version 0.90

DESCRIPTION

@@ -1,5 +1,5 @@
 Package: readtext
-Version: 0.82
+Version: 0.90
 Type: Package
 Title: Import and Handling for Plain and Formatted Text Files
 Authors@R: c( person("Kenneth", "Benoit", email = "kbenoit@lse.ac.uk", role =
@@ -25,7 +25,7 @@ LazyData: TRUE
 VignetteBuilder: knitr
 RoxygenNote: 7.2.3
 NeedsCompilation: no
-Packaged: 2023-04-06 07:33:28 UTC; kbenoit
+Packaged: 2023-06-03 16:53:33 UTC; kbenoit
 Author: Kenneth Benoit [aut, cre, cph],
   Adam Obeng [aut],
   Kohei Watanabe [ctb],
@@ -34,4 +34,4 @@ Author: Kenneth Benoit [aut, cre, cph],
   Stefan Müller [ctb]
 Maintainer: Kenneth Benoit <kbenoit@lse.ac.uk>
 Repository: CRAN
-Date/Publication: 2023-04-06 08:00:02 UTC
+Date/Publication: 2023-06-03 17:30:02 UTC

MD5

@@ -1,24 +1,24 @@
-2585d7d1a618fea232eff4e133aa400e *DESCRIPTION
-0e9837068f198497821087fcc0141306 *NAMESPACE
-44a5bc385a8ffe17ab6049da88c46050 *NEWS.md
+2e8f66947863e9668efa098c60694599 *DESCRIPTION
+2a9aad74ee91f090319822abd90e454a *NAMESPACE
+d66c08943e0c7b95ddad22ee0db7e169 *NEWS.md
 82e67223e0d183311e939e72101bc758 *R/data.R
 19d9450f25f93038ab2bb861c04417e0 *R/encoding.R
 e85eb081256d8315c17f7ed8e8e0029f *R/get-functions.R
 1b342ca0615d4481c3e6cd8b71c20c06 *R/nexis.R
-a9edb84c4333bfcecd740285c68e63c2 *R/quanteda-methods.R
+d80aaa1d0a6aab58239abadd7e79dd48 *R/quanteda-methods.R
 e1dcc814843dfa28ba45f6c7b6933543 *R/readtext-methods.R
 1b29240359589c6854ffdbd357caf7d5 *R/readtext-package.R
 2290605f9616eec87c8a593de43790f3 *R/readtext.R
 b348d381c0640f8c63d83443cd0ef02d *R/readtext_options.R
 977f7ad0fe198d849a9c505473f930ad *R/utils.R
 ae20b98d0ec92f3c945e3a28e7e7f05d *R/zzz.R
-fba5d8a3bab958c845222c33f190922f *README.md
-a45cd788f25fdbbaa738793a35cf96a3 *build/vignette.rds
+fc84d20d0ff5d9942f74eb653a8ec253 *README.md
+681511d74263fb590b147a1ceea50c98 *build/vignette.rds
 c9f29bdb8cd5223a346d3c2a2c71512a *data/data_char_encodedtexts.rda
 d32239bcb673463ab874e80d47fae504 *inst/LICENSE.txt
 867187beed7edb0ae6f5b38ba71eac78 *inst/doc/readtext_vignette.R
 efc0ace01769db1aff92c36894bdf703 *inst/doc/readtext_vignette.Rmd
-e17a738acc3c5acd9e35f58282e902eb *inst/doc/readtext_vignette.html
+13982452978ea9ec0020dd0d355215ae *inst/doc/readtext_vignette.html
 19b51d415cf3974ebe55ee693cff2aef *inst/extdata/csv/inaugCorpus.csv
 c7c1de428544b4f6951551ae5db03794 *inst/extdata/data_files_encodedtexts.zip
 9ce9a26c657050487faf8578db7bbb89 *inst/extdata/json/inaugural_sample.json
@@ -88,8 +88,6 @@ d124e6dc06b759c88e402a590cb7f87e *man/basename_unique.Rd
 8775ff22964f23cb904cb34d70abf914 *man/cache_remote.Rd
 f25d60023eb7dad2007d685a00b713fd *man/data_char_encodedtexts.Rd
 0f25f41994f6df47bd92a5f09ea7deb7 *man/data_files_encodedtexts.Rd
-7cdd586406823671d2a99cd714152d83 *man/docnames.Rd
-10b8f7eca40d99db14dbca44514d1f2b *man/docvars.Rd
 42b88e6e43babcadc585b8fbee99fee7 *man/encoding.Rd
 7e69a682bb64367afa7ec6ae48ca940b *man/get_nexis_html.Rd
 92b45c9a0a6b79bd00297ccfc73e215c *man/get_temp.Rd
@@ -199,7 +197,7 @@ e272d61e00293b8f5d09ef9bea2c809c *tests/testthat/test-encoding.R
 6ff1bfb34b911c6b880a155f48245c49 *tests/testthat/test-nexis.R
 8d59d23d17bd58ac41920108f4458df9 *tests/testthat/test-readtext-methods.R
 a6430f63a9edfe0052460cbe22eb2b03 *tests/testthat/test-readtext-uppercaseextensions.R
-3d7aaad97c4ad381b45094a9056b4761 *tests/testthat/test-readtext.R
+8dd4cce916ed707013cda33358dbd5c3 *tests/testthat/test-readtext.R
 2481ea2eb36e78d3c24506556c403ccf *tests/testthat/test-readtext_options.R
 f0c09c80d56dec49b78b6021b4a6a9f2 *tests/testthat/test-utils.R
 9d20ecec3e3bb49265b3954350ccdd88 *vignettes/mystyle.css

