Class: Studium::DateSanitizer

Inherits:
Base
  • Object
show all
Defined in:
lib/studium/check_and_sanitize/date_sanitizer.rb

Overview

Studium::DateSanitizer

Constant Summary collapse

TIME_RANGE_FROM_TO =
#

TIME_RANGE_FROM_TO

#
/(\d{2}:\d{2}-\d{2}:\d{2})/

Constants inherited from Base

Base::COMMON_YEAR_DAYS_IN_MONTH, Base::LEFT_PADDING, Base::NAMESPACE, Base::N_CHARACTERS_PER_LINE

Constants included from Colours

Colours::COLOURS

Class Method Summary collapse

Instance Method Summary collapse

Methods inherited from Base

#add_proper_year_entry_to_this_line, #already_solved_this_lva_number?, #append_what_into, #available_topics_as_short_name, #average_grade, #bachelor_master_or_diploma, #be_silent, #be_verbose?, #beautiful_url, #change_directory, #cheering_person, #chmod, #cliner, #colour_for_ects_points, #colourize_percentage, #convert_this_array_of_lectures_into_the_full_dataset, #copy, #course_filter, #cpruby, #create_directory, #create_file, #csv_file?, #current_month?, #current_semester?, #dataset?, #datum?, #day_month_year, #debug?, #delete_file, #directory_of_the_exam_topics?, #directory_to_my_exam_topics, #directory_to_the_exam_topics?, #disable_colours, #disable_colours_globally, #do_not_be_verbose, #do_not_use_opn, #do_these_curricula_include_both_a_bachelor_and_a_master_curriculum?, #does_this_line_include_a_german_weekday?, #does_this_line_include_a_html_colour?, #does_this_line_include_an_english_weekday?, #does_this_line_start_with_a_german_weekday?, #e, #ecomment, #editor?, #ee, #egrey, #enable_colours, #enable_colours_globally, #enable_debug, #encoding?, #english_to_german_weekday, #ensure_that_a_base_directory_exists_for_this_file, #ensure_that_the_log_directory_exists, #eparse, #esystem, #etomato, #exit_program, #extract_dd_mm_yyyy, #fetch_this_curriculum, #file_important_exams?, #file_lecture_information?, #file_passed_exams_per_month, #file_read_with_proper_encoding, #filter_away_already_answered_questions, #filter_away_invalid_questions, #filter_for_all_passed_exams, #find_corresponding_exam_topic, #from_curriculum_id_to_university, #german_date_notation, #german_weekday?, #german_weekdays?, #german_weekend_for?, #german_yes_or_no, #has_a_bachelor_and_a_master_curriculum?, #has_a_bachelor_curriculum?, #has_a_master_curriculum?, #has_lva_dates_registered?, #has_this_exam_topic_been_solved?, #has_year_entry?, #hh_mm_ss_dd_mm_yyyy, #horizontal_bar?, #html_log_directory?, #infer_the_namespace, #initialize_the_internal_hash, #internal_hash?, #is_a_master_lecture?, #is_a_registered_curriculum?, #is_a_weekday?, #is_connected_to_the_www?, #is_german_weekday?, #is_on_roebe?, #is_prüfungsimmanent?, #is_this_a_registered_exam_topic?, #is_this_a_valid_html_colour?, #is_this_day_today?, #is_this_lecture_a_practical_course?, #konsole_support?, #last_file?, #lectures_from_indi1, #lectures_from_indi2, #lectures_from_indi3, #lectures_from_indi4, #lectures_from_the_bachelor_genetik_curriculum, #lectures_from_the_individual_vektor_curricula, #left_arrow?, #load_yaml_dataset, #map_input_to_this_curriculum_filename, #move_file, #n_days_difference_from_today_to_this_day, #n_seconds_to_n_days, #namespace?, #no_ext_name, #no_file_exists_at, #number_to_month, #obtain, #obtain_lectures_from_this_curriculum, #open_in_browser, #open_in_editor, #opne, #opnerev, #opnn, #padded_current_month?, #parse_dd_mm_yyyy, #parse_this_line_for_date_entry, #path_to_exam_topic?, #project_yaml_directory?, #rds, #read_dataset_from_a_curriculum_file, #read_in_exam_dataset_from_this_file, #read_this_file_with_default_encoding, #readlines_from_this_input_file, #register_sigint, #remove_empty_strings, #remove_escape_sequences, #remove_internal_comments, #remove_leading_comments, #remove_leading_weekday_names_from, #remove_newlines, #remove_tags_from_this_input, #rename_kde_konsole_tab, #rename_konsole_tab?, #replace_all_html_colours_in_this, #replace_bold_token_with_default_colour, #replace_italic_token_with_default_colour, #replace_italic_token_with_this_colour, #replace_regular_numbers_with_unicode_numbers, #replace_underline_token_with_default_colour, #replace_underline_token_with_this_colour, #require_open_uri, #reset_the_internal_state, #return_all_bachelor_lectures, #return_all_exams_on_this_day, #return_all_numbers_from, #return_all_registered_curricula, #return_all_steop_lectures, #return_current_year, #return_dataset_for_this_topic, #return_dataset_from_this_curriculum_file, #return_dd_mm_yy_and_time_from, #return_directory_for, #return_ects_points_from_these_lectures, #return_either_grey_or_the_custom_colour_for_answers, #return_either_grey_or_the_custom_colour_for_questions, #return_file_for_this_curriculum, #return_german_name_for_this_english_month, #return_german_weekday_of?, #return_hh_mm_ss_from, #return_hour_from_this, #return_lectures_from_bachelor_vektor_curriculum, #return_lectures_with_at_the_least_one_upcoming_exam, #return_local_path_of_this_pwdstud, #return_lva_number_of_this_lecture, #return_month_fitting_to_this_input, #return_n_days_until_monday, #return_n_days_until_sunday, #return_n_exam_questions_in, #return_n_questions_were_answered_for_this_topic, #return_name_of_the_weekday, #return_name_of_this_curriculum, #return_name_of_this_curriculum_based_on_its_id_number, #return_opnn, #return_passed_courses, #return_pwd, #return_random_curriculum, #return_sanitized_dataset_from_the_file_lecture_information, #return_solved_lectures, #return_steop_lectures, #return_the_remote_homepage_url, #return_this_line_has_n_characters_as_html_colour_tags, #return_title_from_this_curriculum_file, #right_arrow?, #rinstall2, #roebe_exam_directory?, #roebe_path_to_file_lecture_information?, #ruby_src_dir_at_home?, #sanitize_this_topic, #sanitize_url, #select_for_prüfungsimmanente_LVs, #select_lectures_with_this_key, #set_be_verbose, #set_this_cd_alias_to, #set_xorg_buffer, #sfancy, #shall_we_make_use_of_unicode_symbols?, #show_todays_date, #silently_open_in_browser, #simp, #sort_these_lecture_names_by_time, #spacer, #studium_log_dir?, #this_month_has_n_days?, #total_ects_points_passed, #translate_dd_mm_yyyy_to_weekday, #try_to_require_html_templates, #try_to_require_the_open_gem, #try_to_require_the_rcfiles, #try_to_require_the_verbose_truth_gem, #turn_this_array_into_the_full_dataset, #unicode_blocks_line, #use_colours?, #use_opn?, #vertical_bar?, #web_liner, #weekday?, #weekdays?, #word_wrap, #write_what_into, #www_connection_is_unavailable, #yaml_dir?, #yellowrev, #yes_or_no

