feat: support react-native-vision-camera v3

README.md

@@ -1,11 +1,10 @@
-<div align="right">
-<img align="right" src="docs/demo.gif">
-</div>
 
 # vision-camera-ocr
 
 A [VisionCamera](https://github.com/mrousavy/react-native-vision-camera) Frame Processor Plugin to preform text detection on images using [**MLKit Vision** Text Recognition](https://developers.google.com/ml-kit/vision/text-recognition).
 
+<img style='width:200px;' src="docs/demo.gif">
+
 ## Installation
 
 ```sh
@@ -17,14 +16,7 @@ Add the plugin to your `babel.config.js`:
 
 ```js
 module.exports = {
-  plugins: [
-    [
-      'react-native-reanimated/plugin',
-      {
-        globals: ['__scanOCR'],
-      },
-    ],
-
+   plugins: [['react-native-worklets-core/plugin']],
     // ...
 ```
 
@@ -33,7 +25,7 @@ module.exports = {
 ## Usage
 
 ```js
-import { labelImage } from "vision-camera-image-labeler";
+import {scanOCR} from 'vision-camera-ocr';
 
 // ...
 const frameProcessor = useFrameProcessor((frame) => {
@@ -56,7 +48,7 @@ const frameProcessor = useFrameProcessor((frame) => {
 ```
 
 The text object closely resembles the object documented in the MLKit documents.
-https://developers.google.com/ml-kit/vision/text-recognition#text_structure
+<https://developers.google.com/ml-kit/vision/text-recognition#text_structure>
 
