-
-
Save lbusett/da7b1fba4345e03192a450226a17636e to your computer and use it in GitHub Desktop.
| #' @title bibtex_2academic | |
| #' @description import publications from a bibtex file to a hugo-academic website | |
| #' @author Lorenzo Busetto, phD (2017) <[email protected]> | |
| bibtex_2academic <- function(bibfile, | |
| outfold, | |
| abstract = FALSE, | |
| overwrite = FALSE) { | |
| require(RefManageR) | |
| require(dplyr) | |
| require(stringr) | |
| require(anytime) | |
| # Import the bibtex file and convert to data.frame | |
| mypubs <- ReadBib(bibfile, check = "warn", .Encoding = "UTF-8") %>% | |
| as.data.frame() | |
| # assign "categories" to the different types of publications | |
| mypubs <- mypubs %>% | |
| dplyr::mutate( | |
| pubtype = dplyr::case_when(document_type == "Article" ~ "2", | |
| document_type == "Article in Press" ~ "2", | |
| document_type == "InProceedings" ~ "1", | |
| document_type == "Proceedings" ~ "1", | |
| document_type == "Conference" ~ "1", | |
| document_type == "Conference Paper" ~ "1", | |
| document_type == "MastersThesis" ~ "3", | |
| document_type == "PhdThesis" ~ "3", | |
| document_type == "Manual" ~ "4", | |
| document_type == "TechReport" ~ "4", | |
| document_type == "Book" ~ "5", | |
| document_type == "InCollection" ~ "6", | |
| document_type == "InBook" ~ "6", | |
| document_type == "Misc" ~ "0", | |
| TRUE ~ "0")) | |
| # create a function which populates the md template based on the info | |
| # about a publication | |
| create_md <- function(x) { | |
| # define a date and create filename by appending date and start of title | |
| if (!is.na(x[["year"]])) { | |
| x[["date"]] <- paste0(x[["year"]], "-01-01") | |
| } else { | |
| x[["date"]] <- "2999-01-01" | |
| } | |
| filename <- paste(x[["date"]], x[["title"]] %>% | |
| str_replace_all(fixed(" "), "_") %>% | |
| str_remove_all(fixed(":")) %>% | |
| str_sub(1, 20) %>% | |
| paste0(".md"), sep = "_") | |
| # start writing | |
| if (!file.exists(file.path(outfold, filename)) | overwrite) { | |
| fileConn <- file.path(outfold, filename) | |
| write("+++", fileConn) | |
| # Title and date | |
| write(paste0("title = \"", x[["title"]], "\""), fileConn, append = T) | |
| write(paste0("date = \"", anydate(x[["date"]]), "\""), fileConn, append = T) | |
| # Authors. Comma separated list, e.g. `["Bob Smith", "David Jones"]`. | |
| auth_hugo <- str_replace_all(x["author"], " and ", "\", \"") | |
| auth_hugo <- stringi::stri_trans_general(auth_hugo, "latin-ascii") | |
| write(paste0("authors = [\"", auth_hugo,"\"]"), fileConn, append = T) | |
| # Publication type. Legend: | |
| # 0 = Uncategorized, 1 = Conference paper, 2 = Journal article | |
| # 3 = Manuscript, 4 = Report, 5 = Book, 6 = Book section | |
| write(paste0("publication_types = [\"", x[["pubtype"]],"\"]"), | |
| fileConn, append = T) | |
| # Publication details: journal, volume, issue, page numbers and doi link | |
| publication <- x[["journal"]] | |
| if (!is.na(x[["volume"]])) publication <- paste0(publication, | |
| ", (", x[["volume"]], ")") | |
| if (!is.na(x[["number"]])) publication <- paste0(publication, | |
| ", ", x[["number"]]) | |
| if (!is.na(x[["pages"]])) publication <- paste0(publication, | |
| ", _pp. ", x[["pages"]], "_") | |
| if (!is.na(x[["doi"]])) publication <- paste0(publication, | |
| ", ", paste0("https://doi.org/", | |
| x[["doi"]])) | |
| write(paste0("publication = \"", publication,"\""), fileConn, append = T) | |
| write(paste0("publication_short = \"", publication,"\""),fileConn, append = T) | |
| # Abstract and optional shortened version. | |
| if (abstract) { | |
| write(paste0("abstract = \"", x[["abstract"]],"\""), fileConn, append = T) | |
| } else { | |
| write("abstract = \"\"", fileConn, append = T) | |
| } | |
| write(paste0("abstract_short = \"","\""), fileConn, append = T) | |
| # other possible fields are kept empty. They can be customized later by | |
| # editing the created md | |
| write("image_preview = \"\"", fileConn, append = T) | |
| write("selected = false", fileConn, append = T) | |
| write("projects = []", fileConn, append = T) | |
| write("tags = []", fileConn, append = T) | |
| #links | |
| write("url_pdf = \"\"", fileConn, append = T) | |
| write("url_preprint = \"\"", fileConn, append = T) | |
| write("url_code = \"\"", fileConn, append = T) | |
| write("url_dataset = \"\"", fileConn, append = T) | |
| write("url_project = \"\"", fileConn, append = T) | |
| write("url_slides = \"\"", fileConn, append = T) | |
| write("url_video = \"\"", fileConn, append = T) | |
| write("url_poster = \"\"", fileConn, append = T) | |
| write("url_source = \"\"", fileConn, append = T) | |
| #other stuff | |
| write("math = true", fileConn, append = T) | |
| write("highlight = true", fileConn, append = T) | |
| # Featured image | |
| write("[header]", fileConn, append = T) | |
| write("image = \"\"", fileConn, append = T) | |
| write("caption = \"\"", fileConn, append = T) | |
| write("+++", fileConn, append = T) | |
| } | |
| } | |
| # apply the "create_md" function over the publications list to generate | |
| # the different "md" files. | |
| apply(mypubs, FUN = function(x) create_md(x), MARGIN = 1) | |
| } |
Thank you for this script!
