Add MH things

.Rbuildignore

@@ -12,3 +12,11 @@
 ^pkgdown$
 ^cran-comments\.md$
 ^CRAN-SUBMISSION$
+^CITATION\.cff$
+^install\.R$
+^postBuild$
+^apt\.txt$
+^runtime\.txt$
+^_quarto\.yml$
+^\.quarto$
+^methodshub

.gitignore

@@ -2,3 +2,5 @@
 README.html
 inst/doc
 docs
+
+/.quarto/

CITATION.cff

@@ -0,0 +1,155 @@
+# --------------------------------------------
+# CITATION file created with {cffr} R package
+# See also: https://docs.ropensci.org/cffr/
+# --------------------------------------------
+
+cff-version: 1.2.0
+message: 'To cite package "adaR" in publications use:'
+type: software
+license: MIT
+title: 'adaR: A Fast ''WHATWG'' Compliant URL Parser'
+version: 0.3.2
+abstract: A wrapper for 'ada-url', a 'WHATWG' compliant and fast URL parser written
+  in modern 'C++'. Also contains auxiliary functions such as a public suffix extractor.
+authors:
+- family-names: Schoch
+  given-names: David
+  email: [email protected]
+  orcid: https://orcid.org/0000-0003-2952-4812
+- family-names: Chan
+  given-names: Chung-hong
+  email: [email protected]
+  orcid: https://orcid.org/0000-0002-6232-7530
+repository: https://CRAN.R-project.org/package=adaR
+repository-code: https://github.com/gesistsa/adaR
+url: https://gesistsa.github.io/adaR/
+contact:
+- family-names: Schoch
+  given-names: David
+  email: [email protected]
+  orcid: https://orcid.org/0000-0003-2952-4812
+keywords:
+- r
+- rstats
+- rstats-package
+- url-parser
+references:
+- type: software
+  title: Rcpp
+  abstract: 'Rcpp: Seamless R and C++ Integration'
+  notes: LinkingTo
+  url: https://www.rcpp.org
+  repository: https://CRAN.R-project.org/package=Rcpp
+  authors:
+  - family-names: Eddelbuettel
+    given-names: Dirk
+  - family-names: Francois
+    given-names: Romain
+  - family-names: Allaire
+    given-names: JJ
+  - family-names: Ushey
+    given-names: Kevin
+  - family-names: Kou
+    given-names: Qiang
+  - family-names: Russell
+    given-names: Nathan
+  - family-names: Ucar
+    given-names: Inaki
+  - family-names: Bates
+    given-names: Douglas
+  - family-names: Chambers
+    given-names: John
+  year: '2024'
+- type: software
+  title: triebeard
+  abstract: 'triebeard: ''Radix'' Trees in ''Rcpp'''
+  notes: Imports
+  url: https://github.com/Ironholds/triebeard/
+  repository: https://CRAN.R-project.org/package=triebeard
+  authors:
+  - family-names: Keyes
+    given-names: Os
+  - family-names: Schmidt
+    given-names: Drew
+  - family-names: Takano
+    given-names: Yuuki
+  year: '2024'
+- type: software
+  title: knitr
+  abstract: 'knitr: A General-Purpose Package for Dynamic Report Generation in R'
+  notes: Suggests
+  url: https://yihui.org/knitr/
+  repository: https://CRAN.R-project.org/package=knitr
+  authors:
+  - family-names: Xie
+    given-names: Yihui
+    email: [email protected]
+    orcid: https://orcid.org/0000-0003-0645-5666
+  year: '2024'
+- type: software
+  title: rmarkdown
+  abstract: 'rmarkdown: Dynamic Documents for R'
+  notes: Suggests
+  url: https://pkgs.rstudio.com/rmarkdown/
+  repository: https://CRAN.R-project.org/package=rmarkdown
+  authors:
+  - family-names: Allaire
+    given-names: JJ
+    email: [email protected]
+  - family-names: Xie
+    given-names: Yihui
+    email: [email protected]
+    orcid: https://orcid.org/0000-0003-0645-5666
+  - family-names: Dervieux
+    given-names: Christophe
+    email: [email protected]
+    orcid: https://orcid.org/0000-0003-4474-2498
+  - family-names: McPherson
+    given-names: Jonathan
+    email: [email protected]
+  - family-names: Luraschi
+    given-names: Javier
+  - family-names: Ushey
+    given-names: Kevin
+    email: [email protected]
+  - family-names: Atkins
+    given-names: Aron
+    email: [email protected]
+  - family-names: Wickham
+    given-names: Hadley
+    email: [email protected]
+  - family-names: Cheng
+    given-names: Joe
+    email: [email protected]
+  - family-names: Chang
+    given-names: Winston
+    email: [email protected]
+  - family-names: Iannone
+    given-names: Richard
+    email: [email protected]
+    orcid: https://orcid.org/0000-0003-3925-190X
+  year: '2024'
+- type: software
+  title: testthat
+  abstract: 'testthat: Unit Testing for R'
+  notes: Suggests
+  url: https://testthat.r-lib.org
+  repository: https://CRAN.R-project.org/package=testthat
+  authors:
+  - family-names: Wickham
+    given-names: Hadley
+    email: [email protected]
+  year: '2024'
+  version: '>= 3.0.0'
+- type: software
+  title: 'R: A Language and Environment for Statistical Computing'
+  notes: Depends
+  url: https://www.R-project.org/
+  authors:
+  - name: R Core Team
+  institution:
+    name: R Foundation for Statistical Computing
+    address: Vienna, Austria
+  year: '2024'
+  version: '>= 4.2'
+

