update docs + re-add win bundle

Author: pachadotdev

.github/workflows/test-coverage.yaml

@@ -26,7 +26,7 @@ jobs:
         run: |
           sudo add-apt-repository -y ppa:alex-p/tesseract-ocr5
           sudo apt-get update
-          sudo apt-get install -y libtesseract-dev tesseract-ocr tesseract-ocr-eng libpoppler-cpp-dev libmagick++-dev
+          sudo apt-get install -y libtesseract-dev tesseract-ocr tesseract-ocr-eng libpoppler-cpp-dev
 
       - name: Query dependencies
         run: |

DESCRIPTION

@@ -17,7 +17,9 @@ Authors@R: c(person("Mauricio", "Vargas Sepulveda",
                     role = "fnd")
             )
 Description: Bindings to 'Tesseract': 
-     a powerful optical character recognition (OCR) engine that supports over
+     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.
 License: Apache License (>= 2)
@@ -37,7 +39,6 @@ LinkingTo:
 RoxygenNote: 7.3.2
 Roxygen: list(markdown = TRUE)
 Suggests:
-    magick (>= 2.7),
     spelling,
     knitr,
     tibble,

R/images.R

@@ -26,27 +26,16 @@
 #' @references [Tesseract: Improving Quality](https://github.com/tesseract-ocr/tesseract/wiki/ImproveQuality)
 #' @examples
 #' # Simple example
-#' file <- system.file("examples", "testocr.png", package = "cpp11tesseract")
+#' file <- system.file("examples", "wilde.jpg", package = "cpp11tesseract")
 #' text <- ocr(file)
 #' cat(text)
 ocr <- function(file, engine = tesseract("eng"), HOCR = FALSE, opw = "", upw = "") {
   if (is.character(engine)) {
     engine <- tesseract(engine)
   }
   stopifnot(inherits(engine, "externalptr"))
-  if (isTRUE(inherits(file, "magick-image"))) {
-    vapply(file, function(x) {
-      tmp <- tempfile(fileext = ".png")
-      on.exit(unlink(tmp))
-      magick::image_write(x, tmp, format = "PNG", density = "300x300")
-      ocr(tmp, engine = engine, HOCR = HOCR)
-    }, character(1))
-  } else if (isTRUE(is.character(file))) {
-    if (isFALSE(is.tiff(file))) {
-      vapply(file, ocr_file, character(1), ptr = engine, HOCR = HOCR, USE.NAMES = FALSE)
-    } else {
-      ocr(tiff_convert(file), engine, HOCR = HOCR)
-    }
+  if (isTRUE(is.character(file))) {
+    vapply(file, ocr_file, character(1), ptr = engine, HOCR = HOCR, USE.NAMES = FALSE)
   } else if (isTRUE(is.raw(file))) {
     ocr_raw(file, engine, HOCR = HOCR)
   } else {
@@ -61,14 +50,7 @@ ocr_data <- function(file, engine = tesseract("eng")) {
     engine <- tesseract(engine)
   }
   stopifnot(inherits(engine, "externalptr"))
-  df_list <- if (inherits(file, "magick-image")) {
-    lapply(file, function(x) {
-      tmp <- tempfile(fileext = ".png")
-      on.exit(unlink(tmp))
-      magick::image_write(x, tmp, format = "PNG", density = "300x300")
-      ocr_data(tmp, engine = engine)
-    })
-  } else if (is.character(file)) {
+  df_list <- if (is.character(file)) {
     lapply(file, function(im) {
       ocr_file_data(im, ptr = engine)
     })

R/ocr.R

@@ -13,7 +13,7 @@ knitr::opts_chunk$set(
 )
 ```
 
-# cpp11tesseract <img src="man/figures/logo.svg" align="right" height="139" alt="" />
+# cpp11tesseract
 
 [![R-CMD-check](https://github.com/pachadotdev/cpp11tesseract/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/pachadotdev/cpp11tesseract/actions/workflows/R-CMD-check.yaml)
 [![codecov](https://codecov.io/gh/pachadotdev/cpp11tesseract/graph/badge.svg?token=mWfiUCgfNu)](https://app.codecov.io/gh/pachadotdev/cpp11tesseract)
@@ -36,9 +36,9 @@ obtain the best possible results.
 
 How to extract text from an image:
 
-```r
-# Simple example
-text <- ocr("inst/examples/figures/testocr.png")
+```{r}
+library(cpp11tesseract)
+text <- ocr("inst/examples/wilde.jpg")
 cat(text)
 ```
 

README.Rmd

@@ -1,7 +1,7 @@
 
 <!-- README.md is generated from README.Rmd. Please edit that file -->
 
-# cpp11tesseract <img src="man/figures/logo.svg" align="right" height="139" alt="" />
+# cpp11tesseract
 
 [![R-CMD-check](https://github.com/pachadotdev/cpp11tesseract/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/pachadotdev/cpp11tesseract/actions/workflows/R-CMD-check.yaml)
 [![codecov](https://codecov.io/gh/pachadotdev/cpp11tesseract/graph/badge.svg?token=mWfiUCgfNu)](https://app.codecov.io/gh/pachadotdev/cpp11tesseract)
@@ -30,9 +30,42 @@ detection algorithms and obtain the best possible results.
 How to extract text from an image:
 
 ``` r
-# Simple example
-text <- ocr("inst/examples/figures/testocr.png")
+library(cpp11tesseract)
+text <- ocr("inst/examples/wilde.jpg")
 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.
 ```
 
 ## Differences with the original tesseract R package