NAMESPACE

@@ -1,16 +1,12 @@
 # Generated by roxygen2: do not edit by hand
 
 S3method(as.character,readtext)
-S3method(docnames,readtext)
-S3method(docvars,readtext)
 S3method(encoding,character)
 S3method(encoding,readtext)
 S3method(format,trunc_mat_tibble)
 S3method(print,readtext)
 S3method(print,trunc_mat_tibble)
 S3method(texts,readtext)
-export(docnames)
-export(docvars)
 export(encoding)
 export(readtext)
 export(readtext_options)

NEWS.md

@@ -1,4 +1,8 @@
-readtext v0.81
+readtext v0.90
+==============
+* Removes the deprecated quanteda functions: `docvars()`, `docnames()`, `texts()`.
+
+readtext v0.82
 ==============
 * Moves some quanteda functions to this package: `docvars()`, `docnames()`, `texts()`
 * Updates print method to use **pillar** instead of tibble

R/quanteda-methods.R

@@ -23,33 +23,3 @@ texts.readtext <- function(x, ...) {
     .Deprecated("Use as.character() instead")
     as.character(x)
 }
-
-#' Extract document variables from a readtext object
-#' 
-#' Returns document variables from a readtext object.
-#' @param x a [readtext] object whose document variables will be extracted
-#' @returns a data.frame of document variables
-#' @export
-docvars <- function(x) {
-    UseMethod("docvars")
-}
-
-#' @export
-docvars.readtext <- function(x) {
-    as.data.frame(x[, -c(match(c("doc_id", "text"), colnames(x)))])
-}
-
-#' Extract document names from a readtext object
-#' 
-#' Returns document names from a readtext object.
-#' @param x a readtext object whose document names will be extracted
-#' @returns a character vector of document names
-#' @export
-docnames <- function(x) {
-    UseMethod("docnames")
-}
-
-#' @export
-docnames.readtext <- function(x) {
-    x[["doc_id"]]
-}

