prism 0.22.0 → 0.24.0

data/lib/prism/node_ext.rb

@@ -94,7 +94,7 @@ module Prism
 
     # Returns the full name of this constant. For example: "Foo"
     def full_name
-      name.name
+      name.to_s
     end
   end
 
@@ -135,7 +135,17 @@ module Prism
     # Returns the list of parts for the full name of this constant path.
     # For example: [:Foo, :Bar]
     def full_name_parts
-      (parent&.full_name_parts || [:""]).push(child.name)
+      parts = case parent
+      when ConstantPathNode, ConstantReadNode
+        parent.full_name_parts
+      when nil
+        [:""]
+      else
+        raise ConstantPathNode::DynamicPartsInConstantPathError,
+          "Constant path target contains dynamic parts. Cannot compute full name"
+      end
+
+      parts.push(child.name)
     end
 
     # Returns the full name of this constant path. For example: "Foo::Bar"
@@ -144,6 +154,19 @@ module Prism
     end
   end
 
+  class ConstantTargetNode < Node
+    # Returns the list of parts for the full name of this constant.
+    # For example: [:Foo]
+    def full_name_parts
+      [name]
+    end
+
+    # Returns the full name of this constant. For example: "Foo"
+    def full_name
+      name.to_s
+    end
+  end
+
   class ParametersNode < Node
     # Mirrors the Method#parameters method.
     def signature

data/lib/prism/parse_result.rb

@@ -9,18 +9,16 @@ module Prism
     attr_reader :source
 
     # The line number where this source starts.
-    attr_accessor :start_line
+    attr_reader :start_line
 
     # The list of newline byte offsets in the source code.
     attr_reader :offsets
 
-    # Create a new source object with the given source code and newline byte
-    # offsets. If no newline byte offsets are given, they will be computed from
-    # the source code.
-    def initialize(source, start_line = 1, offsets = compute_offsets(source))
+    # Create a new source object with the given source code.
+    def initialize(source, start_line = 1, offsets = [])
       @source = source
-      @start_line = start_line
-      @offsets = offsets
+      @start_line = start_line # set after parsing is done
+      @offsets = offsets # set after parsing is done
     end
 
     # Perform a byteslice on the source code using the given byte offset and
@@ -56,6 +54,23 @@ module Prism
       character_offset(byte_offset) - character_offset(line_start(byte_offset))
     end
 
+    # Returns the offset from the start of the file for the given byte offset
+    # counting in code units for the given encoding.
+    #
+    # This method is tested with UTF-8, UTF-16, and UTF-32. If there is the
+    # concept of code units that differs from the number of characters in other
+    # encodings, it is not captured here.
+    def code_units_offset(byte_offset, encoding)
+      byteslice = source.byteslice(0, byte_offset).encode(encoding)
+      (encoding == Encoding::UTF_16LE || encoding == Encoding::UTF_16BE) ? (byteslice.bytesize / 2) : byteslice.length
+    end
+
+    # Returns the column number in code units for the given encoding for the
+    # given byte offset.
+    def code_units_column(byte_offset, encoding)
+      code_units_offset(byte_offset, encoding) - code_units_offset(line_start(byte_offset), encoding)
+    end
+
     private
 
     # Binary search through the offsets to find the line number for the given
@@ -77,14 +92,6 @@ module Prism
 
       left - 1
     end
-
-    # Find all of the newlines in the source code and return their byte offsets
-    # from the start of the string an array.
-    def compute_offsets(code)
-      offsets = [0]
-      code.b.scan("\n") { offsets << $~.end(0) }
-      offsets
-    end
   end
 
   # This represents a location in the source.
@@ -138,6 +145,11 @@ module Prism
       source.character_offset(start_offset)
     end
 
+    # The offset from the start of the file in code units of the given encoding.
+    def start_code_units_offset(encoding = Encoding::UTF_16LE)
+      source.code_units_offset(start_offset, encoding)
+    end
+
     # The byte offset from the beginning of the source where this location ends.
     def end_offset
       start_offset + length
@@ -149,6 +161,11 @@ module Prism
       source.character_offset(end_offset)
     end
 
+    # The offset from the start of the file in code units of the given encoding.
+    def end_code_units_offset(encoding = Encoding::UTF_16LE)
+      source.code_units_offset(end_offset, encoding)
+    end
+
     # The line number where this location starts.
     def start_line
       source.line(start_offset)
@@ -177,6 +194,12 @@ module Prism
       source.character_column(start_offset)
     end
 
+    # The column number in code units of the given encoding where this location
+    # starts from the start of the line.
+    def start_code_units_column(encoding = Encoding::UTF_16LE)
+      source.code_units_column(start_offset, encoding)
+    end
+
     # The column number in bytes where this location ends from the start of the
     # line.
     def end_column
@@ -189,6 +212,12 @@ module Prism
       source.character_column(end_offset)
     end
 
+    # The column number in code units of the given encoding where this location
+    # ends from the start of the line.
+    def end_code_units_column(encoding = Encoding::UTF_16LE)
+      source.code_units_column(end_offset, encoding)
+    end
+
     # Implement the hash pattern matching interface for Location.
     def deconstruct_keys(keys)
       { start_offset: start_offset, end_offset: end_offset }
@@ -423,17 +452,19 @@ module Prism
 
   # This represents a token from the Ruby source.
   class Token
+    # The Source object that represents the source this token came from.
+    attr_reader :source
+    private :source
+
     # The type of token that this token is.
     attr_reader :type
 
     # A byteslice of the source that this token represents.
     attr_reader :value
 
-    # A Location object representing the location of this token in the source.
-    attr_reader :location
-
     # Create a new token object with the given type, value, and location.
-    def initialize(type, value, location)
+    def initialize(source, type, value, location)
+      @source = source
       @type = type
       @value = value
       @location = location
@@ -444,6 +475,12 @@ module Prism
       { type: type, value: value, location: location }
     end
 
+    # A Location object representing the location of this token in the source.
+    def location
+      return @location if @location.is_a?(Location)
+      @location = Location.new(source, @location >> 32, @location & 0xFFFFFFFF)
+    end
+
     # Implement the pretty print interface for Token.
     def pretty_print(q)
       q.group do