Module: UncleKryon::Util

Defined in:
lib/unclekryon/util.rb

Constant Summary collapse

DATE_FORMAT = 
'%F'
DATETIME_FORMAT = 
'%F %T'

Class Method Summary collapse

Class Method Details

.add_trail_slash(url) ⇒ Object 



26
27
28
29
30
31
 
# File 'lib/unclekryon/util.rb', line 26

def self.add_trail_slash(url)
  #url = url + '/' if url !~ /\/\z/
  #return url

  return File.join(url,'')
end

.clean_charset(str) ⇒ Object 



33
34
35
 
# File 'lib/unclekryon/util.rb', line 33

def self.clean_charset(str)
  return str.encode('utf-8','MacRoman',universal_newline: true) # X-MAC-ROMAN
end

.clean_data(str) ⇒ Object 



37
38
39
40
41
42
43
44
 
# File 'lib/unclekryon/util.rb', line 37

def self.clean_data(str)
  # Have to use "[[:space:]]" for "&nbsp;" and "<br/>"
  # This is necessary for "<br />\s+" (see 2015 "KRYON IN LIMA, PERU (2)")
  str = str.clone
  str.gsub!(/[[:space:]]+/,' ') # Replace all spaces with one space
  str.strip!
  return clean_charset(str)
end

.clean_link(url, link) ⇒ Object 



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
 
# File 'lib/unclekryon/util.rb', line 46

def self.clean_link(url,link)
  if url !~ %r{/\z}
    # Don't know if the end is a filename or a dirname, so just assume it is a filename and chop it off
    url = File.dirname(url)
    url = add_trail_slash(url)
  end

  # 1st, handle "/" (because you won't have "/../filename", which is invalid)
  slash_regex = %r{\A(/+\.*/*)+}

  if link =~ slash_regex
    link = link.gsub(slash_regex,'')
    link = get_top_link(url) + link # get_top_link(...) adds a slash

    return link # Already handles "../" or "./" in the regex
  end

  # 2nd, handle "../" (and potentially "../././/" or "..//")
  # - Ignores "./" if has it
  dotdot_regex = %r{\A(\.\./)((\./)*(/)*)*} # \A (../) ( (./)* (/)* )*
  num_dirs = 0 # Could be a boolean; left as int because of legacy code

  while link =~ dotdot_regex
    num_dirs += 1
    link = link.gsub(dotdot_regex,'')
    url = File.dirname(url)
  end

  if num_dirs > 0
    link = add_trail_slash(url) + link

    return link # Already handled "./" in the regex
  end

  # 3rd, handle "./"
  dot_regex = %r{\A(\./+)+}

  if link =~ dot_regex
    link = link.gsub(dot_regex,'')
    link = url + link # Slash already added at top of method

    return link
  end

  # 4th, handle no path
  #if link !~ /#{get_top_link(url)}/i
  if link !~ /\Ahttps?:/i
    link = url + link
  else
    link = link.sub(/\Ahttp:/i,'https:')
  end

  return link
end

.empty_s?(str) ⇒ Boolean 



101
102
103
 
# File 'lib/unclekryon/util.rb', line 101

def self.empty_s?(str)
  return str.nil? || str.gsub(/[[:space:]]+/,'').empty?
end

.fix_link(url) ⇒ Object 



105
106
107
108
109
110
111
112
 
# File 'lib/unclekryon/util.rb', line 105

def self.fix_link(url)
  # If we do URI.escape(), then if it's already "%20",
  # then it will convert it to "%2520"

  url = url.gsub(/[[:space:]]/,'%20')

  return url
end

.fix_shortwith_text(text) ⇒ Object 



114
115
116
117
118
119
120
121
122
123
 
# File 'lib/unclekryon/util.rb', line 114

def self.fix_shortwith_text(text)
  if text =~ %r{w/[[:alnum:]]}i
    # I think it looks better with a space, personally.
    #  Some grammar guides say no space, but the Chicago style guide says there should be a space when it
    #    is a word by itself.
    text = text.gsub(%r{w/}i,'w/ ')
  end

  return text
end

.format_date(date) ⇒ Object 



125
126
127
 
# File 'lib/unclekryon/util.rb', line 125

def self.format_date(date)
  return date.nil? ? nil : date.strftime(DATE_FORMAT)
end

