studium 0.16.9

data/lib/studium/curricula/attribute_lecture_to_curriculum/attribute_boku_lecture_to_curriculum.rb

@@ -0,0 +1,384 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === Studium::AttributeBokuLectureToCurriculum
+#
+# This class is a subclass of AttributeLectureToCurriculum.
+#
+# For now, pass in the URL for the particular exam at hand. This currently
+# only works for lectures at the BOKU, since their online webpages are
+# easy to parse. For the university of Vienna, they use some kind of
+# javascrip to display content, which is harder to obtain.
+#
+# Usage example:
+#
+#   Studium::AttributeBokuLectureToCurriculum.new(ARGV)
+#
+# =========================================================================== #
+# require 'studium/utility_scripts/attribute_lecture_to_curriculum/attribute_boku_lecture_to_curriculum.rb'
+# =========================================================================== #
+require 'studium/utility_scripts/attribute_lecture_to_curriculum/attribute_lecture_to_curriculum.rb'
+
+module Studium
+
+class AttributeBokuLectureToCurriculum < AttributeLectureToCurriculum # === AttributeBokuLectureToCurriculum.new
+
+  require 'open-uri'
+
+  # ========================================================================= #
+  # === USE_THIS_REGEX
+  #
+  # See the following link at Rubular:
+  #   http://rubular.com/r/4wM8G28SGA
+  # ========================================================================= #
+  USE_THIS_REGEX =
+    /e\)\);}"><\/span><span>(\d{3}) (.+) <\/span><span>\(?/
+
+  # ========================================================================= #
+  # === REGEX_FOR_OBTAINING_THE_TITLE
+  #
+  # See here: http://rubular.com/r/0NZsnBjENG
+  # ========================================================================= #
+  REGEX_FOR_OBTAINING_THE_TITLE =
+    /<td class=" MaskRenderer  MaskLabel"><label class="Mask ">Titel<\/label><\/td><td colspan="0" class=" MaskRenderer top"><table class=" MaskSpacing">\s*<tr>\s*<td class=" MaskRenderer"><span class="bold ">(.+)<\/span><\/td>/
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      this_url    = ARGV,
+      run_already = true
+    )
+    reset
+    set_url(this_url)
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+    infer_the_namespace
+  end
+
+  # ========================================================================= #
+  # === determine_commandline_arguments
+  # ========================================================================= #
+  def determine_commandline_arguments(i)
+    if i.any? {|entry| entry.start_with?('--') }
+      @commandline = i.select  {|entry| entry.start_with?('--') } # Only add "--" entries to @commandline.
+    end
+  end
+
+  # ========================================================================= #
+  # === url?
+  # ========================================================================= #
+  def url?
+    @url
+  end; alias input? url? # === input?
+
+  # ========================================================================= #
+  # === obtain_dataset_from_the_remote_website
+  # ========================================================================= #
+  def obtain_dataset_from_the_remote_website
+    use_this_url = url?
+    if use_this_url
+      # ===================================================================== #
+      # Make use of open-uri to access the remote website.
+      # ===================================================================== #
+      opnn; e "Obtaining the dataset from this remote "\
+              "website: #{sfancy(use_this_url)}"
+      @dataset = URI.open(use_this_url).read # Keep in mind that open-uri will yield UTF-8 Strings.
+    end
+  end
+
+  # ========================================================================= #
+  # === use_this_regex?
+  # ========================================================================= #
+  def use_this_regex?
+    USE_THIS_REGEX
+  end; alias regex? use_this_regex? # === regex?
+
+  # ========================================================================= #
+  # === determine_title_of_the_lecture
+  # ========================================================================= #
+  def determine_title_of_the_lecture
+    _ = dataset?
+    if _
+      _ =~ REGEX_FOR_OBTAINING_THE_TITLE
+      set_title($1.to_s.dup)
+    end
+  end
+
+  # ========================================================================= #
+  # === apply_regex
+  #
+  # This will also determine @results.
+  # ========================================================================= #
+  def apply_regex
+    if @dataset
+      scanned_dataset = @dataset.scan(regex?)
