Show prow build instead of deprecated travis

Add json6902 patch filter based on kyaml libraries

.golangci-kustomize.yml

@@ -7,8 +7,13 @@ linters:
     - bodyclose
     - deadcode
     - depguard
+    # - dogsled
     - dupl
+    # - errcheck
+    # - funlen
+    # - gochecknoinits
     - goconst
+    # - gocritic
     - gocyclo
     - gofmt
     - goimports
@@ -21,6 +26,7 @@ linters:
     - lll
     - misspell
     - nakedret
+    # - scopelint
     - staticcheck
     - structcheck
     # stylecheck demands that acronyms not be treated as words
@@ -28,9 +34,10 @@ linters:
     # - stylecheck
     - typecheck
     - unconvert
-    - unused
     - unparam
+    - unused
     - varcheck
+    # - whitespace
 
 linters-settings:
   dupl:

.travis.yml

@@ -1,43 +0,0 @@
-os:
-  - linux
-  - osx
-# TODO: Speed up the slowness of the osx travis runs
-# Maybe cache brew installs?
-#
-# TODO: Uncomment when some gets the tests running on Windows.
-#  - windows
-
-addons:
-  apt:
-    packages:
-    - tree
-  homebrew:
-    packages:
-    - tree
-    update: true
-
-# Only clone the most recent commit.
-git:
-  depth: 1
-
-language: go
-
-go:
-  - "1.13"
-
-go_import_path: sigs.k8s.io/kustomize
-
-before_install:
-  - source ./travis/consider-early-travis-exit.sh
-
-# Skip the install process; let pre-commit.sh do it.
-install: true
-
-script:
-  - make verify-kustomize
-  - ./travis/kyaml-pre-commit.sh
-  - ./travis/check-go-mod.sh
-
-# TBD. Suppressing for now.
-notifications:
-  email: false

Makefile

@@ -17,18 +17,30 @@ verify-kustomize: \
 	test-examples-kustomize-against-HEAD \
 	test-examples-kustomize-against-latest
 
+# The following target referenced by a file in
+# https://github.com/kubernetes/test-infra/tree/master/config/jobs/kubernetes-sigs/kustomize
+.PHONY: prow-presubmit-check
+prow-presubmit-check: \
+	lint-kustomize \
+	test-unit-kustomize-all \
+	test-unit-cmd-all \
+	test-go-mod
+
+.PHONY: verify-kustomize-e2e
+verify-kustomize-e2e: test-examples-e2e-kustomize
+
 # Other builds in this repo might want a different linter version.
 # Without one Makefile to rule them all, the different makes
 # cannot assume that golanci-lint is at the version they want
 # since everything uses the same implicit GOPATH.
 # This installs in a temp dir to avoid overwriting someone else's
 # linter, then installs in MYGOBIN with a new name.
-# Version pinned by api/go.mod
+# Version pinned by hack/go.mod
 $(MYGOBIN)/golangci-lint-kustomize:
 	( \
 		set -e; \
-		export GOBIN=$$(mktemp -d) \
-		cd api; \
+		export GOBIN=$$(mktemp -d); \
+		cd hack; \
 		GO111MODULE=on go install github.com/golangci/golangci-lint/cmd/golangci-lint; \
 		mv $$GOBIN/golangci-lint $(MYGOBIN)/golangci-lint-kustomize \
 	)
@@ -48,6 +60,11 @@ $(MYGOBIN)/goimports:
 	cd api; \
 	go install golang.org/x/tools/cmd/goimports
 
+# Install resource from whatever is checked out.
+$(MYGOBIN)/resource:
+	cd cmd/resource; \
+	go install .
+
 # To pin pluginator, use this recipe instead:
 #   cd api;
 #   go install sigs.k8s.io/kustomize/pluginator/v2
@@ -189,10 +206,26 @@ test-unit-kustomize-all: \
 	test-unit-kustomize-cli \
 	test-unit-kustomize-plugins
 
+test-unit-cmd-all:
+	./travis/kyaml-pre-commit.sh
+
+test-go-mod:
+	./travis/check-go-mod.sh
+
 .PHONY:
 test-examples-kustomize-against-HEAD: $(MYGOBIN)/kustomize $(MYGOBIN)/mdrip
 	./hack/testExamplesAgainstKustomize.sh HEAD
 
+.PHONY:
+test-examples-e2e-kustomize: $(MYGOBIN)/mdrip $(MYGOBIN)/kind
+	( \
+		set -e; \
+		/bin/rm -f $(MYGOBIN)/kustomize; \
+		echo "Installing kustomize from ."; \
+		cd kustomize; go install .; cd ..; \
+		./hack/testExamplesE2EAgainstKustomize.sh .; \
+	)
+
 .PHONY:
 test-examples-kustomize-against-latest: $(MYGOBIN)/mdrip
 	( \
@@ -237,6 +270,16 @@ $(MYGOBIN)/helm:
 		rm -rf $$d \
 	)
 
+$(MYGOBIN)/kind:
+	( \
+        set -e; \
+        d=$(shell mktemp -d); cd $$d; \
+        wget -O ./kind https://github.com/kubernetes-sigs/kind/releases/download/v0.7.0/kind-$(shell uname)-amd64; \
+        chmod +x ./kind; \
+        mv ./kind $(MYGOBIN); \
+        rm -rf $$d; \
+	)
+
 .PHONY: clean
 clean: kustomize-external-go-plugin-clean
 	go clean --cache

OWNERS_ALIASES

@@ -9,3 +9,4 @@ aliases:
     - mengqiy
     - monopole
     - pwittrock
+    - mortent

README.md

@@ -12,8 +12,7 @@ and it's like [`sed`], in that it emits edited text.
 This tool is sponsored by [sig-cli] ([KEP]), and
 inspired by [DAM].
 
-
-[![Build Status](https://travis-ci.org/kubernetes-sigs/kustomize.svg?branch=master)](https://travis-ci.org/kubernetes-sigs/kustomize)
+[![Build Status](https://prow.k8s.io/badge.svg?jobs=kustomize-presubmit-master)](https://prow.k8s.io/job-history/kubernetes-jenkins/pr-logs/directory/kustomize-presubmit-master)
 [![Go Report Card](https://goreportcard.com/badge/github.com/kubernetes-sigs/kustomize)](https://goreportcard.com/report/github.com/kubernetes-sigs/kustomize)
 
 Download a binary from the [release page], or see
@@ -107,7 +106,7 @@ Take the work from step (1) above, move it into a
 `someApp` subdirectory called `base`, then
 place overlays in a sibling directory.
 
-An overlay is just another kustomization, refering to
+An overlay is just another kustomization, referring to
 the base, and referring to patches to apply to that
 base.
 

api/builtins/AnnotationsTransformer.go

@@ -4,9 +4,11 @@
 package builtins
 
 import (
+	"sigs.k8s.io/kustomize/api/filters/annotations"
 	"sigs.k8s.io/kustomize/api/resmap"
 	"sigs.k8s.io/kustomize/api/transform"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/filtersutil"
 	"sigs.k8s.io/yaml"
 )
 
@@ -14,6 +16,10 @@ import (
 type AnnotationsTransformerPlugin struct {
 	Annotations map[string]string `json:"annotations,omitempty" yaml:"annotations,omitempty"`
 	FieldSpecs  []types.FieldSpec `json:"fieldSpecs,omitempty" yaml:"fieldSpecs,omitempty"`
+
+	// YAMLSupport can be set to true to use the kyaml filter instead of the
+	// kunstruct transformer
+	YAMLSupport bool `json:"yamlSupport,omitempty" yaml:"yamlSupport,omitempty"`
 }
 
 func (p *AnnotationsTransformerPlugin) Config(
@@ -24,14 +30,27 @@ func (p *AnnotationsTransformerPlugin) Config(
 }
 
 func (p *AnnotationsTransformerPlugin) Transform(m resmap.ResMap) error {
-	t, err := transform.NewMapTransformer(
-		p.FieldSpecs,
-		p.Annotations,
-	)
-	if err != nil {
-		return err
+	if p.YAMLSupport {
+		for _, r := range m.Resources() {
+			err := filtersutil.ApplyToJSON(annotations.Filter{
+				Annotations: p.Annotations,
+				FsSlice:     p.FieldSpecs,
+			}, r.Kunstructured)
+			if err != nil {
+				return err
+			}
+		}
+		return nil
+	} else {
+		t, err := transform.NewMapTransformer(
+			p.FieldSpecs,
+			p.Annotations,
+		)
+		if err != nil {
+			return err
+		}
+		return t.Transform(m)
 	}
-	return t.Transform(m)
 }
 
 func NewAnnotationsTransformerPlugin() resmap.TransformerPlugin {

api/builtins/ImageTagTransformer.go

@@ -144,8 +144,10 @@ func (p *ImageTagTransformerPlugin) findContainers(obj map[string]interface{}) e
 }
 
 func isImageMatched(s, t string) bool {
-	// Tag values are limited to [a-zA-Z0-9_.-].
-	pattern, _ := regexp.Compile("^" + t + "(@sha256)?(:[a-zA-Z0-9_.-]*)?$")
+	// Tag values are limited to [a-zA-Z0-9_.{}-].
+	// Some tools like Bazel rules_k8s allow tag patterns with {} characters.
+	// More info: https://github.com/bazelbuild/rules_k8s/pull/423
+	pattern, _ := regexp.Compile("^" + t + "(@sha256)?(:[a-zA-Z0-9_.{}-]*)?$")
 	return pattern.MatchString(s)
 }
 

api/builtins/NamespaceTransformer.go

@@ -6,12 +6,13 @@ package builtins
 import (
 	"fmt"
 
-	"sigs.k8s.io/kustomize/api/transform"
-
+	"sigs.k8s.io/kustomize/api/filters/namespace"
 	"sigs.k8s.io/kustomize/api/resid"
 	"sigs.k8s.io/kustomize/api/resmap"
 	"sigs.k8s.io/kustomize/api/resource"
+	"sigs.k8s.io/kustomize/api/transform"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/filtersutil"
 	"sigs.k8s.io/yaml"
 )
 
@@ -19,6 +20,11 @@ import (
 type NamespaceTransformerPlugin struct {
 	types.ObjectMeta `json:"metadata,omitempty" yaml:"metadata,omitempty" protobuf:"bytes,1,opt,name=metadata"`
 	FieldSpecs       []types.FieldSpec `json:"fieldSpecs,omitempty" yaml:"fieldSpecs,omitempty"`
+
+	// YAMLSupport can be set to true to use the kyaml filter instead of the
+	// kunstruct transformer.
+	// TODO: change the default to use kyaml when it is stable
+	YAMLSupport bool `json:"yamlSupport,omitempty" yaml:"yamlSupport,omitempty"`
 }
 
 func (p *NamespaceTransformerPlugin) Config(
@@ -39,12 +45,25 @@ func (p *NamespaceTransformerPlugin) Transform(m resmap.ResMap) error {
 		}
 
 		id := r.OrgId()
-		applicableFs := p.applicableFieldSpecs(id)
 
-		for _, fs := range applicableFs {
-			err := transform.MutateField(
-				r.Map(), fs.PathSlice(), fs.CreateIfNotPresent,
-				p.changeNamespace(r))
+		if !p.YAMLSupport {
+			// use the old style transform
+			applicableFs := p.applicableFieldSpecs(id)
+
+			for _, fs := range applicableFs {
+				err := transform.MutateField(
+					r.Map(), fs.PathSlice(), fs.CreateIfNotPresent,
+					p.changeNamespace(r))
+				if err != nil {
+					return err
+				}
+			}
+		} else {
+			// use the new style transform
+			err := filtersutil.ApplyToJSON(namespace.Filter{
+				Namespace: p.Namespace,
+				FsSlice:   p.FieldSpecs,
+			}, r.Kunstructured)
 			if err != nil {
 				return err
 			}
@@ -52,7 +71,7 @@ func (p *NamespaceTransformerPlugin) Transform(m resmap.ResMap) error {
 
 		matches := m.GetMatchingResourcesByCurrentId(r.CurId().Equals)
 		if len(matches) != 1 {
-			return fmt.Errorf("namespace tranformation produces ID conflict: %+v", matches)
+			return fmt.Errorf("namespace transformation produces ID conflict: %+v", matches)
 		}
 	}
 	return nil

api/builtins/PatchJson6902Transformer.go

@@ -8,10 +8,12 @@ import (
 
 	jsonpatch "github.com/evanphx/json-patch"
 	"github.com/pkg/errors"
+	"sigs.k8s.io/kustomize/api/filters/patchjson6902"
 	"sigs.k8s.io/kustomize/api/ifc"
 	"sigs.k8s.io/kustomize/api/resid"
 	"sigs.k8s.io/kustomize/api/resmap"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/filtersutil"
 	"sigs.k8s.io/yaml"
 )
 
@@ -21,6 +23,8 @@ type PatchJson6902TransformerPlugin struct {
 	Target       types.PatchTarget `json:"target,omitempty" yaml:"target,omitempty"`
 	Path         string            `json:"path,omitempty" yaml:"path,omitempty"`
 	JsonOp       string            `json:"jsonOp,omitempty" yaml:"jsonOp,omitempty"`
+
+	YAMLSupport bool `json:"yamlSupport,omitempty" yaml:"yamlSupport,omitempty"`
 }
 
 func (p *PatchJson6902TransformerPlugin) Config(
@@ -83,16 +87,22 @@ func (p *PatchJson6902TransformerPlugin) Transform(m resmap.ResMap) error {
 	if err != nil {
 		return err
 	}
-	rawObj, err := obj.MarshalJSON()
-	if err != nil {
-		return err
+	if !p.YAMLSupport {
+		rawObj, err := obj.MarshalJSON()
+		if err != nil {
+			return err
+		}
+		modifiedObj, err := p.decodedPatch.Apply(rawObj)
+		if err != nil {
+			return errors.Wrapf(
+				err, "failed to apply json patch '%s'", p.JsonOp)
+		}
+		return obj.UnmarshalJSON(modifiedObj)
+	} else {
+		return filtersutil.ApplyToJSON(patchjson6902.Filter{
+			Patch: p.JsonOp,
+		}, obj.Kunstructured)
 	}
-	modifiedObj, err := p.decodedPatch.Apply(rawObj)
-	if err != nil {
-		return errors.Wrapf(
-			err, "failed to apply json patch '%s'", p.JsonOp)
-	}
-	return obj.UnmarshalJSON(modifiedObj)
 }
 
 func NewPatchJson6902TransformerPlugin() resmap.TransformerPlugin {

api/builtins/PatchStrategicMergeTransformer.go

@@ -4,11 +4,16 @@
 package builtins
 
 import (
+	"encoding/json"
 	"fmt"
 
+	kyaml "sigs.k8s.io/kustomize/kyaml/yaml"
+
+	"sigs.k8s.io/kustomize/api/filters/patchstrategicmerge"
 	"sigs.k8s.io/kustomize/api/resmap"
 	"sigs.k8s.io/kustomize/api/resource"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/filtersutil"
 	"sigs.k8s.io/yaml"
 )
 
@@ -17,6 +22,8 @@ type PatchStrategicMergeTransformerPlugin struct {
 	loadedPatches []*resource.Resource
 	Paths         []types.PatchStrategicMerge `json:"paths,omitempty" yaml:"paths,omitempty"`
 	Patches       string                      `json:"patches,omitempty" yaml:"patches,omitempty"`
+
+	YAMLSupport bool `json:"yamlSupport,omitempty" yaml:"yamlSupport,omitempty"`
 }
 
 func (p *PatchStrategicMergeTransformerPlugin) Config(
@@ -69,22 +76,42 @@ func (p *PatchStrategicMergeTransformerPlugin) Transform(m resmap.ResMap) error
 		if err != nil {
 			return err
 		}
-		err = target.Patch(patch.Kunstructured)
-		if err != nil {
-			return err
-		}
-		// remove the resource from resmap
-		// when the patch is to $patch: delete that target
-		if len(target.Map()) == 0 {
-			err = m.Remove(target.CurId())
+		if !p.YAMLSupport {
+			err = target.Patch(patch.Kunstructured)
 			if err != nil {
 				return err
 			}
+			// remove the resource from resmap
+			// when the patch is to $patch: delete that target
+			if len(target.Map()) == 0 {
+				err = m.Remove(target.CurId())
+				if err != nil {
+					return err
+				}
+			}
+		} else {
+			node, err := getRNode(patch)
+			if err != nil {
+				return err
+			}
+			err = filtersutil.ApplyToJSON(patchstrategicmerge.Filter{
+				Patch: node,
+			}, target.Kunstructured)
 		}
 	}
 	return nil
 }
 
+//TODO: Remove this once the next version of kyaml is released which
+// exposes GetRNode from the filutersutil package.
+func getRNode(k json.Marshaler) (*kyaml.RNode, error) {
+	j, err := k.MarshalJSON()
+	if err != nil {
+		return nil, err
+	}
+	return kyaml.Parse(string(j))
+}
+
 func NewPatchStrategicMergeTransformerPlugin() resmap.TransformerPlugin {
 	return &PatchStrategicMergeTransformerPlugin{}
 }

api/filters/annotations/annotations.go

@@ -0,0 +1,42 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package annotations
+
+import (
+	"sigs.k8s.io/kustomize/api/filters/filtersutil"
+	"sigs.k8s.io/kustomize/api/filters/fsslice"
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+type annoMap map[string]string
+
+type Filter struct {
+	// Annotations is the set of annotations to apply to the inputs
+	Annotations annoMap `yaml:"annotations,omitempty"`
+
+	// FsSlice contains the FieldSpecs to locate the namespace field
+	FsSlice types.FsSlice
+}
+
+var _ kio.Filter = Filter{}
+
+func (f Filter) Filter(nodes []*yaml.RNode) ([]*yaml.RNode, error) {
+	keys := filtersutil.SortedMapKeys(f.Annotations)
+	_, err := kio.FilterAll(yaml.FilterFunc(
+		func(node *yaml.RNode) (*yaml.RNode, error) {
+			for _, k := range keys {
+				if err := node.PipeE(fsslice.Filter{
+					FsSlice:    f.FsSlice,
+					SetValue:   fsslice.SetEntry(k, f.Annotations[k]),
+					CreateKind: yaml.MappingNode, // Annotations are MappingNodes.
+				}); err != nil {
+					return nil, err
+				}
+			}
+			return node, nil
+		})).Filter(nodes)
+	return nodes, err
+}

api/filters/annotations/annotations_test.go

@@ -0,0 +1,139 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package annotations
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
+	filtertest_test "sigs.k8s.io/kustomize/api/testutils/filtertest"
+	"sigs.k8s.io/kustomize/api/types"
+)
+
+var annosFs = builtinconfig.MakeDefaultConfig().CommonAnnotations
+
+func TestAnnotations_Filter(t *testing.T) {
+	testCases := map[string]struct {
+		input          string
+		expectedOutput string
+		filter         Filter
+		fsslice        types.FsSlice
+	}{
+		"add": {
+			input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  annotations:
+    hero: batman
+    fiend: riddler
+`,
+			expectedOutput: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  annotations:
+    hero: batman
+    fiend: riddler
+    auto: ford
+    bean: cannellini
+    clown: emmett kelley
+    dragon: smaug
+`,
+			filter: Filter{Annotations: annoMap{
+				"clown":  "emmett kelley",
+				"auto":   "ford",
+				"dragon": "smaug",
+				"bean":   "cannellini",
+			}},
+		},
+		"update": {
+			input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  annotations:
+    hero: batman
+    fiend: riddler
+`,
+			expectedOutput: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  annotations:
+    hero: superman
+    fiend: luthor
+    bean: cannellini
+    clown: emmett kelley
+`,
+			filter: Filter{Annotations: annoMap{
+				"clown": "emmett kelley",
+				"hero":  "superman",
+				"fiend": "luthor",
+				"bean":  "cannellini",
+			}},
+		},
+		"data-fieldspecs": {
+			input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+`,
+			expectedOutput: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  annotations:
+    sleater: kinney
+a:
+  b:
+    sleater: kinney
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+  annotations:
+    sleater: kinney
+a:
+  b:
+    sleater: kinney
+`,
+			filter: Filter{Annotations: annoMap{
+				"sleater": "kinney",
+			}},
+			fsslice: []types.FieldSpec{
+				{
+					Path:               "a/b",
+					CreateIfNotPresent: true,
+				},
+			},
+		},
+	}
+
+	for tn, tc := range testCases {
+		t.Run(tn, func(t *testing.T) {
+			filter := tc.filter
+			filter.FsSlice = append(annosFs, tc.fsslice...)
+			if !assert.Equal(t,
+				strings.TrimSpace(tc.expectedOutput),
+				strings.TrimSpace(filtertest_test.RunFilter(t, tc.input, filter))) {
+				t.FailNow()
+			}
+		})
+	}
+}

api/filters/annotations/doc.go

@@ -0,0 +1,6 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+// Package annotations contains a kio.Filter implementation of the kustomize
+// annotations transformer.
+package annotations

api/filters/annotations/example_test.go

@@ -0,0 +1,55 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package annotations
+
+import (
+	"bytes"
+	"log"
+	"os"
+
+	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+)
+
+func ExampleFilter() {
+	fss := builtinconfig.MakeDefaultConfig().CommonAnnotations
+	err := kio.Pipeline{
+		Inputs: []kio.Reader{&kio.ByteReader{Reader: bytes.NewBufferString(`
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+`)}},
+		Filters: []kio.Filter{Filter{
+			Annotations: map[string]string{
+				"foo": "bar",
+			},
+			FsSlice: fss,
+		}},
+		Outputs: []kio.Writer{kio.ByteWriter{Writer: os.Stdout}},
+	}.Execute()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	// Output:
+	// apiVersion: example.com/v1
+	// kind: Foo
+	// metadata:
+	//   name: instance
+	//   annotations:
+	//     foo: bar
+	// ---
+	// apiVersion: example.com/v1
+	// kind: Bar
+	// metadata:
+	//   name: instance
+	//   annotations:
+	//     foo: bar
+}

api/filters/filtersutil/filtersutil.go

@@ -0,0 +1,21 @@
+// Copyright 2019 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package filtersutil
+
+import (
+	"sort"
+)
+
+// SortedMapKeys returns a sorted slice of keys to the given map.
+// Writing this function never gets old.
+func SortedMapKeys(m map[string]string) []string {
+	keys := make([]string, len(m))
+	i := 0
+	for k := range m {
+		keys[i] = k
+		i++
+	}
+	sort.Strings(keys)
+	return keys
+}

api/filters/filtersutil/filtersutil_test.go

@@ -0,0 +1,34 @@
+package filtersutil_test
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"sigs.k8s.io/kustomize/api/filters/filtersutil"
+)
+
+func TestSortedKeys(t *testing.T) {
+	testCases := map[string]struct {
+		input    map[string]string
+		expected []string
+	}{
+		"empty": {
+			input:    map[string]string{},
+			expected: []string{}},
+		"one": {
+			input:    map[string]string{"a": "aaa"},
+			expected: []string{"a"}},
+		"three": {
+			input:    map[string]string{"c": "ccc", "b": "bbb", "a": "aaa"},
+			expected: []string{"a", "b", "c"}},
+	}
+	for tn, tc := range testCases {
+		t.Run(tn, func(t *testing.T) {
+			if !assert.Equal(t,
+				filtersutil.SortedMapKeys(tc.input),
+				tc.expected) {
+				t.FailNow()
+			}
+		})
+	}
+}

api/filters/fsslice/doc.go

@@ -0,0 +1,6 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+// Package fsslice contains a yaml.Filter to modify a resource using an
+// FsSlice to identify fields to be updated within the resource.
+package fsslice

api/filters/fsslice/example_test.go

@@ -0,0 +1,62 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package fsslice_test
+
+import (
+	"bytes"
+	"log"
+	"os"
+
+	"sigs.k8s.io/kustomize/api/filters/fsslice"
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+func ExampleFilter() {
+	in := &kio.ByteReader{
+		Reader: bytes.NewBufferString(`
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+`),
+	}
+	fltr := fsslice.Filter{
+		CreateKind: yaml.ScalarNode,
+		SetValue:   fsslice.SetScalar("green"),
+		FsSlice: []types.FieldSpec{
+			{Path: "a/b", CreateIfNotPresent: true},
+		},
+	}
+
+	err := kio.Pipeline{
+		Inputs:  []kio.Reader{in},
+		Filters: []kio.Filter{kio.FilterAll(fltr)},
+		Outputs: []kio.Writer{kio.ByteWriter{Writer: os.Stdout}},
+	}.Execute()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	// Output:
+	// apiVersion: example.com/v1
+	// kind: Foo
+	// metadata:
+	//   name: instance
+	// a:
+	//   b: green
+	// ---
+	// apiVersion: example.com/v1
+	// kind: Bar
+	// metadata:
+	//   name: instance
+	// a:
+	//   b: green
+}

api/filters/fsslice/fieldspec_filter.go

@@ -0,0 +1,145 @@
+// Copyright 2019 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package fsslice
+
+import (
+	"strings"
+
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/errors"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+// fieldSpecFilter applies a single fieldSpec to a single object
+// fieldSpecFilter stores internal state and should not be reused
+type fieldSpecFilter struct {
+	// FieldSpec contains the path to the value to set.
+	FieldSpec types.FieldSpec `yaml:"fieldSpec"`
+
+	// Set the field using this function
+	SetValue SetFn
+
+	// CreateKind defines the type of node to create if the field is not found
+	CreateKind yaml.Kind
+
+	// path keeps internal state about the current path
+	path []string
+}
+
+func (fltr fieldSpecFilter) Filter(obj *yaml.RNode) (*yaml.RNode, error) {
+	// check if the FieldSpec applies to the object
+	if match, err := isMatchGVK(fltr.FieldSpec, obj); !match || err != nil {
+		return obj, errors.Wrap(err)
+	}
+	fltr.path = strings.Split(fltr.FieldSpec.Path, "/")
+	if err := fltr.filter(obj); err != nil {
+		s, _ := obj.String()
+		return nil, errors.WrapPrefixf(err,
+			"obj %v at path %v", s, fltr.FieldSpec.Path)
+	}
+	return obj, nil
+}
+
+func (fltr fieldSpecFilter) filter(obj *yaml.RNode) error {
+	if len(fltr.path) == 0 {
+		// found the field -- set its value
+		return fltr.SetValue(obj)
+	}
+	switch obj.YNode().Kind {
+	case yaml.SequenceNode:
+		return fltr.seq(obj)
+	case yaml.MappingNode:
+		return fltr.field(obj)
+	}
+	// not found -- this might be an error since the type doesn't match
+
+	return errors.Errorf("unsupported yaml node")
+}
+
+// field calls filter on the field matching the next path element
+func (fltr fieldSpecFilter) field(obj *yaml.RNode) error {
+	fieldName, isSeq := isSequenceField(fltr.path[0])
+
+	// lookup the field matching the next path element
+	var lookupField yaml.Filter
+	switch {
+	case !fltr.FieldSpec.CreateIfNotPresent || fltr.CreateKind == 0 || isSeq:
+		// dont' create the field if we don't find it
+		lookupField = yaml.Lookup(fieldName)
+	case len(fltr.path) <= 1:
+		// create the field if it is missing: use the provided node kind
+		lookupField = yaml.LookupCreate(fltr.CreateKind, fieldName)
+	default:
+		// create the field if it is missing: must be a mapping node
+		lookupField = yaml.LookupCreate(yaml.MappingNode, fieldName)
+	}
+
+	// locate (or maybe create) the field
+	field, err := obj.Pipe(lookupField)
+	if err != nil || field == nil {
+		return errors.WrapPrefixf(err, "fieldName: %s", fieldName)
+	}
+
+	// copy the current fltr and change the path on the copy
+	var next = fltr
+	// call filter for the next path element on the matching field
+	next.path = fltr.path[1:]
+	return next.filter(field)
+}
+
+// seq calls filter on all sequence elements
+func (fltr fieldSpecFilter) seq(obj *yaml.RNode) error {
+	if err := obj.VisitElements(func(node *yaml.RNode) error {
+		// recurse on each element -- re-allocating a fieldSpecFilter is
+		// not strictly required, but is more consistent with field
+		// and less likely to have side effects
+		// keep the entire path -- it does not contain parts for sequences
+		return fltr.filter(node)
+	}); err != nil {
+		return errors.WrapPrefixf(err,
+			"visit traversal on path: %v", fltr.path)
+	}
+
+	return nil
+}
+
+// isSequenceField returns true if the path element is for a sequence field.
+// isSequence also returns the path element with the '[]' suffix trimmed
+func isSequenceField(name string) (string, bool) {
+	isSeq := strings.HasSuffix(name, "[]")
+	name = strings.TrimSuffix(name, "[]")
+	return name, isSeq
+}
+
+// isMatchGVK returns true if the fs.GVK matches the obj GVK.
+func isMatchGVK(fs types.FieldSpec, obj *yaml.RNode) (bool, error) {
+	meta, err := obj.GetMeta()
+	if err != nil {
+		return false, err
+	}
+	if fs.Kind != "" && fs.Kind != meta.Kind {
+		// kind doesn't match
+		return false, err
+	}
+
+	// parse the group and version from the apiVersion field
+	var group, version string
+	parts := strings.SplitN(meta.APIVersion, "/", 2)
+	group = parts[0]
+	if len(parts) > 1 {
+		version = parts[1]
+	}
+
+	if fs.Group != "" && fs.Group != group {
+		// group doesn't match
+		return false, nil
+	}
+
+	if fs.Version != "" && fs.Version != version {
+		// version doesn't match
+		return false, nil
+	}
+
+	return true, nil
+}