I had the same problem on Max OS X as @dcava. RefmanageR produces a column "bibtype". Changing "document_type" to "bibtype" worked BUT only with type "journal". It seems to me that you have focussed only on this publication type with the line publication <- x[["journal"]]. I looked at your website and understand that it worked for you, as you just transferred journal articles.
I'm getting an error Error: 'case_when' is not an exported object from 'namespace:dplyr'
What am I missing?
I'm getting an error
Error: 'case_when' is not an exported object from 'namespace:dplyr'What am I missing?
To answer this for others finding this gist - RStudio on the Mac was including an outdated version of dplyr. Using install.packages("dplyr",type="source") solved the problem.
Hi Lorenzo, thanks for the great script!
I have made some minor modifications to make the script work for me:
- Make it work regardless whether the document type is called bibtype or document_type.
- Added some opportunistic string cleaning code (mostly removing {} and escapes)
- Make it add publictions in a dedicated folder instead of a file
- Export a cite.bib file into each folder to make the entries directly citeable on the website.
I have posted my modified version here:
https://pppichler.github.io/pepesblog/post/set-this-up/setting-up-this-site/
paul
I had the same issue with needing to change document_type to bibtype (which is what it was called in my bib file I used with JabRef). I had an additional issue that overwrite was not set in the inner function. I set it to create_md <- function(x, overwrite=T).
This should probably be changed on Lorenzo's blog post as that is most likely to be seen by people.
@pppichler Your version is down.
sorry @bshor, I moved my site. in case that's still useful, the file is now here.
http://www.pik-potsdam.de/~pichler/blog/post/set-this-up/setting-up-this-site/
That's really helpful, thanks!
sorry @bshor, I moved my site. in case that's still useful, the file is now here.
http://www.pik-potsdam.de/~pichler/blog/post/set-this-up/setting-up-this-site/
@pppichler, my url_pdf always renders as NA. Would you mind posting your bibtex file so i can see what I'm doing wrong?
thanks!
@pppichler, my url_pdf always renders as NA. Would you mind posting your bibtex file so i can see what I'm doing wrong?
thanks!
hi, does it only render as NA or is the "url_pdf" property empty in the generated index.md file empty? The url_pdf is taken from the "url" property in the bib file. I have just noticed that things can go wrong with better bibtex exports so you might want to try standard bibtex export if you are using zotero or another reference manager. my entries look like this, for example:
@Article{lenzenEnvironmentalFootprintHealth2020,
title = {The environmental footprint of health care: a global assessment},
issn = {2542-5196},
url = {https://www.thelancet.com/journals/lanplh/article/PIIS2542-5196(20)30121-2/abstract},
doi = {10.1016/S2542-5196(20)30121-2},
language = {English},
urldate = {2020-08-06},
journal = {The Lancet Planetary Health},
author = {Manfred Lenzen and Arunima Malik and Mengyu Li and Jacob Fry and Helga Weisz and Peter-Paul Pichler and Leonardo Suveges Moreira Chaves and Anthony Capon and David Pencheon},
year = {2020},
volume = {4},
number = {7},
month = {jul},
pages = {e271--e279},
pmid = {32681898},
shorttitle = {The environmental footprint of health care},
pubtype = {2},
date = {2020-01-01},
}
hope this helps
paul
Hi thanks for this.
On my Mac, running against a google scholar bibtex export, ReadBib produces a column called "bibtype" not "document_type".
Not sure if that's universal, but had to change the var name in the mutate section to get it working.