Methods included from RunmodeModule

#commandline?, #runmode?, #set_commandline_mode, #set_runmode, #set_www_mode, #www_mode?

Methods included from CommandlineArgumentsModule

#commandline_arguments?, #commandline_arguments_joined, #commandline_arguments_with_hyphens?, #commandline_arguments_without_leading_hyphens?, #first_argument?, #first_non_hyphen_argument?, #reset_the_commandline_arguments, #set_commandline_arguments, #set_first_argument

Methods included from HtmlColoursModule

#aquamarine, #blanchedalmond, #brown, #cadetblue, #chocolate, #coral, #cornflowerblue, #crimson, #cyan, #darkblue, #darkcyan, #darkgoldenrod, #darkgreen, #darkkhaki, #darkolivegreen, #darkorange, #darkred, #darkseagreen, #darkslateblue, #darkslategray, #darkturquoise, #deepskyblue, #firebrick, #forestgreen, #gold, #goldenrod, #green, #grey, #indianred, #khaki, #lavender, #lawngreen, #lightblue, #lightcoral, #lightgreen, #lightred, #lightseagreen, #lightskyblue, #lightslategray, #lightslategrey, #lime, #limegreen, #mediumaquamarine, #mediumblue, #mediumpurple, #mediumseagreen, #mediumslateblue, #mediumspringgreen, #mediumturquoise, #mediumvioletred, #mintcream, #moccasin, #oldlace, #olive, #olivedrab, #orange, #orangered, #orchid, #palegoldenrod, #palegreen, #paleturquoise, #palevioletred, #peru, #plum, #powderblue, #red, #rosybrown, #royalblue, #saddlebrown, #salmon, #sandybrown, #seagreen, #sienna, #silver, #skyblue, #slateblue, #slategray, #springgreen, #steelblue, #tan, #teal, #thistle, #tomato, #turquoise, #violet, #whitesmoke, #yellow, #yellowgreen

