check clang19

Author: pachadotdev

.github/workflows/clang19.yaml

@@ -0,0 +1,20 @@
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+    branches: [main, master]
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    container:
+      image: ghcr.io/r-hub/containers/clang19:latest
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Install dependencies
+      run: |
+        R -q -e 'pak::pkg_install(c("deps::.", "any::rcmdcheck"), dependencies = TRUE)'
+
+    - uses: r-lib/actions/check-r-package@v2

CRAN-SUBMISSION

@@ -1,3 +1,3 @@
-Version: 5.3.4
-Date: 2024-12-17 21:04:41 UTC
-SHA: 97f5b5e9d7320a878ddbbd128dc52d8adc40ca0a
+Version: 5.3.5
+Date: 2024-12-21 03:07:36 UTC
+SHA: 7d202f614b340caca7fec216dee6b254bb434552

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: cpp11tesseract
 Type: Package
 Title: Open Source OCR Engine
-Version: 5.3.4
+Version: 5.3.5
 Authors@R: c(person("Mauricio", "Vargas Sepulveda",
                     role = c("aut", "cre"), 
                     email = "m.sepulveda@mail.utoronto.ca", 

R/ocr.R

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

R/tessdata.R

@@ -1,45 +1,52 @@
 #' Tesseract Training Data
 #'
 #' Helper function to download training data from the official
-#' [tessdata](https://tesseract-ocr.github.io/tessdoc/Data-Files) repository. On Linux, the fast training data can be installed directly with
+#' [tessdata](https://tesseract-ocr.github.io/tessdoc/Data-Files) repository.
+#' On Linux, the fast training data can be installed directly with
 #' [yum](https://src.fedoraproject.org/rpms/tesseract) or
 #' [apt-get](https://packages.debian.org/search?suite=stable&section=all&arch=any&searchon=names&keywords=tesseract-ocr-).
 #'
 #' Tesseract uses training data to perform OCR. Most systems default to English
-#' training data. To improve OCR performance for other languages you can to install the
-#' training data from your distribution. For example to install the spanish training data:
+#' training data. To improve OCR performance for other languages you can to
+#' install the training data from your distribution. For example to install the
+#' spanish training data:
 #'
-#'  - [tesseract-ocr-spa](https://packages.debian.org/testing/tesseract-ocr-spa) (Debian, Ubuntu)
+#'  - [tesseract-ocr-spa](https://packages.debian.org/testing/tesseract-ocr-spa)
+#'    (Debian, Ubuntu)
 #'  - `tesseract-langpack-spa` (Fedora, EPEL)
 #'
-#' On Windows and MacOS you can install languages using the [tesseract_download] function
-#' which downloads training data directly from [github](https://github.com/tesseract-ocr/tessdata)
+#' On Windows and MacOS you can install languages using the [tesseract_download]
+#' function which downloads training data directly from
+#' [github](https://github.com/tesseract-ocr/tessdata)
 #' and stores it in a the path on disk given by the `TESSDATA_PREFIX` variable.
 #'
 #' @export
 #' @return no return value, called for side effects
 #' @aliases tessdata
 #' @rdname tessdata
 #' @family tesseract
-#' @param lang three letter code for language, see [tessdata](https://github.com/tesseract-ocr/tessdata) repository.
+#' @param lang three letter code for language, see
+#' [tessdata](https://github.com/tesseract-ocr/tessdata) repository.
+#' @param model either `fast` or `best` is currently supported. The latter
+#' downloads more accurate (but slower) trained models for Tesseract 4.0 or
+#' higher
 #' @param datapath destination directory where to download store the file
-#' @param model either `fast` or `best` is currently supported. The latter downloads
-#' more accurate (but slower) trained models for Tesseract 4.0 or higher
 #' @param progress print progress while downloading
-#' @references [tesseract wiki: training data](https://tesseract-ocr.github.io/tessdoc/Data-Files)
+#' @references
+#' [tesseract wiki: training data](https://tesseract-ocr.github.io/tessdoc/Data-Files)
 #' @examples
 #' # download the french training data
+#' # this is wrapped around a \donttest{} block because otherwise the clang19
+#' # CRAN check will fail with a "> 5 seconds" message
 #' \donttest{
-#'   tesseract_download("fra", model = "best", datapath = tempdir())
+#'  dir <- tempdir()
+#'  tesseract_download("fra", model = "best", datapath = dir)
+#'  file <- system.file("examples", "french.png", package = "cpp11tesseract")
+#'  text <- ocr(file, engine = tesseract("fra", datapath = dir))
+#'  cat(text)
 #' }
-#'
-#' if (any("fra" %in% tesseract_info()$available)) {
-#'   french <- tesseract("fra")
-#'   file <- system.file("examples", "french.png", package = "cpp11tesseract")
-#'   text <- ocr(file, engine = french)
-#'   cat(text)
-#' }
-tesseract_download <- function(lang, datapath = NULL, model = c("fast", "best"), progress = interactive()) {
+tesseract_download <- function(lang, model = c("fast", "best"),
+  datapath = NULL, progress = interactive()) {
   stopifnot(is.character(lang))
   model <- match.arg(model)
   if (!length(datapath)) {
@@ -56,44 +63,50 @@ tesseract_download <- function(lang, datapath = NULL, model = c("fast", "best"),
     repo <- paste0("tessdata_", model)
     release <- "4.1.0"
   }
-  url <- sprintf("https://github.com/tesseract-ocr/%s/raw/%s/%s.traineddata", repo, release, lang)
+  url <- sprintf("https://github.com/tesseract-ocr/%s/raw/%s/%s.traineddata",
+    repo, release, lang)
   download_helper(url, datapath, progress)
 }
 
