1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
|
module CodeRay
module Scanners
# Scanner for output of the diff command.
#
# Alias: +patch+
class Diff < Scanner
register_for :diff
title 'diff output'
DEFAULT_OPTIONS = {
:highlight_code => true,
:inline_diff => true,
}
protected
def scan_tokens encoder, options
line_kind = nil
state = :initial
deleted_lines_count = 0
scanners = Hash.new do |h, lang|
h[lang] = Scanners[lang].new '', :keep_tokens => true, :keep_state => true
end
content_scanner = scanners[:plain]
content_scanner_entry_state = nil
until eos?
if match = scan(/\n/)
deleted_lines_count = 0 unless line_kind == :delete
if line_kind
encoder.end_line line_kind
line_kind = nil
end
encoder.text_token match, :space
next
end
case state
when :initial
if match = scan(/--- |\+\+\+ |=+|_+/)
encoder.begin_line line_kind = :head
encoder.text_token match, :head
if match = scan(/[^\x00\n]+?(?=$|[\t\n]| \(revision)/)
encoder.text_token match, :filename
if options[:highlight_code] && match != '/dev/null'
file_type = CodeRay::FileType.fetch(match, :text)
file_type = :text if file_type == :diff
content_scanner = scanners[file_type]
content_scanner_entry_state = nil
end
end
next unless match = scan(/.+/)
encoder.text_token match, :plain
elsif match = scan(/Index: |Property changes on: /)
encoder.begin_line line_kind = :head
encoder.text_token match, :head
next unless match = scan(/.+/)
encoder.text_token match, :plain
elsif match = scan(/Added: /)
encoder.begin_line line_kind = :head
encoder.text_token match, :head
next unless match = scan(/.+/)
encoder.text_token match, :plain
state = :added
elsif match = scan(/\\ .*/)
encoder.text_token match, :comment
elsif match = scan(/@@(?>[^@\n]+)@@/)
content_scanner.state = :initial unless match?(/\n\+/)
content_scanner_entry_state = nil
if check(/\n|$/)
encoder.begin_line line_kind = :change
else
encoder.begin_group :change
end
encoder.text_token match[0,2], :change
encoder.text_token match[2...-2], :plain
encoder.text_token match[-2,2], :change
encoder.end_group :change unless line_kind
next unless match = scan(/.+/)
if options[:highlight_code]
content_scanner.tokenize match, :tokens => encoder
else
encoder.text_token match, :plain
end
next
elsif match = scan(/\+/)
encoder.begin_line line_kind = :insert
encoder.text_token match, :insert
next unless match = scan(/.+/)
if options[:highlight_code]
content_scanner.tokenize match, :tokens => encoder
else
encoder.text_token match, :plain
end
next
elsif match = scan(/-/)
deleted_lines_count += 1
if options[:inline_diff] && deleted_lines_count == 1 && (changed_lines_count = 1 + check(/.*(?:\n\-.*)*/).count("\n")) && changed_lines_count <= 100_000 && match?(/(?>.*(?:\n\-.*){#{changed_lines_count - 1}}(?:\n\+.*){#{changed_lines_count}})$(?!\n\+)/)
deleted_lines = Array.new(changed_lines_count) { |i| skip(/\n\-/) if i > 0; scan(/.*/) }
inserted_lines = Array.new(changed_lines_count) { |i| skip(/\n\+/) ; scan(/.*/) }
deleted_lines_tokenized = []
inserted_lines_tokenized = []
for deleted_line, inserted_line in deleted_lines.zip(inserted_lines)
pre, deleted_part, inserted_part, post = diff deleted_line, inserted_line
content_scanner_entry_state = content_scanner.state
deleted_lines_tokenized << content_scanner.tokenize([pre, deleted_part, post], :tokens => Tokens.new)
content_scanner.state = content_scanner_entry_state || :initial
inserted_lines_tokenized << content_scanner.tokenize([pre, inserted_part, post], :tokens => Tokens.new)
end
for pre, deleted_part, post in deleted_lines_tokenized
encoder.begin_line :delete
encoder.text_token '-', :delete
encoder.tokens pre
unless deleted_part.empty?
encoder.begin_group :eyecatcher
encoder.tokens deleted_part
encoder.end_group :eyecatcher
end
encoder.tokens post
encoder.end_line :delete
encoder.text_token "\n", :space
end
for pre, inserted_part, post in inserted_lines_tokenized
encoder.begin_line :insert
encoder.text_token '+', :insert
encoder.tokens pre
unless inserted_part.empty?
encoder.begin_group :eyecatcher
encoder.tokens inserted_part
encoder.end_group :eyecatcher
end
encoder.tokens post
changed_lines_count -= 1
if changed_lines_count > 0
encoder.end_line :insert
encoder.text_token "\n", :space
end
end
line_kind = :insert
elsif match = scan(/.*/)
encoder.begin_line line_kind = :delete
encoder.text_token '-', :delete
if options[:highlight_code]
if deleted_lines_count == 1
content_scanner_entry_state = content_scanner.state
end
content_scanner.tokenize match, :tokens => encoder unless match.empty?
if !match?(/\n-/)
if match?(/\n\+/)
content_scanner.state = content_scanner_entry_state || :initial
end
content_scanner_entry_state = nil
end
else
encoder.text_token match, :plain
end
end
next
elsif match = scan(/ .*/)
if options[:highlight_code]
content_scanner.tokenize match, :tokens => encoder
else
encoder.text_token match, :plain
end
next
elsif match = scan(/.+/)
encoder.begin_line line_kind = :comment
encoder.text_token match, :plain
else
raise_inspect 'else case rached'
end
when :added
if match = scan(/ \+/)
encoder.begin_line line_kind = :insert
encoder.text_token match, :insert
next unless match = scan(/.+/)
encoder.text_token match, :plain
else
state = :initial
next
end
end
end
encoder.end_line line_kind if line_kind
encoder
end
private
def diff a, b
# i will be the index of the leftmost difference from the left.
i_max = [a.size, b.size].min
i = 0
i += 1 while i < i_max && a[i] == b[i]
# j_min will be the index of the leftmost difference from the right.
j_min = i - i_max
# j will be the index of the rightmost difference from the right which
# does not precede the leftmost one from the left.
j = -1
j -= 1 while j >= j_min && a[j] == b[j]
return a[0...i], a[i..j], b[i..j], (j < -1) ? a[j+1..-1] : ''
end
end
end
end
|
