Discover jobs/hooks in find images and diff git repo patches (#1645)

## Description

Implements hook discovery for images and shows changes from patch-git.

## Related Issue

Fixes #1246 
Relates to #1625 

## Type of change

- [X] Bug fix (non-breaking change which fixes an issue)
- [ ] New feature (non-breaking change which adds functionality)
- [X] Other (security config, docs update, etc)

## Checklist before merging

- [ ] Test, docs, adr added or updated as needed
- [X] [Contributor Guide
Steps](https://github.com/defenseunicorns/zarf/blob/main/CONTRIBUTING.md#developer-workflow)
followed

go.mod

@@ -33,6 +33,7 @@ require (
 	github.com/otiai10/copy v1.11.0
 	github.com/pkg/errors v0.9.1
 	github.com/pterm/pterm v0.12.59
+	github.com/sergi/go-diff v1.3.1
 	github.com/sigstore/cosign v1.13.1
 	github.com/spf13/cobra v1.7.0
 	github.com/spf13/viper v1.15.0
@@ -320,7 +321,6 @@ require (
 	github.com/scylladb/go-set v1.0.3-0.20200225121959-cc7b2070d91e // indirect
 	github.com/secure-systems-lab/go-securesystemslib v0.4.0 // indirect
 	github.com/segmentio/ksuid v1.0.4 // indirect
-	github.com/sergi/go-diff v1.3.1 // indirect
 	github.com/shibumi/go-pathspec v1.3.0 // indirect
 	github.com/shopspring/decimal v1.3.1 // indirect
 	github.com/sigstore/fulcio v0.6.0 // indirect

src/cmd/prepare.go

@@ -47,6 +47,9 @@ var prepareTransformGitLinks = &cobra.Command{
 		text := string(content)
 		processedText := transform.MutateGitURLsInText(pkgConfig.InitOpts.GitServer.Address, text, pkgConfig.InitOpts.GitServer.PushUsername)
 
+		// Print the differences
+		message.PrintDiff(text, processedText)
+
 		// Ask the user before this destructive action
 		confirm := false
 		prompt := &survey.Confirm{

src/internal/packager/helm/chart.go

@@ -182,9 +182,15 @@ func (h *Helm) TemplateChart() (string, error) {
 		return "", fmt.Errorf("error generating helm chart template: %w", err)
 	}
 
+	manifest := templatedChart.Manifest
+
+	for _, hook := range templatedChart.Hooks {
+		manifest += fmt.Sprintf("\n---\n%s", hook.Manifest)
+	}
+
 	spinner.Success()
 
-	return templatedChart.Manifest, nil
+	return manifest, nil
 }
 
 // GenerateChart generates a helm chart for a given Zarf manifest.

src/pkg/message/message.go

@@ -15,6 +15,7 @@ import (
 	"time"
 
 	"github.com/pterm/pterm"
+	"github.com/sergi/go-diff/diffmatchpatch"
 )
 
 // LogLevel is the level of logging to display.
@@ -243,6 +244,17 @@ func Paragraphn(n int, format string, a ...any) string {
 	return pterm.DefaultParagraph.WithMaxWidth(n).Sprintf(format, a...)
 }
 
+// PrintDiff prints the differences between a and b with a as original and b as new
+func PrintDiff(textA, textB string) {
+	dmp := diffmatchpatch.New()
+
+	diffs := dmp.DiffMain(textA, textB, true)
+
+	diffs = dmp.DiffCleanupSemantic(diffs)
+
+	pterm.Println(dmp.DiffPrettyText(diffs))
+}
+
 func debugPrinter(offset int, a ...any) {
 	printer := pterm.Debug.WithShowLineNumber(logLevel > 2).WithLineNumberOffset(offset)
 	now := time.Now().Format(time.RFC3339)

src/pkg/packager/prepare.go

@@ -20,6 +20,7 @@ import (
 	"github.com/defenseunicorns/zarf/src/types"
 	"github.com/google/go-containerregistry/pkg/crane"
 	v1 "k8s.io/api/apps/v1"
+	batchv1 "k8s.io/api/batch/v1"
 	"k8s.io/apimachinery/pkg/apis/meta/v1/unstructured"
 	"k8s.io/apimachinery/pkg/runtime"
 )
@@ -58,7 +59,7 @@ func (p *Packager) FindImages(baseDir, repoHelmChartPath string) error {
 		}
 	}
 
-	fmt.Printf("components:\n")
+	componentDefinition := "\ncomponents:\n"
 
 	for _, component := range p.cfg.Pkg.Components {
 
@@ -204,36 +205,38 @@ func (p *Packager) FindImages(baseDir, repoHelmChartPath string) error {
 
 		if sortedImages := k8s.SortImages(matchedImages, nil); len(sortedImages) > 0 {
 			// Log the header comment
-			fmt.Printf("\n  - name: %s\n    images:\n", component.Name)
+			componentDefinition += fmt.Sprintf("\n  - name: %s\n    images:\n", component.Name)
 			for _, image := range sortedImages {
 				// Use print because we want this dumped to stdout
-				fmt.Println("      - " + image)
+				componentDefinition += fmt.Sprintf("      - %s\n", image)
 			}
 		}
 
