Skip to content

Commit

Permalink
Normalize publishers
Browse files Browse the repository at this point in the history
  • Loading branch information
herreio committed Dec 6, 2024
1 parent b75ba40 commit 61bcd30
Show file tree
Hide file tree
Showing 7 changed files with 1,261 additions and 1,195 deletions.
1,146 changes: 573 additions & 573 deletions data/doaj_changelog_withdrawn_list_enriched_ascii.csv

Large diffs are not rendered by default.

1,146 changes: 573 additions & 573 deletions data/doaj_changelog_withdrawn_list_enriched_utf8.csv

Large diffs are not rendered by default.

Binary file modified data/doaj_changelog_withdrawn_list_enriched_utf8.xlsx
Binary file not shown.
36 changes: 12 additions & 24 deletions data/doaj_changelog_withdrawn_publisher.json
Original file line number Diff line number Diff line change
Expand Up @@ -213,10 +213,9 @@
"Brazilian Society for Computational and Applied Mathematics",
"Brazilian Society of Physical Activity and Sport",
"Briefland",
"Briefland|Medknow Publications",
"Briefland|Wolters Kluwer",
"Bright Publisher",
"Brighthall",
"Brill",
"Brno University of Technology",
"BRNSS Publication Hub",
"Brock University Library",
Expand Down Expand Up @@ -340,8 +339,7 @@
"Czestochowa University of Technology",
"Dalhousie Journal of Interdisciplinary Management",
"Dartmouth College Library Press",
"De Gruyter Poland Sp. z o.o.",
"De Gruyter Poland Sp. z o.o.|Walter de Gruyter GmbH",
"De Gruyter Brill",
"Defence Scientific Information and Documentation Centre",
"Definitive International Institute of Life Science (DIILI Publication)",
"Department of Arabic Studies and Islamic Civilization",
Expand Down Expand Up @@ -369,7 +367,6 @@
"Dokuz Eylul University Graduate School of Socal Sciences",
"DoNotEdit",
"Dorma Trading Est",
"Dove Medical Press",
"Dr. D. Scientific Consulting",
"Dr. Soetomo University",
"Duzce Universitesi Bilim ve Teknoloji Dergisi",
Expand Down Expand Up @@ -428,7 +425,7 @@
"Elmer Press, Inc.",
"ELS Publishing Co. Limited",
"Elsevier",
"Elsevier|SAGE Publications",
"Elsevier|SAGE",
"Elsevier|SciELO",
"Elsevier|The Korean Society of Nephrology",
"EManuscript Services",
Expand Down Expand Up @@ -556,7 +553,7 @@
"Fraunhofer-Institut fur Materialfluss und Logistik",
"Free International University of Moldova",
"Friends Science Publishers",
"Frontiers Media SA",
"Frontiers",
"FSBEI HE Voronezh State University of Engineering Technologies",
"FSBSI Agricultural Research Center Donskoy",
"FSFEI HE Don State Technical University",
Expand Down Expand Up @@ -629,9 +626,6 @@
"Herald Scholarly Open Access",
"Higher Education and Oriental Studies",
"Hikari, Ltd.",
"Hindawi (International Scholarly Research Network)",
"Hindawi Limited",
"Hindawi Publishing Corporation (Sage-Hindawi Access to Research)",
"Hipatia Press",
"Historia Ambiental Latinoamericana y Caribena - HALAC",
"Historia Oral",
Expand Down Expand Up @@ -691,8 +685,6 @@
"Industrial and Organizational Psychology Association",
"Influential Scholarly Research Publication",
"INFOCOMP Journal of Computer Science",
"Informa UK (Taylor & Francis)",
"Informa UK (Taylor & Francis)|University of Technology, Sydney",
"Informatics Publishing Limited",
"Information Bulletin on Variable Stars (IBVS)",
"Information Engineering Research Institute",
Expand Down Expand Up @@ -1035,7 +1027,7 @@
"Maulana Malik Ibrahim State Islamic University",
"Maxwell Scientific Publication Corp.",
"McGill University Library and Archives",
"MDPI AG",
"MDPI",
"Meandros Medical and Dental Journal",
"Mebas Medikal Basin Yayin",
"MECS Publisher",
Expand All @@ -1047,7 +1039,6 @@
"Mediprint",
"Mediterranean BioMedical Journals",
"Mediterranean Journal of Chemistry",
"Medknow Publications",
"Medpharm Publications",
"Medsci Publications",
"Mehmet Akif Ersoy Universitesi Veteriner Fakultesi Dergisi",
Expand Down Expand Up @@ -1150,7 +1141,6 @@
"Ormancilik Arastirma Dergisi",
"OsloMet - Oslo Metropolitan University",
