add CRAN changes to repo

pachadotdev · pachadotdev · commit 03cabea1c4cd · 2025-01-03T08:31:08.000Z
diff --git a/CRAN-SUBMISSION b/CRAN-SUBMISSION
@@ -1,3 +1,3 @@
-Version: 1.0.5-3
-Date: 2024-05-20 21:23:46 UTC
-SHA: afc71d378ab49fa29ae1c6075d499f8249a80110
+Version: 1.0.5-5
+Date: 2024-11-15 04:06:48 UTC
+SHA: 7325a8d2b58e7fb0dc6097572b4e20bd469e8dc5
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -7,7 +7,7 @@ Description: Bindings for the 'Tabula' <https://tabula.technology/> 'Java'
     journalism. It allows for automatic and manual table extraction, the latter
     facilitated through a 'Shiny' interface, enabling manual areas selection\
     with a computer mouse for data retrieval.
-Version: 1.0.5-4
+Version: 1.0.5-5
 Authors@R: c(
     person("Thomas J.", "Leeper",
             role = "aut", 
@@ -57,4 +57,4 @@ SystemRequirements: Java (>= 7.0):
     openjdk@11 (brew)
 VignetteBuilder: knitr
 Encoding: UTF-8
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,7 @@
+# CHANGES TO tabulapdf 1.0.5-5
+
+* Updated tests to use offline files.
+
 # CHANGES TO tabulapdf 1.0.5-4
 
 * Faster Shiny interface (parts of PR #56, @jkeuskamp)
diff --git a/R/extract_metadata.R b/R/extract_metadata.R
@@ -11,7 +11,6 @@
 #' @examples
 #' # simple demo file
 #' f <- system.file("examples", "mtcars.pdf", package = "tabulapdf")
-#'
 #' extract_metadata(f)
 #' @seealso \code{\link{extract_tables}}, \code{\link{extract_areas}}, \code{\link{extract_text}}, \code{\link{split_pdf}}
 #' @importFrom rJava J new
diff --git a/R/extract_tables.R b/R/extract_tables.R
@@ -36,7 +36,6 @@
 #' @examples
 #' # simple demo file
 #' f <- system.file("examples", "mtcars.pdf", package = "tabulapdf")
-#'
 #' # extract tables from only second page
 #' extract_tables(f, pages = 2)
 #' @seealso \code{\link{extract_areas}}, \code{\link{get_page_dims}}, \code{\link{make_thumbnails}}, \code{\link{split_pdf}}
diff --git a/R/extract_text.R b/R/extract_text.R
@@ -14,13 +14,10 @@
 #' @examples
 #' # simple demo file
 #' f <- system.file("examples", "fortytwo.pdf", package = "tabulapdf")
-#'
-#' # extract all text
-#' extract_text(f)
-#'
+#' 
 #' # extract all text from page 1 only
 #' extract_text(f, pages = 1)
-#'
+#' 
 #' # extract text from selected area only
 #' extract_text(f, area = list(c(209.4, 140.5, 304.2, 500.8)))
 #' @seealso \code{\link{extract_tables}}, \code{\link{extract_areas}}, \code{\link{split_pdf}}
diff --git a/R/get_page_dims.R b/R/get_page_dims.R
@@ -15,7 +15,6 @@
 #' @examples
 #' # simple demo file
 #' f <- system.file("examples", "mtcars.pdf", package = "tabulapdf")
-#'
 #' get_n_pages(file = f)
 #' get_page_dims(f)
 #' @importFrom tools file_path_sans_ext
diff --git a/R/make_thumbnails.R b/R/make_thumbnails.R
@@ -25,8 +25,9 @@
 #' @examples
 #' # simple demo file
 #' f <- system.file("examples", "mtcars.pdf", package = "tabulapdf")
-#'
-#' make_thumbnails(f)
+#' 
+#' # extract thumbnails from the first page
+#' make_thumbnails(f, page = 1)
 #' @importFrom tools file_path_sans_ext
 #' @importFrom rJava J new .jfloat
 #' @seealso \code{\link{extract_tables}}, \code{\link{extract_text}},
diff --git a/README.Rmd b/README.Rmd
@@ -29,9 +29,13 @@ You need do this before installing rJava or attempting to use tabulapdf. More on
 [this](#installing-java-on-windows-with-chocolatey) and
 [troubleshooting](#troubleshooting) below.
 
