add contributed models

.Rbuildignore

@@ -13,3 +13,7 @@ vignettes/.*\.png$
 ^configure.log$
 ^\.github$
 ^\.vscode$
+^README\.Rmd$
+^README\.html$
+^docs$
+^pkgdown$

NAMESPACE

@@ -4,6 +4,7 @@ S3method(print,tesseract)
 export(ocr)
 export(ocr_data)
 export(tesseract)
+export(tesseract_contributed_download)
 export(tesseract_download)
 export(tesseract_info)
 export(tesseract_params)

NEWS.md

@@ -0,0 +1,10 @@
+# 5.3.0
+  - This is a fork of the original tesseract package made by Jeroen Ooms.
+  - Differences:
+    - Uses cpp11 instead of Rcpp.
+    - Provides functions to download and use the slower but more accurate
+      models.
+    - Provides functions to download and use contributed models.
+    - The documentation works offline.
+    - Explicitly tests on Ubuntu with Tesseract 4 (Ubuntu 22.04 default) and
+      Tesseract 5 (PPA).

R/tessdata.R

@@ -27,8 +27,9 @@
 #' @param progress print progress while downloading
 #' @references [tesseract wiki: training data](https://tesseract-ocr.github.io/tessdoc/Data-Files)
 #' @examples \dontrun{
-#' if(is.na(match("fra", tesseract_info()$available)))
+#' if (is.na(match("fra", tesseract_info()$available))) {
 #'   tesseract_download("fra", model = "best")
+#' }
 #' french <- tesseract("fra")
 #' file <- system.file("examples", "french.png", package = "cpp11tesseract")
 #' text <- ocr(file, engine = french)
@@ -37,57 +38,127 @@
 tesseract_download <- function(lang, datapath = NULL, model = c("fast", "best"), progress = interactive()) {
   stopifnot(is.character(lang))
   model <- match.arg(model)
-  if(!length(datapath)){
+  if (!length(datapath)) {
     warn_on_linux()
     datapath <- tesseract_info()$datapath
   }
   datapath <- normalizePath(datapath, mustWork = TRUE)
   version <- tesseract_version_major()
 
-  if(version < 4){
+  if (version < 4) {
     repo <- "tessdata"
     release <- "3.04.00"
   } else {
     repo <- paste0("tessdata_", model)
     release <- "4.1.0"
   }
-
   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.
+#'
+#' @export
+#' @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 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)
+#' @examples
+#' \dontrun{
+#' if (is.na(match("grc_hist", tesseract_info()$available))) {
+#'  tesseract_contributed_download("grc_hist")
+#' }
+#' greek <- tesseract("grc_hist")
+#' file <- system.file("examples", "polytonicgreek.png", package = "cpp11tesseract")
+#' text <- ocr(file, engine = greek)
+#' cat(text)
+#' }
+tesseract_contributed_download <- function(lang, datapath = NULL, model = c("fast", "best"), progress = interactive()) {
+  stopifnot(is.character(lang))
+  if (!any(lang %in% c("grc_hist", "akk"))) {
+    stop("The only available contributed models are Akkadian and Polytonic Greek (for now).", call. = FALSE)
+  }
+  model <- match.arg(model)
+  if (!length(datapath)) {
+    warn_on_linux()
+    datapath <- tesseract_info()$datapath
+  }
+  datapath <- normalizePath(datapath, mustWork = TRUE)
+  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)
+  }
+
+  if (lang == "grc_hist") {
+    if (model == "fast") {
+      warning("The Polytonic Greek model is only available in 'best' quality.", call. = FALSE)
+    }
+    release <- "grc_hist/best"
+  }
+
+  if (lang == "akk" && version < 4) {
+    release <- "akk/legacy"
+  } else if (lang == "akk" && model == "best") {
+    release <- "akk/best"
+  } else if (lang == "akk" && model == "fast") {
+    release <- "akk/fast"
+  }
+
+  url <- sprintf("https://github.com/tesseract-ocr/tessdata_contrib/raw/main/%s/%s.traineddata", release, lang)
+  print(url)
+
+  download_helper(url, datapath, progress)
+}
+
+download_helper <- function(url, datapath, progress) {
   destfile <- file.path(datapath, basename(url))
 
   if (file.exists(destfile)) {
-    message(paste("Training data already exists. Overwriting", destfile))
+    message("The training data already exists. Skipping download.")
+    return(destfile)
   }
 
   req <- curl::curl_fetch_memory(url, curl::new_handle(
     progressfunction = progress_fun,
     noprogress = !isTRUE(progress)
   ))
-  if(progress)
+
+  if (progress) {
     cat("\n")
-  if(req$status_code != 200)
+  }
+  if (req$status_code != 200) {
     stop("Download failed: HTTP ", req$status_code, call. = FALSE)
-
+  }
   writeBin(req$content, destfile)
   return(destfile)
 }
 
 progress_fun <- function(down, up) {
   total <- down[[1]]
   now <- down[[2]]
-  pct <- if(length(total) && total > 0){
-    paste0("(", round(now/total * 100), "%)")
+  pct <- if (length(total) && total > 0) {
+    paste0("(", round(now / total * 100), "%)")
   } else {
     ""
   }
-  if(now > 10000)
+  if (now > 10000) {
     cat("\r Downloaded:", sprintf("%.2f", now / 2^20), "MB ", pct)
+  }
   TRUE
 }
 
-warn_on_linux <- function(){
-  if(identical(.Platform$OS.type, "unix") && !identical(Sys.info()[["sysname"]], "Darwin")){
+warn_on_linux <- function() {
+  if (identical(.Platform$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)
   }
 }