api/filters/fsslice/fsslice.go

@@ -0,0 +1,78 @@
+// Copyright 2019 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package fsslice
+
+import (
+	"strings"
+
+	"sigs.k8s.io/kustomize/api/resid"
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+// SetFn sets a value
+type SetFn func(*yaml.RNode) error
+
+// SetScalar returns a SetFn to set a scalar value
+func SetScalar(value string) SetFn {
+	return func(node *yaml.RNode) error {
+		return node.PipeE(yaml.FieldSetter{StringValue: value})
+	}
+}
+
+// SetEntry returns a SetFn to set an entry in a map
+func SetEntry(key, value string) SetFn {
+	return func(node *yaml.RNode) error {
+		return node.PipeE(yaml.FieldSetter{
+			Name: key, StringValue: value})
+	}
+}
+
+var _ yaml.Filter = Filter{}
+
+// Filter uses an FsSlice to modify fields on a single object
+type Filter struct {
+	// FieldSpecList list of FieldSpecs to set
+	FsSlice types.FsSlice `yaml:"fsSlice"`
+
+	// SetValue is called on each field that matches one of the FieldSpecs
+	SetValue SetFn
+
+	// CreateKind is used to create fields that do not exist
+	CreateKind yaml.Kind
+}
+
+func (fltr Filter) Filter(obj *yaml.RNode) (*yaml.RNode, error) {
+	for i := range fltr.FsSlice {
+		// apply this FieldSpec
+		// create a new filter for each iteration because they
+		// store internal state about the field paths
+		_, err := (&fieldSpecFilter{
+			FieldSpec:  fltr.FsSlice[i],
+			SetValue:   fltr.SetValue,
+			CreateKind: fltr.CreateKind,
+		}).Filter(obj)
+		if err != nil {
+			return nil, err
+		}
+	}
+	return obj, nil
+}
+
+// GetGVK parses the metadata into a GVK
+func GetGVK(meta yaml.ResourceMeta) resid.Gvk {
+	// parse the group and version from the apiVersion field
+	var group, version string
+	parts := strings.SplitN(meta.APIVersion, "/", 2)
+	group = parts[0]
+	if len(parts) > 1 {
+		version = parts[1]
+	}
+
+	return resid.Gvk{
+		Group:   group,
+		Version: version,
+		Kind:    meta.Kind,
+	}
+}

api/filters/fsslice/fsslice_test.go

@@ -0,0 +1,354 @@
+// Copyright 2019 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package fsslice_test
+
+import (
+	"bytes"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"sigs.k8s.io/kustomize/api/filters/fsslice"
+	"sigs.k8s.io/kustomize/api/resid"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+type TestCase struct {
+	name     string
+	input    string
+	expected string
+	filter   fsslice.Filter
+	fsSlice  string
+	error    string
+}
+
+var tests = []TestCase{
+	{
+		name: "update",
+		fsSlice: `
+- path: a/b
+  group: foo
+  kind: Bar
+`,
+		input: `
+apiVersion: foo/v1beta1
+kind: Bar
+a:
+  b: c
+`,
+		expected: `
+apiVersion: foo/v1beta1
+kind: Bar
+a:
+  b: e
+`,
+		filter: fsslice.Filter{
+			SetValue: fsslice.SetScalar("e"),
+		},
+	},
+
+	{
+		name: "update-kind-not-match",
+		fsSlice: `
+- path: a/b
+  group: foo
+  kind: Bar1
+`,
+		input: `
+apiVersion: foo/v1beta1
+kind: Bar2
+a:
+  b: c
+`,
+		expected: `
+apiVersion: foo/v1beta1
+kind: Bar2
+a:
+  b: c
+`,
+		filter: fsslice.Filter{
+			SetValue: fsslice.SetScalar("e"),
+		},
+	},
+
+	{
+		name: "update-group-not-match",
+		fsSlice: `
+- path: a/b
+  group: foo1
+  kind: Bar
+`,
+		input: `
+apiVersion: foo2/v1beta1
+kind: Bar
+a:
+  b: c
+`,
+		expected: `
+apiVersion: foo2/v1beta1
+kind: Bar
+a:
+  b: c
+`,
+		filter: fsslice.Filter{
+			SetValue: fsslice.SetScalar("e"),
+		},
+	},
+
+	{
+		name: "update-version-not-match",
+		fsSlice: `
+- path: a/b
+  group: foo
+  version: v1beta1
+  kind: Bar
+`,
+		input: `
+apiVersion: foo/v1beta2
+kind: Bar
+a:
+  b: c
+`,
+		expected: `
+apiVersion: foo/v1beta2
+kind: Bar
+a:
+  b: c
+`,
+		filter: fsslice.Filter{
+			SetValue: fsslice.SetScalar("e"),
+		},
+	},
+
+	{
+		name: "bad-version",
+		fsSlice: `
+- path: a/b
+  group: foo
+  version: v1beta1
+  kind: Bar
+`,
+		input: `
+apiVersion: foo/v1beta2/something
+kind: Bar
+a:
+  b: c
+`,
+		expected: `
+apiVersion: foo/v1beta2/something
+kind: Bar
+a:
+  b: c
+`,
+		filter: fsslice.Filter{
+			SetValue: fsslice.SetScalar("e"),
+		},
+	},
+
+	{
+		name: "bad-meta",
+		fsSlice: `
+- path: a/b
+  group: foo
+  version: v1beta1
+  kind: Bar
+`,
+		input: `
+a:
+  b: c
+`,
+		filter: fsslice.Filter{
+			SetValue: fsslice.SetScalar("e"),
+		},
+		error: "missing Resource metadata",
+	},
+
+	{
+		name: "miss-match-type",
+		fsSlice: `
+- path: a/b/c
+  kind: Bar
+`,
+		input: `
+kind: Bar
+a:
+  b: a
+`,
+		error: "obj kind: Bar\na:\n  b: a\n at path a/b/c: unsupported yaml node",
+		filter: fsslice.Filter{
+			SetValue: fsslice.SetScalar("e"),
+		},
+	},
+
+	{
+		name: "add",
+		fsSlice: `
+- path: a/b/c/d
+  group: foo
+  create: true
+  kind: Bar
+`,
+		input: `
+apiVersion: foo/v1beta1
+kind: Bar
+a: {}
+`,
+		expected: `
+apiVersion: foo/v1beta1
+kind: Bar
+a: {b: {c: {d: e}}}
+`,
+		filter: fsslice.Filter{
+			SetValue:   fsslice.SetScalar("e"),
+			CreateKind: yaml.ScalarNode,
+		},
+	},
+
+	{
+		name: "update-in-sequence",
+		fsSlice: `
+- path: a/b[]/c/d
+  group: foo
+  kind: Bar
+`,
+		input: `
+apiVersion: foo/v1beta1
+kind: Bar
+a:
+  b:
+  - c:
+      d: a
+`,
+		expected: `
+apiVersion: foo/v1beta1
+kind: Bar
+a:
+  b:
+  - c:
+      d: e
+`,
+		filter: fsslice.Filter{
+			SetValue: fsslice.SetScalar("e"),
+		},
+	},
+
+	// Don't create a sequence
+	{
+		name: "empty-sequence-no-create",
+		fsSlice: `
+- path: a/b[]/c/d
+  group: foo
+  create: true
+  kind: Bar
+`,
+		input: `
+apiVersion: foo/v1beta1
+kind: Bar
+a: {}
+`,
+		expected: `
+apiVersion: foo/v1beta1
+kind: Bar
+a: {}
+`,
+		filter: fsslice.Filter{
+			SetValue:   fsslice.SetScalar("e"),
+			CreateKind: yaml.ScalarNode,
+		},
+	},
+
+	// Create a new field for an element in a sequence
+	{
+		name: "empty-sequence-create",
+		fsSlice: `
+- path: a/b[]/c/d
+  group: foo
+  create: true
+  kind: Bar
+`,
+		input: `
+apiVersion: foo/v1beta1
+kind: Bar
+a:
+  b:
+  - c: {}
+`,
+		expected: `
+apiVersion: foo/v1beta1
+kind: Bar
+a:
+  b:
+  - c: {d: e}
+`,
+		filter: fsslice.Filter{
+			SetValue:   fsslice.SetScalar("e"),
+			CreateKind: yaml.ScalarNode,
+		},
+	},
+}
+
+func TestFilter_Filter(t *testing.T) {
+	for i := range tests {
+		test := tests[i]
+		t.Run(test.name, func(t *testing.T) {
+			err := yaml.Unmarshal([]byte(test.fsSlice), &test.filter.FsSlice)
+			if !assert.NoError(t, err) {
+				t.FailNow()
+			}
+
+			out := &bytes.Buffer{}
+			rw := &kio.ByteReadWriter{
+				Reader:                bytes.NewBufferString(test.input),
+				Writer:                out,
+				OmitReaderAnnotations: true,
+			}
+
+			// run the filter
+			err = kio.Pipeline{
+				Inputs:  []kio.Reader{rw},
+				Filters: []kio.Filter{kio.FilterAll(test.filter)},
+				Outputs: []kio.Writer{rw},
+			}.Execute()
+			if test.error != "" {
+				if !assert.EqualError(t, err, test.error) {
+					t.FailNow()
+				}
+				// stop rest of test
+				return
+			}
+
+			if !assert.NoError(t, err) {
+				t.FailNow()
+			}
+
+			// check results
+			if !assert.Equal(t,
+				strings.TrimSpace(test.expected),
+				strings.TrimSpace(out.String())) {
+				t.FailNow()
+			}
+		})
+	}
+}
+
+func TestGetGVK(t *testing.T) {
+	obj, err := yaml.Parse(`
+apiVersion: apps/v1
+kind: Deployment
+`)
+	if !assert.NoError(t, err) {
+		t.FailNow()
+	}
+	meta, err := obj.GetMeta()
+	if !assert.NoError(t, err) {
+		t.FailNow()
+	}
+
+	gvk := fsslice.GetGVK(meta)
+	expected := resid.Gvk{Group: "apps", Version: "v1", Kind: "Deployment"}
+	if !assert.Equal(t, expected, gvk) {
+		t.FailNow()
+	}
+}

api/filters/imagetag/doc.go

@@ -0,0 +1,12 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+// Package imagetag contains two kio.Filter implementations to cover the
+// functionality of the kustomize imagetag transformer.
+//
+// Filter updates fields based on a FieldSpec and an ImageTag.
+//
+// LegacyFilter doesn't use a FieldSpec, and instead only updates image
+// references if the field is name image and it is underneath a field called
+// either containers or initContainers.
+package imagetag

api/filters/imagetag/example_test.go

@@ -0,0 +1,126 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package imagetag
+
+import (
+	"bytes"
+	"log"
+	"os"
+
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+)
+
+func ExampleFilter() {
+	err := kio.Pipeline{
+		Inputs: []kio.Reader{&kio.ByteReader{Reader: bytes.NewBufferString(`
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  containers:
+  - name: FooBar
+    image: nginx
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+spec:
+  containers:
+  - name: BarFoo
+    image: nginx:1.2.1
+`)}},
+		Filters: []kio.Filter{Filter{
+			ImageTag: types.Image{
+				Name:    "nginx",
+				NewName: "apache",
+				Digest:  "12345",
+			},
+			FsSlice: []types.FieldSpec{
+				{
+					Path: "spec/containers[]/image",
+				},
+			},
+		}},
+		Outputs: []kio.Writer{kio.ByteWriter{Writer: os.Stdout}},
+	}.Execute()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	// Output:
+	// apiVersion: example.com/v1
+	// kind: Foo
+	// metadata:
+	//   name: instance
+	// spec:
+	//   containers:
+	//   - name: FooBar
+	//     image: apache@12345
+	// ---
+	// apiVersion: example.com/v1
+	// kind: Bar
+	// metadata:
+	//   name: instance
+	// spec:
+	//   containers:
+	//   - name: BarFoo
+	//     image: apache@12345
+}
+
+func ExampleLegacyFilter() {
+	err := kio.Pipeline{
+		Inputs: []kio.Reader{&kio.ByteReader{Reader: bytes.NewBufferString(`
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  containers:
+  - name: FooBar
+    image: nginx
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+spec:
+  containers:
+  - name: BarFoo
+    image: nginx:1.2.1
+`)}},
+		Filters: []kio.Filter{LegacyFilter{
+			ImageTag: types.Image{
+				Name:    "nginx",
+				NewName: "apache",
+				Digest:  "12345",
+			},
+		}},
+		Outputs: []kio.Writer{kio.ByteWriter{Writer: os.Stdout}},
+	}.Execute()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	// Output:
+	// apiVersion: example.com/v1
+	// kind: Foo
+	// metadata:
+	//   name: instance
+	// spec:
+	//   containers:
+	//   - name: FooBar
+	//     image: apache@12345
+	// ---
+	// apiVersion: example.com/v1
+	// kind: Bar
+	// metadata:
+	//   name: instance
+	// spec:
+	//   containers:
+	//   - name: BarFoo
+	//     image: apache@12345
+}

api/filters/imagetag/imagetag.go

@@ -0,0 +1,44 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package imagetag
+
+import (
+	"sigs.k8s.io/kustomize/api/filters/fsslice"
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+type Filter struct {
+	// imageTag is the tag we want to apply to the inputs
+	ImageTag types.Image `json:"imageTag,omitempty" yaml:"imageTag,omitempty"`
+
+	// FsSlice contains the FieldSpecs to locate the namespace field
+	FsSlice types.FsSlice `json:"fieldSpecs,omitempty" yaml:"fieldSpecs,omitempty"`
+}
+
+var _ kio.Filter = Filter{}
+
+func (f Filter) Filter(nodes []*yaml.RNode) ([]*yaml.RNode, error) {
+	_, err := kio.FilterAll(yaml.FilterFunc(f.filter)).Filter(nodes)
+	return nodes, err
+}
+
+func (f Filter) filter(node *yaml.RNode) (*yaml.RNode, error) {
+	if err := node.PipeE(fsslice.Filter{
+		FsSlice:  f.FsSlice,
+		SetValue: updateImageTagFn(f.ImageTag),
+	}); err != nil {
+		return nil, err
+	}
+	return node, nil
+}
+
+func updateImageTagFn(imageTag types.Image) fsslice.SetFn {
+	return func(node *yaml.RNode) error {
+		return node.PipeE(imageTagUpdater{
+			ImageTag: imageTag,
+		})
+	}
+}

api/filters/imagetag/imagetag_test.go

@@ -0,0 +1,101 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package imagetag
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	filtertest "sigs.k8s.io/kustomize/api/testutils/filtertest"
+	"sigs.k8s.io/kustomize/api/types"
+)
+
+func TestImageTagUpdater_Filter(t *testing.T) {
+	testCases := map[string]struct {
+		input          string
+		expectedOutput string
+		filter         Filter
+		fsSlice        types.FsSlice
+	}{
+		"update with digest": {
+			input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  image: nginx:1.2.1
+`,
+			expectedOutput: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  image: apache@12345
+`,
+			filter: Filter{
+				ImageTag: types.Image{
+					Name:    "nginx",
+					NewName: "apache",
+					Digest:  "12345",
+				},
+			},
+			fsSlice: []types.FieldSpec{
+				{
+					Path: "spec/image",
+				},
+			},
+		},
+		"multiple matches in sequence": {
+			input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  containers:
+  - image: nginx:1.2.1
+  - image: not_nginx@54321
+  - image: nginx:1.2.1
+`,
+			expectedOutput: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  containers:
+  - image: apache:3.2.1
+  - image: not_nginx@54321
+  - image: apache:3.2.1
+`,
+			filter: Filter{
+				ImageTag: types.Image{
+					Name:    "nginx",
+					NewName: "apache",
+					NewTag:  "3.2.1",
+				},
+			},
+			fsSlice: []types.FieldSpec{
+				{
+					Path: "spec/containers/image",
+				},
+			},
+		},
+	}
+
+	for tn, tc := range testCases {
+		t.Run(tn, func(t *testing.T) {
+			filter := tc.filter
+			filter.FsSlice = tc.fsSlice
+			if !assert.Equal(t,
+				strings.TrimSpace(tc.expectedOutput),
+				strings.TrimSpace(filtertest.RunFilter(t, tc.input, filter))) {
+				t.FailNow()
+			}
+		})
+	}
+}

api/filters/imagetag/legacy.go

@@ -0,0 +1,113 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package imagetag
+
+import (
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+// LegacyFilter is an implementation of the kio.Filter interface
+// that scans through the provided kyaml data structure and updates
+// any values of any image fields that is inside a sequence under
+// a field called either containers or initContainers. The field is only
+// update if it has a value that matches and image reference and the name
+// of the image is a match with the provided ImageTag.
+type LegacyFilter struct {
+	ImageTag types.Image `json:"imageTag,omitempty" yaml:"imageTag,omitempty"`
+}
+
+var _ kio.Filter = LegacyFilter{}
+
+func (lf LegacyFilter) Filter(nodes []*yaml.RNode) ([]*yaml.RNode, error) {
+	return kio.FilterAll(yaml.FilterFunc(lf.filter)).Filter(nodes)
+}
+
+func (lf LegacyFilter) filter(node *yaml.RNode) (*yaml.RNode, error) {
+	meta, err := node.GetMeta()
+	if err != nil {
+		return nil, err
+	}
+
+	// We do not make any changes if the type of the resource
+	// is CustomResourceDefinition.
+	if meta.Kind == `CustomResourceDefinition` {
+		return node, nil
+	}
+
+	fff := findFieldsFilter{
+		fields:        []string{"containers", "initContainers"},
+		fieldCallback: checkImageTagsFn(lf.ImageTag),
+	}
+	if err := node.PipeE(fff); err != nil {
+		return nil, err
+	}
+	return node, nil
+}
+
+type fieldCallback func(node *yaml.RNode) error
+
+// findFieldsFilter is an implementation of the kio.Filter
+// interface. It will walk the data structure and look for fields
+// that matches the provided list of field names. For each match,
+// the value of the field will be passed in as a parameter to the
+// provided fieldCallback.
+// TODO: move this to kyaml/filterutils
+type findFieldsFilter struct {
+	fields []string
+
+	fieldCallback fieldCallback
+}
+
+func (f findFieldsFilter) Filter(obj *yaml.RNode) (*yaml.RNode, error) {
+	return obj, f.walk(obj)
+}
+
+func (f findFieldsFilter) walk(node *yaml.RNode) error {
+	switch node.YNode().Kind {
+	case yaml.MappingNode:
+		return node.VisitFields(func(n *yaml.MapNode) error {
+			err := f.walk(n.Value)
+			if err != nil {
+				return err
+			}
+			key := n.Key.YNode().Value
+			if contains(f.fields, key) {
+				return f.fieldCallback(n.Value)
+			}
+			return nil
+		})
+	case yaml.SequenceNode:
+		return node.VisitElements(func(n *yaml.RNode) error {
+			return f.walk(n)
+		})
+	}
+	return nil
+}
+
+func contains(slice []string, str string) bool {
+	for _, s := range slice {
+		if s == str {
+			return true
+		}
+	}
+	return false
+}
+
+func checkImageTagsFn(imageTag types.Image) fieldCallback {
+	return func(node *yaml.RNode) error {
+		if node.YNode().Kind != yaml.SequenceNode {
+			return nil
+		}
+
+		return node.VisitElements(func(n *yaml.RNode) error {
+			// Look up any fields on the provided node that is named
+			// image.
+			return n.PipeE(yaml.Get("image"), imageTagUpdater{
+				ImageTag: imageTag,
+			})
+		})
+	}
+}

api/filters/imagetag/legacy_test.go

@@ -0,0 +1,136 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package imagetag
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	filtertest "sigs.k8s.io/kustomize/api/testutils/filtertest"
+	"sigs.k8s.io/kustomize/api/types"
+)
+
+func TestLegacyImageTag_Filter(t *testing.T) {
+	testCases := map[string]struct {
+		input          string
+		expectedOutput string
+		filter         LegacyFilter
+	}{
+		"updates multiple images inside containers": {
+			input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  containers:
+  - image: nginx:1.2.1
+  - image: nginx:2.1.2
+`,
+			expectedOutput: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  containers:
+  - image: apache@12345
+  - image: apache@12345
+`,
+			filter: LegacyFilter{
+				ImageTag: types.Image{
+					Name:    "nginx",
+					NewName: "apache",
+					Digest:  "12345",
+				},
+			},
+		},
+		"updates inside both containers and initContainers": {
+			input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  containers:
+  - image: nginx:1.2.1
+  - image: tomcat:1.2.3
+  initContainers:
+  - image: nginx:1.2.1
+  - image: apache:1.2.3
+`,
+			expectedOutput: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  containers:
+  - image: apache:3.2.1
+  - image: tomcat:1.2.3
+  initContainers:
+  - image: apache:3.2.1
+  - image: apache:1.2.3
+`,
+			filter: LegacyFilter{
+				ImageTag: types.Image{
+					Name:    "nginx",
+					NewName: "apache",
+					NewTag:  "3.2.1",
+				},
+			},
+		},
+		"updates on multiple depths": {
+			input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  containers:
+  - image: nginx:1.2.1
+  - image: tomcat:1.2.3
+  template:
+    spec: 
+      initContainers:
+      - image: nginx:1.2.1
+      - image: apache:1.2.3
+`,
+			expectedOutput: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  containers:
+  - image: apache:3.2.1
+  - image: tomcat:1.2.3
+  template:
+    spec:
+      initContainers:
+      - image: apache:3.2.1
+      - image: apache:1.2.3
+`,
+			filter: LegacyFilter{
+				ImageTag: types.Image{
+					Name:    "nginx",
+					NewName: "apache",
+					NewTag:  "3.2.1",
+				},
+			},
+		},
+	}
+
+	for tn, tc := range testCases {
+		t.Run(tn, func(t *testing.T) {
+			filter := tc.filter
+			if !assert.Equal(t,
+				strings.TrimSpace(tc.expectedOutput),
+				strings.TrimSpace(filtertest.RunFilter(t, tc.input, filter))) {
+				t.FailNow()
+			}
+		})
+	}
+}

api/filters/imagetag/updater.go

@@ -0,0 +1,43 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package imagetag
+
+import (
+	"sigs.k8s.io/kustomize/api/image"
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+// imageTagUpdater is an implementation of the kio.Filter interface
+// that will update the value of the yaml node based on the provided
+// ImageTag if the current value matches the format of an image reference.
+type imageTagUpdater struct {
+	Kind     string      `yaml:"kind,omitempty"`
+	ImageTag types.Image `yaml:"imageTag,omitempty"`
+}
+
+func (u imageTagUpdater) Filter(rn *yaml.RNode) (*yaml.RNode, error) {
+	if err := yaml.ErrorIfInvalid(rn, yaml.ScalarNode); err != nil {
+		return nil, err
+	}
+
+	value := rn.YNode().Value
+
+	if !image.IsImageMatched(value, u.ImageTag.Name) {
+		return rn, nil
+	}
+
+	name, tag := image.Split(value)
+	if u.ImageTag.NewName != "" {
+		name = u.ImageTag.NewName
+	}
+	if u.ImageTag.NewTag != "" {
+		tag = ":" + u.ImageTag.NewTag
+	}
+	if u.ImageTag.Digest != "" {
+		tag = "@" + u.ImageTag.Digest
+	}
+
+	return rn.Pipe(yaml.FieldSetter{StringValue: name + tag})
+}

api/filters/labels/doc.go

@@ -0,0 +1,6 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+// Package labels contains a kio.Filter implementation of the kustomize
+// labels transformer.
+package labels

api/filters/labels/example_test.go

@@ -0,0 +1,55 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package labels
+
+import (
+	"bytes"
+	"log"
+	"os"
+
+	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+)
+
+func ExampleFilter() {
+	fss := builtinconfig.MakeDefaultConfig().CommonLabels
+	err := kio.Pipeline{
+		Inputs: []kio.Reader{&kio.ByteReader{Reader: bytes.NewBufferString(`
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+`)}},
+		Filters: []kio.Filter{Filter{
+			Labels: map[string]string{
+				"foo": "bar",
+			},
+			FsSlice: fss,
+		}},
+		Outputs: []kio.Writer{kio.ByteWriter{Writer: os.Stdout}},
+	}.Execute()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	// Output:
+	// apiVersion: example.com/v1
+	// kind: Foo
+	// metadata:
+	//   name: instance
+	//   labels:
+	//     foo: bar
+	// ---
+	// apiVersion: example.com/v1
+	// kind: Bar
+	// metadata:
+	//   name: instance
+	//   labels:
+	//     foo: bar
+}

api/filters/labels/labels.go

@@ -0,0 +1,43 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package labels
+
+import (
+	"sigs.k8s.io/kustomize/api/filters/filtersutil"
+	"sigs.k8s.io/kustomize/api/filters/fsslice"
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+type labelMap map[string]string
+
+// Filter sets labels.
+type Filter struct {
+	// Labels is the set of labels to apply to the inputs
+	Labels labelMap `yaml:"labels,omitempty"`
+
+	// FsSlice identifies the label fields.
+	FsSlice types.FsSlice
+}
+
+var _ kio.Filter = Filter{}
+
+func (f Filter) Filter(nodes []*yaml.RNode) ([]*yaml.RNode, error) {
+	keys := filtersutil.SortedMapKeys(f.Labels)
+	_, err := kio.FilterAll(yaml.FilterFunc(
+		func(node *yaml.RNode) (*yaml.RNode, error) {
+			for _, k := range keys {
+				if err := node.PipeE(fsslice.Filter{
+					FsSlice:    f.FsSlice,
+					SetValue:   fsslice.SetEntry(k, f.Labels[k]),
+					CreateKind: yaml.MappingNode, // Labels are MappingNodes.
+				}); err != nil {
+					return nil, err
+				}
+			}
+			return node, nil
+		})).Filter(nodes)
+	return nodes, err
+}

api/filters/labels/labels_test.go

@@ -0,0 +1,139 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package labels
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
+	filtertest_test "sigs.k8s.io/kustomize/api/testutils/filtertest"
+	"sigs.k8s.io/kustomize/api/types"
+)
+
+var labelsFs = builtinconfig.MakeDefaultConfig().CommonLabels
+
+func TestLabels_Filter(t *testing.T) {
+	testCases := map[string]struct {
+		input          string
+		expectedOutput string
+		filter         Filter
+		fsSlice        types.FsSlice
+	}{
+		"add": {
+			input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  labels:
+    hero: batman
+    fiend: riddler
+`,
+			expectedOutput: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  labels:
+    hero: batman
+    fiend: riddler
+    auto: ford
+    bean: cannellini
+    clown: emmett kelley
+    dragon: smaug
+`,
+			filter: Filter{Labels: labelMap{
+				"clown":  "emmett kelley",
+				"auto":   "ford",
+				"dragon": "smaug",
+				"bean":   "cannellini",
+			}},
+		},
+		"update": {
+			input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  labels:
+    hero: batman
+    fiend: riddler
+`,
+			expectedOutput: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  labels:
+    hero: superman
+    fiend: luthor
+    bean: cannellini
+    clown: emmett kelley
+`,
+			filter: Filter{Labels: labelMap{
+				"clown": "emmett kelley",
+				"hero":  "superman",
+				"fiend": "luthor",
+				"bean":  "cannellini",
+			}},
+		},
+		"data-fieldspecs": {
+			input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+`,
+			expectedOutput: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  labels:
+    sleater: kinney
+a:
+  b:
+    sleater: kinney
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+  labels:
+    sleater: kinney
+a:
+  b:
+    sleater: kinney
+`,
+			filter: Filter{Labels: labelMap{
+				"sleater": "kinney",
+			}},
+			fsSlice: []types.FieldSpec{
+				{
+					Path:               "a/b",
+					CreateIfNotPresent: true,
+				},
+			},
+		},
+	}
+
+	for tn, tc := range testCases {
+		t.Run(tn, func(t *testing.T) {
+			filter := tc.filter
+			filter.FsSlice = append(labelsFs, tc.fsSlice...)
+			if !assert.Equal(t,
+				strings.TrimSpace(tc.expectedOutput),
+				strings.TrimSpace(filtertest_test.RunFilter(t, tc.input, filter))) {
+				t.FailNow()
+			}
+		})
+	}
+}

api/filters/namespace/doc.go

@@ -0,0 +1,9 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+// Package namespace contains a kio.Filter implementation of the kustomize
+// namespace transformer.
+//
+// Special cases for known Kubernetes resources have been hardcoded in addition
+// to those defined by the FsSlice.
+package namespace

api/filters/namespace/example_test.go

@@ -0,0 +1,50 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package namespace_test
+
+import (
+	"bytes"
+	"log"
+	"os"
+
+	"sigs.k8s.io/kustomize/api/filters/namespace"
+	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+)
+
+func ExampleFilter() {
+	fss := builtinconfig.MakeDefaultConfig().NameSpace
+	err := kio.Pipeline{
+		Inputs: []kio.Reader{&kio.ByteReader{Reader: bytes.NewBufferString(`
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+  namespace: bar
+`)}},
+		Filters: []kio.Filter{namespace.Filter{Namespace: "app", FsSlice: fss}},
+		Outputs: []kio.Writer{kio.ByteWriter{Writer: os.Stdout}},
+	}.Execute()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	// Output:
+	// apiVersion: example.com/v1
+	// kind: Foo
+	// metadata:
+	//   name: instance
+	//   namespace: app
+	// ---
+	// apiVersion: example.com/v1
+	// kind: Bar
+	// metadata:
+	//   name: instance
+	//   namespace: app
+}

