import 'proceedings-article' and 'book-chapter'

[Adafede]

I faced recently some failures due to the type of publication imported (mainly proceedings-article and book-chapter), here are some examples:

• 10.1016/B978-0-08-100412-8.00022-X (https://doi.org/10.1016/B978-0-08-100412-8.00022-X): leading to (None, ['unknown type: book-chapter', 'ISSN:[None] not found'], ValueError('can not create WDItemID with None'))
• 10.1109/ICIP.2009.5413556 (https://doi.org/10.1109/ICIP.2009.5413556): leading to (None, ['unknown type: proceedings-article', 'ISSN:[None] not found'], ValueError('can not create WDItemID with None'))

I am not sure what is the best mapping to adopt for book-chapter, but Q23927052 seems reasonable for proceedings-article?

[WolfgangFahl]

As of 2022-01-21 there are 12343 instance of conference papers. At wikidata.bitplan.com you can analyze the availability of properties.
The most common properties are:

The following query covers the properties but unfortunately times out on Wikidata Query Service. https://qlever.cs.uni-freiburg.de/wikidata is down today so i could not test it there.

# truly tabular aggregate query for 
# Q23927052:conference paper
# generated by trulytabular.py version 0.4.7 on 2023-01-21T10:43:31.435852
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX schema: <http://schema.org/>
PREFIX wd: <http://www.wikidata.org/entity/>
PREFIX wdt: <http://www.wikidata.org/prop/direct/>
PREFIX wikibase: <http://wikiba.se/ontology#>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>