"OU Scientific Route",
"Ovid Technologies (Wolters Kluwer) - Lippincott Williams & Wilkins",
"Oxford University Press",
"Ozcan Gungor",
"P4M STIE Putra Bangsa",
Expand Down Expand Up @@ -1349,7 +1339,7 @@
"Sachsische Landesbibliothek, Staats- und Universitatsbibliothek Dresden",
"Sada Institute",
"SAE Publications",
"SAGE Publications",
"SAGE",
"Saint Petersburg State University",
"Sakarya Universitesi Ilahiyat Fakultesi Dergisi",
"Sakarya University Journal of Education",
Expand Down Expand Up @@ -1469,10 +1459,8 @@
"Southwest University Neofit Rilski",
"SOYLEM Filoloji Dergisi",
"Species Survival Commission",
"Springer (Biomed Central Ltd.)",
"Springer (Biomed Central Ltd.)|Wiley (John Wiley & Sons)",
"Springer Fachmedien Wiesbaden GmbH",
"Springer-Verlag",
"Springer Nature",
"Springer Nature|Wiley",
"SPVS - Sociedade Portuguesa de Vida Selvagem",
"SQS-lehti",
"SRI Institute of Political and Mediametric Studies IPMS",
Expand Down Expand Up @@ -1514,6 +1502,8 @@
"TathQeef Scientific Publishing",
"Tavukculuk Arastirma Dergisi",
"Tawasul International Centre for Publishing, Research and Dialogue",
"Taylor & Francis",
"Taylor & Francis|University of Technology, Sydney",
"Te Pukenga",
"Tech Science Press",
"Technium Science",
Expand Down Expand Up @@ -1928,7 +1918,6 @@
"Ural State University of Architecture and Art",
"Urban Planning Institute of the Republic of Slovenia",
"Valley International",
"Vandenhoeck & Ruprecht GmbH & Co, KG - V&R Unipress",
"Vanderbilt University Library",
"Vasile Alecsandri University of Bacau",
"Verlag Holzhausen GmbH",
Expand All @@ -1947,16 +1936,15 @@
"Vytautas Magnus University",
"Vytautas Magnus University Agriculture Academy",
"Vytautas Magnus University Education Academy",
"Walter de Gruyter GmbH",
"Warsaw University of Life Sciences – SGGW Press",
"West Indian Medical Journal",
"West Pomeranian University of Technology, Szczecin",
"Westerdijk Fungal Biodiversity Institute",
"White Globe Publications",
"Wichtig Publishing, SRL",
"Wiley (Blackwell Publishing)|Wiley (The Physiological Society)",
"Wiley (John Wiley & Sons)",
"Wiley",
"Winchester University Press",
"Wolters Kluwer",
"World Scholars",
"World Scientific",
"Wroclaw Medical University",
Expand Down
36 changes: 12 additions & 24 deletions data/doaj_changelog_withdrawn_publisher.txt
Original file line number Diff line number Diff line change
Expand Up @@ -212,10 +212,9 @@ Brazilian Journal of Natural Science
Brazilian Society for Computational and Applied Mathematics
Brazilian Society of Physical Activity and Sport
Briefland
Briefland|Medknow Publications
Briefland|Wolters Kluwer
Bright Publisher
Brighthall
Brill
Brno University of Technology
BRNSS Publication Hub
Brock University Library
Expand Down Expand Up @@ -339,8 +338,7 @@ Czech University of Life Sciences Prague
Czestochowa University of Technology
Dalhousie Journal of Interdisciplinary Management
Dartmouth College Library Press
De Gruyter Poland Sp. z o.o.
De Gruyter Poland Sp. z o.o.|Walter de Gruyter GmbH
De Gruyter Brill
Defence Scientific Information and Documentation Centre
Definitive International Institute of Life Science (DIILI Publication)
Department of Arabic Studies and Islamic Civilization
Expand Down Expand Up @@ -368,7 +366,6 @@ Dnipro State Medical University
Dokuz Eylul University Graduate School of Socal Sciences
DoNotEdit
Dorma Trading Est
Dove Medical Press
Dr. D. Scientific Consulting
Dr. Soetomo University
Duzce Universitesi Bilim ve Teknoloji Dergisi
Expand Down Expand Up @@ -427,7 +424,7 @@ Eleyon Publishers
Elmer Press, Inc.
ELS Publishing Co. Limited
Elsevier
Elsevier|SAGE Publications
Elsevier|SAGE
Elsevier|SciELO
Elsevier|The Korean Society of Nephrology
EManuscript Services
Expand Down Expand Up @@ -555,7 +552,7 @@ Foundation Pro Scientia Publica
Fraunhofer-Institut fur Materialfluss und Logistik
Free International University of Moldova
Friends Science Publishers
Frontiers Media SA
Frontiers