.format_datetime(datetime) ⇒ Object 



129
130
131
 
# File 'lib/unclekryon/util.rb', line 129

def self.format_datetime(datetime)
  return datetime.nil? ? nil : datetime.strftime(DATETIME_FORMAT)
end

.get_top_link(url) ⇒ Object 



133
134
135
136
137
138
139
140
141
142
143
144
145
 
# File 'lib/unclekryon/util.rb', line 133

def self.get_top_link(url)
  raise "No top link: #{url}" if DevOpts.instance.dev? && url !~ /\Ahttps?\:/i

  http_regex = /\Ahttps?\:|\A\./i # Check '.' to prevent infinite loop

  while File.basename(File.dirname(url)) !~ http_regex
    url = File.dirname(url).strip

    break if url == '.' || url.empty?
  end

  return add_trail_slash(url)
end

.get_url_header_data(url) ⇒ Object 



147
148
149
150
151
152
153
154
155
156
157
 
# File 'lib/unclekryon/util.rb', line 147

def self.get_url_header_data(url)
  uri = URI(url)
  r = {}

  Net::HTTP.start(uri.host,uri.port) do |http|
    resp = http.request_head(uri)
    r = resp.to_hash
  end

  return r
end

.hash_def(hash, keys, value) ⇒ Object 



159
160
161
162
163
164
165
166
167
168
 
# File 'lib/unclekryon/util.rb', line 159

def self.hash_def(hash,keys,value)
  v = hash

  (0..keys.length - 2).each do |i|
    v = v[keys[i]]
  end

  v[keys[keys.length - 1]] = value if v[keys[keys.length - 1]].nil?
  return v[keys[keys.length - 1]]
end

.hash_def_all(hash, keys, value) ⇒ Object 



170
171
172
173
174
175
176
177
178
179
180
181
182
 
# File 'lib/unclekryon/util.rb', line 170

def self.hash_def_all(hash,keys,value)
  v = hash

  (0..keys.length - 2).each do |i|
    if v[keys[i]].nil?
      v[keys[i]] = {}
      v = v[keys[i]]
    end
  end

  v[keys[keys.length - 1]] = value if v[keys[keys.length - 1]].nil?
  return v[keys[keys.length - 1]]
end

.mk_dirs_from_filepath(filepath) ⇒ Object 



184
185
186
187
188
189
190
191
192
193
194
195
 
# File 'lib/unclekryon/util.rb', line 184

def self.mk_dirs_from_filepath(filepath)
  dirname = File.dirname(filepath)

  if !dirname.nil?
    raise "Spaces around dirname: '#{dirname}'" if dirname != dirname.strip

    if !Dir.exist?(dirname)
      Log.instance.info("Making dirs: '#{dirname}'...")
      FileUtils.mkdir_p(dirname)
    end
  end
end

.parse_date_s(str) ⇒ Object 



197
198
199
 
# File 'lib/unclekryon/util.rb', line 197

def self.parse_date_s(str)
  return empty_s?(str) ? nil : Date.strptime(str,DATE_FORMAT)
end

.parse_datetime_s(str) ⇒ Object 



201
202
203
 
# File 'lib/unclekryon/util.rb', line 201

def self.parse_datetime_s(str)
  return empty_s?(str) ? nil : DateTime.strptime(str,DATETIME_FORMAT)
end

.parse_url_filename(url) ⇒ Object 



205
206
207
208
209
210
 
# File 'lib/unclekryon/util.rb', line 205

def self.parse_url_filename(url)
  uri = URI.parse(url)
  r = File.basename(uri.path)
  r = CGI.unescape(r)
  return r.strip
end

.safe_max(a, b) ⇒ Object 



212
213
214
 
# File 'lib/unclekryon/util.rb', line 212

def self.safe_max(a,b)
  return a.nil? ? b : (b.nil? ? a : ((a > b) ? a : b))
end