Struct CodePoints

Source

pub struct CodePoints { /* private fields */ }

Expand description

Represents a collection of Unicode code points.

This struct provides functionality for checking if strings contain only the specified code points, and for performing set operations on code point collections.

§Examples

use japanese_codepoints::CodePoints;

let cp = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
assert!(cp.contains("あ"));
assert!(cp.contains("い"));
assert!(!cp.contains("う"));

Implementations§

Source §

impl CodePoints

Source

pub fn new(codepoints: Vec<u32>) -> Self

Creates a new CodePoints instance from a vector of code points.

§Arguments

codepoints - A vector of Unicode code points (u32)

§Examples

use japanese_codepoints::CodePoints;
let cp = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
assert!(cp.contains("あ"));

Source

pub fn from_string(s: &str) -> Self

Creates a new CodePoints instance from a string.

This method extracts all unique code points from the given string.

§Arguments

s - A string containing the code points

§Examples

use japanese_codepoints::CodePoints;

let cp = CodePoints::from_string("あい");
assert!(cp.contains("あ"));
assert!(cp.contains("い"));

Source

pub fn contains(&self, s: &str) -> bool

Checks if the given string contains only code points from this collection.

§Arguments

s - The string to check

§Returns

true if all characters in the string are in this code point collection, false otherwise.

§Examples

use japanese_codepoints::CodePoints;

let cp = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
assert!(cp.contains("あ"));
assert!(cp.contains("あい"));
assert!(!cp.contains("あいう"));

Source

pub fn first_excluded_with_position(&self, s: &str) -> Option<(u32, usize)>

Returns the first code point in the string that is not in this collection, along with its character index.

§Arguments

s - The string to check

§Returns

Some((code_point, char_index)) if a disallowed character is found, where char_index is the index of the character (not byte index) in the string. Returns None if all characters are allowed.

§Note

The returned index is the character index (as in .chars().enumerate()), not the byte index.

§Examples

use japanese_codepoints::CodePoints;
let cp = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
assert_eq!(cp.first_excluded_with_position("あい"), None);
assert_eq!(cp.first_excluded_with_position("あいう"), Some((0x3046, 2))); // う at char index 2

Source

pub fn first_excluded(&self, s: &str) -> Option<u32>

Returns the first code point in the string that is not in this collection.

§Arguments

s - The string to check

§Returns

Some(code_point) if a disallowed character is found, None otherwise.

§Examples

use japanese_codepoints::CodePoints;
let cp = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
assert_eq!(cp.first_excluded("あいう"), Some(0x3046)); // う
assert_eq!(cp.first_excluded("あい"), None);

Source

pub fn all_excluded(&self, s: &str) -> Vec<u32>

Returns all unique code points in the string that are not in this collection.

§Arguments

s - The string to check

§Returns

A vector of unique excluded code points (no duplicates, order not guaranteed).

§Examples

use japanese_codepoints::CodePoints;
let cp = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
let excluded = cp.all_excluded("あいうえ");
assert_eq!(excluded, vec![0x3046, 0x3048]); // う, え

Source

pub fn union(&self, other: &CodePoints) -> CodePoints

Returns the union of this code point collection with another.

§Arguments

other - Another CodePoints instance

§Returns

A new CodePoints instance containing all code points from both collections.

§Examples

use japanese_codepoints::CodePoints;

let cp1 = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
let cp2 = CodePoints::new(vec![0x3044, 0x3046]); // い, う
let union = cp1.union(&cp2);
assert!(union.contains("あいう"));

Source

pub fn intersection(&self, other: &CodePoints) -> CodePoints

Returns the intersection of this code point collection with another.

§Arguments

other - Another CodePoints instance

§Returns

A new CodePoints instance containing only code points present in both collections.

§Examples

use japanese_codepoints::CodePoints;

let cp1 = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
let cp2 = CodePoints::new(vec![0x3044, 0x3046]); // い, う
let intersection = cp1.intersection(&cp2);
assert!(intersection.contains("い"));
assert!(!intersection.contains("あ"));
assert!(!intersection.contains("う"));

Source

pub fn difference(&self, other: &CodePoints) -> CodePoints

Returns the difference of this code point collection with another.

§Arguments

other - Another CodePoints instance

§Returns

A new CodePoints instance containing code points in this collection but not in the other.

§Examples

use japanese_codepoints::CodePoints;

let cp1 = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
let cp2 = CodePoints::new(vec![0x3044, 0x3046]); // い, う
let difference = cp1.difference(&cp2);
assert!(difference.contains("あ"));
assert!(!difference.contains("い"));

Source

pub fn len(&self) -> usize

Returns the number of code points in this collection.

§Examples

use japanese_codepoints::CodePoints;

let cp = CodePoints::new(vec![0x3042, 0x3044, 0x3046]); // あ, い, う
assert_eq!(cp.len(), 3);

Source

pub fn is_empty(&self) -> bool

Returns true if this collection contains no code points.

§Examples

use japanese_codepoints::CodePoints;

let cp = CodePoints::new(vec![]);
assert!(cp.is_empty());

Source

pub fn iter(&self) -> Iter<'_, u32>

Returns an iterator over the code points in this collection.

§Examples

use japanese_codepoints::CodePoints;

let cp = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
let mut iter = cp.iter();
let first = iter.next();
let second = iter.next();
assert_eq!(iter.next(), None);
assert!(first.is_some());
assert!(second.is_some());

Source

pub fn ascii_control() -> Self

Creates a new CodePoints instance with ASCII control characters.

