studium 0.18.7

data/lib/studium/check_and_sanitize/date_sanitizer.rb

@@ -0,0 +1,350 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === Studium::DateSanitizer
+#
+# This class will work on a String. This String should be a single line
+# containing a date such as 25.03.2024.
+#
+# This class is NOT allowed to output anything on its own.
+#
+# Usage example:
+#
+#   Studium::DateSanitizer.new(ARGV)
+#
+# =========================================================================== #
+# require 'studium/check_and_sanitize/date_sanitizer.rb'
+# Studium::DateSanitizer.new(ARGV)
+# =========================================================================== #
+require 'studium/base/base.rb'
+
+module Studium
+
+class DateSanitizer < ::Studium::Base # === Studium::DateSanitizer
+
+  # ========================================================================= #
+  # === TIME_RANGE_FROM_TO
+  # ========================================================================= #
+  TIME_RANGE_FROM_TO = /(\d{2}:\d{2}-\d{2}:\d{2})/
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  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
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  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
+
+  # ========================================================================= #
+  # === left_padding_to_use_for_the_weekdays?
+  # ========================================================================= #
+  def left_padding_to_use_for_the_weekdays?
+    @internal_hash[:left_padding_to_use_for_the_weekdays]
+  end; alias left_pad? left_padding_to_use_for_the_weekdays? # === left_pad?
+
+  # ========================================================================= #
+  # === set_result
+  # ========================================================================= #
+  def set_result(i)
+    @internal_hash[:result] = i
+  end
+
+  # ========================================================================= #
+  # === result?
+  # ========================================================================= #
+  def result?
+    @internal_hash[:result]
+  end; alias result result? # === result
+
+  # ========================================================================= #
+  # === output_this_line_in_a_colourized_manner
+  # ========================================================================= #
+  def output_this_line_in_a_colourized_manner(i)
+    e tomato(i)
+  end
+
+  # ========================================================================= #
+  # === try_to_sanitize_this_string                                (main tag)
+  # ========================================================================= #
+  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; alias sanitize       try_to_sanitize_this_string # === sanitize
+       alias sanitize_input try_to_sanitize_this_string # === sanitize_input
+       alias parse          try_to_sanitize_this_string # === parse
+       alias reparse        try_to_sanitize_this_string # === reparse
+       alias reformat       try_to_sanitize_this_string # === reformat
+
+  # ========================================================================= #
+  # === sanitize_the_given_input
+  # ========================================================================= #
+  def sanitize_the_given_input(
+      _ = first?
+    )
+    try_to_sanitize_this_string(_) if _
+  end
+
+  # ========================================================================= #
+  # === has_a_year_entry?
+  # ========================================================================= #
+  def has_a_year_entry?(i)
+    i =~ /\.\d{4}/
+  end
+
+  # ========================================================================= #
+  # === 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".
+  # ========================================================================= #
+  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
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    sanitize_the_given_input
+  end
+
+  # ========================================================================= #
+  # === Studium::DateSanitizer[]
+  # ========================================================================= #
+  def self.[](i = ARGV)
+    new(i)
+  end
+
+end
+
+# =========================================================================== #
+# === Studium.date_sanitizer
+# =========================================================================== #
+def self.date_sanitizer(i = ARGV)
+  Studium::DateSanitizer.new(i)
+end; self.instance_eval { alias sanitize_this_string_containing_the_lva_dates date_sanitizer } # === Studium.sanitize_this_string_containing_the_lva_dates
+     self.instance_eval { alias date_sanitize                                 date_sanitizer } # === Studium.date_sanitize
+     self.instance_eval { alias parse_lva_dates                               date_sanitizer } # === Studium.parse_lva_dates
+     self.instance_eval { alias parse_this_lva_date                           date_sanitizer } # === Studium.parse_this_lva_date
+     self.instance_eval { alias sanitize_lva_date                             date_sanitizer } # === Studium.sanitize_lva_date
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  alias e puts
+  _ = DATA.read
+  e Colours.rev+'Original input is: '+Colours.steelblue(_)
+  date_sanitizer = Studium::DateSanitizer.new(_)
+  e Colours.rev+'New output is:     '+Colours.steelblue(date_sanitizer.result)
+# - "Donnerstag 19.10.2023, 15:00 - 16:30 UZA2 Hörsaal 5 (Raum 2Z202) 2.OG"
+# - "Mittwoch	12.06.	08:00 - 09:30	UZA2 Hörsaal 8 (Raum 2Z206) 2.OG"
+# - "Donnerstag 19.10.2023, 15:00 - 16:30 UZA2 Hörsaal 5 (Raum 2Z202) 2.OG"
+# Mi	12.06.	08:00 - 09:30	UZA2 Hörsaal 8 (Raum 2Z206) 2.OG"
+# - "Mittwoch	12.06.	08:00 - 09:30	UZA2 Hörsaal 8 (Raum 2Z206) 2.OG"
+# - " N  Dienstag  25.06.2024  13:15 - 14:45  UZA2 Hörsaal 6 (Raum 2Z227) 2.OG"
+# - "Donnerstag  26.09.2024  16:45 - 18:15  UZA2 Hörsaal 8 (Raum 2Z206) 2.OG"
+# - "Freitag  12.04.2024,  14:00 - 17:00, Ort:  Digital"
+# - " N  Dienstag  25.06.2024  13:15 - 14:45  UZA2 Hörsaal 6 (Raum 2Z227) 2.OG"
+# - "Donnerstag  26.09.2024  16:45 - 18:15  UZA2 Hörsaal 8 (Raum 2Z206) 2.OG" 
+# - " N  Dienstag  25.06.2024  13:15 - 14:45  UZA2 Hörsaal 6 (Raum 2Z227) 2.OG"
+# - "Donnerstag  26.09.2024  16:45 - 18:15  UZA2 Hörsaal 8 (Raum 2Z206) 2.OG"
+# - " N  Dienstag  25.06.2024  13:15 - 14:45  UZA2 Hörsaal 6 (Raum 2Z227) 2.OG"
+end # datesan
+__END__
+ - " N  Dienstag  25.06.2024  13:15 - 14:45  UZA2 Hörsaal 6 (Raum 2Z227) 2.OG"

