split tests

Author: pachadotdev

.Rbuildignore

@@ -25,3 +25,5 @@ vignettes/.*\.png$
 ^dev$
 ^lib$
 ^\.covrignore$
+^vignettes/bondargentina_1\.png$
+^vignettes/bondargentina_2\.png$

CRAN-SUBMISSION

@@ -1,3 +1,3 @@
-Version: 0.1.0
-Date: 2024-12-16 23:10:09 UTC
-SHA: 0172b7e010c38e32d1ab317eae369384c4cb4255
+Version: 5.3.4
+Date: 2024-12-17 21:04:41 UTC
+SHA: 97f5b5e9d7320a878ddbbd128dc52d8adc40ca0a

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: cpp11tesseract
 Type: Package
 Title: Open Source OCR Engine
-Version: 0.1.0
+Version: 5.3.4
 Authors@R: c(person("Mauricio", "Vargas Sepulveda",
                     role = c("aut", "cre"), 
                     email = "m.sepulveda@mail.utoronto.ca", 
@@ -16,12 +16,11 @@ Authors@R: c(person("Mauricio", "Vargas Sepulveda",
              person("Munk School of Global Affairs and Public Policy",
                     role = "fnd")
             )
-Description: Bindings to 'Tesseract': 
-     Tesseract
-     (<[https://github.com/tesseract-ocr/tesseract]https://github.com/tesseract-ocr/tesseract>)
-     is a powerful optical character recognition (OCR) engine that supports over
-     100 languages. The engine is highly configurable in order to tune the
-     detection algorithms and obtain the best possible results.
+Description: Bindings to 'tesseract': 
+     'tesseract' (<https://github.com/tesseract-ocr/tesseract>) is a powerful
+     optical character recognition (OCR) engine that supports over 100
+     languages. The engine is highly configurable in order to tune the detection
+     algorithms and obtain the best possible results.
 License: Apache License (>= 2)
 URL: https://pacha.dev/cpp11tesseract/
 BugReports: https://github.com/pachadotdev/cpp11tesseract/issues
@@ -43,10 +42,7 @@ Suggests:
     knitr,
     tibble,
     rmarkdown,
-    testthat (>= 3.0.0),
-    cpp11poppler
-Remotes: 
-    pachadotdev/cpp11poppler
+    testthat (>= 3.0.0)
 Encoding: UTF-8
 VignetteBuilder: knitr
 Language: en-US

NEWS.md

@@ -1,4 +1,4 @@
-# 0.1.0
+# 5.3.3
 
 - This is a fork of the original tesseract package made by Jeroen Ooms. The
   differences are:

R/ocr.R

@@ -25,8 +25,7 @@
 #' @rdname ocr
 #' @references [Tesseract: Improving Quality](https://github.com/tesseract-ocr/tesseract/wiki/ImproveQuality)
 #' @examples
-#' # Simple example
-#' file <- system.file("examples", "wilde.jpg", package = "cpp11tesseract")
+#' file <- system.file("examples", "wilde.png", package = "cpp11tesseract")
 #' text <- ocr(file)
 #' cat(text)
 ocr <- function(file, engine = tesseract("eng"), HOCR = FALSE, opw = "", upw = "") {

R/tessdata.R

@@ -30,7 +30,7 @@
 #' @examples
 #' # download the french training data
 #' \donttest{
-#' tesseract_download("fra", model = "best", datapath = tempdir())
+#'   tesseract_download("fra", model = "best", datapath = tempdir())
 #' }
 #'
 #' if (any("fra" %in% tesseract_info()$available)) {
@@ -80,7 +80,8 @@ tesseract_download <- function(lang, datapath = NULL, model = c("fast", "best"),
 #' @examples
 #' # download the polytonic greek training data
 #' \donttest{
-#' tesseract_contributed_download("grc_hist", model = "best", datapath = tempdir())
+#'   tesseract_contributed_download("grc_hist", model = "best",
+#'     datapath = tempdir())
 #' }
 #'
 #' if (any("grc_hist" %in% tesseract_info()$available)) {

R/tesseract.R

@@ -45,7 +45,8 @@ tesseract <- local({
 #' @return no return value, called for side effects
 #' @rdname tesseract
 #' @param filter only list parameters containing a particular string
-#' @examples tesseract_params("debug")
+#' @examples
+#' tesseract_params("smooth")
 tesseract_params <- function(filter = "") {
   tmp <- print_params(tempfile())
   on.exit(unlink(tmp))