api/filters/namespace/namespace.go

@@ -0,0 +1,167 @@
+// Copyright 2019 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package namespace
+
+import (
+	"sigs.k8s.io/kustomize/api/filters/fsslice"
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+type Filter struct {
+	// Namespace is the namespace to apply to the inputs
+	Namespace string `yaml:"namespace,omitempty"`
+
+	// FsSlice contains the FieldSpecs to locate the namespace field
+	FsSlice types.FsSlice `json:"fieldSpecs,omitempty" yaml:"fieldSpecs,omitempty"`
+}
+
+var _ kio.Filter = Filter{}
+
+func (ns Filter) Filter(nodes []*yaml.RNode) ([]*yaml.RNode, error) {
+	return kio.FilterAll(yaml.FilterFunc(ns.run)).Filter(nodes)
+}
+
+// Run runs the filter on a single node rather than a slice
+func (ns Filter) run(node *yaml.RNode) (*yaml.RNode, error) {
+	// hacks for hardcoded types -- :(
+	if err := ns.hacks(node); err != nil {
+		return nil, err
+	}
+
+	// Remove the fieldspecs that are for hardcoded fields.  The fieldspecs
+	// exist for backwards compatibility with other implementations
+	// of this transformation.
+	// This implementation of the namespace transformation
+	// Does not use the fieldspecs for implementing cases which
+	// require hardcoded logic.
+	ns.FsSlice = ns.removeFieldSpecsForHacks(ns.FsSlice)
+
+	// transformations based on data -- :)
+	err := node.PipeE(fsslice.Filter{
+		FsSlice:    ns.FsSlice,
+		SetValue:   fsslice.SetScalar(ns.Namespace),
+		CreateKind: yaml.ScalarNode, // Namespace is a ScalarNode
+	})
+	return node, err
+}
+
+// hacks applies the namespace transforms that are hardcoded rather
+// than specified through FieldSpecs.
+func (ns Filter) hacks(obj *yaml.RNode) error {
+	meta, err := obj.GetMeta()
+	if err != nil {
+		return err
+	}
+
+	if err := ns.metaNamespaceHack(obj, meta); err != nil {
+		return err
+	}
+
+	return ns.roleBindingHack(obj, meta)
+}
+
+// metaNamespaceHack is a hack for implementing the namespace transform
+// for the metadata.namespace field on namespace scoped resources.
+// namespace scoped resources are determined by NOT being present
+// in a blacklist of cluster-scoped resource types (by apiVersion and kind).
+//
+// This hack should be updated to allow individual resources to specify
+// if they are cluster scoped through either an annotation on the resources,
+// or through inlined OpenAPI on the resource as a YAML comment.
+func (ns Filter) metaNamespaceHack(obj *yaml.RNode, meta yaml.ResourceMeta) error {
+	gvk := fsslice.GetGVK(meta)
+	if !gvk.IsNamespaceableKind() {
+		return nil
+	}
+	f := fsslice.Filter{
+		FsSlice: []types.FieldSpec{
+			{Path: metaNamespaceField, CreateIfNotPresent: true},
+		},
+		SetValue:   fsslice.SetScalar(ns.Namespace),
+		CreateKind: yaml.ScalarNode, // Namespace is a ScalarNode
+	}
+	_, err := f.Filter(obj)
+	return err
+}
+
+// roleBindingHack is a hack for implementing the namespace transform
+// for RoleBinding and ClusterRoleBinding resource types.
+// RoleBinding and ClusterRoleBinding have namespace set on
+// elements of the "subjects" field if and only if the subject elements
+// "name" is "default".  Otherwise the namespace is not set.
+//
+// Example:
+//
+// kind: RoleBinding
+// subjects:
+// - name: "default" # this will have the namespace set
+//   ...
+// - name: "something-else" # this will not have the namespace set
+//   ...
+func (ns Filter) roleBindingHack(obj *yaml.RNode, meta yaml.ResourceMeta) error {
+	if meta.Kind != roleBindingKind && meta.Kind != clusterRoleBindingKind {
+		return nil
+	}
+
+	// Lookup the namespace field on all elements.
+	// We should change the fieldspec so this isn't necessary.
+	obj, err := obj.Pipe(yaml.Lookup(subjectsField))
+	if err != nil || yaml.IsEmpty(obj) {
+		return err
+	}
+
+	// add the namespace to each "subject" with name: default
+	err = obj.VisitElements(func(o *yaml.RNode) error {
+		// copied from kunstruct based kustomize NamespaceTransformer plugin
+		// The only case we need to force the namespace
+		// if for the "service account". "default" is
+		// kind of hardcoded here for right now.
+		name, err := o.Pipe(
+			yaml.Lookup("name"), yaml.Match("default"),
+		)
+		if err != nil || yaml.IsEmpty(name) {
+			return err
+		}
+
+		// set the namespace for the default account
+		v := yaml.NewScalarRNode(ns.Namespace)
+		return o.PipeE(
+			yaml.LookupCreate(yaml.ScalarNode, "namespace"),
+			yaml.FieldSetter{Value: v},
+		)
+	})
+
+	return err
+}
+
+// removeFieldSpecsForHacks removes from the list fieldspecs that
+// have hardcoded implementations
+func (ns Filter) removeFieldSpecsForHacks(fs types.FsSlice) types.FsSlice {
+	var val types.FsSlice
+	for i := range fs {
+		// implemented by metaNamespaceHack
+		if fs[i].Path == metaNamespaceField {
+			continue
+		}
+		// implemented by roleBindingHack
+		if fs[i].Kind == roleBindingKind && fs[i].Path == subjectsField {
+			continue
+		}
+		// implemented by roleBindingHack
+		if fs[i].Kind == clusterRoleBindingKind && fs[i].Path == subjectsField {
+			continue
+		}
+		val = append(val, fs[i])
+	}
+	return val
+}
+
+const (
+	metaNamespaceField     = "metadata/namespace"
+	subjectsField          = "subjects"
+	roleBindingKind        = "RoleBinding"
+	clusterRoleBindingKind = "ClusterRoleBinding"
+)

api/filters/namespace/namespace_test.go

@@ -0,0 +1,280 @@
+// Copyright 2019 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package namespace_test
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"sigs.k8s.io/kustomize/api/filters/namespace"
+	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
+	filtertest_test "sigs.k8s.io/kustomize/api/testutils/filtertest"
+	"sigs.k8s.io/kustomize/api/types"
+)
+
+var tests = []TestCase{
+	{
+		name: "add",
+		input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+`,
+		expected: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  namespace: foo
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+  namespace: foo
+`,
+		filter: namespace.Filter{Namespace: "foo"},
+	},
+
+	{
+		name: "add-recurse",
+		input: `
+apiVersion: example.com/v1
+kind: Foo
+---
+apiVersion: example.com/v1
+kind: Bar
+`,
+		expected: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  namespace: foo
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  namespace: foo
+`,
+		filter: namespace.Filter{Namespace: "foo"},
+	},
+
+	{
+		name: "update",
+		input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  # update this namespace
+  namespace: bar
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+  namespace: bar
+`,
+		expected: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  # update this namespace
+  namespace: foo
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+  namespace: foo
+`,
+		filter: namespace.Filter{Namespace: "foo"},
+	},
+
+	{
+		name: "update-rolebinding",
+		input: `
+apiVersion: example.com/v1
+kind: RoleBinding
+subjects:
+- name: default
+---
+apiVersion: example.com/v1
+kind: RoleBinding
+subjects:
+- name: default
+  namespace: foo
+---
+apiVersion: example.com/v1
+kind: RoleBinding
+subjects:
+- name: something
+---
+apiVersion: example.com/v1
+kind: RoleBinding
+subjects:
+- name: something
+  namespace: foo
+`,
+		expected: `
+apiVersion: example.com/v1
+kind: RoleBinding
+subjects:
+- name: default
+  namespace: bar
+metadata:
+  namespace: bar
+---
+apiVersion: example.com/v1
+kind: RoleBinding
+subjects:
+- name: default
+  namespace: bar
+metadata:
+  namespace: bar
+---
+apiVersion: example.com/v1
+kind: RoleBinding
+subjects:
+- name: something
+metadata:
+  namespace: bar
+---
+apiVersion: example.com/v1
+kind: RoleBinding
+subjects:
+- name: something
+  namespace: foo
+metadata:
+  namespace: bar
+`,
+		filter: namespace.Filter{Namespace: "bar"},
+	},
+
+	{
+		name: "update-clusterrolebinding",
+		input: `
+apiVersion: example.com/v1
+kind: ClusterRoleBinding
+subjects:
+- name: default
+---
+apiVersion: example.com/v1
+kind: ClusterRoleBinding
+subjects:
+- name: default
+  namespace: foo
+---
+apiVersion: example.com/v1
+kind: ClusterRoleBinding
+subjects:
+- name: something
+---
+apiVersion: example.com/v1
+kind: ClusterRoleBinding
+subjects:
+- name: something
+  namespace: foo
+`,
+		expected: `
+apiVersion: example.com/v1
+kind: ClusterRoleBinding
+subjects:
+- name: default
+  namespace: bar
+---
+apiVersion: example.com/v1
+kind: ClusterRoleBinding
+subjects:
+- name: default
+  namespace: bar
+---
+apiVersion: example.com/v1
+kind: ClusterRoleBinding
+subjects:
+- name: something
+---
+apiVersion: example.com/v1
+kind: ClusterRoleBinding
+subjects:
+- name: something
+  namespace: foo
+`,
+		filter: namespace.Filter{Namespace: "bar"},
+	},
+
+	{
+		name: "data-fieldspecs",
+		input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+`,
+		expected: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+  namespace: foo
+a:
+  b:
+    c: foo
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+  namespace: foo
+a:
+  b:
+    c: foo
+`,
+		filter: namespace.Filter{Namespace: "foo"},
+		fsslice: []types.FieldSpec{
+			{
+				Path:               "a/b/c",
+				CreateIfNotPresent: true,
+			},
+		},
+	},
+}
+
+type TestCase struct {
+	name     string
+	input    string
+	expected string
+	filter   namespace.Filter
+	fsslice  types.FsSlice
+}
+
+var config = builtinconfig.MakeDefaultConfig()
+
+func TestNamespace_Filter(t *testing.T) {
+	for i := range tests {
+		test := tests[i]
+		t.Run(test.name, func(t *testing.T) {
+			test.filter.FsSlice = append(config.NameSpace, test.fsslice...)
+			if !assert.Equal(t,
+				strings.TrimSpace(test.expected),
+				strings.TrimSpace(
+					filtertest_test.RunFilter(t, test.input, test.filter))) {
+				t.FailNow()
+			}
+		})
+	}
+}

api/filters/patchjson6902/doc.go

@@ -0,0 +1,6 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+// Package namespace contains a kio.Filter implementation of the kustomize
+// patchjson6902 transformer
+package patchjson6902

api/filters/patchjson6902/example_test.go

@@ -0,0 +1,55 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package patchjson6902
+
+import (
+	"bytes"
+	"log"
+	"os"
+
+	"sigs.k8s.io/kustomize/kyaml/kio"
+)
+
+func ExampleFilter() {
+	err := kio.Pipeline{
+		Inputs: []kio.Reader{&kio.ByteReader{Reader: bytes.NewBufferString(`
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+  namespace: bar
+`)}},
+		Filters: []kio.Filter{
+			Filter{
+				Patch: `
+- op: replace
+  path: /metadata/namespace
+  value: "ns"
+`,
+			},
+		},
+		Outputs: []kio.Writer{kio.ByteWriter{Writer: os.Stdout}},
+	}.Execute()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	// Output:
+	// apiVersion: example.com/v1
+	// kind: Foo
+	// metadata:
+	//   name: instance
+	//   namespace: ns
+	// ---
+	// apiVersion: example.com/v1
+	// kind: Bar
+	// metadata:
+	//   name: instance
+	//   namespace: ns
+}

api/filters/patchjson6902/patchjson6902.go

@@ -0,0 +1,65 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package patchjson6902
+
+import (
+	"strings"
+
+	jsonpatch "github.com/evanphx/json-patch"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+	k8syaml "sigs.k8s.io/yaml"
+)
+
+type Filter struct {
+	Patch string
+
+	decodedPatch jsonpatch.Patch
+}
+
+var _ kio.Filter = Filter{}
+
+func (pf Filter) Filter(nodes []*yaml.RNode) ([]*yaml.RNode, error) {
+	decodedPatch, err := pf.decodePatch()
+	if err != nil {
+		return nil, err
+	}
+	pf.decodedPatch = decodedPatch
+	return kio.FilterAll(yaml.FilterFunc(pf.run)).Filter(nodes)
+}
+
+func (pf Filter) decodePatch() (jsonpatch.Patch, error) {
+	patch := pf.Patch
+	// If the patch doesn't look like a JSON6902 patch, we
+	// try to parse it to json.
+	if !strings.HasPrefix(pf.Patch, "[") {
+		p, err := k8syaml.YAMLToJSON([]byte(patch))
+		if err != nil {
+			return nil, err
+		}
+		patch = string(p)
+	}
+	decodedPatch, err := jsonpatch.DecodePatch([]byte(patch))
+	if err != nil {
+		return nil, err
+	}
+	return decodedPatch, nil
+}
+
+func (pf Filter) run(node *yaml.RNode) (*yaml.RNode, error) {
+	// We don't actually use the kyaml library for manipulating the
+	// yaml here. We just marshal it to json and rely on the
+	// jsonpatch library to take care of applying the patch.
+	// This means ordering might not be preserved with this filter.
+	b, err := node.MarshalJSON()
+	if err != nil {
+		return nil, err
+	}
+	res, err := pf.decodedPatch.Apply(b)
+	if err != nil {
+		return nil, err
+	}
+	err = node.UnmarshalJSON(res)
+	return node, err
+}

api/filters/patchjson6902/patchjson6902_test.go

@@ -0,0 +1,173 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package patchjson6902
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	filtertest "sigs.k8s.io/kustomize/api/testutils/filtertest"
+)
+
+const input = `
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: myDeploy
+spec:
+  replica: 2
+  template:
+    metadata:
+      labels:
+        old-label: old-value
+    spec:
+      containers:
+      - image: nginx
+        name: nginx
+`
+
+func TestSomething(t *testing.T) {
+	testCases := []struct {
+		testName       string
+		input          string
+		filter         Filter
+		expectedOutput string
+	}{
+		{
+			testName: "single operation, json",
+			input:    input,
+			filter: Filter{
+				Patch: `[
+{"op": "replace", "path": "/spec/replica", "value": 5}
+]`,
+			},
+			expectedOutput: `
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: myDeploy
+spec:
+  replica: 5
+  template:
+    metadata:
+      labels:
+        old-label: old-value
+    spec:
+      containers:
+      - image: nginx
+        name: nginx
+`,
+		},
+		{
+			testName: "multiple operations, json",
+			input:    input,
+			filter: Filter{
+				Patch: `[
+{"op": "replace", "path": "/spec/template/spec/containers/0/name", "value": "my-nginx"},
+{"op": "add", "path": "/spec/replica", "value": 999},
+{"op": "add", "path": "/spec/template/spec/containers/0/command", "value": ["arg1", "arg2", "arg3"]}
+]`,
+			},
+			expectedOutput: `
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: myDeploy
+spec:
+  replica: 999
+  template:
+    metadata:
+      labels:
+        old-label: old-value
+    spec:
+      containers:
+      - command:
+        - arg1
+        - arg2
+        - arg3
+        image: nginx
+        name: my-nginx
+`,
+		},
+		{
+			testName: "single operation, yaml",
+			input:    input,
+			filter: Filter{
+				Patch: `
+- op: replace
+  path: /spec/replica
+  value: 5
+`,
+			},
+			expectedOutput: `
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: myDeploy
+spec:
+  replica: 5
+  template:
+    metadata:
+      labels:
+        old-label: old-value
+    spec:
+      containers:
+      - image: nginx
+        name: nginx
+`,
+		},
+		{
+			testName: "multiple operations, yaml",
+			input:    input,
+			filter: Filter{
+				Patch: `
+- op: replace
+  path: /spec/template/spec/containers/0/name
+  value: my-nginx
+- op: add
+  path: /spec/replica
+  value: 999
+- op: add
+  path: /spec/template/spec/containers/0/command
+  value:
+  - arg1
+  - arg2
+  - arg3
+`,
+			},
+			expectedOutput: `
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: myDeploy
+spec:
+  replica: 999
+  template:
+    metadata:
+      labels:
+        old-label: old-value
+    spec:
+      containers:
+      - command:
+        - arg1
+        - arg2
+        - arg3
+        image: nginx
+        name: my-nginx
+`,
+		},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.testName, func(t *testing.T) {
+			if !assert.Equal(t,
+				strings.TrimSpace(tc.expectedOutput),
+				strings.TrimSpace(
+					filtertest.RunFilter(t, tc.input, tc.filter))) {
+				t.FailNow()
+			}
+		})
+	}
+}

api/filters/patchstrategicmerge/doc.go

@@ -0,0 +1,6 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+// Package patchstrategicmerge contains a kio.Filter implementation of the
+// kustomize strategic merge patch transformer.
+package patchstrategicmerge

api/filters/patchstrategicmerge/example_test.go

@@ -0,0 +1,49 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package patchstrategicmerge
+
+import (
+	"bytes"
+	"log"
+	"os"
+
+	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+func ExampleFilter() {
+	err := kio.Pipeline{
+		Inputs: []kio.Reader{&kio.ByteReader{Reader: bytes.NewBufferString(`
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  replicas: 3
+`)}},
+		Filters: []kio.Filter{Filter{
+			Patch: yaml.MustParse(`
+spec:
+  template:
+    containers:
+    - image: nginx
+`),
+		}},
+		Outputs: []kio.Writer{kio.ByteWriter{Writer: os.Stdout}},
+	}.Execute()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	// Output:
+	// apiVersion: example.com/v1
+	// kind: Foo
+	// metadata:
+	//   name: instance
+	// spec:
+	//   replicas: 3
+	//   template:
+	//     containers:
+	//     - image: nginx
+}

api/filters/patchstrategicmerge/patchstrategicmerge.go

@@ -0,0 +1,21 @@
+package patchstrategicmerge
+
+import (
+	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+	"sigs.k8s.io/kustomize/kyaml/yaml/merge2"
+)
+
+type Filter struct {
+	Patch *yaml.RNode
+}
+
+var _ kio.Filter = Filter{}
+
+func (pf Filter) Filter(nodes []*yaml.RNode) ([]*yaml.RNode, error) {
+	return kio.FilterAll(yaml.FilterFunc(pf.run)).Filter(nodes)
+}
+
+func (pf Filter) run(node *yaml.RNode) (*yaml.RNode, error) {
+	return merge2.Merge(pf.Patch, node)
+}

api/filters/patchstrategicmerge/patchstrategicmerge_test.go

@@ -0,0 +1,82 @@
+package patchstrategicmerge
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	filtertest "sigs.k8s.io/kustomize/api/testutils/filtertest"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+func TestFilter(t *testing.T) {
+	testCases := map[string]struct {
+		input    string
+		patch    *yaml.RNode
+		expected string
+	}{
+		"simple patch": {
+			input: `
+apiVersion: apps/v1
+metadata:
+  name: myDeploy
+kind: Deployment
+`,
+			patch: yaml.MustParse(`
+metadata:
+  name: yourDeploy
+`),
+			expected: `
+apiVersion: apps/v1
+metadata:
+  name: yourDeploy
+kind: Deployment
+`,
+		},
+		"nested patch": {
+			input: `
+apiVersion: apps/v1
+metadata:
+  name: myDeploy
+kind: Deployment
+spec:
+  containers:
+  - name: nginx
+    args:
+    - abc
+`,
+			patch: yaml.MustParse(`
+spec:
+  containers:
+  - name: nginx
+    args:
+    - def
+`),
+			expected: `
+apiVersion: apps/v1
+metadata:
+  name: myDeploy
+kind: Deployment
+spec:
+  containers:
+  - name: nginx
+    args:
+    - def
+`,
+		},
+	}
+
+	for tn, tc := range testCases {
+		t.Run(tn, func(t *testing.T) {
+			f := Filter{
+				Patch: tc.patch,
+			}
+			if !assert.Equal(t,
+				strings.TrimSpace(tc.expected),
+				strings.TrimSpace(
+					filtertest.RunFilter(t, tc.input, f))) {
+				t.FailNow()
+			}
+		})
+	}
+}

api/filters/prefixsuffix/doc.go

@@ -0,0 +1,6 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+// Package prefixsuffix contains a kio.Filter implementation of the kustomize
+// PrefixSuffixTransformer.
+package prefixsuffix

api/filters/prefixsuffix/example_test.go

@@ -0,0 +1,47 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package prefixsuffix_test
+
+import (
+	"bytes"
+	"log"
+	"os"
+
+	"sigs.k8s.io/kustomize/api/filters/prefixsuffix"
+	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+)
+
+func ExampleFilter() {
+	fss := builtinconfig.MakeDefaultConfig().NamePrefix
+	err := kio.Pipeline{
+		Inputs: []kio.Reader{&kio.ByteReader{Reader: bytes.NewBufferString(`
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+`)}},
+		Filters: []kio.Filter{prefixsuffix.Filter{Prefix: "baz-", FsSlice: fss}},
+		Outputs: []kio.Writer{kio.ByteWriter{Writer: os.Stdout}},
+	}.Execute()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	// Output:
+	// apiVersion: example.com/v1
+	// kind: Foo
+	// metadata:
+	//   name: baz-instance
+	// ---
+	// apiVersion: example.com/v1
+	// kind: Bar
+	// metadata:
+	//   name: baz-instance
+}

api/filters/prefixsuffix/prefixsuffix.go

@@ -0,0 +1,43 @@
+// Copyright 2019 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package prefixsuffix
+
+import (
+	"fmt"
+
+	"sigs.k8s.io/kustomize/api/filters/fsslice"
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+// Filter applies resource name prefix's and suffix's using the fieldSpecs
+type Filter struct {
+	Prefix string `json:"prefix,omitempty" yaml:"prefix,omitempty"`
+	Suffix string `json:"suffix,omitempty" yaml:"suffix,omitempty"`
+
+	FsSlice types.FsSlice `json:"fieldSpecs,omitempty" yaml:"fieldSpecs,omitempty"`
+}
+
+var _ kio.Filter = Filter{}
+
+func (ns Filter) Filter(nodes []*yaml.RNode) ([]*yaml.RNode, error) {
+	return kio.FilterAll(yaml.FilterFunc(ns.run)).Filter(nodes)
+}
+
+// Run runs the filter on a single node rather than a slice
+func (ns Filter) run(node *yaml.RNode) (*yaml.RNode, error) {
+	// transformations based on data -- :)
+	err := node.PipeE(fsslice.Filter{
+		FsSlice:    ns.FsSlice,
+		SetValue:   ns.set,
+		CreateKind: yaml.ScalarNode, // Name is a ScalarNode
+	})
+	return node, err
+}
+
+func (ns Filter) set(node *yaml.RNode) error {
+	return fsslice.SetScalar(fmt.Sprintf(
+		"%s%s%s", ns.Prefix, node.YNode().Value, ns.Suffix))(node)
+}

api/filters/prefixsuffix/prefixsuffix_test.go

@@ -0,0 +1,167 @@
+// Copyright 2019 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package prefixsuffix_test
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"sigs.k8s.io/kustomize/api/filters/prefixsuffix"
+	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
+	filtertest_test "sigs.k8s.io/kustomize/api/testutils/filtertest"
+	"sigs.k8s.io/kustomize/api/types"
+)
+
+var tests = []TestCase{
+	{
+		name: "prefix",
+		input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+`,
+		expected: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: foo-instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: foo-instance
+`,
+		filter: prefixsuffix.Filter{Prefix: "foo-"},
+	},
+
+	{
+		name: "suffix",
+		input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+`,
+		expected: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance-foo
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance-foo
+`,
+		filter: prefixsuffix.Filter{Suffix: "-foo"},
+	},
+
+	{
+		name: "prefix-suffix",
+		input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+`,
+		expected: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: bar-instance-foo
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: bar-instance-foo
+`,
+		filter: prefixsuffix.Filter{Prefix: "bar-", Suffix: "-foo"},
+	},
+
+	{
+		name: "data-fieldspecs",
+		input: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+a:
+  b:
+    c: d
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+a:
+  b:
+    c: d
+`,
+		expected: `
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: foo-instance
+a:
+  b:
+    c: foo-d
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: foo-instance
+a:
+  b:
+    c: foo-d
+`,
+		filter: prefixsuffix.Filter{Prefix: "foo-"},
+		fsslice: []types.FieldSpec{
+			{
+				Path: "a/b/c",
+			},
+		},
+	},
+}
+
+type TestCase struct {
+	name     string
+	input    string
+	expected string
+	filter   prefixsuffix.Filter
+	fsslice  types.FsSlice
+}
+
+var config = builtinconfig.MakeDefaultConfig()
+
+func TestFilter(t *testing.T) {
+	for i := range tests {
+		test := tests[i]
+		t.Run(test.name, func(t *testing.T) {
+			test.filter.FsSlice = append(config.NamePrefix, test.fsslice...)
+			if !assert.Equal(t,
+				strings.TrimSpace(test.expected),
+				strings.TrimSpace(
+					filtertest_test.RunFilter(t, test.input, test.filter))) {
+				t.FailNow()
+			}
+		})
+	}
+}

api/filters/replicacount/doc.go

@@ -0,0 +1,6 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+// Package replicacount contains a kio.Filter implementation of the kustomize
+// ReplicaCountTransformer.
+package replicacount

api/filters/replicacount/example_test.go

@@ -0,0 +1,64 @@
+package replicacount
+
+import (
+	"bytes"
+	"log"
+	"os"
+
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+)
+
+func ExampleFilter() {
+	err := kio.Pipeline{
+		Inputs: []kio.Reader{&kio.ByteReader{Reader: bytes.NewBufferString(`
+apiVersion: example.com/v1
+kind: Foo
+metadata:
+  name: instance
+spec:
+  template:
+    replicas: 5
+---
+apiVersion: example.com/v1
+kind: Bar
+metadata:
+  name: instance
+spec:
+  template:
+    replicas: 5
+`)}},
+		Filters: []kio.Filter{Filter{
+			Replica: types.Replica{
+				Count: 42,
+				Name:  "instance",
+			},
+			FsSlice: types.FsSlice{
+				{
+					Path: "spec/template/replicas",
+				},
+			},
+		}},
+		Outputs: []kio.Writer{kio.ByteWriter{Writer: os.Stdout}},
+	}.Execute()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	// Output:
+	// apiVersion: example.com/v1
+	// kind: Foo
+	// metadata:
+	//   name: instance
+	// spec:
+	//   template:
+	//     replicas: 42
+	// ---
+	// apiVersion: example.com/v1
+	// kind: Bar
+	// metadata:
+	//   name: instance
+	// spec:
+	//   template:
+	//     replicas: 42
+}

api/filters/replicacount/replicacount.go

@@ -0,0 +1,48 @@
+package replicacount
+
+import (
+	"strconv"
+
+	"sigs.k8s.io/kustomize/api/filters/fsslice"
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+// Filter updates/sets replicas fields using the fieldSpecs
+type Filter struct {
+	Replica types.Replica `json:"replica,omitempty" yaml:"replica,omitempty"`
+
+	// FsSlice contains the FieldSpecs to locate the namespace field
+	FsSlice types.FsSlice `json:"fieldSpecs,omitempty" yaml:"fieldSpecs,omitempty"`
+}
+
+var _ kio.Filter = Filter{}
+
+func (rc Filter) Filter(nodes []*yaml.RNode) ([]*yaml.RNode, error) {
+	return kio.FilterAll(yaml.FilterFunc(rc.run)).Filter(nodes)
+}
+
+// run processes each node individually.
+func (rc Filter) run(node *yaml.RNode) (*yaml.RNode, error) {
+	meta, err := node.GetMeta()
+	if err != nil {
+		return nil, err
+	}
+
+	// only update resources where the name matches the Replica name.
+	if meta.Name != rc.Replica.Name {
+		return node, nil
+	}
+
+	err = node.PipeE(fsslice.Filter{
+		FsSlice:    rc.FsSlice,
+		SetValue:   rc.set,
+		CreateKind: yaml.ScalarNode, // replicas is a ScalarNode
+	})
+	return node, err
+}
+
+func (rc Filter) set(node *yaml.RNode) error {
+	return fsslice.SetScalar(strconv.FormatInt(rc.Replica.Count, 10))(node)
+}

api/filters/replicacount/replicacount_test.go

@@ -0,0 +1,164 @@
+package replicacount
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
+	filtertest_test "sigs.k8s.io/kustomize/api/testutils/filtertest"
+	"sigs.k8s.io/kustomize/api/types"
+)
+
+func TestFilter(t *testing.T) {
+	var config = builtinconfig.MakeDefaultConfig()
+
+	testCases := map[string]struct {
+		input    string
+		expected string
+		filter   Filter
+		fsslice  types.FsSlice
+	}{
+		"update field": {
+			input: `
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dep
+spec:
+  replicas: 5
+`,
+			expected: `
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: dep
+spec:
+  replicas: 42
+`,
+			filter: Filter{
+				Replica: types.Replica{
+					Name:  "dep",
+					Count: 42,
+				},
+			},
+			fsslice: types.FsSlice{
+				{
+					Path: "spec/replicas",
+				},
+			},
+		},
+		"add field": {
+			input: `
+apiVersion: custom/v1
+kind: Custom
+metadata:
+  name: cus
+spec:
+  template:
+    other: something
+`,
+			expected: `
+apiVersion: custom/v1
+kind: Custom
+metadata:
+  name: cus
+spec:
+  template:
+    other: something
+    replicas: 42
+`,
+			filter: Filter{
+				Replica: types.Replica{
+					Name:  "cus",
+					Count: 42,
+				},
+			},
+			fsslice: types.FsSlice{
+				{
+					Path:               "spec/template/replicas",
+					CreateIfNotPresent: true,
+				},
+			},
+		},
+		"no update if CreateIfNotPresent is false": {
+			input: `
+apiVersion: custom/v1
+kind: Custom
+metadata:
+  name: cus
+spec:
+  template:
+    other: something
+`,
+			expected: `
+apiVersion: custom/v1
+kind: Custom
+metadata:
+  name: cus
+spec:
+  template:
+    other: something
+`,
+			filter: Filter{
+				Replica: types.Replica{
+					Name:  "cus",
+					Count: 42,
+				},
+			},
+			fsslice: types.FsSlice{
+				{
+					Path: "spec/template/replicas",
+				},
+			},
+		},
+		"update multiple fields": {
+			input: `
+apiVersion: custom/v1
+kind: Custom
+metadata:
+  name: cus
+spec:
+  replicas: 5
+  template:
+    replicas: 5
+`,
+			expected: `
+apiVersion: custom/v1
+kind: Custom
+metadata:
+  name: cus
+spec:
+  replicas: 42
+  template:
+    replicas: 42
+`,
+			filter: Filter{
+				Replica: types.Replica{
+					Name:  "cus",
+					Count: 42,
+				},
+			},
+			fsslice: types.FsSlice{
+				{
+					Path: "spec/template/replicas",
+				},
+				{
+					Path: "spec/replicas",
+				},
+			},
+		},
+	}
+
+	for tn, tc := range testCases {
+		t.Run(tn, func(t *testing.T) {
+			tc.filter.FsSlice = append(config.Replicas, tc.fsslice...)
+			if !assert.Equal(t,
+				strings.TrimSpace(tc.expected),
+				strings.TrimSpace(
+					filtertest_test.RunFilter(t, tc.input, tc.filter))) {
+				t.FailNow()
+			}
+		})
+	}
+}

