Use xmllint to validate SIP manifests

Fixes #39

Switch from the internal `ValidateMetadata` activity which calls a
Python (xsdval.py) script to the `temporal-activities/xmlvalidate`
activity. xmlvalidate calls the xmllint C program to validate the SIP
manifest file against the XSD schema files included in the SIP.

- Import github.com/artefactual-sdps/temporal-activities/xmlvalidate
- Switch to xmlvalidate with the xmllint validator for validating the
  SIP metadata file
- Remove the internal "validate metadata" activivity
- Remove the sampledata directory containing the `xsdval.py` script,
  Arelda XSD files, and sample SIP

.dockerignore

@@ -1,6 +1,5 @@
 **
 !cmd
-!hack/sampledata/xsd
 !internal
 !go.mod
 !go.sum

Dockerfile

@@ -50,7 +50,6 @@ RUN addgroup -g ${GROUP_ID} -S preprocessing
 RUN adduser -u ${USER_ID} -S -D preprocessing preprocessing
 
 USER preprocessing
-COPY --from=build-preprocessing-worker --link /src/hack/sampledata/xsd/* /
 COPY --from=build-preprocessing-worker --link /out/preprocessing-worker /home/preprocessing/bin/preprocessing-worker
 RUN mkdir /home/preprocessing/shared
 

cmd/worker/workercmd/cmd.go

@@ -5,6 +5,7 @@ import (
 	"crypto/rand"
 
 	"github.com/artefactual-sdps/temporal-activities/bagcreate"
+	"github.com/artefactual-sdps/temporal-activities/xmlvalidate"
 	"github.com/go-logr/logr"
 	"go.artefactual.dev/tools/temporal"
 	temporalsdk_activity "go.temporal.io/sdk/activity"
@@ -89,8 +90,8 @@ func (m *Main) Run(ctx context.Context) error {
 		temporalsdk_activity.RegisterOptions{Name: activities.AddPREMISAgentName},
 	)
 	w.RegisterActivityWithOptions(
-		activities.NewValidateMetadata().Execute,
-		temporalsdk_activity.RegisterOptions{Name: activities.ValidateMetadataName},
+		xmlvalidate.New(xmlvalidate.NewXMLLintValidator()).Execute,
+		temporalsdk_activity.RegisterOptions{Name: xmlvalidate.Name},
 	)
 	w.RegisterActivityWithOptions(
 		activities.NewTransformSIP().Execute,

go.mod

@@ -3,7 +3,7 @@ module github.com/artefactual-sdps/preprocessing-sfa
 go 1.23.2
 
 require (
-	github.com/artefactual-sdps/temporal-activities v0.0.0-20240821162351-47302711bc7b
+	github.com/artefactual-sdps/temporal-activities v0.0.0-20241018212855-8ea34d29bdf4
 	github.com/beevik/etree v1.4.0
 	github.com/deckarep/golang-set/v2 v2.6.0
 	github.com/go-logr/logr v1.4.2

go.sum

@@ -13,8 +13,8 @@ cloud.google.com/go/iam v1.1.13/go.mod h1:K8mY0uSXwEXS30KrnVb+j54LB/ntfZu1dr+4zF
 cloud.google.com/go/storage v1.43.0 h1:CcxnSohZwizt4LCzQHWvBf1/kvtHUn7gk9QERXPyXFs=
 cloud.google.com/go/storage v1.43.0/go.mod h1:ajvxEa7WmZS1PxvKRq4bq0tFT3vMd502JwstCcYv0Q0=
 github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
-github.com/artefactual-sdps/temporal-activities v0.0.0-20240821162351-47302711bc7b h1:kTOc2pbkdII6/Z84Bus1q52z5KAOaT8vLpfRoOs1l1I=
-github.com/artefactual-sdps/temporal-activities v0.0.0-20240821162351-47302711bc7b/go.mod h1:FVh79rCGNlUU1QnioAU+lrSjLqrA1PJFYKIhWPsmyug=
+github.com/artefactual-sdps/temporal-activities v0.0.0-20241018212855-8ea34d29bdf4 h1:WF95IOkZRVSCST/26SAqPYsUrtUuJpavBht6lvdeKl0=
+github.com/artefactual-sdps/temporal-activities v0.0.0-20241018212855-8ea34d29bdf4/go.mod h1:FVh79rCGNlUU1QnioAU+lrSjLqrA1PJFYKIhWPsmyug=
 github.com/aws/aws-sdk-go v1.55.5 h1:KKUZBfBoyqy5d3swXyiC7Q76ic40rYcbqH7qjh59kzU=
 github.com/aws/aws-sdk-go v1.55.5/go.mod h1:eRwEWoyTWFMVYVQzKMNHWP5/RV4xIUGMQfXQHfHkpNU=
 github.com/aws/aws-sdk-go-v2 v1.30.3 h1:jUeBtG0Ih+ZIFH0F4UkmL9w3cSpaMv9tYYDbzILP8dY=