Methods included from Colours

#bold_blue, #bold_red, #bold_yellow, cadetblue, #cadetblue, #chartreuse, #coral, coral, #cornflowerblue, cornflowerblue, crimson, #cyan, cyan, darkgoldenrod, #darkgoldenrod, #darkgray, darkgreen, darkolivegreen, darkseagreen, #darkslateblue, darkslateblue, #darkslategray, darkslategray, #darkturquoise, darkturquoise, #deepskyblue, deepskyblue, default_colour, #dimgray, disable_colours, #dodgerblue, e, #efancy, enable_colours, #erev, #ewarn, #forestgreen, forestgreen, gold, #goldenrod, goldenrod, #grey, grey, indianred, #indianred, khaki, #khaki, lawngreen, #lawngreen, lightblue, lightgreen, lightsalmon, #lightseagreen, lightseagreen, lightskyblue, #lightskyblue, #lightslategray, lightslategray, #lightsteelblue, lime, #lime, limegreen, #limegreen, #mediumaquamarine, mediumaquamarine, #mediumorchid, #mediumpurple, mediumpurple, #mediumseagreen, mediumseagreen, #mediumslateblue, mediumslateblue, #mediumspringgreen, mediumspringgreen, #mediumturquoise, mediumturquoise, #oldlace, olive, #olive, olivedrab, #olivedrab, orange, orangered, #orchid, orchid, palegreen, #palegreen, paleturquoise, #paleturquoise, palevioletred, #papayawhip, peru, #peru, plum, #plum, #powderblue, powderblue, rev, #rev?, royalblue, saddlebrown, #saddlebrown, #sandybrown, sandybrown, sdir, #sdir, seagreen, #seagreen, sfancy, #sfancy, sfile, #sfile, #simp, simp, #skyblue, skyblue, slateblue, #slategray, slategray, springgreen, #springgreen, #steelblue, steelblue, #swarn, swarn, #tan, tan, teal, #teal, #tomato, tomato, turquoise, use_colours?, use_this_colour_for_exam_answers, use_this_colour_for_exam_questions, #yellow, yellowgreen, #yellowgreen

Constructor Details

#initialize(i = ARGV, run_already = true, &block) ⇒ DateSanitizer

#

initialize

#


34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
 
# File 'lib/studium/check_and_sanitize/date_sanitizer.rb', line 34

def initialize(
    i           = ARGV,
    run_already = true,
    &block
  )
  reset
  set_commandline_arguments(i)
  # ======================================================================= #
  # === Handle blocks next
  # ======================================================================= #
  if block_given?
    yielded = yield
    case yielded
    # ===================================================================== #
    # === :do_not_run_yet
    # ===================================================================== #
    when :do_not_run_yet
      run_already = false
    end
  end
  run if run_already
end

Class Method Details

.[](i = ARGV) ⇒ Object

#

Studium::DateSanitizer[]

#


310
311
312
 
# File 'lib/studium/check_and_sanitize/date_sanitizer.rb', line 310

def self.[](i = ARGV)
  new(i)
end

Instance Method Details

#can_this_line_be_parsed?(i) ⇒ Boolean

#

can_this_line_be_parsed?

This method determines whether this class can parse the given input or not.

We need to keep in mind that some faulty input should be allowed here too, such as - “Freitag 15.11.2024”.

#

Returns:

  • (Boolean) 


283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
 
# File 'lib/studium/check_and_sanitize/date_sanitizer.rb', line 283

def can_this_line_be_parsed?(i)
  if (
    i.include?(' ') and
    (i =~ /\d{2}\.\d{2}/) and # 12.04.,  14:00 - 17:00, Ort:  Digital
    (i =~ /\d{2}:\d{2}/)
  )
    return true
  elsif (
    does_this_line_include_a_german_weekday?(i) and
    (i =~ /\d{2}\.\d{2}\.\d{4}/)
  ) # Last one is for instance: 14:00
    return true
  else
    return false
  end
end

#has_a_year_entry?(i) ⇒ Boolean

#

has_a_year_entry?