api/go.mod

@@ -4,15 +4,18 @@ go 1.13
 
 require (
 	github.com/evanphx/json-patch v4.5.0+incompatible
-	github.com/go-openapi/spec v0.19.4
+	github.com/go-openapi/spec v0.19.5
 	github.com/golangci/golangci-lint v1.21.0
 	github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510
 	github.com/pkg/errors v0.8.1
+	github.com/stretchr/testify v1.4.0
+	github.com/yujunz/go-getter v1.4.1-lite
 	golang.org/x/tools v0.0.0-20191010075000-0337d82405ff
-	gopkg.in/yaml.v2 v2.2.4
+	gopkg.in/yaml.v2 v2.2.7
 	k8s.io/api v0.17.0
 	k8s.io/apimachinery v0.17.0
 	k8s.io/client-go v0.17.0
 	k8s.io/kube-openapi v0.0.0-20191107075043-30be4d16710a
+	sigs.k8s.io/kustomize/kyaml v0.1.5
 	sigs.k8s.io/yaml v1.1.0
 )

api/go.sum

@@ -1,6 +1,7 @@
 cloud.google.com/go v0.26.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw=
 cloud.google.com/go v0.34.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw=
 cloud.google.com/go v0.38.0/go.mod h1:990N+gfupTy94rShfmMCWGDn0LpTmnzTp2qbd1dvSRU=
+github.com/360EntSecGroup-Skylar/excelize v1.4.1/go.mod h1:vnax29X2usfl7HHkBrX5EvSCJcmH3dT9luvxzu8iGAE=
 github.com/Azure/go-autorest/autorest v0.9.0/go.mod h1:xyHB1BMZT0cuDHU7I0+g046+BFDTQ8rEZB0s4Yfa6bI=
 github.com/Azure/go-autorest/autorest/adal v0.5.0/go.mod h1:8Z9fGy2MpX0PvDjB1pEgQTmVqjGhiHBW7RJJEciWzS0=
 github.com/Azure/go-autorest/autorest/date v0.1.0/go.mod h1:plvfp3oPSKwf2DNjlBjWF/7vwR+cUD/ELuzDCXwHUVA=
@@ -14,6 +15,7 @@ github.com/NYTimes/gziphandler v0.0.0-20170623195520-56545f4a5d46/go.mod h1:3wb0
 github.com/OneOfOne/xxhash v1.2.2/go.mod h1:HSdplMjZKSmBqAxg5vPj2TmRDmfkzw+cTzAElWljhcU=
 github.com/OpenPeeDeeP/depguard v1.0.1 h1:VlW4R6jmBIv3/u1JNlawEvJMM4J+dPORPaZasQee8Us=
 github.com/OpenPeeDeeP/depguard v1.0.1/go.mod h1:xsIw86fROiiwelg+jB2uM9PiKihMMmUx/1V+TNhjQvM=
+github.com/PuerkitoBio/goquery v1.5.0/go.mod h1:qD2PgZ9lccMbQlc7eEOjaeRlFQON7xY8kdmcsrnKqMg=
 github.com/PuerkitoBio/purell v1.0.0/go.mod h1:c11w/QuzBsJSee3cPx9rAFu61PvFxuPbtSwDGJws/X0=
 github.com/PuerkitoBio/purell v1.1.1 h1:WEQqlqaGbrPkxLJWfBwQmfEAE1Z7ONdDLqrN38tNFfI=
 github.com/PuerkitoBio/purell v1.1.1/go.mod h1:c11w/QuzBsJSee3cPx9rAFu61PvFxuPbtSwDGJws/X0=
@@ -23,12 +25,18 @@ github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578/go.mod h1:uGdko
 github.com/StackExchange/wmi v0.0.0-20180116203802-5d049714c4a6/go.mod h1:3eOhrUMpNV+6aFIbp5/iudMxNCF27Vw2OZgy4xEx0Fg=
 github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
 github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
+github.com/andybalholm/cascadia v1.0.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
 github.com/armon/consul-api v0.0.0-20180202201655-eb2c6b5be1b6/go.mod h1:grANhF5doyWs3UAsr3K4I6qtAmlQcZDesFNEHPZAzj8=
 github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973/go.mod h1:Dwedo/Wpr24TaqPxmxbtue+5NUziq4I4S80YR8gNf3Q=
 github.com/beorn7/perks v1.0.0/go.mod h1:KWe93zE9D1o94FZ5RNwFwVgaQK1VOXiVxmqh+CedLV8=
+github.com/bgentry/go-netrc v0.0.0-20140422174119-9fd32a8b3d3d h1:xDfNPAt8lFiC1UJrqV3uuy861HCTo708pDMbjHHdCas=
+github.com/bgentry/go-netrc v0.0.0-20140422174119-9fd32a8b3d3d/go.mod h1:6QX/PXZ00z/TKoufEY6K/a0k6AhaJrQKdFe6OfVXsa4=
 github.com/bombsimon/wsl v1.2.5 h1:9gTOkIwVtoDZywvX802SDHokeX4kW1cKnV8ZTVAPkRs=
 github.com/bombsimon/wsl v1.2.5/go.mod h1:43lEF/i0kpXbLCeDXL9LMT8c92HyBywXb0AsgMHYngM=
 github.com/cespare/xxhash v1.1.0/go.mod h1:XrSqR1VqqWfGrhpAt58auRo0WTKS1nRRg3ghfAqPWnc=
+github.com/chzyer/logex v1.1.10/go.mod h1:+Ywpsq7O8HXn0nuIou7OrIPyXbp3wmkHB+jjWRnGsAI=
+github.com/chzyer/readline v0.0.0-20180603132655-2972be24d48e/go.mod h1:nSuG5e5PlCu98SY8svDHJxuZscDgtXS6KTTbou5AhLI=
+github.com/chzyer/test v0.0.0-20180213035817-a1ea475d72b1/go.mod h1:Q3SI9o4m/ZMnBNeIyt5eFwwo7qiLfzFZmjNmxjkiQlU=
 github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
 github.com/coreos/bbolt v1.3.2/go.mod h1:iRUV2dpdMOn7Bo10OQBFzIJO9kkE559Wcmn+qkEiiKk=
 github.com/coreos/etcd v3.3.10+incompatible/go.mod h1:uF7uidLiAD3TWHmW31ZFd/JWoc32PjwdhPthX9715RE=
@@ -45,6 +53,7 @@ github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSs
 github.com/dgrijalva/jwt-go v3.2.0+incompatible/go.mod h1:E3ru+11k8xSBh+hMPgOLZmtrrCbhqsmaPHjLKYnJCaQ=
 github.com/dgryski/go-sip13 v0.0.0-20181026042036-e10d5fee7954/go.mod h1:vAd38F8PWV+bWy6jNmig1y/TA+kYO4g3RSRF0IAv0no=
 github.com/docker/spdystream v0.0.0-20160310174837-449fdfce4d96/go.mod h1:Qh8CwZgvJUkLughtfhJv5dyTYa91l1fOUCrgjqmcifM=
+github.com/dustmop/soup v1.1.2-0.20190516214245-38228baa104e/go.mod h1:CgNC6SGbT+Xb8wGGvzilttZL1mc5sQ/5KkcxsZttMIk=
 github.com/elazarl/goproxy v0.0.0-20170405201442-c4fc26588b6e/go.mod h1:/Zj4wYkgs4iZTTu3o/KG3Itv/qCCa8VVMlb3i9OVuzc=
 github.com/emicklei/go-restful v0.0.0-20170410110728-ff4f55a20633 h1:H2pdYOb3KQ1/YsqVWoWNLQO+fusocsw354rqGTZtAgw=
 github.com/emicklei/go-restful v0.0.0-20170410110728-ff4f55a20633/go.mod h1:otzb+WCGbkyDHkqmQmT5YD2WR4BBwUdeQoFo8l/7tVs=
@@ -59,6 +68,8 @@ github.com/ghodss/yaml v0.0.0-20150909031657-73d445a93680/go.mod h1:4dBDuWmgqj2H
 github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
 github.com/go-critic/go-critic v0.3.5-0.20190904082202-d79a9f0c64db h1:GYXWx7Vr3+zv833u+8IoXbNnQY0AdXsxAgI0kX7xcwA=
 github.com/go-critic/go-critic v0.3.5-0.20190904082202-d79a9f0c64db/go.mod h1:+sE8vrLDS2M0pZkBk0wy6+nLdKexVDrl/jBqQOTDThA=
+github.com/go-errors/errors v1.0.1 h1:LUHzmkK3GUKUrL/1gfBUxAHzcev3apQlezX/+O7ma6w=
+github.com/go-errors/errors v1.0.1/go.mod h1:f4zRHt4oKfwPJE5k8C9vpYG+aDHdBFUsgrm6/TyX73Q=
 github.com/go-kit/kit v0.8.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
 github.com/go-lintpack/lintpack v0.5.2 h1:DI5mA3+eKdWeJ40nU4d6Wc26qmdG8RCi/btYq0TuRN0=
 github.com/go-lintpack/lintpack v0.5.2/go.mod h1:NwZuYi2nUHho8XEIZ6SIxihrnPoqBTDqfpXvXAN0sXM=
@@ -74,8 +85,8 @@ github.com/go-openapi/jsonreference v0.0.0-20160704190145-13c6e3589ad9/go.mod h1
 github.com/go-openapi/jsonreference v0.19.2 h1:o20suLFB4Ri0tuzpWtyHlh7E7HnkqTNLq6aR6WVNS1w=
 github.com/go-openapi/jsonreference v0.19.2/go.mod h1:jMjeRr2HHw6nAVajTXJ4eiUwohSTlpa0o73RUL1owJc=
 github.com/go-openapi/spec v0.0.0-20160808142527-6aced65f8501/go.mod h1:J8+jY1nAiCcj+friV/PDoE1/3eeccG9LYBs0tYvLOWc=
-github.com/go-openapi/spec v0.19.4 h1:ixzUSnHTd6hCemgtAJgluaTSGYpLNpJY4mA2DIkdOAo=
-github.com/go-openapi/spec v0.19.4/go.mod h1:FpwSN1ksY1eteniUU7X0N/BgJ7a4WvBFVA8Lj9mJglo=
+github.com/go-openapi/spec v0.19.5 h1:Xm0Ao53uqnk9QE/LlYV5DEU09UAgpliA85QoT9LzqPw=
+github.com/go-openapi/spec v0.19.5/go.mod h1:Hm2Jr4jv8G1ciIAo+frC/Ft+rR2kQDh8JHKHb3gWUSk=
 github.com/go-openapi/swag v0.0.0-20160704191624-1d0bd113de87/go.mod h1:DXUve3Dpr1UfpPtxFw+EFuQ41HhCWZfha5jSVRG7C7I=
 github.com/go-openapi/swag v0.19.2/go.mod h1:POnQmlKehdgb5mhVOsnJFsivZCEZ/vjK9gh66Z9tfKk=
 github.com/go-openapi/swag v0.19.5 h1:lTz6Ys4CmqqCQmZPBlbQENR1/GucA2bzYTE12Pw4tFY=
@@ -176,6 +187,12 @@ github.com/gregjones/httpcache v0.0.0-20180305231024-9cad4c3443a7/go.mod h1:Fecb
 github.com/grpc-ecosystem/go-grpc-middleware v1.0.0/go.mod h1:FiyG127CGDf3tlThmgyCl78X/SZQqEOJBCDaAfeWzPs=
 github.com/grpc-ecosystem/go-grpc-prometheus v1.2.0/go.mod h1:8NvIoxWQoOIhqOTXgfV/d3M/q6VIi02HzZEHgUlZvzk=
 github.com/grpc-ecosystem/grpc-gateway v1.9.0/go.mod h1:vNeuVxBJEsws4ogUvrchl83t/GYV9WGTSLVdBhOQFDY=
+github.com/hashicorp/go-cleanhttp v0.5.0 h1:wvCrVc9TjDls6+YGAF2hAifE1E5U1+b4tH6KdvN3Gig=
+github.com/hashicorp/go-cleanhttp v0.5.0/go.mod h1:JpRdi6/HCYpAwUzNwuwqhbovhLtngrth3wmdIIUrZ80=
+github.com/hashicorp/go-safetemp v1.0.0 h1:2HR189eFNrjHQyENnQMMpCiBAsRxzbTMIgBhEyExpmo=
+github.com/hashicorp/go-safetemp v1.0.0/go.mod h1:oaerMy3BhqiTbVye6QuFhFtIceqFoDHxNAB65b+Rj1I=
+github.com/hashicorp/go-version v1.1.0 h1:bPIoEKD27tNdebFGGxxYwcL4nepeY4j1QP23PFRGzg0=
+github.com/hashicorp/go-version v1.1.0/go.mod h1:fltr4n8CU8Ke44wwGCBoEymUuxUHl09ZGVZPK5anwXA=
 github.com/hashicorp/golang-lru v0.5.0/go.mod h1:/m3WP610KZHVQ1SGc6re/UDhFvYD7pJ4Ao+sR/qLZy8=
 github.com/hashicorp/golang-lru v0.5.1/go.mod h1:/m3WP610KZHVQ1SGc6re/UDhFvYD7pJ4Ao+sR/qLZy8=
 github.com/hashicorp/hcl v1.0.0 h1:0Anlzjpi4vEasTeNFn2mLJgTSwt0+6sfsiTG8qcWGx4=
@@ -205,7 +222,6 @@ github.com/kr/logfmt v0.0.0-20140226030751-b84e30acd515/go.mod h1:+0opPa2QZZtGFB
 github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
 github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
-github.com/kr/pty v1.1.5/go.mod h1:9r2w37qlBe7rQ6e1fg1S/9xpWHSnaqNdHD3WcMdbPDA=
 github.com/kr/pty v1.1.8/go.mod h1:O1sed60cT9XZ5uDucP5qwvh+TE3NnUj51EiZO/lmSfw=
 github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
@@ -225,9 +241,12 @@ github.com/mattn/go-isatty v0.0.8 h1:HLtExJ+uU2HOZ+wI0Tt5DtUDrx8yhUqDcp7fYERX4CE
 github.com/mattn/go-isatty v0.0.8/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hdxcsrc5s=
 github.com/mattn/goveralls v0.0.2/go.mod h1:8d1ZMHsd7fW6IRPKQh46F2WRpyib5/X4FOpevwGNQEw=
 github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
+github.com/mitchellh/go-homedir v1.0.0/go.mod h1:SfyaCUpYCn1Vlf4IUYiD9fPX4A5wJrkLzIz1N1q0pr0=
 github.com/mitchellh/go-homedir v1.1.0 h1:lukF9ziXFxDFPkA1vsr5zpc1XuPDn/wFntq5mG+4E0Y=
 github.com/mitchellh/go-homedir v1.1.0/go.mod h1:SfyaCUpYCn1Vlf4IUYiD9fPX4A5wJrkLzIz1N1q0pr0=
 github.com/mitchellh/go-ps v0.0.0-20190716172923-621e5597135b/go.mod h1:r1VsdOzOPt1ZSrGZWFoNhsAedKnEd6r9Np1+5blZCWk=
+github.com/mitchellh/go-testing-interface v1.0.0 h1:fzU/JVNcaqHQEcVFAKeR41fkiLdIPrefOvVG1VZ96U0=
+github.com/mitchellh/go-testing-interface v1.0.0/go.mod h1:kRemZodwjscx+RGhAo8eIhFbs2+BFgRtFPeD/KE+zxI=
 github.com/mitchellh/mapstructure v1.1.2 h1:fmNYVwqnSfB9mZU6OS2O6GsXM+wcskZDuKQzvN1EDeE=
 github.com/mitchellh/mapstructure v1.1.2/go.mod h1:FVVH3fgwuzCH5S8UJGiWEs2h04kUh9fWfEaFds41c1Y=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
@@ -237,6 +256,7 @@ github.com/modern-go/reflect2 v0.0.0-20180320133207-05fbef0ca5da/go.mod h1:bx2lN
 github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
 github.com/modern-go/reflect2 v1.0.1 h1:9f412s+6RmYXLWZSEzVVgPGK7C2PphHj5RJrvfx9AWI=
 github.com/modern-go/reflect2 v1.0.1/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
+github.com/mohae/deepcopy v0.0.0-20170929034955-c48cc78d4826/go.mod h1:TaXosZuwdSHYgviHp1DAtfrULt5eUgsSMsZf+YrPgl8=
 github.com/mozilla/tls-observatory v0.0.0-20190404164649-a3c1b6cfecfd/go.mod h1:SrKMQvPiws7F7iqYp8/TX+IhxCYhzr6N/1yb8cwHsGk=
 github.com/munnerz/goautoneg v0.0.0-20120707110453-a547fc61f48d/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
 github.com/mwitkow/go-conntrack v0.0.0-20161129095857-cc309e4a2223/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
@@ -251,6 +271,7 @@ github.com/onsi/ginkgo v1.10.1/go.mod h1:lLunBs/Ym6LB5Z9jYTR76FiuTmxDTDusOGeTQH+
 github.com/onsi/gomega v0.0.0-20170829124025-dcabb60a477c/go.mod h1:C1qb7wdrVGGVU+Z6iS04AVkA3Q65CEZX59MT0QO5uiA=
 github.com/onsi/gomega v1.7.0 h1:XPnZz8VVBHjVsy1vzJmRwIcSwiUO+JFfrv/xGiigmME=
 github.com/onsi/gomega v1.7.0/go.mod h1:ex+gbHU/CVuBBDIJjb2X0qEXbFg53c61hWP/1CpauHY=
+github.com/paulmach/orb v0.1.3/go.mod h1:VFlX/8C+IQ1p6FTRRKzKoOPJnvEtA5G0Veuqwbu//Vk=
 github.com/pelletier/go-toml v1.2.0 h1:T5zMGML61Wp+FlcbWjRDT7yAxhJNAiPPLOFECq181zc=
 github.com/pelletier/go-toml v1.2.0/go.mod h1:5z9KED0ma1S8pY6P1sdut58dfprrGBbd/94hg7ilaic=
 github.com/peterbourgon/diskv v2.0.1+incompatible/go.mod h1:uqqh8zWWbv1HBMNONnaR/tNboyR3/BZd58JJSHlUSCU=
@@ -269,12 +290,14 @@ github.com/prometheus/common v0.4.0/go.mod h1:TNfzLD0ON7rHzMJeJkieUDPYmFC7Snx/y8
 github.com/prometheus/procfs v0.0.0-20181005140218-185b4288413d/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk=
 github.com/prometheus/procfs v0.0.0-20190507164030-5867b95ac084/go.mod h1:TjEm7ze935MbeOT/UhFTIMYKhuLP4wbCsTZCD3I8kEA=
 github.com/prometheus/tsdb v0.7.1/go.mod h1:qhTCs0VvXwvX/y3TZrWD7rabWM+ijKTux40TwIPHuXU=
+github.com/qri-io/starlib v0.4.2-0.20200213133954-ff2e8cd5ef8d/go.mod h1:7DPO4domFU579Ga6E61sB9VFNaniPVwJP5C4bBCu3wA=
 github.com/quasilyte/go-consistent v0.0.0-20190521200055-c6f3937de18c/go.mod h1:5STLWrekHfjyYwxBRVRXNOSewLJ3PWfDJd1VyTS21fI=
 github.com/rogpeppe/fastuuid v0.0.0-20150106093220-6724a57986af/go.mod h1:XWv6SoW27p1b0cqNHllgS5HIMJraePCO15w5zCzIWYg=
 github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
 github.com/russross/blackfriday v1.5.2/go.mod h1:JO/DiYxRf+HjHt06OyowR9PTA263kcR/rfWxYHBV53g=
 github.com/securego/gosec v0.0.0-20191002120514-e680875ea14d h1:BzRvVq1EHuIjxpijCEKpAxzKUUMurOQ4sknehIATRh8=
 github.com/securego/gosec v0.0.0-20191002120514-e680875ea14d/go.mod h1:w5+eXa0mYznDkHaMCXA4XYffjlH+cy1oyKbfzJXa2Do=
+github.com/sergi/go-diff v1.1.0/go.mod h1:STckp+ISIX8hZLjrqAeVduY0gWCT9IjLuqbuNXdaHfM=
 github.com/shirou/gopsutil v0.0.0-20190901111213-e4ec7b275ada/go.mod h1:WWnYX4lzhCH5h/3YBfyVA3VbLYjlMZZAQcW9ojMexNc=
 github.com/shirou/w32 v0.0.0-20160930032740-bb4de0191aa4/go.mod h1:qsXQc7+bwAM3Q1u/4XEfrquwF8Lw7D7y5cD8CuHnfIc=
 github.com/shurcooL/go v0.0.0-20180423040247-9e1955d9fb6e h1:MZM7FHLqUHYI0Y/mQAt3d2aYa0SiNms/hFqC9qJYolM=
@@ -310,6 +333,7 @@ github.com/stretchr/objx v0.2.0 h1:Hbg2NidpLE8veEBkEZTL3CvlkUIVzuU9jDplZO54c48=
 github.com/stretchr/objx v0.2.0/go.mod h1:qt09Ya8vawLte6SNmTgCsAVtYtaKzEcn8ATUoHMkEqE=
 github.com/stretchr/testify v0.0.0-20151208002404-e3a8ff8ce365/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
 github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
+github.com/stretchr/testify v1.2.3-0.20181224173747-660f15d67dbb/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
 github.com/stretchr/testify v1.4.0 h1:2E4SXV/wtOkTonXsotYi4li6zVWxYlZuYNCXe9XRJyk=
 github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
@@ -318,6 +342,8 @@ github.com/timakin/bodyclose v0.0.0-20190930140734-f7f2e9bca95e/go.mod h1:Qimiff
 github.com/tmc/grpc-websocket-proxy v0.0.0-20190109142713-0ad062ec5ee5/go.mod h1:ncp9v5uamzpCO7NfCPTXjqaC+bZgJeR0sMTm6dMHP7U=
 github.com/ugorji/go v1.1.4/go.mod h1:uQMGLiO92mf5W77hV/PUCpI3pbzQx3CRekS0kk+RGrc=
 github.com/ugorji/go/codec v0.0.0-20181204163529-d75b2dcb6bc8/go.mod h1:VFNgLljTbGfSG7qAOspJ7OScBnGdDN/yBr0sguwnwf0=
+github.com/ulikunitz/xz v0.5.5 h1:pFrO0lVpTBXLpYw+pnLj6TbvHuyjXMfjGeCwSqCVwok=
+github.com/ulikunitz/xz v0.5.5/go.mod h1:2bypXElzHzzJZwzH67Y6wb67pO62Rzfn7BSiF4ABRW8=
 github.com/ultraware/funlen v0.0.2 h1:Av96YVBwwNSe4MLR7iI/BIa3VyI7/djnto/pK3Uxbdo=
 github.com/ultraware/funlen v0.0.2/go.mod h1:Dp4UiAus7Wdb9KUZsYWZEWiRzGuM2kXM1lPbfaF6xhA=
 github.com/ultraware/whitespace v0.0.4 h1:If7Va4cM03mpgrNH9k49/VOicWpGoG70XPBFFODYDsg=
@@ -329,9 +355,15 @@ github.com/valyala/fasthttp v1.2.0/go.mod h1:4vX61m6KN+xDduDNwXrhIAVZaZaZiQ1luJk
 github.com/valyala/quicktemplate v1.2.0/go.mod h1:EH+4AkTd43SvgIbQHYu59/cJyxDoOVRUAfrukLPuGJ4=
 github.com/valyala/tcplisten v0.0.0-20161114210144-ceec8f93295a/go.mod h1:v3UYOV9WzVtRmSR+PDvWpU/qWl4Wa5LApYYX4ZtKbio=
 github.com/xiang90/probing v0.0.0-20190116061207-43a291ad63a2/go.mod h1:UETIi67q53MR2AWcXfiuqkDkRtnGDLqkBTpCHuJHxtU=
+github.com/xlab/treeprint v0.0.0-20181112141820-a009c3971eca h1:1CFlNzQhALwjS9mBAUkycX616GzgsuYUOCHA5+HSlXI=
+github.com/xlab/treeprint v0.0.0-20181112141820-a009c3971eca/go.mod h1:ce1O1j6UtZfjr22oyGxGLbauSBp2YVXpARAosm7dHBg=
 github.com/xordataexchange/crypt v0.0.3-0.20170626215501-b2862e3d0a77/go.mod h1:aYKd//L2LvnjZzWKhF00oedf4jCCReLcmhLdhm1A27Q=
+github.com/yujunz/go-getter v1.4.1-lite h1:FhvNc94AXMZkfqUwfMKhnQEC9phkphSGdPTL7tIdhOM=
+github.com/yujunz/go-getter v1.4.1-lite/go.mod h1:sbmqxXjyLunH1PkF3n7zSlnVeMvmYUuIl9ZVs/7NyCc=
 go.etcd.io/bbolt v1.3.2/go.mod h1:IbVyRI1SCnLcuJnV2u8VeU0CEYM7e686BmAb1XKL+uU=
 go.opencensus.io v0.21.0/go.mod h1:mSImk1erAIZhrmZN+AvHh14ztQfjbGwt4TtuofqLduU=
+go.starlark.net v0.0.0-20190528202925-30ae18b8564f/go.mod h1:c1/X6cHgvdXj6pUlmWKMkuqRnW4K8x2vwt6JAaaircg=
+go.starlark.net v0.0.0-20200306205701-8dd3e2ee1dd5/go.mod h1:nmDLcffg48OtT/PSW0Hg7FvpRQsQh5OSqIylirxKC7o=
 go.uber.org/atomic v1.4.0/go.mod h1:gD2HeocX3+yG+ygLZcrzQJaqmWj9AIm7n08wl/qW/PE=
 go.uber.org/multierr v1.1.0/go.mod h1:wR5kodmAFQ0UK8QlbwjlSNy0Z68gJhDJUG5sjR94q/0=
 go.uber.org/zap v1.10.0/go.mod h1:vwi/ZaCAaUcBkycHslxD9B2zi4UTXhF60s6SWpuDF0Q=
@@ -340,7 +372,6 @@ golang.org/x/crypto v0.0.0-20181203042331-505ab145d0a9/go.mod h1:6SG95UA2DQfeDnf
 golang.org/x/crypto v0.0.0-20190211182817-74369b46fc67/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20190510104115-cbcb75029529/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
-golang.org/x/crypto v0.0.0-20190611184440-5c40567a22f8/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20190820162420-60c769a6c586/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20190923035154-9ee001bba392/go.mod h1:/lpIB1dKB+9EgE3H3cr1v9wB50oz8l4C4h62xy7jSTY=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
@@ -350,6 +381,7 @@ golang.org/x/lint v0.0.0-20190301231843-5614ed5bae6f/go.mod h1:UVdnD1Gm6xHRNCYTk
 golang.org/x/lint v0.0.0-20190313153728-d0100b6bd8b3/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
 golang.org/x/mod v0.0.0-20190513183733-4bf6d317e70e/go.mod h1:mXi4GBBbnImb6dmsKGUJ2LatrhH/nqhxcFungHvyanc=
 golang.org/x/net v0.0.0-20170114055629-f2499483f923/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20180218175443-cbe0f9307d01/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -387,10 +419,10 @@ golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5h
 golang.org/x/sys v0.0.0-20190222072716-a9d3bda3a223/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190422165155-953cdadca894/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20190616124812-15dcb6c0061f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190826190057-c7b8b68b1456/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190922100055-0a153f010e69 h1:rOhMmluY6kLMhdnrivzec6lLgaVbMHMn2ISQXJeJ5EM=
 golang.org/x/sys v0.0.0-20190922100055-0a153f010e69/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20191002063906-3421d5a6bb1c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/text v0.0.0-20160726164857-2910a502d2bf/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.1-0.20180807135948-17ff2d5776d2/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -412,8 +444,6 @@ golang.org/x/tools v0.0.0-20190311215038-5c2858a9cfe5/go.mod h1:LCzVGOaR6xXOjkQ3
 golang.org/x/tools v0.0.0-20190312170243-e65039ee4138/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
 golang.org/x/tools v0.0.0-20190322203728-c1a832b0ad89/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
 golang.org/x/tools v0.0.0-20190521203540-521d6ed310dd/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
-golang.org/x/tools v0.0.0-20190614205625-5aca471b1d59 h1:QjA/9ArTfVTLfEhClDCG7SGrZkZixxWpwNCDiwJfh88=
-golang.org/x/tools v0.0.0-20190614205625-5aca471b1d59/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc=
 golang.org/x/tools v0.0.0-20190621195816-6e04913cbbac/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc=
 golang.org/x/tools v0.0.0-20190719005602-e377ae9d6386/go.mod h1:jcCCGcm9btYwXyDqrUWc6MKQKKGJCWEQ3AfLSRIbEuI=
 golang.org/x/tools v0.0.0-20190910044552-dd2b5c81c578/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
@@ -448,6 +478,10 @@ gopkg.in/yaml.v2 v2.2.1/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.4 h1:/eiJrUcujPVeJ3xlSWaiNi3uSVmDGBK1pDHUHAnao1I=
 gopkg.in/yaml.v2 v2.2.4/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v2 v2.2.7 h1:VUgggvou5XRW9mHwD/yXxIYSMtY0zoKQf/v226p2nyo=
+gopkg.in/yaml.v2 v2.2.7/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v3 v3.0.0-20191120175047-4206685974f2 h1:XZx7nhd5GMaZpmDaEHFVafUZC7ya0fuo7cSJ3UCKYmM=
+gopkg.in/yaml.v3 v3.0.0-20191120175047-4206685974f2/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
 honnef.co/go/tools v0.0.0-20190106161140-3f1c8253044a/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
 honnef.co/go/tools v0.0.1-2019.2.3 h1:3JgtbtFHMiCmsznwGVTUWbgGov+pVqnlf1dEJTNAXeM=
@@ -472,6 +506,15 @@ mvdan.cc/lint v0.0.0-20170908181259-adc824a0674b h1:DxJ5nJdkhDlLok9K6qO+5290kphD
 mvdan.cc/lint v0.0.0-20170908181259-adc824a0674b/go.mod h1:2odslEg/xrtNQqCYg2/jCoyKnw3vv5biOc3JnIcYfL4=
 mvdan.cc/unparam v0.0.0-20190720180237-d51796306d8f h1:Cq7MalBHYACRd6EesksG1Q8EoIAKOsiZviGKbOLIej4=
 mvdan.cc/unparam v0.0.0-20190720180237-d51796306d8f/go.mod h1:4G1h5nDURzA3bwVMZIVpwbkw+04kSxk3rAtzlimaUJw=
+sigs.k8s.io/kustomize v1.0.11 h1:Yb+6DDt9+aR2AvQApvUaKS/ugteeG4MPyoFeUHiPOjk=
+sigs.k8s.io/kustomize v2.0.3+incompatible h1:JUufWFNlI44MdtnjUqVnvh29rR37PQFzPbLXqhyOyX0=
+sigs.k8s.io/kustomize/kyaml v0.1.1 h1:nGUNYINljZNmlAS8uoobUv/wx/s3Pg8dNxYo+W7uYh0=
+sigs.k8s.io/kustomize/kyaml v0.1.1/go.mod h1:/NdPPfrperSCGjm55cwEro1loBVtbtVIXSb7FguK6uk=
+sigs.k8s.io/kustomize/kyaml v0.1.2 h1:l12+QGl+ETUHhP8/bZAi6TknU7H194fXL/9b2gUxZFY=
+sigs.k8s.io/kustomize/kyaml v0.1.3 h1:zbeHVTMCQPtWgjIH/YYJZC45mm7coTdw2TblyJ79BrY=
+sigs.k8s.io/kustomize/kyaml v0.1.3/go.mod h1:461i94nj0h0ylJ6w83jLkR4SqqVhn1iY6fjD0JSTQeE=
+sigs.k8s.io/kustomize/kyaml v0.1.5 h1:NicBWYTwkuOfVyZDbNkfSBSCwSgin4uirkedtyZltIc=
+sigs.k8s.io/kustomize/kyaml v0.1.5/go.mod h1:461i94nj0h0ylJ6w83jLkR4SqqVhn1iY6fjD0JSTQeE=
 sigs.k8s.io/structured-merge-diff v0.0.0-20190525122527-15d366b2352e/go.mod h1:wWxsB5ozmmv/SG7nM11ayaAW51xMvak/t1r0CSlcokI=
 sigs.k8s.io/yaml v1.1.0 h1:4A07+ZFc2wgJwo8YNlQpr1rVlgUDlxXHhPJciaPY5gs=
 sigs.k8s.io/yaml v1.1.0/go.mod h1:UJmg0vDUVViEyp3mgSv9WPwZCDxu4rQW1olrI1uml+o=

