2019-02-21 18:29:44 +00:00
|
|
|
|
[Regular expressions time extraction]
|
|
|
|
|
|
session_start_time = (?:Die Sitzung wird [umrn]+ (?:(?:(\d{1,2}) Uhr (?:(\d{1,2})?)|(?:(\d{1,2})\.(?:(\d{1,2})) Uhr)) ?(?:Minuten?)?.?)? ?(?:durch\n*[\w \.;'\(\)]*)?[\s \. A-z]*(?:(?:eröffnet\.)|(?:eingeleitet[\w „\",\.]+)))|(?:Begi[\w]+:? (\d{1,2})(?:[, \.]*)?(?:(\d{1,2}))? ?Uhr\.?)|(?:Die Sitzung wird [umrn]+ (\d{1,2}) Uhr eröffnet.)
|
|
|
|
|
|
session_end_time = (?:\(Schlu(?:(?:ss)|ß)(?: .?der .?Sitzung)?(?:[;:]*)[\w\n,\. ]*\s(?:(?:(\d{1,2})\sUhr\s(\d{1,2}).?\sMinuten?)|(?:(\d{1,2})[\., ]+(\d{1,2})\sUhr)|(?:(\d{1,2})[\., ]+(\d{1,2})\sUhr\))|(?:(\d{1,2})\sUhr))[\., ]*\))|(?:\(Schlu(?:(?:ss)|ß)(?: .?der .?Sitzung)?(?:[;: ]*)\s?(?:(?:(\d{1,2})\sUhr (\d{1,2})\sMinuten?)|(?:(\d{1,2})[\., ]+(\d{1,2})\sUhr)|(?:(\d{1,2})[\., ]+(\d{1,2})\sUhr\))|(?:(\d{1,2})\sUhr))[\., ]*\))|(?:\(Schlu(?:(?:ss)|ß)(?: .?der .?Sitzung)?(?:[;:]*)[\w\n,\. ]*\s(?:(?:(\d{1,2})\sUhr und\s.?(\d{1,2}).?\sMinuten?\.\))))|(?:\(Schlu(?:(?:ss)|ß):? (\d{1,2}) Uhr (\d{1,2})\.\))
|
|
|
|
|
|
|
|
|
|
|
|
[Regular expressions splits]
|
|
|
|
|
|
session_start_president_split = (\n\w*(?:P|p)räsident\w* [ÜÖÄA-züöäß \-\.,]+ ?:)
|
|
|
|
|
|
attachment_split = ((?:\(Schlu(?:(?:ss)|ß)(?: .?der .?Sitzung)?(?:[;:]*)[\w\n,\. ]*\s(?:(?:(?:\d{1,2})\sUhr\s(?:\d{1,2}).?\sMinuten?)|(?:(?:\d{1,2})[\., ]+(?:\d{1,2})\sUhr)|(?:(?:\d{1,2})[\., ]+(?:\d{1,2})\sUhr\))|(?:(?:\d{1,2})\sUhr))[\., ]*\))|(?:\(Schlu(?:(?:ss)|ß)(?: .?der .?Sitzung)?(?:[;: ]*)\s?(?:(?:(?:\d{1,2})\sUhr (?:\d{1,2})\sMinuten?)|(?:(?:\d{1,2})[\., ]+(?:\d{1,2})\sUhr)|(?:(?:\d{1,2})[\., ]+(?:\d{1,2})\sUhr\))|(?:(?:\d{1,2})\sUhr))[\., ]*\))|(?:\(Schlu(?:(?:ss)|ß)(?: .?der .?Sitzung)?(?:[;:]*)[\w\n,\. ]*\s(?:(?:(?:\d{1,2})\sUhr und\s.?(?:\d{1,2}).?\sMinuten?\.\))))|(?:\(Schlu(?:(?:ss)|ß):? (?:\d{1,2}) Uhr (?:\d{1,2})\.\)))
|
|
|
|
|
|
|
|
|
|
|
|
[Regular expressions speakers]
|
|
|
|
|
|
speaker_president_first = ^\w*(?:P|p)räsident\w* [ÜÖÄA-züöäß \-\.,]+ ?: ; first ; Präsident
|
|
|
|
|
|
speaker_state_secretary = ^[ \-\.,\w]+ Staatssekretär[\-\w\n, \n]+: ; middle ; Staatssekretär
|
|
|
|
|
|
speaker_minister_of_state = ^[ \-\.,\w]+ Staatsminister[\-\w\n, \n]+: ; middle ; Staatsminister
|
|
|
|
|
|
speaker_applicant = [ \-\.,\w]+ (\([\w ]+\))?, (?:A|a)ntragsteller(?:in)?[\-\w\n, \n]*: ; middle ; Antragsteller
|
|
|
|
|
|
speaker_president = ^\w*(?:P|p)räsident\w* [ÜÖÄA-züöäß \-\.,]+ ?: ; middle ; Präsident
|
|
|
|
|
|
speaker_undefined = ^[ \-\.,\w]+ ?(\([\w ]+\))? ?\([\w\/ \d\-\.]+\) ?: ; middle ; MdB
|
|
|
|
|
|
speaker_defined = ^[\w \-\.,]+ ?Bundesminister(in)? [\w\-\., ]* ?: ; middle ; Bundesminister
|
|
|
|
|
|
speaker_chancellor = ^[\w \-\.\,]+Bundeskanzler(in)? ?: ; middle ; Bundeskanzler
|
|
|
|
|
|
speaker_secretary = ^[\w \-\.,]+ ?Schriftführer(in)? ?: ; middle ; Schriftführer