 ```
 The Text Recognizer segments text into blocks, lines, and elements. Roughly speaking:
@@ -68,8 +60,6 @@ a Line is a contiguous set of words on the same axis, and
 an Element is a contiguous set of alphanumeric characters ("word") on the same axis in most Latin languages, or a character in others
 ```
 
-
-
 ## Contributing
 
 See the [contributing guide](CONTRIBUTING.md) to learn how to contribute to the repository and the development workflow.

vision-camera-ocr.podspec → VisionCameraOcr.podspec

@@ -3,7 +3,7 @@ require "json"
 package = JSON.parse(File.read(File.join(__dir__, "package.json")))
 
 Pod::Spec.new do |s|
-  s.name         = "vision-camera-ocr"
+  s.name         = "VisionCameraOcr"
   s.version      = package["version"]
   s.summary      = package["description"]
   s.homepage     = package["homepage"]
@@ -16,5 +16,5 @@ Pod::Spec.new do |s|
   s.source_files = "ios/**/*.{h,m,mm,swift}"
 
   s.dependency "React-Core"
-  s.dependency "GoogleMLKit/TextRecognition", "2.2.0"
+  s.dependency "GoogleMLKit/TextRecognition", "3.1.0"
 end

android/build.gradle

@@ -3,12 +3,16 @@ buildscript {
   def kotlin_version = rootProject.ext.has('kotlinVersion') ? rootProject.ext.get('kotlinVersion') : project.properties['VisionCameraOcr_kotlinVersion']
 
   repositories {
+    maven {
+      url "https://plugins.gradle.org/m2/"
+    }
     google()
     mavenCentral()
+
   }
 
   dependencies {
-    classpath 'com.android.tools.build:gradle:3.2.1'
+    classpath "com.android.tools.build:gradle:8.0.1"
     // noinspection DifferentKotlinGradleVersion
     classpath "org.jetbrains.kotlin:kotlin-gradle-plugin:$kotlin_version"
   }
@@ -45,8 +49,8 @@ android {
     disable 'GradleCompatible'
   }
   compileOptions {
-    sourceCompatibility JavaVersion.VERSION_1_8
-    targetCompatibility JavaVersion.VERSION_1_8
+    sourceCompatibility JavaVersion.VERSION_11
+    targetCompatibility JavaVersion.VERSION_11
   }
 }
 
@@ -129,6 +133,6 @@ dependencies {
   implementation "org.jetbrains.kotlin:kotlin-stdlib:$kotlin_version"
 
   implementation project(':react-native-vision-camera')
-  implementation 'com.google.android.gms:play-services-mlkit-text-recognition:18.0.0'
-  implementation "androidx.camera:camera-core:1.1.0-alpha08"
+  implementation "com.google.mlkit:text-recognition:16.0.0-beta4"
+  implementation "androidx.camera:camera-core:1.1.0"
 }

android/gradle.properties

@@ -1,5 +1,5 @@
-VisionCameraOcr_kotlinVersion=1.5.30
+VisionCameraOcr_kotlinVersion=1.7.20
 VisionCameraOcr_compileSdkVersion=31
-VisionCameraOcr_buildToolsVersion=30.0.0
+VisionCameraOcr_buildToolsVersion=33.0.0
 VisionCameraOcr_targetSdkVersion=31
 VisionCameraOcr_ndkVersion=21.4.7075529

android/src/main/java/com/visioncameraocr/OCRFrameProcessorPlugin.kt

@@ -1,124 +1,139 @@
-package com.visioncameraocr
-
-import android.annotation.SuppressLint
-import android.graphics.Point
-import android.graphics.Rect
-import android.media.Image
-import androidx.camera.core.ImageProxy
-import com.facebook.react.bridge.WritableNativeArray
-import com.facebook.react.bridge.WritableNativeMap
-import com.google.android.gms.tasks.Task
-import com.google.android.gms.tasks.Tasks
-import com.google.mlkit.vision.common.InputImage
-import com.google.mlkit.vision.text.Text
-import com.google.mlkit.vision.text.TextRecognition
-import com.google.mlkit.vision.text.latin.TextRecognizerOptions
-import com.mrousavy.camera.frameprocessor.FrameProcessorPlugin
-
-class OCRFrameProcessorPlugin: FrameProcessorPlugin("scanOCR") {
-
-    private fun getBlockArray(blocks: MutableList<Text.TextBlock>): WritableNativeArray {
-        val blockArray = WritableNativeArray()
-
-        for (block in blocks) {
-            val blockMap = WritableNativeMap()
-
-            blockMap.putString("text", block.text)
-            blockMap.putArray("recognizedLanguages", getRecognizedLanguages(block.recognizedLanguage))
-            blockMap.putArray("cornerPoints", block.cornerPoints?.let { getCornerPoints(it) })
-            blockMap.putMap("frame", getFrame(block.boundingBox))
-            blockMap.putArray("lines", getLineArray(block.lines))
-
-            blockArray.pushMap(blockMap)
-        }
-        return blockArray
-    }
-
-    private fun getLineArray(lines: MutableList<Text.Line>): WritableNativeArray {
-        val lineArray = WritableNativeArray()