api/image/image.go

@@ -0,0 +1,50 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package image
+
+import (
+	"regexp"
+	"strings"
+)
+
+// IsImageMatched returns true if the value of t is identical to the
+// image name in the full image name and tag as given by s.
+func IsImageMatched(s, t string) bool {
+	// Tag values are limited to [a-zA-Z0-9_.{}-].
+	// Some tools like Bazel rules_k8s allow tag patterns with {} characters.
+	// More info: https://github.com/bazelbuild/rules_k8s/pull/423
+	pattern, _ := regexp.Compile("^" + t + "(@sha256)?(:[a-zA-Z0-9_.{}-]*)?$")
+	return pattern.MatchString(s)
+}
+
+// Split separates and returns the name and tag parts
+// from the image string using either colon `:` or at `@` separators.
+// Note that the returned tag keeps its separator.
+func Split(imageName string) (name string, tag string) {
+	// check if image name contains a domain
+	// if domain is present, ignore domain and check for `:`
+	ic := -1
+	if slashIndex := strings.Index(imageName, "/"); slashIndex < 0 {
+		ic = strings.LastIndex(imageName, ":")
+	} else {
+		lastIc := strings.LastIndex(imageName[slashIndex:], ":")
+		// set ic only if `:` is present
+		if lastIc > 0 {
+			ic = slashIndex + lastIc
+		}
+	}
+	ia := strings.LastIndex(imageName, "@")
+	if ic < 0 && ia < 0 {
+		return imageName, ""
+	}
+
+	i := ic
+	if ia > 0 {
+		i = ia
+	}
+
+	name = imageName[:i]
+	tag = imageName[i:]
+	return
+}

api/image/image_test.go

@@ -0,0 +1,80 @@
+// Copyright 2020 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package image
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestIsImageMatched(t *testing.T) {
+	testCases := []struct {
+		testName  string
+		value     string
+		name      string
+		isMatched bool
+	}{
+		{
+			testName:  "identical",
+			value:     "nginx",
+			name:      "nginx",
+			isMatched: true,
+		},
+		{
+			testName:  "name is match",
+			value:     "nginx:12345",
+			name:      "nginx",
+			isMatched: true,
+		},
+		{
+			testName:  "name is not a match",
+			value:     "apache:12345",
+			name:      "nginx",
+			isMatched: false,
+		},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.testName, func(t *testing.T) {
+			assert.Equal(t, tc.isMatched, IsImageMatched(tc.value, tc.name))
+		})
+	}
+}
+
+func TestSplit(t *testing.T) {
+	testCases := []struct {
+		testName string
+		value    string
+		name     string
+		tag      string
+	}{
+		{
+			testName: "no tag",
+			value:    "nginx",
+			name:     "nginx",
+			tag:      "",
+		},
+		{
+			testName: "with tag",
+			value:    "nginx:1.2.3",
+			name:     "nginx",
+			tag:      ":1.2.3",
+		},
+		{
+			testName: "with digest",
+			value:    "nginx@12345",
+			name:     "nginx",
+			tag:      "@12345",
+		},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.testName, func(t *testing.T) {
+			name, tag := Split(tc.value)
+			assert.Equal(t, tc.name, name)
+			assert.Equal(t, tc.tag, tag)
+		})
+	}
+}

api/internal/crawl/README.md

@@ -209,7 +209,7 @@ but they are functional.
 
 ## Technical details
 
-### Overall design and imlpementation
+### Overall design and implementations
 
 There are a few components that are all running together in order to get
 the overall application to work smoothly. This section will provide a brief

api/internal/crawl/backend/search_backend.go

@@ -44,7 +44,7 @@ type kustomizeSearch struct {
 // /register: not implemented, but meant as an endpoint for adding new
 // kustomization files to the corpus.
 func NewKustomizeSearch(ctx context.Context) (*kustomizeSearch, error) {
-	idx, err := index.NewKustomizeIndex(ctx)
+	idx, err := index.NewKustomizeIndex(ctx, "kustomize")
 	if err != nil {
 		return nil, err
 	}

api/internal/crawl/cmd/crawler/crawler.go

@@ -2,12 +2,15 @@ package main
 
 import (
 	"context"
+	"flag"
 	"fmt"
 	"log"
 	"net/http"
 	"os"
 	"time"
 
+	"sigs.k8s.io/kustomize/api/internal/crawl/utils"
+
 	"sigs.k8s.io/kustomize/api/internal/crawl/crawler"
 	"sigs.k8s.io/kustomize/api/internal/crawl/crawler/github"
 	"sigs.k8s.io/kustomize/api/internal/crawl/doc"
@@ -25,6 +28,7 @@ const (
 )
 
 type CrawlMode int
+
 const (
 	CrawlUnknown CrawlMode = iota
 	// Crawl all the kustomization files in all the repositories of a Github user
@@ -45,7 +49,7 @@ func NewCrawlMode(s string) CrawlMode {
 		return CrawlUser
 	case "github-repo":
 		return CrawlRepo
-	case "":
+	case "index+github":
 		return CrawlIndexAndGithub
 	case "index":
 		return CrawlIndex
@@ -56,30 +60,33 @@ func NewCrawlMode(s string) CrawlMode {
 	}
 }
 
-func Usage() {
-	fmt.Printf("Usage: %s [mode] [githubUser|githubRepo]\n", os.Args[0])
-	fmt.Printf("\tmode can be one of [github-user, github-repo, index, github]\n")
-	fmt.Printf("%s: crawl all the documents in the index and crawling all the kustomization files on Github\n", os.Args[0])
-	fmt.Printf("%s index: crawl all the documents in the index\n", os.Args[0])
-	fmt.Printf("%s gihub: crawl all the kustomization files on Github\n", os.Args[0])
-	fmt.Printf("%s github-user <github-user>: Crawl all the kustomization files in all the repositories of a Github user\n", os.Args[0])
-	fmt.Printf("\tFor example, %s github-user kubernetes-sigs\n", os.Args[0])
-	fmt.Printf("%s github-repo <github-repo>: Crawl all the kustomization files in a Github repo\n", os.Args[0])
-	fmt.Printf("\tFor example, %s github-repo kubernetes-sigs/kustomize\n", os.Args[0])
-}
-
 func main() {
+	indexNamePtr := flag.String(
+		"index", "kustomize", "The name of the ElasticSearch index.")
+	modePtr := flag.String("mode", "index+github",
+		`The crawling mode, which can be one of [github-user, github-repo, index, github, index+github].
+  * github-user: crawl all the kustomization files in all the repositories of a Github user (--github-user must be specified for this mode).
+  * github-repo: crawl all the kustomization files in a Github repository (--github-repo must be specified for this mode).
+  * index: crawl all the documents in the index.
+  * gihub: crawl all the kustomization files on Github.
+  * index+github: crawl all the documents in the index and crawling all the kustomization files on Github.`)
+	githubUserPtr := flag.String("github-user", "",
+		"A github user name (e.g., kubernetes-sigs). This flag is required for the `github-user` mode.")
+	githubRepoPtr := flag.String("github-repo", "",
+		"A github repository name (e.g., kubernetes-sigs/kustomize). This flag is required for the `github-repo` mode.")
+	flag.Parse()
+
 	githubToken := os.Getenv(githubAccessTokenVar)
 	if githubToken == "" {
-		fmt.Printf("Must set the variable '%s' to make github requests.\n",
+		log.Printf("Must set the variable '%s' to make github requests.\n",
 			githubAccessTokenVar)
 		return
 	}
 
 	ctx := context.Background()
-	idx, err := index.NewKustomizeIndex(ctx)
+	idx, err := index.NewKustomizeIndex(ctx, *indexNamePtr)
 	if err != nil {
-		fmt.Printf("Could not create an index: %v\n", err)
+		log.Printf("Could not create an index: %v\n", err)
 		return
 	}
 
@@ -87,7 +94,7 @@ func main() {
 	cache, err := redis.DialURL(cacheURL)
 	clientCache := &http.Client{}
 	if err != nil {
-		fmt.Printf("Error: redis could not make a connection: %v\n", err)
+		log.Printf("Error: redis could not make a connection: %v\n", err)
 	} else {
 		clientCache = httpclient.NewClient(cache)
 	}
@@ -108,10 +115,10 @@ func main() {
 		case *doc.KustomizationDocument:
 			switch mode {
 			case index.Delete:
-				fmt.Println("Deleting: ", d)
+				log.Printf("Deleting: %v", d)
 				return idx.Delete(d.ID())
 			default:
-				fmt.Println("Inserting: ", d)
+				log.Printf("Inserting: %v", d)
 				return idx.Put(d.ID(), d)
 			}
 		default:
@@ -119,20 +126,15 @@ func main() {
 		}
 	}
 
-	// seen tracks the IDs of all the documents in the index.
+	// seen tracks the IDs of all the documents in the index and their corresponding file types.
 	// This helps avoid indexing a given document multiple times.
-	seen := make(map[string]struct{})
+	seen := utils.NewSeenMap()
 
-	var mode CrawlMode
-	if len(os.Args) == 1 {
-		mode = CrawlIndexAndGithub
-	} else {
-		mode = NewCrawlMode(os.Args[1])
-	}
+	mode := NewCrawlMode(*modePtr)
 
 	ghCrawlerConstructor := func(user, repo string) crawler.Crawler {
 		if user != "" {
-			return 	github.NewCrawler(githubToken, retryCount, clientCache,
+			return github.NewCrawler(githubToken, retryCount, clientCache,
 				github.QueryWith(
 					github.Filename("kustomization.yaml"),
 					github.Filename("kustomization.yml"),
@@ -165,11 +167,11 @@ func main() {
 		it := idx.IterateQuery(query, 10000, 60*time.Second)
 		for it.Next() {
 			for _, hit := range it.Value().Hits.Hits {
-				seedDocs = append(seedDocs, hit.Document.Copy())
+				seedDocs = append(seedDocs, hit.Document.Document.Copy())
 			}
 		}
 		if err := it.Err(); err != nil {
-			fmt.Printf("Error iterating: %v\n", err)
+			log.Fatalf("getSeedDocsFunc Error iterating: %v\n", err)
 		}
 	}
 
@@ -185,23 +187,29 @@ func main() {
 		crawler.CrawlFromSeed(ctx, seedDocs, crawlers, docConverter, indexFunc, seen)
 	case CrawlGithub:
 		crawlers := []crawler.Crawler{ghCrawlerConstructor("", "")}
+		// add all the documents in the index into seen.
+		// this greatly reduces the time overhead of CrawlGithub.
+		getSeedDocsFunc()
+		for _, d := range seedDocs {
+			seen[d.ID()] = d.FileType
+		}
 		crawler.CrawlGithub(ctx, crawlers, docConverter, indexFunc, seen)
 	case CrawlUser:
-		if len(os.Args) < 3 {
-			Usage()
-			log.Fatalf("Please specify a github user!")
+		if *githubUserPtr == "" {
+			flag.Usage()
+			log.Fatalf("Please specify a github user with the github-user flag!")
 		}
-		crawlers := []crawler.Crawler{ghCrawlerConstructor(os.Args[2], "")}
+		crawlers := []crawler.Crawler{ghCrawlerConstructor(*githubUserPtr, "")}
 		crawler.CrawlGithub(ctx, crawlers, docConverter, indexFunc, seen)
 	case CrawlRepo:
-		if len(os.Args) < 3 {
-			Usage()
-			log.Fatalf("Please specify a github repo!")
+		if *githubRepoPtr == "" {
+			flag.Usage()
+			log.Fatalf("Please specify a github repository with the github-repo flag!")
 		}
-		crawlers := []crawler.Crawler{ghCrawlerConstructor("", os.Args[2])}
+		crawlers := []crawler.Crawler{ghCrawlerConstructor("", *githubRepoPtr)}
 		crawler.CrawlGithub(ctx, crawlers, docConverter, indexFunc, seen)
 	case CrawlUnknown:
-		Usage()
-		log.Fatalf("The crawler mode must be one of [github-user, github-repo, index, github]")
+		flag.Usage()
+		log.Fatalf("The --mode flag must be one of [github-user, github-repo, index, github, index+github].")
 	}
 }

api/internal/crawl/cmd/kustomize_stats/main.go

@@ -2,15 +2,16 @@ package main
 
 import (
 	"context"
+	"crypto/sha256"
 	"flag"
 	"fmt"
 	"log"
-	"path/filepath"
 	"sort"
 	"time"
 
+	"sigs.k8s.io/kustomize/api/internal/crawl/doc"
+
 	"sigs.k8s.io/kustomize/api/internal/crawl/index"
-	"sigs.k8s.io/kustomize/api/konfig"
 )
 
 // iterateArr adds each item in arr into countMap.
@@ -25,29 +26,90 @@ func iterateArr(arr []string, countMap map[string]int) {
 
 }
 
-// isKustomizationFile determines whether a file path is a kustomization file
-func isKustomizationFile(path string) bool {
-	basename := filepath.Base(path)
-	for _, name := range konfig.RecognizedKustomizationFileNames() {
-		if basename == name {
-			return true
-		}
-	}
-	return false
-}
-
-// SortMapKeyByValue takes a map as its input, sorts its keys according to their values
+// SortMapKeyByValueInt takes a map as its input, sorts its keys according to their values
 // in the map, and outputs the sorted keys as a slice.
-func SortMapKeyByValue(m map[string]int) []string {
+func SortMapKeyByValueInt(m map[string]int) []string {
 	keys := make([]string, 0, len(m))
 	for key := range m {
 		keys = append(keys, key)
 	}
 	// sort keys according to their values in the map m
-	sort.Slice(keys, func(i, j int) bool {return m[keys[i]] > m[keys[j]]})
+	sort.Slice(keys, func(i, j int) bool { return m[keys[i]] > m[keys[j]] })
 	return keys
 }
 
+// SortMapKeyByValue takes a map as its input, sorts its keys according to their values
+// in the map, and outputs the sorted keys as a slice.
+func SortMapKeyByValueLen(m map[string][]string) []string {
+	keys := make([]string, 0, len(m))
+	for key := range m {
+		keys = append(keys, key)
+	}
+	// sort keys according to their values in the map m
+	sort.Slice(keys, func(i, j int) bool { return len(m[keys[i]]) > len(m[keys[j]]) })
+	return keys
+}
+
+func GeneratorOrTransformerStats(docs []*doc.KustomizationDocument) {
+	n := len(docs)
+	if n == 0 {
+		return
+	}
+
+	fileType := docs[0].FileType
+	fmt.Printf("There are totally %d %s files.\n", n, fileType)
+
+	GitRepositorySummary(docs, fileType)
+
+	// key of kindToUrls: a string in the KustomizationDocument.Kinds field
+	// value of kindToUrls: a slice of string urls defining a given kind.
+	kindToUrls := make(map[string][]string)
+
+	for _, d := range docs {
+		url := fmt.Sprintf("%s/blob/%s/%s", d.RepositoryURL, d.DefaultBranch, d.FilePath)
+		for _, kind := range d.Kinds {
+			if _, ok := kindToUrls[kind]; !ok {
+				kindToUrls[kind] = []string{url}
+			} else {
+				kindToUrls[kind] = append(kindToUrls[kind], url)
+			}
+		}
+	}
+	fmt.Printf("There are totally %d kinds of %s\n", len(kindToUrls), fileType)
+	sortedKeys := SortMapKeyByValueLen(kindToUrls)
+	for _, k := range sortedKeys {
+		sort.Strings(kindToUrls[k])
+		fmt.Printf("%s kind %s appears %d times\n", fileType, k, len(kindToUrls[k]))
+		for _, url := range kindToUrls[k] {
+			fmt.Printf("%s\n", url)
+		}
+	}
+}
+
+// GitRepositorySummary counts the distribution of docs:
+// 1) how many git repositories are these docs from?
+// 2) how many docs are from each git repository?
+func GitRepositorySummary(docs []*doc.KustomizationDocument, fileType string) {
+	m := make(map[string]int)
+	for _, d := range docs {
+		if _, ok := m[d.RepositoryURL]; ok {
+			m[d.RepositoryURL]++
+		} else {
+			m[d.RepositoryURL] = 1
+		}
+	}
+	sortedKeys := SortMapKeyByValueInt(m)
+	topN := 10
+	i := 0
+	for _, k := range sortedKeys {
+		if i >= topN {
+			break
+		}
+		fmt.Printf("%d %s are from %s\n", m[k], fileType, k)
+		i++
+	}
+}
+
 func main() {
 	topKindsPtr := flag.Int(
 		"kinds", -1,
@@ -64,10 +126,12 @@ If you only want to list the 10 most popular identifiers, set the flag to 10.`)
 		`the number of kustomize features to be listed according to their popularities.
 By default, all the features will be listed.
 If you only want to list the 10 most popular features, set the flag to 10.`)
+	indexNamePtr := flag.String(
+		"index", "kustomize", "The name of the ElasticSearch index.")
 	flag.Parse()
 
 	ctx := context.Background()
-	idx, err := index.NewKustomizeIndex(ctx)
+	idx, err := index.NewKustomizeIndex(ctx, *indexNamePtr)
 	if err != nil {
 		log.Fatalf("Could not create an index: %v\n", err)
 	}
@@ -85,35 +149,59 @@ If you only want to list the 10 most popular features, set the flag to 10.`)
 	// ids tracks the unique IDs of the documents in the index
 	ids := make(map[string]struct{})
 
+	// generatorFiles include all the non-kustomization files whose FileType is generator
+	generatorFiles := make([]*doc.KustomizationDocument, 0)
+
+	// transformersFiles include all the non-kustomization files whose FileType is transformer
+	transformersFiles := make([]*doc.KustomizationDocument, 0)
+
+	checksums := make(map[string]int)
+
 	// get all the documents in the index
 	query := []byte(`{ "query":{ "match_all":{} } }`)
 	it := idx.IterateQuery(query, 10000, 60*time.Second)
 	for it.Next() {
 		for _, hit := range it.Value().Hits.Hits {
+			sum := fmt.Sprintf("%x", sha256.Sum256([]byte(hit.Document.DocumentData)))
+			if _, ok := checksums[sum]; ok {
+				checksums[sum]++
+			} else {
+				checksums[sum] = 1
+			}
+
 			// check whether there is any duplicate IDs in the index
 			if _, ok := ids[hit.ID]; !ok {
 				ids[hit.ID] = struct{}{}
 			} else {
-				fmt.Printf("Found duplicate ID (%s)\n", hit.ID)
+				log.Printf("Found duplicate ID (%s)\n", hit.ID)
 			}
 
 			count++
 			iterateArr(hit.Document.Kinds, kindsMap)
 			iterateArr(hit.Document.Identifiers, identifiersMap)
 
-			if isKustomizationFile(hit.Document.FilePath) {
+			if doc.IsKustomizationFile(hit.Document.FilePath) {
 				kustomizationFilecount++
 				iterateArr(hit.Document.Identifiers, kustomizeIdentifiersMap)
+
+			} else {
+				switch hit.Document.FileType {
+				case "generator":
+					generatorFiles = append(generatorFiles, hit.Document.Copy())
+				case "transformer":
+					transformersFiles = append(transformersFiles, hit.Document.Copy())
+				}
 			}
 		}
 	}
+
 	if err := it.Err(); err != nil {
-		fmt.Printf("Error iterating: %v\n", err)
+		log.Fatalf("Error iterating: %v\n", err)
 	}
 
-	sortedKindsMapKeys := SortMapKeyByValue(kindsMap)
-	sortedIdentifiersMapKeys := SortMapKeyByValue(identifiersMap)
-	sortedKustomizeIdentifiersMapKeys := SortMapKeyByValue(kustomizeIdentifiersMap)
+	sortedKindsMapKeys := SortMapKeyByValueInt(kindsMap)
+	sortedIdentifiersMapKeys := SortMapKeyByValueInt(identifiersMap)
+	sortedKustomizeIdentifiersMapKeys := SortMapKeyByValueInt(kustomizeIdentifiersMap)
 
 	fmt.Printf(`The count of unique document IDs in the kustomize index: %d
 There are %d documents in the kustomize index.
@@ -147,4 +235,15 @@ There are %d documents in the kustomize index.
 			kustomizeFeatureCount++
 		}
 	}
+
+	GeneratorOrTransformerStats(generatorFiles)
+	GeneratorOrTransformerStats(transformersFiles)
+
+	fmt.Printf("There are total %d checksums of document contents\n", len(checksums))
+	sortedChecksums := SortMapKeyByValueInt(checksums)
+	sortedChecksums = sortedChecksums[:20]
+	fmt.Printf("The top 20 checksums are:\n")
+	for _, key := range sortedChecksums {
+		fmt.Printf("checksum %s apprears %d\n", key, checksums[key])
+	}
 }

api/internal/crawl/cmd/log-parser/kustomize-stats-cmd

@@ -0,0 +1,7 @@
+wget <log-file-url> -O log
+go build .
+./log-parser log >out
+cat out | grep "kind \`" | cut -d\` -f2 | tail -n 50
+cat out | grep "kind \`" | awk '{print $6}' | tail -n 50
+cat out | grep "feature \`" | grep -v "\`resources\`" | grep -v -e "\`apiVersion\`" | grep -v -e "\`apiversion\`" | cut -d\` -f2
+cat out | grep "feature \`" | grep -v "\`resources\`" | grep -v -e "\`apiVersion\`" | grep -v -e "\`apiversion\`" | awk '{print $6}'

api/internal/crawl/cmd/log-parser/main.go

@@ -36,6 +36,7 @@ func main() {
 
 		m := entry.(map[string]interface{})
 		if payload, ok := m["textPayload"]; ok {
+			// use fmt.Printf here instead of log.Printf to avoid the time and code location info the log package provides
 			fmt.Printf("%s", payload)
 		} else {
 			log.Printf("the log entry does not have the `textPayload` field: %s\n", line)

api/internal/crawl/config/base/kustomization.yaml

@@ -2,5 +2,4 @@ configmapGenerator:
 - name: elasticsearch-config
   literals:
   - es-url="http://esbasic-master:9200"
-  - kustomize-index-name="kustomize"
   - plugin-index-name="plugin"

api/internal/crawl/config/crawler/base/.gitignore

@@ -0,0 +1 @@
+github_api_secret.txt

api/internal/crawl/config/crawler/cronjob/cronjob.yaml

@@ -1,9 +1,10 @@
 apiVersion: batch/v1beta1
 kind: CronJob
 metadata:
-  name: crawler
+  name: crawler-cronjob
 spec:
-  schedule: "5 0 * * */1"
+  # run the cronjob at 00:00 every 7 days
+  schedule: "0 0 */7 * *"
   jobTemplate:
     spec:
       template:
@@ -11,7 +12,9 @@ spec:
           restartPolicy: OnFailure
           containers:
           - name: crawler
-            image: gcr.io/kustomize-search/crawler:latest
+            image: gcr.io/haiyanmeng-gke-dev/crawler:v1
+            command: ["/crawler"]
+            args: ["--mode=index+github", "--github-repo=kubernetes-sigs/kustomize", "--index=kustomize"]
             imagePullPolicy: Always
             env:
             - name: GITHUB_ACCESS_TOKEN

api/internal/crawl/config/crawler/job/README.md

@@ -1,4 +1,4 @@
-There are three ways of running the crawler job.
+The crawler job can run in one of the following mode:
 
 # Crawling all the documents in the index and crawling all the kustomization files on Github
 
@@ -7,14 +7,13 @@ of the container should be:
 
 ```
         command: ["/crawler"]
-        args: []
 ```
 
 Or
 
 ```
         command: ["/crawler"]
-        args: [""]
+        args: ["--mode=index+github"]
 ```
 
 # Crawling all the documents in the index
@@ -23,7 +22,7 @@ The `command` and `args` field of the container should be:
 
 ```
         command: ["/crawler"]
-        args: ["index"]
+        args: ["--mode=index"]
 ```
 
 # Crawling all the kustomization files on Github
@@ -32,7 +31,7 @@ The `command` and `args` field of the container should be:
 
 ```
         command: ["/crawler"]
-        args: ["github"]
+        args: ["--mode=github"]
 ```
 
 # Crawling all the kustomization files in a Github repo
@@ -41,7 +40,7 @@ The `command` and `args` field of the container should be like:
 
 ```
         command: ["/crawler"]
-        args: ["github-repo", "kubernetes-sigs/kustomize"]
+        args: ["--mode=github-repo", "--github-repo=kubernetes-sigs/kustomize"]
 ```
 
 # Crawling all the kustomization files in all the repositories of a Github user
@@ -50,5 +49,5 @@ The `command` and `args` field of the container should be like:
 
 ```
         command: ["/crawler"]
-        args: ["github-user", "kubernetes-sigs"]
+        args: ["--github-user", "--github-user=kubernetes-sigs"]
 ```

api/internal/crawl/config/crawler/job/job.yaml

@@ -11,7 +11,7 @@ spec:
         image: gcr.io/haiyanmeng-gke-dev/crawler:v1
         imagePullPolicy: Always
         command: ["/crawler"]
-        args: ["github-repo", "kubernetes-sigs/kustomize"]
+        args: ["--mode=github-repo", "--github-repo=kubernetes-sigs/kustomize", "--index=kustomize"]
         env:
         - name: GITHUB_ACCESS_TOKEN
           valueFrom:

api/internal/crawl/config/crawler/kustomize_stats/job.yaml

@@ -11,7 +11,7 @@ spec:
         image: gcr.io/haiyanmeng-gke-dev/kustomize_stats:v1
         imagePullPolicy: Always
         command: ["/kustomize_stats"]
-        args: ["--kinds=50", "--identifiers=50", "--kustomize-features=50"]
+        args: ["--index=kustomize", "--kinds=51", "--identifiers=50", "--kustomize-features=50"]
         env:
         - name: ELASTICSEARCH_URL
           valueFrom:

api/internal/crawl/config/elastic/esbackup.yaml

@@ -0,0 +1,23 @@
+# ESBackup depends on ESCluster, and is depended by ESSnapshot.
+# Creating `esbackup/kustomize-backbup` will create the `kustomize-backup` snapshot repository.
+# Deleting `esbackup/kustomize-backbup` will delete the `kustomize-backup` snapshot repository.
+# Deleting `esbackup/kustomize-backbup` will NOT delete the snapshots in the `kustomize-backup` snapshot repository, instead makes all the snapshots in the repository inaccessible.
+# Deleting `esbackup/kustomize-backbup` will NOT delete the essnapshot objects depending on it, but will cause those essnapshot objects to be reconciled, which update the status of the essnapshot objects to reflect the fact that the esbackup object is missing.
+# If you delete the `kustomize-backup` snapshot repository directly without deleting `esbackup/kustomize-backbup`, the ESBackup object will not recreate the snapshot repository.
+apiVersion: elasticsearch.cloud.google.com/v1alpha1
+kind: ESBackup
+metadata:
+  name: kustomize-backup
+spec:
+  storage:
+    gcs:
+      # the bucket must exist for the snapshot repository to be created successfully.
+      bucket: kustomize-backup
+      # the path does not need to exist.
+      # If the path does not exist, the controller will create the folder in the GCS bucket.
+      # If the path already exists and includes snapshots, these snapshots can be used.
+      path: kustomize
+      secret:
+        name: kustomizesa
+  escluster:
+    name: esbasic

api/internal/crawl/config/elastic/escluster.yaml

@@ -1,3 +1,4 @@
+# ESCluster is depended by ESBackup and ESRestore.
 apiVersion: elasticsearch.cloud.google.com/v1alpha1
 kind: ESCluster
 metadata:
@@ -8,6 +9,13 @@ spec:
     - repository-gcs
     - ingest-user-agent
     - ingest-geoip
+  # To set `gcpserviceaccount`,
+  # First, create and download a GCP service account into a json file, named `sakey.json` following the instruction:
+  #     https://www.elastic.co/guide/en/elasticsearch/plugins/6.5/repository-gcs-usage.html#repository-gcs-using-service-account
+  # Second, create a secret for the service account using the following command:
+  #     $ kubectl create secret generic kustomizesa --from-file=./sakey.json
+  gcpserviceaccount:
+    name: kustomizesa
   config:
     env:
       example: test

api/internal/crawl/config/elastic/esrestore.yaml

@@ -0,0 +1,19 @@
+# ESRestore depends on both ESCluster and ESSnapshot.
+# Creating `esrestore/kustomize-restore` will restore the `kuostmize` index in the `kustomize-snapshot` snapshot to a new index named `kusotmize-restore`.
+# Deleting `esrestore/kustomize-restore` will not delete the restored index.
+# Deleting `esrestore/kustomize-restore` should happen before deleting `essnapshot/kustomize-snapshot`.
+# After the restore is complete, if the `kusotmize-restore` index is deleted manually, the ESRestore object will NOT restore the `kustomize` index to it again.
+# The correct way of using ESRestore is: create a ESRestore object to restore the index; delete the ESRestore object after the restore is complete.
+apiVersion: elasticsearch.cloud.google.com/v1alpha1
+kind: ESRestore
+metadata:
+  name: kustomize-restore
+spec:
+  include_global_state: true
+  ignore_unavailable: true
+  rename_pattern: kustomize
+  rename_replacement: kustomize-restore
+  essnapshot:
+    name: kustomize-snapshot
+  escluster:
+    name: esbasic

api/internal/crawl/config/elastic/essnapshot.yaml

@@ -0,0 +1,23 @@
+# ESSnapshot depends on ESBackup, and is depended by ESRestore.
+# Creating `essnapshot/kustomize-snapshot` will create a snapshot named `kustomize-snapshot` in the `kustomize-backup` snapshot repository.
+# After being created, the `kustomize-snapshot` snapshot will not be automatically updated when the `kuostomize` index is updated.
+# If you delete `essnapshot/kustomize-snapshot` and recreate it, the new snapshot will capture the current status of the `kustomize` index.
+# Deleting `essnapshot/kustomize-snapshot` will delete the snapshot.
+# Deleting `essnapshot/kustomize-snapshot` should happen before deleting `esbackup/kustomize-backup`.
+# If the `kustomize-snapshot` snapshot is deleted directly without deleting `essnapshot/kustomize-snapshot`, the ESSnapshot object will recreate the snapshot.
+# The correct way of using ESSnapshot is: create an ESSnapshot object to create a snapshot, keep the ESSnapshot object until the snapshot is no longer needed.
+# To update the snapshot to capture the latest version of the index, you can either:
+#   1) delete the snapshot, and wait for the ESSnapshot object to recreate the snapshot;
+#   2) delete the ESSnapshot object, and recreate the ESSnapshot object.
+apiVersion: elasticsearch.cloud.google.com/v1alpha1
+kind: ESSnapshot
+metadata:
+  name: kustomize-snapshot
+spec:
+  # indices are optional. If not specified all indices are selected.
+  indices:
+  - kustomize
+  include_global_state: true
+  ignore_unavailable: true
+  esbackup:
+    name: kustomize-backup

api/internal/crawl/crawler/crawler.go

@@ -10,6 +10,8 @@ import (
 	"os"
 	"sync"
 