-tabulapdf is not available on CRAN, but it can be installed from rOpenSci's
+tabulapdf is available on CRAN, and it can also be installed from rOpenSci's
 R-Universe:
 ```r
+# either
+install.packages("tabulapdf")
+
+# or
 install.packages("tabulapdf", repos = c("https://ropensci.r-universe.dev", "https://cloud.r-project.org"))
 ```
 
diff --git a/README.md b/README.md
@@ -21,10 +21,14 @@ Java. You need do this before installing rJava or attempting to use
 tabulapdf. More on [this](#installing-java-on-windows-with-chocolatey)
 and [troubleshooting](#troubleshooting) below.
 
-tabulapdf is not available on CRAN, but it can be installed from
+tabulapdf is available on CRAN, and it can also be installed from
 rOpenSci’s R-Universe:
 
 ``` r
+# either
+install.packages("tabulapdf")
+
+# or
 install.packages("tabulapdf", repos = c("https://ropensci.r-universe.dev", "https://cloud.r-project.org"))
 ```
 
@@ -113,6 +117,18 @@ directory before trying to install the package. This can be changed from
 ensure write permission by choosing “Run as administrator” when
 launching R (again, from the right-click context menu).
 
+## Debugging
+
+Load the package like this:
+
+``` r
+devtools::load_all()
+libname = "/home/pacha/R/x86_64-pc-linux-gnu-library/4.4"
+pkgname = "tabulapdf"
+rJava::.jpackage(pkgname, jars = "*", lib.loc = libname)
+rJava::J("java.lang.System")$setProperty("java.awt.headless", "true")
+```
+
 ## Meta
 
   - Please [report any issues or
diff --git a/cran-comments.md b/cran-comments.md
@@ -1,8 +1,15 @@
 ## R CMD check results
 
-0 errors | 0 warnings | 1 note
+0 errors | 0 warnings | 2 notes
 
-tabulapdf 1.0.5-3
-* This is a new release that replaces the archived tabulizer package.
-* Moves examples with CPU time > 2.5 times elapsed time on Debian.
-* Most of the R functions were designed to make it sure this works with Java 11 or later.
+tabulapdf 1.0.5-5
+* Updated tests to use offline files.
+* The rest remains the same.
+
+❯ checking installed package size ... NOTE
+    installed size is 13.7Mb
+    sub-directories of 1Mb or more:
+      java  12.7Mb
+
+❯ checking for future file timestamps ... NOTE
+  unable to verify current time
diff --git a/inst/examples/argentina.pdf b/inst/examples/argentina.pdf
diff --git a/inst/examples/quebec.pdf b/inst/examples/quebec.pdf
diff --git a/tests/testthat/test_non-latin.R b/tests/testthat/test_non-latin.R
@@ -1,7 +1,8 @@
 context("Non-latin character tests")
 
 test_that("Read Spanish language PDF", {
-  f1 <- "https://github.com/tabulapdf/tabula-java/raw/98957221950af4b90620b51a29e0bbe502eea9ad/src/test/resources/technology/tabula/argentina_diputados_voting_record.pdf"
+  # file from "https://github.com/tabulapdf/tabula-java/raw/98957221950af4b90620b51a29e0bbe502eea9ad/src/test/resources/technology/tabula/argentina_diputados_voting_record.pdf"
+  f1 <- system.file("examples", "argentina.pdf", package = "tabulapdf")
   t1 <- extract_tables(f1, pages = 1, area = list(c(269.875, 12.75, 790.5, 561)), guess = FALSE)
   t1a <- extract_tables(f1, pages = 1, area = list(c(269.875, 12.75, 790.5, 561)), guess = FALSE, output = "tibble", encoding = "latin1")
   t1b <- extract_tables(f1, pages = 1, area = list(c(269.875, 12.75, 790.5, 561)), guess = FALSE, output = "tibble", encoding = "UTF-8")
@@ -11,7 +12,8 @@ test_that("Read Spanish language PDF", {
 })
 
 test_that("Read French language PDF w/correct encoding", {
-  f2 <- "http://www.europarl.europa.eu/oeil/popups/printfichetechnical.pdf?id=673511&lang=fr"
+  # file from https://cdn-contenu.quebec.ca/cdn-contenu/adm/min/finances/publications-adm/Comptes-publics/FR/CPFR_Devancement_Preparation.pdf
+  f2 <- system.file("examples", "quebec.pdf", package = "tabulapdf")
   t2a <- extract_text(f2, page = 1, encoding = "latin1")
   t2b <- extract_text(f2, page = 1, encoding = "UTF-8")
   expect_false(t2a == t2b)
