ryan77627/guix
1
0
Fork 0
mirror of https://git.in.rschanz.org/ryan77627/guix.git synced 2024-11-18 12:47:33 -05:00
Code Issues Projects Releases Packages Wiki Activity Actions

gnu: Add r-textclean.

Browse source 
* gnu/packages/cran.scm (r-textclean): New variable.
This commit is contained in:
Lars-Dominik Braun 2021-03-15 09:40:05 +01:00
parent 584c868fbd
commit 804fad34e8
No known key found for this signature in database
GPG key ID: 421377011A378446
1 changed files with 35 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
gnu/packages/cran.scm
View file

@ -27510,3 +27510,38 @@ (define-public r-english
three, ... Ordinals are also available, first, second, third, ... and
indefinite article choice, \"a\" or \"an\".")
(license license:gpl2)))
(define-public r-textclean
(package
(name "r-textclean")
(version "0.9.3")
(source
(origin
(method url-fetch)
(uri (cran-uri "textclean" version))
(sha256
(base32
"0kgjh6c4f14qkjc4fds7q7rpf4nkma3p0igm54fplmm3p853nvrz"))))
(properties `((upstream-name . "textclean")))
(build-system r-build-system)
(propagated-inputs
`(("r-data-table" ,r-data-table)
("r-english" ,r-english)
("r-glue" ,r-glue)
("r-lexicon" ,r-lexicon)
("r-mgsub" ,r-mgsub)
("r-qdapregex" ,r-qdapregex)
("r-stringi" ,r-stringi)
("r-textshape" ,r-textshape)))
(home-page
"https://github.com/trinker/textclean")
(synopsis "Text Cleaning Tools")
(description
"Tools to clean and process text. Tools are geared at checking for
substrings that are not optimal for analysis and replacing or removing them
(normalizing) with more analysis friendly substrings (see Sproat, Black, Chen,
Kumar, Ostendorf, & Richards (2001) @url{doi:10.1006/csla.2001.0169}) or
extracting them into new variables. For example, emoticons are often used in
text but not always easily handled by analysis algorithms. The
@code{replace_emoticon()} function replaces emoticons with word equivalents.")
(license license:gpl2)))