Improve StringProcessing and RegexBuilder documentation

Sources/RegexBuilder/Anchor.swift

@@ -147,7 +147,7 @@ extension Anchor {
   ///
   /// Word boundaries are identified using the Unicode default word boundary
   /// algorithm by default. To specify a different word boundary algorithm,
-  /// see the `RegexComponent.wordBoundaryKind(_:)` method.
+  /// see the `RegexComponent/wordBoundaryKind(_:)` method.
   ///
   /// This anchor is equivalent to `\b` in regex syntax.
   public static var wordBoundary: Anchor {
@@ -157,7 +157,7 @@ extension Anchor {
   /// The inverse of this anchor, which matches at every position that this
   /// anchor does not.
   ///
-  /// For the `wordBoundary` and `textSegmentBoundary` anchors, the inverted
+  /// For the ``wordBoundary`` and ``textSegmentBoundary`` anchors, the inverted
   /// version corresponds to `\B` and `\Y`, respectively.
   public var inverted: Anchor {
     var result = self

Sources/RegexBuilder/Builder.swift

@@ -11,6 +11,15 @@
 
 @_spi(RegexBuilder) import _StringProcessing
 
+/// A custom parameter attribute that constructs regular expressions from
+/// closures.
+///
+/// You typically see `RegexComponentBuilder` as a parameter attribute for
+/// `Regex`- or `RegexComponent`-producing closure parameters, allowing those
+/// closures to combine multiple regular expression components. Type
+/// initializers and string algorithm methods in the RegexBuilder framework
+/// include a builder closure parameter, so that you can use regular expression
+/// components together.
 @available(SwiftStdlib 5.7, *)
 @resultBuilder
 public enum RegexComponentBuilder {

Sources/RegexBuilder/CharacterClass.swift

@@ -12,6 +12,11 @@
 @_implementationOnly import _RegexParser
 @_spi(RegexBuilder) import _StringProcessing
 
+/// A class of characters that match in a regex.
+///
+/// A character class can represent individual characters, a group of
+/// characters, the set of character that match some set of criteria, or
+/// a set algebraic combination of all of the above.
 @available(SwiftStdlib 5.7, *)
 public struct CharacterClass {
   internal var ccc: DSLTree.CustomCharacterClass
@@ -42,6 +47,20 @@ extension CharacterClass: RegexComponent {
 
 @available(SwiftStdlib 5.7, *)
 extension CharacterClass {
+  /// A character class that matches any character that does not match this
+  /// character class.
+  ///
+  /// For example, you can use the `inverted` property to create a character
+  /// class that excludes a specific group of characters:
+  ///
+  ///     let validCharacters = CharacterClass("a"..."z", .anyOf("-_"))
+  ///     let invalidCharacters = validCharacters.inverted
+  ///
+  ///     let username = "user123"
+  ///     if username.contains(invalidCharacters) {
+  ///         print("Invalid username: '\(username)'")
+  ///     }
+  ///     // Prints "Invalid username: 'user123'"
   public var inverted: CharacterClass {
     if let inv = builtin?.inverted {
       return CharacterClass(builtin: inv)
@@ -53,26 +72,50 @@ extension CharacterClass {
 
 @available(SwiftStdlib 5.7, *)
 extension RegexComponent where Self == CharacterClass {
+  /// A character class that matches any element.
+  ///
+  /// This character class is unaffected by the `dotMatchesNewlines()` method.
+  /// To match any character that isn't a newline, see
+  /// ``anyNonNewline``.
+  ///
+  /// This character class is equivalent to the regex syntax "dot"
+  /// metacharacter in single-line mode: `(?s:.)`.
   public static var any: CharacterClass {
     .init(DSLTree.CustomCharacterClass(members: [.atom(.any)]))
   }
 
+  /// A character class that matches any element that isn't a newline.
+  ///
+  /// This character class is unaffected by the `dotMatchesNewlines()` method.
+  /// To match any character, including newlines, see ``any``.
+  ///
+  /// This character class is equivalent to the regex syntax "dot"
+  /// metacharacter with single-line mode disabled: `(?-s:.)`.
   public static var anyNonNewline: CharacterClass {
     .init(DSLTree.CustomCharacterClass(members: [.atom(.anyNonNewline)]))
   }
 
+  /// A character class that matches any single `Character`, or extended
+  /// grapheme cluster, regardless of the current semantic level.
+  ///
+  /// This character class is equivalent to `\X` in regex syntax.
   public static var anyGraphemeCluster: CharacterClass {
     .init(builtin: .anyGrapheme)
   }
 
-  public static var whitespace: CharacterClass {
-    .init(builtin: .whitespace)
-  }
-
+  /// A character class that matches any digit.
+  ///
+  /// This character class is equivalent to `\d` in regex syntax.
   public static var digit: CharacterClass {
     .init(builtin: .digit)
   }
 