+	"sigs.k8s.io/kustomize/api/internal/crawl/utils"
+
 	"sigs.k8s.io/kustomize/api/internal/crawl/index"
 
 	_ "github.com/gomodule/redigo/redis"
@@ -29,13 +31,15 @@ type Crawler interface {
 	// Crawl returns when it is done processing. This method does not take
 	// ownership of the channel. The channel is write only, and it
 	// designates where the crawler should forward the documents.
-	Crawl(ctx context.Context, output chan<- CrawledDocument) error
+	Crawl(ctx context.Context, output chan<- CrawledDocument, seen utils.SeenMap) error
 
 	// Get the document data given the FilePath, Repo, and Ref/Tag/Branch.
 	FetchDocument(context.Context, *doc.Document) error
 	// Write to the document what the created time is.
 	SetCreated(context.Context, *doc.Document) error
 
+	SetDefaultBranch(*doc.Document)
+
 	Match(*doc.Document) bool
 }
 
@@ -43,7 +47,12 @@ type CrawledDocument interface {
 	ID() string
 	GetDocument() *doc.Document
 	// Get all the Documents directly referred in a Document.
-	GetResources() ([]*doc.Document, error)
+	// For a Document representing a non-kustomization file, an empty slice will be returned.
+	// For a Document representing a kustomization file:
+	// the `includeResources` parameter determines whether the documents referred in the `resources` field are returned or not;
+	// the `includeTransformers` parameter determines whether the documents referred in the `transformers` field are returned or not;
+	// the `includeGenerators` parameter determines whether the documents referred in the `generators` field are returned or not.
+	GetResources(includeResources, includeTransformers, includeGenerators bool) ([]*doc.Document, error)
 	WasCached() bool
 }
 
@@ -69,25 +78,27 @@ func findMatch(d *doc.Document, crawlers []Crawler) Crawler {
 }
 
 func addBranches(cdoc CrawledDocument, match Crawler, indx IndexFunc,
-	seen map[string]struct{}, stack *CrawlSeed) {
+	seen utils.SeenMap, stack *CrawlSeed) {
 
-	seen[cdoc.ID()] = struct{}{}
+	seen.Set(cdoc.ID(), cdoc.GetDocument().FileType)
+
+	match.SetDefaultBranch(cdoc.GetDocument())
 
 	// Insert into index
 	if err := indx(cdoc, index.InsertOrUpdate); err != nil {
-		logger.Printf("Failed to insert or update %s %s: %v",
-			cdoc.GetDocument().RepositoryURL, cdoc.GetDocument().FilePath, err)
+		logger.Printf("Failed to insert or update doc(%s): %v",
+			cdoc.GetDocument().Path(), err)
 		return
 	}
 
-	deps, err := cdoc.GetResources()
+	deps, err := cdoc.GetResources(true, true, true)
 	if err != nil {
 		logger.Println(err)
 		return
 	}
 
 	for _, dep := range deps {
-		if _, ok := seen[dep.ID()]; ok {
+		if seen.Seen(dep.ID()) && seen.Value(dep.ID()) == dep.FileType {
 			continue
 		}
 		*stack = append(*stack, dep)
@@ -95,7 +106,7 @@ func addBranches(cdoc CrawledDocument, match Crawler, indx IndexFunc,
 }
 
 func doCrawl(ctx context.Context, docsPtr *CrawlSeed, crawlers []Crawler, conv Converter, indx IndexFunc,
-	seen map[string]struct{}, stack *CrawlSeed) {
+	seen utils.SeenMap, stack *CrawlSeed, refreshDoc bool, updateFileType bool) {
 
 	UpdatedDocCount := 0
 	seenDocCount := 0
@@ -105,6 +116,7 @@ func doCrawl(ctx context.Context, docsPtr *CrawlSeed, crawlers []Crawler, conv C
 	SetCreatedErrCount := 0
 	convErrCount := 0
 	deleteDocCount := 0
+	crawledDocCount := 0
 
 	// During the execution of the for loop, more Documents may be added into (*docsPtr).
 	for len(*docsPtr) > 0 {
@@ -114,13 +126,19 @@ func doCrawl(ctx context.Context, docsPtr *CrawlSeed, crawlers []Crawler, conv C
 		// remove the last Document in (*docPtr)
 		*docsPtr = (*docsPtr)[:(len(*docsPtr) - 1)]
 
-		if _, ok := seen[tail.ID()]; ok {
-			seenDocCount++
-			continue
+		crawledDocCount++
+		logger.Printf("Crawling doc %d: %s", crawledDocCount, tail.Path())
+
+		if seen.Seen(tail.ID()) {
+			if !updateFileType || seen.Value(tail.ID()) == tail.FileType {
+				logger.Printf("this doc has been seen before")
+				seenDocCount++
+				continue
+			}
 		}
 
 		if tail.WasCached() {
-			logger.Printf("%s %s is cached already", tail.RepositoryURL, tail.FilePath)
+			logger.Printf("doc(%s) is cached already", tail.Path())
 			cachedDocCount++
 			continue
 		}
@@ -132,36 +150,52 @@ func doCrawl(ctx context.Context, docsPtr *CrawlSeed, crawlers []Crawler, conv C
 			continue
 		}
 
-		logger.Println("Crawling ", tail.RepositoryURL, tail.FilePath)
-		if err := match.FetchDocument(ctx, tail); err != nil {
-			logger.Printf("FetchDocument failed on %s %s: %v",
-				tail.RepositoryURL, tail.FilePath, err)
-			FetchDocumentErrCount++
-			// delete the document from the index
-			cdoc := &doc.KustomizationDocument{
-				Document: *tail,
-			}
-			seen[cdoc.ID()] = struct{}{}
-			if err := indx(cdoc, index.Delete); err != nil {
-				logger.Printf("Failed to delete %s %s: %v",
-					cdoc.RepositoryURL, cdoc.FilePath, err)
-			}
-			deleteDocCount++
-			continue
+		if tail.User == "" {
+			tail.User = doc.UserName(tail.RepositoryURL)
 		}
 
-		if err := match.SetCreated(ctx, tail); err != nil {
-			logger.Printf("SetCreated failed on %s %s: %v",
-				tail.RepositoryURL, tail.FilePath, err)
-			SetCreatedErrCount++
+		// If the Document represents a kustomization root, FetchDcoument will change
+		// the `filePath` field of the Document by adding `kustomization.yaml` or
+		// `kustomization.yml` or `kustomization` into the the field.
+		// Therefore, it is necessary to add the ID of the Document into seen before
+		// calling FetchDocument. Otherwise, the binary may enter into an infinite loop
+		// if a kustomization file points to its kustmozation root in its `resources` or
+		// `bases` field.
+		seen.Set(tail.ID(), tail.FileType)
+
+		if refreshDoc || tail.DefaultBranch == "" {
+			match.SetDefaultBranch(tail)
+		}
+
+		if refreshDoc || tail.DocumentData == "" {
+			if err := match.FetchDocument(ctx, tail); err != nil {
+				logger.Printf("FetchDocument failed on doc(%s): %v", tail.Path(), err)
+				FetchDocumentErrCount++
+				// delete the document from the index
+				cdoc := &doc.KustomizationDocument{
+					Document: *tail,
+				}
+				seen.Set(cdoc.ID(), tail.FileType)
+				if err := indx(cdoc, index.Delete); err != nil {
+					logger.Printf("Failed to delete doc(%s): %v", cdoc.Path(), err)
+				}
+				deleteDocCount++
+				continue
+			}
+		}
+
+		if refreshDoc || tail.CreationTime == nil {
+			if err := match.SetCreated(ctx, tail); err != nil {
+				logger.Printf("SetCreated failed on doc(%s): %v", tail.Path(), err)
+				SetCreatedErrCount++
+			}
 		}
 
 		cdoc, err := conv(tail)
 		// If conv returns an error, cdoc can still be added into the index so that
 		// cdoc.Document can be searched.
 		if err != nil {
-			logger.Printf("conv failed on %s %s: %v",
-				tail.RepositoryURL, tail.FilePath, err)
+			logger.Printf("conv failed on doc(%s): %v", tail.Path(), err)
 			convErrCount++
 		}
 
@@ -182,7 +216,7 @@ func doCrawl(ctx context.Context, docsPtr *CrawlSeed, crawlers []Crawler, conv C
 // CrawlFromSeed updates all the documents in seed, and crawls all the new
 // documents referred in the seed.
 func CrawlFromSeed(ctx context.Context, seed CrawlSeed, crawlers []Crawler,
-	conv Converter, indx IndexFunc, seen map[string]struct{}) {
+	conv Converter, indx IndexFunc, seen utils.SeenMap) {
 
 	// stack tracks the documents directly referred in other documents.
 	stack := make(CrawlSeed, 0)
@@ -190,14 +224,14 @@ func CrawlFromSeed(ctx context.Context, seed CrawlSeed, crawlers []Crawler,
 	// Exploit seed to update bulk of corpus.
 	logger.Printf("updating %d documents from seed\n", len(seed))
 	// each unique document in seed will be crawled once.
-	doCrawl(ctx, &seed, crawlers, conv, indx, seen, &stack)
+	doCrawl(ctx, &seed, crawlers, conv, indx, seen, &stack, true, false)
 
 	// Traverse any new documents added while updating corpus.
 	logger.Printf("crawling %d new documents found in the seed\n", len(stack))
 	// While crawling each document in stack, the documents directly referred in the document
 	// will be added into stack.
 	// After this statement is done, stack will become empty.
-	doCrawl(ctx, &stack, crawlers, conv, indx, seen, &stack)
+	doCrawl(ctx, &stack, crawlers, conv, indx, seen, &stack, false, true)
 }
 
 // CrawlGithubRunner is a blocking function and only returns once all of the
@@ -218,7 +252,7 @@ func CrawlFromSeed(ctx context.Context, seed CrawlSeed, crawlers []Crawler,
 // from the seed will be processed before any other documents from the
 // crawlers.
 func CrawlGithubRunner(ctx context.Context, output chan<- CrawledDocument,
-	crawlers []Crawler) []error {
+	crawlers []Crawler, seen utils.SeenMap) []error {
 
 	errs := make([]error, len(crawlers))
 	wg := sync.WaitGroup{}
@@ -252,7 +286,7 @@ func CrawlGithubRunner(ctx context.Context, output chan<- CrawledDocument,
 				}
 			}()
 			defer close(docs)
-			errs[idx] = crawler.Crawl(ctx, docs)
+			errs[idx] = crawler.Crawl(ctx, docs, seen)
 		}(i, crawler, docs) // Copies the index and the crawler
 	}
 
@@ -262,7 +296,7 @@ func CrawlGithubRunner(ctx context.Context, output chan<- CrawledDocument,
 
 // CrawlGithub crawls all the kustomization files on Github.
 func CrawlGithub(ctx context.Context, crawlers []Crawler, conv Converter,
-	indx IndexFunc, seen map[string]struct{}) {
+	indx IndexFunc, seen utils.SeenMap) {
 	// stack tracks the documents directly referred in other documents.
 	stack := make(CrawlSeed, 0)
 
@@ -274,8 +308,14 @@ func CrawlGithub(ctx context.Context, crawlers []Crawler, conv Converter,
 	wg.Add(1)
 	go func() {
 		defer wg.Done()
+		docCount := 0
 		for cdoc := range ch {
-			if _, ok := seen[cdoc.ID()]; ok {
+			docCount++
+			logger.Printf("Processing doc %d found on Github", docCount)
+			// all the docs here are kustomization files found by querying Github, and
+			// their `FileType` fields all should be empty.
+			if seen.Seen(cdoc.ID()) {
+				logger.Printf("the doc has been seen before")
 				continue
 			}
 			match := findMatch(cdoc.GetDocument(), crawlers)
@@ -289,7 +329,7 @@ func CrawlGithub(ctx context.Context, crawlers []Crawler, conv Converter,
 	}()
 
 	logger.Println("processing the documents found from crawling github")
-	if errs := CrawlGithubRunner(ctx, ch, crawlers); errs != nil {
+	if errs := CrawlGithubRunner(ctx, ch, crawlers, seen); errs != nil {
 		for _, err := range errs {
 			logIfErr(err)
 		}
@@ -300,5 +340,5 @@ func CrawlGithub(ctx context.Context, crawlers []Crawler, conv Converter,
 	// Handle deps of newly discovered documents.
 	logger.Printf("crawling the %d new documents referred by other documents",
 		len(stack))
-	doCrawl(ctx, &stack, crawlers, conv, indx, seen, &stack)
+	doCrawl(ctx, &stack, crawlers, conv, indx, seen, &stack, false, true)
 }

api/internal/crawl/crawler/crawler_test.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"log"
 	"reflect"
 	"sort"
 	"strings"
@@ -11,6 +12,8 @@ import (
 	"testing"
 	"time"
 
+	"sigs.k8s.io/kustomize/api/internal/crawl/utils"
+
 	"sigs.k8s.io/kustomize/api/internal/crawl/index"
 
 	"sigs.k8s.io/kustomize/api/internal/crawl/doc"
@@ -34,6 +37,8 @@ func (c testCrawler) Match(d *doc.Document) bool {
 	return d != nil
 }
 
+func (c testCrawler) SetDefaultBranch(d *doc.Document) {}
+
 func (c testCrawler) FetchDocument(_ context.Context, d *doc.Document) error {
 	if i, ok := c.lukp[d.ID()]; ok {
 		d.DocumentData = c.docs[i].DocumentData
@@ -75,7 +80,7 @@ func newCrawler(matchPrefix string, err error,
 
 // Crawl implements the Crawler interface for testing.
 func (c testCrawler) Crawl(_ context.Context,
-	output chan<- CrawledDocument) error {
+	output chan<- CrawledDocument, _ utils.SeenMap) error {
 
 	for i, d := range c.docs {
 		isResource := true
@@ -110,7 +115,7 @@ func (s sortableDocs) Len() int {
 }
 
 func TestCrawlGithubRunner(t *testing.T) {
-	fmt.Println("testing CrawlGithubRunner")
+	log.Println("testing CrawlGithubRunner")
 	tests := []struct {
 		tc   []Crawler
 		errs []error
@@ -181,8 +186,9 @@ func TestCrawlGithubRunner(t *testing.T) {
 			defer close(output)
 			defer wg.Done()
 
+			seen := utils.NewSeenMap()
 			errs := CrawlGithubRunner(context.Background(),
-				output, test.tc)
+				output, test.tc, seen)
 
 			// Check that errors are returned as they should be.
 			if !reflect.DeepEqual(errs, test.errs) {
@@ -215,7 +221,7 @@ func TestCrawlGithubRunner(t *testing.T) {
 }
 
 func TestCrawlFromSeed(t *testing.T) {
-	fmt.Println("testing CrawlFromSeed")
+	log.Println("testing CrawlFromSeed")
 
 	tests := []struct {
 		seed    CrawlSeed
@@ -322,7 +328,7 @@ resources:
 				visited[d.ID()]++
 				return nil
 			},
-			make(map[string]struct{}),
+			utils.NewSeenMap(),
 		)
 		if lv, lc := len(visited), len(tc.corpus); lv != lc {
 			t.Errorf("error: %d of %d documents visited.", lv, lc)

api/internal/crawl/crawler/github/crawler.go

@@ -16,6 +16,8 @@ import (
 	"strings"
 	"time"
 
+	"sigs.k8s.io/kustomize/api/internal/crawl/utils"
+
 	"sigs.k8s.io/kustomize/api/internal/crawl/crawler"
 	"sigs.k8s.io/kustomize/api/internal/crawl/doc"
 	"sigs.k8s.io/kustomize/api/internal/crawl/httpclient"
@@ -30,6 +32,8 @@ var logger = log.New(os.Stdout, "Github Crawler: ",
 type githubCrawler struct {
 	client GhClient
 	query  Query
+	// branchMap maps github repositories to their default branches
+	branchMap map[string]string
 }
 
 type GhClient struct {
@@ -51,13 +55,60 @@ func NewCrawler(accessToken string, retryCount uint64, client *http.Client,
 			},
 			accessToken: accessToken,
 		},
-		query: query,
+		query:     query,
+		branchMap: map[string]string{},
 	}
 }
 
+func (gc githubCrawler) SetDefaultBranch(d *doc.Document) {
+	url := gc.client.ReposRequest(d.RepositoryFullName())
+	defaultBranch, err := gc.client.GetDefaultBranch(url, d.RepositoryURL, gc.branchMap)
+	if err != nil {
+		logger.Printf(
+			"(error: %v) setting default_branch to master\n", err)
+		defaultBranch = "master"
+	}
+	d.DefaultBranch = defaultBranch
+	gc.branchMap[d.RepositoryURL] = d.DefaultBranch
+}
+
+func (gc githubCrawler) DefaultBranch(repo string) string {
+	return gc.branchMap[repo]
+}
+
 // Implements crawler.Crawler.
-func (gc githubCrawler) Crawl(
-	ctx context.Context, output chan<- crawler.CrawledDocument) error {
+func (gc githubCrawler) Crawl(ctx context.Context,
+	output chan<- crawler.CrawledDocument, seen utils.SeenMap) error {
+
+	ranges := []RangeWithin{
+		RangeWithin{
+		start: uint64(0),
+		end:   githubMaxFileSize,
+	},
+	}
+
+	errs := make(multiError, 0)
+	for len(ranges) > 0 {
+		tailRange := ranges[len(ranges) - 1]
+		ranges = ranges[:(len(ranges) - 1)]
+		reProcessQueryRanges, err := gc.CrawlSingleRange(ctx, output, seen, tailRange.start, tailRange.end)
+		if err != nil {
+			errs = append(errs, err)
+		}
+		ranges = append(ranges, reProcessQueryRanges...)
+	}
+
+	if len(errs) > 0 {
+		return errs
+	}
+	return nil
+}
+
+func (gc githubCrawler) CrawlSingleRange(ctx context.Context,
+	output chan<- crawler.CrawledDocument, seen utils.SeenMap,
+	lowerBound, upperBound uint64) ([]RangeWithin, error) {
+
+	log.Printf("CrawlSingleRange [%d, %d]", lowerBound, upperBound)
 
 	noETagClient := GhClient{
 		RequestConfig: gc.client.RequestConfig,
@@ -66,12 +117,25 @@ func (gc githubCrawler) Crawl(
 		accessToken:   gc.client.accessToken,
 	}
 
+	var reProcessQueryRanges []RangeWithin
+
+	var ranges []string
+	var err error
 	// Since Github returns a max of 1000 results per query, we can use
 	// multiple queries that split the search space into chunks of at most
 	// 1000 files to get all of the data.
-	ranges, err := FindRangesForRepoSearch(newCache(noETagClient, gc.query))
+	for i := 0; i < 5; i++ {
+		ranges, err = FindRangesForRepoSearch(newCache(noETagClient, gc.query),
+			lowerBound, upperBound)
+		if err == nil {
+			logger.Printf("FindRangesForRepoSearch succeeded after %d retries", i)
+			break
+		} else {
+			time.Sleep(time.Minute)
+		}
+	}
 	if err != nil {
-		return fmt.Errorf("could not split %v into ranges, %v\n",
+		return reProcessQueryRanges, fmt.Errorf("could not split %v into ranges, %v\n",
 			gc.query, err)
 	}
 
@@ -79,35 +143,31 @@ func (gc githubCrawler) Crawl(
 
 	// Query each range for files.
 	errs := make(multiError, 0)
+	queryResult := RangeQueryResult{}
 	for _, query := range ranges {
-		err := processQuery(ctx, gc.client, query, output)
+		reProcessQuery, rangeResult, err := processQuery(ctx, gc.client, query, output, seen, gc.branchMap)
 		if err != nil {
 			errs = append(errs, err)
 		}
+		queryResult.Add(rangeResult)
+		if reProcessQuery {
+			reProcessQueryRanges = append(reProcessQueryRanges, RangeSizes(query))
+		}
 	}
 
+	logger.Printf("Summary of Crawl: %s", queryResult.String())
+
 	if len(errs) > 0 {
-		return errs
+		return reProcessQueryRanges, errs
 	}
 
-	return nil
+	return reProcessQueryRanges, nil
 }
 
 // FetchDocument first tries to fetch the document with d.FilePath. If it fails,
 // it will try to add each string in konfig.RecognizedKustomizationFileNames() to
 // d.FilePath, and try to fetch the document again.
 func (gc githubCrawler) FetchDocument(_ context.Context, d *doc.Document) error {
-	// set the default branch if it is empty
-	if d.DefaultBranch == "" {
-		url := gc.client.ReposRequest(d.RepositoryFullName())
-		defaultBranch, err := gc.client.GetDefaultBranch(url)
-		if err != nil {
-			logger.Printf(
-				"(error: %v) setting default_branch to master\n", err)
-			defaultBranch = "master"
-		}
-		d.DefaultBranch = defaultBranch
-	}
 	repoURL := d.RepositoryURL + "/" + d.FilePath + "?ref=" + d.DefaultBranch
 	repoSpec, err := git.NewRepoSpecFromUrl(repoURL)
 	if err != nil {
@@ -176,10 +236,32 @@ func (gc githubCrawler) Match(d *doc.Document) bool {
 	return strings.Contains(repoSpec.Host, "github.com")
 }
 
+type RangeQueryResult struct {
+	totalDocCnt uint64
+	seenDocCnt  uint64
+	newDocCnt   uint64
+	errorCnt    uint64
+}
+
+func (r *RangeQueryResult) Add(other RangeQueryResult) {
+	r.totalDocCnt += other.totalDocCnt
+	r.newDocCnt += other.newDocCnt
+	r.seenDocCnt += other.seenDocCnt
+	r.errorCnt += other.errorCnt
+}
+
+func (r *RangeQueryResult) String() string {
+	return fmt.Sprintf("got %d files from API. "+
+		"%d have been seen before. %d are new and sent to the output channel."+
+		" %d have kustomizationResultAdapter errors.",
+		r.totalDocCnt, r.seenDocCnt, r.newDocCnt, r.errorCnt)
+}
+
 // processQuery follows all of the pages in a query, and updates/adds the
 // documents from the crawl to the datastore/index.
 func processQuery(ctx context.Context, gcl GhClient, query string,
-	output chan<- crawler.CrawledDocument) error {
+	output chan<- crawler.CrawledDocument, seen utils.SeenMap,
+	branchMap map[string]string) (bool, RangeQueryResult, error) {
 
 	queryPages := make(chan GhResponseInfo)
 
@@ -195,57 +277,84 @@ func processQuery(ctx context.Context, gcl GhClient, query string,
 		close(queryPages)
 	}()
 
+	reProcessQuery := false
+
 	errs := make(multiError, 0)
-	errorCnt := 0
-	totalCnt := 0
+	result := RangeQueryResult{}
+	pageID := 1
 	for page := range queryPages {
 		if page.Error != nil {
 			errs = append(errs, page.Error)
 			continue
 		}
-
+		pageResult := RangeQueryResult{}
 		for _, file := range page.Parsed.Items {
-			k, err := kustomizationResultAdapter(gcl, file)
+			k, err := kustomizationResultAdapter(gcl, file, seen, branchMap)
 			if err != nil {
 				logger.Printf("kustomizationResultAdapter failed: %v", err)
 				errs = append(errs, err)
-				errorCnt++
+				pageResult.errorCnt++
 			}
 			if k != nil {
+				pageResult.newDocCnt++
 				output <- k
+			} else {
+				pageResult.seenDocCnt++
 			}
-			totalCnt++
+			pageResult.totalDocCnt++
 		}
 
-		logger.Printf("got %d files out of %d from API. %d of %d had errors\n",
-			totalCnt, page.Parsed.TotalCount, errorCnt, totalCnt)
+		logger.Printf("processQuery [TotalCount %d - page %d]: %s",
+			page.Parsed.TotalCount, pageID, pageResult.String())
+		result.Add(pageResult)
+
+		pageID++
+
+		if page.Parsed.TotalCount > githubMaxResultsPerQuery {
+			reProcessQuery = true
+		}
 	}
 
-	return errs
+	logger.Printf("Summary of processQuery: %s", result.String())
+
+	return reProcessQuery, result, errs
 }
 
-func kustomizationResultAdapter(gcl GhClient, k GhFileSpec) (
-	crawler.CrawledDocument, error) {
-
-	data, err := gcl.GetFileData(k)
-	if err != nil {
-		return nil, err
-	}
-
+func kustomizationResultAdapter(gcl GhClient, k GhFileSpec, seen utils.SeenMap,
+	branchMap map[string]string) (crawler.CrawledDocument, error) {
 	url := gcl.ReposRequest(k.Repository.FullName)
-	defaultBranch, err := gcl.GetDefaultBranch(url)
+	defaultBranch, err := gcl.GetDefaultBranch(url, k.Repository.URL, branchMap)
 	if err != nil {
 		logger.Printf(
 			"(error: %v) setting default_branch to master\n", err)
 		defaultBranch = "master"
 	}
 
+	// document here is a kustomization file found by querying Github, whose
+	// `FileType` field should be empty.
+	document := doc.Document{
+		FilePath:      k.Path,
+		DefaultBranch: defaultBranch,
+		RepositoryURL: k.Repository.URL,
+		User:          doc.UserName(k.Repository.URL),
+	}
+
+	if seen.Seen(document.ID()) {
+		return nil, nil
+	}
+
+	data, err := gcl.GetFileData(k)
+	if err != nil {
+		return nil, err
+	}
+
 	d := doc.KustomizationDocument{
 		Document: doc.Document{
 			DocumentData:  string(data),
 			FilePath:      k.Path,
 			DefaultBranch: defaultBranch,
 			RepositoryURL: k.Repository.URL,
+			User:          doc.UserName(k.Repository.URL),
 		},
 	}
 	creationTime, err := gcl.GetFileCreationTime(k)
@@ -270,7 +379,7 @@ func (gcl GhClient) ForwardPaginatedQuery(ctx context.Context, query string,
 	output chan<- GhResponseInfo) error {
 
 	logger.Println("querying: ", query)
-	response := gcl.parseGithubResponse(query)
+	response := gcl.parseGithubResponseWithRetry(query)
 
 	if response.Error != nil {
 		return response.Error
@@ -283,7 +392,7 @@ func (gcl GhClient) ForwardPaginatedQuery(ctx context.Context, query string,
 		case <-ctx.Done():
 			return nil
 		default:
-			response = gcl.parseGithubResponse(response.NextURL)
+			response = gcl.parseGithubResponseWithRetry(response.NextURL)
 			if response.Error != nil {
 				return response.Error
 			}
@@ -344,7 +453,15 @@ func CloseResponseBody(resp *http.Response) {
 	}
 }
 
-func (gcl GhClient) GetDefaultBranch(url string) (string, error) {
+// GetDefaultBranch gets the default branch of a github repository.
+// m is a map which maps a github repository to its default branch.
+// If repo is already in m, the default branch for url will be obtained from m;
+// otherwise, a query will be made to github to obtain the default branch.
+func (gcl GhClient) GetDefaultBranch(url, repo string, m map[string]string) (string, error) {
+	if v, ok := m[repo]; ok {
+		return v, nil
+	}
+
 	resp, err := gcl.GetReposData(url)
 	if err != nil {
 		return "", fmt.Errorf(
@@ -470,6 +587,8 @@ type githubResponse struct {
 	// This is the number of files that match the query.
 	TotalCount uint64 `json:"total_count,omitempty"`
 