README.md

@@ -5,7 +5,7 @@
 
 [![CRAN
 Version](https://www.r-pkg.org/badges/version/readtext)](https://CRAN.R-project.org/package=readtext)
-[![](https://img.shields.io/badge/devel%20version-0.82-royalblue.svg)](https://github.com/quanteda/readtext)
+[![](https://img.shields.io/badge/devel%20version-0.90-royalblue.svg)](https://github.com/quanteda/readtext)
 [![Downloads](https://cranlogs.r-pkg.org/badges/readtext)](https://CRAN.R-project.org/package=readtext)
 [![Total
 Downloads](https://cranlogs.r-pkg.org/badges/grand-total/readtext?color=orange)](https://CRAN.R-project.org/package=readtext)
@@ -132,7 +132,7 @@ all docvars and other meta-data.
 
 ``` r
 library("quanteda")
-## Package version: 3.2.4
+## Package version: 3.3.1
 ## Unicode version: 14.0
 ## ICU version: 71.1
 ## Parallel computing: 10 of 10 threads used.

inst/doc/readtext_vignette.html

@@ -718,16 +718,16 @@ <h1>3. Inter-operability with quanteda</h1>
 <span id="cb13-8"><a href="#cb13-8" aria-hidden="true" tabindex="-1"></a><span class="fu">summary</span>(corpus_csv, <span class="dv">5</span>)</span>
 <span id="cb13-9"><a href="#cb13-9" aria-hidden="true" tabindex="-1"></a>}</span>
 <span id="cb13-10"><a href="#cb13-10" aria-hidden="true" tabindex="-1"></a><span class="do">## Loading required package: quanteda</span></span>
-<span id="cb13-11"><a href="#cb13-11" aria-hidden="true" tabindex="-1"></a><span class="do">## Package version: 3.2.4</span></span>
+<span id="cb13-11"><a href="#cb13-11" aria-hidden="true" tabindex="-1"></a><span class="do">## Package version: 3.3.1</span></span>
 <span id="cb13-12"><a href="#cb13-12" aria-hidden="true" tabindex="-1"></a><span class="do">## Unicode version: 14.0</span></span>
 <span id="cb13-13"><a href="#cb13-13" aria-hidden="true" tabindex="-1"></a><span class="do">## ICU version: 71.1</span></span>
 <span id="cb13-14"><a href="#cb13-14" aria-hidden="true" tabindex="-1"></a><span class="do">## Parallel computing: 10 of 10 threads used.</span></span>
 <span id="cb13-15"><a href="#cb13-15" aria-hidden="true" tabindex="-1"></a><span class="do">## See https://quanteda.io for tutorials and examples.</span></span>
 <span id="cb13-16"><a href="#cb13-16" aria-hidden="true" tabindex="-1"></a><span class="do">## </span></span>
 <span id="cb13-17"><a href="#cb13-17" aria-hidden="true" tabindex="-1"></a><span class="do">## Attaching package: &#39;quanteda&#39;</span></span>
-<span id="cb13-18"><a href="#cb13-18" aria-hidden="true" tabindex="-1"></a><span class="do">## The following objects are masked from &#39;package:readtext&#39;:</span></span>
+<span id="cb13-18"><a href="#cb13-18" aria-hidden="true" tabindex="-1"></a><span class="do">## The following object is masked from &#39;package:readtext&#39;:</span></span>
 <span id="cb13-19"><a href="#cb13-19" aria-hidden="true" tabindex="-1"></a><span class="do">## </span></span>
-<span id="cb13-20"><a href="#cb13-20" aria-hidden="true" tabindex="-1"></a><span class="do">##     docnames, docvars, texts</span></span>
+<span id="cb13-20"><a href="#cb13-20" aria-hidden="true" tabindex="-1"></a><span class="do">##     texts</span></span>
 <span id="cb13-21"><a href="#cb13-21" aria-hidden="true" tabindex="-1"></a><span class="do">## Corpus consisting of 5 documents, showing 5 documents:</span></span>
 <span id="cb13-22"><a href="#cb13-22" aria-hidden="true" tabindex="-1"></a><span class="do">## </span></span>
 <span id="cb13-23"><a href="#cb13-23" aria-hidden="true" tabindex="-1"></a><span class="do">##               Text Types Tokens Sentences Year  President FirstName</span></span>
@@ -891,8 +891,8 @@ <h2>4.2 Read files with different encodings</h2>
 <span id="cb20-5"><a href="#cb20-5" aria-hidden="true" tabindex="-1"></a><span class="do">## Corpus consisting of 36 documents, showing 5 documents:</span></span>
 <span id="cb20-6"><a href="#cb20-6" aria-hidden="true" tabindex="-1"></a><span class="do">## </span></span>
 <span id="cb20-7"><a href="#cb20-7" aria-hidden="true" tabindex="-1"></a><span class="do">##                                Text Types Tokens Sentences     document</span></span>