+      results = scanned_dataset.map {|inner_array|
+        inner_array.map(&:strip)
+      }.uniq
+      set_results(results)
+    end
+  end
+
+  # ========================================================================= #
+  # === report_the_title_in_use
+  # ========================================================================= #
+  def report_the_title_in_use
+    e lightblue(title?)
+  end
+
+  # ========================================================================= #
+  # === menu                                                       (menu tag)
+  #
+  # Note that @commandline will only include "--" instructions.
+  # ========================================================================= #
+  def menu(i = commandline_arguments?)
+    if i.is_a? Array
+      i.each {|entry| menu(entry) }
+    else
+      i = i.to_s.delete('')
+      case i # case tag
+      # ===================================================================== #
+      # === attribute_boku --location?
+      # ===================================================================== #
+      when /file/,
+           /location\??/
+        show_location_of_important_files
+        exit
+      # ===================================================================== #
+      # === attribute_boku batch
+      # ===================================================================== #
+      when /batch/ # batch-process all BOKU lectures.
+        do_batch_process_all_boku_lectures
+      else
+        i = match_curriculum_name_to_curriculum_number(i)
+        if i =~ /^-?-?0+/ # If it starts with a 0.
+          # ================================================================= #
+          # Ok, we now know that it is a number, starting with 0.
+          # ================================================================= #
+          if registered_curricula?.include?(i.delete('-'))
+            show_all_lectures_from_this_curriculum(i.delete('-'))
+          end
+        end
+      end
+    end if i
+  end
+
+  # ========================================================================= #
+  # === show_location_of_important_files
+  # ========================================================================= #
+  def show_location_of_important_files
+    e return_location_of_file_that_keeps_all_lectures_registered
+  end
+
+  # ========================================================================= #
+  # === return_location_of_file_that_keeps_all_lectures_registered
+  # ========================================================================= #
+  def return_location_of_file_that_keeps_all_lectures_registered
+    log_dir?+'lectures_registered_in_a_specific_curriculum.md'
+  end
+
+  # ========================================================================= #
+  # === save_into_a_file                                           (save tag)
+  #
+  # Do not forget that we have to load up the old dataset if it exists,
+  # before saving the file again. However had, we will do so only if
+  # we have not found the same key yet.
+  #
+  # Note that this presently will append into the file no matter what.
+  #
+  # If I should ever update this code, then we also need to add the
+  # ability to NOT append something IF this lecture has already been
+  # registered (and to also store the lecture-id, since some lectures
+  # may have the same name).
+  # ========================================================================= #
+  def save_into_a_file
+    if @do_save_into_a_file and @dataset
+      into = return_location_of_file_that_keeps_all_lectures_registered
+      key = "#{name_of_the_lecture?.dup}:"
+      # ===================================================================== #
+      # Load the file, if it actually exists.
+      # ===================================================================== #
+      if File.exist? into
+        dataset = File.read(into).split("---\n")
+        dataset.select! {|line|
+          line =~ /^[a-zA-Z]+.+:/ # See: http://rubular.com/r/KUrLIIY9iI
+        }
+      end
+      what = ''.dup # This is our to-save String.
+      what << "#{key}#{N}"
+      @results.each {|inner_array| # Note that @results is an Array
+        what << "  #{inner_array.join('|')}#{N}"
+      }
+      what << "#{N}---#{N}" # This is our terminator character.
+      e "Now storing into `#{sfile(into)}`."
+      append_what_into(what, into)
+    end
+  end
+
+  # ========================================================================= #
+  # === display_result                                          (display tag)
+  # ========================================================================= #
+  def display_result
+    report_the_title_in_use
+    e
+    e seagreen('The following curricula are attributed to the lecture '+
+      sfancy(title?))+seagreen(':')
+    e
+    @results.each {|inner_array|
+      number_of_the_curriculum = inner_array.first
+      name_of_the_curriculum   = inner_array.last.ljust(88)
+      e "  #{sfancy(name_of_the_curriculum)} "\
+        "#{orange(number_of_the_curriculum)}"
+    }; e # And a newline.
