Class: Prism::Source

Inherits:
Object
  • Object
show all
Defined in:
lib/prism/parse_result.rb,
ext/prism/extension.c

Overview

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.

Direct Known Subclasses

ASCIISource

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(source, start_line = 1, offsets = []) ⇒ Source

Create a new source object with the given source code.



45
46
47
48
49
 
# File 'lib/prism/parse_result.rb', line 45

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

Instance Attribute Details

#offsets ⇒ Object (readonly)

The list of newline byte offsets in the source code.



42
43
44
 
# File 'lib/prism/parse_result.rb', line 42

def offsets
  @offsets
end

#source ⇒ Object (readonly)

The source code that this source object represents.



36
37
38
 
# File 'lib/prism/parse_result.rb', line 36

def source
  @source
end

#start_line ⇒ Object (readonly)

The line number where this source starts.



39
40
41
 
# File 'lib/prism/parse_result.rb', line 39

def start_line
  @start_line
end

Class Method Details

.for(source, start_line = 1, offsets = []) ⇒ Object

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.



12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
 
# 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)
  elsif source.encoding == Encoding::BINARY
    source.force_encoding(Encoding::UTF_8)

    if source.valid_encoding?
      new(source, start_line, offsets)
    else
      # This is an extremely niche use case where the file is marked as
      # binary, contains multi-byte characters, and those characters are not
      # valid UTF-8. In this case we'll mark it as binary and fall back to
      # treating everything as a single-byte character. This _may_ cause
      # problems when asking for code units, but it appears to be the
      # cleanest solution at the moment.
      source.force_encoding(Encoding::BINARY)
      ASCIISource.new(source, start_line, offsets)
    end
  else
    new(source, start_line, offsets)
  end
end

Instance Method Details

#character_column(byte_offset) ⇒ Object

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



107
108
109
 
# File 'lib/prism/parse_result.rb', line 107

def character_column(byte_offset)
  character_offset(byte_offset) - character_offset(line_start(byte_offset))
end

#character_offset(byte_offset) ⇒ Object

Return the character offset for the given byte offset.



102
103
104
 
# File 'lib/prism/parse_result.rb', line 102

def character_offset(byte_offset)
  (source.byteslice(0, byte_offset) or raise).length
end

#code_units_cache(encoding) ⇒ Object

Generate a cache that targets a specific encoding for calculating code unit offsets.



135
136
137
 
# File 'lib/prism/parse_result.rb', line 135

def code_units_cache(encoding)
  CodeUnitsCache.new(source, encoding)
end

#code_units_column(byte_offset, encoding) ⇒ Object

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



141
142
143
 
# File 'lib/prism/parse_result.rb', line 141

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) ⇒ Object

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.

We purposefully replace invalid and undefined characters with replacement characters in this conversion. This happens for two reasons. First, it’s possible that the given byte offset will not occur on a character boundary. Second, it’s possible that the source code will contain a character that has no equivalent in the given encoding.



123
124
125
126
127
128
129
130
131
 
# File 'lib/prism/parse_result.rb', line 123

def code_units_offset(byte_offset, encoding)
  byteslice = (source.byteslice(0, byte_offset) or raise).encode(encoding, invalid: :replace, undef: :replace)

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

#column(byte_offset) ⇒ Object

Return the column number for the given byte offset.



97
98
99
 
# File 'lib/prism/parse_result.rb', line 97

def column(byte_offset)
  byte_offset - line_start(byte_offset)
end

#deep_freeze ⇒ Object

Freeze this object and the objects it contains.



146
147
148
149
150
 
# File 'lib/prism/parse_result.rb', line 146

def deep_freeze
  source.freeze
  offsets.freeze
  freeze
end

#encoding ⇒ Object

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



63
64
65
 
# File 'lib/prism/parse_result.rb', line 63

def encoding
  source.encoding
end

#line(byte_offset) ⇒ Object

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



80
81
82
 
# File 'lib/prism/parse_result.rb', line 80

def line(byte_offset)
  start_line + find_line(byte_offset)
end

#line_end(byte_offset) ⇒ Object

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



92
93
94
 
# File 'lib/prism/parse_result.rb', line 92

def line_end(byte_offset)
  offsets[find_line(byte_offset) + 1] || source.bytesize
end

#line_start(byte_offset) ⇒ Object

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



86
87
88
 
# File 'lib/prism/parse_result.rb', line 86

def line_start(byte_offset)
  offsets[find_line(byte_offset)]
end

#lines ⇒ Object

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



68
69
70
 
# File 'lib/prism/parse_result.rb', line 68

def lines
  source.lines
end

#replace_offsets(offsets) ⇒ Object

Replace the value of offsets with the given value.



57
58
59
 
# File 'lib/prism/parse_result.rb', line 57

def replace_offsets(offsets)
  @offsets.replace(offsets)
end

#replace_start_line(start_line) ⇒ Object

Replace the value of start_line with the given value.



52
53
54
 
# File 'lib/prism/parse_result.rb', line 52

def replace_start_line(start_line)
  @start_line = start_line
end

#slice(byte_offset, length) ⇒ Object

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



74
75
76
 
# File 'lib/prism/parse_result.rb', line 74

def slice(byte_offset, length)
  source.byteslice(byte_offset, length) or raise
end