+	IncompleteResults bool `json:"incomplete_results,omitempty"`
+
 	// Github representation of a file.
 	Items []GhFileSpec `json:"items,omitempty"`
 }
@@ -512,6 +631,17 @@ func parseGithubLinkFormat(links string) (string, string) {
 	return next, last
 }
 
+func (gcl GhClient) parseGithubResponseWithRetry(getRequest string) GhResponseInfo {
+	resp := gcl.parseGithubResponse(getRequest)
+	retries := 0
+	for resp.Parsed.IncompleteResults {
+		resp = gcl.parseGithubResponse(getRequest)
+		retries++
+	}
+	log.Printf("The result of query(%s) is complete after %d retries", getRequest, retries)
+	return resp
+}
+
 func (gcl GhClient) parseGithubResponse(getRequest string) GhResponseInfo {
 	resp, err := gcl.SearchGithubAPI(getRequest)
 	requestInfo := GhResponseInfo{
@@ -589,7 +719,7 @@ func (gcl GhClient) Do(query string) (*http.Response, error) {
 
 	// gcl.client.Do: a non-2xx status code doesn't cause an error.
 	// See https://golang.org/pkg/net/http/#Client.Do for more info.
-	resp, err :=  gcl.client.Do(req)
+	resp, err := gcl.client.Do(req)
 	if resp != nil && resp.StatusCode != http.StatusOK {
 		err = fmt.Errorf("GhClient.Do(%s) failed with response code: %d",
 			query, resp.StatusCode)

api/internal/crawl/crawler/github/queries.go

@@ -117,7 +117,7 @@ type RequestConfig struct {
 // understand why the request object is useful.
 func (rc RequestConfig) CodeSearchRequestWith(query Query) request {
 	vals := url.Values{
-		"sort": []string{"indexed"},
+		"sort":  []string{"indexed"},
 		"order": []string{"desc"},
 	}
 	req := rc.makeRequest("search/code", query, vals)
@@ -166,7 +166,7 @@ type request struct {
 	query Query
 }
 
-// CopyWith copies the requests and adds the extra query parameters. Usefull
+// CopyWith copies the requests and adds the extra query parameters. It is useful
 // for dynamically adding sizes to a filename only query without modifying it.
 func (r request) CopyWith(queryParams ...queryField) request {
 	cpy := r

api/internal/crawl/crawler/github/split_search_ranges.go

@@ -93,13 +93,15 @@ package github
 //   apiCallsPerResult * 10(pages) * 100(resultsPerPage) * totalResults / 1000
 //   = apiCallsPerResult * totalResults.
 //
-// So it could very well take apiCallsPerResult * 50 times longer to acutally
+// So it could very well take apiCallsPerResult * 50 times longer to actually
 // fetch the results (assuming the quotas for the API calls are the same as the
 // search API), than it does to perform these range searches.
 
 import (
 	"fmt"
 	"math/bits"
+	"strconv"
+	"strings"
 )
 
 // Files cannot be more than 2^19 bytes, according to
@@ -112,7 +114,7 @@ const (
 // Interface instead of struct for testing purposes.
 // Not expecting to have multiple implementations.
 type cachedSearch interface {
-	CountResults(uint64) (uint64, error)
+	CountResults(uint64, uint64) (uint64, error)
 	RequestString(filesize rangeFormatter) string
 }
 
@@ -139,7 +141,7 @@ type cachedSearch interface {
 //    problematic). The current cache implementation looks at the
 //    predecessor entry to find out if the current value is monotonic.
 //    This is where the bit trick is used, since each step in the binary
-//    search is adding or ommiting to add a decreasing power of 2 to the query
+//    search is adding or omitting to add a decreasing power of 2 to the query
 //    value, we can remove the least significant set bit to find the
 //    predecessor in constant time. Ultimately since the search is rate
 //    limited, we could also easily afford to compute this in linear time
@@ -161,16 +163,16 @@ func newCache(client GhClient, query Query) githubCachedSearch {
 	}
 }
 
-func (c githubCachedSearch) CountResults(upperBound uint64) (uint64, error) {
+func (c githubCachedSearch) CountResults(lowerBound, upperBound uint64) (uint64, error) {
 	count, cached := c.cache[upperBound]
 	if cached {
 		return count, nil
 	}
 
-	sizeRange := RangeWithin{0, upperBound}
+	sizeRange := RangeWithin{lowerBound, upperBound}
 	rangeRequest := c.RequestString(sizeRange)
 
-	result := c.gcl.parseGithubResponse(rangeRequest)
+	result := c.gcl.parseGithubResponseWithRetry(rangeRequest)
 	if result.Error != nil {
 		return count, result.Error
 	}
@@ -204,7 +206,7 @@ func (c githubCachedSearch) CountResults(upperBound uint64) (uint64, error) {
 			"Retrying query... current lower bound: %d, got: %d\n",
 			c.cache[prev], result.Parsed.TotalCount)
 
-		result = c.gcl.parseGithubResponse(rangeRequest)
+		result = c.gcl.parseGithubResponseWithRetry(rangeRequest)
 		if result.Error != nil {
 			return count, result.Error
 		}
@@ -219,8 +221,8 @@ func (c githubCachedSearch) CountResults(upperBound uint64) (uint64, error) {
 	}
 
 	count = result.Parsed.TotalCount
-	logger.Printf("Caching new query %s, with count %d\n",
-		sizeRange.RangeString(), count)
+	logger.Printf("Caching new query %s, with count %d (incomplete_results: %v)\n",
+		sizeRange.RangeString(), count, result.Parsed.IncompleteResults)
 	c.cache[upperBound] = count
 	return count, nil
 }
@@ -238,8 +240,8 @@ func (c githubCachedSearch) RequestString(filesize rangeFormatter) string {
 // This would mean that the search as it is could not find all files. If queries
 // are sorted by last indexed, and retrieved on regular intervals, it should be
 // sufficient to get most if not all documents.
-func FindRangesForRepoSearch(cache cachedSearch) ([]string, error) {
-	totalFiles, err := cache.CountResults(githubMaxFileSize)
+func FindRangesForRepoSearch(cache cachedSearch, lowerBound, upperBound uint64) ([]string, error) {
+	totalFiles, err := cache.CountResults(lowerBound, upperBound)
 	if err != nil {
 		return nil, err
 	}
@@ -247,7 +249,7 @@ func FindRangesForRepoSearch(cache cachedSearch) ([]string, error) {
 
 	if githubMaxResultsPerQuery >= totalFiles {
 		return []string{
-			cache.RequestString(RangeWithin{0, githubMaxFileSize}),
+			cache.RequestString(RangeWithin{lowerBound, upperBound}),
 		}, nil
 	}
 
@@ -275,6 +277,7 @@ func FindRangesForRepoSearch(cache cachedSearch) ([]string, error) {
 	// range.
 	filesAccessible := uint64(0)
 	sizes := make([]uint64, 0)
+	sizes = append(sizes, lowerBound)
 	for filesAccessible < totalFiles {
 		target := filesAccessible + githubMaxResultsPerQuery
 		if target >= totalFiles {
@@ -284,22 +287,22 @@ func FindRangesForRepoSearch(cache cachedSearch) ([]string, error) {
 		logger.Printf("%d accessible files, next target = %d\n",
 			filesAccessible, target)
 
-		cur, err := lowerBoundFileCount(cache, target)
+		size, err := FindFileSize(cache, target, lowerBound, upperBound)
 		if err != nil {
 			return nil, err
 		}
 
 		// If there are more than 1000 files in the next bucket, we must
 		// advance anyway and lose out on some files :(.
-		if l := len(sizes); l > 0 && sizes[l-1] == cur {
-			cur++
+		if l := len(sizes); l > 0 && sizes[l-1] == size {
+			size++
 		}
 
-		nextAccessible, err := cache.CountResults(cur)
+		nextAccessible, err := cache.CountResults(lowerBound, size)
 		if err != nil {
 			return nil, fmt.Errorf(
 				"cache should be populated at %d already, got %v",
-				cur, err)
+				size, err)
 		}
 		if nextAccessible < filesAccessible {
 			return nil, fmt.Errorf(
@@ -309,31 +312,31 @@ func FindRangesForRepoSearch(cache cachedSearch) ([]string, error) {
 
 		filesAccessible = nextAccessible
 		if nextAccessible < totalFiles {
-			sizes = append(sizes, cur)
+			sizes = append(sizes, size)
 		}
 	}
-
+	sizes = append(sizes, upperBound)
 	return formatFilesizeRanges(cache, sizes), nil
 }
 
-// lowerBoundFileCount finds the filesize range from [0, return value] that has
+// FindFileSize finds the filesize range from [lowerBound, return value] that has
 // the largest file count that is smaller than or equal to
 // githubMaxResultsPerQuery. It is important to note that this returned value
 // could already be in a previous range if the next file size has more than 1000
 // results. It is left to the caller to handle this bit of logic and guarantee
 // forward progession in this case.
-func lowerBoundFileCount(
-	cache cachedSearch, targetFileCount uint64) (uint64, error) {
+func FindFileSize(
+	cache cachedSearch, targetFileCount, lowerBound, upperBound uint64) (uint64, error) {
 
 	// Binary search for file sizes that make up the next <=1000 element
 	// chunk.
-	cur := uint64(0)
-	increase := githubMaxFileSize / 2
+	cur := lowerBound
+	increase := (upperBound - lowerBound) / 2
 
 	for increase > 0 {
 		mid := cur + increase
 
-		count, err := cache.CountResults(mid)
+		count, err := cache.CountResults(lowerBound, mid)
 		if err != nil {
 			return count, err
 		}
@@ -353,26 +356,24 @@ func lowerBoundFileCount(
 }
 
 func formatFilesizeRanges(cache cachedSearch, sizes []uint64) []string {
-	ranges := make([]string, 0, len(sizes)+1)
-
-	if len(sizes) > 0 {
-		ranges = append(ranges, cache.RequestString(
-			RangeLessThan{sizes[0] + 1},
-		))
+	n := len(sizes)
+	if n < 2 {
+		return []string{}
 	}
 
-	for i := 0; i < len(sizes)-1; i += 1 {
-		ranges = append(ranges, cache.RequestString(
-			RangeWithin{sizes[i] + 1, sizes[i+1]},
-		))
-
-		if i != len(sizes)-2 {
-			continue
-		}
-		ranges = append(ranges, cache.RequestString(
-			RangeGreaterThan{sizes[i+1]},
-		))
+	ranges := make([]string, 0, n-1)
+	ranges = append(ranges, cache.RequestString(RangeWithin{sizes[0], sizes[1]}))
+	for i := 1; i < n-1; i++ {
+		ranges = append(ranges, cache.RequestString(RangeWithin{sizes[i] + 1, sizes[i+1]}))
 	}
-
 	return ranges
 }
+
+func RangeSizes(s string) RangeWithin {
+	start := strings.Index(s, "+size:") + len("+size:")
+	end := strings.Index(s, "&")
+	ranges := strings.Split(s[start:end], "..")
+	lowerBound, _ := strconv.ParseUint(ranges[0], 10, 64)
+	upperBound, _ := strconv.ParseUint(ranges[1], 10, 64)
+	return RangeWithin{lowerBound, upperBound}
+}

api/internal/crawl/crawler/github/split_search_ranges_test.go

@@ -2,6 +2,7 @@ package github
 
 import (
 	"fmt"
+	"log"
 	"reflect"
 	"testing"
 )
@@ -10,8 +11,8 @@ type testCachedSearch struct {
 	cache map[uint64]uint64
 }
 
-func (c testCachedSearch) CountResults(upperBound uint64) (uint64, error) {
-	fmt.Printf("CountResults(%05x)\n", upperBound)
+func (c testCachedSearch) CountResults(lowerBound, upperBound uint64) (uint64, error) {
+	log.Printf("CountResults(%05x)\n", upperBound)
 	count, ok := c.cache[upperBound]
 	if !ok {
 		return count, fmt.Errorf("cache not set at %x", upperBound)
@@ -72,19 +73,29 @@ func TestRangeSplitting(t *testing.T) {
 		},
 	}
 
-	requests, err := FindRangesForRepoSearch(cache)
+	requests, err := FindRangesForRepoSearch(cache, 0, 524288)
 	if err != nil {
 		t.Errorf("Error while finding ranges: %v", err)
 	}
 	expected := []string{
-		"<107",      // cache.RequestString(RangeLessThan{0x6b}),
-		"107..128",  // cache.RequestString(RangeWithin{0x6b, 0x80}),
-		"129..256",  // cache.RequestString(RangeWithin{0x81, 0x100}),
-		"257..4095", // cache.RequestString(RangeWithin{0x101, 0xfff}),
-		">4095",     // cache.RequestString(RangeGreaterThan{0xfff}),
+		"0..106",       // cache.RequestString(RangeWithin{0x00, 0x6a}),
+		"107..128",     // cache.RequestString(RangeWithin{0x6b, 0x80}),
+		"129..256",     // cache.RequestString(RangeWithin{0x81, 0x100}),
+		"257..4095",    // cache.RequestString(RangeWithin{0x101, 0xfff}),
+		"4096..524288", // cache.RequestString(RangeWithin{0x1000, 0x80000}),
 	}
 
 	if !reflect.DeepEqual(requests, expected) {
 		t.Errorf("Expected requests (%v) to equal (%v)", requests, expected)
 	}
 }
+
+func TestRangeSizes(t *testing.T) {
+	s := "https://api.github.com/search/code?q=filename:kustomization.yaml+filename:kustomization.yml" +
+		"+filename:kustomization+size:2365..10000&order=desc&per_page=100&sort=indexed"
+	returnedResult := RangeSizes(s)
+	expectedResult := RangeWithin{uint64(2365), uint64(10000)}
+	if !reflect.DeepEqual(returnedResult, expectedResult) {
+		t.Errorf("RangeSizes expected (%v), got (%v)",expectedResult, returnedResult)
+	}
+}

api/internal/crawl/doc/doc.go

@@ -2,6 +2,8 @@ package doc
 
 import (
 	"fmt"
+	"log"
+	"path/filepath"
 	"sort"
 	"strings"
 
@@ -44,21 +46,36 @@ type KustomizationDocument struct {
 
 type set map[string]struct{}
 
+func (doc *KustomizationDocument) Copy() *KustomizationDocument {
+	return &KustomizationDocument{
+		Document:    *(doc.Document.Copy()),
+		Kinds:       doc.Kinds,
+		Identifiers: doc.Identifiers,
+		Values:      doc.Values,
+	}
+}
+
 func (doc *KustomizationDocument) String() string {
 	return fmt.Sprintf("%s %s %s %v %v %v len(identifiers):%v  len(values):%v",
 		doc.RepositoryURL, doc.FilePath, doc.DefaultBranch, doc.CreationTime,
 		doc.IsSame, doc.Kinds, len(doc.Identifiers), len(doc.Values))
 }
 
-// Implements the CrawlerDocument interface.
-func (doc *KustomizationDocument) GetResources() ([]*Document, error) {
-	isResource := true
-	for _, suffix := range konfig.RecognizedKustomizationFileNames() {
-		if strings.HasSuffix(doc.FilePath, "/"+suffix) {
-			isResource = false
+// IsKustomizationFile determines whether a file path is a kustomization file
+func IsKustomizationFile(path string) bool {
+	basename := filepath.Base(path)
+	for _, name := range konfig.RecognizedKustomizationFileNames() {
+		if basename == name {
+			return true
 		}
 	}
-	if isResource {
+	return false
+}
+
+// Implements the CrawlerDocument interface.
+func (doc *KustomizationDocument) GetResources(
+	includeResources, includeTransformers, includeGenerators bool) ([]*Document, error) {
+	if !IsKustomizationFile(doc.FilePath) {
 		return []*Document{}, nil
 	}
 
@@ -76,20 +93,44 @@ func (doc *KustomizationDocument) GetResources() ([]*Document, error) {
 	}
 	k.FixKustomizationPostUnmarshalling()
 
-	res := make([]*Document, 0, len(k.Resources))
-	for _, r := range k.Resources {
+	res := make([]*Document, 0)
+
+	if includeResources {
+		resourceDocs := doc.CollectDocuments(k.Resources, "resource")
+		res = append(res, resourceDocs...)
+	}
+
+	if includeGenerators {
+		generatorDocs := doc.CollectDocuments(k.Generators, "generator")
+		res = append(res, generatorDocs...)
+	}
+
+	if includeTransformers {
+		transformerDocs := doc.CollectDocuments(k.Transformers, "transformer")
+		res = append(res, transformerDocs...)
+	}
+
+	return res, nil
+}
+
+// CollectDocuments construct a Document for each path in paths, and return
+// a slice of Document pointers.
+func (doc *KustomizationDocument) CollectDocuments(
+	paths []string, fileType string) []*Document {
+	docs := make([]*Document, 0, len(paths))
+	for _, r := range paths {
 		if strings.TrimSpace(r) == "" {
 			continue
 		}
 		next, err := doc.Document.FromRelativePath(r)
 		if err != nil {
-			fmt.Printf("GetResources error: %v\n", err)
+			log.Printf("CollectDocuments error: %v\n", err)
 			continue
 		}
-		res = append(res, &next)
+		next.FileType = fileType
+		docs = append(docs, &next)
 	}
-
-	return res, nil
+	return docs
 }
 
 func (doc *KustomizationDocument) readBytes() ([]map[string]interface{}, error) {

api/internal/crawl/doc/doc_test.go

@@ -189,11 +189,13 @@ metadata:
 	}
 }
 
+type TestStructForGetResources struct {
+	doc       KustomizationDocument
+	resources []*Document
+}
+
 func TestGetResources(t *testing.T) {
-	tests := []struct {
-		doc       KustomizationDocument
-		resources []*Document
-	}{
+	tests := []TestStructForGetResources{
 		{
 			doc: KustomizationDocument{
 				Document: Document{
@@ -213,19 +215,27 @@ resources:
 				{
 					RepositoryURL: "sigs.k8s.io/kustomize",
 					FilePath:      "some/path/to/base",
+					FileType:      "resource",
+					User:          "sigs.k8s.io",
 				},
 				{
 					RepositoryURL: "sigs.k8s.io/kustomize",
 					FilePath:      "some/path/to/otherbase",
+					FileType:      "resource",
+					User:          "sigs.k8s.io",
 				},
 				{
 					RepositoryURL: "sigs.k8s.io/kustomize",
 					FilePath:      "some/path/to/kdir/file.yaml",
+					FileType:      "resource",
+					User:          "sigs.k8s.io",
 				},
 				{
 					RepositoryURL: "https://github.com/kubernetes-sigs/kustomize",
 					FilePath:      "examples/helloWorld",
 					DefaultBranch: "v3.1.0",
+					FileType:      "resource",
+					User:          "kubernetes-sigs",
 				},
 			},
 		},
@@ -248,9 +258,12 @@ resources:
 			resources: []*Document{},
 		},
 	}
+	runTest(t, tests, true, false, false)
+}
 
+func runTest(t *testing.T, tests []TestStructForGetResources, includeResources, includeTransformers, includeGenerators bool) {
 	for _, test := range tests {
-		res, err := test.doc.GetResources()
+		res, err := test.doc.GetResources(includeResources, includeTransformers, includeGenerators)
 		if err != nil {
 			t.Errorf("Unexpected error: %v\n", err)
 			continue
@@ -284,3 +297,83 @@ resources:
 		}
 	}
 }
+
+func TestGetResourcesAndGenerators(t *testing.T) {
+	tests := []TestStructForGetResources{
+		{
+			doc: KustomizationDocument{
+				Document: Document{
+					RepositoryURL: "sigs.k8s.io/kustomize",
+					FilePath:      "some/path/to/kdir/kustomization.yaml",
+					DocumentData: `
+resources:
+- file.yaml
+
+generators:
+- gen.yaml
+
+transformers:
+- tr.yaml
+`},
+			},
+			resources: []*Document{
+				{
+					RepositoryURL: "sigs.k8s.io/kustomize",
+					FilePath:      "some/path/to/kdir/gen.yaml",
+					FileType:      "generator",
+					User:          "sigs.k8s.io",
+				},
+				{
+					RepositoryURL: "sigs.k8s.io/kustomize",
+					FilePath:      "some/path/to/kdir/file.yaml",
+					FileType:      "resource",
+					User:          "sigs.k8s.io",
+				},
+			},
+		},
+	}
+	runTest(t, tests, true, false, true)
+}
+
+func TestGetResourcesAndGeneratorsAndTransformers(t *testing.T) {
+	tests := []TestStructForGetResources{
+		{
+			doc: KustomizationDocument{
+				Document: Document{
+					RepositoryURL: "sigs.k8s.io/kustomize",
+					FilePath:      "some/path/to/kdir/kustomization.yaml",
+					DocumentData: `
+resources:
+- file.yaml
+
+generators:
+- gen.yaml
+
+transformers:
+- tr.yaml
+`},
+			},
+			resources: []*Document{
+				{
+					RepositoryURL: "sigs.k8s.io/kustomize",
+					FilePath:      "some/path/to/kdir/tr.yaml",
+					FileType:      "transformer",
+					User:          "sigs.k8s.io",
+				},
+				{
+					RepositoryURL: "sigs.k8s.io/kustomize",
+					FilePath:      "some/path/to/kdir/gen.yaml",
+					FileType:      "generator",
+					User:          "sigs.k8s.io",
+				},
+				{
+					RepositoryURL: "sigs.k8s.io/kustomize",
+					FilePath:      "some/path/to/kdir/file.yaml",
+					FileType:      "resource",
+					User:          "sigs.k8s.io",
+				},
+			},
+		},
+	}
+	runTest(t, tests, true, true, true)
+}

api/internal/crawl/doc/docname.go

@@ -11,12 +11,18 @@ import (
 )
 
 type Document struct {
-	RepositoryURL string     `json:"repositoryUrl,omitempty"`
+	RepositoryURL string `json:"repositoryUrl,omitempty"`
+	// User makes it easy to aggregate data in the user level instead
+	// of the repository level
+	User          string     `json:"user,omitempty"`
 	FilePath      string     `json:"filePath,omitempty"`
 	DefaultBranch string     `json:"defaultBranch,omitempty"`
 	DocumentData  string     `json:"document,omitempty"`
 	CreationTime  *time.Time `json:"creationTime,omitempty"`
 	IsSame        bool       `json:"-"`
+	// FileType can be one of the following:
+	// "generator", "transformer", "resource", "".
+	FileType string `json:"fileType,omitempty"`
 }
 
 // Implements the CrawlerDocument interface.
@@ -27,14 +33,21 @@ func (doc *Document) GetDocument() *Document {
 func (doc *Document) Copy() *Document {
 	return &Document{
 		RepositoryURL: doc.RepositoryURL,
+		User:          doc.User,
 		FilePath:      doc.FilePath,
 		DefaultBranch: doc.DefaultBranch,
 		DocumentData:  doc.DocumentData,
 		CreationTime:  doc.CreationTime,
 		IsSame:        doc.IsSame,
+		FileType:      doc.FileType,
 	}
 }
 
+func (doc *Document) Path() string {
+	return fmt.Sprintf("repoURL: %s filePath: %s branch: %s",
+		doc.RepositoryURL, doc.FilePath, doc.DefaultBranch)
+}
+
 // Implements the CrawlerDocument interface.
 func (doc *Document) WasCached() bool {
 	return doc.IsSame
@@ -47,6 +60,7 @@ func (doc *Document) FromRelativePath(newFile string) (Document, error) {
 			RepositoryURL: repoSpec.Host + path.Clean(repoSpec.OrgRepo),
 			FilePath:      path.Clean(repoSpec.Path),
 			DefaultBranch: repoSpec.Ref,
+			User:          UserName(repoSpec.Host + path.Clean(repoSpec.OrgRepo)),
 		}, nil
 	}
 	// else document is probably relative path.
@@ -54,6 +68,7 @@ func (doc *Document) FromRelativePath(newFile string) (Document, error) {
 	ret := Document{
 		RepositoryURL: doc.RepositoryURL,
 		DefaultBranch: doc.DefaultBranch,
+		User:          UserName(doc.RepositoryURL),
 	}
 	ogDir, _ := path.Split(doc.FilePath)
 
@@ -78,13 +93,7 @@ func (doc *Document) ID() string {
 }
 
 func (doc *Document) RepositoryFullName() string {
-	url := strings.TrimRight(doc.RepositoryURL, "/")
-
-	gitPrefix := "git@github.com:"
-	if strings.HasPrefix(url, gitPrefix) {
-		url = url[len(gitPrefix):]
-	}
-
+	url := TrimUrl(doc.RepositoryURL)
 	sections := strings.Split(url, "/")
 	l := len(sections)
 	if l < 2 {
@@ -92,3 +101,24 @@ func (doc *Document) RepositoryFullName() string {
 	}
 	return path.Join(sections[l-2], sections[l-1])
 }
+
+// TrimUrl removes all the trailing slashes and the "git@github.com:" prefix (if exists).
+func TrimUrl(s string) string {
+	url := strings.TrimRight(s, "/")
+
+	gitPrefix := "git@github.com:"
+	if strings.HasPrefix(url, gitPrefix) {
+		url = url[len(gitPrefix):]
+	}
+	return url
+}
+
+func UserName(repositoryURL string) string {
+	url := TrimUrl(repositoryURL)
+	sections := strings.Split(url, "/")
+	l := len(sections)
+	if l < 2 {
+		return url
+	}
+	return sections[l-2]
+}

api/internal/crawl/doc/docname_test.go

@@ -28,6 +28,7 @@ func TestFromRelativePath(t *testing.T) {
 						RepositoryURL: "example.com/repo",
 						FilePath:      "path/to/other/file/resource.yaml",
 						DefaultBranch: "master",
+						User:          "example.com",
 					},
 				},
 				{
@@ -36,6 +37,7 @@ func TestFromRelativePath(t *testing.T) {
 						RepositoryURL: "example.com/repo",
 						FilePath:      "path/to/other/file/patch.yaml",
 						DefaultBranch: "master",
+						User:          "example.com",
 					},
 				},
 				{
@@ -44,6 +46,7 @@ func TestFromRelativePath(t *testing.T) {
 						RepositoryURL: "example.com/repo",
 						FilePath:      "path/to/file/service.yaml",
 						DefaultBranch: "master",
+						User:          "example.com",
 					},
 				},
 			},
@@ -65,7 +68,7 @@ func TestFromRelativePath(t *testing.T) {
 
 func TestDocument_RepositoryFullName(t *testing.T) {
 	testCases := []struct {
-		doc Document
+		doc                        Document
 		expectedRepositoryFullName string
 	}{
 		{
@@ -108,4 +111,40 @@ func TestDocument_RepositoryFullName(t *testing.T) {
 				returnedRepositoryFullName)
 		}
 	}
-}
+}
+
+func TestDocument_UserName(t *testing.T) {
+	testCases := []struct {
+		repositoryURL    string
+		expectedUserName string
+	}{
+		{
+			repositoryURL:    "https://github.com/user/repo",
+			expectedUserName: "user",
+		},
+		{
+			repositoryURL:    "https://github.com//user/repo////",
+			expectedUserName: "user",
+		},
+		{
+			repositoryURL:    "repo/",
+			expectedUserName: "repo",
+		},
+		{
+			repositoryURL:    "",
+			expectedUserName: "",
+		},
+		{
+			repositoryURL:    "git@github.com:user/repo",
+			expectedUserName: "user",
+		},
+	}
+
+	for _, tc := range testCases {
+		returnedUserName := UserName(tc.repositoryURL)
+		if returnedUserName != tc.expectedUserName {
+			t.Errorf("UserName expected %s, got %s",
+				tc.expectedUserName, returnedUserName)
+		}
+	}
+}

api/internal/crawl/doc/unique_doc.go

@@ -0,0 +1,36 @@
+package doc
+
+import (
+	"sigs.k8s.io/kustomize/api/internal/crawl/utils"
+)
+
+// UniqueDocuments make sure a Document with a given ID appears only once
+type UniqueDocuments struct {
+	docs   []*Document
+	docIDs utils.SeenMap
+}
+
+func NewUniqueDocuments() UniqueDocuments {
+	return UniqueDocuments{
+		docs:   []*Document{},
+		docIDs: utils.NewSeenMap(),
+	}
+}
+
+func (uds *UniqueDocuments) Add(d *Document) {
+	if uds.docIDs.Seen(d.ID()) {
+		return
+	}
+	uds.docs = append(uds.docs, d)
+	uds.docIDs.Set(d.ID(), "")
+}
+
+func (uds *UniqueDocuments) AddDocuments(docs []*Document) {
+	for _, d := range docs {
+		uds.Add(d)
+	}
+}
+
+func (uds *UniqueDocuments) Documents() []*Document {
+	return uds.docs
+}

api/internal/crawl/index/elasticsearch.go

@@ -20,12 +20,18 @@ const IndexConfig = `
 				"repositoryUrl": {
 					"type": "keyword"
 				},
+				"user": {
+					"type": "keyword"
+				},
 				"filePath": {
 					"type": "keyword"
 				},
 				"defaultBranch": {
 					"type": "keyword"
 				},
+				"fileType": {
+					"type": "keyword"
+				},
 				"document": {
 					"type": "text"
 				},
@@ -87,7 +93,7 @@ func (idx *index) responseErrorOrNil(info string, res *esapi.Response,
 
 	defer res.Body.Close()
 	if res.IsError() {
-		return fmt.Errorf("%s: %s", messageStart, res.String())
+		return fmt.Errorf("%s: %s [%d]", messageStart, res.String(), res.StatusCode)
 	}
 
 	if reader != nil {

api/internal/crawl/index/kustomize.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"io"
 	"io/ioutil"
+	"log"
 	"strings"
 	"time"
 
@@ -17,6 +18,7 @@ const (
 )
 
 type Mode int
+
 const (
 	InsertOrUpdate = iota
 	Delete
@@ -97,14 +99,14 @@ type KustomizeIndex struct {
 }
 
