Merge pull request #4282 from KnVerey/pinToCmdConfig

Pin to cmd/config v0.10.2

.github/workflows/go.yml

@@ -16,14 +16,14 @@ jobs:
     - name: Set up Go 1.x
       uses: actions/setup-go@v2
       with:
-        go-version: ^1.13
+        go-version: ^1.16
       id: go
 
     - name: Check out code into the Go module directory
       uses: actions/checkout@v2
 
     - name: Lint
-      run: ./scripts/kyaml-pre-commit.sh
+      run: ./hack/kyaml-pre-commit.sh
       env:
         KUSTOMIZE_DOCKER_E2E: false # don't need to do e2e tests for linting
 
@@ -35,7 +35,7 @@ jobs:
       - name: Set up Go 1.x
         uses: actions/setup-go@v2
         with:
-          go-version: ^1.13
+          go-version: ^1.16
         id: go
 
       - name: Check out code into the Go module directory
@@ -45,6 +45,10 @@ jobs:
         run: go test -cover ./...
         working-directory: ./kyaml
 
+      - name: Test api
+        run: go test -cover ./... -ldflags "-X sigs.k8s.io/kustomize/api/provenance.version=v444.333.222"
+        working-directory: ./api
+
       - name: Test cmd/config
         run: go test -cover ./...
         working-directory: ./cmd/config
@@ -59,7 +63,7 @@ jobs:
       - name: Set up Go 1.x
         uses: actions/setup-go@v2
         with:
-          go-version: ^1.13
+          go-version: ^1.16
         id: go
 
       - name: Check out code into the Go module directory
@@ -69,6 +73,10 @@ jobs:
         run: go test -cover ./...
         working-directory: ./kyaml
 
+      - name: Test api
+        run: go test -cover ./... -ldflags "-X sigs.k8s.io/kustomize/api/provenance.version=v444.333.222"
+        working-directory: ./api
+
       - name: Test cmd/config
         run: go test -cover ./...
         working-directory: ./cmd/config
@@ -83,7 +91,7 @@ jobs:
       - name: Set up Go 1.x
         uses: actions/setup-go@v2
         with:
-          go-version: ^1.13
+          go-version: ^1.16
         id: go
 
       - name: Check out code into the Go module directory
@@ -93,6 +101,11 @@ jobs:
         run: go test -cover ./...
         working-directory: ./kyaml
 
+      # TODO: uncomment once Windows tests are passing.
+      # - name: Test api
+      #   run: go test -cover ./... -ldflags "-X sigs.k8s.io/kustomize/api/provenance.version=v444.333.222"
+      #   working-directory: ./api
+
       - name: Test cmd/config
         run: go test -cover ./...
         working-directory: ./cmd/config

CONTRIBUTING.md

@@ -1,6 +1,25 @@
+[SIG-CLI]: https://github.com/kubernetes/community/tree/master/sig-cli
+[Slack channel]: https://kubernetes.slack.com/messages/kustomize
+[Mailing list]: https://groups.google.com/forum/#!forum/kubernetes-sig-cli
+
+[OWNERS file spec]: https://github.com/kubernetes/community/blob/master/contributors/guide/owners.md
+[Kustomize OWNERS_ALIASES]: https://github.com/kubernetes-sigs/kustomize/blob/8049f7b1af52e8a7ec26faf6cf714f560d0043c5/OWNERS_ALIASES
+[SIG-CLI Teams]: https://github.com/kubernetes/org/blob/main/config/kubernetes-sigs/sig-cli/teams.yaml
+[Github permissions]: https://docs.github.com/en/organizations/managing-access-to-your-organizations-repositories/repository-permission-levels-for-an-organization#repository-access-for-each-permission-level
+
+[Contributor License Agreement]: https://git.k8s.io/community/CLA.md
+[Kubernetes Contributor Guide]: http://git.k8s.io/community/contributors/guide
+[Contributor Cheat Sheet]: https://git.k8s.io/community/contributors/guide/contributor-cheatsheet/README.md
+[CNCF Code of Conduct]: https://github.com/cncf/foundation/blob/master/code-of-conduct.md
+[Kubernetes Community Membership]: https://github.com/kubernetes/community/blob/master/community-membership.md
+
+[Contribution Guide]: https://kubectl.docs.kubernetes.io/contributing/kustomize/
+[MacOS Dev Guide]: https://kubectl.docs.kubernetes.io/contributing/kustomize/mac/
+[Windows Dev Guide]: https://kubectl.docs.kubernetes.io/contributing/kustomize/windows/
+
 # Contributing Guidelines
 
-Welcome to Kubernetes. We are excited about the prospect of you joining our [community](https://github.com/kubernetes/community)! The Kubernetes community abides by the CNCF [code of conduct](code-of-conduct.md). Here is an excerpt:
+Welcome to Kubernetes. We are excited about the prospect of you joining our [community](https://github.com/kubernetes/community)! The Kubernetes community abides by the [CNCF Code of Conduct]. Here is an excerpt:
 
 _As contributors and maintainers of this project, and in the interest of fostering an open and welcoming community, we pledge to respect all people who contribute through reporting issues, posting feature requests, updating documentation, submitting pull requests or patches, and other activities._
 
@@ -8,19 +27,45 @@ _As contributors and maintainers of this project, and in the interest of fosteri
 
 Dev guides:
 
-- [Mac](docs/macDevGuide.md)
+- [Contribution Guide]
+- [MacOS Dev Guide]
+- [Windows Dev Guide]
 
-We have full documentation on how to get started contributing here:
+General resources for contributors:
 
-- [Contributor License Agreement](https://git.k8s.io/community/CLA.md) Kubernetes projects require that you sign a Contributor License Agreement (CLA) before we can accept your pull requests
-- [Kubernetes Contributor Guide](http://git.k8s.io/community/contributors/guide) - Main contributor documentation, or you can just jump directly to the [contributing section](http://git.k8s.io/community/contributors/guide#contributing)
-- [Contributor Cheat Sheet](https://git.k8s.io/community/contributors/guide/contributor-cheatsheet/README.md) - Common resources for existing developers
+- [Contributor License Agreement] - Kubernetes projects require that you sign a Contributor License Agreement (CLA) before we can accept your pull requests.
+- [Kubernetes Contributor Guide] - Main contributor documentation.
+- [Contributor Cheat Sheet] - Common resources for existing developers.
+
+Here are some additional ideas to help you get started with Kustomize:
+- Attend a Kustomize Bug Scrub. Check the [SIG-CLI] meetings list to find the next one.
+- Help triage issues by confirming validity and applying the appropriate `kind` label (e.g. comment `/kind bug`).
+- Pick up an issue to fix. Issues with the `help-wanted` label are a good place to start, but you can also look for any issue with the `triage/accepted` label and no assignee. Remember to `/assign` yourself to let others know you're working on it.
+- Help confirm new issues labelled `kind/bug` by reproducing them with the latest release.
+- Support Kustomize users by responding to questions on issues labelled `kind/support` or in the [Slack channel].
 
 ## Mentorship
 
 - [Mentoring Initiatives](https://git.k8s.io/community/mentoring) - We have a diverse set of mentorship programs available that are always looking for volunteers!
 
+## Contributor Ladder
+
+Kustomize follows the [Kubernetes Community Membership] contributor ladder. Roles are as follows:
+
+1. Contributor: Anyone who actively contributes code, issues or reviews to the project. All contributors must sign the [Contributor License Agreement].
+1. Reviewer: Contributors with a history of review and authorship on Kustomize. Has LGTM rights on the Kustomize repo (as do all kubernetes-sigs org members). Active contributors are encouraged to join the reviewers list to be automatically pinged on PRs.
+1. Approver: Highly experienced active reviewer and contributor to Kustomize. Has both LTGM and approval rights on the Kustomize repo, as well as "maintain" [Github permissions].
+1. Owner: Approver who sets technical direction and makes or approves design decisions for the project. Has LGTM and approval rights on the Kustomize repo as well as "admin" [Github permissions].
+
+The kyaml module within the Kustomize repo has additional owners following the same ladder.
+
+Administrative notes:
+
+- The [OWNERS file spec] is a useful resources in making changes.
+- Maintainers and admins must be added to the appropriate lists in both [Kustomize OWNERS_ALIASES] and [SIG-CLI Teams]. If this isn't done, the individual in question will lack either PR approval rights (Kustomize list) or the appropriate Github repository permissions (community list).
+
+
 ## Contact Information
 
-- [Slack channel](https://kubernetes.slack.com/messages/sig-cli)
-- [Mailing list](https://groups.google.com/forum/#!forum/kubernetes-sig-cli)
+- [Slack channel]
+- [Mailing list]

Makefile

@@ -4,12 +4,15 @@
 # Makefile for kustomize CLI and API.
 
 SHELL := /usr/bin/env bash
+GOOS = $(shell go env GOOS)
+GOARCH = $(shell go env GOARCH)
 MYGOBIN = $(shell go env GOBIN)
 ifeq ($(MYGOBIN),)
 MYGOBIN = $(shell go env GOPATH)/bin
 endif
 export PATH := $(MYGOBIN):$(PATH)
 MODULES := '"cmd/config" "api/" "kustomize/" "kyaml/"'
+LATEST_V4_RELEASE=v4.4.0
 
 # Provide defaults for REPO_OWNER and REPO_NAME if not present.
 # Typically these values would be provided by Prow.
@@ -22,58 +25,48 @@ REPO_NAME := "kustomize"
 endif
 
 .PHONY: all
-all: verify-kustomize
+all: install-tools verify-kustomize
 
 .PHONY: verify-kustomize
 verify-kustomize: \
 	lint-kustomize \
 	test-unit-kustomize-all \
 	test-examples-kustomize-against-HEAD \
-	test-examples-kustomize-against-4.0
+	test-examples-kustomize-against-v4-release
 
 # 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: \
+	install-tools \
 	lint-kustomize \
 	test-multi-module \
 	test-unit-kustomize-all \
 	test-unit-cmd-all \
 	test-go-mod \
 	test-examples-kustomize-against-HEAD \
-	test-examples-kustomize-against-4.0
+	test-examples-kustomize-against-v4-release
 
 .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 hack/go.mod
+# cannot assume that golanci-lint is at the version they want.
+# This installs what kustomize wants to use.
 $(MYGOBIN)/golangci-lint-kustomize:
-	( \
-		set -e; \
-		cd hack; \
-		GO111MODULE=on go build -tags=tools -o $(MYGOBIN)/golangci-lint-kustomize github.com/golangci/golangci-lint/cmd/golangci-lint; \
-	)
+	rm -f $(CURDIR)/hack/golangci-lint
+	GOBIN=$(CURDIR)/hack go install github.com/golangci/golangci-lint/cmd/golangci-lint@v1.23.8
+	mv $(CURDIR)/hack/golangci-lint $(MYGOBIN)/golangci-lint-kustomize
 
-# Install from version specified in api/go.mod.
 $(MYGOBIN)/mdrip:
-	cd api; \
-	go install github.com/monopole/mdrip
+	go install github.com/monopole/mdrip@v1.0.2
 
-# Install from version specified in api/go.mod.
 $(MYGOBIN)/stringer:
-	cd api; \
-	go install golang.org/x/tools/cmd/stringer
+	go get golang.org/x/tools/cmd/stringer
 
-# Install from version specified in api/go.mod.
 $(MYGOBIN)/goimports:
-	cd api; \
-	go install golang.org/x/tools/cmd/goimports
+	go get golang.org/x/tools/cmd/goimports
 
 # Build from local source.
 $(MYGOBIN)/gorepomod:
@@ -141,6 +134,7 @@ pSrc=plugin/builtin
 _builtinplugins = \
 	AnnotationsTransformer.go \
 	ConfigMapGenerator.go \
+	IAMPolicyGenerator.go \
 	HashTransformer.go \
 	ImageTagTransformer.go \
 	LabelTransformer.go \
@@ -150,6 +144,7 @@ _builtinplugins = \
 	PatchStrategicMergeTransformer.go \
 	PatchTransformer.go \
 	PrefixSuffixTransformer.go \
+	ReplacementTransformer.go \
 	ReplicaCountTransformer.go \
 	SecretGenerator.go \
 	ValueAddTransformer.go \
@@ -167,6 +162,7 @@ builtinplugins = $(patsubst %,$(pGen)/%,$(_builtinplugins))
 # that file, will be recreated.
 $(pGen)/AnnotationsTransformer.go: $(pSrc)/annotationstransformer/AnnotationsTransformer.go
 $(pGen)/ConfigMapGenerator.go: $(pSrc)/configmapgenerator/ConfigMapGenerator.go
+$(pGen)/GkeSaGenerator.go: $(pSrc)/gkesagenerator/GkeSaGenerator.go
 $(pGen)/HashTransformer.go: $(pSrc)/hashtransformer/HashTransformer.go
 $(pGen)/ImageTagTransformer.go: $(pSrc)/imagetagtransformer/ImageTagTransformer.go
 $(pGen)/LabelTransformer.go: $(pSrc)/labeltransformer/LabelTransformer.go
@@ -176,6 +172,7 @@ $(pGen)/PatchJson6902Transformer.go: $(pSrc)/patchjson6902transformer/PatchJson6
 $(pGen)/PatchStrategicMergeTransformer.go: $(pSrc)/patchstrategicmergetransformer/PatchStrategicMergeTransformer.go
 $(pGen)/PatchTransformer.go: $(pSrc)/patchtransformer/PatchTransformer.go
 $(pGen)/PrefixSuffixTransformer.go: $(pSrc)/prefixsuffixtransformer/PrefixSuffixTransformer.go
+$(pGen)/ReplacementTransformer.go: $(pSrc)/replacementtransformer/ReplacementTransformer.go
 $(pGen)/ReplicaCountTransformer.go: $(pSrc)/replicacounttransformer/ReplicaCountTransformer.go
 $(pGen)/SecretGenerator.go: $(pSrc)/secretgenerator/SecretGenerator.go
 $(pGen)/ValueAddTransformer.go: $(pSrc)/valueaddtransformer/ValueAddTransformer.go
@@ -209,7 +206,7 @@ clean-kustomize-external-go-plugin:
 ### End kustomize plugin rules.
 
 .PHONY: lint-kustomize
-lint-kustomize: install-tools $(builtinplugins)
+lint-kustomize: $(MYGOBIN)/golangci-lint-kustomize $(builtinplugins)
 	cd api; $(MYGOBIN)/golangci-lint-kustomize \
 	  -c ../.golangci-kustomize.yml \
 	  run ./...
@@ -232,7 +229,8 @@ generate-kustomize-api: $(MYGOBIN)/k8scopy
 
 .PHONY: test-unit-kustomize-api
 test-unit-kustomize-api: build-kustomize-api
-	cd api; go test ./...  -ldflags "-X sigs.k8s.io/kustomize/api/provenance.version=v444.333.222"
+	cd api; go test ./...  -ldflags "-X sigs.k8s.io/kustomize/api/provenance.version=v444.333.222"; \
+	cd krusty; OPENAPI_TEST=true go test -run TestCustomOpenAPIFieldFromComponentWithOverlays
 
 .PHONY: test-unit-kustomize-plugins
 test-unit-kustomize-plugins:
@@ -249,10 +247,10 @@ test-unit-kustomize-all: \
 	test-unit-kustomize-plugins
 
 test-unit-cmd-all:
-	./scripts/kyaml-pre-commit.sh
+	./hack/kyaml-pre-commit.sh
 
 test-go-mod:
-	./scripts/check-go-mod.sh
+	./hack/check-go-mod.sh
 
 # Environment variables are defined at
 # https://github.com/kubernetes/test-infra/blob/master/prow/jobs.md#job-environment-variables
@@ -264,7 +262,7 @@ test-multi-module: $(MYGOBIN)/prchecker
 		export REPO_NAME=$(REPO_NAME); \
 		export PULL_NUMBER=$(PULL_NUMBER); \
 		export MODULES=$(MODULES); \
-		./scripts/check-multi-module.sh; \
+		./hack/check-multi-module.sh; \
 	)
 
 .PHONY:
@@ -282,8 +280,8 @@ test-examples-kustomize-against-HEAD: $(MYGOBIN)/kustomize $(MYGOBIN)/mdrip
 	./hack/testExamplesAgainstKustomize.sh HEAD
 
 .PHONY:
-test-examples-kustomize-against-4.0: $(MYGOBIN)/mdrip
-	./hack/testExamplesAgainstKustomize.sh v4@v4.0.5
+test-examples-kustomize-against-v4-release: $(MYGOBIN)/mdrip
+	./hack/testExamplesAgainstKustomize.sh v4@$(LATEST_V4_RELEASE)
 
 # linux only.
 # This is for testing an example plugin that
@@ -295,8 +293,8 @@ $(MYGOBIN)/kubeval:
 	( \
 		set -e; \
 		d=$(shell mktemp -d); cd $$d; \
-		wget https://github.com/instrumenta/kubeval/releases/latest/download/kubeval-linux-amd64.tar.gz; \
-		tar xf kubeval-linux-amd64.tar.gz; \
+		wget https://github.com/instrumenta/kubeval/releases/latest/download/kubeval-$(GOOS)-$(GOARCH).tar.gz; \
+		tar xf kubeval-$(GOOS)-$(GOARCH).tar.gz; \
 		mv kubeval $(MYGOBIN); \
 		rm -rf $$d; \
 	)
@@ -310,10 +308,10 @@ $(MYGOBIN)/helmV2:
 	( \
 		set -e; \
 		d=$(shell mktemp -d); cd $$d; \
-		tgzFile=helm-v2.13.1-linux-amd64.tar.gz; \
+		tgzFile=helm-v2.13.1-$(GOOS)-$(GOARCH).tar.gz; \
 		wget https://storage.googleapis.com/kubernetes-helm/$$tgzFile; \
 		tar -xvzf $$tgzFile; \
-		mv linux-amd64/helm $(MYGOBIN)/helmV2; \
+		mv $(GOOS)-$(GOARCH)/helm $(MYGOBIN)/helmV2; \
 		rm -rf $$d \
 	)
 
@@ -323,10 +321,10 @@ $(MYGOBIN)/helmV3:
 	( \
 		set -e; \
 		d=$(shell mktemp -d); cd $$d; \
-		tgzFile=helm-v3.5.3-linux-amd64.tar.gz; \
+		tgzFile=helm-v3.6.3-$(GOOS)-$(GOARCH).tar.gz; \
 		wget https://get.helm.sh/$$tgzFile; \
 		tar -xvzf $$tgzFile; \
-		mv linux-amd64/helm $(MYGOBIN)/helmV3; \
+		mv $(GOOS)-$(GOARCH)/helm $(MYGOBIN)/helmV3; \
 		rm -rf $$d \
 	)
 
@@ -334,7 +332,7 @@ $(MYGOBIN)/kind:
 	( \
         set -e; \
         d=$(shell mktemp -d); cd $$d; \
-        wget -O ./kind https://github.com/kubernetes-sigs/kind/releases/download/v0.7.0/kind-$(shell uname)-amd64; \
+        wget -O ./kind https://github.com/kubernetes-sigs/kind/releases/download/v0.7.0/kind-$(GOOS)-$(GOARCH); \
         chmod +x ./kind; \
         mv ./kind $(MYGOBIN); \
         rm -rf $$d; \
@@ -345,10 +343,10 @@ $(MYGOBIN)/gh:
 	( \
 		set -e; \
 		d=$(shell mktemp -d); cd $$d; \
-		tgzFile=gh_1.0.0_linux_amd64.tar.gz; \
+		tgzFile=gh_1.0.0_$(GOOS)_$(GOARCH).tar.gz; \
 		wget https://github.com/cli/cli/releases/download/v1.0.0/$$tgzFile; \
 		tar -xvzf $$tgzFile; \
-		mv gh_1.0.0_linux_amd64/bin/gh  $(MYGOBIN)/gh; \
+		mv gh_1.0.0_$(GOOS)_$(GOARCH)/bin/gh  $(MYGOBIN)/gh; \
 		rm -rf $$d \
 	)
 
@@ -356,8 +354,12 @@ $(MYGOBIN)/gh:
 clean: clean-kustomize-external-go-plugin
 	go clean --cache
 	rm -f $(builtinplugins)
-	rm -f $(MYGOBIN)/kustomize
+	rm -f $(MYGOBIN)/goimports
 	rm -f $(MYGOBIN)/golangci-lint-kustomize
+	rm -f $(MYGOBIN)/kustomize
+	rm -f $(MYGOBIN)/mdrip
+	rm -f $(MYGOBIN)/prchecker
+	rm -f $(MYGOBIN)/stringer
 
 # Handle pluginator manually.
 # rm -f $(MYGOBIN)/pluginator

OWNERS

@@ -1,4 +1,6 @@
 # See https://github.com/kubernetes/community/blob/master/community-membership.md
 approvers:
-  - kustomize-admins
-  - kustomize-maintainers
+  - kustomize-approvers
+
+reviewers:
+  - kustomize-reviewers

OWNERS_ALIASES

@@ -1,15 +1,30 @@
+# Keep *-owners and *-approvers lists in sync with *-admins and *-maintainers in
+# https://github.com/kubernetes/org/blob/main/config/kubernetes-sigs/sig-cli/teams.yaml
 aliases:
-  kustomize-admins:
+  kustomize-owners:
+    - knverey
     - monopole
     - pwittrock
-  kustomize-maintainers:
-    - droot
+  kustomize-approvers:
     - justinsb
-    - liujingfang1
-    - mengqiy
+    - knverey
     - monopole
+    - natasha41575
     - pwittrock
+  kustomize-reviewers:
+    - knverey
+    - monopole
+    - natasha41575
+
+  kyaml-approvers:
+    - mengqiy
     - mortent
     - phanimarupaka
+  kyaml-reviewers:
+    - mengqiy
+    - mortent
+    - phanimarupaka
+
+  emeritus-approvers:
+    - liujingfang1
     - Shell32-Natsu
-    - natasha41575

README.md

@@ -22,15 +22,22 @@ This tool is sponsored by [sig-cli] ([KEP]).
 