+  end
+
+  # ========================================================================= #
+  # === do_batch_process_all_boku_lectures
+  #
+  # This method can be used to batch-process all passed lectures at
+  # the BOKU university.
+  #
+  # To invoke this method, do:
+  #   attribute_boku_lecture --batch
+  # ========================================================================= #
+  def do_batch_process_all_boku_lectures(shall_we_exit = true)
+    # ======================================================================= #
+    # First, determine the lectures that are part of BOKU.
+    # ======================================================================= #
+    all_boku_lectures = Studium.sanitized_dataset_from_file_passed_exams_per_month
+    all_boku_lectures.select! {|line|
+      line.include?(' BOKU ') # Select all BOKU lectures here.
+    }
+    all_boku_lectures.each {|line|
+      # line = line.force_encoding(@use_this_encoding) # No longer necessary, I think.
+      splitted = line.split('|').map(&:strip)
+      name_of_the_lecture = splitted.last
+      new_url = BeautifulUrl.new('BOKU '+name_of_the_lecture)
+      new_url = new_url.first if new_url.is_a? Array
+      # ===================================================================== #
+      # We first have to set the url. The new URL will simply be the name
+      # of the lecture in question, with a prepended "BOKU " String.
+      # ===================================================================== #
+      set_url(new_url)
+      # ===================================================================== #
+      # The next line is some early error-control. Every new_url variable
+      # must include "https" - if not then it is wrong and we will exit
+      # early, with a message.
+      # ===================================================================== #
+      unless new_url.include? 'https'
+        opnn
+        e 'The URL ('+sfancy(new_url)+') for the lecture '+
+           sfancy(name_of_the_lecture)+' may possibly be wrong.'
+        opnn
+        e 'Thus, '+swarn('we will exit now.')
+        exit
+      end
+      # ===================================================================== #
+      # Then we can perform the main powerhorse of this class.
+      # ===================================================================== #
+      perform_the_main_task_of_this_class
+    }
+    exit if shall_we_exit
+  end
+
+  # ========================================================================= #
+  # === show_all_lectures_from_this_curriculum
+  #
+  # Invoce this method like so:
+  #   attribute_boku --033217
+  #   attribute_boku --033255
+  # ========================================================================= #
+  def show_all_lectures_from_this_curriculum(
+      curriculum_id_as_number
+    )
+    curriculum_id_as_number = curriculum_id_as_number.to_s
+    use_this_encoding = encoding?
+    name_of_the_curriculum = assigned_exams?[curriculum_id_as_number]
+    if name_of_the_curriculum.include? '#'
+      name_of_the_curriculum = name_of_the_curriculum[0..(name_of_the_curriculum.index('#')-1)].strip
+    end
+    dataset = curricula_assigned_exams?
+    selection = dataset.select {|key, array_values|
+      key if array_values.include? curriculum_id_as_number
+    }
+    n_passed_exams = selection.size.to_s 
+    e
+    e darkslateblue('Curriculum: ')+
+      sfancy(name_of_the_curriculum)+
+      darkslateblue(' (CurriculumID: ')+
+      lightblue(curriculum_id_as_number.to_s)+
+      darkslateblue(')')
+    e
+    e crimson('The passed ')+simp(n_passed_exams)+crimson(' exams are:')
+    e
+    hash_statistics = {} # This Hash will keep some statistical information.
+    index_counter = 0
+    n_total_ects_points = 0
+    selection.each_pair {|name_of_the_lecture, array_values|
+      index_counter += 1
+      name_of_the_lecture = name_of_the_lecture.dup if name_of_the_lecture.frozen?
+      name_of_the_lecture = name_of_the_lecture.force_encoding(use_this_encoding)
+      _remote_url = BeautifulUrl.new(name_of_the_lecture).first
+      lv_id_number = ::Studium.return_lv_id_number(name_of_the_lecture).to_s
+      index = sienna((index_counter.to_s+')').rjust(5)) # Colourize the index here.
