fix_tsv_conflict 0.1.2 → 0.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/Guardfile +1 -1
- data/lib/fix_tsv_conflict/conflict.rb +30 -0
- data/lib/fix_tsv_conflict/repairman.rb +38 -139
- data/lib/fix_tsv_conflict/resolver.rb +111 -0
- data/lib/fix_tsv_conflict/version.rb +1 -1
- metadata +4 -3
- data/lib/fix_tsv_conflict/diff_printer.rb +0 -53
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 073b4ff002e1a394af88ca8d2415786d8ee40c69c77af3741bbedc1585f5cd52
|
4
|
+
data.tar.gz: ab701259a3360cef72e8d37c0f9bed15c0bc6abcb1ff178afa1392d9f965f443
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6ab5861f20e17388137f1c3a83c03b6c13e05bc0865e80894557849c701379f9ac9e9c56ed73b96102447b431758d01f8da0366f67531f9b9ac9b618f26ed0e1
|
7
|
+
data.tar.gz: bf957e7a2d6614b233cc7e0769a1130f8c6b0f32523761546947e2d7b3f399e2461633d90fbddf2698fafc7c998ae540db71ecf2f1c25b3c7181307190f56be4
|
data/Guardfile
CHANGED
@@ -0,0 +1,30 @@
|
|
1
|
+
module FixTSVConflict
|
2
|
+
class Conflict
|
3
|
+
attr_reader :left, :lbranch, :right, :rbranch
|
4
|
+
|
5
|
+
def initialize(left, lbranch, right, rbranch)
|
6
|
+
@left = left
|
7
|
+
@lbranch = lbranch
|
8
|
+
@right = right
|
9
|
+
@rbranch = rbranch
|
10
|
+
end
|
11
|
+
|
12
|
+
ID_REGEXP = /\A[0-9]+\t/
|
13
|
+
NL_REGEXP = /\A\n/
|
14
|
+
|
15
|
+
def valid?
|
16
|
+
left.all? { |line| ID_REGEXP =~ line || NL_REGEXP =~ line} &&
|
17
|
+
right.all? { |line| ID_REGEXP =~ line || NL_REGEXP =~ line }
|
18
|
+
end
|
19
|
+
|
20
|
+
def to_a
|
21
|
+
result = []
|
22
|
+
result << "#{LEFT} #{lbranch}\n"
|
23
|
+
result += left
|
24
|
+
result << "#{SEP}\n"
|
25
|
+
result += right
|
26
|
+
result << "#{RIGHT} #{rbranch}\n"
|
27
|
+
result
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
@@ -1,48 +1,46 @@
|
|
1
|
-
require "fix_tsv_conflict/
|
1
|
+
require "fix_tsv_conflict/conflict"
|
2
2
|
require "fix_tsv_conflict/logging"
|
3
|
+
require "fix_tsv_conflict/resolver"
|
3
4
|
|
4
5
|
module FixTSVConflict
|
5
6
|
class Repairman
|
6
7
|
include Logging
|
7
8
|
|
8
|
-
|
9
|
-
using Module.new {
|
10
|
-
refine String do
|
11
|
-
def blank?
|
12
|
-
BLANK_RE === self
|
13
|
-
end
|
14
|
-
end
|
15
|
-
}
|
16
|
-
|
17
|
-
attr_reader :stderr
|
9
|
+
attr_reader :stdin, :stderr
|
18
10
|
|
19
11
|
def initialize(stdin: $stdin, stderr: $stderr)
|
20
12
|
@stdin = stdin
|
21
13
|
@stderr = stderr
|
22
14
|
end
|
23
15
|
|
16
|
+
def resolver
|
17
|
+
@resolver ||= Resolver.new(stdin: stdin, stderr: stderr)
|
18
|
+
end
|
19
|
+
|
24
20
|
def repair(source)
|
25
21
|
result = []
|
26
|
-
branch
|
22
|
+
branch = nil
|
23
|
+
left, lbranch = [], nil
|
24
|
+
right, rbranch = [], nil
|
27
25
|
|
28
26
|
source.each_line.with_index do |line, i|
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
|
27
|
+
if i.zero?