 The kustomize build flow at [v2.0.3] was added
 to [kubectl v1.14][kubectl announcement].  The kustomize
-flow in kubectl has remained frozen at v2.0.3 while work
-to extract kubectl from the k/k repo, and work to remove
-kustomize's dependence on core k/k code ([#2506]) has proceeded.
-The reintegration effort is tracked in [#1500] (and its blocking
-issues).
+flow in kubectl remained frozen at v2.0.3 until kubectl v1.21,
+which [updated it to v4.0.5][kust-in-kubectl update]. It will
+be updated on a regular basis going forward, and such updates
+will be reflected in the Kubernetes release notes.
+
+| Kubectl version | Kustomize version |
+| --- | --- |
+| < v1.14 | n/a |
+| v1.14-v1.20 | v2.0.3 |
+| v1.21 | v4.0.5 |
+| v1.22 | v4.2.0 |
 
 [v2.0.3]: /../../tree/v2.0.3
 [#2506]: https://github.com/kubernetes-sigs/kustomize/issues/2506
 [#1500]: https://github.com/kubernetes-sigs/kustomize/issues/1500
+[kust-in-kubectl update]: https://github.com/kubernetes/kubernetes/blob/4d75a6238a6e330337526e0513e67d02b1940b63/CHANGELOG/CHANGELOG-1.21.md#kustomize-updates-in-kubectl
 
 For examples and guides for using the kubectl integration please
 see the [kubectl book] or the [kubernetes documentation].
@@ -145,7 +152,7 @@ is governed by the [Kubernetes Code of Conduct].
 [`make`]: https://www.gnu.org/software/make
 [`sed`]: https://www.gnu.org/software/sed
 [DAM]: https://kubernetes-sigs.github.io/kustomize/api-reference/glossary#declarative-application-management
-[KEP]: https://github.com/kubernetes/enhancements/blob/master/keps/sig-cli/0008-kustomize.md
+[KEP]: https://github.com/kubernetes/enhancements/blob/master/keps/sig-cli/2377-Kustomize/README.md
 [Kubernetes Code of Conduct]: code-of-conduct.md
 [applied]: https://kubernetes-sigs.github.io/kustomize/api-reference/glossary#apply
 [base]: https://kubernetes-sigs.github.io/kustomize/api-reference/glossary#base

api/builtins/AnnotationsTransformer.go

@@ -27,16 +27,10 @@ func (p *AnnotationsTransformerPlugin) Transform(m resmap.ResMap) error {
 	if len(p.Annotations) == 0 {
 		return nil
 	}
-	for _, r := range m.Resources() {
-		err := r.ApplyFilter(annotations.Filter{
-			Annotations: p.Annotations,
-			FsSlice:     p.FieldSpecs,
-		})
-		if err != nil {
-			return err
-		}
-	}
-	return nil
+	return m.ApplyFilter(annotations.Filter{
+		Annotations: p.Annotations,
+		FsSlice:     p.FieldSpecs,
+	})
 }
 
 func NewAnnotationsTransformerPlugin() resmap.TransformerPlugin {

api/builtins/HelmChartInflationGenerator.go

@@ -267,6 +267,9 @@ func (p *HelmChartInflationGeneratorPlugin) templateCommand() []string {
 	if p.ReleaseName != "" {
 		args = append(args, p.ReleaseName)
 	}
+	if p.Namespace != "" {
+		args = append(args, "--namespace", p.Namespace)
+	}
 	args = append(args, filepath.Join(p.absChartHome(), p.Name))
 	if p.ValuesFile != "" {
 		args = append(args, "--values", p.ValuesFile)
@@ -277,6 +280,9 @@ func (p *HelmChartInflationGeneratorPlugin) templateCommand() []string {
 		// I've tried placing the flag before and after the name argument.
 		args = append(args, "--generate-name")
 	}
+	if p.IncludeCRDs {
+		args = append(args, "--include-crds")
+	}
 	return args
 }
 

api/builtins/IAMPolicyGenerator.go

@@ -0,0 +1,33 @@
+// Code generated by pluginator on IAMPolicyGenerator; DO NOT EDIT.
+// pluginator {unknown  1970-01-01T00:00:00Z  }
+
+package builtins
+
+import (
+	"sigs.k8s.io/kustomize/api/filters/iampolicygenerator"
+	"sigs.k8s.io/kustomize/api/resmap"
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/yaml"
+)
+
+type IAMPolicyGeneratorPlugin struct {
+	types.IAMPolicyGeneratorArgs
+}
+
+func (p *IAMPolicyGeneratorPlugin) Config(h *resmap.PluginHelpers, config []byte) (err error) {
+	p.IAMPolicyGeneratorArgs = types.IAMPolicyGeneratorArgs{}
+	err = yaml.Unmarshal(config, p)
+	return
+}
+
+func (p *IAMPolicyGeneratorPlugin) Generate() (resmap.ResMap, error) {
+	r := resmap.New()
+	err := r.ApplyFilter(iampolicygenerator.Filter{
+		IAMPolicyGenerator: p.IAMPolicyGeneratorArgs,
+	})
+	return r, err
+}
+
+func NewIAMPolicyGeneratorPlugin() resmap.GeneratorPlugin {
+	return &IAMPolicyGeneratorPlugin{}
+}

api/builtins/ImageTagTransformer.go

@@ -25,24 +25,15 @@ func (p *ImageTagTransformerPlugin) Config(
 }
 
 func (p *ImageTagTransformerPlugin) Transform(m resmap.ResMap) error {
-	for _, r := range m.Resources() {
-		// traverse all fields at first
-		err := r.ApplyFilter(imagetag.LegacyFilter{
-			ImageTag: p.ImageTag,
-		})
-		if err != nil {
-			return err
-		}
-		// then use user specified field specs
-		err = r.ApplyFilter(imagetag.Filter{
-			ImageTag: p.ImageTag,
-			FsSlice:  p.FieldSpecs,
-		})
-		if err != nil {
-			return err
-		}
+	if err := m.ApplyFilter(imagetag.LegacyFilter{
+		ImageTag: p.ImageTag,
+	}); err != nil {
+		return err
 	}
-	return nil
+	return m.ApplyFilter(imagetag.Filter{
+		ImageTag: p.ImageTag,
+		FsSlice:  p.FieldSpecs,
+	})
 }
 
 func NewImageTagTransformerPlugin() resmap.TransformerPlugin {

api/builtins/LabelTransformer.go

@@ -27,16 +27,10 @@ func (p *LabelTransformerPlugin) Transform(m resmap.ResMap) error {
 	if len(p.Labels) == 0 {
 		return nil
 	}
-	for _, r := range m.Resources() {
-		err := r.ApplyFilter(labels.Filter{
-			Labels:  p.Labels,
-			FsSlice: p.FieldSpecs,
-		})
-		if err != nil {
-			return err
-		}
-	}
-	return nil
+	return m.ApplyFilter(labels.Filter{
+		Labels:  p.Labels,
+		FsSlice: p.FieldSpecs,
+	})
 }
 
 func NewLabelTransformerPlugin() resmap.TransformerPlugin {

api/builtins/NamespaceTransformer.go

@@ -30,7 +30,7 @@ func (p *NamespaceTransformerPlugin) Transform(m resmap.ResMap) error {
 		return nil
 	}
 	for _, r := range m.Resources() {
-		if r.IsEmpty() {
+		if r.IsNilOrEmpty() {
 			// Don't mutate empty objects?
 			continue
 		}

api/builtins/PatchJson6902Transformer.go

@@ -12,6 +12,7 @@ import (
 	"sigs.k8s.io/kustomize/api/ifc"
 	"sigs.k8s.io/kustomize/api/resmap"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/kio/kioutil"
 	"sigs.k8s.io/yaml"
 )
 
@@ -78,12 +79,23 @@ func (p *PatchJson6902TransformerPlugin) Transform(m resmap.ResMap) error {
 		return err
 	}
 	for _, res := range resources {
+		internalAnnotations := kioutil.GetInternalAnnotations(&res.RNode)
+
 		err = res.ApplyFilter(patchjson6902.Filter{
 			Patch: p.JsonOp,
 		})
 		if err != nil {
 			return err
 		}
+
+		annotations := res.GetAnnotations()
+		for key, value := range internalAnnotations {
+			annotations[key] = value
+		}
+		err = res.SetAnnotations(annotations)
+		if err != nil {
+			return err
+		}
 	}
 	return nil
 }

api/builtins/PatchTransformer.go

@@ -12,6 +12,7 @@ import (
 	"sigs.k8s.io/kustomize/api/resmap"
 	"sigs.k8s.io/kustomize/api/resource"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/kio/kioutil"
 	"sigs.k8s.io/yaml"
 )
 
@@ -62,10 +63,10 @@ func (p *PatchTransformerPlugin) Config(
 	if errSM == nil {
 		p.loadedPatch = patchSM
 		if p.Options["allowNameChange"] {
-			p.loadedPatch.SetAllowNameChange("true")
+			p.loadedPatch.AllowNameChange()
 		}
 		if p.Options["allowKindChange"] {
-			p.loadedPatch.SetAllowKindChange("true")
+			p.loadedPatch.AllowKindChange()
 		}
 	} else {
 		p.decodedPatch = patchJson
@@ -76,10 +77,9 @@ func (p *PatchTransformerPlugin) Config(
 func (p *PatchTransformerPlugin) Transform(m resmap.ResMap) error {
 	if p.loadedPatch == nil {
 		return p.transformJson6902(m, p.decodedPatch)
-	} else {
-		// The patch was a strategic merge patch
-		return p.transformStrategicMerge(m, p.loadedPatch)
 	}
+	// The patch was a strategic merge patch
+	return p.transformStrategicMerge(m, p.loadedPatch)
 }
 
 // transformStrategicMerge applies the provided strategic merge patch
@@ -112,12 +112,19 @@ func (p *PatchTransformerPlugin) transformJson6902(m resmap.ResMap, patch jsonpa
 	}
 	for _, res := range resources {
 		res.StorePreviousId()
+		internalAnnotations := kioutil.GetInternalAnnotations(&res.RNode)
 		err = res.ApplyFilter(patchjson6902.Filter{
 			Patch: p.Patch,
 		})
 		if err != nil {
 			return err
 		}
+
+		annotations := res.GetAnnotations()
+		for key, value := range internalAnnotations {
+			annotations[key] = value
+		}
+		err = res.SetAnnotations(annotations)
 	}
 	return nil
 }

api/builtins/PrefixSuffixTransformer.go

@@ -7,9 +7,9 @@ import (
 	"errors"
 
 	"sigs.k8s.io/kustomize/api/filters/prefixsuffix"
-	"sigs.k8s.io/kustomize/api/resid"
 	"sigs.k8s.io/kustomize/api/resmap"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 	"sigs.k8s.io/yaml"
 )
 
@@ -73,12 +73,11 @@ func (p *PrefixSuffixTransformerPlugin) Transform(m resmap.ResMap) error {
 					r.StorePreviousId()
 				}
 			}
-			err := r.ApplyFilter(prefixsuffix.Filter{
+			if err := r.ApplyFilter(prefixsuffix.Filter{
 				Prefix:    p.Prefix,
 				Suffix:    p.Suffix,
 				FieldSpec: fs,
-			})
-			if err != nil {
+			}); err != nil {
 				return err
 			}
 		}

api/builtins/ReplacementTransformer.go

@@ -0,0 +1,59 @@
+// Code generated by pluginator on ReplacementTransformer; DO NOT EDIT.
+// pluginator {unknown  1970-01-01T00:00:00Z  }
+
+package builtins
+
+import (
+	"fmt"
+
+	"sigs.k8s.io/kustomize/api/filters/replacement"
+	"sigs.k8s.io/kustomize/api/resmap"
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/yaml"
+)
+
+// Replace values in targets with values from a source
+type ReplacementTransformerPlugin struct {
+	ReplacementList []types.ReplacementField `json:"replacements,omitempty" yaml:"replacements,omitempty"`
+	Replacements    []types.Replacement      `json:"omitempty" yaml:"omitempty"`
+}
+
+func (p *ReplacementTransformerPlugin) Config(
+	h *resmap.PluginHelpers, c []byte) (err error) {
+	p.ReplacementList = []types.ReplacementField{}
+	if err := yaml.Unmarshal(c, p); err != nil {
+		return err
+	}
+
+	for _, r := range p.ReplacementList {
+		if r.Path != "" && (r.Source != nil || len(r.Targets) != 0) {
+			return fmt.Errorf("cannot specify both path and inline replacement")
+		}
+		if r.Path != "" {
+			// load the replacement from the path
+			content, err := h.Loader().Load(r.Path)
+			if err != nil {
+				return err
+			}
+			repl := types.Replacement{}
+			if err := yaml.Unmarshal(content, &repl); err != nil {
+				return err
+			}
+			p.Replacements = append(p.Replacements, repl)
+		} else {
+			// replacement information is already loaded
+			p.Replacements = append(p.Replacements, r.Replacement)
+		}
+	}
+	return nil
+}
+
+func (p *ReplacementTransformerPlugin) Transform(m resmap.ResMap) (err error) {
+	return m.ApplyFilter(replacement.Filter{
+		Replacements: p.Replacements,
+	})
+}
+
+func NewReplacementTransformerPlugin() resmap.TransformerPlugin {
+	return &ReplacementTransformerPlugin{}
+}

api/builtins/ReplicaCountTransformer.go

@@ -7,9 +7,9 @@ import (
 	"fmt"
 
 	"sigs.k8s.io/kustomize/api/filters/replicacount"
-	"sigs.k8s.io/kustomize/api/resid"
 	"sigs.k8s.io/kustomize/api/resmap"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 	"sigs.k8s.io/yaml"
 )
 

api/filesys/filesys.go

@@ -0,0 +1,61 @@
+// Copyright 2021 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+// Package filesys provides a file system abstraction,
+// a subset of that provided by golang.org/pkg/os,
+// with an on-disk and in-memory representation.
+//
+// Deprecated: use sigs.k8s.io/kustomize/kyaml/filesys instead.
+package filesys
+
+import "sigs.k8s.io/kustomize/kyaml/filesys"
+
+const (
+	// Separator is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.Separator.
+	Separator = filesys.Separator
+	// SelfDir is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.SelfDir.
+	SelfDir = filesys.SelfDir
+	// ParentDir is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.ParentDir.
+	ParentDir = filesys.ParentDir
+)
+
+type (
+	// FileSystem is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.FileSystem.
+	FileSystem = filesys.FileSystem
+	// FileSystemOrOnDisk is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.FileSystemOrOnDisk.
+	FileSystemOrOnDisk = filesys.FileSystemOrOnDisk
+	// ConfirmedDir is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.ConfirmedDir.
+	ConfirmedDir = filesys.ConfirmedDir
+)
+
+// MakeEmptyDirInMemory is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.MakeEmptyDirInMemory.
+func MakeEmptyDirInMemory() FileSystem { return filesys.MakeEmptyDirInMemory() }
+
+// MakeFsInMemory is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.MakeFsInMemory.
+func MakeFsInMemory() FileSystem { return filesys.MakeFsInMemory() }
+
+// MakeFsOnDisk is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.MakeFsOnDisk.
+func MakeFsOnDisk() FileSystem { return filesys.MakeFsOnDisk() }
+
+// NewTmpConfirmedDir is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.NewTmpConfirmedDir.
+func NewTmpConfirmedDir() (filesys.ConfirmedDir, error) { return filesys.NewTmpConfirmedDir() }
+
+// RootedPath is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.RootedPath.
+func RootedPath(elem ...string) string { return filesys.RootedPath(elem...) }
+
+// StripTrailingSeps is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.StripTrailingSeps.
+func StripTrailingSeps(s string) string { return filesys.StripTrailingSeps(s) }
+
+// StripLeadingSeps is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.StripLeadingSeps.
+func StripLeadingSeps(s string) string { return filesys.StripLeadingSeps(s) }
+
+// PathSplit is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.PathSplit.
+func PathSplit(incoming string) []string { return filesys.PathSplit(incoming) }
+
+// PathJoin is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.PathJoin.
+func PathJoin(incoming []string) string { return filesys.PathJoin(incoming) }
+
+// InsertPathPart is deprecated, use sigs.k8s.io/kustomize/kyaml/filesys.InsertPathPart.
+func InsertPathPart(path string, pos int, part string) string {
+	return filesys.InsertPathPart(path, pos, part)
+}

api/filesys/filesystem.go

@@ -1,50 +0,0 @@
-// Copyright 2019 The Kubernetes Authors.
-// SPDX-License-Identifier: Apache-2.0
-
-// Package filesys provides a file system abstraction layer.
-package filesys
-
-import (
-	"path/filepath"
-)
-
-const (
-	Separator = string(filepath.Separator)
-	SelfDir   = "."
-	ParentDir = ".."
-)
-
-// FileSystem groups basic os filesystem methods.
-// It's supposed be functional subset of https://golang.org/pkg/os
-type FileSystem interface {
-	// Create a file.
-	Create(path string) (File, error)
-	// MkDir makes a directory.
-	Mkdir(path string) error
-	// MkDirAll makes a directory path, creating intervening directories.
-	MkdirAll(path string) error
-	// RemoveAll removes path and any children it contains.
-	RemoveAll(path string) error
-	// Open opens the named file for reading.
-	Open(path string) (File, error)
-	// IsDir returns true if the path is a directory.
-	IsDir(path string) bool
-	// CleanedAbs converts the given path into a
-	// directory and a file name, where the directory
-	// is represented as a ConfirmedDir and all that implies.
-	// If the entire path is a directory, the file component
-	// is an empty string.
-	CleanedAbs(path string) (ConfirmedDir, string, error)
-	// Exists is true if the path exists in the file system.
-	Exists(path string) bool
-	// Glob returns the list of matching files,
-	// emulating https://golang.org/pkg/path/filepath/#Glob
-	Glob(pattern string) ([]string, error)
-	// ReadFile returns the contents of the file at the given path.
-	ReadFile(path string) ([]byte, error)
-	// WriteFile writes the data to a file at the given path,
-	// overwriting anything that's already there.
-	WriteFile(path string, data []byte) error
-	// Walk walks the file system with the given WalkFunc.
-	Walk(path string, walkFn filepath.WalkFunc) error
-}

api/filters/doc.go

@@ -0,0 +1,5 @@
+package filters
+
+// Package filters collects various implementations
+// sigs.k8s.io/kustomize/kyaml/kio.Filter used by kustomize
+// transformers to modify kubernetes objects.