FSBEI HE Voronezh State University of Engineering Technologies
FSBSI Agricultural Research Center Donskoy
FSFEI HE Don State Technical University
Expand Down Expand Up @@ -628,9 +625,6 @@ Healthcare Bulletin
Herald Scholarly Open Access
Higher Education and Oriental Studies
Hikari, Ltd.
Hindawi (International Scholarly Research Network)
Hindawi Limited
Hindawi Publishing Corporation (Sage-Hindawi Access to Research)
Hipatia Press
Historia Ambiental Latinoamericana y Caribena - HALAC
Historia Oral
Expand Down Expand Up @@ -690,8 +684,6 @@ Indonesian Society Fisheries Product Processing
Industrial and Organizational Psychology Association
Influential Scholarly Research Publication
INFOCOMP Journal of Computer Science
Informa UK (Taylor & Francis)
Informa UK (Taylor & Francis)|University of Technology, Sydney
Informatics Publishing Limited
Information Bulletin on Variable Stars (IBVS)
Information Engineering Research Institute
Expand Down Expand Up @@ -1034,7 +1026,7 @@ Mattioli1885
Maulana Malik Ibrahim State Islamic University
Maxwell Scientific Publication Corp.
McGill University Library and Archives
MDPI AG
MDPI
Meandros Medical and Dental Journal
Mebas Medikal Basin Yayin
MECS Publisher
Expand All @@ -1046,7 +1038,6 @@ Medip Academy
Mediprint
Mediterranean BioMedical Journals
Mediterranean Journal of Chemistry
Medknow Publications
Medpharm Publications
Medsci Publications
Mehmet Akif Ersoy Universitesi Veteriner Fakultesi Dergisi
Expand Down Expand Up @@ -1149,7 +1140,6 @@ Oriental Scientific Publishing Company
Ormancilik Arastirma Dergisi
OsloMet - Oslo Metropolitan University
OU Scientific Route
Ovid Technologies (Wolters Kluwer) - Lippincott Williams & Wilkins
Oxford University Press
Ozcan Gungor
P4M STIE Putra Bangsa
Expand Down Expand Up @@ -1348,7 +1338,7 @@ S. Karger AG
Sachsische Landesbibliothek, Staats- und Universitatsbibliothek Dresden
Sada Institute
SAE Publications
SAGE Publications
SAGE
Saint Petersburg State University
Sakarya Universitesi Ilahiyat Fakultesi Dergisi
Sakarya University Journal of Education
Expand Down Expand Up @@ -1468,10 +1458,8 @@ Southwest Journal of Pulmonary and Critical Care
Southwest University Neofit Rilski
SOYLEM Filoloji Dergisi
Species Survival Commission
Springer (Biomed Central Ltd.)
Springer (Biomed Central Ltd.)|Wiley (John Wiley & Sons)
Springer Fachmedien Wiesbaden GmbH
Springer-Verlag
Springer Nature
Springer Nature|Wiley
SPVS - Sociedade Portuguesa de Vida Selvagem
SQS-lehti
SRI Institute of Political and Mediametric Studies IPMS
Expand Down Expand Up @@ -1513,6 +1501,8 @@ Taras Shevchenko National University of Kyiv
TathQeef Scientific Publishing
Tavukculuk Arastirma Dergisi
Tawasul International Centre for Publishing, Research and Dialogue
Taylor & Francis
Taylor & Francis|University of Technology, Sydney
Te Pukenga
Tech Science Press
Technium Science
Expand Down Expand Up @@ -1927,7 +1917,6 @@ Ural State Mining University
Ural State University of Architecture and Art
Urban Planning Institute of the Republic of Slovenia
Valley International
Vandenhoeck & Ruprecht GmbH & Co, KG - V&R Unipress
Vanderbilt University Library
Vasile Alecsandri University of Bacau
Verlag Holzhausen GmbH
Expand All @@ -1946,16 +1935,15 @@ VU E-Publishing
Vytautas Magnus University
Vytautas Magnus University Agriculture Academy
Vytautas Magnus University Education Academy
Walter de Gruyter GmbH
Warsaw University of Life Sciences – SGGW Press
West Indian Medical Journal
West Pomeranian University of Technology, Szczecin
Westerdijk Fungal Biodiversity Institute
White Globe Publications
Wichtig Publishing, SRL
Wiley (Blackwell Publishing)|Wiley (The Physiological Society)
Wiley (John Wiley & Sons)
Wiley
Winchester University Press
Wolters Kluwer
World Scholars
World Scientific
Wroclaw Medical University
Expand Down
89 changes: 89 additions & 0 deletions src/publishers.R
Original file line number Diff line number Diff line change
@@ -0,0 +1,89 @@
# Mapping by @MiWohlgemuth