SELECT ?conference_paperItem ?conference_paper
  (MAX (?authorItem) AS ?authorItem_max)
  (SAMPLE (?authorItem) AS ?authorItem_sample)
  (GROUP_CONCAT (DISTINCT ?authorItem;SEPARATOR="|") AS ?authorItem_list)
  (COUNT (DISTINCT ?authorItem) AS ?authorItem_count)
  ?author
  (MAX (?page_s_) AS ?page_s__max)
  (SAMPLE (?page_s_) AS ?page_s__sample)
  (GROUP_CONCAT (DISTINCT ?page_s_;SEPARATOR="|") AS ?page_s__list)
  (COUNT (DISTINCT ?page_s_) AS ?page_s__count)
  (MAX (?DOI) AS ?DOI_max)
  (SAMPLE (?DOI) AS ?DOI_sample)
  (GROUP_CONCAT (DISTINCT ?DOI;SEPARATOR="|") AS ?DOI_list)
  (COUNT (DISTINCT ?DOI) AS ?DOI_count)
  (MAX (?language_of_work_or_nameItem) AS ?language_of_work_or_nameItem_max)
  (SAMPLE (?language_of_work_or_nameItem) AS ?language_of_work_or_nameItem_sample)
  (GROUP_CONCAT (DISTINCT ?language_of_work_or_nameItem;SEPARATOR="|") AS ?language_of_work_or_nameItem_list)
  (COUNT (DISTINCT ?language_of_work_or_nameItem) AS ?language_of_work_or_nameItem_count)
  ?language_of_work_or_name
  (MAX (?publication_date) AS ?publication_date_max)
  (SAMPLE (?publication_date) AS ?publication_date_sample)
  (GROUP_CONCAT (DISTINCT ?publication_date;SEPARATOR="|") AS ?publication_date_list)
  (COUNT (DISTINCT ?publication_date) AS ?publication_date_count)
  (MAX (?sponsorItem) AS ?sponsorItem_max)
  (SAMPLE (?sponsorItem) AS ?sponsorItem_sample)
  (GROUP_CONCAT (DISTINCT ?sponsorItem;SEPARATOR="|") AS ?sponsorItem_list)
  (COUNT (DISTINCT ?sponsorItem) AS ?sponsorItem_count)
  ?sponsor
  (MAX (?main_subjectItem) AS ?main_subjectItem_max)
  (SAMPLE (?main_subjectItem) AS ?main_subjectItem_sample)
  (GROUP_CONCAT (DISTINCT ?main_subjectItem;SEPARATOR="|") AS ?main_subjectItem_list)
  (COUNT (DISTINCT ?main_subjectItem) AS ?main_subjectItem_count)
  ?main_subject
  (MAX (?full_work_available_at_URL) AS ?full_work_available_at_URL_max)
  (SAMPLE (?full_work_available_at_URL) AS ?full_work_available_at_URL_sample)
  (GROUP_CONCAT (DISTINCT ?full_work_available_at_URL;SEPARATOR="|") AS ?full_work_available_at_URL_list)
  (COUNT (DISTINCT ?full_work_available_at_URL) AS ?full_work_available_at_URL_count)
  (MAX (?author_name_string) AS ?author_name_string_max)
  (SAMPLE (?author_name_string) AS ?author_name_string_sample)
  (GROUP_CONCAT (DISTINCT ?author_name_string;SEPARATOR="|") AS ?author_name_string_list)
  (COUNT (DISTINCT ?author_name_string) AS ?author_name_string_count)
  (MAX (?published_inItem) AS ?published_inItem_max)
  (SAMPLE (?published_inItem) AS ?published_inItem_sample)
  (GROUP_CONCAT (DISTINCT ?published_inItem;SEPARATOR="|") AS ?published_inItem_list)
  (COUNT (DISTINCT ?published_inItem) AS ?published_inItem_count)
  ?published_in
  (MAX (?NIOSHTIC_2_ID) AS ?NIOSHTIC_2_ID_max)
  (SAMPLE (?NIOSHTIC_2_ID) AS ?NIOSHTIC_2_ID_sample)
  (GROUP_CONCAT (DISTINCT ?NIOSHTIC_2_ID;SEPARATOR="|") AS ?NIOSHTIC_2_ID_list)
  (COUNT (DISTINCT ?NIOSHTIC_2_ID) AS ?NIOSHTIC_2_ID_count)
  (MAX (?on_focus_list_of_Wikimedia_projectItem) AS ?on_focus_list_of_Wikimedia_projectItem_max)
  (SAMPLE (?on_focus_list_of_Wikimedia_projectItem) AS ?on_focus_list_of_Wikimedia_projectItem_sample)
  (GROUP_CONCAT (DISTINCT ?on_focus_list_of_Wikimedia_projectItem;SEPARATOR="|") AS ?on_focus_list_of_Wikimedia_projectItem_list)
  (COUNT (DISTINCT ?on_focus_list_of_Wikimedia_projectItem) AS ?on_focus_list_of_Wikimedia_projectItem_count)
  ?on_focus_list_of_Wikimedia_project
  (MAX (?title) AS ?title_max)
  (SAMPLE (?title) AS ?title_sample)
  (GROUP_CONCAT (DISTINCT ?title;SEPARATOR="|") AS ?title_list)
  (COUNT (DISTINCT ?title) AS ?title_count)
WHERE {
  # instanceof Q23927052:conference paper
  ?conference_paperItem wdt:P31 wd:Q23927052.
  # label
  ?conference_paperItem rdfs:label ?conference_paper.  
  FILTER (LANG(?conference_paper) = "en").
  # author (P50)
  OPTIONAL { 
    ?conference_paperItem wdt:P50 ?authorItem. 
    ?authorItem rdfs:label ?author.
    FILTER (LANG(?author) = "en").
  }
  # page(s) (P304)
  OPTIONAL { 
    ?conference_paperItem wdt:P304 ?page_s_. 
  }
  # DOI (P356)
  OPTIONAL { 
    ?conference_paperItem wdt:P356 ?DOI. 
  }
  # language of work or name (P407)
  OPTIONAL { 
    ?conference_paperItem wdt:P407 ?language_of_work_or_nameItem. 
    ?language_of_work_or_nameItem rdfs:label ?language_of_work_or_name.
    FILTER (LANG(?language_of_work_or_name) = "en").
  }
  # publication date (P577)
  OPTIONAL { 
    ?conference_paperItem wdt:P577 ?publication_date. 
  }
  # sponsor (P859)
  OPTIONAL { 
    ?conference_paperItem wdt:P859 ?sponsorItem. 
    ?sponsorItem rdfs:label ?sponsor.
    FILTER (LANG(?sponsor) = "en").
  }
  # main subject (P921)
  OPTIONAL { 
    ?conference_paperItem wdt:P921 ?main_subjectItem. 
    ?main_subjectItem rdfs:label ?main_subject.
    FILTER (LANG(?main_subject) = "en").
  }
  # full work available at URL (P953)
  OPTIONAL { 
    ?conference_paperItem wdt:P953 ?full_work_available_at_URL. 
  }
  # author name string (P2093)
  OPTIONAL { 
    ?conference_paperItem wdt:P2093 ?author_name_string. 
  }
  # published in (P1433)
  OPTIONAL { 
    ?conference_paperItem wdt:P1433 ?published_inItem. 
    ?published_inItem rdfs:label ?published_in.
    FILTER (LANG(?published_in) = "en").
  }
  # NIOSHTIC-2 ID (P2880)
  OPTIONAL { 
    ?conference_paperItem wdt:P2880 ?NIOSHTIC_2_ID. 
  }
  # on focus list of Wikimedia project (P5008)
  OPTIONAL { 
    ?conference_paperItem wdt:P5008 ?on_focus_list_of_Wikimedia_projectItem. 
    ?on_focus_list_of_Wikimedia_projectItem rdfs:label ?on_focus_list_of_Wikimedia_project.
    FILTER (LANG(?on_focus_list_of_Wikimedia_project) = "en").
  }
  # title (P1476)
  OPTIONAL { 
    ?conference_paperItem wdt:P1476 ?title. 
  }
}
GROUP BY
  ?conference_paperItem 
  ?conference_paper

  ?author
  ?language_of_work_or_name
  ?sponsor
  ?main_subject
  ?published_in
  ?on_focus_list_of_Wikimedia_project