api/filters/fieldspec/fieldspec.go

@@ -11,6 +11,7 @@ import (
 	"sigs.k8s.io/kustomize/api/internal/utils"
 	"sigs.k8s.io/kustomize/api/types"
 	"sigs.k8s.io/kustomize/kyaml/errors"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 	"sigs.k8s.io/kustomize/kyaml/yaml"
 )
 
@@ -45,12 +46,11 @@ type Filter struct {
 
 func (fltr Filter) 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)
+	if match := isMatchGVK(fltr.FieldSpec, obj); !match {
+		return obj, nil
 	}
-	fltr.path = utils.PathSplitter(fltr.FieldSpec.Path)
-	err := fltr.filter(obj)
-	if err != nil {
+	fltr.path = utils.PathSplitter(fltr.FieldSpec.Path, "/")
+	if err := fltr.filter(obj); err != nil {
 		s, _ := obj.String()
 		return nil, errors.WrapPrefixf(err,
 			"considering field '%s' of object\n%v", fltr.FieldSpec.Path, s)
@@ -158,28 +158,24 @@ func isSequenceField(name string) (string, bool) {
 }
 
 // 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 {
+func isMatchGVK(fs types.FieldSpec, obj *yaml.RNode) bool {
+	if kind := obj.GetKind(); fs.Kind != "" && fs.Kind != kind {
 		// kind doesn't match
-		return false, err
+		return false
 	}
 
 	// parse the group and version from the apiVersion field
-	group, version := parseGV(meta.APIVersion)
+	group, version := resid.ParseGroupVersion(obj.GetApiVersion())
 
 	if fs.Group != "" && fs.Group != group {
 		// group doesn't match
-		return false, nil
+		return false
 	}
 
 	if fs.Version != "" && fs.Version != version {
 		// version doesn't match
-		return false, nil
+		return false
 	}
 
-	return true, nil
+	return true
 }

api/filters/fieldspec/fieldspec_test.go

@@ -46,10 +46,11 @@ xxx:
 		"empty path": {
 			fieldSpec: `
 group: foo
+version: v1
 kind: Bar
 `,
 			input: `
-apiVersion: foo
+apiVersion: foo/v1
 kind: Bar
 xxx:
 `,
@@ -59,7 +60,7 @@ kind: Bar
 xxx:
 `,
 			error: `considering field '' of object
-apiVersion: foo
+apiVersion: foo/v1
 kind: Bar
 xxx:
 : cannot set or create an empty field name`,
@@ -195,11 +196,14 @@ kind: Bar
 			input: `
 a:
   b: c
+`,
+			expected: `
+a:
+  b: c
 `,
 			filter: fieldspec.Filter{
 				SetValue: filtersutil.SetScalar("e"),
 			},
-			error: "missing Resource metadata",
 		},
 
 		"miss-match-type": {

api/filters/fieldspec/gvk.go

@@ -1,49 +0,0 @@
-// Copyright 2019 The Kubernetes Authors.
-// SPDX-License-Identifier: Apache-2.0
-package fieldspec
-
-import (
-	"strings"
-
-	"sigs.k8s.io/kustomize/api/resid"
-	"sigs.k8s.io/kustomize/kyaml/yaml"
-)
-
-// Return true for 'v' followed by a 1 or 2, and don't look at rest.
-// I.e. 'v1', 'v1beta1', 'v2', would return true.
-func looksLikeACoreApiVersion(s string) bool {
-	if len(s) < 2 {
-		return false
-	}
-	if s[0:1] != "v" {
-		return false
-	}
-	return s[1:2] == "1" || s[1:2] == "2"
-}
-
-// parseGV parses apiVersion field into group and version.
-func parseGV(apiVersion string) (group, version string) {
-	// parse the group and version from the apiVersion field
-	parts := strings.SplitN(apiVersion, "/", 2)
-	group = parts[0]
-	if len(parts) > 1 {
-		version = parts[1]
-	}
-	// Special case the original "apiVersion" of what
-	// we now call the "core" (empty) group.
-	if version == "" && looksLikeACoreApiVersion(group) {
-		version = group
-		group = ""
-	}
-	return
-}
-
-// GetGVK parses the metadata into a GVK
-func GetGVK(meta yaml.ResourceMeta) resid.Gvk {
-	group, version := parseGV(meta.APIVersion)
-	return resid.Gvk{
-		Group:   group,
-		Version: version,
-		Kind:    meta.Kind,
-	}
-}

api/filters/fieldspec/gvk_test.go

@@ -1,156 +0,0 @@
-// Copyright 2019 The Kubernetes Authors.
-// SPDX-License-Identifier: Apache-2.0
-package fieldspec
-
-import (
-	"strings"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"sigs.k8s.io/kustomize/api/resid"
-	"sigs.k8s.io/kustomize/kyaml/yaml"
-)
-
-func TestParseGV(t *testing.T) {
-	testCases := map[string]struct {
-		input           string
-		expectedGroup   string
-		expectedVersion string
-	}{
-		"empty": {
-			input:           "",
-			expectedGroup:   "",
-			expectedVersion: "",
-		},
-		"certSigning": {
-			input:           "certificates.k8s.io/v1beta1",
-			expectedGroup:   "certificates.k8s.io",
-			expectedVersion: "v1beta1",
-		},
-		"extensions": {
-			input:           "extensions/v1beta1",
-			expectedGroup:   "extensions",
-			expectedVersion: "v1beta1",
-		},
-		"normal": {
-			input:           "apps/v1",
-			expectedGroup:   "apps",
-			expectedVersion: "v1",
-		},
-		"justApps": {
-			input:           "apps",
-			expectedGroup:   "apps",
-			expectedVersion: "",
-		},
-		"coreV1": {
-			input:           "v1",
-			expectedGroup:   "",
-			expectedVersion: "v1",
-		},
-		"coreV2": {
-			input:           "v2",
-			expectedGroup:   "",
-			expectedVersion: "v2",
-		},
-		"coreV2Beta1": {
-			input:           "v2beta1",
-			expectedGroup:   "",
-			expectedVersion: "v2beta1",
-		},
-	}
-
-	for tn, tc := range testCases {
-		t.Run(tn, func(t *testing.T) {
-			group, version := parseGV(tc.input)
-			if !assert.Equal(t, tc.expectedGroup, group) {
-				t.FailNow()
-			}
-			if !assert.Equal(t, tc.expectedVersion, version) {
-				t.FailNow()
-			}
-		})
-	}
-}
-
-func TestGetGVK(t *testing.T) {
-	testCases := map[string]struct {
-		input      string
-		expected   resid.Gvk
-		parseError string
-		metaError  string
-	}{
-		"empty": {
-			input: `
-`,
-			parseError: "EOF",
-		},
-		"junk": {
-			input: `
-congress: effective
-`,
-			metaError: "missing Resource metadata",
-		},
-		"normal": {
-			input: `
-apiVersion: apps/v1
-kind: Deployment
-`,
-			expected: resid.Gvk{Group: "apps", Version: "v1", Kind: "Deployment"},
-		},
-		"apiVersionOnlyWithSlash": {
-			input: `
-apiVersion: apps/v1
-`,
-			expected: resid.Gvk{Group: "apps", Version: "v1", Kind: ""},
-		},
-		"apiVersionOnlyNoSlash1": {
-			input: `
-apiVersion: apps
-`,
-			expected: resid.Gvk{Group: "apps", Version: "", Kind: ""},
-		},
-		"apiVersionOnlyNoSlash2": {
-			input: `
-apiVersion: v1
-`,
-			expected: resid.Gvk{Group: "", Version: "v1", Kind: ""},
-		},
-	}
-
-	for tn, tc := range testCases {
-		t.Run(tn, func(t *testing.T) {
-			obj, err := yaml.Parse(tc.input)
-			if len(tc.parseError) != 0 {
-				if err == nil {
-					t.Error("expected parse error")
-					return
-				}
-				if !strings.Contains(err.Error(), tc.parseError) {
-					t.Errorf("expected parse err '%s', got '%v'", tc.parseError, err)
-				}
-				return
-			}
-			if !assert.NoError(t, err) {
-				t.FailNow()
-			}
-			meta, err := obj.GetMeta()
-			if len(tc.metaError) != 0 {
-				if err == nil {
-					t.Error("expected meta error")
-					return
-				}
-				if !strings.Contains(err.Error(), tc.metaError) {
-					t.Errorf("expected meta err '%s', got '%v'", tc.metaError, err)
-				}
-				return
-			}
-			if !assert.NoError(t, err) {
-				t.FailNow()
-			}
-			gvk := GetGVK(meta)
-			if !assert.Equal(t, tc.expected, gvk) {
-				t.FailNow()
-			}
-		})
-	}
-}

api/filters/iampolicygenerator/doc.go

@@ -0,0 +1,3 @@
+// Package gkesagenerator contains a kio.Filter that that generates a
+// iampolicy-related resources for a given cloud provider
+package iampolicygenerator

api/filters/iampolicygenerator/example_test.go

@@ -0,0 +1,46 @@
+// Copyright 2021 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package iampolicygenerator
+
+import (
+	"log"
+	"os"
+
+	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+func ExampleFilter() {
+	f := Filter{}
+	var err = yaml.Unmarshal([]byte(`
+cloud: gke
+kubernetesService: 
+  namespace: k8s-namespace
+  name: k8s-sa-name
+serviceAccount:
+  name: gsa-name
+  projectId: project-id
+`), &f)
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	err = kio.Pipeline{
+		Inputs:  []kio.Reader{},
+		Filters: []kio.Filter{f},
+		Outputs: []kio.Writer{kio.ByteWriter{Writer: os.Stdout}},
+	}.Execute()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	// Output:
+	// apiVersion: v1
+	// kind: ServiceAccount
+	// metadata:
+	//   annotations:
+	//     iam.gke.io/gcp-service-account: gsa-name@project-id.iam.gserviceaccount.com
+	//   name: k8s-sa-name
+	//   namespace: k8s-namespace
+}

api/filters/iampolicygenerator/iampolicygenerator.go

@@ -0,0 +1,55 @@
+// Copyright 2021 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package iampolicygenerator
+
+import (
+	"fmt"
+
+	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/yaml"
+)
+
+type Filter struct {
+	IAMPolicyGenerator types.IAMPolicyGeneratorArgs `json:",inline,omitempty" yaml:",inline,omitempty"`
+}
+
+// Filter adds a GKE service account object to nodes
+func (f Filter) Filter(nodes []*yaml.RNode) ([]*yaml.RNode, error) {
+	switch f.IAMPolicyGenerator.Cloud {
+	case types.GKE:
+		IAMPolicyResources, err := f.generateGkeIAMPolicyResources()
+		if err != nil {
+			return nil, err
+		}
+		nodes = append(nodes, IAMPolicyResources...)
+	default:
+		return nil, fmt.Errorf("cloud provider %s not supported yet", f.IAMPolicyGenerator.Cloud)
+	}
+	return nodes, nil
+}
+
+func (f Filter) generateGkeIAMPolicyResources() ([]*yaml.RNode, error) {
+	var result []*yaml.RNode
+	input := fmt.Sprintf(`
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  annotations:
+    iam.gke.io/gcp-service-account: %s@%s.iam.gserviceaccount.com
+  name: %s
+`, f.IAMPolicyGenerator.ServiceAccount.Name,
+		f.IAMPolicyGenerator.ProjectId,
+		f.IAMPolicyGenerator.KubernetesService.Name)
+
+	if f.IAMPolicyGenerator.Namespace != "" {
+		input = input + fmt.Sprintf("\n  namespace: %s", f.IAMPolicyGenerator.Namespace)
+	}
+
+	sa, err := yaml.Parse(input)
+	if err != nil {
+		return nil, err
+	}
+
+	return append(result, sa), nil
+}

api/filters/iampolicygenerator/iampolicygenerator_test.go

@@ -0,0 +1,75 @@
+// Copyright 2021 The Kubernetes Authors.
+// SPDX-License-Identifier: Apache-2.0
+
+package iampolicygenerator
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	filtertest "sigs.k8s.io/kustomize/api/testutils/filtertest"
+	"sigs.k8s.io/kustomize/api/types"
+)
+
+func TestFilter(t *testing.T) {
+	testCases := map[string]struct {
+		args     types.IAMPolicyGeneratorArgs
+		expected string
+	}{
+		"with namespace": {
+			args: types.IAMPolicyGeneratorArgs{
+				Cloud: types.GKE,
+				KubernetesService: types.KubernetesService{
+					Namespace: "k8s-namespace",
+					Name:      "k8s-sa-name",
+				},
+				ServiceAccount: types.ServiceAccount{
+					Name:      "gsa-name",
+					ProjectId: "project-id",
+				},
+			},
+			expected: `
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  annotations:
+    iam.gke.io/gcp-service-account: gsa-name@project-id.iam.gserviceaccount.com
+  name: k8s-sa-name
+  namespace: k8s-namespace
+`,
+		},
+		"without namespace": {
+			args: types.IAMPolicyGeneratorArgs{
+				Cloud: types.GKE,
+				KubernetesService: types.KubernetesService{
+					Name: "k8s-sa-name",
+				},
+				ServiceAccount: types.ServiceAccount{
+					Name:      "gsa-name",
+					ProjectId: "project-id",
+				},
+			},
+			expected: `
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  annotations:
+    iam.gke.io/gcp-service-account: gsa-name@project-id.iam.gserviceaccount.com
+  name: k8s-sa-name
+`,
+		},
+	}
+
+	for tn, tc := range testCases {
+		t.Run(tn, func(t *testing.T) {
+			f := Filter{
+				IAMPolicyGenerator: tc.args,
+			}
+			actual := filtertest.RunFilter(t, "", f)
+			if !assert.Equal(t, strings.TrimSpace(tc.expected), strings.TrimSpace(actual)) {
+				t.FailNow()
+			}
+		})
+	}
+}

api/filters/imagetag/legacy.go

@@ -4,6 +4,7 @@
 package imagetag
 
 import (
+	"sigs.k8s.io/kustomize/api/internal/utils"
 	"sigs.k8s.io/kustomize/api/types"
 	"sigs.k8s.io/kustomize/kyaml/kio"
 	"sigs.k8s.io/kustomize/kyaml/yaml"
@@ -74,7 +75,7 @@ func (f findFieldsFilter) walk(node *yaml.RNode) error {
 				return err
 			}
 			key := n.Key.YNode().Value
-			if contains(f.fields, key) {
+			if utils.StringSliceContains(f.fields, key) {
 				return f.fieldCallback(n.Value)
 			}
 			return nil
@@ -87,15 +88,6 @@ func (f findFieldsFilter) walk(node *yaml.RNode) error {
 	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 {

api/filters/labels/labels_test.go

@@ -8,9 +8,9 @@ import (
 	"testing"
 
 	"github.com/stretchr/testify/assert"
-	"sigs.k8s.io/kustomize/api/resid"
 	filtertest_test "sigs.k8s.io/kustomize/api/testutils/filtertest"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 )
 
 func TestLabels_Filter(t *testing.T) {

api/filters/nameref/nameref.go

@@ -6,11 +6,11 @@ import (
 
 	"github.com/pkg/errors"
 	"sigs.k8s.io/kustomize/api/filters/fieldspec"
-	"sigs.k8s.io/kustomize/api/resid"
 	"sigs.k8s.io/kustomize/api/resmap"
 	"sigs.k8s.io/kustomize/api/resource"
 	"sigs.k8s.io/kustomize/api/types"
 	"sigs.k8s.io/kustomize/kyaml/kio"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 	"sigs.k8s.io/kustomize/kyaml/yaml"
 )
 
@@ -56,6 +56,7 @@ func (f Filter) run(node *yaml.RNode) (*yaml.RNode, error) {
 		// sanity check.
 		return nil, err
 	}
+	f.NameFieldToUpdate.Gvk = f.Referrer.GetGvk()
 	if err := node.PipeE(fieldspec.Filter{
 		FieldSpec: f.NameFieldToUpdate,
 		SetValue:  f.set,
@@ -184,7 +185,7 @@ func (f Filter) recordTheReferral(referral *resource.Resource) {
 
 // getRoleRefGvk returns a Gvk in the roleRef field. Return error
 // if the roleRef, roleRef/apiGroup or roleRef/kind is missing.
-func getRoleRefGvk(n *yaml.RNode) (*resid.Gvk, error) {
+func getRoleRefGvk(n *resource.Resource) (*resid.Gvk, error) {
 	roleRef, err := n.Pipe(yaml.Lookup("roleRef"))
 	if err != nil {
 		return nil, err
@@ -257,8 +258,7 @@ func previousIdSelectedByGvk(gvk *resid.Gvk) sieveFunc {
 
 // If the we are updating a 'roleRef/name' field, the 'apiGroup' and 'kind'
 // fields in the same 'roleRef' map must be considered.
-// If either object is cluster-scoped (!IsNamespaceableKind), there
-// can be a referral.
+// If either object is cluster-scoped, there can be a referral.
 // E.g. a RoleBinding (which exists in a namespace) can refer
 // to a ClusterRole (cluster-scoped) object.
 // https://kubernetes.io/docs/reference/access-authn-authz/rbac/#role-and-clusterrole
@@ -270,7 +270,7 @@ func (f Filter) roleRefFilter() sieveFunc {
 	if !strings.HasSuffix(f.NameFieldToUpdate.Path, "roleRef/name") {
 		return acceptAll
 	}
-	roleRefGvk, err := getRoleRefGvk(f.Referrer.AsRNode())
+	roleRefGvk, err := getRoleRefGvk(f.Referrer)
 	if err != nil {
 		return acceptAll
 	}
@@ -285,12 +285,12 @@ func prefixSuffixEquals(other resource.ResCtx) sieveFunc {
 
 func (f Filter) sameCurrentNamespaceAsReferrer() sieveFunc {
 	referrerCurId := f.Referrer.CurId()
-	if !referrerCurId.IsNamespaceableKind() {
+	if referrerCurId.IsClusterScoped() {
 		// If the referrer is cluster-scoped, let anything through.
 		return acceptAll
 	}
 	return func(r *resource.Resource) bool {
-		if !r.CurId().IsNamespaceableKind() {
+		if r.CurId().IsClusterScoped() {
 			// Allow cluster-scoped through.
 			return true
 		}

api/filters/nameref/nameref_test.go

@@ -6,10 +6,10 @@ import (
 
 	"github.com/stretchr/testify/assert"
 	"sigs.k8s.io/kustomize/api/provider"
-	"sigs.k8s.io/kustomize/api/resid"
 	"sigs.k8s.io/kustomize/api/resmap"
 	filtertest_test "sigs.k8s.io/kustomize/api/testutils/filtertest"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 )
 
 func TestNamerefFilter(t *testing.T) {

api/filters/namespace/namespace.go

@@ -4,11 +4,11 @@
 package namespace
 
 import (
-	"sigs.k8s.io/kustomize/api/filters/fieldspec"
 	"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/resid"
 	"sigs.k8s.io/kustomize/kyaml/yaml"
 )
 
@@ -54,16 +54,11 @@ func (ns Filter) run(node *yaml.RNode) (*yaml.RNode, error) {
 // 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 {
+	gvk := resid.GvkFromNode(obj)
+	if err := ns.metaNamespaceHack(obj, gvk); err != nil {
 		return err
 	}
-
-	if err := ns.metaNamespaceHack(obj, meta); err != nil {
-		return err
-	}
-
-	return ns.roleBindingHack(obj, meta)
+	return ns.roleBindingHack(obj, gvk)
 }
 
 // metaNamespaceHack is a hack for implementing the namespace transform
@@ -74,9 +69,8 @@ func (ns Filter) hacks(obj *yaml.RNode) error {
 // 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 := fieldspec.GetGVK(meta)
-	if !gvk.IsNamespaceableKind() {
+func (ns Filter) metaNamespaceHack(obj *yaml.RNode, gvk resid.Gvk) error {
+	if gvk.IsClusterScoped() {
 		return nil
 	}
 	f := fsslice.Filter{
@@ -104,8 +98,8 @@ func (ns Filter) metaNamespaceHack(obj *yaml.RNode, meta yaml.ResourceMeta) erro
 //   ...
 // - 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 {
+func (ns Filter) roleBindingHack(obj *yaml.RNode, gvk resid.Gvk) error {
+	if gvk.Kind != roleBindingKind && gvk.Kind != clusterRoleBindingKind {
 		return nil
 	}
 

api/filters/refvar/refvar_test.go

@@ -250,6 +250,7 @@ metadata:
   name: dep
   annotations:
     config.kubernetes.io/index: '0'
+    internal.config.kubernetes.io/index: '0'
 data:
   slice:
   - false
@@ -276,6 +277,7 @@ metadata:
   name: dep
   annotations:
     config.kubernetes.io/index: '0'
+    internal.config.kubernetes.io/index: '0'
 data:
   1: str
 : invalid map key: value='1', tag='` + yaml.NodeTagInt + `'`,

api/filters/replacement/replacement.go

@@ -7,13 +7,15 @@ import (
 	"fmt"
 	"strings"
 