|
|
|
|
|
|
speaker_rapporteur = ^[ \-\.,\w]+ ?(\([\w ]+\))? ?\([\w\/ \d\-]+\) ?, (?:B|b)erichterstatter: ; middle ; Berichterstatter
|
|
|
|
|
|
end_of_session = (?:\(Schlu(?:(?:ss)|ß)(?: .?der .?Sitzung)?(?:[;:]*)[\w\n,\. ]*\s(?:(?:(?:\d{1,2})\sUhr\s(?:\d{1,2}).?\sMinuten?)|(?:(?:\d{1,2})[\., ]+(?:\d{1,2})\sUhr)|(?:(?:\d{1,2})[\., ]+(?:\d{1,2})\sUhr\))|(?:(?:\d{1,2})\sUhr))[\., ]*\))|(?:\(Schlu(?:(?:ss)|ß)(?: .?der .?Sitzung)?(?:[;: ]*)\s?(?:(?:(?:\d{1,2})\sUhr (?:\d{1,2})\sMinuten?)|(?:(?:\d{1,2})[\., ]+(?:\d{1,2})\sUhr)|(?:(?:\d{1,2})[\., ]+(?:\d{1,2})\sUhr\))|(?:(?:\d{1,2})\sUhr))[\., ]*\))|(?:\(Schlu(?:(?:ss)|ß)(?: .?der .?Sitzung)?(?:[;:]*)[\w\n,\. ]*\s(?:(?:(?:\d{1,2})\sUhr und\s.?(?:\d{1,2}).?\sMinuten?\.\))))|(?:\(Schlu(?:(?:ss)|ß):? (?:\d{1,2}) Uhr (?:\d{1,2})\.\)) ; last ; Zeitpunkt
|
|
|
|
|
|
|
|
|
|
|
|
[Additional name features]
|
|
|
|
|
|
academic_titles = Dr. Dr. h. c. ; Dr. h. c.
|
|
|
|
|
|
parties = DIE LINKE ; CDU/CSU ; PDS/Linke Liste ; Fraktionslos ; F.D.P.
|
|
|
|
|
|
|
|
|
|
|
|
[Regular expressions speeches]
|
|
|
|
|
|
comments = \B\([^\(\)]*\)\B ; kommentar
|
|
|
|
|
|
date_string = [\d\t ]*Deutscher Bundestag (?:–|—|-|--) \d{1,2} ?\. Wahlperiode (?:–|—|-|--) \d{1,3} ?\. Sitzung ?\. (?:Bonn|Berlin), (?:Montag|Dienstag|Mittwoch|Donnerstag|Freitag|Samstag|Sonntag), den \d{1,2} ?\. (?:Januar|Februar|März|April|Mai|Juni|Juli|September|Oktober|November|Dezmber) \d{4}[\d\t ]*|[\d\t ]*Deutscher Bundestag (?:–|—|-|--) \d{1,3}\. Sitzung ?\. (?:Bonn|Berlin), (?:Montag|Dienstag|Mittwoch|Donnerstag|Freitag|Samstag|Sonntag), den \d{1,2} ?\. (?:Januar|Februar|März|April|Mai|Juni|Juli|September|Oktober|November|Dezmber) \d{4}[\d\t ]* ; metadata
|
|
|
|
|
|
|
|
|
|
|
|
[Multiline entities]
|
|
|
|
|
|
multiline_comment = \B\([^\(\)]* ; [^\(\)]*\)\B ; kommentar
|
|
|
|
|
|
|
|
|
|
|
|
[File paths]
|
2019-03-03 17:41:12 +00:00
|
|
|
|
output_folder = /home/stephan/Downloads/output
|
|
|
|
|
|
input_folder_xmls = /home/stephan/Downloads/development_data_xml
|
|
|
|
|
|
new_metadata = /home/stephan/Downloads/output/new_metadata
|
|
|
|
|
|
new_simple_markup = /home/stephan/Downloads/output/simple_xml
|
|
|
|
|
|
complex_markup = /home/stephan/Downloads/output/complex_markup
|
|
|
|
|
|
clear_speech_markup = /home/stephan/Downloads/output/clear_speech_markup
|
|
|
|
|
|
tmp_path = /home/stephan/Downloads/nlp_output/lemmatized/tmp
|
|
|
|
|
|
beautiful_xml = /home/stephan/Downloads/output/beautiful_xml
|
|
|
|
|
|
nlp_output = /home/stephan/Downloads/nlp_output
|
|
|
|
|
|
nlp_input = /home/stephan/Downloads/nlp_output/nlp_beuatiful_xml/
|
|
|
|
|
|
nlp_lemmatized_tokenized = /home/stephan/Downloads/nlp_output/lemmatized
|
|
|
|
|
|
nlp_beuatiful_xml = /home/stephan/Downloads/nlp_output/nlp_beuatiful_xml
|
2019-02-21 18:29:44 +00:00
|
|
|
|
|
