class Prism::Source

This represents a source of Ruby code that has been parsed. It is used in conjunction with locations to allow them to resolve line numbers and source ranges.

Attributes

offsets [R]

The list of newline byte offsets in the source code.

source [R]

The source code that this source object represents.

start_line [R]

The line number where this source starts.

Public Class Methods

for (source, start_line = 1, offsets = [])

Create a new source object with the given source code. This method should be used instead of ‘new` and it will return either a `Source` or a specialized and more performant `ASCIISource` if no multibyte characters are present in the source code.

# File lib/prism/parse_result.rb, line 12
def self.for(source, start_line = 1, offsets = [])
  if source.ascii_only?
    ASCIISource.new(source, start_line, offsets)
  else
    new(source, start_line, offsets)
  end
end

new (source, start_line = 1, offsets = [])

Create a new source object with the given source code.

# File lib/prism/parse_result.rb, line 30
def initialize(source, start_line = 1, offsets = [])
  @source = source
  @start_line = start_line # set after parsing is done
  @offsets = offsets # set after parsing is done
end

Public Instance Methods

character_column (byte_offset)

Return the column number in characters for the given byte offset.

# File lib/prism/parse_result.rb, line 82
def character_column(byte_offset)
  character_offset(byte_offset) - character_offset(line_start(byte_offset))
end

character_offset (byte_offset)

Return the character offset for the given byte offset.

# File lib/prism/parse_result.rb, line 77
def character_offset(byte_offset)
  (source.byteslice(0, byte_offset) or raise).length
end

code_units_column (byte_offset, encoding)

Returns the column number in code units for the given encoding for the given byte offset.

# File lib/prism/parse_result.rb, line 104
def code_units_column(byte_offset, encoding)
  code_units_offset(byte_offset, encoding) - code_units_offset(line_start(byte_offset), encoding)
end

code_units_offset (byte_offset, encoding)

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.

# File lib/prism/parse_result.rb, line 92
def code_units_offset(byte_offset, encoding)
  byteslice = (source.byteslice(0, byte_offset) or raise).encode(encoding)

  if encoding == Encoding::UTF_16LE || encoding == Encoding::UTF_16BE
    byteslice.bytesize / 2
  else
    byteslice.length
  end
end

column (byte_offset)

Return the column number for the given byte offset.

# File lib/prism/parse_result.rb, line 72
def column(byte_offset)
  byte_offset - line_start(byte_offset)
end

encoding ()

Returns the encoding of the source code, which is set by parameters to the parser or by the encoding magic comment.

# File lib/prism/parse_result.rb, line 38
def encoding
  source.encoding
end

line (byte_offset)

Binary search through the offsets to find the line number for the given byte offset.

# File lib/prism/parse_result.rb, line 55
def line(byte_offset)
  start_line + find_line(byte_offset)
end

line_end (byte_offset)

Returns the byte offset of the end of the line corresponding to the given byte offset.

# File lib/prism/parse_result.rb, line 67
def line_end(byte_offset)
  offsets[find_line(byte_offset) + 1] || source.bytesize
end

line_start (byte_offset)

Return the byte offset of the start of the line corresponding to the given byte offset.

# File lib/prism/parse_result.rb, line 61
def line_start(byte_offset)
  offsets[find_line(byte_offset)]
end

lines ()

Returns the lines of the source code as an array of strings.

# File lib/prism/parse_result.rb, line 43
def lines
  source.lines
end

slice (byte_offset, length)

Perform a byteslice on the source code using the given byte offset and byte length.

# File lib/prism/parse_result.rb, line 49
def slice(byte_offset, length)
  source.byteslice(byte_offset, length) or raise
end