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
|
# frozen_string_literal: true
class String
# Returns the string, first removing all whitespace on both ends of
# the string, and then changing remaining consecutive whitespace
# groups into one space each.
#
# Note that it handles both ASCII and Unicode whitespace.
#
# %{ Multi-line
# string }.squish # => "Multi-line string"
# " foo bar \n \t boo".squish # => "foo bar boo"
def squish
dup.squish!
end
# Performs a destructive squish. See String#squish.
# str = " foo bar \n \t boo"
# str.squish! # => "foo bar boo"
# str # => "foo bar boo"
def squish!
gsub!(/[[:space:]]+/, " ")
strip!
self
end
# Returns a new string with all occurrences of the patterns removed.
# str = "foo bar test"
# str.remove(" test") # => "foo bar"
# str.remove(" test", /bar/) # => "foo "
# str # => "foo bar test"
def remove(*patterns)
dup.remove!(*patterns)
end
# Alters the string by removing all occurrences of the patterns.
# str = "foo bar test"
# str.remove!(" test", /bar/) # => "foo "
# str # => "foo "
def remove!(*patterns)
patterns.each do |pattern|
gsub! pattern, ""
end
self
end
# Truncates a given +text+ after a given <tt>length</tt> if +text+ is longer than <tt>length</tt>:
#
# 'Once upon a time in a world far far away'.truncate(27)
# # => "Once upon a time in a wo..."
#
# Pass a string or regexp <tt>:separator</tt> to truncate +text+ at a natural break:
#
# 'Once upon a time in a world far far away'.truncate(27, separator: ' ')
# # => "Once upon a time in a..."
#
# 'Once upon a time in a world far far away'.truncate(27, separator: /\s/)
# # => "Once upon a time in a..."
#
# The last characters will be replaced with the <tt>:omission</tt> string (defaults to "...")
# for a total length not exceeding <tt>length</tt>:
#
# 'And they found that many people were sleeping better.'.truncate(25, omission: '... (continued)')
# # => "And they f... (continued)"
def truncate(truncate_at, options = {})
return dup unless length > truncate_at
omission = options[:omission] || "..."
length_with_room_for_omission = truncate_at - omission.length
stop = \
if options[:separator]
rindex(options[:separator], length_with_room_for_omission) || length_with_room_for_omission
else
length_with_room_for_omission
end
"#{self[0, stop]}#{omission}"
end
# Truncates +text+ to at most <tt>bytesize</tt> bytes in length without
# breaking string encoding by splitting multibyte characters or breaking
# grapheme clusters ("perceptual characters") by truncating at combining
# characters.
#
# >> "🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪".size
# => 20
# >> "🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪".bytesize
# => 80
# >> "🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪".truncate_bytes(20)
# => "🔪🔪🔪🔪…"
#
# The truncated text ends with the <tt>:omission</tt> string, defaulting
# to "…", for a total length not exceeding <tt>bytesize</tt>.
def truncate_bytes(truncate_at, omission: "…")
omission ||= ""
case
when bytesize <= truncate_at
dup
when omission.bytesize > truncate_at
raise ArgumentError, "Omission #{omission.inspect} is #{omission.bytesize}, larger than the truncation length of #{truncate_at} bytes"
when omission.bytesize == truncate_at
omission.dup
else
self.class.new.tap do |cut|
cut_at = truncate_at - omission.bytesize
scan(/\X/) do |grapheme|
if cut.bytesize + grapheme.bytesize <= cut_at
cut << grapheme
else
break
end
end
cut << omission
end
end
end
# Truncates a given +text+ after a given number of words (<tt>words_count</tt>):
#
# 'Once upon a time in a world far far away'.truncate_words(4)
# # => "Once upon a time..."
#
# Pass a string or regexp <tt>:separator</tt> to specify a different separator of words:
#
# 'Once<br>upon<br>a<br>time<br>in<br>a<br>world'.truncate_words(5, separator: '<br>')
# # => "Once<br>upon<br>a<br>time<br>in..."
#
# The last characters will be replaced with the <tt>:omission</tt> string (defaults to "..."):
#
# 'And they found that many people were sleeping better.'.truncate_words(5, omission: '... (continued)')
# # => "And they found that many... (continued)"
def truncate_words(words_count, options = {})
sep = options[:separator] || /\s+/
sep = Regexp.escape(sep.to_s) unless Regexp === sep
if self =~ /\A((?>.+?#{sep}){#{words_count - 1}}.+?)#{sep}.*/m
$1 + (options[:omission] || "...")
else
dup
end
end
end
|