_quarto.yml

@@ -0,0 +1,5 @@
+project:
+  title: adaR
+  type: default
+  render:
+    - methodshub.qmd

apt.txt

@@ -0,0 +1 @@
+zip

install.R

@@ -0,0 +1 @@
+install.packages("adaR")

methodshub.md

@@ -0,0 +1,126 @@
+# adaR - A Fast ‘WHATWG’ Compliant URL Parser
+
+
+## Description
+
+<!-- - Provide a brief and clear description of the method, its purpose, and what it aims to achieve. Add a link to a related paper from social science domain and show how your method can be applied to solve that research question.   -->
+
+A wrapper for ‘ada-url’, a ‘WHATWG’ compliant and fast URL parser
+written in modern ‘C++’. Also contains auxiliary functions such as a
+public suffix extractor.
+
+## Keywords
+
+<!-- EDITME -->
+
+- URL Parsing
+- Webtracking Data
+- Webscraping
+
+## Science Usecase(s)
+
+<!-- - Include usecases from social sciences that would make this method applicable in a certain scenario.  -->
+<!-- The use cases or research questions mentioned should arise from the latest social science literature cited in the description. -->
+
+URL parsing is an important process in the analysis of webtracking data,
+e.g. [GESIS Web
+Tracking](https://www.gesis.org/en/services/planning-studies-and-collecting-data/tools-for-the-collection-of-digital-behavioral-data/gesis-web-tracking).
+Although not using this package, the technique has been used in various
+social science publications, e.g. [de León et
+al. (2023)](https://doi.org/10.5117/CCR2023.2.4.DELE).
+
+The package was used in various webscraping projects for communication
+research, e.g. [paperboy](https://github.com/JBGruber/paperboy).
+
+## Repository structure
+
+This repository follows [the standard structure of an R
+package](https://cran.r-project.org/doc/FAQ/R-exts.html#Package-structure).
+
+## Environment Setup
+
+With R installed:
+
+``` r
+install.packages("adaR")
+```
+
+<!-- ## Hardware Requirements (Optional) -->
+<!-- - The hardware requirements may be needed in specific cases when a method is known to require more memory/compute power.  -->
+<!-- - The method need to be executed on a specific architecture (GPUs, Hadoop cluster etc.) -->
+
+## Input Data
+
+<!-- - The input data has to be a Digital Behavioral Data (DBD) Dataset -->
+<!-- - You can provide link to a public DBD dataset. GESIS DBD datasets (https://www.gesis.org/en/institute/digital-behavioral-data) -->
+
+The input data has to be a vector of URLs.
+
+## Sample Input and Output Data
+
+<!-- - Show how the input data looks like through few sample instances -->
+<!-- - Providing a sample output on the sample input to help cross check  -->
+
+The input data looks like this:
+
+``` r
+urls <- c("https://www.google.de/search?q=GESIS&client=ubuntu&hs=ixb&sca_esv=dccc38f8e2930152&sca_upv=1")
+
+urls
+```
+
+    [1] "https://www.google.de/search?q=GESIS&client=ubuntu&hs=ixb&sca_esv=dccc38f8e2930152&sca_upv=1"
+
+The output data is a data frame of parsed URLs.
+
+## How to Use
+
+<!-- - Providing HowTos on the method for different types of usages -->
+<!-- - Describe how the method should be used, including installation, configuration, and any specific instructions for users. -->
+
+Please refer to the [“Introduction to
+adaR”](https://gesistsa.github.io/adaR/articles/adaR.html) for a
+comprehensive introduction of the package.
+
+The main function of this package is `ada_url_parse()` and it decomposes
+a url into its components.
+
+``` r
+library(adaR)
+
+urls <- c("https://www.google.de/search?q=GESIS&client=ubuntu&hs=ixb&sca_esv=dccc38f8e2930152&sca_upv=1",
+          "https://www.nytimes.com/2024/06/19/world/africa/sudan-darfur-takeaways.html",
+          "https://www.sueddeutsche.de/thema/Fu%C3%9Fball-EM")
+
+ada_url_parse(urls)
+```
+
+                                                                                              href
+    1 https://www.google.de/search?q=GESIS&client=ubuntu&hs=ixb&sca_esv=dccc38f8e2930152&sca_upv=1
+    2                  https://www.nytimes.com/2024/06/19/world/africa/sudan-darfur-takeaways.html
+    3                                                 https://www.sueddeutsche.de/thema/Fußball-EM
+      protocol username password                host            hostname port
+    1   https:                         www.google.de       www.google.de     
+    2   https:                       www.nytimes.com     www.nytimes.com     
+    3   https:                   www.sueddeutsche.de www.sueddeutsche.de     
+                                                  pathname
+    1                                              /search
+    2 /2024/06/19/world/africa/sudan-darfur-takeaways.html
+    3                                    /thema/Fußball-EM
+                                                                search hash
+    1 ?q=GESIS&client=ubuntu&hs=ixb&sca_esv=dccc38f8e2930152&sca_upv=1     
+    2                                                                      
+    3                                                                      
+
+## Contact Details
+
+Maintainer: David Schoch <[email protected]>
+
+Issue Tracker: <https://github.com/gesistsa/adaR/issues>
+
+<!-- ## Publication -->
+<!-- - Include information on publications or articles related to the method, if applicable. -->
+<!-- ## Acknowledgements -->
+<!-- - Acknowledgements if any -->
+<!-- ## Disclaimer -->
+<!-- - Add any disclaimers, legal notices, or usage restrictions for the method, if necessary. -->