initial commit

.Rbuildignore

@@ -0,0 +1,7 @@
+^.*\.Rproj$
+^\.Rproj\.user$
+^README\.Rmd$
+^README-.*\.png$
+^\.travis\.yml$
+^CONDUCT\.md$
+^README\.md$

.gitignore

@@ -0,0 +1,3 @@
+.Rproj.user
+.Rhistory
+.RData

.travis.yml

@@ -0,0 +1,14 @@
+# Sample .travis.yml for R projects
+
+language: r
+warnings_are_errors: true
+sudo: required
+
+env:
+ global:
+   - CRAN: http://cran.rstudio.com
+
+notifications:
+  email:
+    on_success: change
+    on_failure: change

CONDUCT.md

@@ -0,0 +1,25 @@
+# Contributor Code of Conduct
+
+As contributors and maintainers of this project, we pledge to respect all people who 
+contribute through reporting issues, posting feature requests, updating documentation,
+submitting pull requests or patches, and other activities.
+
+We are committed to making participation in this project a harassment-free experience for
+everyone, regardless of level of experience, gender, gender identity and expression,
+sexual orientation, disability, personal appearance, body size, race, ethnicity, age, or religion.
+
+Examples of unacceptable behavior by participants include the use of sexual language or
+imagery, derogatory comments or personal attacks, trolling, public or private harassment,
+insults, or other unprofessional conduct.
+
+Project maintainers have the right and responsibility to remove, edit, or reject comments,
+commits, code, wiki edits, issues, and other contributions that are not aligned to this 
+Code of Conduct. Project maintainers who do not follow the Code of Conduct may be removed 
+from the project team.
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by 
+opening an issue or contacting one or more of the project maintainers.
+
+This Code of Conduct is adapted from the Contributor Covenant 
+(http:contributor-covenant.org), version 1.0.0, available at 
+http://contributor-covenant.org/version/1/0/0/

DESCRIPTION

@@ -0,0 +1,11 @@
+Package: htmltidy
+Title: Clean up gnarly HTML/XML
+Version: 0.0.0.9000
+Authors@R: c(person("Bob", "Rudis", email = "bob@rudis.net", role = c("aut", "cre")))
+Description: Clean up gnarly HTML/XML
+Depends: R (>= 3.3.0)
+License: AGPL + file LICENSE
+LazyData: true
+Suggests: testthat
+LinkingTo: Rcpp
+Imports: Rcpp

LICENSE

@@ -0,0 +1,2 @@
+YEAR: 2016
+COPYRIGHT HOLDER: Bob Rudis

NAMESPACE

@@ -0,0 +1,5 @@
+# Generated by roxygen2 (4.1.1): do not edit by hand
+
+export(tidy)
+importFrom(Rcpp,sourceCpp)
+useDynLib(htmltidy)

R/RcppExports.R

@@ -0,0 +1,11 @@
+# This file was generated by Rcpp::compileAttributes
+# Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393
+
+#' Tidy HTML/XML
+#'
+#' @param source length 1 character vetor containing the HTML/XML source to process
+#' @export
+tidy <- function(source) {
+    .Call('htmltidy_tidy', PACKAGE = 'htmltidy', source)
+}
+

R/htmltidy-package.r

@@ -0,0 +1,8 @@
+#' Clean up gnarly HTML/XML
+#'
+#' @name htmltidy
+#' @docType package
+#' @author Bob Rudis (@@hrbrmstr)
+#' @useDynLib htmltidy
+#' @importFrom Rcpp sourceCpp
+NULL

README.Rmd

@@ -0,0 +1,48 @@
+---
+output: rmarkdown::github_document
+---
+
+<!-- README.md is generated from README.Rmd. Please edit that file -->
+
+```{r, echo = FALSE}
+knitr::opts_chunk$set(
+  collapse = TRUE,
+  comment = "#>",
+  fig.retina=2,
+  fig.path = "README-"
+)
+```
+
+`htmltidy` — Clean up gnarly HTML/XML
+
+NOTE: Requires [`libtidy`](http://www.html-tidy.org/) and presently is super-basic (no way to set options and pretty much only does HTML)
+
+The following functions are implemented:
+
+- `tidy` : Clean up gnarly HTML/XML
+
+### Installation
+
+```{r eval=FALSE}
+devtools::install_github("hrbrmstr/htmltidy")
+```
+
+```{r echo=FALSE, message=FALSE, warning=FALSE, error=FALSE}
+options(width=120)
+```
+
+### Usage
+
+```{r}
+library(htmltidy)
+
+# current verison
+packageVersion("htmltidy")
+
+cat(tidy("<b><p><a href='http://google.com'>google &gt</a></p></b>"))
+```
+
+### Code of Conduct
+
+Please note that this project is released with a [Contributor Code of Conduct](CONDUCT.md). 
+By participating in this project you agree to abide by its terms.