-	"sigs.k8s.io/kustomize/api/resid"
+	"sigs.k8s.io/kustomize/api/internal/utils"
+	"sigs.k8s.io/kustomize/api/resource"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 	"sigs.k8s.io/kustomize/kyaml/yaml"
 )
 
 type Filter struct {
-	Replacements []types.Replacement
+	Replacements []types.Replacement `json:"replacements,omitempty" yaml:"replacements,omitempty"`
 }
 
 // Filter replaces values of targets with values from sources
@@ -43,11 +45,28 @@ func applyReplacement(nodes []*yaml.RNode, value *yaml.RNode, targets []*types.T
 			t.FieldPaths = []string{types.DefaultReplacementFieldPath}
 		}
 		for _, n := range nodes {
-			nodeId := getKrmId(n)
-			if t.Select.KrmId.Match(nodeId) && !rejectId(t.Reject, nodeId) {
-				err := applyToNode(n, value, t)
-				if err != nil {
-					return nil, err
+			ids, err := utils.MakeResIds(n)
+			if err != nil {
+				return nil, err
+			}
+
+			// filter targets by label and annotation selectors
+			selectByAnnoAndLabel, err := selectByAnnoAndLabel(n, t)
+			if err != nil {
+				return nil, err
+			}
+			if !selectByAnnoAndLabel {
+				continue
+			}
+
+			// filter targets by matching resource IDs
+			for _, id := range ids {
+				if id.IsSelectedBy(t.Select.ResId) && !rejectId(t.Reject, &id) {
+					err := applyToNode(n, value, t)
+					if err != nil {
+						return nil, err
+					}
+					break
 				}
 			}
 		}
@@ -55,9 +74,37 @@ func applyReplacement(nodes []*yaml.RNode, value *yaml.RNode, targets []*types.T
 	return nodes, nil
 }
 
-func rejectId(rejects []*types.Selector, nodeId *types.KrmId) bool {
+func selectByAnnoAndLabel(n *yaml.RNode, t *types.TargetSelector) (bool, error) {
+	if matchesSelect, err := matchesAnnoAndLabelSelector(n, t.Select); !matchesSelect || err != nil {
+		return false, err
+	}
+	for _, reject := range t.Reject {
+		if reject.AnnotationSelector == "" && reject.LabelSelector == "" {
+			continue
+		}
+		if m, err := matchesAnnoAndLabelSelector(n, reject); m || err != nil {
+			return false, err
+		}
+	}
+	return true, nil
+}
+
+func matchesAnnoAndLabelSelector(n *yaml.RNode, selector *types.Selector) (bool, error) {
+	r := resource.Resource{RNode: *n}
+	annoMatch, err := r.MatchesAnnotationSelector(selector.AnnotationSelector)
+	if err != nil {
+		return false, err
+	}
+	labelMatch, err := r.MatchesLabelSelector(selector.LabelSelector)
+	if err != nil {
+		return false, err
+	}
+	return annoMatch && labelMatch, nil
+}
+
+func rejectId(rejects []*types.Selector, id *resid.ResId) bool {
 	for _, r := range rejects {
-		if r.KrmId.Match(nodeId) {
+		if !r.ResId.IsEmpty() && id.IsSelectedBy(r.ResId) {
 			return true
 		}
 	}
@@ -66,7 +113,7 @@ func rejectId(rejects []*types.Selector, nodeId *types.KrmId) bool {
 
 func applyToNode(node *yaml.RNode, value *yaml.RNode, target *types.TargetSelector) error {
 	for _, fp := range target.FieldPaths {
-		fieldPath := strings.Split(fp, ".")
+		fieldPath := utils.SmarterPathSplitter(fp, ".")
 		var t *yaml.RNode
 		var err error
 		if target.Options != nil && target.Options.Create {
@@ -87,12 +134,11 @@ func applyToNode(node *yaml.RNode, value *yaml.RNode, target *types.TargetSelect
 }
 
 func setTargetValue(options *types.FieldOptions, t *yaml.RNode, value *yaml.RNode) error {
+	value = value.Copy()
 	if options != nil && options.Delimiter != "" {
-
 		if t.YNode().Kind != yaml.ScalarNode {
 			return fmt.Errorf("delimiter option can only be used with scalar nodes")
 		}
-
 		tv := strings.Split(t.YNode().Value, options.Delimiter)
 		v := yaml.GetValue(value)
 		// TODO: Add a way to remove an element
@@ -119,16 +165,17 @@ func getReplacement(nodes []*yaml.RNode, r *types.Replacement) (*yaml.RNode, err
 	if r.Source.FieldPath == "" {
 		r.Source.FieldPath = types.DefaultReplacementFieldPath
 	}
-	fieldPath := strings.Split(r.Source.FieldPath, ".")
+	fieldPath := utils.SmarterPathSplitter(r.Source.FieldPath, ".")
 
 	rn, err := source.Pipe(yaml.Lookup(fieldPath...))
 	if err != nil {
 		return nil, err
 	}
-	if !rn.IsNilOrEmpty() {
-		return getRefinedValue(r.Source.Options, rn)
+	if rn.IsNilOrEmpty() {
+		return nil, fmt.Errorf("fieldPath `%s` is missing for replacement source %s", r.Source.FieldPath, r.Source)
 	}
-	return rn, nil
+
+	return getRefinedValue(r.Source.Options, rn)
 }
 
 func getRefinedValue(options *types.FieldOptions, rn *yaml.RNode) (*yaml.RNode, error) {
@@ -152,34 +199,23 @@ func getRefinedValue(options *types.FieldOptions, rn *yaml.RNode) (*yaml.RNode,
 func selectSourceNode(nodes []*yaml.RNode, selector *types.SourceSelector) (*yaml.RNode, error) {
 	var matches []*yaml.RNode
 	for _, n := range nodes {
-		if selector.KrmId.Match(getKrmId(n)) {
-			if len(matches) > 0 {
-				return nil, fmt.Errorf("more than one match for source %v", selector)
+		ids, err := utils.MakeResIds(n)
+		if err != nil {
+			return nil, err
+		}
+		for _, id := range ids {
+			if id.IsSelectedBy(selector.ResId) {
+				if len(matches) > 0 {
+					return nil, fmt.Errorf(
+						"multiple matches for selector %s", selector)
+				}
+				matches = append(matches, n)
+				break
 			}
-			matches = append(matches, n)
 		}
 	}
 	if len(matches) == 0 {
-		return nil, fmt.Errorf("found no matches for source %v", selector)
+		return nil, fmt.Errorf("nothing selected by %s", selector)
 	}
 	return matches[0], nil
 }
-
-func getKrmId(n *yaml.RNode) *types.KrmId {
-	ns, err := n.GetNamespace()
-	if err != nil {
-		// Resource has no metadata (no apiVersion, kind, nor metadata field).
-		// In this case, it cannot be selected.
-		return &types.KrmId{}
-	}
-	apiVersion := n.Field(yaml.APIVersionField)
-	var group, version string
-	if apiVersion != nil {
-		group, version = resid.ParseGroupVersion(yaml.GetValue(apiVersion.Value))
-	}
-	return &types.KrmId{
-		Gvk:       resid.Gvk{Group: group, Version: version, Kind: n.GetKind()},
-		Name:      n.GetName(),
-		Namespace: ns,
-	}
-}

api/filters/replacement/replacement_test.go

@@ -269,7 +269,7 @@ spec:
   - select:
       kind: Deployment
 `,
-			expectedErr: "more than one match for source ~G_~V_Deployment",
+			expectedErr: "multiple matches for selector ~G_~V_Deployment|~X|~N",
 		},
 		"replacement has no source": {
 			input: `apiVersion: v1
@@ -1338,6 +1338,480 @@ spec:
 `,
 			expectedErr: "delimiter option can only be used with scalar nodes",
 		},
+		"mapping value contains '.' character": {
+			input: `apiVersion: v1
+kind: Custom
+metadata:
+  name: custom
+  annotations:
+    a.b.c/d-e: source
+    f.g.h/i-j: target
+`,
+			replacements: `replacements:
+- source:
+    name: custom
+    fieldPath: metadata.annotations.[a.b.c/d-e]
+  targets:
+  - select:
+      name: custom
+    fieldPaths: 
+    - metadata.annotations.[f.g.h/i-j]
+`,
+			expected: `apiVersion: v1
+kind: Custom
+metadata:
+  name: custom
+  annotations:
+    a.b.c/d-e: source
+    f.g.h/i-j: source
+`,
+		},
+		"list index contains '.' character": {
+			input: `apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: source
+data:
+  value: example
+---
+apiVersion: kubernetes-client.io/v1
+kind: ExternalSecret
+metadata:
+  name: some-secret
+spec:
+  backendType: secretsManager
+  data:
+    - key: some-prefix-replaceme
+      name: .first
+      version: latest
+      property: first
+    - key: some-prefix-replaceme
+      name: second
+      version: latest
+      property: second
+`,
+			replacements: `replacements:
+- source:
+    kind: ConfigMap
+    version: v1
+    name: source
+    fieldPath: data.value
+  targets:
+  - select:
+      group: kubernetes-client.io
+      version: v1
+      kind: ExternalSecret
+      name: some-secret
+    fieldPaths:
+    - spec.data.[name=.first].key
+    - spec.data.[name=second].key
+    options:
+      delimiter: "-"
+      index: 2
+`,
+			expected: `apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: source
+data:
+  value: example
+---
+apiVersion: kubernetes-client.io/v1
+kind: ExternalSecret
+metadata:
+  name: some-secret
+spec:
+  backendType: secretsManager
+  data:
+  - key: some-prefix-example
+    name: .first
+    version: latest
+    property: first
+  - key: some-prefix-example
+    name: second
+    version: latest
+    property: second`,
+		},
+		"multiple field paths in target": {
+			input: `apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: source
+data:
+  value: example
+---
+apiVersion: kubernetes-client.io/v1
+kind: ExternalSecret
+metadata:
+  name: some-secret
+spec:
+  backendType: secretsManager
+  data:
+    - key: some-prefix-replaceme
+      name: first
+      version: latest
+      property: first
+    - key: some-prefix-replaceme
+      name: second
+      version: latest
+      property: second
+    - key: some-prefix-replaceme
+      name: third
+      version: latest
+      property: third
+`,
+			replacements: `replacements:
+- source:
+    kind: ConfigMap
+    version: v1
+    name: source
+    fieldPath: data.value
+  targets:
+  - select:
+      group: kubernetes-client.io
+      version: v1
+      kind: ExternalSecret
+      name: some-secret
+    fieldPaths:
+    - spec.data.0.key
+    - spec.data.1.key
+    - spec.data.2.key
+    options:
+      delimiter: "-"
+      index: 2
+`,
+			expected: `apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: source
+data:
+  value: example
+---
+apiVersion: kubernetes-client.io/v1
+kind: ExternalSecret
+metadata:
+  name: some-secret
+spec:
+  backendType: secretsManager
+  data:
+  - key: some-prefix-example
+    name: first
+    version: latest
+    property: first
+  - key: some-prefix-example
+    name: second
+    version: latest
+    property: second
+  - key: some-prefix-example
+    name: third
+    version: latest
+    property: third
+`,
+		},
+		"using a previous ID": {
+			input: `apiVersion: v1
+kind: Deployment
+metadata:
+  name: pre-deploy
+  annotations: 
+    internal.config.kubernetes.io/previousNames: deploy,deploy
+    internal.config.kubernetes.io/previousKinds: CronJob,Deployment
+    internal.config.kubernetes.io/previousNamespaces: default,default
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: postgres:1.8.0
+        name: postgresdb
+`,
+			replacements: `replacements:
+- source:
+    kind: CronJob
+    name: deploy
+    fieldPath: spec.template.spec.containers.0.image
+  targets:
+  - select:
+      kind: Deployment
+      name: deploy
+    fieldPaths: 
+    - spec.template.spec.containers.1.image
+`,
+			expected: `apiVersion: v1
+kind: Deployment
+metadata:
+  name: pre-deploy
+  annotations:
+    internal.config.kubernetes.io/previousNames: deploy,deploy
+    internal.config.kubernetes.io/previousKinds: CronJob,Deployment
+    internal.config.kubernetes.io/previousNamespaces: default,default
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: nginx:1.7.9
+        name: postgresdb
+`,
+		},
+
+		"replacement source.fieldPath does not exist": {
+			input: `apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: ports-from
+data:
+  grpcPort: 8080
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: ports-to
+data:
+  grpcPort: 8081
+`,
+			replacements: `replacements:
+- source:
+    kind: ConfigMap
+    name: ports-from
+    fieldPath: data.httpPort
+  targets:
+  - select:
+      kind: ConfigMap
+      name: ports-to
+    fieldPaths:
+    - data.grpcPort
+    options:
+      create: true
+`,
+			expectedErr: "fieldPath `data.httpPort` is missing for replacement source ~G_~V_ConfigMap|~X|ports-from:data.httpPort",
+		},
+		"annotationSelector": {
+			input: `apiVersion: v1
+kind: Deployment
+metadata:
+  name: deploy-1
+  annotations:
+    foo: bar-1
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: postgres:1.8.0
+        name: postgresdb
+---
+apiVersion: v1
+kind: Deployment
+metadata:
+  name: deploy-2
+  annotations:
+    foo: bar-2
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: postgres:1.8.0
+        name: postgresdb
+
+`,
+			replacements: `replacements:
+- source:
+    kind: Deployment
+    name: deploy-1
+    fieldPath: spec.template.spec.containers.0.image
+  targets:
+  - select:
+      annotationSelector: foo=bar-1
+    fieldPaths: 
+    - spec.template.spec.containers.1.image
+`,
+			expected: `apiVersion: v1
+kind: Deployment
+metadata:
+  name: deploy-1
+  annotations:
+    foo: bar-1
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: nginx:1.7.9
+        name: postgresdb
+---
+apiVersion: v1
+kind: Deployment
+metadata:
+  name: deploy-2
+  annotations:
+    foo: bar-2
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: postgres:1.8.0
+        name: postgresdb
+`,
+		},
+		"labelSelector": {
+			input: `apiVersion: v1
+kind: Deployment
+metadata:
+  name: deploy-1
+  labels:
+    foo: bar-1
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: postgres:1.8.0
+        name: postgresdb
+---
+apiVersion: v1
+kind: Deployment
+metadata:
+  name: deploy-2
+  labels:
+    foo: bar-2
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: postgres:1.8.0
+        name: postgresdb
+
+`,
+			replacements: `replacements:
+- source:
+    kind: Deployment
+    name: deploy-1
+    fieldPath: spec.template.spec.containers.0.image
+  targets:
+  - select:
+      labelSelector: foo=bar-1
+    fieldPaths: 
+    - spec.template.spec.containers.1.image
+`,
+			expected: `apiVersion: v1
+kind: Deployment
+metadata:
+  name: deploy-1
+  labels:
+    foo: bar-1
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: nginx:1.7.9
+        name: postgresdb
+---
+apiVersion: v1
+kind: Deployment
+metadata:
+  name: deploy-2
+  labels:
+    foo: bar-2
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: postgres:1.8.0
+        name: postgresdb
+`,
+		},
+		"reject via labelSelector": {
+			input: `apiVersion: v1
+kind: Deployment
+metadata:
+  name: deploy-1
+  labels:
+    foo: bar-1
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: postgres:1.8.0
+        name: postgresdb
+---
+apiVersion: v1
+kind: Deployment
+metadata:
+  name: deploy-2
+  labels:
+    foo: bar-2
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: postgres:1.8.0
+        name: postgresdb
+
+`,
+			replacements: `replacements:
+- source:
+    kind: Deployment
+    name: deploy-1
+    fieldPath: spec.template.spec.containers.0.image
+  targets:
+  - select:
+      kind: Deployment
+    reject:
+    - labelSelector: foo=bar-2
+    fieldPaths: 
+    - spec.template.spec.containers.1.image
+`,
+			expected: `apiVersion: v1
+kind: Deployment
+metadata:
+  name: deploy-1
+  labels:
+    foo: bar-1
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: nginx:1.7.9
+        name: postgresdb
+---
+apiVersion: v1
+kind: Deployment
+metadata:
+  name: deploy-2
+  labels:
+    foo: bar-2
+spec:
+  template:
+    spec:
+      containers:
+      - image: nginx:1.7.9
+        name: nginx-tagged
+      - image: postgres:1.8.0
+        name: postgresdb
+`,
+		},
 	}
 
 	for tn, tc := range testCases {
@@ -1353,7 +1827,7 @@ spec:
 					t.Errorf("unexpected error: %s\n", err.Error())
 					t.FailNow()
 				}
-				if !assert.Equal(t, tc.expectedErr, err.Error()) {
+				if !assert.Contains(t, err.Error(), tc.expectedErr) {
 					t.FailNow()
 				}
 			}

api/filters/valueadd/valueadd.go

@@ -6,7 +6,7 @@ package valueadd
 import (
 	"strings"
 