de_gruyter_brill <- c(
"De Gruyter",
"Brill",
"Vandenhoeck",
"Sciendo"
)

elsevier <- c(
"Elsevier",
"KeAi Comm"
)

frontiers <- c(
"Frontiers Media"
)

informa <- c(
"Taylor & Francis",
"Dove Medical"
)

mdpi <- c(
"MDPI"
)

oxford <- c(
"Oxford University"
)

sage <- c(
"SAGE "
)

springer_nature <- c(
"Springer",
"Biomed Central"
)

wolters_kluwer <- c(
"Medknow Publ",
"Wolters Kluwer"
)

wiley <- c(
"Wiley",
"Hindawi"
)

publishers <- list(
"de_gruyter_brill" = paste0(de_gruyter_brill, collapse = "|"),
"elsevier" = paste0(elsevier, collapse = "|"),
"frontiers" = paste0(frontiers, collapse = "|"),
"informa" = paste0(informa, collapse = "|"),
"mdpi" = paste0(mdpi, collapse = "|"),
"oxford" = paste0(oxford, collapse = "|"),
"sage" = paste0(sage, collapse = "|"),
"springer_nature" = paste0(springer_nature, collapse = "|"),
"wolters_kluwer" = paste0(wolters_kluwer, collapse = "|"),
"wiley" = paste0(wiley, collapse = "|")
)

publishers_out <- list(
"de_gruyter_brill" = "De Gruyter Brill",
"elsevier" = "Elsevier",
"frontiers" = "Frontiers",
"informa" = "Taylor & Francis",
"mdpi" = "MDPI",
"oxford" = "Oxford University Press",
"sage" = "SAGE",
"springer_nature" = "Springer Nature",
"wolters_kluwer" = "Wolters Kluwer",
"wiley" = "Wiley"
)

parse_publisher <- function(publisher) {
result <- paste0(sort(unique(unlist(lapply(names(publishers), function(x) {
pattern <- publishers[[x]]
if (grepl(pattern, publisher, ignore.case = TRUE)) {
publishers_out[[x]]
}
})))), collapse = "#")
if (grepl("^$", result)) {
publisher
} else {
result
}
}
Loading

0 comments on commit 61bcd30

Please sign in to comment.