|
28
|
+
load_tabs_count(line)
|
29
|
+
result << line
|
30
|
+
elsif line.start_with?(LEFT)
|
31
|
+
lbranch = line.chomp.split(" ").last
|
32
|
+
branch = left
|
33
|
+
elsif line.start_with?(SEP)
|
34
|
+
branch = right
|
35
|
+
elsif line.start_with?(RIGHT)
|
36
|
+
rbranch = line.chomp.split(" ").last
|
37
|
+
result += handle(left, lbranch, right, rbranch)
|
38
|
+
branch = nil
|
39
|
+
left.clear
|
40
|
+
right.clear
|
42
41
|
else
|
43
|
-
if
|
44
|
-
|
45
|
-
branch = left
|
42
|
+
if branch
|
43
|
+
branch << line
|
46
44
|
else
|
47
45
|
result << line
|
48
46
|
end
|
@@ -51,130 +49,31 @@ module FixTSVConflict
|
|
51
49
|
result.join
|
52
50
|
end
|
53
51
|
|
54
|
-
def
|
55
|
-
|
56
|
-
|
52
|
+
def load_tabs_count(header)
|
53
|
+
resolver.tabs = header.count(TAB)
|
54
|
+
end
|
55
|
+
|
56
|
+
def handle(left, lbranch, right, rbranch)
|
57
|
+
conflict = Conflict.new(left, lbranch, right, rbranch)
|
58
|
+
print_conflict(conflict)
|
59
|
+
result = resolver.resolve(conflict)
|
57
60
|
print_result(result)
|
58
61
|
result
|
59
62
|
end
|
60
63
|
|
61
|
-
def
|
62
|
-
|
64
|
+
def print_conflict(conflict)
|
65
|
+
info "Found a conflict:"
|
63
66
|
blank
|
64
|
-
dump
|
65
|
-
dump left
|
66
|
-
dump SEP
|
67
|
-
dump right
|
68
|
-
dump "#{RIGHT} #{@rbranch}"
|
67
|
+
dump conflict.to_a
|
69
68
|
blank
|
70
69
|
end
|
71
70
|
|
72
71
|
def print_result(result)
|
73
|
-
notice "
|
72
|
+
notice "Resolved to:"
|
74
73
|
blank
|
75
74
|
dump result
|
76
75
|
blank
|
77
76
|
blank
|
78
77
|
end
|
79
|
-
|
80
|
-
def resolve_conflicts(left, right)
|
81
|
-
left = index_by_id(left.reject(&:blank?))
|
82
|
-
right = index_by_id(right.reject(&:blank?))
|
83
|
-
(left.keys + right.keys).uniq.sort.map do |id|
|
84
|
-
l = left[id]
|
85
|
-
r = right[id]
|
86
|
-
if l && r
|
87
|
-
select(l, r)
|
88
|
-
else
|
89
|
-
l || r
|
90
|
-
end
|
91
|
-
end
|
92
|
-
end
|
93
|
-
|
94
|
-
def select(l, r)
|
95
|
-
selected = if l.rstrip == r.rstrip
|
96
|
-
pick_by_trailing_tabs(l, r)
|
97
|
-
else
|
98
|
-
prompt(l, r)
|
99
|
-
end
|
100
|
-
end
|
101
|
-
|
102
|
-
def prompt(l, r)
|
103
|
-
print_diff(l, r)
|
104
|
-
prompt_select(l, r)
|
105
|
-
end
|
106
|
-
|
107
|
-
def print_diff(l, r)
|
108
|
-
log "Diff by columns:"
|
109
|
-
blank
|
110
|
-
printer = DiffPrinter.new(stderr: @stderr)
|
111
|
-
printer.print(@cols, l, @lbranch, r, @rbranch)
|
112
|
-
end
|
113
|
-
|
114
|
-
def prompt_select(l, r)
|
115
|
-
text = <<-TEXT
|
116
|
-
|
117
|
-
Which do you want keep?
