feat: add screenshot OCR extraction

This commit is contained in:
2026-07-08 00:42:49 +08:00
parent 18a9f53062
commit 273af6a429
14 changed files with 1407 additions and 46 deletions
+57
View File
@@ -0,0 +1,57 @@
package application
import (
"context"
"fmt"
"strings"
"github.com/mmmy/snapgo/internal/infrastructure/clipboard"
)
// OCRRecognizer describes a provider capable of extracting text from a PNG
// screenshot.
type OCRRecognizer interface {
RecognizeText(ctx context.Context, pngBytes []byte) (string, error)
}
// CaptureOCRService wires screenshot bytes -> OCR provider -> clipboard. It
// leaves progress reporting to the caller so native and web overlays can share
// the same status HUD.
type CaptureOCRService struct {
Recognizer OCRRecognizer
Clipboard clipboard.Writer
}
// Recognize asks the configured OCR provider to extract text from the PNG.
func (s *CaptureOCRService) Recognize(ctx context.Context, pngBytes []byte) (string, error) {
if s.Recognizer == nil {
return "", fmt.Errorf("ocr is not configured")
}
if len(pngBytes) == 0 {
return "", fmt.Errorf("empty screenshot")
}
text, err := s.Recognizer.RecognizeText(ctx, pngBytes)
if err != nil {
return "", err
}
text = strings.TrimSpace(text)
if text == "" {
return "", fmt.Errorf("ocr result is empty")
}
return text, nil
}
// CopyText writes the extracted text to the clipboard.
func (s *CaptureOCRService) CopyText(_ context.Context, text string) error {
text = strings.TrimSpace(text)
if text == "" {
return fmt.Errorf("empty ocr text")
}
if s.Clipboard == nil {
return fmt.Errorf("clipboard is not configured")
}
if err := s.Clipboard.WriteText(text); err != nil {
return fmt.Errorf("clipboard write failed: %w", err)
}
return nil
}
+50
View File
@@ -0,0 +1,50 @@
package application
import (
"context"
"testing"
)
type fakeOCRRecognizer struct {
image []byte
text string
}
func (f *fakeOCRRecognizer) RecognizeText(_ context.Context, pngBytes []byte) (string, error) {
f.image = append([]byte(nil), pngBytes...)
if f.text == "" {
return "extracted text", nil
}
return f.text, nil
}
func TestCaptureOCRServiceRecognizesAndCopies(t *testing.T) {
ctx := context.Background()
recognizer := &fakeOCRRecognizer{}
clip := &fakeClipboard{}
svc := &CaptureOCRService{Recognizer: recognizer, Clipboard: clip}
text, err := svc.Recognize(ctx, []byte("png"))
if err != nil {
t.Fatalf("recognize: %v", err)
}
if string(recognizer.image) != "png" {
t.Fatalf("expected screenshot bytes forwarded, got %q", string(recognizer.image))
}
if text != "extracted text" {
t.Fatalf("expected extracted text, got %q", text)
}
if err := svc.CopyText(ctx, text); err != nil {
t.Fatalf("copy text: %v", err)
}
if clip.text != "extracted text" {
t.Fatalf("expected ocr text copied, got %q", clip.text)
}
}
func TestCaptureOCRServiceRejectsEmptyResult(t *testing.T) {
svc := &CaptureOCRService{Recognizer: &fakeOCRRecognizer{text: " \n "}}
if _, err := svc.Recognize(context.Background(), []byte("png")); err == nil {
t.Fatalf("expected empty OCR result to fail")
}
}