#

Returns:

  • (Boolean) 


270
271
272
 
# File 'lib/studium/check_and_sanitize/date_sanitizer.rb', line 270

def has_a_year_entry?(i)
  i =~ /\.\d{4}/
end

#left_padding_to_use_for_the_weekdays? ⇒ Boolean Also known as: left_pad?

#

left_padding_to_use_for_the_weekdays?

#

Returns:

  • (Boolean) 


75
76
77
 
# File 'lib/studium/check_and_sanitize/date_sanitizer.rb', line 75

def left_padding_to_use_for_the_weekdays?
  @internal_hash[:left_padding_to_use_for_the_weekdays]
end

#output_this_line_in_a_colourized_manner(i) ⇒ Object

#

output_this_line_in_a_colourized_manner

#


96
97
98
 
# File 'lib/studium/check_and_sanitize/date_sanitizer.rb', line 96

def output_this_line_in_a_colourized_manner(i)
  e tomato(i)
end

#reset ⇒ Object

#

reset (reset tag)

#


60
61
62
63
64
65
66
67
68
69
70
 
# File 'lib/studium/check_and_sanitize/date_sanitizer.rb', line 60

def reset
  super()
  # ======================================================================= #
  # === :result
  # ======================================================================= #
  @internal_hash[:result] = nil
  # ======================================================================= #
  # === :left_padding_to_use_for_the_weekdays
  # ======================================================================= #
  @internal_hash[:left_padding_to_use_for_the_weekdays] = 8
end

#result? ⇒ Boolean Also known as: result

#

result?

#

Returns:

  • (Boolean) 


89
90
91
 
# File 'lib/studium/check_and_sanitize/date_sanitizer.rb', line 89

def result?
  @internal_hash[:result]
end

#run ⇒ Object

#

run (run tag)

#


303
304
305
 
# File 'lib/studium/check_and_sanitize/date_sanitizer.rb', line 303

def run
  sanitize_the_given_input
end

#sanitize_the_given_input(_ = first? ) ⇒ Object

#

sanitize_the_given_input

#


261
262
263
264
265
 
# File 'lib/studium/check_and_sanitize/date_sanitizer.rb', line 261

def sanitize_the_given_input(
    _ = first?
  )
  try_to_sanitize_this_string(_) if _
end

#set_result(i) ⇒ Object

#

set_result

#


82
83
84
 
# File 'lib/studium/check_and_sanitize/date_sanitizer.rb', line 82

def set_result(i)
  @internal_hash[:result] = i
end

#try_to_sanitize_this_string(_) ⇒ Object Also known as: sanitize, sanitize_input, parse, reparse, reformat

#

try_to_sanitize_this_string (main tag)

#


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
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
 