data/lib/studium/check_and_sanitize/find_duplicate_lectures.rb

@@ -0,0 +1,124 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === Studium::FindDuplicateLectures
+#
+# The task of this class is to find duplicate lectures. Note that 
+# outdated lectures may be reported as duplicates erroneously - for
+# now there is no way to change it. At a later time we may have
+# to look into changing that.
+#
+# Usage example:
+#
+#   Studium::FindDuplicateLectures.new(ARGV)
+#
+# =========================================================================== #
+# require 'studium/check_and_sanitize/find_duplicate_lectures.rb'
+# =========================================================================== #
+require 'studium/base/base.rb'
+
+module Studium
+
+class FindDuplicateLectures < Base # === Studium::FindDuplicateLectures
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      run_already = true
+    )
+    reset
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+    infer_the_namespace
+    # ======================================================================= #
+    # === @dataset
+    # ======================================================================= #
+    @dataset = default_readlines(
+      Studium.file_lecture_information
+    )
+    sanitize_main_dataset
+  end
+
+  # ========================================================================= #
+  # === sanitize_main_dataset
+  # ========================================================================= #
+  def sanitize_main_dataset
+    opne 'Sanitizing the dataset next ...'
+    @dataset.select! {|a|
+      a =~ /^".+":\n$/ # We select for certain entries here.
+    }
+  end
+
+  # ========================================================================= #
+  # === verbose_check_for_duplicates
+  # ========================================================================= #
+  def verbose_check_for_duplicates
+    if @dataset.size == @dataset.uniq.size
+      opne 'Everything is fine - there are no duplicates. '+
+            gold(CHEERING_PERSON)
+    else
+      # ===================================================================== #
+      # else we have to find out which variants are duplicates.
+      # ===================================================================== #
+      opne 'Now building up the frequency-hash.'
+      hash_frequencies = {}
+      hash_frequencies.default = 0
+      @dataset.each {|word|
+        hash_frequencies[word] += 1
+      }
+      selection = hash_frequencies.select {|a, b|
+        b > 1
+      }
+      report_these_duplicates(selection)
+    end
+  end
+
+  # ========================================================================= #
+  # === report_these_duplicates
+  # ========================================================================= #
+  def report_these_duplicates(i)
+    if i.empty?
+      opne 'No duplicates were found. '+cheering_person
+    else
+      opne "The following #{slateblue('duplicates')} could be found:"
+      e
+      i.each {|this_duplicate|
+        entry = this_duplicate.first.strip
+        if entry.start_with? '"'
+          entry[0,1] = ''
+        end
+        if entry.end_with? '":'
+          entry[-2,2] = ''
+        end
+        e royalblue("  #{entry}")
+      }; e
+    end
+  end; alias report report_these_duplicates # === report
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    verbose_check_for_duplicates
+  end
+
+  # ========================================================================= #
+  # === Studium::FindDuplicateLectures[]
+  # ========================================================================= #
+  def self.[](i = ARGV)
+    new(i)
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  Studium::FindDuplicateLectures.new(ARGV)
+end # findduplicatelectures

data/lib/studium/check_and_sanitize/missing_priority_entry.rb

@@ -0,0 +1,44 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# This file can tell us which entries in the file lecture_information.yml
+# have a missing :priority tag.
+# =========================================================================== #
+module Studium
+
+  require 'studium/colours/colours.rb'
+  require 'studium/toplevel_methods/toplevel_methods.rb'
+
+  # ========================================================================= #
+  # === Studium.report_missing_priority_entries
+  #
+  # This method will report the missing :priority entries in the file
+  # 'lecture_information.yml'.
+  # ========================================================================= #
+  def self.report_missing_priority_entries
+    dataset = Studium.return_sanitized_dataset_from_the_file_lecture_information
+    is_there_at_the_least_one_entry = false
+    dataset.each {|key, value|
+      priority = value[:priority]
+      if priority
+        # Then all is fine.
+      else
+        e 'No :priority entry for `'+::Studium::Colours.sfancy(key)+'`.'
+        unless is_there_at_the_least_one_entry == true
+          is_there_at_the_least_one_entry = true
+        end
+      end
+    }
+    unless is_there_at_the_least_one_entry
+      e ::Studium::Colours.gold('Good!')+
+        ' Every relevant entry in file lecture_information.yml '\
+        'has a :priority tag.'
+    end
+  end
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  Studium.report_missing_priority_entries
+end # missingpriorityentry