 #' Tesseract Contributed Training Data
 #'
 #' Helper function to download training data from the contributed
-#' [tessdata_contrib](https://github.com/tesseract-ocr/tessdata_contrib) repository.
+#' [tessdata_contrib](https://github.com/tesseract-ocr/tessdata_contrib)
+#' repository.
 #'
 #' @export
 #' @return no return value, called for side effects
 #' @aliases tessdata
 #' @rdname tessdata
 #' @family tesseract
 #' @seealso [tesseract_download]
-#' @param lang three letter code for language, see [tessdata](https://github.com/tesseract-ocr/tessdata) repository.
+#' @param lang three letter code for language, see
+#' [tessdata](https://github.com/tesseract-ocr/tessdata) repository.
+#' @param model either `fast` or `best` is currently supported. The latter
+#' downloads more accurate (but slower) trained models for Tesseract 4.0 or
+#' higher
 #' @param datapath destination directory where to download store the file
-#' @param model either `fast` or `best` is currently supported. The latter downloads
-#' more accurate (but slower) trained models for Tesseract 4.0 or higher
 #' @param progress print progress while downloading
-#' @references [tesseract wiki: training data](https://tesseract-ocr.github.io/tessdoc/Data-Files)
+#' @references
+#' [tesseract wiki: training data](https://tesseract-ocr.github.io/tessdoc/Data-Files)
 #' @examples
-#' # download the polytonic greek training data
+#' # download the greek training data
+#' # this is wrapped around a \donttest{} block because otherwise the clang19
+#' # CRAN check will fail with a "> 5 seconds" message
 #' \donttest{
-#'   tesseract_contributed_download("grc_hist", model = "best",
-#'     datapath = tempdir())
-#' }
-#'
-#' if (any("grc_hist" %in% tesseract_info()$available)) {
-#'   greek <- tesseract("grc_hist")
-#'   file <- system.file("examples", "polytonicgreek.png", package = "cpp11tesseract")
-#'   text <- ocr(file, engine = greek)
-#'   cat(text)
+#'  dir <- tempdir()
+#'  tesseract_contributed_download("grc_hist", model = "best", datapath = dir)
+#'  file <- system.file("examples", "polytonicgreek.png",
+#'    package = "cpp11tesseract")
+#'  text <- ocr(file, engine = tesseract("grc_hist", datapath = dir))
+#'  cat(text)
 #' }
-tesseract_contributed_download <- function(lang, datapath = NULL, model = c("fast", "best"), progress = interactive()) {
+tesseract_contributed_download <- function(lang, model = c("fast", "best"),
+  datapath = NULL, progress = interactive()) {
   stopifnot(is.character(lang))
   if (!any(lang %in% c("grc_hist", "akk"))) {
-    stop("The only available contributed models are Akkadian and Polytonic Greek (for now).", call. = FALSE)
+    stop(paste("The only available contributed models are Akkadian and",
+      "Polytonic Greek (for now)."), call. = FALSE)
   }
   model <- match.arg(model)
   if (!length(datapath)) {
@@ -104,12 +117,14 @@ tesseract_contributed_download <- function(lang, datapath = NULL, model = c("fas
   version <- tesseract_version_major()
 
