MythEclipse/asepharyana-hub
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat(infra): add tools service with document scanner, image & PDF tools

Browse Source 
Implement self-hosted document scanner and media processing tools as
an alternative to CamScanner/ilovepdf without third-party uploads.

Backend: Rust Axum gateway + worker pool with NATS JetStream queue
Frontend: Next.js 16 + shadcn/ui + Tailwind v4 + Framer Motion
Pipeline: Canny edge detection -> DLT homography warp -> Sauvola
binarization -> Hough deskew -> Tesseract OCR -> searchable PDF

Phase 1 (MVP) delivers:
- Document scanner with perspective correction and OCR
- Image compress/resize/convert tools
- PDF merge/split/compress tools
- Real-time WebSocket progress updates
- Rate limiting, auto-cleanup, Prometheus metrics
- Full CI/CD pipeline with Docker multi-stage build

Co-Authored-By: Kilo <kilo@kilo.ai>
This commit is contained in:
asepharyana
2026-07-24 13:08:09 +07:00
co-authored by Kilo
parent 9c12d135e4
commit 67288c8723
102 changed files with 11527 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/deploy-docker.yml
+1 -1
View File
@@ -89,7 +89,7 @@ jobs:
git fetch origin main --depth=1 || true
# Detect changed files before resetting
ALL_COMPOSE_FILES="infra/compose/traefik.yml infra/compose/shared.yml infra/compose/scraper.yml infra/compose/hub.yml infra/compose/nats.yml infra/compose/dapr.yml infra/compose/observability.yml"
ALL_COMPOSE_FILES="infra/compose/traefik.yml infra/compose/shared.yml infra/compose/scraper.yml infra/compose/hub.yml infra/compose/tools.yml infra/compose/nats.yml infra/compose/dapr.yml infra/compose/observability.yml"
TRAEFIK_DYNAMIC_DIR="infra/traefik/dynamic"
if git rev-parse HEAD >/dev/null 2>&1; then
.github/workflows/docker-build-push.yml
+11 -2
View File
@@ -7,6 +7,7 @@ on:
paths:
- 'apps/scraper/**'
- 'apps/hub/**'
- 'apps/tools/**'
- '.github/workflows/docker-build-push.yml'
- 'infra/**'
- '!infra/compose/**'
@@ -36,6 +37,7 @@ jobs:
matrix: ${{ steps.set-matrix.outputs.matrix }}
scraper-api: ${{ steps.filter.outputs['scraper-api'] == 'true' || steps.dispatch.outputs['scraper-api'] == 'true' || github.event_name == 'workflow_dispatch' }}
hub: ${{ steps.filter.outputs['hub'] == 'true' || steps.dispatch.outputs['hub'] == 'true' || github.event_name == 'workflow_dispatch' }}
tools: ${{ steps.filter.outputs['tools'] == 'true' || steps.dispatch.outputs['tools'] == 'true' || github.event_name == 'workflow_dispatch' }}
steps:
- uses: actions/checkout@v7
with:
@@ -63,6 +65,7 @@ jobs:
echo "scraper-api=$(changed '^(apps/scraper(/|$)|\.github/workflows/docker-build-push\.yml$|infra/docker/scraper\.Dockerfile$)')" >> "$GITHUB_OUTPUT"
echo "hub=$(changed '^(apps/hub(/|$)|\.github/workflows/docker-build-push\.yml$|infra/docker/hub\.Dockerfile$)')" >> "$GITHUB_OUTPUT"
echo "tools=$(changed '^(apps/tools(/|$)|\.github/workflows/docker-build-push\.yml$|infra/docker/tools\.Dockerfile$)')" >> "$GITHUB_OUTPUT"
- name: Parse repository_dispatch payload
id: dispatch
@@ -84,7 +87,7 @@ jobs:
fi
case "$SERVICE" in
scraper-api|hub) ;;
scraper-api|hub|tools) ;;
*)
exit 1
;;
@@ -92,7 +95,7 @@ jobs:
if ! [[ "$SHA" =~ ^[0-9a-fA-F]{40}$ ]]; then echo "::error::Invalid sha '$SHA'. Expected 40 hex characters"; fi
SERVICES=(scraper-api hub)
SERVICES=(scraper-api hub tools)
for svc in "${SERVICES[@]}"; do
if [ "$SERVICE" = "$svc" ]; then
echo "${svc}=true" >> "$GITHUB_OUTPUT"
@@ -111,6 +114,7 @@ jobs:
if [ "${{ steps.filter.outputs['scraper-api'] == 'true' || steps.dispatch.outputs['scraper-api'] == 'true' || github.event_name == 'workflow_dispatch' }}" == "true" ]; then add_service "scraper-api" "docker-scraper" "apps/scraper"; fi
if [ "${{ steps.filter.outputs['hub'] == 'true' || steps.dispatch.outputs['hub'] == 'true' || github.event_name == 'workflow_dispatch' }}" == "true" ]; then add_service "hub" "docker-hub" "apps/hub"; fi
if [ "${{ steps.filter.outputs['tools'] == 'true' || steps.dispatch.outputs['tools'] == 'true' || github.event_name == 'workflow_dispatch' }}" == "true" ]; then add_service "tools" "docker-tools" "apps/tools"; fi
JSON_ARRAY="[$(IFS=,; echo "${SERVICES[*]}")]"
echo "matrix=$JSON_ARRAY" >> $GITHUB_OUTPUT
@@ -131,6 +135,7 @@ jobs:
case "$SERVICE" in
"scraper-api") REPO="https://github.com/asepharyana/asepharyana-hub-scraper.git" ;;
"hub") REPO="https://github.com/asepharyana/asepharyana-hub-hub.git" ;;
"tools") echo "tools is built from monorepo, no submodule wait needed"; exit 0 ;;
*)
echo "::error::Unsupported service '$SERVICE'"
exit 1
@@ -213,6 +218,7 @@ jobs:
case "$SVC_NAME" in
"scraper-api") echo "dockerfile=infra/docker/scraper.Dockerfile" >> $GITHUB_OUTPUT ;;
"hub") echo "dockerfile=infra/docker/hub.Dockerfile" >> $GITHUB_OUTPUT ;;
"tools") echo "dockerfile=infra/docker/tools.Dockerfile" >> $GITHUB_OUTPUT ;;
esac
- name: Build and Push Docker image
@@ -258,10 +264,12 @@ jobs:
declare -A SERVICES
SERVICES["scraper-api"]="scraper.yml"
SERVICES["hub"]="hub.yml"
SERVICES["tools"]="tools.yml"
declare -A PATHS
PATHS["scraper-api"]="apps/scraper"
PATHS["hub"]="apps/hub"
PATHS["tools"]="apps/tools"
# Use git config for possible commits
git config --local user.email "action@github.com"
@@ -271,6 +279,7 @@ jobs:
SHOULD_HAVE_RUN=false
if [ "${{ needs.changes.outputs['scraper-api'] }}" == "true" ] && [ "$id" == "scraper-api" ]; then SHOULD_HAVE_RUN=true; fi
if [ "${{ needs.changes.outputs['hub'] }}" == "true" ] && [ "$id" == "hub" ]; then SHOULD_HAVE_RUN=true; fi
if [ "${{ needs.changes.outputs['tools'] }}" == "true" ] && [ "$id" == "tools" ]; then SHOULD_HAVE_RUN=true; fi
if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then SHOULD_HAVE_RUN=true; fi