feat: add screenshot OCR extraction

frontend/wailsjs/go/main/App.d.ts

@@ -17,6 +17,10 @@ export function CopyNativeRegionImage(arg1:main.CaptureResult):Promise<void>;
 
 export function CopyRegionImage(arg1:main.CaptureResult):Promise<void>;
 
+export function ExtractTextNativeRegion(arg1:main.CaptureResult):Promise<void>;
+
+export function ExtractTextRegion(arg1:main.CaptureResult):Promise<void>;
+
 export function GetConfig():Promise<domain.AppConfig>;
 
 export function QuitApp():Promise<void>;

frontend/wailsjs/go/main/App.js

@@ -30,6 +30,14 @@ export function CopyRegionImage(arg1) {
   return window['go']['main']['App']['CopyRegionImage'](arg1);
 }
 
+export function ExtractTextNativeRegion(arg1) {
+  return window['go']['main']['App']['ExtractTextNativeRegion'](arg1);
+}
+
+export function ExtractTextRegion(arg1) {
+  return window['go']['main']['App']['ExtractTextRegion'](arg1);
+}
+
 export function GetConfig() {
   return window['go']['main']['App']['GetConfig']();
 }

frontend/wailsjs/go/models.ts

@@ -1,13 +1,13 @@
 export namespace application {
-	
+
 	export class Point {
 	    x: number;
 	    y: number;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new Point(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.x = source["x"];
@@ -19,11 +19,11 @@ export namespace application {
 	    color: string;
 	    points: Point[];
 	    text?: string;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new Annotation(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.tool = source["tool"];
@@ -31,7 +31,7 @@ export namespace application {
 	        this.points = this.convertValues(source["points"], Point);
 	        this.text = source["text"];
 	    }
-	
+
 		convertValues(a: any, classs: any, asMap: boolean = false): any {
 		    if (!a) {
 		        return a;
@@ -54,7 +54,67 @@ export namespace application {
 }
 
 export namespace domain {
-	
+
+	export class OCRProviderConfig {
+	    label: string;
+	    endpoint: string;
+	    accessKeyId: string;
+	    accessKeySecret: string;
+	    region: string;
+	    service: string;
+	    action: string;
+	    version: string;
+	    timeoutSecs: number;
+
+	    static createFrom(source: any = {}) {
+	        return new OCRProviderConfig(source);
+	    }
+
+	    constructor(source: any = {}) {
+	        if ('string' === typeof source) source = JSON.parse(source);
+	        this.label = source["label"];
+	        this.endpoint = source["endpoint"];
+	        this.accessKeyId = source["accessKeyId"];
+	        this.accessKeySecret = source["accessKeySecret"];
+	        this.region = source["region"];
+	        this.service = source["service"];
+	        this.action = source["action"];
+	        this.version = source["version"];
+	        this.timeoutSecs = source["timeoutSecs"];
+	    }
+	}
+	export class OCRConfig {
+	    activeProvider: string;
+	    providers: Record<string, OCRProviderConfig>;
+
+	    static createFrom(source: any = {}) {
+	        return new OCRConfig(source);
+	    }
+
+	    constructor(source: any = {}) {
+	        if ('string' === typeof source) source = JSON.parse(source);
+	        this.activeProvider = source["activeProvider"];
+	        this.providers = this.convertValues(source["providers"], OCRProviderConfig, true);
+	    }
+
+		convertValues(a: any, classs: any, asMap: boolean = false): any {
+		    if (!a) {
+		        return a;
+		    }
+		    if (a.slice && a.map) {
+		        return (a as any[]).map(elem => this.convertValues(elem, classs));
+		    } else if ("object" === typeof a) {
+		        if (asMap) {
+		            for (const key of Object.keys(a)) {
+		                a[key] = new classs(a[key]);
+		            }
+		            return a;
+		        }
+		        return new classs(a);
+		    }
+		    return a;
+		}
+	}
 	export class LLMProviderConfig {
 	    label: string;
 	    baseUrl: string;
@@ -64,11 +124,11 @@ export namespace domain {
 	    temperature: number;
 	    timeoutSecs: number;
 	    maxInlineBytes: number;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new LLMProviderConfig(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.label = source["label"];
@@ -85,18 +145,18 @@ export namespace domain {
 	    activeProvider: string;
 	    prompt: string;
 	    providers: Record<string, LLMProviderConfig>;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new LLMConfig(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.activeProvider = source["activeProvider"];
 	        this.prompt = source["prompt"];
 	        this.providers = this.convertValues(source["providers"], LLMProviderConfig, true);
 	    }
-	
+
 		convertValues(a: any, classs: any, asMap: boolean = false): any {
 		    if (!a) {
 		        return a;
@@ -125,11 +185,11 @@ export namespace domain {
 	    strictHostKey: boolean;
 	    knownHostsPath: string;
 	    connectTimeoutSecs: number;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new SSHConfig(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.host = source["host"];
@@ -152,11 +212,11 @@ export namespace domain {
 	    pathPrefix: string;
 	    publicUrlBase: string;
 	    usePathStyle: boolean;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new S3Config(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.endpoint = source["endpoint"];
@@ -175,11 +235,12 @@ export namespace domain {
 	    s3: S3Config;
 	    ssh: SSHConfig;
 	    llm: LLMConfig;
-	
+	    ocr: OCRConfig;
+
 	    static createFrom(source: any = {}) {
 	        return new AppConfig(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.hotkey = source["hotkey"];
@@ -187,8 +248,9 @@ export namespace domain {
 	        this.s3 = this.convertValues(source["s3"], S3Config);
 	        this.ssh = this.convertValues(source["ssh"], SSHConfig);
 	        this.llm = this.convertValues(source["llm"], LLMConfig);
+	        this.ocr = this.convertValues(source["ocr"], OCRConfig);
 	    }
-	
+
 		convertValues(a: any, classs: any, asMap: boolean = false): any {
 		    if (!a) {
 		        return a;
@@ -207,22 +269,24 @@ export namespace domain {
 		    return a;
 		}
 	}
-	
-	
-	
+
+
+
+
+
 
 }
 
 export namespace main {
-	
+
 	export class CaptureActionResult {
 	    completed: boolean;
 	    path?: string;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new CaptureActionResult(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.completed = source["completed"];
@@ -234,11 +298,11 @@ export namespace main {
 	    y: number;
 	    w: number;
 	    h: number;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new RegionRect(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.x = source["x"];
@@ -250,17 +314,17 @@ export namespace main {
 	export class CaptureResult {
 	    rect: RegionRect;
 	    annotations: application.Annotation[];
-	
+
 	    static createFrom(source: any = {}) {
 	        return new CaptureResult(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.rect = this.convertValues(source["rect"], RegionRect);
 	        this.annotations = this.convertValues(source["annotations"], application.Annotation);
 	    }
-	
+
 		convertValues(a: any, classs: any, asMap: boolean = false): any {
 		    if (!a) {
 		        return a;