clause License.
https://stdlib.ponylang.io/builtin-String