-	"sigs.k8s.io/kustomize/api/filesys"
+	"sigs.k8s.io/kustomize/kyaml/filesys"
 	"sigs.k8s.io/kustomize/kyaml/kio"
 	"sigs.k8s.io/kustomize/kyaml/yaml"
 )

api/go.mod

@@ -3,14 +3,14 @@ module sigs.k8s.io/kustomize/api
 go 1.16
 
 require (
-	github.com/evanphx/json-patch v4.5.0+incompatible
+	github.com/evanphx/json-patch v4.11.0+incompatible
 	github.com/go-errors/errors v1.0.1
-	github.com/go-openapi/spec v0.19.5
 	github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510
 	github.com/imdario/mergo v0.3.5
 	github.com/pkg/errors v0.9.1
-	github.com/stretchr/testify v1.4.0
+	github.com/stretchr/testify v1.5.1
 	gopkg.in/yaml.v2 v2.4.0
-	sigs.k8s.io/kustomize/kyaml v0.10.17
+	k8s.io/kube-openapi v0.0.0-20210421082810-95288971da7e
+	sigs.k8s.io/kustomize/kyaml v0.13.0
 	sigs.k8s.io/yaml v1.2.0
 )

api/go.sum

@@ -1,17 +1,14 @@
 cloud.google.com/go v0.26.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw=
 github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
+github.com/NYTimes/gziphandler v0.0.0-20170623195520-56545f4a5d46/go.mod h1:3wb06e3pkSAbeQ52E9H9iFoQsEEwGN64994WTCIhntQ=
 github.com/OneOfOne/xxhash v1.2.2/go.mod h1:HSdplMjZKSmBqAxg5vPj2TmRDmfkzw+cTzAElWljhcU=
-github.com/PuerkitoBio/purell v1.1.0/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=
 github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578 h1:d+Bc7a5rLufV/sSk/8dngufqelfh6jnri85riMAaF/M=
 github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578/go.mod h1:uGdkoq3SwY9Y+13GIhn11/XLaGBb4BfwItxLd5jeuXE=
-github.com/agnivade/levenshtein v1.0.1/go.mod h1:CURSv5d9Uaml+FovSIICkLbAUZ9S4RqaHDIsdSBg7lM=
 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/andreyvit/diff v0.0.0-20170406064948-c7f18ee00883/go.mod h1:rCTlJbsFo29Kk6CurOXKm700vrz8f0KW0JNfpkRJY/8=
 github.com/armon/consul-api v0.0.0-20180202201655-eb2c6b5be1b6/go.mod h1:grANhF5doyWs3UAsr3K4I6qtAmlQcZDesFNEHPZAzj8=
-github.com/asaskevich/govalidator v0.0.0-20180720115003-f9ffefc3facf/go.mod h1:lB+ZfQJz7igIIfQNfa7Ml4HSf2uFQQRzpGGRXenZAgY=
 github.com/asaskevich/govalidator v0.0.0-20190424111038-f61b66f89f4a/go.mod h1:lB+ZfQJz7igIIfQNfa7Ml4HSf2uFQQRzpGGRXenZAgY=
 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=
@@ -31,66 +28,25 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 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/go-units v0.3.3/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk=
-github.com/docker/go-units v0.4.0/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk=
-github.com/evanphx/json-patch v4.5.0+incompatible h1:ouOWdg56aJriqS0huScTkVXPC5IcNrDCXZ6OoTAWu7M=
-github.com/evanphx/json-patch v4.5.0+incompatible/go.mod h1:50XU6AFN0ol/bzJsmQLiYLvXMP4fmwYFNcr97nuDLSk=
+github.com/docopt/docopt-go v0.0.0-20180111231733-ee0de3bc6815/go.mod h1:WwZ+bS3ebgob9U8Nd0kOddGdZWjyMGR8Wziv+TBNwSE=
+github.com/emicklei/go-restful v0.0.0-20170410110728-ff4f55a20633/go.mod h1:otzb+WCGbkyDHkqmQmT5YD2WR4BBwUdeQoFo8l/7tVs=
+github.com/evanphx/json-patch v4.11.0+incompatible h1:glyUF9yIYtMHzn8xaKw5rMhdWcwsYV8dZHIq5567/xs=
+github.com/evanphx/json-patch v4.11.0+incompatible/go.mod h1:50XU6AFN0ol/bzJsmQLiYLvXMP4fmwYFNcr97nuDLSk=
 github.com/fsnotify/fsnotify v1.4.7/go.mod h1:jwhsz4b93w/PPRr/qN1Yymfu8t87LnFCMoQvtojpjFo=
 github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
-github.com/globalsign/mgo v0.0.0-20180905125535-1ca0a4f7cbcb/go.mod h1:xkRDCp4j0OGD1HRkm4kmhM+pmpv3AKq5SU7GMg4oO/Q=
-github.com/globalsign/mgo v0.0.0-20181015135952-eeefdecb41b8/go.mod h1:xkRDCp4j0OGD1HRkm4kmhM+pmpv3AKq5SU7GMg4oO/Q=
 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-logfmt/logfmt v0.3.0/go.mod h1:Qt1PoO58o5twSAckw1HlFXLmHsOX5/0LbT9GBnD5lWE=
 github.com/go-logfmt/logfmt v0.4.0/go.mod h1:3RMwSq7FuexP4Kalkev3ejPJsZTpXXBr9+V4qmtdjCk=
-github.com/go-openapi/analysis v0.0.0-20180825180245-b006789cd277/go.mod h1:k70tL6pCuVxPJOHXQ+wIac1FUrvNkHolPie/cLEU6hI=
-github.com/go-openapi/analysis v0.17.0/go.mod h1:IowGgpVeD0vNm45So8nr+IcQ3pxVtpRoBWb8PVZO0ik=
-github.com/go-openapi/analysis v0.18.0/go.mod h1:IowGgpVeD0vNm45So8nr+IcQ3pxVtpRoBWb8PVZO0ik=
-github.com/go-openapi/analysis v0.19.2/go.mod h1:3P1osvZa9jKjb8ed2TPng3f0i/UY9snX6gxi44djMjk=
-github.com/go-openapi/analysis v0.19.5/go.mod h1:hkEAkxagaIvIP7VTn8ygJNkd4kAYON2rCu0v0ObL0AU=
-github.com/go-openapi/errors v0.17.0/go.mod h1:LcZQpmvG4wyF5j4IhA73wkLFQg+QJXOQHVjmcZxhka0=
-github.com/go-openapi/errors v0.18.0/go.mod h1:LcZQpmvG4wyF5j4IhA73wkLFQg+QJXOQHVjmcZxhka0=
-github.com/go-openapi/errors v0.19.2/go.mod h1:qX0BLWsyaKfvhluLejVpVNwNRdXZhEbTA4kxxpKBC94=
-github.com/go-openapi/jsonpointer v0.17.0/go.mod h1:cOnomiV+CVVwFLk0A/MExoFMjwdsUdVpsRhURCKh+3M=
-github.com/go-openapi/jsonpointer v0.18.0/go.mod h1:cOnomiV+CVVwFLk0A/MExoFMjwdsUdVpsRhURCKh+3M=
-github.com/go-openapi/jsonpointer v0.19.2/go.mod h1:3akKfEdA7DF1sugOqz1dVQHBcuDBPKZGEoHC/NkiQRg=
+github.com/go-logr/logr v0.1.0/go.mod h1:ixOQHD9gLJUVQQ2ZOR7zLEifBX6tGkNJF4QyIY7sIas=
 github.com/go-openapi/jsonpointer v0.19.3 h1:gihV7YNZK1iK6Tgwwsxo2rJbD1GTbdm72325Bq8FI3w=
 github.com/go-openapi/jsonpointer v0.19.3/go.mod h1:Pl9vOtqEWErmShwVjC8pYs9cog34VGT37dQOVbmoatg=
-github.com/go-openapi/jsonreference v0.17.0/go.mod h1:g4xxGn04lDIRh0GJb5QlpE3HfopLOL6uZrK/VgnsK9I=
-github.com/go-openapi/jsonreference v0.18.0/go.mod h1:g4xxGn04lDIRh0GJb5QlpE3HfopLOL6uZrK/VgnsK9I=
-github.com/go-openapi/jsonreference v0.19.2/go.mod h1:jMjeRr2HHw6nAVajTXJ4eiUwohSTlpa0o73RUL1owJc=
 github.com/go-openapi/jsonreference v0.19.3 h1:5cxNfTy0UVC3X8JL5ymxzyoUZmo8iZb+jeTWn7tUa8o=
 github.com/go-openapi/jsonreference v0.19.3/go.mod h1:rjx6GuL8TTa9VaixXglHmQmIL98+wF9xc8zWvFonSJ8=
-github.com/go-openapi/loads v0.17.0/go.mod h1:72tmFy5wsWx89uEVddd0RjRWPZm92WRLhf7AC+0+OOU=
-github.com/go-openapi/loads v0.18.0/go.mod h1:72tmFy5wsWx89uEVddd0RjRWPZm92WRLhf7AC+0+OOU=
-github.com/go-openapi/loads v0.19.0/go.mod h1:72tmFy5wsWx89uEVddd0RjRWPZm92WRLhf7AC+0+OOU=
-github.com/go-openapi/loads v0.19.2/go.mod h1:QAskZPMX5V0C2gvfkGZzJlINuP7Hx/4+ix5jWFxsNPs=
-github.com/go-openapi/loads v0.19.4/go.mod h1:zZVHonKd8DXyxyw4yfnVjPzBjIQcLt0CCsn0N0ZrQsk=
-github.com/go-openapi/runtime v0.0.0-20180920151709-4f900dc2ade9/go.mod h1:6v9a6LTXWQCdL8k1AO3cvqx5OtZY/Y9wKTgaoP6YRfA=
-github.com/go-openapi/runtime v0.19.0/go.mod h1:OwNfisksmmaZse4+gpV3Ne9AyMOlP1lt4sK4FXt0O64=
-github.com/go-openapi/runtime v0.19.4/go.mod h1:X277bwSUBxVlCYR3r7xgZZGKVvBd/29gLDlFGtJ8NL4=
-github.com/go-openapi/spec v0.17.0/go.mod h1:XkF/MOi14NmjsfZ8VtAKf8pIlbZzyoTvZsdfssdxcBI=
-github.com/go-openapi/spec v0.18.0/go.mod h1:XkF/MOi14NmjsfZ8VtAKf8pIlbZzyoTvZsdfssdxcBI=
-github.com/go-openapi/spec v0.19.2/go.mod h1:sCxk3jxKgioEJikev4fgkNmwS+3kuYdJtcsZsD5zxMY=
-github.com/go-openapi/spec v0.19.3/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/strfmt v0.17.0/go.mod h1:P82hnJI0CXkErkXi8IKjPbNBM6lV6+5pLP5l494TcyU=
-github.com/go-openapi/strfmt v0.18.0/go.mod h1:P82hnJI0CXkErkXi8IKjPbNBM6lV6+5pLP5l494TcyU=
-github.com/go-openapi/strfmt v0.19.0/go.mod h1:+uW+93UVvGGq2qGaZxdDeJqSAqBqBdl+ZPMF/cC8nDY=
-github.com/go-openapi/strfmt v0.19.3/go.mod h1:0yX7dbo8mKIvc3XSKp7MNfxw4JytCfCD6+bY1AVL9LU=
-github.com/go-openapi/strfmt v0.19.5/go.mod h1:eftuHTlB/dI8Uq8JJOyRlieZf+WkkxUuk0dgdHXr2Qk=
-github.com/go-openapi/swag v0.17.0/go.mod h1:AByQ+nYG6gQg71GINrmuDXCPWdL640yX49/kXLo40Tg=
-github.com/go-openapi/swag v0.18.0/go.mod h1:AByQ+nYG6gQg71GINrmuDXCPWdL640yX49/kXLo40Tg=
-github.com/go-openapi/swag v0.19.2/go.mod h1:POnQmlKehdgb5mhVOsnJFsivZCEZ/vjK9gh66Z9tfKk=
 github.com/go-openapi/swag v0.19.5 h1:lTz6Ys4CmqqCQmZPBlbQENR1/GucA2bzYTE12Pw4tFY=
 github.com/go-openapi/swag v0.19.5/go.mod h1:POnQmlKehdgb5mhVOsnJFsivZCEZ/vjK9gh66Z9tfKk=
-github.com/go-openapi/validate v0.18.0/go.mod h1:Uh4HdOzKt19xGIGm1qHf/ofbX1YQ4Y+MYsct2VUrAJ4=
-github.com/go-openapi/validate v0.19.2/go.mod h1:1tRCw7m3jtI8eNWEEliiAqUIcBztB2KDnRCRMUi7GTA=
-github.com/go-openapi/validate v0.19.8/go.mod h1:8DJv2CVJQ6kGNpFW6eV9N3JviE1C85nY1c2z52x1Gk4=
 github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
-github.com/gobuffalo/here v0.6.0/go.mod h1:wAG085dHOYqUpf+Ap+WOdrPTp5IYcDAs/x7PLa8Y5fM=
 github.com/gogo/protobuf v1.1.1/go.mod h1:r8qH/GZQm5c6nD/R0oafs1akxWv10x8SbQlK7atdtwQ=
 github.com/gogo/protobuf v1.2.1/go.mod h1:hp+jE20tsWTFYpLwKvXlhS1hjn+gTNwPg2I6zVXpSg4=
 github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
@@ -98,15 +54,23 @@ github.com/golang/groupcache v0.0.0-20190129154638-5b532d6fd5ef/go.mod h1:cIg4er
 github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
 github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
 github.com/golang/protobuf v1.3.1/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
+github.com/golang/protobuf v1.4.0-rc.1/go.mod h1:ceaxUfeHdC40wWswd/P6IGgMaK3YpKi5j83Wpe3EHw8=
+github.com/golang/protobuf v1.4.0-rc.1.0.20200221234624-67d41d38c208/go.mod h1:xKAWHe0F5eneWXFV3EuXVDTCmh+JuBKY0li0aMyXATA=
+github.com/golang/protobuf v1.4.0-rc.2/go.mod h1:LlEzMj4AhA7rCAGe4KMBDvJI+AwstrUpVNzEA03Pprs=
+github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:WU3c8KckQ9AFe+yFwt9sWVRKCVIyN9cPHBJSNnbL67w=
+github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0=
+github.com/golang/protobuf v1.4.2/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
 github.com/google/btree v1.0.0/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ=
 github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
 github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
+github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
 github.com/google/go-cmp v0.4.0 h1:xsAVV57WRhGj6kEIi8ReJzQlHHqcBYCElAvkovg3B/4=
 github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 h1:El6M4kTTCOh6aBiKaUGG7oYTSPP8MxqL4YI3kZKwcP4=
 github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510/go.mod h1:pupxD2MaaD3pAXIBCelhxNneeOaAeabZDe5s4K6zSpQ=
-github.com/google/uuid v1.0.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/google/uuid v1.1.1/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/googleapis/gnostic v0.5.1/go.mod h1:6U4PtQXGIEt/Z3h5MAT7FNofLnw9vXk2cUuW7uA/OeU=
 github.com/gorilla/websocket v1.4.0/go.mod h1:E7qHFY5m1UJ88s3WnNqhKjPHQ0heANvMoAMk2YaljkQ=
 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=
@@ -116,33 +80,35 @@ github.com/imdario/mergo v0.3.5 h1:JboBksRwiiAJWvIYJVo46AfV+IAIKZpfrSzVKj42R4Q=
 github.com/imdario/mergo v0.3.5/go.mod h1:2EnlNZ0deacrJVfApfmtdGgDfMuh/nq6Ok1EcJh5FfA=
 github.com/inconshreveable/mousetrap v1.0.0/go.mod h1:PxqpIevigyE2G7u3NXJIT2ANytuPF1OarO4DADm73n8=
 github.com/jonboulle/clockwork v0.1.0/go.mod h1:Ii8DK3G1RaLaWxj9trq07+26W01tbo22gdxWY5EU2bo=
+github.com/json-iterator/go v1.1.6/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCVDaaPEHmU=
 github.com/julienschmidt/httprouter v1.2.0/go.mod h1:SYymIcj16QtmaHHD7aYtjjsJG7VTCxuUUipMqKk8s4w=
 github.com/kisielk/errcheck v1.1.0/go.mod h1:EZBBE59ingxPouuu3KfxchcWSUPOHkagtvWXihfKN4Q=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
 github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
 github.com/kr/logfmt v0.0.0-20140226030751-b84e30acd515/go.mod h1:+0opPa2QZZtGFBFZlji/RkVcI2GknAs/DXo4wKdlNEc=
-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/pretty v0.2.0 h1:s5hAObm+yFO5uHYt5dYjxi2rXrsnmRpJx4OYvIWUaQs=
+github.com/kr/pretty v0.2.0/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
 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/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/magiconair/properties v1.8.0/go.mod h1:PppfXfuXeibc/6YijjN8zIbojt8czPbwD3XqdrwzmxQ=
-github.com/mailru/easyjson v0.0.0-20180823135443-60711f1a8329/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
-github.com/mailru/easyjson v0.0.0-20190312143242-1de009706dbe/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
 github.com/mailru/easyjson v0.0.0-20190614124828-94de47d64c63/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
 github.com/mailru/easyjson v0.0.0-20190626092158-b2ccc519800e/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
 github.com/mailru/easyjson v0.7.0 h1:aizVhC/NAAcKWb+5QsU1iNOZb4Yws5UO2I+aIprQITM=
 github.com/mailru/easyjson v0.7.0/go.mod h1:KAzv3t3aY1NaHWoQz1+4F1ccyAH66Jk7yos7ldAVICs=
-github.com/markbates/pkger v0.17.1/go.mod h1:0JoVlrol20BSywW79rN3kdFFsE5xYM+rSCQDXbLhiuI=
 github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
 github.com/mitchellh/go-homedir v1.1.0/go.mod h1:SfyaCUpYCn1Vlf4IUYiD9fPX4A5wJrkLzIz1N1q0pr0=
 github.com/mitchellh/mapstructure v1.1.2/go.mod h1:FVVH3fgwuzCH5S8UJGiWEs2h04kUh9fWfEaFds41c1Y=
+github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
+github.com/modern-go/reflect2 v1.0.1/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
 github.com/monochromegane/go-gitignore v0.0.0-20200626010858-205db1a8cc00 h1:n6/2gBQ3RWajuToeY6ZtZTIKv2v7ThUy5KKusIT0yc0=
 github.com/monochromegane/go-gitignore v0.0.0-20200626010858-205db1a8cc00/go.mod h1:Pm3mSP3c5uWn86xMLZ5Sa7JB9GsEZySvHYXCTK4E9q4=
+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=
 github.com/oklog/ulid v1.3.1/go.mod h1:CirwcVhetQ6Lv90oh/F+FBtV6XMibvdAFo93nm5qn4U=
-github.com/pborman/uuid v1.2.0/go.mod h1:X/NO0urCmaxf9VXbdlT7C2Yzkj2IKimNn4k+gtPdI/k=
+github.com/onsi/ginkgo v0.0.0-20170829012221-11459a886d9c/go.mod h1:lLunBs/Ym6LB5Z9jYTR76FiuTmxDTDusOGeTQH+WWjE=
+github.com/onsi/gomega v0.0.0-20170829124025-dcabb60a477c/go.mod h1:C1qb7wdrVGGVU+Z6iS04AVkA3Q65CEZX59MT0QO5uiA=
 github.com/pelletier/go-toml v1.2.0/go.mod h1:5z9KED0ma1S8pY6P1sdut58dfprrGBbd/94hg7ilaic=
 github.com/pkg/errors v0.8.0/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
@@ -160,7 +126,6 @@ github.com/prometheus/procfs v0.0.0-20190507164030-5867b95ac084/go.mod h1:TjEm7z
 github.com/prometheus/tsdb v0.7.1/go.mod h1:qhTCs0VvXwvX/y3TZrWD7rabWM+ijKTux40TwIPHuXU=
 github.com/rogpeppe/fastuuid v0.0.0-20150106093220-6724a57986af/go.mod h1:XWv6SoW27p1b0cqNHllgS5HIMJraePCO15w5zCzIWYg=
 github.com/russross/blackfriday/v2 v2.0.1/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
-github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAmXWZgo=
 github.com/sergi/go-diff v1.1.0 h1:we8PVUC3FE2uYfodKH/nBHMSetSfHDR6scGdBi+erh0=
 github.com/sergi/go-diff v1.1.0/go.mod h1:STckp+ISIX8hZLjrqAeVduY0gWCT9IjLuqbuNXdaHfM=
 github.com/shurcooL/sanitized_anchor_name v1.0.0/go.mod h1:1NzhyTcUVG4SuEtjjoZeVRXNmyL/1OwPU0+IJeTBvfc=
@@ -171,29 +136,27 @@ github.com/spf13/afero v1.1.2/go.mod h1:j4pytiNVoe2o6bmDsKpLACNPDBIoEAkihy7loJ1B
 github.com/spf13/cast v1.3.0/go.mod h1:Qx5cxh0v+4UWYiBimWS+eyWzqEqokIECu5etghLkUJE=
 github.com/spf13/cobra v1.0.0/go.mod h1:/6GTrnGXV9HjY+aR4k0oJ5tcvakLuG6EuKReYlHNrgE=
 github.com/spf13/jwalterweatherman v1.0.0/go.mod h1:cQK4TGJAtQXfYWX+Ddv3mKDzgVb68N+wFjFa4jdeBTo=
+github.com/spf13/pflag v0.0.0-20170130214245-9ff6c6923cff/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4=
 github.com/spf13/pflag v1.0.3/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4=
 github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
 github.com/spf13/viper v1.4.0/go.mod h1:PTJ7Z/lr49W6bUbkmS1V3by4uWynFiR9p7+dSq/yZzE=
+github.com/stoewer/go-strcase v1.2.0/go.mod h1:IBiWB2sKIp3wVVQ3Y035++gc+knqhUQag1KpM8ahLw8=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.1.1/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.2.0 h1:Hbg2NidpLE8veEBkEZTL3CvlkUIVzuU9jDplZO54c48=
 github.com/stretchr/objx v0.2.0/go.mod h1:qt09Ya8vawLte6SNmTgCsAVtYtaKzEcn8ATUoHMkEqE=
 github.com/stretchr/testify v1.2.2/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=
-github.com/tidwall/pretty v1.0.0/go.mod h1:XNkn88O1ChpSDQmQeStsy+sBenx6DDtFZJxhVysOjyk=
+github.com/stretchr/testify v1.5.1 h1:nOGnQDM7FYENwehXlg/kFVnos3rEvtKTjRvOWSzb6H4=
+github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
 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/vektah/gqlparser v1.1.2/go.mod h1:1ycwN7Ij5njmMkPPAOaRFY4rET2Enx7IkVv3vaXspKw=
 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=
 go.etcd.io/bbolt v1.3.2/go.mod h1:IbVyRI1SCnLcuJnV2u8VeU0CEYM7e686BmAb1XKL+uU=
-go.mongodb.org/mongo-driver v1.0.3/go.mod h1:u7ryQJ+DOzQmeO7zB6MHyr8jkEQvC8vH7qLUO4lqsUM=
-go.mongodb.org/mongo-driver v1.1.1/go.mod h1:u7ryQJ+DOzQmeO7zB6MHyr8jkEQvC8vH7qLUO4lqsUM=
-go.mongodb.org/mongo-driver v1.1.2/go.mod h1:u7ryQJ+DOzQmeO7zB6MHyr8jkEQvC8vH7qLUO4lqsUM=
 go.starlark.net v0.0.0-20200306205701-8dd3e2ee1dd5 h1:+FNtrFTmVw0YZGpBGX56XDee331t6JAXeK2bcyhLOOc=
 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=
@@ -201,36 +164,27 @@ go.uber.org/multierr v1.1.0/go.mod h1:wR5kodmAFQ0UK8QlbwjlSNy0Z68gJhDJUG5sjR94q/
 go.uber.org/zap v1.10.0/go.mod h1:vwi/ZaCAaUcBkycHslxD9B2zi4UTXhF60s6SWpuDF0Q=
 golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
-golang.org/x/crypto v0.0.0-20190320223903-b7391e95e576/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
-golang.org/x/crypto v0.0.0-20190611184440-5c40567a22f8/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
-golang.org/x/crypto v0.0.0-20190617133340-57b3e21c3d56/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
 golang.org/x/lint v0.0.0-20190313153728-d0100b6bd8b3/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
 golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
-golang.org/x/net v0.0.0-20181005035420-146acd28ed58/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20181220203305-927f97764cc3/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
-golang.org/x/net v0.0.0-20190320064053-1272bf9dcd53/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
-golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190522155817-f3200d17e092/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks=
-golang.org/x/net v0.0.0-20190613194153-d28f0bde5980/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
-golang.org/x/net v0.0.0-20190827160401-ba9fcec4b297 h1:k7pJ2yAPLPgbskkFdhRCsA77k2fySZ1zf2zCjvQCiIM=
 golang.org/x/net v0.0.0-20190827160401-ba9fcec4b297/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20200324143707-d3edc9973b7e h1:3G+cUijn7XD+S4eJFddp53Pv7+slrESplyjG25HgL+k=
+golang.org/x/net v0.0.0-20200324143707-d3edc9973b7e/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20181107165924-66b7b1311ac8/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
-golang.org/x/sys v0.0.0-20190321052220-f7bb7a8bee54/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20190616124812-15dcb6c0061f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20191002063906-3421d5a6bb1c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.2 h1:tW2bmiBqwgJj/UpqtC8EpXEZVYOwU0yG4iWbprSVAcs=
 golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
@@ -238,15 +192,18 @@ golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxb
 golang.org/x/tools v0.0.0-20180221164845-07fd8470d635/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
-golang.org/x/tools v0.0.0-20190125232054-d66bd3c5d5a6/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
-golang.org/x/tools v0.0.0-20190614205625-5aca471b1d59/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc=
-golang.org/x/tools v0.0.0-20190617190820-da514acc4774/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
 google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc=
 google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
 google.golang.org/grpc v1.21.0/go.mod h1:oYelfM1adQP15Ek0mdvEgi9Df8B9CZIaU1084ijfRaM=
+google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8=
+google.golang.org/protobuf v0.0.0-20200221191635-4d8936d0db64/go.mod h1:kwYJMbMJ01Woi6D6+Kah6886xMZcty6N08ah7+eCXa0=
+google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQJ+fmap5saPgwCLgHXTUD7jkjRqWcaiX5VyM=
+google.golang.org/protobuf v1.20.1-0.20200309200217-e05f789c0967/go.mod h1:A+miEFZTKqfCUM6K7xSMQL9OKL/b6hQv+e19PK+JZNE=
+google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzikPIcrTAo=
+google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
 gopkg.in/alecthomas/kingpin.v2 v2.2.6/go.mod h1:FMv+mEhP44yOT+4EoQTLFTRgOQ1FBLkstjWtayDeSgw=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
@@ -257,14 +214,17 @@ gopkg.in/yaml.v2 v2.0.0-20170812160011-eb3733d160e7/go.mod h1:JAlM8MvJe8wmxCU4Bl
 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/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
-gopkg.in/yaml.v2 v2.2.7/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.8/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
 gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
-gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c h1:dUUwHk2QECo/6vqA44rthZ8ie2QXMNeKRTHCNY2nXvo=
-gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v3 v3.0.0-20200615113413-eeeca48fe776/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
-sigs.k8s.io/kustomize/kyaml v0.10.17 h1:4zrV0ym5AYa0e512q7K3Wp1u7mzoWW0xR3UHJcGWGIg=
-sigs.k8s.io/kustomize/kyaml v0.10.17/go.mod h1:mlQFagmkm1P+W4lZJbJ/yaxMd8PqMRSC4cPcfUVt5Hg=
+k8s.io/gengo v0.0.0-20200413195148-3a45101e95ac/go.mod h1:ezvh/TsK7cY6rbqRK0oQQ8IAqLxYwwyPxAX1Pzy0ii0=
+k8s.io/klog/v2 v2.0.0/go.mod h1:PBfzABfn139FHAV07az/IF9Wp1bkk3vpT2XSJ76fSDE=
+k8s.io/kube-openapi v0.0.0-20210421082810-95288971da7e h1:KLHHjkdQFomZy8+06csTWZ0m1343QqxZhR2LJ1OxCYM=
+k8s.io/kube-openapi v0.0.0-20210421082810-95288971da7e/go.mod h1:vHXdDvt9+2spS2Rx9ql3I8tycm3H9FDfdUoIuKCefvw=
+sigs.k8s.io/kustomize/kyaml v0.13.0 h1:9c+ETyNfSrVhxvphs+K2dzT3dh5oVPPEqPOE/cUpScY=
+sigs.k8s.io/kustomize/kyaml v0.13.0/go.mod h1:FTJxEZ86ScK184NpGSAQcfEqee0nul8oLCK30D47m4E=
+sigs.k8s.io/structured-merge-diff/v4 v4.0.2/go.mod h1:bJZC9H9iH24zzfZ/41RGcq60oK1F7G282QMXDPYydCw=
 sigs.k8s.io/yaml v1.2.0 h1:kr/MCeFWJWTwyaHoR9c8EjH9OumOmoF9YGiZd7lFm/Q=
 sigs.k8s.io/yaml v1.2.0/go.mod h1:yfXDCHCao9+ENCvLSE62v9VSji2MKu5jeNfTrofGhJc=