-<span id="cb20-8"><a href="#cb20-8" aria-hidden="true" tabindex="-1"></a><span class="do">##   IndianTreaty_English_UTF-16LE.txt   617   2577       152 IndianTreaty</span></span>
-<span id="cb20-9"><a href="#cb20-9" aria-hidden="true" tabindex="-1"></a><span class="do">##  IndianTreaty_English_UTF-8-BOM.txt   645   3092       150 IndianTreaty</span></span>
+<span id="cb20-8"><a href="#cb20-8" aria-hidden="true" tabindex="-1"></a><span class="do">##   IndianTreaty_English_UTF-16LE.txt   618   2577       152 IndianTreaty</span></span>
+<span id="cb20-9"><a href="#cb20-9" aria-hidden="true" tabindex="-1"></a><span class="do">##  IndianTreaty_English_UTF-8-BOM.txt   647   3085       150 IndianTreaty</span></span>
 <span id="cb20-10"><a href="#cb20-10" aria-hidden="true" tabindex="-1"></a><span class="do">##          UDHR_Arabic_ISO-8859-6.txt   753   1555        86         UDHR</span></span>
 <span id="cb20-11"><a href="#cb20-11" aria-hidden="true" tabindex="-1"></a><span class="do">##               UDHR_Arabic_UTF-8.txt   753   1555        86         UDHR</span></span>
 <span id="cb20-12"><a href="#cb20-12" aria-hidden="true" tabindex="-1"></a><span class="do">##        UDHR_Arabic_WINDOWS-1256.txt   753   1555        86         UDHR</span></span>

tests/testthat/test-readtext.R

@@ -2,7 +2,7 @@
 # TODO: Check and remove extranous codes # TODO: recurse file listing for e.g. remote ZIP file
 # TODO: readtext with csv doesn"t seem to require text_field
 
-context("test readtext.R")
+library("quanteda")
 
 test_that("test readtext with single filename", {
     fox <- c(fox.txt = "The quick brown fox jumps over the lazy dog.")
@@ -169,19 +169,19 @@ test_that("test csv files", {
 
 test_that("test tab files", {
     testreadtext <- readtext("../data/tab/test.tab", text_field = "text")
-    expect_that(
-        docvars(testreadtext),
-        equals(data.frame(list(colour = c("green", "red"), number = c(42, 99)), 
-                          stringsAsFactors = FALSE))
+    expect_equal(
+        docvars(corpus(testreadtext)),
+        data.frame(list(colour = c("green", "red"), number = c(42, 99)), 
+                          stringsAsFactors = FALSE)
     )
-    expect_that(
-        as.character(testreadtext),
-        equals(c(test.tab.1 = "Lorem ipsum.", test.tab.2 = "Dolor sit"))
+    expect_equal(
+        testreadtext$text,
+        unname(c(test.tab.1 = "Lorem ipsum.", test.tab.2 = "Dolor sit"))
     )
 
     expect_error(
-        readtext("../data/tab/test.tab", text_field = "nonexistant"),
-                 "There is no field called nonexistant"
+        readtext("../data/tab/test.tab", text_field = "nonexistent"),
+                 "There is no field called nonexistent"
     )
 
 })
@@ -825,13 +825,14 @@ test_that("tests for ODS files", {
         readtext("../data/ods/test.ods", text_field = "text"))),
         c("The quick", "brown fox", "jumps over", "the lazy dog.")
     )
-    expect_equal(
-        docvars(readtext("../data/ods/test.ods", text_field = "text")),
-        data.frame(list(
-                        colour = c("orange", "blue", "pink", "pink"),
-                        number = c(0, NA, NA, NA),
-                        taste = c(NA, NA, "sweet", "umami")
-                        ), stringsAsFactors = FALSE)
+    expect_identical(
+        readtext("../data/ods/test.ods", text_field = "text"),
+        structure(list(doc_id = c("test.ods.1", "test.ods.2", "test.ods.3", 
+                                  "test.ods.4"), text = c("The quick", "brown fox", "jumps over", 
+                                                          "the lazy dog."), colour = c("orange", "blue", "pink", "pink"
+                                                          ), number = c(0L, NA, NA, NA), taste = c(NA, NA, "sweet", "umami"
+                                                          )), row.names = c(NA, -4L), class = c("readtext", "data.frame"
+                                                          ))
     )
 
 })