   if (lang == "grc_hist" && version < 4) {
-    stop("The Polytonic Greek model is only available for Tesseract 4.0 or higher.", call. = FALSE)
+    stop(paste("The Polytonic Greek model is only available for Tesseract 4.0",
+      "or higher."), call. = FALSE)
   }
 
   if (lang == "grc_hist") {
     if (model == "fast") {
-      warning("The Polytonic Greek model is only available in 'best' quality.", call. = FALSE)
+      warning(paste("The Polytonic Greek model is only available in 'best'",
+        "quality."), call. = FALSE)
     }
     release <- "grc_hist/best"
   }
@@ -122,7 +137,8 @@ tesseract_contributed_download <- function(lang, datapath = NULL, model = c("fas
     release <- "akk/fast"
   }
 
-  url <- sprintf("https://github.com/tesseract-ocr/tessdata_contrib/raw/main/%s/%s.traineddata", release, lang)
+  url <- sprintf(paste0("https://github.com/tesseract-ocr/tessdata_contrib/",
+    "raw/main/%s/%s.traineddata"), release, lang)
   print(url)
 
   download_helper(url, datapath, progress)
@@ -166,7 +182,9 @@ progress_fun <- function(down, up) {
 }
 
 warn_on_linux <- function() {
-  if (identical(.Platform$OS.type, "unix") && !identical(Sys.info()[["sysname"]], "Darwin")) {
-    warning("On Linux you should install training data via yum/apt. Please check the manual page.", call. = FALSE)
+  if (identical(.Platform$OS.type, "unix") &&
+      !identical(Sys.info()[["sysname"]], "Darwin")) {
+    warning("On Linux you should install training data via yum/apt. Please
+      check the manual page.", call. = FALSE)
   }
 }

README.Rmd

@@ -38,7 +38,7 @@ How to extract text from an image:
 
 ```{r}
 library(cpp11tesseract)
-text <- ocr("inst/examples/wilde.jpg")
+text <- ocr("inst/examples/wilde.png")
 cat(text)
 ```
 
@@ -118,3 +118,12 @@ Alternatively you can manually download training data from [github](https://gith
 and store it in a path on disk that you pass in the `datapath` parameter or set a default path via the
 `TESSDATA_PREFIX` environment variable. Note that the Tesseract 4 and Tesseract 3 use different 
 training data format. Make sure to download training data from the branch that matches your libtesseract version.
+
+## Testing with docker (development)
+
+```
+mkdir check
+docker run -v `pwd`/check:/check ghcr.io/r-hub/containers/clang19:latest apt install apt-utils libcurl4-openssl-dev &\
+  R -q -e "install.packages(c('Rcpp', 'jsonlite', 'curl', 'httr', 'yaml', 'rex', 'digest', 'crayon', 'withr', 'cli', 'magick', 'processx', 'tibble', 'V8', 'testthat', 'mockery', 'whoami', 'covr', 'asciicast'), repos = 'https://cloud.r-project.org')" &\
+  r-check
+```