README.md

@@ -0,0 +1,42 @@
+
+<!-- README.md is generated from README.Rmd. Please edit that file -->
+`htmltidy` — Clean up gnarly HTML/XML
+
+NOTE: Requires [`libtidy`](http://www.html-tidy.org/) and presently is super-basic (no way to set options and pretty much only does HTML)
+
+The following functions are implemented:
+
+-   `tidy` : Clean up gnarly HTML/XML
+
+### Installation
+
+``` r
+devtools::install_github("hrbrmstr/htmltidy")
+```
+
+### Usage
+
+``` r
+library(htmltidy)
+
+# current verison
+packageVersion("htmltidy")
+#> [1] '0.0.0.9000'
+
+cat(tidy("<b><p><a href='http://google.com'>google &gt</a></p></b>"))
+#> <!DOCTYPE html>
+#> <html xmlns="http://www.w3.org/1999/xhtml">
+#> <head>
+#> <meta name="generator" content=
+#> "HTML Tidy for HTML5 for Mac OS X version 5.2.0" />
+#> <title></title>
+#> </head>
+#> <body>
+#> <p><b><a href='http://google.com'>google &gt;</a></b></p>
+#> </body>
+#> </html>
+```
+
+### Code of Conduct
+
+Please note that this project is released with a [Contributor Code of Conduct](CONDUCT.md). By participating in this project you agree to abide by its terms.

htmltidy.Rproj

@@ -0,0 +1,25 @@
+Version: 1.0
+
+RestoreWorkspace: No
+SaveWorkspace: No
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+Encoding: UTF-8
+
+AutoAppendNewline: Yes
+StripTrailingWhitespace: Yes
+
+BuildType: Package
+PackageUseDevtools: Yes
+PackageInstallArgs: --no-multiarch --with-keep.source
+PackageRoxygenize: rd,collate,namespace
+
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX
+
+PackageBuildArgs: --resave-data
+PackageCheckArgs: --as-cran

man/htmltidy.Rd

@@ -0,0 +1,14 @@
+% Generated by roxygen2 (4.1.1): do not edit by hand
+% Please edit documentation in R/htmltidy-package.r
+\docType{package}
+\name{htmltidy}
+\alias{htmltidy}
+\alias{htmltidy-package}
+\title{Clean up gnarly HTML/XML}
+\description{
+Clean up gnarly HTML/XML
+}
+\author{
+Bob Rudis (@hrbrmstr)
+}
+

man/tidy.Rd

@@ -0,0 +1,15 @@
+% Generated by roxygen2 (4.1.1): do not edit by hand
+% Please edit documentation in R/RcppExports.R
+\name{tidy}
+\alias{tidy}
+\title{Tidy HTML/XML}
+\usage{
+tidy(source)
+}
+\arguments{
+\item{source}{length 1 character vetor containing the HTML/XML source to process}
+}
+\description{
+Tidy HTML/XML
+}
+

src/.gitignore

@@ -0,0 +1,3 @@
+*.o
+*.so
+*.dll

src/Makevars

@@ -0,0 +1 @@
+PKG_LIBS=-ltidy

src/RcppExports.cpp

@@ -0,0 +1,18 @@
+// This file was generated by Rcpp::compileAttributes
+// Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393
+
+#include <Rcpp.h>
+
+using namespace Rcpp;
+
+// tidy
+std::string tidy(std::string source);
+RcppExport SEXP htmltidy_tidy(SEXP sourceSEXP) {
+BEGIN_RCPP
+    Rcpp::RObject __result;
+    Rcpp::RNGScope __rngScope;
+    Rcpp::traits::input_parameter< std::string >::type source(sourceSEXP);
+    __result = Rcpp::wrap(tidy(source));
+    return __result;
+END_RCPP
+}

src/htmltidy.cpp

@@ -0,0 +1,41 @@
+#include <Rcpp.h>
+#include <tidy.h>
+#include <tidybuffio.h>
+
+// http://api.html-tidy.org/tidy/tidylib_api_5.2.0/tidyenum_8h.html#a3a1401652599150188a168dade7dc150
+
+//' Tidy HTML/XML
+//'
+//' @param source length 1 character vetor containing the HTML/XML source to process
+//' @export
+//[[Rcpp::export]]
+std::string tidy(std::string source) {
+
+  TidyBuffer output = {0};
+  TidyBuffer errbuf = {0};
+  int rc = -1;
+  Bool ok;
+
+  TidyDoc tdoc = tidyCreate();
+
+  ok = tidyOptSetBool(tdoc, TidyXhtmlOut, yes);
+
+  rc = tidySetErrorBuffer(tdoc, &errbuf);
+
+  rc = tidyParseString(tdoc, source.c_str());
+
+  rc = tidyCleanAndRepair(tdoc);
+
+  rc = tidyRunDiagnostics(tdoc);
+
+  rc = tidySaveBuffer(tdoc, &output);
+
+  std::string ret = std::string(reinterpret_cast<const char*>(output.bp));
+
+  tidyBufFree(&output);
+  tidyBufFree(&errbuf);
+  tidyRelease(tdoc);
+
+  return(ret);
+
+}

tests/testthat.R

@@ -0,0 +1,4 @@
+library(testthat)
+library(htmltidy)
+
+test_check("htmltidy")

tests/testthat/test-htmltidy.R

@@ -0,0 +1,6 @@
+context("basic functionality")
+test_that("we can do something", {
+
+  #expect_that(some_function(), is_a("data.frame"))
+
+})