api/internal/accumulator/loadconfigfromcrds.go

@@ -7,13 +7,13 @@ import (
 	"encoding/json"
 	"strings"
 
-	"github.com/go-openapi/spec"
 	"github.com/pkg/errors"
-	"sigs.k8s.io/kustomize/api/filesys"
+	"k8s.io/kube-openapi/pkg/validation/spec"
 	"sigs.k8s.io/kustomize/api/ifc"
 	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
-	"sigs.k8s.io/kustomize/api/resid"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/filesys"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 	"sigs.k8s.io/yaml"
 )
 
@@ -178,9 +178,12 @@ func loadCrdIntoConfig(
 			}
 		}
 		if property.Ref.GetURL() != nil {
-			loadCrdIntoConfig(
+			err = loadCrdIntoConfig(
 				theConfig, theGvk, theMap,
 				property.Ref.String(), append(path, propName))
+			if err != nil {
+				return
+			}
 		}
 	}
 	return nil

api/internal/accumulator/loadconfigfromcrds_test.go

@@ -7,12 +7,13 @@ import (
 	"reflect"
 	"testing"
 
-	"sigs.k8s.io/kustomize/api/filesys"
+	"github.com/stretchr/testify/require"
 	. "sigs.k8s.io/kustomize/api/internal/accumulator"
 	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
 	"sigs.k8s.io/kustomize/api/loader"
-	"sigs.k8s.io/kustomize/api/resid"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/filesys"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 )
 
 // This defines two CRD's:  Bee and MyKind.
@@ -162,16 +163,13 @@ func TestLoadCRDs(t *testing.T) {
 	}
 
 	fSys := filesys.MakeFsInMemory()
-	fSys.WriteFile("/testpath/crd.json", []byte(crdContent))
+	err := fSys.WriteFile("/testpath/crd.json", []byte(crdContent))
+	require.NoError(t, err)
 	ldr, err := loader.NewLoader(loader.RestrictionRootOnly, "/testpath", fSys)
-	if err != nil {
-		t.Fatalf("unexpected error:%v", err)
-	}
+	require.NoError(t, err)
 
 	actualTc, err := LoadConfigFromCRDs(ldr, []string{"crd.json"})
-	if err != nil {
-		t.Fatalf("unexpected error:%v", err)
-	}
+	require.NoError(t, err)
 	if !reflect.DeepEqual(actualTc, expectedTc) {
 		t.Fatalf("expected\n %v\n but got\n %v\n", expectedTc, actualTc)
 	}

api/internal/accumulator/namereferencetransformer.go

@@ -11,6 +11,7 @@ import (
 	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
 	"sigs.k8s.io/kustomize/api/resmap"
 	"sigs.k8s.io/kustomize/api/resource"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 )
 
 type nameReferenceTransformer struct {
@@ -109,11 +110,18 @@ func debug(fMap filterMap) {
 // 'spec/scaleTargetRef/name' field. Return a filter that can do that.
 func (t *nameReferenceTransformer) determineFilters(
 	resources []*resource.Resource) (fMap filterMap) {
+
+	// We cache the resource OrgId values because they don't change and otherwise are very visible in a memory pprof
+	resourceOrgIds := make([]resid.ResId, len(resources))
+	for i, resource := range resources {
+		resourceOrgIds[i] = resource.OrgId()
+	}
+
 	fMap = make(filterMap)
 	for _, backReference := range t.backRefs {
 		for _, referrerSpec := range backReference.Referrers {
-			for _, res := range resources {
-				if res.OrgId().IsSelected(&referrerSpec.Gvk) {
+			for i, res := range resources {
+				if resourceOrgIds[i].IsSelected(&referrerSpec.Gvk) {
 					// If this is true, the res might be a referrer, and if
 					// so, the name reference it holds might need an update.
 					if resHasField(res, referrerSpec.Path) {

api/internal/accumulator/namereferencetransformer_test.go

@@ -9,9 +9,9 @@ import (
 
 	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
 	"sigs.k8s.io/kustomize/api/provider"
-	"sigs.k8s.io/kustomize/api/resid"
 	"sigs.k8s.io/kustomize/api/resmap"
 	resmaptest_test "sigs.k8s.io/kustomize/api/testutils/resmaptest"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 )
 
 const notEqualErrFmt = "expected (self) doesn't match actual (other): %v"
@@ -885,9 +885,9 @@ func TestNameReferenceClusterWide(t *testing.T) {
 			}).ResMap()
 
 	clusterRoleId := resid.NewResId(
-		resid.Gvk{Group: "rbac.authorization.k8s.io", Version: "v1", Kind: "ClusterRole"}, modifiedname)
+		resid.NewGvk("rbac.authorization.k8s.io", "v1", "ClusterRole"), modifiedname)
 	clusterRoleBindingId := resid.NewResId(
-		resid.Gvk{Group: "rbac.authorization.k8s.io", Version: "v1", Kind: "ClusterRoleBinding"}, modifiedname)
+		resid.NewGvk("rbac.authorization.k8s.io", "v1", "ClusterRoleBinding"), modifiedname)
 	clusterRole, _ := expected.GetByCurrentId(clusterRoleId)
 	clusterRole.AppendRefBy(clusterRoleBindingId)
 
@@ -897,7 +897,9 @@ func TestNameReferenceClusterWide(t *testing.T) {
 		t.Fatalf("unexpected error: %v", err)
 	}
 
+	expected.RemoveBuildAnnotations()
 	m.RemoveBuildAnnotations()
+
 	if err = expected.ErrorIfNotEqualLists(m); err != nil {
 		t.Fatalf(notEqualErrFmt, err)
 	}
@@ -1012,9 +1014,11 @@ func TestNameReferenceNamespaceTransformation(t *testing.T) {
 			}).ResMap()
 
 	clusterRoleId := resid.NewResId(
-		resid.Gvk{Group: "rbac.authorization.k8s.io", Version: "v1", Kind: "ClusterRole"}, modifiedname)
+		resid.NewGvk("rbac.authorization.k8s.io", "v1", "ClusterRole"),
+		modifiedname)
 	clusterRoleBindingId := resid.NewResId(
-		resid.Gvk{Group: "rbac.authorization.k8s.io", Version: "v1", Kind: "ClusterRoleBinding"}, modifiedname)
+		resid.NewGvk("rbac.authorization.k8s.io", "v1", "ClusterRoleBinding"),
+		modifiedname)
 	clusterRole, _ := expected.GetByCurrentId(clusterRoleId)
 	clusterRole.AppendRefBy(clusterRoleBindingId)
 

api/internal/accumulator/refvartransformer_test.go

@@ -7,10 +7,10 @@ import (
 	"reflect"
 	"testing"
 
-	"sigs.k8s.io/kustomize/api/resid"
 	"sigs.k8s.io/kustomize/api/resmap"
 	resmaptest_test "sigs.k8s.io/kustomize/api/testutils/resmaptest"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 )
 
 func TestRefVarTransformer(t *testing.T) {

api/internal/accumulator/resaccumulator.go

@@ -9,9 +9,9 @@ import (
 	"strings"
 
 	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
-	"sigs.k8s.io/kustomize/api/resid"
 	"sigs.k8s.io/kustomize/api/resmap"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 )
 
 // ResAccumulator accumulates resources and the rules
@@ -72,7 +72,7 @@ func (ra *ResAccumulator) MergeVars(incoming []types.Var) error {
 	for _, v := range incoming {
 		targetId := resid.NewResIdWithNamespace(v.ObjRef.GVK(), v.ObjRef.Name, v.ObjRef.Namespace)
 		idMatcher := targetId.GvknEquals
-		if targetId.Namespace != "" || !targetId.IsNamespaceableKind() {
+		if targetId.Namespace != "" || targetId.IsClusterScoped() {
 			// Preserve backward compatibility. An empty namespace means
 			// wildcard search on the namespace hence we still use GvknEquals
 			idMatcher = targetId.Equals
@@ -107,6 +107,7 @@ func (ra *ResAccumulator) findVarValueFromResources(v types.Var) (interface{}, e
 	for _, res := range ra.resMap.Resources() {
 		for _, varName := range res.GetRefVarNames() {
 			if varName == v.Name {
+				//nolint: staticcheck
 				s, err := res.GetFieldValue(v.FieldRef.FieldPath)
 				if err != nil {
 					return "", fmt.Errorf(
@@ -167,3 +168,23 @@ func (ra *ResAccumulator) FixBackReferences() (err error) {
 	return ra.Transform(
 		newNameReferenceTransformer(ra.tConfig.NameReference))
 }
+
+// Intersection drops the resources which "other" does not have.
+func (ra *ResAccumulator) Intersection(other resmap.ResMap) error {
+	for _, curId := range ra.resMap.AllIds() {
+		toDelete := true
+		for _, otherId := range other.AllIds() {
+			if otherId == curId {
+				toDelete = false
+				break
+			}
+		}
+		if toDelete {
+			err := ra.resMap.Remove(curId)
+			if err != nil {
+				return err
+			}
+		}
+	}
+	return nil
+}

api/internal/accumulator/resaccumulator_test.go

@@ -10,14 +10,15 @@ import (
 	"strings"
 	"testing"
 
+	"github.com/stretchr/testify/require"
 	. "sigs.k8s.io/kustomize/api/internal/accumulator"
 	"sigs.k8s.io/kustomize/api/internal/plugins/builtinconfig"
 	"sigs.k8s.io/kustomize/api/provider"
-	"sigs.k8s.io/kustomize/api/resid"
 	"sigs.k8s.io/kustomize/api/resmap"
 	"sigs.k8s.io/kustomize/api/resource"
 	resmaptest_test "sigs.k8s.io/kustomize/api/testutils/resmaptest"
 	"sigs.k8s.io/kustomize/api/types"
+	"sigs.k8s.io/kustomize/kyaml/resid"
 )
 
 func makeResAccumulator(t *testing.T) *ResAccumulator {
@@ -224,20 +225,26 @@ func TestResolveVarConflicts(t *testing.T) {
 	// create accumulators holding apparently conflicting vars that are not
 	// actually in conflict because they point to the same concrete value.
 	rm0 := resmap.New()
-	rm0.Append(rf.FromMap(fooAws))
+	err := rm0.Append(rf.FromMap(fooAws))
+	require.NoError(t, err)
 	ac0 := MakeEmptyAccumulator()
-	ac0.AppendAll(rm0)
-	ac0.MergeVars([]types.Var{varFoo})
+	err = ac0.AppendAll(rm0)
+	require.NoError(t, err)
+	err = ac0.MergeVars([]types.Var{varFoo})
+	require.NoError(t, err)
 
 	rm1 := resmap.New()
-	rm1.Append(rf.FromMap(barAws))
+	err = rm1.Append(rf.FromMap(barAws))
+	require.NoError(t, err)
 	ac1 := MakeEmptyAccumulator()
-	ac1.AppendAll(rm1)
-	ac1.MergeVars([]types.Var{varBar})
+	err = ac1.AppendAll(rm1)
+	require.NoError(t, err)
+	err = ac1.MergeVars([]types.Var{varBar})
+	require.NoError(t, err)
 
