fix: prefer aggregate OCR text

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"];
@@ -25,7 +25,7 @@ export namespace application {
 	    static createFrom(source: any = {}) {
 	        return new Annotation(source);
 	    }
-
+	
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.tool = source["tool"];
@@ -35,7 +35,7 @@ export namespace application {
 	        this.strokeWidth = source["strokeWidth"];
 	        this.fontSize = source["fontSize"];
 	    }
-
+	
 		convertValues(a: any, classs: any, asMap: boolean = false): any {
 		    if (!a) {
 		        return a;
@@ -58,7 +58,7 @@ export namespace application {
 }
 
 export namespace domain {
-
+	
 	export class OCRProviderConfig {
 	    label: string;
 	    endpoint: string;
@@ -69,11 +69,11 @@ export namespace domain {
 	    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"];
@@ -90,17 +90,17 @@ export namespace domain {
 	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;
@@ -128,11 +128,11 @@ 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"];
@@ -149,18 +149,18 @@ 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;
@@ -189,11 +189,11 @@ 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"];
@@ -216,11 +216,11 @@ 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"];
@@ -240,11 +240,11 @@ export namespace domain {
 	    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"];
@@ -254,7 +254,7 @@ export namespace domain {
 	        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;
@@ -273,24 +273,24 @@ 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"];
@@ -302,11 +302,11 @@ 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"];
@@ -318,17 +318,17 @@ 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;
@@ -349,3 +349,4 @@ export namespace main {
 	}
 
 }
+

internal/infrastructure/ocr/client.go

@@ -264,6 +264,9 @@ func parseOCRText(data []byte) (string, error) {
 	if msg := responseError(root); msg != "" {
 		return "", errors.New(msg)
 	}
+	if text := normalizeOCRText(extractOverallOCRText(root, "")); text != "" {
+		return text, nil
+	}
 	parts := collectOCRParts(root, "")
 	if len(parts) == 0 {
 		return "", fmt.Errorf("no text found")
@@ -312,6 +315,62 @@ func responseError(v any) string {
 	return ""
 }
 
+func extractOverallOCRText(v any, parentKey string) string {
+	switch value := v.(type) {
+	case string:
+		text := strings.TrimSpace(value)
+		if text == "" {
+			return ""
+		}
+		if looksLikeJSON(text) {
+			var nested any
+			if err := json.Unmarshal([]byte(text), &nested); err == nil {
+				if nestedText := extractOverallOCRText(nested, parentKey); nestedText != "" {
+					return nestedText
+				}
+			}
+		}
+		if isAggregateContainerKey(parentKey) {
+			return text
+		}
+		return ""
+	case map[string]any:
+		for _, key := range aggregateTextKeys() {
+			if child, ok := value[key]; ok {
+				if text := extractOverallOCRText(child, key); text != "" {
+					return text
+				}
+			}
+		}
+		for _, key := range responseContainerKeys() {
+			if child, ok := value[key]; ok {
+				if text := extractOverallOCRText(child, key); text != "" {
+					return text
+				}
+			}
+		}
+		keys := make([]string, 0, len(value))
+		for key := range value {
+			keys = append(keys, key)
+		}
+		sort.Strings(keys)
+		for _, key := range keys {
+			if isAggregateTextKey(key) ||
+				isResponseContainerKey(key) ||
+				isBlockContainerKey(key) ||
+				isMetadataKey(key) {
+				continue
+			}
+			if text := extractOverallOCRText(value[key], key); text != "" {
+				return text
+			}
+		}
+		return ""
+	default:
+		return ""
+	}
+}
+
 func collectOCRParts(v any, parentKey string) []string {
 	switch value := v.(type) {
 	case string:
@@ -359,6 +418,36 @@ func collectOCRParts(v any, parentKey string) []string {
 	}
 }
 
+func aggregateTextKeys() []string {
+	return []string{
+		"content",
+		"Content",
+		"text",
+		"Text",
+		"full_text",
+		"FullText",
+		"fullText",
+		"plain_text",
+		"PlainText",
+		"plainText",
+		"recognized_text",
+		"RecognizedText",
+		"recognizedText",
+		"ocr_text",
+		"OCRText",
+		"ocrText",
+	}
+}
+
+func responseContainerKeys() []string {
+	return []string{
+		"Data",
+		"data",
+		"Result",
+		"result",
+	}
+}
+
 func priorityOCRKeys() []string {
 	return []string{
 		"Data",
@@ -394,6 +483,38 @@ func priorityOCRKeys() []string {
 	}
 }
 
+func isAggregateTextKey(key string) bool {
+	for _, item := range aggregateTextKeys() {
+		if item == key {
+			return true
+		}
+	}
+	return false
+}
+
+func isAggregateContainerKey(key string) bool {
+	return isAggregateTextKey(key) || isResponseContainerKey(key)
+}
+
+func isResponseContainerKey(key string) bool {
+	for _, item := range responseContainerKeys() {
+		if item == key {
+			return true
+		}
+	}
+	return false
+}
+
+func isBlockContainerKey(key string) bool {
+	switch normalizeKey(key) {
+	case "wordsresult", "prismwordsinfo", "prismwords", "ocrinfos", "items",
+		"blocks", "regions", "words", "linetexts", "lines", "cells":
+		return true
+	default:
+		return false
+	}
+}
+
 func isPriorityOCRKey(key string) bool {
 	for _, item := range priorityOCRKeys() {
 		if item == key {
@@ -459,6 +580,18 @@ func dedupeNonEmpty(parts []string) []string {
 	return out
 }
 
+func normalizeOCRText(text string) string {
+	lines := strings.Split(strings.TrimSpace(text), "\n")
+	out := make([]string, 0, len(lines))
+	for _, line := range lines {
+		line = strings.TrimSpace(line)
+		if line != "" {
+			out = append(out, line)
+		}
+	}
+	return strings.Join(out, "\n")
+}
+
 func looksLikeJSON(text string) bool {
 	return strings.HasPrefix(text, "{") || strings.HasPrefix(text, "[")
 }

internal/infrastructure/ocr/client_test.go

@@ -142,6 +142,33 @@ func TestParseOCRTextSupportsWordsResult(t *testing.T) {
 	}
 }
 
+func TestParseOCRTextPrefersOverallContentOverBlocks(t *testing.T) {
+	text, err := parseOCRText([]byte(`{
+		"Data": "{\"content\":\"整体识别文本\",\"prism_wordsInfo\":[{\"word\":\"整体\"},{\"word\":\"识别\"},{\"word\":\"文本\"}]}"
+	}`))
+	if err != nil {
+		t.Fatalf("parse ocr text: %v", err)
+	}
+	if text != "整体识别文本" {
+		t.Fatalf("expected overall content only, got %q", text)
+	}
+}
+
+func TestParseOCRTextPrefersResultTextOverWordsResult(t *testing.T) {
+	text, err := parseOCRText([]byte(`{
+		"Result": {
+			"text": "hello world",
+			"words_result": [{"words":"hello"},{"words":"world"}]
+		}
+	}`))
+	if err != nil {
+		t.Fatalf("parse ocr text: %v", err)
+	}
+	if text != "hello world" {
+		t.Fatalf("expected result text only, got %q", text)
+	}
+}
+
 func TestParseOCRTextReturnsProviderError(t *testing.T) {
 	_, err := parseOCRText([]byte(`{"ResponseMetadata":{"Error":{"Code":"BadRequest","Message":"bad image"}}}`))
 	if err == nil || !strings.Contains(err.Error(), "bad image") {