|
118
|
-
|
119
|
-
1) #{@lbranch}
|
120
|
-
2) #{@rbranch}
|
121
|
-
k) keep as is
|
122
|
-
|
123
|
-
Please enter 1, 2, or k:
|
124
|
-
TEXT
|
125
|
-
|
126
|
-
info text.chomp, no_newline: true
|
127
|
-
|
128
|
-
loop do
|
129
|
-
case selected = @stdin.gets.strip
|
130
|
-
when "1"
|
131
|
-
break l
|
132
|
-
when "2"
|
133
|
-
break r
|
134
|
-
when "k"
|
135
|
-
break "#{LEFT} #{@lbranch}\n#{l}#{SEP}\n#{r}#{RIGHT} #{@rbranch}\n"
|
136
|
-
else
|
137
|
-
text = <<-TEXT
|
138
|
-
Invalid input: #{selected}
|
139
|
-
Please enter 1, 2, or k:
|
140
|
-
TEXT
|
141
|
-
@stderr.print text.chomp
|
142
|
-
end
|
143
|
-
end
|
144
|
-
end
|
145
|
-
|
146
|
-
def index_by_id(lines)
|
147
|
-
result = {}
|
148
|
-
lines.each do |line|
|
149
|
-
id = line.split(TAB, 2).first
|
150
|
-
result[id] = line
|
151
|
-
end
|
152
|
-
result
|
153
|
-
end
|
154
|
-
|
155
|
-
def parse_header(line)
|
156
|
-
@cols = {}
|
157
|
-
line.chomp.split(TAB).each.with_index do |col, i|
|
158
|
-
@cols[col] = i
|
159
|
-
end
|
160
|
-
@tabs = @cols.length - 1
|
161
|
-
end
|
162
|
-
|
163
|
-
def pick_by_trailing_tabs(l, r)
|
164
|
-
info "Trailing tab conflicts were fixed automatically."
|
165
|
-
|
166
|
-
ltabs = l.count(TAB)
|
167
|
-
rtabs = r.count(TAB)
|
168
|
-
|
169
|
-
if ltabs == @tabs
|
170
|
-
l
|
171
|
-
elsif rtabs == @tabs
|
172
|
-
r
|
173
|
-
else
|
174
|
-
# both are wrong.
|
175
|
-
# so this is a determistic picking.
|
176
|
-
ltabs < rtabs ? l : r
|
177
|
-
end
|
178
|
-
end
|
179
78
|
end
|
180
79
|
end
|
@@ -0,0 +1,111 @@
|
|
1
|
+
require "fix_tsv_conflict/logging"
|
2
|
+
|
3
|
+
module FixTSVConflict
|
4
|
+
class Resolver
|
5
|
+
include Logging
|
6
|
+
|
7
|
+
BLANK_RE = /\A[[:space:]]*\z/
|
8
|
+
using Module.new {
|
9
|
+
refine String do
|
10
|
+
def blank?
|
11
|
+
BLANK_RE === self
|
12
|
+
end
|
13
|
+
end
|
14
|
+
}
|
15
|
+
|
16
|
+
attr_reader :stdin, :stderr
|
17
|
+
attr_accessor :tabs
|
18
|
+
|
19
|
+
def initialize(stdin: $stdin, stderr: $stderr)
|
20
|
+
@stdin = stdin
|
21
|
+
@stderr = stderr
|
22
|
+
|
23
|
+
@tabs = 0
|
24
|
+
end
|
25
|
+
|
26
|
+
def resolve(conflict)
|
27
|
+
unless conflict.valid?
|
28
|
+
return conflict.to_a
|
29
|
+
end
|
30
|
+
|
31
|
+
result = try(conflict)
|
32
|
+
if result
|
33
|
+
return result
|
34
|
+
end
|
35
|
+
|
36
|
+
warn "Failed to resolve it automatically."
|
37
|
+
select(conflict)
|
38
|
+
end
|
39
|
+
|
40
|
+
def try(conflict)
|
41
|
+
result = []
|
42
|
+
left = index_by_id(conflict.left.reject(&:blank?))
|
43
|
+
right = index_by_id(conflict.right.reject(&:blank?))
|
44
|
+
(left.keys + right.keys).uniq.sort.each do |id|
|
45
|
+
l = left[id]
|
46
|
+
r = right[id]
|
47
|
+
if l && r
|
48
|
+
if l.rstrip == r.rstrip
|
49
|
+
result << pick_by_tabs(l, r)
|
50
|
+
else
|
51
|
+
return false
|
52
|
+
end
|
53
|
+
else
|
54
|
+
result << (l || r)
|
55
|
+
end
|
56
|
+
end
|
57
|
+
result
|
58
|
+
end
|
59
|
+
|
60
|
+
def select(conflict)
|
61
|
+
text = <<-TEXT
|
62
|
+
Which do you want keep?
