mirror of
https://github.com/hanzoai/extract-svc.git
synced 2026-10-30 18:36:53 +00:00
Replaces Huly's rekoni service. Native PDF/DOCX/XLSX/PPTX/HTML/RTF/ Markdown/text extraction, IAM JWKS-verified bearer auth, 25 MB streaming upload cap, distroless image, port 4004. PNG/image OCR returns 415 in v0.1 — Tesseract bindings deferred. Module path: github.com/hanzoai/extract-svc (the canonical hanzoai/extract slot belongs to the Rust extraction crate).
85 lines
2.0 KiB
Go
85 lines
2.0 KiB
Go
// Single binary entrypoint. Listens on $PORT (default 4004 — same as
|
|
// Huly's rekoni used, so dropping this in place needs no front-end
|
|
// rewiring) and serves the /v1/* surface.
|
|
package main
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"fmt"
|
|
"log/slog"
|
|
"net/http"
|
|
"os"
|
|
"os/signal"
|
|
"strings"
|
|
"syscall"
|
|
"time"
|
|
|
|
"github.com/hanzoai/extract-svc/pkg/auth"
|
|
"github.com/hanzoai/extract-svc/pkg/server"
|
|
)
|
|
|
|
// Version is overridden via -ldflags="-X main.Version=v0.1.0" at build time.
|
|
var Version = "v0.1.0-dev"
|
|
|
|
func main() {
|
|
if len(os.Args) > 1 && (os.Args[1] == "--version" || os.Args[1] == "-v") {
|
|
fmt.Println(Version)
|
|
return
|
|
}
|
|
logger := slog.New(slog.NewJSONHandler(os.Stdout, &slog.HandlerOptions{
|
|
Level: slog.LevelInfo,
|
|
}))
|
|
slog.SetDefault(logger)
|
|
|
|
addr := envOr("LISTEN_ADDR", ":4004")
|
|
jwks := envOr("IAM_JWKS_URL", auth.DefaultJWKSURL)
|
|
logger.Info("starting extract",
|
|
"version", Version, "addr", addr, "jwks", jwks)
|
|
|
|
s := server.New(server.Config{
|
|
Version: Version,
|
|
JWKSURL: jwks,
|
|
Logger: logger,
|
|
})
|
|
|
|
srv := &http.Server{
|
|
Addr: addr,
|
|
Handler: s.Handler(),
|
|
ReadHeaderTimeout: 10 * time.Second,
|
|
// No write timeout: extraction of a 25 MB PDF can take a while.
|
|
// We bound work inside the handlers themselves (LimitReader,
|
|
// FetchTimeout).
|
|
}
|
|
|
|
errCh := make(chan error, 1)
|
|
go func() { errCh <- srv.ListenAndServe() }()
|
|
|
|
ctx, stop := signal.NotifyContext(context.Background(),
|
|
syscall.SIGINT, syscall.SIGTERM)
|
|
defer stop()
|
|
|
|
select {
|
|
case err := <-errCh:
|
|
if err != nil && !errors.Is(err, http.ErrServerClosed) {
|
|
logger.Error("server failed", "err", err)
|
|
os.Exit(1)
|
|
}
|
|
case <-ctx.Done():
|
|
logger.Info("shutting down")
|
|
shutdownCtx, cancel := context.WithTimeout(context.Background(), 15*time.Second)
|
|
defer cancel()
|
|
if err := srv.Shutdown(shutdownCtx); err != nil {
|
|
logger.Error("shutdown error", "err", err)
|
|
}
|
|
}
|
|
}
|
|
|
|
func envOr(k, def string) string {
|
|
if v := strings.TrimSpace(os.Getenv(k)); v != "" {
|
|
return v
|
|
}
|
|
return def
|
|
}
|
|
|