README.md

@@ -31,41 +31,20 @@ How to extract text from an image:
 
 ``` r
 library(cpp11tesseract)
-text <- ocr("inst/examples/wilde.jpg")
+text <- ocr("inst/examples/wilde.png")
 cat(text)
-#> Act One
-#> [The living room of Algernon Moncrieff's flat in Mayfair, London.
-#> Lane is arranging afternoon tea on a table. Algemion enters}
-#> Algernon: Lane, have you made the cucumber sandwiches for
-#> Lady Bracknell’s tea?
-#> Lane: Yes, sir. [Handing them to Algernon on a silver tray]
-#> Algernon: [Looking carefully at them, taking two and sitting down
-#> on the sofa] Oh, by the way’, Lane, I looked at your notebook. |
-#> noticed that when Lord Shoreman and Mr Worthing dined with
-#> me on Thursday night, eight bottles of champagne were drunk,
-#> Lane: Yes, sir; eight bottles.
-#> Algernon: Why is it that, in a bachelor’s home, the servants
-#> always drink the champagne? I just ask because | am interested,
-#> Lane.
-#> Lane: I think that it is because the champagne is better in a
-#> bachelor’s home. | have noticed that the champagne in married
-#> people's homes is rarely very good.
-#> Algernon: Good heavens*! Is marriage so depressing?
-#> Lane: | believe marriage is very pleasant, sir. | haven't had much
-#> experience of it myself. [ have only been married once, and that
-#> was because of a misunderstanding” between myself and a young
-#> person.
-#> Algernon: [Lazily, without interest] I am not very interested in
-#> your family life, Lane.
-#> Lane: No, sir; it is not a very interesting subject. I never think
-#> of it myself.
-#> Algernon: That is very understandable. Well, thank you, Lane.
-#> [Lane goes off]
-#> Algernon: [To himself] Lane’s views on marriage seem very casual.
-#> Really, if the servants don’t set us a good example, what on earth
-#> is the use of them? They seem to have no morals
-#> [Lane enters]
-#> Lane: Mr Ernest Worthing is here, sir.
+#> Complete Works
+#> oF
+#> OSCAR WILDE
+#> EDITED BY
+#> 
+#> ROBERT ROSS
+#> MISCELLANIES
+#> ‘AUTHORIZED EDITION
+#> 
+#> THE WYMAN-FOGG COMPANY
+#> 
+#> BOSTON :: MASSACHUSETTS
 ```
 
 ## Differences with the original tesseract R package

configure

@@ -13,7 +13,7 @@ PKG_RPM_NAME="tesseract-devel leptonica-devel"
 PKG_BREW_NAME="tesseract"
 PKG_TEST_HEADER_TESSERACT="<tesseract/baseapi.h>"
 PKG_CFLAGS="-I/usr/include/tesseract -I/usr/include/leptonica"
-PKG_LIBS="-ltesseract"
+PKG_LIBS="-ltesseract -larchive -lcurl"
 
 # Use pkg-config if available
 pkg-config --version >/dev/null 2>&1
@@ -23,6 +23,8 @@ if [ $? -eq 0 ]; then
 fi
 
 # Debugging information
+echo "CC: $CC"
+echo "CXX: $CXX"
 echo "PKGCONFIG_CFLAGS_TESSERACT: $PKGCONFIG_CFLAGS_TESSERACT"
 echo "PKGCONFIG_LIBS_TESSERACT: $PKGCONFIG_LIBS_TESSERACT"
 
@@ -37,6 +39,11 @@ elif [ "$PKGCONFIG_CFLAGS_TESSERACT" ] || [ "$PKGCONFIG_LIBS_TESSERACT" ]; then
   PKG_LIBS="${PKGCONFIG_LIBS_TESSERACT}"
 fi
 
+# Check if the compiler is clang
+if [ "$CC" = "clang" ] || [ "$CXX" = "clang++" ]; then
+  PKG_LIBS="$PKG_LIBS -stdlib=libc++"
+fi
+
 # For debugging
 echo "Using PKG_CFLAGS=$PKG_CFLAGS"
 echo "Using PKG_LIBS=$PKG_LIBS"