Skip to content

check similarity on duplicate handling #17

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
weoses merged 1 commit into from
Apr 30, 2025
Merged

check similarity on duplicate handling #17

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions storage-service/src/go.mod
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@ require (
)

require (
github.com/adrg/strutil v0.3.1 // indirect
github.com/dustin/go-humanize v1.0.1 // indirect
github.com/elastic/elastic-transport-go/v8 v8.6.0 // indirect
github.com/gabriel-vasile/mimetype v1.4.8 // indirect
Expand Down
2 changes: 2 additions & 0 deletions storage-service/src/go.sum
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,5 @@
github.com/adrg/strutil v0.3.1 h1:OLvSS7CSJO8lBii4YmBt8jiK9QOtB9CzCzwl4Ic/Fz4=
github.com/adrg/strutil v0.3.1/go.mod h1:8h90y18QLrs11IBffcGX3NW/GFBXCMcNg4M7H6MspPA=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
Expand Down
26 changes: 21 additions & 5 deletions storage-service/src/service/ApiHandlerService.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,12 @@ import (
"context"
"errors"
"fmt"
"github.com/adrg/strutil/metrics"
"log/slog"
"strings"
"time"

"github.com/adrg/strutil"
"github.com/gdexlab/go-render/render"
"github.com/go-playground/validator/v10"
"github.com/google/uuid"
Expand Down Expand Up @@ -74,22 +76,36 @@ func (a *ApiHandler) CreateMeme(
return nil, fmt.Errorf("failed to do ocr : %w", err)
}

ocrTextResult := ocrResult.OcrText
slog.Info("CreateMeme: ocr result",
commonconst.ACCOUNTID_LOG, request.AccountId,
"id", idUuid,
"ocrText", ocrResult.OcrText)
"ocrText", ocrTextResult)

contentDuplicate, err := a.findContentDuplicates(ctx, ocrResult)
if err != nil {
return nil, err
}

if contentDuplicate != nil {
return a.HandleDuplicate(ctx, server.DuplicateImage, contentDuplicate, request)
if strings.TrimSpace(ocrTextResult) == "" {
return nil, errors.New("no text on image")
}

if strings.TrimSpace(ocrResult.OcrText) == "" {
return nil, errors.New("no text on image")
if contentDuplicate != nil {
contentDuplicateTextResult := contentDuplicate.Result
similarity := strutil.Similarity(ocrTextResult, contentDuplicateTextResult, metrics.NewLevenshtein())

slog.Info("CreateMeme: found content-duplicate by embedding search",
commonconst.ACCOUNTID_LOG, request.AccountId,
"id", idUuid,
"dupId", contentDuplicate.ImageId,
"ocrText", ocrTextResult,
"dupOcrText", contentDuplicate.Result,
"similarity", similarity)

if similarity > 0.5 {
return a.HandleDuplicate(ctx, server.DuplicateImage, contentDuplicate, request)
}
}

err = a.imageStorage.Save(ctx, idUuid, ocrResult.Image, ocrResult.Thumbnail.Image)
Expand Down
Loading