-
-        for (line in lines) {
-            val lineMap = WritableNativeMap()
-
-            lineMap.putString("text", line.text)
-            lineMap.putArray("recognizedLanguages", getRecognizedLanguages(line.recognizedLanguage))
-            lineMap.putArray("cornerPoints", line.cornerPoints?.let { getCornerPoints(it) })
-            lineMap.putMap("frame", getFrame(line.boundingBox))
-            lineMap.putArray("elements", getElementArray(line.elements))
-
-            lineArray.pushMap(lineMap)
-        }
-        return lineArray
-    }
-
-    private fun getElementArray(elements: MutableList<Text.Element>): WritableNativeArray {
-        val elementArray = WritableNativeArray()
-
-        for (element in elements) {
-            val elementMap = WritableNativeMap()
-
-            elementMap.putString("text", element.text)
-            elementMap.putArray("cornerPoints", element.cornerPoints?.let { getCornerPoints(it) })
-            elementMap.putMap("frame", getFrame(element.boundingBox))
-        }
-        return elementArray
-    }
-
-    private fun getRecognizedLanguages(recognizedLanguage: String): WritableNativeArray {
-        val recognizedLanguages = WritableNativeArray()
-        recognizedLanguages.pushString(recognizedLanguage)
-        return recognizedLanguages
-    }
-
-    private fun getCornerPoints(points: Array<Point>): WritableNativeArray {
-        val cornerPoints = WritableNativeArray()
-
-        for (point in points) {
-            val pointMap = WritableNativeMap()
-            pointMap.putInt("x", point.x)
-            pointMap.putInt("y", point.y)
-            cornerPoints.pushMap(pointMap)
-        }
-        return cornerPoints
-    }
-
-    private fun getFrame(boundingBox: Rect?): WritableNativeMap {
-        val frame = WritableNativeMap()
-
-        if (boundingBox != null) {
-            frame.putDouble("x", boundingBox.exactCenterX().toDouble())
-            frame.putDouble("y", boundingBox.exactCenterY().toDouble())
-            frame.putInt("width", boundingBox.width())
-            frame.putInt("height", boundingBox.height())
-            frame.putInt("boundingCenterX", boundingBox.centerX())
-            frame.putInt("boundingCenterY", boundingBox.centerY())
-        }
-        return frame
-    }
-
-    override fun callback(frame: ImageProxy, params: Array<Any>): Any? {
-
-        val result = WritableNativeMap()
-
-        val recognizer = TextRecognition.getClient(TextRecognizerOptions.DEFAULT_OPTIONS)
-
-        @SuppressLint("UnsafeOptInUsageError")
-        val mediaImage: Image? = frame.getImage()
-
-        if (mediaImage != null) {
-            val image = InputImage.fromMediaImage(mediaImage, frame.imageInfo.rotationDegrees)
-            val task: Task<Text> = recognizer.process(image)
-            try {
-                val text: Text = Tasks.await<Text>(task)
-                result.putString("text", text.text)
-                result.putArray("blocks", getBlockArray(text.textBlocks))
-            } catch (e: Exception) {
-                return null
-            }
-        }
-
-        val data = WritableNativeMap()
-        data.putMap("result", result)
-        return data
-    }
-}
+ package com.visioncameraocr
+
+ import android.annotation.SuppressLint
+ import android.graphics.Point
+ import android.graphics.Rect
+ import android.media.Image
+ import com.google.android.gms.tasks.Task
+ import com.google.android.gms.tasks.Tasks
+ import com.google.mlkit.vision.common.InputImage
+ import com.google.mlkit.vision.text.Text
+ import com.google.mlkit.vision.text.TextRecognition
+ import com.google.mlkit.vision.text.latin.TextRecognizerOptions
+
+
+ import com.mrousavy.camera.frameprocessor.Frame
+ import com.mrousavy.camera.frameprocessor.FrameProcessorPlugin
+ import com.mrousavy.camera.types.Orientation
+
+ class OCRFrameProcessorPlugin(options: MutableMap<String, Any>?) : FrameProcessorPlugin(options) {
+
+     private fun getBlockArray(blocks: MutableList<Text.TextBlock>): List<HashMap<String, Any?>> {
+         val blockArray = mutableListOf<HashMap<String, Any?>>()
+
+         for (block in blocks) {
+             val blockMap = HashMap<String, Any?>()
+
+             blockMap["text"] = block.text
+             blockMap["recognizedLanguages"] = getRecognizedLanguages(block.recognizedLanguage)