+  /// A character class that matches any hexadecimal digit.
+  ///
+  /// `hexDigit` matches the ASCII characters `0` through `9`, and upper- or
+  /// lowercase `a` through `f`. The corresponding characters in the "Halfwidth
+  /// and Fullwidth Forms" Unicode block are not matched by this character
+  /// class.
   public static var hexDigit: CharacterClass {
     .init(DSLTree.CustomCharacterClass(members: [
       .range(.char("A"), .char("F")),
@@ -81,27 +124,56 @@ extension RegexComponent where Self == CharacterClass {
     ]))
   }
 
+  /// A character class that matches any element that is a "word character".
+  ///
+  /// This character class is equivalent to `\w` in regex syntax.
+  public static var word: CharacterClass {
+    .init(builtin: .word)
+  }
+
+  /// A character class that matches any element that is classified as
+  /// whitespace.
+  ///
+  /// This character class is equivalent to `\s` in regex syntax.
+  public static var whitespace: CharacterClass {
+    .init(builtin: .whitespace)
+  }
+
+  /// A character class that matches any element that is classified as
+  /// horizontal whitespace.
+  ///
+  /// This character class is equivalent to `\h` in regex syntax.
   public static var horizontalWhitespace: CharacterClass {
     .init(builtin: .horizontalWhitespace)
   }
 
+  /// A character class that matches any newline sequence.
+  ///
+  /// This character class is equivalent to `\R` or `\n` in regex syntax.
   public static var newlineSequence: CharacterClass {
     .init(builtin: .newlineSequence)
   }
 
+  /// A character class that matches any element that is classified as
+  /// vertical whitespace.
+  ///
+  /// This character class is equivalent to `\v` in regex syntax.
   public static var verticalWhitespace: CharacterClass {
     .init(builtin: .verticalWhitespace)
   }
-
-  public static var word: CharacterClass {
-    .init(builtin: .word)
-  }
 }
 
 @available(SwiftStdlib 5.7, *)
 extension RegexComponent where Self == CharacterClass {
   /// Returns a character class that matches any character in the given string
   /// or sequence.
+  ///
+  /// Calling this method with a group of characters is equivalent to listing
+  /// those characters in a custom character class in regex syntax. For example,
+  /// the two regexes in this example are equivalent:
+  ///
+  ///     let regex1 = /[abcd]+/
+  ///     let regex2 = OneOrMore(.anyOf("abcd"))
   public static func anyOf<S: Sequence>(_ s: S) -> CharacterClass
     where S.Element == Character
   {
@@ -111,6 +183,9 @@ extension RegexComponent where Self == CharacterClass {
 
   /// Returns a character class that matches any Unicode scalar in the given
   /// sequence.
+  ///
+  /// Calling this method with a group of Unicode scalars is equivalent to
+  /// listing them in a custom character class in regex syntax.
   public static func anyOf<S: Sequence>(_ s: S) -> CharacterClass
     where S.Element == UnicodeScalar
   {
@@ -122,6 +197,11 @@ extension RegexComponent where Self == CharacterClass {
 // Unicode properties
 @available(SwiftStdlib 5.7, *)
 extension CharacterClass {
+  /// Returns a character class that matches any element with the given Unicode
+  /// general category.
+  ///
+  /// For example, when passed `.uppercaseLetter`, this method is equivalent to
+  /// `/\p{Uppercase_Letter}/` or `/\p{Lu}/`.
   public static func generalCategory(_ category: Unicode.GeneralCategory) -> CharacterClass {
     return CharacterClass(.generalCategory(category))
   }
@@ -148,6 +228,7 @@ public func ...(lhs: UnicodeScalar, rhs: UnicodeScalar) -> CharacterClass {
 
 @available(SwiftStdlib 5.7, *)
 extension RegexComponent where Self == CharacterClass {
+  /// Creates a character class that combines the given classes in a union.
   public init(_ first: CharacterClass, _ rest: CharacterClass...) {
     if rest.isEmpty {
       self.init(first.ccc)
@@ -161,24 +242,29 @@ extension RegexComponent where Self == CharacterClass {
 
 @available(SwiftStdlib 5.7, *)
 extension CharacterClass {
+  /// Returns a character class from the union of this class and the given class.
   public func union(_ other: CharacterClass) -> CharacterClass {
     CharacterClass(.init(members: [
       .custom(self.ccc),
       .custom(other.ccc)]))
   }
 
+  /// Returns a character class from the intersection of this class and the given class.
   public func intersection(_ other: CharacterClass) -> CharacterClass {
     CharacterClass(.init(members: [
       .intersection(self.ccc, other.ccc)
     ]))
   }
 
+  /// Returns a character class by subtracting the given class from this class.
   public func subtracting(_ other: CharacterClass) -> CharacterClass {
     CharacterClass(.init(members: [
       .subtraction(self.ccc, other.ccc)
     ]))
   }
 
+  /// Returns a character class matching elements in one or the other, but not both,
+  /// of this class and the given class.
   public func symmetricDifference(_ other: CharacterClass) -> CharacterClass {
     CharacterClass(.init(members: [
       .symmetricDifference(self.ccc, other.ccc)