|
63
|
+
|
64
|
+
1) #{conflict.lbranch}
|
65
|
+
2) #{conflict.rbranch}
|
66
|
+
k) keep as is
|
67
|
+
|
68
|
+
TEXT
|
69
|
+
|
70
|
+
info text
|
71
|
+
|
72
|
+
loop do
|
73
|
+
info "Please enter 1, 2, or k: ", no_newline: true
|
74
|
+
case selected = stdin.gets.strip
|
75
|
+
when "1"
|
76
|
+
return conflict.left
|
77
|
+
when "2"
|
78
|
+
return conflict.right
|
79
|
+
when "k"
|
80
|
+
return conflict.to_a
|
81
|
+
else
|
82
|
+
info "Invalid input: #{selected}"
|
83
|
+
end
|
84
|
+
end
|
85
|
+
end
|
86
|
+
|
87
|
+
def index_by_id(lines)
|
88
|
+
result = {}
|
89
|
+
lines.each do |line|
|
90
|
+
id = line.split(TAB, 2).first
|
91
|
+
result[id] = line
|
92
|
+
end
|
93
|
+
result
|
94
|
+
end
|
95
|
+
|
96
|
+
def pick_by_tabs(l, r)
|
97
|
+
ltabs = l.count(TAB)
|
98
|
+
rtabs = r.count(TAB)
|
99
|
+
|
100
|
+
if ltabs == tabs
|
101
|
+
l
|
102
|
+
elsif rtabs == tabs
|
103
|
+
r
|
104
|
+
else
|
105
|
+
# both are wrong.
|
106
|
+
# so this is a determistic picking.
|
107
|
+
ltabs < rtabs ? l : r
|
108
|
+
end
|
109
|
+
end
|
110
|
+
end
|
111
|
+
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: fix_tsv_conflict
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Masato Ikeda
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2018-02-
|
11
|
+
date: 2018-02-21 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -100,9 +100,10 @@ files:
|
|
100
100
|
- fix_tsv_conflict.gemspec
|
101
101
|
- lib/fix_tsv_conflict.rb
|
102
102
|
- lib/fix_tsv_conflict/cli.rb
|
103
|
-
- lib/fix_tsv_conflict/
|
103
|
+
- lib/fix_tsv_conflict/conflict.rb
|
104
104
|
- lib/fix_tsv_conflict/logging.rb
|
105
105
|
- lib/fix_tsv_conflict/repairman.rb
|
106
|
+
- lib/fix_tsv_conflict/resolver.rb
|
106
107
|
- lib/fix_tsv_conflict/version.rb
|
107
108
|
homepage: https://github.com/a2ikm/fix_tsv_conflict
|
108
109
|
licenses: []
|
@@ -1,53 +0,0 @@
|
|
1
|
-
require "fix_tsv_conflict/logging"
|
2
|
-
|
3
|
-
module FixTSVConflict
|
4
|
-
class DiffPrinter
|
5
|
-
include Logging
|
6
|
-
|
7
|
-
attr_reader :stderr
|
8
|
-
|
9
|
-
def initialize(stderr: $stderr)
|
10
|
-
@stderr = stderr
|
11
|
-
@left, @right = {}, {}
|
12
|
-
end
|
13
|
-
|
14
|
-
def print(cols, left, lbranch, right, rbranch)
|
15
|
-
@lbranch, @rbranch = lbranch, rbranch
|
16
|
-
|
17
|
-
left = left.chomp.split(TAB)
|
18
|
-
right = right.chomp.split(TAB)
|
19
|
-
|
20
|
-
cols.each do |col, i|
|
21
|
-
l, r = left[i], right[i]
|
22
|
-
if l == r
|
23
|
-
flush_conflicts if in_conflict?
|
24
|
-
dump [col, l].join(TAB)
|
25
|
-
else
|
26
|
-
@left[col] = l
|
27
|
-
@right[col] = r
|
28
|
-
end
|
29
|
-
end
|
30
|
-
|
31
|
-
flush_conflicts
|
32
|
-
end
|
33
|
-
|
34
|
-
def flush_conflicts
|
35
|
-
dump "#{LEFT} #{@lbranch}"
|
36
|
-
dump @left.map { |c, v| [c, v].join(TAB) }
|
37
|
-
dump SEP
|
38
|
-
dump @right.map { |c, v| [c, v].join(TAB) }
|
39
|
-
dump "#{RIGHT} #{@rbranch}"
|
40
|
-
|
41
|
-
@left.clear
|
42
|
-
@right.clear
|
43
|
-
end
|
44
|
-
|
45
|
-
def print_col_and_value(col, value)
|
46
|
-
@stderr.puts [col, value].join(TAB)
|
47
|
-
end
|
48
|
-
|
49
|
-
def in_conflict?
|
50
|
-
@left.length > 0 || @right.length > 0
|
51
|
-
end
|
52
|
-
end
|
53
|
-
end
|