tidy_msg

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: msgxtractr
 Type: Package
 Title: Read Outlook '.msg' Files
-Version: 0.2.1
-Date: 2017-08-23
+Version: 0.3.0
+Date: 2020-05-06
 Authors@R: c(
       person("Bob", "Rudis", email = "[email protected]", role = c("aut", "cre")),
       person("Ariya", "Hidayat", email = "[email protected]", role = c("ctb", "cph"), comment = "POLE library"),
@@ -23,9 +23,10 @@ Suggests:
     testthat,
     covr
 Depends:
-    R (>= 3.2.0)
+    R (>= 3.5.0)
 Imports:
     Rcpp,
-    scales
-RoxygenNote: 6.1.1
+    scales,
+    tibble
+RoxygenNote: 7.1.1
 LinkingTo: Rcpp

NAMESPACE

@@ -1,10 +1,13 @@
 # Generated by roxygen2: do not edit by hand
 
+S3method(as_tibble,msg)
 S3method(print,msg)
 export(decode_rtf)
 export(is_rtf)
 export(read_msg)
 export(save_attachments)
+export(tidy_msg)
 importFrom(Rcpp,sourceCpp)
 importFrom(scales,comma)
+importFrom(tibble,as_tibble)
 useDynLib(msgxtractr, .registration=TRUE)

NEWS.md

@@ -1,3 +1,6 @@
+0.3.0
+* Added `tidy_msg()` to turn a `msg` object into a `tibble`
+
 0.2.1
 * Fixed issue #2
 

R/as-tibble.R

@@ -0,0 +1,22 @@
+#' Turn a single `msg` object into a `tibble`
+#'
+#' @param x a `msg` object
+#' @param ... passed on to [tibble::as_tibble()]
+#' @export
+tidy_msg <- function(x, ...) {
+
+  x <- unclass(x)
+
+  x <- x[lengths(x) > 0]
+
+  for (idx in which(sapply(x, mode) == "list")) {
+    x[[idx]] <- list(x[[idx]])
+  }
+
+  tibble::as_tibble(x, ...)
+
+}
+
+#' @rdname tidy_msg
+#' @export
+as_tibble.msg <- tidy_msg

R/msgxtractr-package.R

@@ -8,6 +8,7 @@
 #' @docType package
 #' @author Bob Rudis (bob@@rud.is)
 #' @importFrom scales comma
+#' @importFrom tibble as_tibble
 #' @useDynLib msgxtractr, .registration=TRUE
 #' @importFrom Rcpp sourceCpp
 NULL

README.Rmd

@@ -13,6 +13,7 @@ The following functions are implemented:
 
 - `read_msg`:	Read in an Outlook '.msg' file
 - `save_attachments`:	Save all attachments from a 'msg' object
+- `tidy_msg`:	Turn a 'msg' object into a 'tibble'
 
 ### Installation
 
@@ -29,7 +30,7 @@ options(width=120)
 ```{r message=FALSE, warning=FALSE, error=FALSE}
 library(msgxtractr)
 
-# current verison
+# current version
 packageVersion("msgxtractr")
 
 str(msg1 <- read_msg(system.file("extdata/unicode.msg", package="msgxtractr")))
@@ -41,17 +42,11 @@ str(msg2 <- read_msg(system.file("extdata/TestMessage-ansi.msg", package="msgxtr
 str(msg3 <- read_msg(system.file("extdata/TestMessage-default.msg", package="msgxtractr")))
 
 str(msg4 <- read_msg(system.file("extdata/TestMessage-unicode.msg", package="msgxtractr")))
-```
-
-### Test Results
-
-```{r message=FALSE, warning=FALSE, error=FALSE}
-library(msgxtractr)
-library(testthat)
-
-date()
 
-test_dir("tests/")
+str(tidy_msg(msg1), 2)
+str(tidy_msg(msg2), 2)
+str(tidy_msg(msg3), 2)
+str(tidy_msg(msg4), 2)
 ```
 
 ### Code of Conduct

README.md

@@ -1,14 +1,21 @@
 
-[![Build Status](https://travis-ci.org/hrbrmstr/msgxtractr.svg?branch=master)](https://travis-ci.org/hrbrmstr/msgxtractr) [![AppVeyor Build Status](https://ci.appveyor.com/api/projects/status/github/hrbrmstr/msgxtractr?branch=master&svg=true)](https://ci.appveyor.com/project/hrbrmstr/msgxtractr) [![codecov](https://codecov.io/gh/hrbrmstr/msgxtractr/branch/master/graph/badge.svg)](https://codecov.io/gh/hrbrmstr/msgxtractr)
+[![Build
+Status](https://travis-ci.org/hrbrmstr/msgxtractr.svg?branch=master)](https://travis-ci.org/hrbrmstr/msgxtractr)
+[![AppVeyor Build
+Status](https://ci.appveyor.com/api/projects/status/github/hrbrmstr/msgxtractr?branch=master&svg=true)](https://ci.appveyor.com/project/hrbrmstr/msgxtractr)
+[![codecov](https://codecov.io/gh/hrbrmstr/msgxtractr/branch/master/graph/badge.svg)](https://codecov.io/gh/hrbrmstr/msgxtractr)
 
-`msgxtractr` : Read Outlook '.msg' Files
+`msgxtractr` : Read Outlook ‘.msg’ Files
 
-'Microsoft' 'Outlook' messages can be saved in '.msg' files. Tools are provided that enable extraction of metadata, envelope, headers, body and attachments from these files.
+‘Microsoft’ ‘Outlook’ messages can be saved in ‘.msg’ files. Tools are
+provided that enable extraction of metadata, envelope, headers, body and
+attachments from these files.
 
