First working version of the library

.vscode/settings.json

@@ -2,6 +2,6 @@
     "nim.buildOnSave": false,
     "nim.buildCommand": "c",
     "nim.lintOnSave": true,
-    "nim.project": ["./src/nim_tesseract.nim"],
+    "nim.project": ["./src/nimtesseract.nim"],
     "nim.licenseString": ""
 }

LICENSE

@@ -0,0 +1,24 @@
+This is free and unencumbered software released into the public domain.
+
+Anyone is free to copy, modify, publish, use, compile, sell, or
+distribute this software, either in source code form or as a compiled
+binary, for any purpose, commercial or non-commercial, and by any
+means.
+
+In jurisdictions that recognize copyright laws, the author or authors
+of this software dedicate any and all copyright interest in the
+software to the public domain. We make this dedication for the benefit
+of the public at large and to the detriment of our heirs and
+successors. We intend this dedication to be an overt act of
+relinquishment in perpetuity of all present and future rights to this
+software under copyright law.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
+
+For more information, please refer to <http://unlicense.org/>

README.md

@@ -1,48 +1,47 @@
-> # ⚠️ NOT WORKING YET - Work in progress
-
-# Nim Tesseract
+# Nim Tesseract 👑👁
 Nim Tesseract is a Nim wrapper for the [Tesseract](https://github.com/tesseract-ocr/tesseract/) OCR library, via its dynamic library.
 
-### Development usage:
-Download trained data from https://github.com/tesseract-ocr/tessdata and put it into src folder
-
-```bash
-$ cd src
-$ TESSDATA_PREFIX=$(pwd) nim r -d:pixieUseStb nim_tesseract.nim
-```
-
-`capi.h` reference: https://github.com/tesseract-ocr/tesseract/blob/main/include/tesseract/capi.h
-
-#TODO
- - Working library
- -  - Recognize text
- -  - Choose between pixie (I don't know how to get a proper imagedata and pixel depth) or nim cv2 lib (outdated)
- - Better description
- - Fix memory leaks
- - Fix `=destroy` maybe
- - Rename modules from `nim_tesseract` to `nimtesseract`
- - Remove bindings directory (failed attempts to create bindings via futhark of tesseract's `capi.h`)
-
-## Installation
+## Installation 👇
 ```bash
 $ nimble install https://github.com/DavideGalilei/nimtesseract
 ```
 
-## Usage
-Install (lib)tesseract via your packet manager or put the tesseract so/dll/dylib file in the project directory.
-
+## Usage 🌷
+1. Install (lib)tesseract via your packet manager or put the tesseract so/dll/dylib file in the project directory
 E.g. for Arch Linux (from AUR):
 ```bash
 $ yay -Sy tesseract
 ```
+2. Download trained data from https://github.com/tesseract-ocr/tessdata or https://github.com/tesseract-ocr/tessdata_fast
+3. Done ✅
 
-## Example
+## Example 🤔
 ```nim
-discard "#TODO"
+import nimtesseract
+
+echo imageToText("file.png")
+```
+More examples in the [examples folder](/examples)
+
+## Development 🔩
+Download trained data and put it into src folder
+
+> ⚠️ Outdated, but still useful. Don't refer to this.
+> ```bash
+> $ cd src
+> $ TESSDATA_PREFIX=$(pwd) nim r -d:pixieUseStb nimtesseract.nim
+> ```
+
+Run tests with nimble:
+```bash
+$ nimble test
 ```
 
-## Credits
+`capi.h` reference: https://github.com/tesseract-ocr/tesseract/blob/main/include/tesseract/capi.h
+
+## Credits 👻
 Inspired from https://github.com/Altabeh/tesseract-ocr-wrapper
 
-## License
-#TODO ...
+## License 📕
+This project is under the `Unlicense` license.
+This is free and unencumbered software released into the public domain.

examples/advanced.nim

@@ -0,0 +1,52 @@
+import pixie
+
+import std/[os, json]
+import ../src/nimtesseract
+
+# We get a handle to the created Tesseract instance
+let handle = TessBaseAPICreate()
+
+# Initialize it
+let status = TessBaseAPIInit3(
+    handle = handle,
+    language = cstring("eng"),
+    datapath = cstring(currentSourcePath() / "../../tests"),
+)
+
+# Check if things went wrong
+if int(status) == -1:
+    raise newException(TesseractError, "Couldn't initialize tesseract")
+
+# Open the image with Pixie
+let imagePath = currentSourcePath.parentDir / "test.png"
+var image = readImage(imagePath)
+
+# Pixie stores images as a list of RGBA tuples, hence 4 bytes each
+const bytesPerPixel = 4
+
+# Set the image to recognize the text from
+TessBaseAPISetImage(
+    handle = handle,
+    imagedata = addr(image.data[0]), # Note the [0], from where the actual pixels start
+    width = cint(image.width),
+    height = cint(image.height),
+    bytes_per_pixel = cint(bytesPerPixel),
+    bytes_per_line = cint(image.width * bytesPerPixel),
+)
+
+# Set the PPI
+TessBaseAPISetSourceResolution(
+    handle = handle,
+    ppi = cint(70),
+)
+
+# Get the text. Note: since it's a cstring,
+# we need to convert it back to Nim's string
+# using cstring's `$` procedure.
+let text = $TessBaseAPIGetUTF8Text(handle = handle)
+
+# Don't forget to clean up to avoid memory leaks!
+TessBaseAPIDelete(handle = handle)
+
+echo "Recognized text: ", escapeJson(text)
+# Should look like "Noisy image\nto test\nTesseract OCR\n"

examples/simple.nim

@@ -0,0 +1,11 @@
+import std/[os, json, options]
+import ../src/nimtesseract
+
+# Make sure you downloaded eng.traineddata file
+let recognized = imageToText(
+    "test.png",
+    language = some "eng",
+    datapath = some currentSourcePath() / "../../tests"
+)
+echo "Recognized text: ", escapeJson(recognized)
+# Should look like "Noisy image\nto test\nTesseract OCR\n"

nim_tesseract.nimble → nimtesseract.nimble

@@ -4,3 +4,5 @@ author        = "Davide Galilei"
 description   = "A wrapper to Tesseract OCR library for Nim"
 license       = "MIT"
 srcDir        = "src"
+
+requires "pixie"