 	// validate that two vars of the same name which reference the same concrete
 	// value do not produce a conflict.
-	err := ac0.MergeAccumulator(ac1)
+	err = ac0.MergeAccumulator(ac1)
 	if err == nil {
 		t.Fatalf("see bug gh-1600")
 	}
@@ -246,10 +253,13 @@ func TestResolveVarConflicts(t *testing.T) {
 	// two above (because it contains a variable whose name is used in the other
 	// accumulators AND whose concrete values are different).
 	rm2 := resmap.New()
-	rm2.Append(rf.FromMap(barGcp))
+	err = rm2.Append(rf.FromMap(barGcp))
+	require.NoError(t, err)
 	ac2 := MakeEmptyAccumulator()
-	ac2.AppendAll(rm2)
-	ac2.MergeVars([]types.Var{varBar})
+	err = ac2.AppendAll(rm2)
+	require.NoError(t, err)
+	err = ac2.MergeVars([]types.Var{varBar})
+	require.NoError(t, err)
 	err = ac1.MergeAccumulator(ac2)
 	if err == nil {
 		t.Fatalf("dupe vars w/ different concrete values should conflict")
@@ -352,10 +362,10 @@ func TestResolveVarsWithNoambiguation(t *testing.T) {
 			"metadata": map[string]interface{}{
 				"name": "sub-backendOne",
 				"annotations": map[string]interface{}{
-					"config.kubernetes.io/previousKinds":      "Service",
-					"config.kubernetes.io/previousNames":      "backendOne",
-					"config.kubernetes.io/previousNamespaces": "default",
-					"config.kubernetes.io/prefixes":           "sub-",
+					"internal.config.kubernetes.io/previousKinds":      "Service",
+					"internal.config.kubernetes.io/previousNames":      "backendOne",
+					"internal.config.kubernetes.io/previousNamespaces": "default",
+					"internal.config.kubernetes.io/prefixes":           "sub-",
 				},
 			}}).ResMap()
 

api/internal/crawl/README.md

@@ -1,428 +0,0 @@
-## What is this?
-### In short
-Be the GoDoc.org of k8s configuration files.
-
-### More explicitly
-Support k8s document indexing from open-source configurations in order to make
-it easy for people to learn to use a new feature, explore k8s configs in a
-central hub, and see some metrics about kustomize use.
-
-We want people to be able to support three main classes of queries:
-
-1. Structured document queries: how should I use the following fields
-   - Grace periods: `spec:template:spec:terminationGracePeriod`?
-   - Kustomize inline patch: `patches:patch`?
-
-2. Key value queries: how should I use this more specific use case of a
-   structure configuration.
-   - HorizontalPodAutoScalers: `kind=HorizontalPodAutoScaler`?
-   - Patches on StatefulSets: `patches:target:kind=StatefulSet`?
-
-3. Full text search: search the comments and the document text from any
-   type of k8s config file.
-
-## Road map
-There is a lot that can be added in order to improve the state of this
-application. Some more details along with general thoughts and comments can be
-found in the Roadmap.md file in this directory. This README contains only
-what can be considered as mostly complete and iterable parts of this project.
-
-## Running this project
-Everything is configured using kubernetes, so it should be easy for people to
-spin this up on any k8s cluster. Everything should just work (TM).
-
-The config files live in the `config` directory.
-
-```
-config
-├── base
-│   └── kustomization.yaml
-├── crawler
-│   ├── base
-│   │   ├── github_api_secret.txt
-│   │   └── kustomization.yaml
-│   ├── cronjob
-│   │   ├── cronjob.yaml
-│   │   └── kustomization.yaml
-│   └── job
-│       ├── job.yaml
-│       └── kustomization.yaml
-├── elastic
-│   └── ...
-├── redis
-│   ├── document_keystore
-│   │   ├── kustomization.yaml
-│   │   ├── redis.yaml
-│   │   └── service.yaml
-│   └── http_cache
-│       ├── kustomization.yaml
-│       ├── redis.yaml
-│       └── service.yaml
-├── webapp
-│   ├── backend
-│   │   ├── deployment.yaml
-│   │   ├── kustomization.yaml
-│   │   └── service.yaml
-│   └── frontend
-│       ├── deployment.yaml
-│       ├── kustomization.yaml
-│       └── service.yaml
-└── schema_files
-    └── kustomization_index
-        ├── es_index_mappings.json
-        └── es_index_settings.json
-```
-
-To get everything up and running you have to:
-
-1. Get some instance of elasticsearch working... and configure the
-   configmapGenerator in `config/base` to point to the right endpoint(s). The
-   configurations that need this value to be populated are the following:
-    - `config/crawler/cronjob` to run periodic crawls.
-    - `config/crawler/job` to run crawls on demand.
-    - `config/webapp/backend` to run the search server.
-
-2. Configure the elasticsearch indices:
-```
-kustomize build config/schema_files/kustomization_index | kubectl apply -f -
-```
-This will run a `curl` command that reads json data from a ConfigMap. This will
-setup the schema.  If you want to make more complex modifications to the
-schema, you should refer to the elastic docs to figure out whether the mapping
-can be added to the current index, or whether you will need to copy the
-existing index into a different one with the appropriate mappings. Modifications
-can be made by using the elasticsearch go library and writing a simple program,
-or it can be made with any http command to the appropriate server endpoint from
-within the cluster. Unfortunately I did not have the time to write a few helper
-tools for this. Feel free to contact me if you need help with modifying
-elasticsearch configs, I'm by no means an expert, but I can try to help.
-
-3. (Optional) run the redis http chache for the crawler:
-```
-kubectl apply -k config/redis/http_cache
-```
-  This will create a deployment for the cache, and a service. The crawler should
-  be configured to connect to the `http_cache` if it exists, but you can always
-  check the logs to make sure it connects, and that the identifiers match in the
-  crawler configuration and for the service endpoint.
-
-  The please be aware that the cache does not have a persistent volume.
-
-4. Configure the main redis instance:
-```
-kubectl apply -k config/redis/document_keystore
-```
-  This will create a StatefulSet with a volume of 4GiB for a redis instance.
-
-5. Get an access token from GitHub.
-
-To be able to kindly ask GitHub for it's data on k8s config files, you'll need
-to create an access\_token. From my understanding, this is the only way to do
-these code search queries (without first specifying a repository).
-
-To generate a token, go to your GitHub's account in Settings > Developer
-Settings > Personal access tokens. It should look like this.
-
-![GitHub Token 1](
-https://sigs.k8s.io/kustomize/internal/tools/pictures/github_token.png)
-
-From here you want to generate a new token and  have the following
-configuration:
-
-![GitHub Token 1](
-https://sigs.k8s.io/kustomize/internal/tools/pictures/token_config.png)
-
-If you have uses for any other data from this token, (org data, or something
-else) you can pick and choose, but be careful since it can grant this
-application access to your notifications, etc. However, any such extension
-is explicitly a non-goal and would not be maintained by this project.
-
-6. Launch the crawler:
-```
-kustomize build config/crawler/cronjob | kubectl apply -f -
-```
-This will periodically run the crawler every day according to the cron timing
-rules in the cronjob.yaml file.
-
-Instead, to get the crawler running now, you can run:
-```
-kustomize build config/crawler/cronjob | kubectl apply -f -
-```
-which will launch a non-periodic version of the crawler. It will take a few
-minutes for the crawler to split the search, but then config files should
-start to get populated within 20 minutes. It may take a while to do the
-first crawl, since it has to fetch rate-limited endpoints for each new file it
-finds. It should get significantly faster to update in the future.
-
-5. Launch the search backend
-```
-kustomize build config/webapp/backend | kubectl apply -f -
-```
-
-6. Launch the search frontend
-```
-kustomize build config/webapp/frontend | kubectl apply -f -
-```
-
-## Notes about the components
-
-### Elasticsearch
-I will add a basic working setup soon. I just did the lazy thing and used an
-already packaged solution. Most clouds will provide their own elastic
-environments, however, Elasticsearch is also working on their own
-implementation of a
-![k8s operator](https://www.elastic.co/elasticsearch-kubernetes), which might
-be worth checking out. Please note that it comes with its own license
-agreement.
-
-### Redis
-There are two Redis instances that are used in this application.
-
-One of them is configured to have on disk persistence, so make sure to have
-that set up in your kubernetes cluster. Also note that it is running on a
-single master node (i.e. it does not automatically shard keys to multiple head
-nodes as part of a highly available cluster). Since it's storing a sparse
-graph, I can't imagine this being much of an issue, but it's probably worth
-mentioning.
-
-The other Redis instance is running as a HTTP (RFC 7234) cache for etags from
-GitHub (or any other document store from which we could crawl/index). This one
-does not require full persistent storage on disk. The caching strategy is an
-LRU cache which is probably a good starting point. It might be worth it to
-investigate other cache policies, but I think LRU will work well since
-documents may or may not expire anyway, and the amount of memory allocated for
-keys is fairly large, so eviction of frequently used documents seems unlikely
-anyway.
-
-### Nginx + Angular
-There is a Dockerfile included for generating the container image with Nginx
-(using the default package) and adding all of the supporting compiled angular
-files. Any modifications to the code-base should be compatible with this setup,
-so all that's needed is to rebuild the container image, and possibly modify
-the image tags in the k8s file.
-
-### Supporting Go binaries
-There are a few go binaries that each have their own Dockerfile to build
-containers in which to run them on k8s, namely the crawler and the search
-service. Their configurations are not optimal (read: needs to be cleaned up),
-but they are functional.
-
-## Technical details
-
-### 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
-overview of each component with the following sections going into more details.
-
-The overall structure is outlined in the following figure:
-![overview](
-https://github.com/kubernetes-sigs/kustomize/blob/master/api/internal/crawl/pictures/token_config.png)
-
-#### Crawler
-The leftmost component consists of a crawler with an http cache of GitHub
-queries does two things, it first looks at the list of documents in
-elasticsearch and tries to update them. In doing so, it maintains a set of
-newly updated files to exclude them from other parts of the crawl.
-
-To find newly added documents, the crawler crawls any new dependencies
-introduced in the document updating step and it also queries GitHub for the
-most recently indexed kustomization.\* files. Each new file will be processed
-for efficient text queries and put into the document index. Any new dependency
-will also incur more crawl operations. Finally, a graphical
-representation of the documents and their dependencies is built in Redis to be
-used for graph algorithms such as PageRank and component analysis.
-
-#### Data library
-There are a few helper libaries for dealing with Elasticsearch, Redis and
-documents. This is not persistent, nor is it centralized. They act as small
-components that help to package common pieces of code. Eventually it may make
-sense to merge all of it together and make a proper persistent model around
-this while providing an external API for document insertion/deletion. But
-that is definitely out of scope in terms of getting this to run. However
-there are limitations with the current model in terms of minimizing the
-API surface for the different components of the application. For now this
-problem is mostly mitigated by having the query server only connected to
-a data node of the Elasticsearch cluster, but the problem of knowing what
-is accessible and what isn't is left to the programmer instead of being
-clearly and explicitly supported by the API.
-
-#### Server
-Uses the data library to communicate with the data store and answer queries.
-Processes the user entered text queries into somewhat optimized elasticsearch
-queries. Provides a few endpoints to get different metrics and to eventually
-allow for registration of remote repositories.
-
-This application has an exposing service in order to allow users of the
-application access to queries and the results.
-
-#### Nginx + Angular
-Communicates directly with the backend server to forward user queries and
-their results. Presents the results on an interface. It's still pretty simple
-looking but it seems usable (to me).
-
-
-### Crawling GitHub
-With the use of API keys, GitHub allows account owners to search for files
-using their API.
-
-The search endpoints allow for the use of metadata search
-that is fairly useful/powerful. For instance they provide a `filename:` keyword
-that permits us to look for `kustomization.yaml`, `kustomization.yml`, etc.
-This enables the fetching of a list of kustomization documents, from which
-we can get the actual content from another endpoint
-(raw.githubusercontent.com).
-
-However, the search API is fairly limited. There is a restriction to the number
-of documents that can be retrieved from this method. One possible way to
-mitigate this would be to periodically query GitHub for results, sorted by the
-last indexed time. This would allow you to collect most documents from this
-point forwards. The downside to this is that it may require a large number of
-requests to their API since you cannot know when new files will be added.
-Furthermore, there is a possibility that you would not be able to get all of
-files either, depending on the velocity of growth.
-
-The approach that was taken to mitigate this is to use the `filesize:` keyword
-and to shard the search space into contiguous buckets of appropriate size in
-order to get all of the documents. This is fairly efficient, since you can find
-a good enough way to shard the documents in
-`lg(max file size) * number of documents / 1000` API queries. Moreover, since
-queries are paginated with at most 100 results per query, this solution is
-competitive with getting the optimal (non-contiguous) sharding of result sets.
-Furthermore, filesize queries can be cached to minimize the total number of
-queries called to the API in order to shard the search space. This is done by
-querying for file size intervals that always start with 0..X and binary
-searching over the `filesize:` space. This will allow you to reuse a lot of
-queries when you're looking for the next range, since it is upper bounded and
-lower bounded to a smaller number of queries within a range that has also been
-queried. I think this is only true because filesizes are power law distributed,
-so searches will typically require less queries as they progress from left to
-right.
-
-However, this method in no way depends on intervals of the form 0..X, as
-the number of documents in the many intervals of the range search could be
-added together to also make this work. This approach just seemed simpler to
-implement, maintain, and debug so it was preferred.
-
-To get an idea of how efficient this method is, to shard the search space of
-7000 documents, it will only take ~90 API range queries which should only take
-a few minutes. While actually fetching the documents and their relevant
-metadata (creation time, etc.) will take several hours. Furthermore, this
-could be made more efficient if a prior distribution is approximated.
-This prior could be scaled to the number of documents that need to be fetched,
-and then finding a shard that has an adequate number of requests, will only
-take a few queries per shard. It could probably be supported in a constant
-number of size queries if the size of each shard is halved which shouldn't
-have terrible performance impact for the retrieval. However, there where
-more pressing things to implement. I might revisit this later.
-
-### Document Indexing and Processing
-In order to support simple text queries the structured documents must be
-processed in some way that makes searching them easy. The current method
-is to recursively traverse the map of configurations to generate each sub-path
-and each key-value pair for the leaf nodes of the recursion tree.
-
-However, note that this means that a document has to be valid yaml/json
-format in order for indexing to happen. The rest of the document is treated
-as mostly text and uses default text settings from Elasticsearch.
-
-What this means is that for the following yaml document:
-
-```yaml
-resources:
-- service.yaml
-- deployment.yaml
-
-configmapGenerator:
-- name: app-configuration
-  files:
-  - config.yaml
-
-patchesJson6902:
-- target:
-    version: v1
-    kind: StatefulSet
-    name: ss-name
-  path: ss-patch.yaml
-- target:
-    version: v1
-    kind: Deployment
-    name: dep-name
-  path: dep-patch.yaml
-```
-
-the following flattened structure would look like:
-```
-{
-  "identifiers": [
-    "resources",
-    "configmapGenerator",
-    "configmapGenerator:name",
-    "configmapGenerator:files",
-    "patchesJson6902",
-    "patchesJson6902:target",
-    "patchesJson6902:target:version",
-    "patchesJson6902:target:kind",
-    "patchesJson6902:target:name",
-    "patchesJson6902:path",
-  ],
-  "values": [
-    "resources=service.yaml",
-    "resources=deployment.yaml",
-    "configmapGenerator:name=app-configuration",
-    "configmapGenerator:files=config.yaml",
-    "patchesJson6902:target:version=v1",
-    "patchesJson6902:target:kind=StatefulSet",
-    "patchesJson6902:target:name=ss-name",
-    "patchesJson6902:path=ss-patch.yaml",
-    "patchesJson6902:target:kind=Deployment",
-    "patchesJson6902:target:name=dep-name",
-    "patchesJson6902:path=dep-patch.yaml",
-  ],
-  ...
-}
-```
-
-Note that unique paths and values are deduplicated.
-
-On the search side, exact queries will be prioritized, but the document paths
-and key=value pairs will also be analyzed with 3-grams to have some amount of
-fuzzy search. The reason that a Levenshtein-Distance was not used instead, is due
-to searching multiple fields at the same time, which is a use case where
-Elasticsearch does not support proper fuzzy searching.
-
-### Document Search
-Given a text query, each token is considered separately. Each token will be fed
-through a handful of analyzers on the Elasticsearch side, and will be compared
-with the reverse document index of each document fields. It will then determine
-the best matching documents. Text ordering is largely insignificant. This makes
-sense for the structured search, but may leave room for improvement for the
-text only search within the document.
-
-Each token _must_ be matched, so each white space character acts as a
-conjunction of individual queries. There are also ways of telling
-Elasticsearch that some things _should_ match, but I think for now it makes
-more sense to leave it as is.
-
-I think this behavior is sufficient to make the search feel fairly intuitive
-while providing support for fairly complex use cases.
-
-### Metrics Computation
-From the each kustomization document that is indexed, we can find it's
-resources that are publicly available. This includes other kustomizations.
-From this, we can build a directed graph of dependencies and reverse
-dependencies.
-
-This opens up the possibility to add a plethora of graph metrics that can
-give the project maintainers feedback and insight into how people are using
-their tools.
-
-Some of these are useful such as getting an idea for how large the dependency
-graphs actually grow in practice, and can be used to find _popular_
-kustomizations within the corpus. This lends itself to implementing PageRank
-to help bubble up popular results as good search results. I unfortunately
-did not have the time to implement the algorithm, but I do plan to revisit
-this sometime soon to add a few good and efficient implementations of useful
-graph algorithms that would be useful to have. See the Roadmap.md for a more
-complete list of features that could be added and how I think they could be
-implemented.

api/internal/crawl/ROADMAP.md

@@ -1,176 +0,0 @@
-# Road map and comments about this work
-
-From working on this project, here is a collection of thoughts and suggestions
-for future improvements. For any questions about this, or to request help do
-not hesitate to contact @damienr74 on GitHub, my email should be listed.
-
-I think this project has the potential for the K8s community to promote best
-practices. If this becomes popular, It could become easier to find
-*subjectively good* configurations. This can act as a way to guide newcomers
-to k8s config features that are easy to maintain, practical, and tested in some
-real world environment. However, a lot of work remains to be made if this is
-to happen. Extracting and ranking semantic-level information from the open
-source configuration files, is definitely not trivial, and will require a lot of
-though and consideration from the experts and the patterns that successful k8s
-project follow. This, is outside of my scope having little to no experience with
-k8s other than working on this project; however, if you have ideas I can
-probably suggest approaches in order to implement it, having worked a lot on
-this project.
-
-### Improving configuration files and container configs
-I did not have a lot of time to refactor the images to use configmaps for
-everything. This is a good thing to improve, should be fairly easy. Another
-thing that could make the user experience of launcing this could be to make all
-of the go utilities be subcommands to the same binary/container image. This
-would reduce the number of things that would have to be rebuilt, in order to get
-it running, and it would make the application (and its components) more self
-contained. (also has some disadvantages, so I'll let someone else decide.
-
-### Adding graph metrics
-From the Redis graph representation, we are able to run a multitude of graph
-algorithms (not all of which are implemented).
-
-The simplest one would be to run kruskal's algorithm to find connected
-components, and to compute graph metrics on each component. Here are some of the
-metrics that may be useful:
-
-+ Average size and histograms of the sizes of each components.
-
-+ Average size and histograms of the node with the highest in degree (rdeps) of
-  each component.
-
-+ Average size and histograms of the number of repositories in a connected
-  component.
-
-+ Any other metric that may be helpful to measure the scale of the kustomize
-  import graph.
-
-Another cool thing that may be helpful, would be to output the graph
-representation of deps/rdeps. This should be fairly easy to do with graphviz/dot
-so if anyone really wants this, I (damienr74) should be able to do it. Feel free
-to send me an email or to @ mention me in an issue.
-
-Note: dfs could also be used to find connected components, but I think union
-find is preferable, since the results can be stored and modified very
-efficiently. The only challenging part would be to implement deleting of edges
-and nodes from a component efficiently, but I know it is possible to support
-these operations with a union find structure.
-
-### Implementing PageRank
-The graph is set up to be able to efficiently compute PageRank since the edge
-weights are real valued, and the graph representation is sparse which means that
-it will fit in the memory of a single machine which will make the processing
-much more efficient.
-
-It could also be implemented as a Redis script, but I feel like there's
-something fundamentally wrong with implementing PageRank in lua. :P
-
-### Implement feature tracking
-Each day, when the crawler finds and indexes these structured documents,
-it should insert aggregate data to a separate index. This data could look like the
-following:
-
-```
-{
-  "kind": "kustomization",
-  "added_identifiers": [
-    {
-      "identifier": "some:new:k8s:feature",
-      "addedIn": [
-        "docID1",
-        "docID100",
-        "docID45",
-        ...
-      ],
-    },
-    {
-      "identifier": "another:k8s:feature",
-      "documents": [
-        ...
-      ],
-    },
-    ...
-  ]
-
-  "removed_identifiers": [
-    {
-      "identifier": "some:deprecated:field",
-      "documents": [
-        ...
-      ]
-    }
-  ]
-}
-```
-
-This would make it fairly easy to get deep insight into:
-- the speed at which things can effectively be deprecated.
-- how many people are migrating to current best practices.
-- how many documents get updated frequently/rarely.
-- detailed cross sections of growth/regression over conjunctions of features.
-- a world of possibilities.
-
-This is also something that I would be interested to work on sometime soon, so
-feel free to contact me (damienr74) or ask questions about this.
-
-As needed, it could be a good idea to also aggregate past data with a larger
-granularity. for instance each month, the past 30 days can be aggregated into
-weekish durations, And every year these weekly aggregations can be converted
-into monthly summaries depending on how much data this ends up being, and how
-much you want to pay for the storage of this data.
-
-Another cool way to compress this data would be to dynamically compress this
-data into a logarithmic number of buckets with decreasing granularity. But it
-seems like overkill for the amount of data that we'd likely get.
-
-### The UI probably needs a lot of work
-I'm not much of a UI/UX person and have little to no experience in developing
-these types of applications. If anyone with Angular experience wants to dive in
-and completely restructure the app to make the UI/UX/Code health better that
-would be greatly appreciated.
-
-### Query tuning probably still has to be adjusted
-I'm also not an expert in Elasticsearch. From what I could read in the docs,
-I think I've made sane decisions in converting user queries into meaningful
-Elasticsearch queries, but I'm sure there are a lot of improvements that remain
-to be done in order to get more accurate results.
-
-
-### Some other signals that indicate the presence of a good configuration file
-There are lots of heuristics that could be used to achieve this. Here are a
-couple in no particular order:
-
-+ Penalize for the number of yaml `---` document splits. I'm not sure what the
-  general consensus is, but I think it's better to separate them, since it
-  makes git commits less noisy, it's a trivial transformation, and it makes
-  config files smaller. However, I can understand the argument that its somewhat
-  practical to keep an overall view of the configurations together (maybe).
-
-+ Penalize the number of unique identifiers in a structured document. I think
-  this makes sense, since we don't want to have someone game the search engine
-  to match documents with every possible path from the k8s docs. PageRank might
-  help with this to some extent, but with a small corpus it would be fairly easy
-  to game.
-
-+ Assign weights to the usefulness of certain fields. It would be good to
-  promote documents that use `keyRefFromConfigMap`, liveness probes, etc.
-
-These are the main ones I can think of, but I'm sure there are a *ton* of
-ways to achieve this.
-
-If the corpus gets large enough, we might even be able to use *blockchains*,
-*machine learning*, and maybe even self-driving cars.
-
-### Add more support for indexing of other k8s/kustomize related data
-One thing that jumps to mind is the use of kustomize plugins. They are easy
-to track since they all have an unused global variable: `var KustomizePluggin`
-it would be easy to run the pluginator command and generate godocs for each
-go file with this unique identifier.
-
-For the sake of completeness, here is the full GitHub query that we can use to
-find these:
-`api.github.com/search/code?q=var+KustomizePlugin+extension%3A.go&access_token=access_token`
-
-Godoc will not show much, since most packages will be using package main, but
-using pluginator we can make it a properly named package such that Godoc would
-actually generate the relevant documentation.