 // Create index reference to the index containing the kustomize documents.
-func NewKustomizeIndex(ctx context.Context) (*KustomizeIndex, error) {
-	idx, err := newIndex(ctx, "kustomize")
+func NewKustomizeIndex(ctx context.Context, indexName string) (*KustomizeIndex, error) {
+	idx, err := newIndex(ctx, indexName)
 	if err != nil {
 		return nil, err
 	}
 
 	indicesExistsOp := idx.client.Indices.Exists
-	resp, err := indicesExistsOp([]string{"kustomize"},
+	resp, err := indicesExistsOp([]string{indexName},
 		indicesExistsOp.WithContext(idx.ctx),
 		indicesExistsOp.WithPretty())
 	if err != nil {
@@ -112,9 +114,9 @@ func NewKustomizeIndex(ctx context.Context) (*KustomizeIndex, error) {
 	}
 
 	if resp.StatusCode == 200 {
-		fmt.Printf("The kustomize index already exists\n")
+		log.Printf("The %s index already exists", indexName)
 	} else {
-		fmt.Printf("Creating the kustomize index\n")
+		log.Printf("Creating the %s index\n", indexName)
 		if err := idx.CreateIndex([]byte(IndexConfig)); err != nil {
 			return nil, err
 		}
@@ -252,7 +254,7 @@ func (it *KustomizeIterator) Next() bool {
 	}
 
 	if it.err == nil {
-		fmt.Printf("updating scroll: %s\n", *it.scrollImpl.ScrollID)
+		log.Printf("updating scroll: %s\n", *it.scrollImpl.ScrollID)
 		it.err = it.update(*it.scrollImpl.ScrollID, reader)
 	}
 
@@ -268,7 +270,7 @@ func (it *KustomizeIterator) Value() KustomizeResult {
 	return it.scrollImpl
 }
 
-// Check if any errors have occured.
+// Check if any errors have occurred.
 func (it *KustomizeIterator) Err() error {
 	return it.err
 }
@@ -341,7 +343,7 @@ func (ki *KustomizeIndex) Search(query string,
 	if err != nil {
 		return nil, fmt.Errorf("failed to format query %s", query)
 	}
-	fmt.Printf("formated query: %s\n", data)
+	log.Printf("formated query: %s\n", data)
 
 	var kr ElasticKustomizeResult
 	err = ki.index.Search(data, opts.SearchOptions, func(results io.Reader) error {

api/internal/crawl/search_cmds/creationTime.md

@@ -1,6 +1,6 @@
 Find out the largest value of the `creationTime` field:
 ```
-curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
     "aggs" : {
         "max_creationTime" : { "max" : { "field" : "creationTime" } }
@@ -11,7 +11,7 @@ curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Cont
 
 Find out the smallest value of the `creationTime` field:
 ```
-curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
     "aggs" : {
         "min_creationTime" : { "min" : { "field" : "creationTime" } }
@@ -22,12 +22,12 @@ curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Cont
 
 Find out the smallest value of the `creationTime` field of all the kustomization files:
 ```
-curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
   "query": {
     "bool": {
       "filter": [
-        { "regexp": { "filePath": ".*/kustomization((.yaml)?|(.yml)?)/*" }}
+        { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}
       ]
     }
   },
@@ -40,13 +40,58 @@ curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Cont
 
 Find out the smallest value of the `creationTime` field of all kustomize resource files:
 ```
-curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
   "query": {
     "bool": {
       "must_not": {
-        "regexp": { "filePath": ".*/kustomization((.yaml)?|(.yml)?)/*" }
-      }
+        "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+      }, 
+      "filter": [
+        { "regexp": { "fileType": "resource"  }}
+      ]
+    }
+  },
+  "aggs" : {
+    "min_creationTime" : { "min" : { "field" : "creationTime" } }
+  }
+}
+'
+```
+
+Find out the smallest value of the `creationTime` field of all kustomize generator files:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "must_not": {
+        "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+      }, 
+      "filter": [
+        { "regexp": { "fileType": "generator"  }}
+      ]
+    }
+  },
+  "aggs" : {
+    "min_creationTime" : { "min" : { "field" : "creationTime" } }
+  }
+}
+'
+```
+
+Find out the smallest value of the `creationTime` field of all kustomize transformer files:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "must_not": {
+        "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+      }, 
+      "filter": [
+        { "regexp": { "fileType": "transformer"  }}
+      ]
     }
   },
   "aggs" : {
@@ -58,7 +103,7 @@ curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Cont
 
 Query all the documents whose `creationTime` <= `2016-07-29T17:38:26.000Z`:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "query": {
     "range": {
@@ -73,7 +118,7 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 
 Query all the documents whose `creationTime` falls within the specific range:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "query": {
     "range": {
@@ -87,14 +132,38 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 '
 ```
 
+Query all the kustomization files whose `creationTime` falls within the specific range:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "size": 20,
+  "query": {
+    "bool": {
+      "filter": {
+        "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }
+      },
+      "must": {
+        "range": {
+          "creationTime": {
+            "gte": "2017-09-24T15:49:57.000Z",
+            "lte": "2017-09-24T15:49:57.000Z"
+          }
+        }
+      }
+    }
+  }
+}
+'
+```
+
 Aggregate how many new kustomization files were added into Github each month:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
     "query": {
         "bool": {
             "filter": [
-                { "regexp": { "filePath": ".*/kustomization((.yaml)?|(.yml)?)/*" }}
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }}
             ]
         }
     },
@@ -112,12 +181,67 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Conte
 
 Aggregate how many new kustomize resource files were added into Github each month:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
     "query": {
         "bool": {
             "must_not": [
-                { "regexp": { "filePath": ".*/kustomization((.yaml)?|(.yml)?)/*" }}
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }}
+            ],
+            "filter": [
+                { "regexp": { "fileType": "resource" }}
+            ]
+        }
+    },
+    "aggs" : {
+        "newFiles_over_time" : {
+            "date_histogram" : {
+                "field" : "creationTime",
+                "interval" : "month"
+            }
+        }
+    }
+}
+'
+```
+
+Aggregate how many new kustomize generator files were added into Github each month:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "must_not": [
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }}
+            ],
+            "filter": [
+                { "regexp": { "fileType": "generator" }}
+            ]
+        }
+    },
+    "aggs" : {
+        "newFiles_over_time" : {
+            "date_histogram" : {
+                "field" : "creationTime",
+                "interval" : "month"
+            }
+        }
+    }
+}
+'
+```
+
+Aggregate how many new kustomize transformer files were added into Github each month:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "must_not": [
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }}
+            ],
+            "filter": [
+                { "regexp": { "fileType": "transformer" }}
             ]
         }
     },
@@ -135,12 +259,12 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Conte
 
 Aggregate how many new kustomization files were added into Github each year:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
     "query": {
         "bool": {
             "filter": [
-                { "regexp": { "filePath": ".*/kustomization((.yaml)?|(.yml)?)/*" }}
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }}
             ]
         }
     },
@@ -158,13 +282,16 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Conte
 
 Aggregate how many new kustomize resource files were added into Github each year:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
     "query": {
         "bool": {
             "must_not": [
-                { "regexp": { "filePath": ".*/kustomization((.yaml)?|(.yml)?)/*" }}
-            ]
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }}
+            ],
+            "filter": [
+                { "regexp": { "fileType": "resource" }}
+            ]            
         }
     },
     "aggs" : {
@@ -177,4 +304,108 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Conte
     }
 }
 '
+```
+
+Aggregate how many new kustomize generator files were added into Github each year:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "must_not": [
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }}
+            ],
+            "filter": [
+                { "regexp": { "fileType": "generator" }}
+            ]            
+        }
+    },
+    "aggs" : {
+        "newFiles_over_time" : {
+            "date_histogram" : {
+                "field" : "creationTime",
+                "interval" : "year"
+            }
+        }
+    }
+}
+'
+```
+
+Aggregate how many new kustomize transformer files were added into Github each year:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "must_not": [
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }}
+            ],
+            "filter": [
+                { "regexp": { "fileType": "transformer" }}
+            ]            
+        }
+    },
+    "aggs" : {
+        "newFiles_over_time" : {
+            "date_histogram" : {
+                "field" : "creationTime",
+                "interval" : "year"
+            }
+        }
+    }
+}
+'
+```
+
+Find the generator files created within the given time range:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "fileType": "generator" }}
+      ],
+      "must_not": {
+        "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+      },
+      "must": {
+        "range": {
+          "creationTime": {
+           "gte": "2019-04-26T16:40:02.000Z",
+           "lte": "2019-04-26T16:40:02.000Z"
+          }
+        }
+      }
+    }
+  }
+}
+'
+```
+
+Find the transformer files created within the given time range:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "fileType": "transformer" }}
+      ],
+      "must_not": {
+        "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+      },
+      "must": {
+        "range": {
+          "creationTime": {
+           "gte": "2019-04-26T16:40:02.000Z",
+           "lte": "2019-04-26T16:40:02.000Z"
+          }
+        }
+      }
+    }
+  }
+}
+'
 ```

api/internal/crawl/search_cmds/defaultBranch.md

@@ -1,6 +1,6 @@
 Count distinct values of the `defaultBranch` field:
 ```
-curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
     "aggs" : {
         "defaultBranch_count" : {
@@ -17,7 +17,7 @@ curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Cont
 List all the github branches where kustomization files and kustomize resource files live, 
 and how many kustomization files and kustomize resource files live in each branch:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
     "aggs" : {
         "defaultBranch" : {

api/internal/crawl/search_cmds/fieldExistence.md

@@ -1,7 +1,7 @@
 Count the documents whose `document` field is empty (The reason why the `document` field
 of a document is empty is because of empty documents):
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
    "size": 10000,
     "query": {
@@ -19,7 +19,7 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 
 Find all the documents having the `creationTime` field set:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
     "query": {
         "exists": {
@@ -32,7 +32,7 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 
 Find all the documents whose `creationTime` field is not set:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
    "size": 10000,
     "query": {

api/internal/crawl/search_cmds/fileType.md

@@ -0,0 +1,301 @@
+Find all the documents having the `fileType` field set:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "exists": {
+            "field": "fileType"
+        }
+    }
+}
+'
+```
+
+Find all the documents whose `fileType` field is not set:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+   "size": 10000,
+    "query": {
+        "bool": {
+            "must_not": {
+                "exists": {
+                    "field": "fileType"
+                }
+            }
+        }
+    }
+}
+'
+```
+
+Search for all the documents whose `fileType` field is `resource`:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "fileType": "resource" }}
+      ]
+    }
+  }
+}
+'
+```
+
+Search for all the kustomization files whose `fileType` field is `resource`:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}, 
+       { "regexp": { "fileType": "resource" }}
+      ]
+    }
+  }
+}
+'
+```
+
+Search for all the kustomize resource files:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "fileType": "resource" }}
+      ],
+      "must_not": {
+        "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+      }
+    }
+  }
+}
+'
+```
+
+Search all the kustomization files including a `generators` field:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "size": 10000,
+  "query": {
+    "bool": {
+      "must": {
+        "match" : {
+          "identifiers" : {
+            "query" : "generators"
+          }
+        }
+      },
+      "filter": {
+        "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+      }
+    }
+  }
+}
+'
+```
+
+Search for all the documents whose `fileType` field is `generator`:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "fileType": "generator" }}
+      ]
+    }
+  }
+}
+'
+```
+
+Search for all the kustomization files whose `fileType` field is `generator`:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}, 
+       { "regexp": { "fileType": "generator" }}
+      ]
+    }
+  }
+}
+'
+```
+
+Search for all the kustomize generator files:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "fileType": "generator" }}
+      ],
+      "must_not": {
+        "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+      }
+    }
+  }
+}
+'
+```
+
+Search all the kustomization files including a `transformers` field:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "size": 10000,
+  "query": {
+    "bool": {
+      "must": {
+        "match" : {
+          "identifiers" : {
+            "query" : "transformers"
+          }
+        }
+      },
+      "filter": {
+        "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+      }
+    }
+  }
+}
+'
+```
+
+Search for all the documents whose `fileType` field is `transformer`:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "fileType": "transformer" }}
+      ]
+    }
+  }
+}
+'
+```
+
+Search for all the kustomization files whose `fileType` field is `transformer`:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}, 
+       { "regexp": { "fileType": "transformer" }}
+      ]
+    }
+  }
+}
+'
+```
+
+Search for all the kustomize transformer files:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "fileType": "transformer" }}
+      ],
+      "must_not": {
+        "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+      }
+    }
+  }
+}
+'
+```
+
+Count distinct values of the `fileType` field:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "aggs" : {
+        "fileType_count" : {
+            "cardinality" : {
+                "field" : "fileType",
+                "precision_threshold": 40000
+            }
+        }
+    }
+}
+'
+```
+
+List all the values of the `fileType` field and the frequency of each value:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "aggs" : {
+        "fileType" : {
+            "terms" : {
+              "field" : "fileType"
+            }
+        }
+    }
+}
+'
+```
+
+
+For all the kustomization files in the index, list all the values of the
+`fileType` field and the frequency of each value:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+             "filter": [
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}
+             ]
+        }
+    },
+    "aggs" : {
+        "fileType" : {
+            "terms" : {
+              "field" : "fileType"
+            }
+        }
+    }
+}
+'
+```
+
+For all the non-kustomization files in the index, list all the values of the
+`fileType` field and the frequency of each value:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "must_not": {
+                "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+            }
+        }
+    },
+    "aggs" : {
+        "fileType" : {
+            "terms" : {
+              "field" : "fileType"
+            }
+        }
+    }
+}
+'
+```

api/internal/crawl/search_cmds/generator.md

@@ -0,0 +1,29 @@
+Find all the generator files whose `kinds` field includes `ChartRenderer`, and
+only output certain fields of each document:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "size": 200,
+  "_source": {
+    "includes": ["kinds", "repositoryUrl", "defaultBranch", "filePath"]
+  },
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "fileType": "generator" }}
+      ],
+      "must_not": {
+        "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+      },
+      "must": {
+        "match" : {
+          "kinds" : {
+            "query" : "ChartRenderer"
+          }
+        }
+      }
+    }
+  }
+}
+'
+```

api/internal/crawl/search_cmds/id.md

@@ -0,0 +1,12 @@
+Find the document with the given `_id`:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "terms": {
+      "_id": [ "b3a03f3327841617db696e2d6abc30e1a1bd653f1a2bbce05637f7dcae1a43f7" ] 
+    }
+  }
+}
+'
+```

api/internal/crawl/search_cmds/keyword_search.md

@@ -1,7 +1,7 @@
 Count the documents in the index whose `repositoryUrl` field starts with
 `https://github.com/`:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "query": {
     "bool": {
@@ -17,7 +17,7 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 Count the documents in the index whose `repositoryUrl` field does not start with
 `https://github.com/`:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "query": {
     "bool": {
@@ -33,7 +33,7 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 Search all the documents matching the given `repositoryUrl` and `filePath`, and return 
 a version for each search hit:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "size": 10000,
   "version": true,
@@ -52,12 +52,28 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 Search all the documents whose filePath ends with one of these following three filenames:
 `kustomization.yaml`, `kustomization.yml`, `kustomization`:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "query": {
     "bool": {
       "filter": [
-       { "regexp": { "filePath": ".*/kustomization((.yaml)?|(.yml)?)/*" }}
+       { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }}
+      ]
+    }
+  }
+}
+'
+```
+
+Search all the documents whose filePath does not end with any of these following
+three filenames: `kustomization.yaml`, `kustomization.yml`, `kustomization`:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "must_not": [
+       { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }}
       ]
     }
   }

api/internal/crawl/search_cmds/misc.md

@@ -1,19 +1,32 @@
 Check the health status of an ElasticSearch cluster:
 ```
-curl -X GET "${ElasticSearchURL}:9200/_cat/health?v&pretty"
+curl -s -X GET "${ElasticSearchURL}:9200/_cat/health?v&pretty"
 ```
 
 Check the indices in an ElasticSearch cluster:
 ```
-curl "${ElasticSearchURL}:9200/_cat/indices?v"
+curl -s "${ElasticSearchURL}:9200/_cat/indices?v"
 ```
 
 Get the mapping of the index:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_mapping?pretty"
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_mapping?pretty"
 ```
 
 Delete the kustomize index from the ElasticSearch cluster (**Use this command with caution**):
 ```
-curl -X DELETE "${ElasticSearchURL}:9200/kustomize?pretty"
+curl -s -X DELETE "${ElasticSearchURL}:9200/${INDEXNAME}?pretty"
+```
+
+Add a new field into an existing index.
+```
+curl -s -X PUT "${ElasticSearchURL}:9200/${INDEXNAME}/_mapping/_doc?pretty" -H 'Content-Type: application/json' -d'
+{
+  "properties": {
+    "fileType": {
+      "type": "keyword"
+    }
+  }
+}
+'
 ```

api/internal/crawl/search_cmds/repositoryUrl.md

@@ -1,6 +1,6 @@
 Count distinct values of the `repositoryUrl` field:
 ```
-curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
     "aggs" : {
         "repositoryUrl_count" : {
@@ -16,12 +16,12 @@ curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Cont
 
 Count how many Github repositories include kustomization files:
 ```
-curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
     "query": {
         "bool": {
              "filter": [
-                { "regexp": { "filePath": ".*/kustomization((.yaml)?|(.yml)?)/*" }}
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }}
              ]
         }
     },
@@ -37,16 +37,143 @@ curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Cont
 '
 ```
 
-Count how many Github repositories include kustomize resource files:
+Count distinct values of the `repositoryUrl` field for all the kustomize resource files in the index:
 ```
-curl -X POST "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
     "query": {
         "bool": {
             "must_not": {
-                "regexp": { "filePath": ".*/kustomization((.yaml)?|(.yml)?)/*" }
+                "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+            },
+            "filter": [
+                { "regexp": { "fileType": "resource" }}
+            ]
+        }
+    },
+    "aggs" : {
+        "repositoryUrl_count" : {
+            "cardinality" : {
+                "field" : "repositoryUrl",
+                "precision_threshold": 40000
             }
         }
+    }
+}
+'
+```
+
+Count distinct values of the `repositoryUrl` field for all the kustomize generator files in the index:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "must_not": {
+                "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+            },
+            "filter": [
+                { "regexp": { "fileType": "generator" }}
+            ]
+        }
+    },
+    "aggs" : {
+        "repositoryUrl_count" : {
+            "cardinality" : {
+                "field" : "repositoryUrl",
+                "precision_threshold": 40000
+            }
+        }
+    }
+}
+'
+```
+
+Count distinct values of the `repositoryUrl` field for all the kustomize transformer files in the index:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "must_not": {
+                "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+            },
+            "filter": [
+                { "regexp": { "fileType": "transformer" }}
+            ]
+        }
+    },
+    "aggs" : {
+        "repositoryUrl_count" : {
+            "cardinality" : {
+                "field" : "repositoryUrl",
+                "precision_threshold": 40000
+            }
+        }
+    }
+}
+'
+```
+
+Count distinct values of the `repositoryUrl` field for all the kustomize resource dirs in the index:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "filter": [
+                { "regexp": { "fileType": "resource" }},
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}
+            ]
+        }
+    },
+    "aggs" : {
+        "repositoryUrl_count" : {
+            "cardinality" : {
+                "field" : "repositoryUrl",
+                "precision_threshold": 40000
+            }
+        }
+    }
+}
+'
+```
+
+Count distinct values of the `repositoryUrl` field for all the kustomize generator dirs in the index:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "filter": [
+                { "regexp": { "fileType": "generator" }},
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}
+            ]
+        }
+    },
+    "aggs" : {
+        "repositoryUrl_count" : {
+            "cardinality" : {
+                "field" : "repositoryUrl",
+                "precision_threshold": 40000
+            }
+        }
+    }
+}
+'
+```
+
+Count distinct values of the `repositoryUrl` field for all the kustomize transformer dirs in the index:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "filter": [
+                { "regexp": { "fileType": "transformer" }},
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}
+            ]
+        }
     },
     "aggs" : {
         "repositoryUrl_count" : {
@@ -64,7 +191,7 @@ List all the github repositories including kustomization files and kustomize res
 and how many kustomization files and kustomize resource files each github repository includes
 (the github repository including the most kustomization files is listed first):
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
     "aggs" : {
         "repositoryUrl" : {
@@ -80,12 +207,12 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Conte
 
 List the top 20 Github repositories including the most amount of kustomization files:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
     "query": {
         "bool": {
              "filter": [
-                { "regexp": { "filePath": ".*/kustomization((.yaml)?|(.yml)?)/*" }}
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }}
              ]
         }
     },
@@ -103,13 +230,16 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Conte
 
 List the top 20 Github repositories including the most amount of kustomize resource files:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
 {
     "query": {
         "bool": {
             "must_not": {
-                "regexp": { "filePath": ".*/kustomization((.yaml)?|(.yml)?)/*" }
-            }
+                "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*" }
+            },
+            "filter": [
+                { "regexp": { "fileType": "resource" }}
+            ]
         }
     },
     "aggs" : {

api/internal/crawl/search_cmds/snapshot.md

@@ -0,0 +1,29 @@
+Retrieve information about all registered snapshot repositories:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/_snapshot?pretty"
+```
+
+Retrieve information about a given snapshot repository, `kustomize-backup`:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/_snapshot/kustomize-backup?pretty"
+```
+
+Verify a snapshot repository, `kustomize-backup`, manually:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/_snapshot/kustomize-backup/_verify?pretty"
+```
+
+List all the snapshots in a given snapshot repository:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/_cat/snapshots/kustomize-backup?v&s=id&pretty"
+```
+
+Retrieve a summary information about a given snapshot:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/_snapshot/kustomize-backup/kustomize-snapshot?pretty"
+```
+
+Retrieve a detailed information about a given snapshot:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/_snapshot/kustomize-backup/kustomize-snapshot/_status?pretty"
+```

api/internal/crawl/search_cmds/text_search.md

@@ -1,6 +1,6 @@
 Search for all the kustomize resource files including a Deployment object:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "query": {
     "match" : {
@@ -16,7 +16,7 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 Search for all the kustomize resource files including a Deployment object, but only
 including the `kinds` field in the result:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "_source": {
     "includes": ["kinds"]
@@ -35,7 +35,7 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 Search for all the kustomize resource files including both a Deployment object and 
 a Service object:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "query": {
     "match" : {
@@ -52,7 +52,7 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 Count the number of documents including Deployment and the number of documents 
 including Service:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "size": 0,
   "aggs" : {
@@ -71,7 +71,7 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 
 Search for all the kustomization files involving CRDs:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "size": 10000,
   "query": {
@@ -87,7 +87,7 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 
 Search for all the kustomization files defining configMapGenerator:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "size": 10000,
   "query": {
@@ -103,7 +103,7 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 
 Search for all the documents having a `kind` field:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "query": {
     "bool": {
@@ -118,7 +118,7 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 
 Search for all the kuostmization files having a `kind` field:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "query": {
     "bool": {
@@ -134,7 +134,7 @@ curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type
 
 Search for all the kustomization files defining the `generatorOptions:disableNameSuffixHash` feature:
 ```
-curl -X GET "${ElasticSearchURL}:9200/kustomize/_search?pretty" -H 'Content-Type: application/json' -d'
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
 {
   "query": {
     "match" : {

api/internal/crawl/search_cmds/transformer.md

@@ -0,0 +1,29 @@
+Find all the transformer files whose `kinds` field includes `HelmValues`, and
+only output certain fields of each document:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "size": 200,
+  "_source": {
+    "includes": ["kinds", "repositoryUrl", "defaultBranch", "filePath"]
+  },
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "fileType": "transformer" }}
+      ],
+      "must_not": {
+        "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+      },
+      "must": {
+        "match" : {
+          "kinds" : {
+            "query" : "HelmValues"
+          }
+        }
+      }
+    }
+  }
+}
+'
+```

api/internal/crawl/search_cmds/user.md

@@ -0,0 +1,380 @@
+Find all the documents having the `user` field set:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "exists": {
+            "field": "user"
+        }
+    }
+}
+'
+```
+
+Find all the documents whose `user` field is not set:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+   "size": 10000,
+    "query": {
+        "bool": {
+            "must_not": {
+                "exists": {
+                    "field": "user"
+                }
+            }
+        }
+    }
+}
+'
+```
+
+Search for all the documents whose `user` field is `kubernetes-sigs`:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?pretty" -H 'Content-Type: application/json' -d'
+{
+  "query": {
+    "bool": {
+      "filter": [
+       { "regexp": { "user": "kubernetes-sigs" }}
+      ]
+    }
+  }
+}
+'
+```
+
+Count distinct values of the `user` field:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "aggs" : {
+        "user_count" : {
+            "cardinality" : {
+                "field" : "user",
+                "precision_threshold": 40000
+            }
+        }
+    }
+}
+'
+```
+
+List all the values of the `user` field and the frequency of each value:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "aggs" : {
+        "user" : {
+            "terms" : {
+                "field" : "user",
+                "size" : 20
+            }
+        }
+    }
+}
+'
+```
+
+Count distinct values of the `user` field for all the kustomization files in the index:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+             "filter": [
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}
+             ]
+        }
+    },
+    "aggs" : {
+        "user_count" : {
+            "cardinality" : {
+                "field" : "user",
+                "precision_threshold": 40000
+            }
+        }
+    }
+}
+'
+```
+
+For all the kustomization files in the index, list all the values of the
+`user` field and the frequency of each value:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+             "filter": [
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}
+             ]
+        }
+    },
+    "aggs" : {
+        "user" : {
+            "terms" : {
+                "field" : "user",
+                "size": 20
+            }
+        }
+    }
+}
+'
+```
+
+Count distinct values of the `user` field for all the kustomize resource files in the index:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "must_not": {
+                "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+            },
+            "filter": [
+                { "regexp": { "fileType": "resource" }}
+            ]
+        }
+    },
+    "aggs" : {
+        "user_count" : {
+            "cardinality" : {
+                "field" : "user",
+                "precision_threshold": 40000
+            }
+        }
+    }
+}
+'
+```
+
+For all the kustomize resource files in the index, list all the values of the
+`user` field and the frequency of each value:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "must_not": {
+                "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+            },
+            "filter": [
+                { "regexp": { "fileType": "resource" }}
+            ]
+        }
+    },
+    "aggs" : {
+        "user" : {
+            "terms" : {
+                "field" : "user",
+                "size": 20
+            }
+        }
+    }
+}
+'
+```
+
+Count distinct values of the `user` field for all the kustomize generator files in the index:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "must_not": {
+                "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+            },
+            "filter": [
+                { "regexp": { "fileType": "generator" }}
+            ]
+        }
+    },
+    "aggs" : {
+        "user_count" : {
+            "cardinality" : {
+                "field" : "user",
+                "precision_threshold": 40000
+            }
+        }
+    }
+}
+'
+```
+
+For all the kustomize generator files in the index, list all the values of the
+`user` field and the frequency of each value:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "must_not": {
+                "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+            },
+            "filter": [
+                { "regexp": { "fileType": "generator" }}
+            ]
+        }
+    },
+    "aggs" : {
+        "user" : {
+            "terms" : {
+              "field" : "user",
+              "size": 20  
+            }
+        }
+    }
+}
+'
+```
+
+Count distinct values of the `user` field for all the kustomize transformer files in the index:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "must_not": {
+                "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+            },
+            "filter": [
+                { "regexp": { "fileType": "transformer" }}
+            ]
+        }
+    },
+    "aggs" : {
+        "user_count" : {
+            "cardinality" : {
+                "field" : "user",
+                "precision_threshold": 40000
+            }
+        }
+    }
+}
+'
+```
+
+For all the kustomize transformer files in the index, list all the values of the
+`user` field and the frequency of each value:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "must_not": {
+                "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }
+            },
+            "filter": [
+                { "regexp": { "fileType": "transformer" }}
+            ]
+        }
+    },
+    "aggs" : {
+        "user" : {
+            "terms" : {
+                "field" : "user",
+                "size": 20
+            }
+        }
+    }
+}
+'
+```
+
+Count distinct values of the `user` field for all the kustomize generator dirs in the index:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "filter": [
+                { "regexp": { "fileType": "generator" }},
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}
+            ]
+        }
+    },
+    "aggs" : {
+        "user_count" : {
+            "cardinality" : {
+                "field" : "user",
+                "precision_threshold": 40000
+            }
+        }
+    }
+}
+'
+```
+
+For all the kustomize generator dirs in the index, list all the values of the
+`user` field and the frequency of each value:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "filter": [
+                { "regexp": { "fileType": "generator" }},
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}
+            ]
+        }
+    },
+    "aggs" : {
+        "user" : {
+            "terms" : {
+              "field" : "user",
+              "size": 20  
+            }
+        }
+    }
+}
+'
+```
+
+Count distinct values of the `user` field for all the kustomize transformer dirs in the index:
+```
+curl -s -X POST "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "filter": [
+                { "regexp": { "fileType": "transformer" }},
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}
+            ]
+        }
+    },
+    "aggs" : {
+        "user_count" : {
+            "cardinality" : {
+                "field" : "user",
+                "precision_threshold": 40000
+            }
+        }
+    }
+}
+'
+```
+
+For all the kustomize transformer dirs in the index, list all the values of the
+`user` field and the frequency of each value:
+```
+curl -s -X GET "${ElasticSearchURL}:9200/${INDEXNAME}/_search?size=0&pretty" -H 'Content-Type: application/json' -d'
+{
+    "query": {
+        "bool": {
+            "filter": [
+                { "regexp": { "fileType": "transformer" }},
+                { "regexp": { "filePath": "(.*/)?kustomization((.yaml)?|(.yml)?)(/)*"  }}
+            ]
+        }
+    },
+    "aggs" : {
+        "user" : {
+            "terms" : {
+              "field" : "user"
+            }
+        }
+    }
+}
+'
+```

api/internal/crawl/utils/utils.go

@@ -0,0 +1,21 @@
+package utils
+
+type SeenMap map[string]string
+
+func (seen SeenMap) Seen(item string) bool {
+	_, ok := seen[item]
+	return ok
+}
+
+func (seen SeenMap) Set(k, v string) {
+	seen[k] = v
+}
+
+// The caller should make sure that key is in the map.
+func (seen SeenMap) Value(k string) string {
+	return seen[k]
+}
+
+func NewSeenMap() SeenMap {
+	return make(map[string]string)
+}