# File 'lib/studium/check_and_sanitize/date_sanitizer.rb', line 103

def try_to_sanitize_this_string(_)
  set_result(nil) # Always initialize it here.
  if _ and _.is_a?(Array)
    _ = _.join("\n")
  end
  if _ and !_.empty?
    _ = _.dup if _.frozen?
    # ===================================================================== #
    # Next, replace all tabs with ' '.
    # ===================================================================== #
    _.tr!("\t",' ')
    _.rstrip!
    # ===================================================================== #
    # Condense ' - ' tokens.
    # ===================================================================== #
    if _.include?(' - ') and (_ =~ /\d{2} - \d{2}/) # e. g. 14:00 - 17:00
      _.sub!(/(\d{2}) - (\d{2})/, '\\1-\\2') # Reduce it a little bit.
    end
    if _.include? ' N '
      _.sub!(/ N /,'') # This is primarily due to the format used by the University of Vienna.
    end
    unless _.include? 'Ort:'
      # =================================================================== #
      # We must add "Ort:" next. We will "anchor" this towards e. g.
      # 15:00-16:30
      # =================================================================== #
      _.sub!(
        TIME_RANGE_FROM_TO,
        '\\1, Ort:'
      )
    end
    _.squeeze!(' ') # Get rid of double ' '.
    _.gsub!(/Abhaltungfix/, '') if _.include?('Abhaltungfix')
    if _.include? '(' # We don't need any '(' and ')' in the given input.
      _.delete!('()')
    end
    _.tr!(T ,' ')
    if _.include?(' UZA2') and !_.include?(' Ort: ')
      _.gsub!(/ UZA2/, ' # Ort: UZA2')
    end
    if _.include? 'Abhaltung fix'
      _.gsub!(/Abhaltung fix/,'"')
    end
    if _.include? 'Abhaltung'
      _.gsub!(/Abhaltung/,'')
    end
    if _.include? ' fix'
      _.gsub!(/ fix/,'')
    end
    # ======================================================================= #
    # Next we begin to fix entries such as:
    #
    #   - "Di. 09:00-13:00, Ort: 16.04.2024 GM 8/9 - Hörsaal des Internationalen Wiener Motorensymposiums Biomaterials lecture"
    #
    # This is especially prevalent at lectures offered by the TU Vienna.
    # ======================================================================= #
    if _.include?('Mo. ')
      _.sub!(/Mo\. /,'Montag ')
    end
    if _.include?('Di. ')
      _.sub!(/Di\. /,'Dienstag ')
    end
    if _.include?('Mi. ')
      _.sub!(/Mi\. /,'Mittwoch ')
    end
    if _.include?('Do. ')
      _.sub!(/Do\. /,'Donnerstag ')
    end
    if _.include?('Fr. ')
      _.sub!(/Fr\. /,'Freitag ')
    end
    # ======================================================================= #
    # Next, check weekday-names:
    # ======================================================================= #
    if _ =~ /Montag \d{1}/
      _.gsub!(/Montag (\d{1})/,   'Montag        \1')
    end
    if _ =~ /Dienstag \d{1}/
      _.gsub!(/Dienstag (\d{1})/, 'Dienstag      \1')
    end
    if _ =~ /Mittwoch \d{1}/
      _.gsub!(/Mittwoch (\d{1})/, 'Mittwoch      \1')
    end
    if _ =~ /Donnerstag \d{1}/
      _.gsub!(/Donnerstag (\d{1})/, 'Donnerstag      \1')
    end
    if _ =~ /Freitag \d{1}/
      _.gsub!(/Freitag (\d{1})/, 'Freitag      \1')
    end
    # ===================================================================== #
    # Expand weekend-names next:
    # ===================================================================== #
    _.gsub!(/^Mo\n/, ' - "Montag        ')
    _.gsub!(/^Di\n/, ' - "Dienstag      ')
    _.gsub!(/^Mi\n/, ' - "Mittwoch      ')
    _.gsub!(/^Do\n/, ' - "Donnerstag    ')
    _.gsub!(/^Fr\n/, ' - "Freitag       ')
    _.gsub!(/^Mo/, ' - "Montag        ')
    _.gsub!(/^Di/, ' - "Dienstag      ')
    _.gsub!(/^Mi/, ' - "Mittwoch      ')
    _.gsub!(/^Do/, ' - "Donnerstag    ')
    _.gsub!(/^Fr/, ' - "Freitag       ')
    unless has_a_year_entry?(_) # For instance: - "Mittwoch 12.06. 08:00-09:30, Ort: UZA2 Hörsaal 8 (Raum 2Z206) 2.OG"
      _.sub!(
       /(\d{2}\.\d{2}\.) /,
       '\\1'+current_year?.to_s+', '
      )
    end
    # ===================================================================== #
    # The next line ensures that the year-entry is followed by a ',' entry.
    # ===================================================================== #
    if _ =~ /\d{2}\.\d{2}\.\d{4} \d{2}:\d{2}-\d{2}:\d{2}/ # 25.06.2024 13:15-14:45
      _.sub!(
        /(\d{2}\.\d{2}\.\d{4})( \d{2}:\d{2}-\d{2}:\d{2})/,
        '\\1,\\2'
      )
    end
    if _.include?('- " ')
      _.sub!(
        /- " /,
        '- "'
      )
    end
    unless _ =~ /\d{2}:\d{2}-\d{2}:\d{2}/ # If we do not have an entry such as "16:45-18:15".
      _.chop! if _.end_with?('"')
      _ << ', 01:11-23:23"' # Evidently this should be improved.
    end
    unless _.include?('Ort: ')
      _.chop! if _.end_with?('"')
      _ << ', Ort: unknown location as of yet."'
    end
    unless _.end_with? '"'
      _ << '"' unless _.include?('" #') # Unless it contains a trailing comment.
    end
  end
  if does_this_string_include_a_german_weekday?(_)
    # left_padding_to_use_for_the_weekdays?
    german_weekdays?.each {|this_german_weekday|
      if _.include?(this_german_weekday)
        _.sub!(
          /(#{this_german_weekday}\s+)/, # See: https://rubular.com/r/L23Pmvlxs3bGJG
          this_german_weekday.ljust(12,' ')+
          ' '*left_pad?
        )
      end
    }
  end
  set_result("#{_}\n")
  return _ # And return it as well.
end