Merge pull request swiftlang#109 from akyrtzi/classification-enhancements

Enhancements to classification mechanism

Author: akyrtzi

Sources/SwiftSyntax/Syntax.swift

@@ -251,20 +251,55 @@ extension _SyntaxBase {
   }
 
   /// Sequence of `SyntaxClassifiedRange`s for this syntax node.
+  ///
+  /// The provided classified ranges are consecutive and cover the full source
+  /// text of the node. The ranges may also span multiple tokens, if multiple
+  /// consecutive tokens would have the same classification then a single classified
+  /// range is provided for all of them.
   var classifications: SyntaxClassifications {
     let fullRange = ByteSourceRange(offset: 0, length: byteSize)
     return SyntaxClassifications(self, in: fullRange)
   }
 
   /// Sequence of `SyntaxClassifiedRange`s contained in this syntax node within
   /// a relative range.
+  ///
+  /// The provided classified ranges may extend beyond the provided `range`.
+  /// Active classifications (non-`none`) will extend the range to include the
+  /// full classified range (e.g. from the beginning of the comment block), while
+  /// `none` classified ranges will extend to the beginning or end of the token
+  /// that the `range` touches.
+  /// It is guaranteed that no classified range will be provided that doesn't
+  /// intersect the provided `range`.
+  ///
   /// - Parameters:
   ///   - in: The relative byte range to pull `SyntaxClassifiedRange`s from.
   /// - Returns: Sequence of `SyntaxClassifiedRange`s.
   func classifications(in range: ByteSourceRange) -> SyntaxClassifications {
     return SyntaxClassifications(self, in: range)
   }
 
+  /// The `SyntaxClassifiedRange` for a relative byte offset.
+  /// - Parameters:
+  ///   - at: The relative to the node byte offset.
+  /// - Returns: The `SyntaxClassifiedRange` for the offset or nil if the source text
+  ///   at the given offset is unclassified.
+  func classification(at offset: Int) -> SyntaxClassifiedRange? {
+    let classifications = SyntaxClassifications(self, in: ByteSourceRange(offset: offset, length: 1))
+    var iterator = classifications.makeIterator()
+    return iterator.next()
+  }
+
+  /// The `SyntaxClassifiedRange` for an absolute position.
+  /// - Parameters:
+  ///   - at: The absolute position.
+  /// - Returns: The `SyntaxClassifiedRange` for the position or nil if the source text
+  ///   at the given position is unclassified.
+  func classification(at position: AbsolutePosition) -> SyntaxClassifiedRange? {
+    let relativeOffset = position.utf8Offset - self.position.utf8Offset
+    return self.classification(at: relativeOffset)
+  }
+
   /// Returns a value representing the unique identity of the node.
   var uniqueIdentifier: SyntaxIdentifier {
     return data.nodeId
@@ -483,19 +518,51 @@ extension Syntax {
   }
 
   /// Sequence of `SyntaxClassifiedRange`s for this syntax node.
+  ///
+  /// The provided classification ranges are consecutive and cover the full source
+  /// text of the node. The ranges may also span multiple tokens, if multiple
+  /// consecutive tokens would have the same classification then a single classified
+  /// range is provided for all of them.
   public var classifications: SyntaxClassifications {
     return base.classifications
   }
 
   /// Sequence of `SyntaxClassifiedRange`s contained in this syntax node within
   /// a relative range.
+  ///
+  /// The provided classified ranges may extend beyond the provided `range`.
+  /// Active classifications (non-`none`) will extend the range to include the
+  /// full classified range (e.g. from the beginning of the comment block), while
+  /// `none` classified ranges will extend to the beginning or end of the token
+  /// that the `range` touches.
+  /// It is guaranteed that no classified range will be provided that doesn't
+  /// intersect the provided `range`.
+  ///
   /// - Parameters:
   ///   - in: The relative byte range to pull `SyntaxClassifiedRange`s from.
   /// - Returns: Sequence of `SyntaxClassifiedRange`s.
   public func classifications(in range: ByteSourceRange) -> SyntaxClassifications {
     return base.classifications(in: range)
   }
 
+  /// The `SyntaxClassifiedRange` for a relative byte offset.
+  /// - Parameters:
+  ///   - at: The relative to the node byte offset.
+  /// - Returns: The `SyntaxClassifiedRange` for the offset or nil if the source text
+  ///   at the given offset is unclassified.
+  public func classification(at offset: Int) -> SyntaxClassifiedRange? {
+    return base.classification(at: offset)
+  }
+
+  /// The `SyntaxClassifiedRange` for an absolute position.
+  /// - Parameters:
+  ///   - at: The absolute position.
+  /// - Returns: The `SyntaxClassifiedRange` for the position or nil if the source text
+  ///   at the given position is unclassified.
+  public func classification(at position: AbsolutePosition) -> SyntaxClassifiedRange? {
+    return base.classification(at: position)
+  }
+
   /// Returns a value representing the unique identity of the node.
   public var uniqueIdentifier: SyntaxIdentifier {
     return base.uniqueIdentifier

Sources/SwiftSyntax/SyntaxClassification.swift.gyb

@@ -55,7 +55,7 @@ extension SyntaxClassification {
   /// - Returns: A pair of classification and whether it is "forced", or nil if
   ///   no classification is attached.
   internal static func classify(
-    parentKind: SyntaxKind, indexInParent: UInt32, childKind: SyntaxKind
+    parentKind: SyntaxKind, indexInParent: Int, childKind: SyntaxKind
   ) -> (SyntaxClassification, Bool)? {
     // Separate checks for token nodes (most common checks) versus checks for layout nodes.
     if childKind == .token {
@@ -83,18 +83,18 @@ extension SyntaxClassification {
 }
 
 extension RawTokenKind {
-  internal var classification: SyntaxClassification? {
+  internal var classification: SyntaxClassification {
     switch (self) {
 % for token in SYNTAX_TOKENS:
     case .${token.swift_kind()}:
-%   if token.classification and token.classification.name != 'None':
+%   if token.classification:
       return .${token.classification.swift_name}
 %   else:
-      return nil
+      return .none
 %   end
 % end
     case .eof:
-      return nil
+      return .none
     }
   }
 }