+      n_ects_points = ::Studium.return_ects_from_this_lva_number(
+        lv_id_number, name_of_the_lecture
+      ).to_f
+      n_total_ects_points += n_ects_points # Always keep that.
+      date_when_this_exam_was_passed = Studium.when_was_this_lecture_passed?(name_of_the_lecture)
+      year = date_when_this_exam_was_passed.split('.').last.to_i
+      hash_statistics[year] = { n_ects_points: 0 } unless hash_statistics.has_key? year # Initialize it here.
+      hash_statistics[year][:n_ects_points] += n_ects_points
+      # ===================================================================== #
+      # Output our result next. This is fairly big.
+      # ===================================================================== #
+      e '  '+index+' '+
+        slateblue(name_of_the_lecture.ljust(60))+' '+
+        '('+palegoldenrod('LV-ID:')+' '+lv_id_number.to_s+
+        '; '+palegoldenrod('n ECTS:')+' '+
+        n_ects_points.to_s.rjust(4)+
+        '; '+palegoldenrod('Passed at:')+
+        ' '+date_when_this_exam_was_passed.to_s+
+        ') '
+        # +simp(_remote_url) # We presently will not show the remote URL. 
+    }
+    e
+    e 'In total, '+simp(n_total_ects_points.to_s)+' ECTS points were '\
+      'passed in the curriculum '+sfancy(name_of_the_curriculum)+'.'
+    e
+    unless hash_statistics.empty?
+      e 'The statistics are as follows:'
+      e
+      hash_statistics.each_pair {|year, hash_n_ects_points_passed_in_that_year|
+        n_ects_points_passed_in_that_year = hash_n_ects_points_passed_in_that_year[:n_ects_points]
+        e '  In the year '+sfancy(year.to_s)+' '+
+          orange(n_ects_points_passed_in_that_year.to_s.rjust(4))+
+          ' ECTS points were passed.'
+      }; e # And a pretty, trailing newline.
+    end
+  end
+
+  # ========================================================================= #
+  # === Studium::AttributeBokuLectureToCurriculum[]
+  # ========================================================================= #
+  def self.[](i = '')
+    new(i)
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  Studium::AttributeBokuLectureToCurriculum.new(ARGV)
+  # ========================================================================= #
+  # Alternative, invoke this class like this:
+  #   attribute_boku_lecture --batch
+  # ========================================================================= #
+end # attributebokulecturetocurriculum https://online.boku.ac.at/BOKUonline/wblv.wbShowLvDetail?pStpSpNr=279457

data/lib/studium/curricula/attribute_lecture_to_curriculum/attribute_lecture_to_curriculum.rb

@@ -0,0 +1,238 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === Studium::AttributeLectureToCurriculum
+#
+# This class will correlate a curriculum-number to a particular
+# curriculum, such as 033217 being the Bachelor LBT curriculum. 
+#
+# Usage example:
+#
+#   Studium::AttributeLectureToCurriculum.new(ARGV)
+#
+# =========================================================================== #
+# require 'studium/utility_scripts/attribute_lecture_to_curriculum/attribute_lecture_to_curriculum.rb'
+# =========================================================================== #
+require 'studium/base/base.rb'
+
+module Studium
+
+class AttributeLectureToCurriculum < ::Studium::Base # === Studium::AttributeLectureToCurriculum
+
+  require 'studium/toplevel_methods/when_was_this_lecture_passed.rb'
+
+  # ========================================================================= #
+  # === HASH_KEEP_TRACK_OF_ONLY_THESE_CURRICULA
+  #
+  # This Hash keeps track of the curricula in use.