 The following functions are implemented:
 
--   `read_msg`: Read in an Outlook '.msg' file
--   `save_attachments`: Save all attachments from a 'msg' object
+-   `read_msg`: Read in an Outlook ‘.msg’ file
+-   `save_attachments`: Save all attachments from a ‘msg’ object
+-   `tidy_msg`: Turn a ‘msg’ object into a ‘tibble’
 
 ### Installation
 
@@ -21,18 +28,18 @@ devtools::install_github("hrbrmstr/msgxtractr")
 ``` r
 library(msgxtractr)
 
-# current verison
+# current version
 packageVersion("msgxtractr")
 ```
 
-    ## [1] '0.2.1'
+    ## [1] '0.3.0'
 
 ``` r
 str(msg1 <- read_msg(system.file("extdata/unicode.msg", package="msgxtractr")))
 ```
 
     ## List of 8
-    ##  $ headers         :Classes 'tbl_df', 'tbl' and 'data.frame':    1 obs. of  18 variables:
+    ##  $ headers         : tibble [1 × 18] (S3: tbl_df/tbl/data.frame)
     ##   ..$ Return-path               : chr "<[email protected]>"
     ##   ..$ Received                  :List of 1
     ##   .. ..$ : chr [1:4] "from st11p00mm-smtpin007.mac.com ([17.172.84.240])\nby ms06561.mac.com (Oracle Communications Messaging Server "| __truncated__ "from mail-vc0-f182.google.com ([209.85.220.182])\nby st11p00mm-smtpin007.mac.com\n(Oracle Communications Messag"| __truncated__ "by mail-vc0-f182.google.com with SMTP id ie18so3484487vcb.13 for\n<[email protected]>; Mon, 18 Nov 2013 00:26:25 -0800 (PST)" "by 10.58.207.196 with HTTP; Mon, 18 Nov 2013 00:26:24 -0800 (PST)"
@@ -217,26 +224,58 @@ str(msg4 <- read_msg(system.file("extdata/TestMessage-unicode.msg", package="msg
     ##   ..$ last_mod_name: NULL
     ##  - attr(*, "class")= chr "msg"
 
-### Test Results
+``` r
+str(tidy_msg(msg1), 2)
+```
+
+    ## tibble [1 × 8] (S3: tbl_df/tbl/data.frame)
+    ##  $ headers         :List of 1
+    ##  $ sender          :List of 1
+    ##  $ recipients      :List of 1
+    ##  $ subject         : chr "Test for TIF files"
+    ##  $ body            :List of 1
+    ##  $ attachments     :List of 1
+    ##  $ display_envelope:List of 1
+    ##  $ times           :List of 1
 
 ``` r
-library(msgxtractr)
-library(testthat)
+str(tidy_msg(msg2), 2)
+```
 
-date()
+    ## tibble [1 × 4] (S3: tbl_df/tbl/data.frame)
+    ##  $ recipients :List of 1
+    ##  $ body       :List of 1
+    ##  $ attachments:List of 1
+    ##  $ times      :List of 1
+
+``` r
+str(tidy_msg(msg3), 2)
 ```
 
-    ## [1] "Mon Aug 28 21:55:44 2017"
+    ## tibble [1 × 7] (S3: tbl_df/tbl/data.frame)
+    ##  $ sender          :List of 1
+    ##  $ recipients      :List of 1
+    ##  $ subject         : chr "New Message!"
+    ##  $ body            :List of 1
+    ##  $ attachments     :List of 1
+    ##  $ display_envelope:List of 1
+    ##  $ times           :List of 1
 
 ``` r
-test_dir("tests/")
+str(tidy_msg(msg4), 2)
 ```
 
-    ## ..........testthat results ========================================================================================================
-    ## OK: 4 SKIPPED: 0 FAILED: 0
-    ## 
-    ## DONE ===================================================================================================================
+    ## tibble [1 × 7] (S3: tbl_df/tbl/data.frame)
+    ##  $ sender          :List of 1
+    ##  $ recipients      :List of 1
+    ##  $ subject         : chr "New Message!"
+    ##  $ body            :List of 1
+    ##  $ attachments     :List of 1
+    ##  $ display_envelope:List of 1
+    ##  $ times           :List of 1
 
 ### 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.
+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.

msgxtractr.Rproj

@@ -1,21 +1,21 @@
-Version: 1.0
-
-RestoreWorkspace: Default
-SaveWorkspace: Default
-AlwaysSaveHistory: Default
-
-EnableCodeIndexing: Yes
-UseSpacesForTab: Yes
-NumSpacesForTab: 2
-Encoding: UTF-8
-
-RnwWeave: Sweave
-LaTeX: pdfLaTeX
-
-StripTrailingWhitespace: Yes
-
-BuildType: Package
-PackageUseDevtools: Yes
-PackageInstallArgs: --no-multiarch --with-keep.source
-PackageBuildArgs: --resave-data
-PackageRoxygenize: rd,collate,namespace
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX
+
+StripTrailingWhitespace: Yes
+
+BuildType: Package
+PackageUseDevtools: Yes
+PackageInstallArgs: --no-multiarch --with-keep.source
+PackageBuildArgs: --resave-data
+PackageRoxygenize: rd,collate,namespace

tests/testthat/test-msgxtractr.R

@@ -34,4 +34,13 @@ test_that("we can do something", {
 
   expect_equal(nrow(mail_df), 100)
 
+  do.call(
+    rbind.data.frame,
+    lapply(1:10, function(.x) {
+      tidy_msg(read_msg(system.file("extdata/unicode.msg", package="msgxtractr")))
+    })
+  ) -> res
+
+  expect_equal(nrow(res), 10)
+
 })