 		// Handle the "maybes"
 		if sortedImages := k8s.SortImages(maybeImages, matchedImages); len(sortedImages) > 0 {
-			var realImages []string
+			var validImages []string
 			for _, image := range sortedImages {
 				if descriptor, err := crane.Head(image, config.GetCraneOptions(config.CommonOptions.Insecure)...); err != nil {
 					// Test if this is a real image, if not just quiet log to debug, this is normal
 					message.Debugf("Suspected image does not appear to be valid: %#v", err)
 				} else {
 					// Otherwise, add to the list of images
 					message.Debugf("Imaged digest found: %s", descriptor.Digest)
-					realImages = append(realImages, image)
+					validImages = append(validImages, image)
 				}
 			}
 
-			if len(realImages) > 0 {
-				fmt.Printf("      # Possible images - %s - %s\n", p.cfg.Pkg.Metadata.Name, component.Name)
-				for _, image := range realImages {
-					fmt.Println("      - " + image)
+			if len(validImages) > 0 {
+				componentDefinition += fmt.Sprintf("      # Possible images - %s - %s\n", p.cfg.Pkg.Metadata.Name, component.Name)
+				for _, image := range validImages {
+					componentDefinition += fmt.Sprintf("      - %s\n", image)
 				}
 			}
 		}
 	}
 
+	fmt.Println(componentDefinition)
+
 	// In case the directory was changed, reset to prevent breaking relative target paths
 	if originalDir != "" {
 		_ = os.Chdir(originalDir)
@@ -244,7 +247,7 @@ func (p *Packager) FindImages(baseDir, repoHelmChartPath string) error {
 
 func (p *Packager) processUnstructured(resource *unstructured.Unstructured, matchedImages, maybeImages k8s.ImageMap) (k8s.ImageMap, k8s.ImageMap, error) {
 	var imageSanityCheck = regexp.MustCompile(`(?mi)"image":"([^"]+)"`)
-	var imageFuzzyCheck = regexp.MustCompile(`(?mi)"([a-z0-9\-./]+:[\w][\w.\-]{0,127})"`)
+	var imageFuzzyCheck = regexp.MustCompile(`(?mi)"([a-z0-9\-.\/]+:[\w][\w.\-]{0,127})"`)
 	var json string
 
 	contents := resource.UnstructuredContent()
@@ -282,6 +285,13 @@ func (p *Packager) processUnstructured(resource *unstructured.Unstructured, matc
 		}
 		matchedImages = k8s.BuildImageMap(matchedImages, replicaSet.Spec.Template.Spec)
 
+	case "Job":
+		var job batchv1.Job
+		if err := runtime.DefaultUnstructuredConverter.FromUnstructured(contents, &job); err != nil {
+			return matchedImages, maybeImages, fmt.Errorf("could not parse job: %w", err)
+		}
+		matchedImages = k8s.BuildImageMap(matchedImages, job.Spec.Template.Spec)
+
 	default:
 		// Capture any custom images
 		matches := imageSanityCheck.FindAllStringSubmatch(json, -1)

src/pkg/transform/git.go

@@ -18,7 +18,7 @@ var gitURLRegex = regexp.MustCompile(`^(?P<proto>[a-z]+:\/\/)(?P<hostPath>.+?)\/
 
 // MutateGitURLsInText changes the gitURL hostname to use the repository Zarf is configured to use.
 func MutateGitURLsInText(targetBaseURL string, text string, pushUser string) string {
-	extractPathRegex := regexp.MustCompilePOSIX(`https?://[^/]+/(.*\.git)`)
+	extractPathRegex := regexp.MustCompile(`[a-z]+:\/\/[^\/]+\/(.*\.git)`)
 	output := extractPathRegex.ReplaceAllStringFunc(text, func(match string) string {
 		output, err := GitTransformURL(targetBaseURL, match, pushUser)
 		if err != nil {

src/pkg/transform/git_test.go

@@ -46,8 +46,8 @@ func TestMutateGitURLsInText(t *testing.T) {
 	# We transform https://*/*.git URLs
 	https://github.com/defenseunicorns/zarf.git
 	# Even URLs with things on either side
-	stuffhttps://github.com/defenseunicorns/zarf.gitandthings
-	# But not ssh://*/*.git URLs
+	stuff https://github.com/defenseunicorns/zarf.git andthings
+	# Including ssh://*/*.git URLs
 	ssh://[email protected]/defenseunicorns/zarf.git
 	# Or non .git URLs
 	https://www.defenseunicorns.com/
@@ -58,9 +58,9 @@ func TestMutateGitURLsInText(t *testing.T) {
 	# We transform https://*/*.git URLs
 	https://gitlab.com/repo-owner/zarf-1211668992.git
 	# Even URLs with things on either side
-	stuffhttps://gitlab.com/repo-owner/zarf-1211668992.gitandthings
-	# But not ssh://*/*.git URLs
-	ssh://git@github.com/defenseunicorns/zarf.git
+	stuff https://gitlab.com/repo-owner/zarf-1211668992.git andthings
+	# Including ssh://*/*.git URLs
+	https://gitlab.com/repo-owner/zarf-2566185087.git
 	# Or non .git URLs
 	https://www.defenseunicorns.com/
 	`