+  # ========================================================================= #
+  HASH_KEEP_TRACK_OF_ONLY_THESE_CURRICULA = {
+    '033217' => 'Bachelorcurriculum Lebensmittel- und Biotechnologie              # BOKU Wien',
+    '033255' => 'Bachelorcurriculum Agrarwissenschaften                           # BOKU Wien',
+    '033290' => 'Bachelorcurriculum Technische Chemie                             # TU   Wien',
+    '033305' => 'Bachelorcurriculum Pharmazie                                     # Uni  Wien',
+    '033521' => 'Bachelorcurriculum Informatik                                    # Uni  Wien',
+    '033630' => 'Bachelorcurriculum Biologie                                      # Uni  Wien',
+    '033638' => 'Bachelorcurriculum Ernährungswissenschaften                      # Uni  Wien',
+    '033662' => 'Bachelorcurriculum Chemie                                        # Uni  Wien',
+    # ======================================================================= #
+    # Ab hier Master-Curricula die wir tracken möchten.
+    # ======================================================================= #
+    '066418' => 'Mastercurriculum Biotechnology                                   # BOKU Wien',
+    '066455' => 'Mastercurriculum Nutzpflanzenwissenschaften                      # BOKU Wien',
+    '066490' => 'Mastercurriculum Technische Chemie                               # TU   Wien',
+    '066605' => 'Mastercurriculum Pharmazie                                       # Uni  Wien',
+    '066830' => 'Mastercurriculum Molekulare Mikrobiologie, Mikrobielle Ökologie und Immunbiologie # Uni Wien',
+    '066832' => 'Mastercurriculum Botanik                                         # Uni  Wien',
+    '066834' => 'Mastercurriculum Molekulare Biologie                             # Uni  Wien',
+    '066838' => 'Mastercurriculum Ernährungswissenschaften                        # Uni  Wien',
+    '066862' => 'Mastercurriculum Chemie                                          # Uni  Wien',
+    '066863' => 'Mastercurriculum Biologische Chemie                              # Uni  Wien',
+    '066875' => 'Mastercurriculum Bioinformatik                                   # Uni  Wien',
+    '066877' => 'Mastercurriculum Genetik und Entwicklungsbiologie                # Uni  Wien',
+    '066910' => 'Mastercurriculum Computational Science                           # Uni  Wien',
+    '066921' => 'Mastercurriculum Informatik                                      # Uni  Wien'
+  }
+
+  # =========================================================================== #
+  # === reset
+  # =========================================================================== #
+  def reset
+    super()
+    # === @result
+    @result = nil
+    @dataset = nil # Default value.
+    @commandline = nil
+    @title = nil # Default.
+    @do_save_into_a_file = true # If this variable is true then we will store into a yaml file.
+    @use_this_encoding = main_encoding?
+  end
+
+  # =========================================================================== #
+  # === match_curriculum_name_to_curriculum_number
+  #
+  # This method will accept a given input name, and return the curriculum
+  # number, if it is registered in the above hash.
+  #
+  # This method should work quite ok, for both bachelor and master
+  # curricula.
+  #
+  # Invocation examples:
+  #
+  #   attribute --bachelor-biologie
+  #   attribute --master-biotech
+  #
+  # =========================================================================== #
+  def match_curriculum_name_to_curriculum_number(
+      search_for_this_curriculum_name
+    )
+    search_for_this_curriculum_name.delete!(' ') # We will not need these.
+    hash = HASH_KEEP_TRACK_OF_ONLY_THESE_CURRICULA
+    possible_matches = []
+    result = search_for_this_curriculum_name
+
+    hash.each_pair {|curriculum_number, curriculum_name|
+      splitted = search_for_this_curriculum_name.split('-')
+      last = splitted.last
+      curriculum_name = curriculum_name.downcase.delete(' ')
+      if curriculum_name.include? last
+        possible_matches << curriculum_number
+      end
+    }
+    # ======================================================================= #
+    # Next, everything has been stored in the variable possible_matches.
+    # ======================================================================= #
+    unless possible_matches.empty?