+             blockMap["cornerPoints"] = block.cornerPoints?.let { getCornerPoints(it) }
+             blockMap["frame"] = block.boundingBox?.let { getFrame(it) }
+             blockMap["boundingBox"] = block.boundingBox?.let { getBoundingBox(it) }
+             blockMap["lines"] = getLineArray(block.lines)
+
+             blockArray.add(blockMap)
+         }
+         return blockArray
+     }
+
+     private fun getLineArray(lines: MutableList<Text.Line>): List<HashMap<String, Any?>> {
+         val lineArray = mutableListOf<HashMap<String, Any?>>()
+
+         for (line in lines) {
+             val lineMap = hashMapOf<String, Any?>()
+
+             lineMap["text"] = line.text
+             lineMap["recognizedLanguages"] = getRecognizedLanguages(line.recognizedLanguage)
+             lineMap["cornerPoints"] = line.cornerPoints?.let { getCornerPoints(it) }
+             lineMap["frame"] = line.boundingBox?.let { getFrame(it)  }
+             lineMap["boundingBox"] = line.boundingBox?.let { getBoundingBox(it) }
+             lineMap["elements"] = getElementArray(line.elements)
+
+             lineArray.add(lineMap)
+         }
+         return lineArray
+     }
+
+     private fun getElementArray(elements: MutableList<Text.Element>): List<HashMap<String, Any?>> {
+         val elementArray = mutableListOf<HashMap<String, Any?>>()
+
+         for (element in elements) {
+             val elementMap = hashMapOf<String, Any?>()
+
+             elementMap["text"] = element.text
+             elementMap["cornerPoints"] = element.cornerPoints?.let { getCornerPoints(it) }
+             elementMap["frame"] =  element.boundingBox?.let { getFrame(it)  }
+             elementMap["boundingBox"] = element.boundingBox?.let { getBoundingBox(it) }
+             elementArray.add(elementMap)
+
+         }
+         return elementArray
+     }
+
+     private fun getRecognizedLanguages(recognizedLanguage: String): List<String> {
+         return  listOf(recognizedLanguage)
+     }
+
+     private fun getCornerPoints(points: Array<Point>): List<HashMap<String, Int>> {
+         val cornerPoints = mutableListOf<HashMap<String, Int>>()
+
+         for (point in points) {
+             val pointMap = hashMapOf<String, Int>()
+             pointMap["x"] = point.x
+             pointMap["y"] = point.y
+             cornerPoints.add(pointMap)
+         }
+         return cornerPoints
+     }
+
+     private fun getFrame(boundingBox: Rect?): HashMap<String, Any> {
+         val frame = hashMapOf<String, Any>()
+
+         if (boundingBox != null) {
+             frame["x"] = boundingBox.exactCenterX().toDouble()
+             frame["y"] = boundingBox.exactCenterY().toDouble()
+             frame["width"] = boundingBox.width()
+             frame["height"] = boundingBox.height()
+             frame["boundingCenterX"] = boundingBox.centerX()
+             frame["boundingCenterY"] = boundingBox.centerY()
+         }
+         return frame
+     }
+
+     private fun getBoundingBox(boundingBox: Rect?): HashMap<String, Any> {
+         val box = hashMapOf<String,Any>()
+
+         if (boundingBox != null) {
+             box["left"] = boundingBox.left
+             box["top"] = boundingBox.top
+             box["right"] = boundingBox.right
+             box["bottom"] = boundingBox.bottom
+         }
+
+         return box
+     }
+
+     override fun callback(frame: Frame, params: Map<String, Any>?): Any? {
+         val result = hashMapOf<String, Any>()
+
+         val recognizer = TextRecognition.getClient(TextRecognizerOptions.DEFAULT_OPTIONS)
+
+         @SuppressLint("UnsafeOptInUsageError")
+         val mediaImage: Image? = frame.image
+         val orientation = Orientation.fromUnionValue(frame.orientation)
+
+         if (mediaImage != null && orientation!= null) {
+             val image = InputImage.fromMediaImage(mediaImage, orientation.toDegrees())
+             val task: Task<Text> = recognizer.process(image)
+             try {
+                 val text: Text = Tasks.await(task)
+                 result["text"] = text.text
+                 result["blocks"] = getBlockArray(text.textBlocks)
+             } catch (e: Exception) {
+                 return null
+             }
+         }
+
+         return hashMapOf("result" to result)
+     }
+ }