§Examples

use japanese_codepoints::CodePoints;

let cp = CodePoints::ascii_control();
assert!(cp.contains("\n"));
assert!(cp.contains("\r"));
assert!(!cp.contains("a"));

Source

pub fn ascii_control_cached() -> &'static CodePoints

Returns a cached instance of ASCII control characters CodePoints.

This method uses static caching to avoid repeated allocation. Subsequent calls return the same cached instance.

§Examples

use japanese_codepoints::CodePoints;

let cp1 = CodePoints::ascii_control_cached();
let cp2 = CodePoints::ascii_control_cached();
// Both instances share the same underlying data

Source

pub fn ascii_printable() -> Self

Creates a new CodePoints instance with ASCII printable characters.

§Examples

use japanese_codepoints::CodePoints;

let cp = CodePoints::ascii_printable();
assert!(cp.contains("Hello"));
assert!(cp.contains("123"));
assert!(!cp.contains("あ"));

Source

pub fn ascii_printable_cached() -> &'static CodePoints

Returns a cached instance of ASCII printable characters CodePoints.

This method uses static caching to avoid repeated allocation. Subsequent calls return the same cached instance.

§Examples

use japanese_codepoints::CodePoints;

let cp1 = CodePoints::ascii_printable_cached();
let cp2 = CodePoints::ascii_printable_cached();
// Both instances share the same underlying data

Source

pub fn crlf() -> Self

Creates a new CodePoints instance with CRLF characters.

§Examples

use japanese_codepoints::CodePoints;

let cp = CodePoints::crlf();
assert!(cp.contains("\n"));
assert!(cp.contains("\r"));
assert!(!cp.contains("a"));

Source

pub fn crlf_cached() -> &'static CodePoints

Returns a cached instance of CRLF characters CodePoints.

This method uses static caching to avoid repeated allocation. Subsequent calls return the same cached instance.

§Examples

use japanese_codepoints::CodePoints;

let cp1 = CodePoints::crlf_cached();
let cp2 = CodePoints::crlf_cached();
// Both instances share the same underlying data

Source

pub fn ascii_all() -> Self

Creates a new CodePoints instance with all ASCII characters.

§Examples

use japanese_codepoints::CodePoints;

let cp = CodePoints::ascii_all();
assert!(cp.contains("Hello"));
assert!(cp.contains("\n"));
assert!(!cp.contains("あ"));

Source

pub fn ascii_all_cached() -> &'static CodePoints

Returns a cached instance of all ASCII characters CodePoints.

This method uses static caching to avoid repeated allocation. Subsequent calls return the same cached instance.

§Examples

use japanese_codepoints::CodePoints;

let cp1 = CodePoints::ascii_all_cached();
let cp2 = CodePoints::ascii_all_cached();
// Both instances share the same underlying data

Source

pub fn is_subset_of(&self, other: &CodePoints) -> bool

Returns true if this collection is a subset of another CodePoints collection.

§Arguments

other - Another CodePoints instance

§Returns

true if all code points in this collection are also in other.

§Examples

use japanese_codepoints::CodePoints;
let cp1 = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
let cp2 = CodePoints::new(vec![0x3042, 0x3044, 0x3046]); // あ, い, う
assert!(cp1.is_subset_of(&cp2));

Source

pub fn is_superset_of(&self, other: &CodePoints) -> bool

Returns true if this collection is a superset of another CodePoints collection.

§Arguments

other - Another CodePoints instance

§Returns

true if all code points in other are also in this collection.

§Examples

use japanese_codepoints::CodePoints;
let cp1 = CodePoints::new(vec![0x3042, 0x3044, 0x3046]); // あ, い, う
let cp2 = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
assert!(cp1.is_superset_of(&cp2));

Source

pub fn symmetric_difference(&self, other: &CodePoints) -> CodePoints

Returns the symmetric difference of this code point collection with another.

§Arguments

other - Another CodePoints instance

§Returns

A new CodePoints instance containing code points that are in either collection but not in both.

§Examples

use japanese_codepoints::CodePoints;
let cp1 = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
let cp2 = CodePoints::new(vec![0x3044, 0x3046]); // い, う
let diff = cp1.symmetric_difference(&cp2);
assert!(diff.contains("あ"));
assert!(diff.contains("う"));
assert!(!diff.contains("い"));

Source

pub fn contains_all_in_any(s: &str, codepoints_list: &[CodePoints]) -> bool

Checks if the given string contains only code points that are valid in ANY of the provided code point collections.

This is equivalent to the Java method containsAllInAnyCodePoints. Returns true if all characters in the string are included in at least one of the code point collections.

§Arguments

s - The string to check
codepoints_list - A slice of CodePoints instances to check against

§Returns

true if all code points in the given string are included in any of the code points list, false otherwise.

§Examples

use japanese_codepoints::CodePoints;

let hiragana = CodePoints::new(vec![0x3042, 0x3044]); // あ, い
let katakana = CodePoints::new(vec![0x30A2, 0x30A4]); // ア, イ
let mixed_text = "あア"; // Contains both hiragana and katakana

// Each character is valid in at least one collection
assert!(CodePoints::contains_all_in_any("あア", &[hiragana, katakana]));