+      if    search_for_this_curriculum_name.include? 'bachelor'
+        possible_matches.select! {|entry|
+          entry.include? '033'
+        }
+      elsif search_for_this_curriculum_name.include? 'master'
+        possible_matches.select! {|entry|
+          entry.include? '066'
+        }
+      end
+      result = possible_matches.first # This here should be for bachelor
+    end
+    return result
+  end
+
+  # ========================================================================= #
+  # === set_url
+  # ========================================================================= #
+  def set_url(i = '')
+    if i.is_a? Array
+      determine_commandline_arguments(i)
+      i = i.first 
+    end
+    i = i.to_s.dup
+    i = nil if i.include? '--'
+    @url = i
+  end
+
+  # ========================================================================= #
+  # === curricula_assigned_exams?
+  #
+  # This will always return the dataset of the curricula-assigned exams
+  # that were passed already.
+  # ========================================================================= #
+  def curricula_assigned_exams?
+    new_hash = {}
+    dataset = YAML.load_file('/home/x/studium/YAML/curricula_assigned_exams.yml')
+    # ======================================================================= #
+    # Ensure that the values are all Strings.
+    # ======================================================================= #
+    dataset.each_pair {|key, array_value|
+      if array_value
+        array_value = array_value.map(&:to_s)
+        new_hash[key] = array_value
+      end
+    }
+    return new_hash
+  end
+
+  # ========================================================================= #
+  # === set_title
+  # ========================================================================= #
+  def set_title(i)
+    i = i.force_encoding(@use_this_encoding) # Ensure that we use the main Encoding.
+    # ======================================================================= #
+    # Ensure that the title is a valid ISO Encoding rather than an
+    # invalid UTF-8 encoding.
+    # ======================================================================= #
+    # i.gsub!(/ü/,'ü')    if i.include? "ü"    # Sanitize "ü" tokens.
+    # i.gsub!(/Ã\x9C/,'Ü') if i.include? "Ã\x9C" # Sanitize "Ü" tokens.
+    # i.gsub!(/\xDC/,'Ü')  if i.include? "\xDC" # Sanitize "Ü" tokens.
+    # i.gsub!(/ä/,'ä')    if i.include? "ä"    # Sanitize "ä" tokens.
+    # i.gsub!(/Ã\x96/,'Ö') if i.include? "Ã\x96" # Sanitize "Ö" tokens.
+    # i.gsub!(/ö/,'ö')    if i.include? "ö"    # Sanitize "ö" tokens.
+    @title = i
+  end
+
+  # ========================================================================= #
+  # === registered_curricula?
+  # ========================================================================= #
+  def registered_curricula?
+    HASH_KEEP_TRACK_OF_ONLY_THESE_CURRICULA.keys
+  end
+
+  # ========================================================================= #
+  # === assigned_exams?
+  # ========================================================================= #
+  def assigned_exams?
+    HASH_KEEP_TRACK_OF_ONLY_THESE_CURRICULA
+  end
+
+  # ========================================================================= #
+  # === title?
+  # ========================================================================= #
+  def title?
+    @title
+  end; alias name_of_the_lecture? title? # === name_of_the_lecture?
+
+  # ========================================================================= #
+  # === dataset?
+  # ========================================================================= #
+  def dataset?
+    @dataset
+  end
+
+  # ========================================================================= #
+  # === set_results
+  # ========================================================================= #
+  def set_results(i)
+    if i.is_a? Array # Sanitize the Encoding.
+      i.map! {|inner_array|
+        inner_array.map {|inner_inner_array| # <- Awful name but hey, better a long name than a short one.
+          inner_inner_array = inner_inner_array.dup.force_encoding(@use_this_encoding)
+        }
+      }
+    end unless i.empty? # Ignore empty Arrays.
+    @results = i
+  end
+
+  # ========================================================================= #
+  # === perform_the_main_task_of_this_class
+  # ========================================================================= #
+  def perform_the_main_task_of_this_class
+    obtain_dataset_from_the_remote_website
+    apply_regex
+    determine_title_of_the_lecture
+    save_into_a_file # Save it into the yaml file.
+    display_result if @result
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    menu
+    perform_the_main_task_of_this_class
+  end
+
+end; end
+
+if __FILE__ == $PROGRAM_NAME
+  Studium::AttributeLectureToCurriculum.new #('033217') # <- This is just for testing purposes.
+end