api/internal/crawl/backend/search_backend.go

@@ -1,195 +0,0 @@
-package server
-
-import (
-	"context"
-	"encoding/json"
-	"fmt"
-	"log"
-	"net/http"
-	"os"
-	"strconv"
-	"strings"
-
-	"github.com/gorilla/mux"
-	"github.com/rs/cors"
-
-	"sigs.k8s.io/kustomize/api/internal/crawl/index"
-)
-
-type kustomizeSearch struct {
-	ctx context.Context
-	// Eventually pIndex *index.PlugginIndex
-	idx    *index.KustomizeIndex
-	router *mux.Router
-	log    *log.Logger
-}
-
-// New server. Creating a server does not launch it. To launch simply:
-//	srv, _ := NewKustomizeSearch(context.Backgroud())
-//	err := srv.Serve()
-//	if err != nil {
-//		// Handle server issues.
-//	}
-//
-// The server has three enpoints, two of which are functional:
-//
-// /search: processes the ?q= parameter for a text query and
-// returns a list of 10 resutls starting from the ?from= value provided,
-// with the default being zero.
-//
-// /metrics: returns overall metrics about the files indexed. Returns
-// timeseries data for kustomization files, and returns breakdown of file
-// counts by their 'kind' fields
-//
-// /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, "kustomize")
-	if err != nil {
-		return nil, err
-	}
-
-	ks := &kustomizeSearch{
-		ctx:    ctx,
-		idx:    idx,
-		router: mux.NewRouter(),
-		log: log.New(os.Stdout, "Kustomize server: ",
-			log.LstdFlags|log.Llongfile|log.LUTC),
-	}
-
-	return ks, nil
-}
-
-// Set up common middleware and the routes for the server.
-func (ks *kustomizeSearch) routes() {
-
-	// Setup middleware.
-	ks.router.Use(func(handler http.Handler) http.Handler {
-		return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-			w.Header().Set("Content-Type", "application/json")
-			handler.ServeHTTP(w, r)
-		})
-	})
-
-	ks.router.HandleFunc("/liveness", ks.liveness()).Methods(http.MethodGet)
-	ks.router.HandleFunc("/readiness", ks.readiness()).Methods(http.MethodGet)
-	ks.router.HandleFunc("/search", ks.search()).Methods(http.MethodGet)
-	ks.router.HandleFunc("/metrics", ks.metrics()).Methods(http.MethodGet)
-	ks.router.HandleFunc("/register", ks.register()).Methods(http.MethodPost)
-}
-
-// Start listening and serving on the provided port.
-func (ks *kustomizeSearch) Serve(port int) error {
-	ks.routes()
-	handler := cors.Default().Handler(ks.router)
-	s := &http.Server{
-		Addr:    fmt.Sprintf(":%d", port),
-		Handler: handler,
-		// Timeouts/Limits
-	}
-
-	return s.ListenAndServe()
-}
-
-// /liveness endpoint
-func (ks *kustomizeSearch) liveness() http.HandlerFunc {
-	return func(w http.ResponseWriter, r *http.Request) {
-		w.WriteHeader(http.StatusOK)
-	}
-}
-
-// /readyness endpoint
-func (ks *kustomizeSearch) readiness() http.HandlerFunc {
-	return func(w http.ResponseWriter, r *http.Request) {
-		opt := index.KustomizeSearchOptions{}
-		_, err := ks.idx.Search("", opt)
-		if err != nil {
-			http.Error(w,
-				`{ "error": "could not connect to database" }`,
-				http.StatusInternalServerError)
-			return
-		}
-		w.WriteHeader(http.StatusOK)
-	}
-}
-
-// /register endpoint.
-func (ks *kustomizeSearch) register() http.HandlerFunc {
-	return func(w http.ResponseWriter, r *http.Request) {
-		http.Error(w, "not implemented", http.StatusInternalServerError)
-	}
-}
-
-// /search endpoint.
-func (ks *kustomizeSearch) search() http.HandlerFunc {
-	return func(w http.ResponseWriter, r *http.Request) {
-		values := r.URL.Query()
-
-		queries := values["q"]
-		ks.log.Println("Query: ", values)
-
-		var from int
-		fromParam := values["from"]
-		if len(fromParam) > 0 {
-			from, _ = strconv.Atoi(fromParam[0])
-			if from < 0 {
-				from = 0
-			}
-		}
-		_, noKinds := values["nokinds"]
-
-		opt := index.KustomizeSearchOptions{
-			SearchOptions: index.SearchOptions{
-				Size: 10,
-				From: from,
-			},
-			KindAggregation: !noKinds,
-		}
-
-		results, err := ks.idx.Search(strings.Join(queries, " "), opt)
-		if err != nil {
-			ks.log.Println("Error: ", err)
-			http.Error(w, fmt.Sprintf(
-				`{ "error": "could not complete the query" }`),
-				http.StatusInternalServerError)
-			return
-		}
-
-		enc := json.NewEncoder(w)
-		setIndent(enc)
-		if err = enc.Encode(results); err != nil {
-			http.Error(w, `{ "error": "failed to send back results" }`,
-				http.StatusInternalServerError)
-			return
-		}
-		return
-	}
-}
-
-// metrics endpoint.
-func (ks *kustomizeSearch) metrics() http.HandlerFunc {
-	return func(w http.ResponseWriter, r *http.Request) {
-		res, err := ks.idx.Search("", index.KustomizeSearchOptions{
-			KindAggregation:       true,
-			TimeseriesAggregation: true,
-		})
-		if err != nil {
-			http.Error(w, `{ "error": "could not perform the search."}`,
-				http.StatusInternalServerError)
-			return
-		}
-
-		enc := json.NewEncoder(w)
-		setIndent(enc)
-		if err := enc.Encode(res); err != nil {
-			http.Error(w, `{ "error": "could not format return value" }`,
-				http.StatusInternalServerError)
-			return
-		}
-	}
-}
-
-// make json response human readable.
-func setIndent(e *json.Encoder) {
-	e.SetIndent("", "  ")
-}

api/internal/crawl/cmd/backend/Dockerfile

@@ -1,14 +0,0 @@
-FROM golang:1.11 AS build
-
-ARG GO111MODULE=on
-
-WORKDIR /go/src/sigs.k8s.io/kustomize/api/internal/crawl
-COPY . /go/src/sigs.k8s.io/kustomize/api/internal/crawl
-
-RUN go mod download
-RUN CGO_ENABLED=0 go install sigs.k8s.io/kustomize/api/internal/crawl/cmd/backend/
-
-FROM scratch
-COPY --from=build /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/
-COPY --from=build /go/bin/backend /
-ENTRYPOINT ["/backend"]

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

@@ -1,30 +0,0 @@
-package main
-
-import (
-	"context"
-	"log"
-	"os"
-	"strconv"
-
-	server "sigs.k8s.io/kustomize/api/internal/crawl/backend"
-)
-
-func main() {
-	portStr := os.Getenv("PORT")
-	port, err := strconv.Atoi(portStr)
-	if portStr == "" || err != nil {
-		log.Fatalf("$PORT(%s) must be set to an integer\n", portStr)
-	}
-
-	ctx := context.Background()
-
-	ks, err := server.NewKustomizeSearch(ctx)
-	if err != nil {
-		log.Fatalf("Error creating kustomize server: %v", ks)
-	}
-
-	err = ks.Serve(port)
-	if err != nil {
-		log.Fatalf("Error while running server: %v", err)
-	}
-}

api/internal/crawl/cmd/crawler/Dockerfile

@@ -1,15 +0,0 @@
-FROM golang:1.14 AS build
-
-ARG GO111MODULE=on
-
-WORKDIR /go/src/sigs.k8s.io/kustomize/api/internal/crawl
-COPY . /go/src/sigs.k8s.io/kustomize//api/internal/crawl
-
-RUN go mod download
-RUN CGO_ENABLED=0 go install -v ./cmd/crawler/crawler.go
-
-FROM scratch
-COPY --from=build /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/
-COPY --from=build /go/bin/crawler /
-ENTRYPOINT ["/crawler"]
-CMD []

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

@@ -1,206 +0,0 @@
-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"
-	"sigs.k8s.io/kustomize/api/internal/crawl/httpclient"
-	"sigs.k8s.io/kustomize/api/internal/crawl/index"
-
-	"github.com/gomodule/redigo/redis"
-)
-
-const (
-	githubAccessTokenVar = "GITHUB_ACCESS_TOKEN"
-	redisCacheURL        = "REDIS_CACHE_URL"
-	redisKeyURL          = "REDIS_KEY_URL"
-	retryCount           = 3
-)
-
-type CrawlMode int
-
-const (
-	CrawlUnknown CrawlMode = iota
-	// Crawl all the kustomization files in all the repositories of a Github user
-	CrawlUser
-	// Crawl all the kustomization files in a Github repo
-	CrawlRepo
-	// Crawl all the documents in the index
-	CrawlIndex
-	// Crawl all the kustomization files on Github
-	CrawlGithub
-	// Crawl all the documents in the index and crawling all the kustomization files on Github
-	CrawlIndexAndGithub
-)
-
-func NewCrawlMode(s string) CrawlMode {
-	switch s {
-	case "github-user":
-		return CrawlUser
-	case "github-repo":
-		return CrawlRepo
-	case "index+github":
-		return CrawlIndexAndGithub
-	case "index":
-		return CrawlIndex
-	case "github":
-		return CrawlGithub
-	default:
-		return CrawlUnknown
-	}
-}
-
-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 == "" {
-		log.Printf("Must set the variable '%s' to make github requests.\n",
-			githubAccessTokenVar)
-		return
-	}
-
-	ctx := context.Background()
-	idx, err := index.NewKustomizeIndex(ctx, *indexNamePtr)
-	if err != nil {
-		log.Printf("Could not create an index: %v\n", err)
-		return
-	}
-
-	cacheURL := os.Getenv(redisCacheURL)
-	cache, err := redis.DialURL(cacheURL)
-	clientCache := &http.Client{}
-	if err != nil {
-		log.Printf("Error: redis could not make a connection: %v\n", err)
-	} else {
-		clientCache = httpclient.NewClient(cache)
-	}
-
-	// docConverter takes in a plain document and processes it for the index.
-	docConverter := func(d *doc.Document) (crawler.CrawledDocument, error) {
-		kdoc := doc.KustomizationDocument{
-			Document: *d,
-		}
-
-		err := kdoc.ParseYAML()
-		return &kdoc, err
-	}
-
-	// Index updates the value in the index.
-	indexFunc := func(cdoc crawler.CrawledDocument, mode index.Mode) error {
-		switch d := cdoc.(type) {
-		case *doc.KustomizationDocument:
-			switch mode {
-			case index.Delete:
-				log.Printf("Deleting: %v", d)
-				return idx.Delete(d.ID())
-			default:
-				log.Printf("Inserting: %v", d)
-				return idx.Put(d.ID(), d)
-			}
-		default:
-			return fmt.Errorf("type %T not supported", d)
-		}
-	}
-
-	// 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 := utils.NewSeenMap()
-
-	mode := NewCrawlMode(*modePtr)
-
-	ghCrawlerConstructor := func(user, repo string) crawler.Crawler {
-		if user != "" {
-			return github.NewCrawler(githubToken, retryCount, clientCache,
-				github.QueryWith(
-					github.Filename("kustomization.yaml"),
-					github.Filename("kustomization.yml"),
-					github.Filename("kustomization"),
-					github.User(user)),
-			)
-		} else if repo != "" {
-			return github.NewCrawler(githubToken, retryCount, clientCache,
-				github.QueryWith(
-					github.Filename("kustomization.yaml"),
-					github.Filename("kustomization.yml"),
-					github.Filename("kustomization"),
-					github.Repo(repo)),
-			)
-		} else {
-			return github.NewCrawler(githubToken, retryCount, clientCache,
-				github.QueryWith(
-					github.Filename("kustomization.yaml"),
-					github.Filename("kustomization.yml"),
-					github.Filename("kustomization")),
-			)
-		}
-	}
-
-	query := []byte(`{ "query":{ "match_all":{} } }`)
-	it := idx.IterateQuery(query, 10000, 60*time.Second)
-
-	switch mode {
-	case CrawlIndexAndGithub:
-		crawlers := []crawler.Crawler{ghCrawlerConstructor("", "")}
-		crawler.CrawlFromSeedIterator(ctx, it, crawlers, docConverter, indexFunc, seen)
-		crawler.CrawlGithub(ctx, crawlers, docConverter, indexFunc, seen)
-	case CrawlIndex:
-		crawlers := []crawler.Crawler{ghCrawlerConstructor("", "")}
-		crawler.CrawlFromSeedIterator(ctx, it, 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.
-		for it.Next() {
-			for _, hit := range it.Value().Hits.Hits {
-				d := hit.Document.Document
-				seen.Set(d.ID(), d.FileType)
-			}
-		}
-		if err := it.Err(); err != nil {
-			log.Fatalf("Error iterating the index: %v\n", err)
-		}
-
-		crawler.CrawlGithub(ctx, crawlers, docConverter, indexFunc, seen)
-	case CrawlUser:
-		if *githubUserPtr == "" {
-			flag.Usage()
-			log.Fatalf("Please specify a github user with the github-user flag!")
-		}
-		crawlers := []crawler.Crawler{ghCrawlerConstructor(*githubUserPtr, "")}
-		crawler.CrawlGithub(ctx, crawlers, docConverter, indexFunc, seen)
-	case CrawlRepo:
-		if *githubRepoPtr == "" {
-			flag.Usage()
-			log.Fatalf("Please specify a github repository with the github-repo flag!")
-		}
-		crawlers := []crawler.Crawler{ghCrawlerConstructor("", *githubRepoPtr)}
-		crawler.CrawlGithub(ctx, crawlers, docConverter, indexFunc, seen)
-	case CrawlUnknown:
-		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/Dockerfile

@@ -1,14 +0,0 @@
-FROM golang:1.11 AS build
-
-ARG GO111MODULE=on
-
-WORKDIR /go/src/sigs.k8s.io/kustomize/api/internal/crawl
-COPY . /go/src/sigs.k8s.io/kustomize/api/internal/crawl
-
-RUN go mod download
-RUN CGO_ENABLED=0 go install ./cmd/kustomize_stats
-
-FROM scratch
-COPY --from=build /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/
-COPY --from=build /go/bin/kustomize_stats /
-ENTRYPOINT ["/kustomize_stats"]

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

@@ -1,249 +0,0 @@
-package main
-
-import (
-	"context"
-	"crypto/sha256"
-	"flag"
-	"fmt"
-	"log"
-	"sort"
-	"time"
-
-	"sigs.k8s.io/kustomize/api/internal/crawl/doc"
-
-	"sigs.k8s.io/kustomize/api/internal/crawl/index"
-)
-
-// iterateArr adds each item in arr into countMap.
-func iterateArr(arr []string, countMap map[string]int) {
-	for _, item := range arr {
-		if _, ok := countMap[item]; !ok {
-			countMap[item] = 1
-		} else {
-			countMap[item]++
-		}
-	}
-
-}
-
-// 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 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]] })
-	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,
-		`the number of kubernetes object kinds to be listed according to their popularities.
-By default, all the kinds will be listed.
-If you only want to list the 10 most popular kinds, set the flag to 10.`)
-	topIdentifiersPtr := flag.Int(
-		"identifiers", -1,
-		`the number of identifiers to be listed according to their popularities.
-By default, all the identifiers will be listed.
-If you only want to list the 10 most popular identifiers, set the flag to 10.`)
-	topKustomizeFeaturesPtr := flag.Int(
-		"kustomize-features", -1,
-		`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, *indexNamePtr)
-	if err != nil {
-		log.Fatalf("Could not create an index: %v\n", err)
-	}
-
-	// count tracks the number of documents in the index
-	count := 0
-
-	// kustomizationFilecount tracks the number of kustomization files in the index
-	kustomizationFilecount := 0
-
-	kindsMap := make(map[string]int)
-	identifiersMap := make(map[string]int)
-	kustomizeIdentifiersMap := make(map[string]int)
-
-	// 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 {
-				log.Printf("Found duplicate ID (%s)\n", hit.ID)
-			}
-
-			count++
-			iterateArr(hit.Document.Kinds, kindsMap)
-			iterateArr(hit.Document.Identifiers, identifiersMap)
-
-			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 {
-		log.Fatalf("Error iterating: %v\n", err)
-	}
-
-	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.
-%d kinds of kubernetes objects are customized:`, len(ids), count, len(kindsMap))
-	fmt.Printf("\n")
-
-	kindCount := 0
-	for _, key := range sortedKindsMapKeys {
-		if *topKindsPtr < 0 || (*topKindsPtr >= 0 && kindCount < *topKindsPtr) {
-			fmt.Printf("\tkind `%s` is customimzed in %d documents\n", key, kindsMap[key])
-			kindCount++
-		}
-	}
-
-	fmt.Printf("%d kinds of identifiers are found:\n", len(identifiersMap))
-	identifierCount := 0
-	for _, key := range sortedIdentifiersMapKeys {
-		if *topIdentifiersPtr < 0 || (*topIdentifiersPtr >= 0 && identifierCount < *topIdentifiersPtr) {
-			fmt.Printf("\tidentifier `%s` appears in %d documents\n", key, identifiersMap[key])
-			identifierCount++
-		}
-	}
-
-	fmt.Printf(`There are %d kustomization files in the kustomize index.
-%d kinds of kustomize features are found:`, kustomizationFilecount, len(kustomizeIdentifiersMap))
-	fmt.Printf("\n")
-	kustomizeFeatureCount := 0
-	for _, key := range sortedKustomizeIdentifiersMapKeys {
-		if *topKustomizeFeaturesPtr < 0 || (*topKustomizeFeaturesPtr >= 0 && kustomizeFeatureCount < *topKustomizeFeaturesPtr) {
-			fmt.Printf("\tfeature `%s` is used in %d documents\n", key, kustomizeIdentifiersMap[key])
-			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/README.md

@@ -1,8 +0,0 @@
-This binary takes as its input a json file including GKE logs (which can be
-[exported](https://cloud.google.com/logging/docs/export/configure_export_v2) into 
-[Cloud Storage](https://cloud.google.com/storage/docs/)), 
-and extracts the `textPayload` field of each log entry.
-
-Here is an log entry example:
-
-{"insertId":"1sxuh4jg5lw6w10","labels":{"compute.googleapis.com/resource_name":"gke-crawler2-default-pool-5e55ea05-gzgv","container.googleapis.com/namespace_name":"default","container.googleapis.com/pod_name":"kustomize-stats-5bczg","container.googleapis.com/stream":"stdout"},"logName":"projects/haiyanmeng-gke-dev/logs/kustomize-stats","receiveTimestamp":"2020-01-06T23:33:07.012831742Z","resource":{"labels":{"cluster_name":"crawler2","container_name":"kustomize-stats","instance_id":"8183086081854184383","namespace_id":"default","pod_id":"kustomize-stats-5bczg","project_id":"haiyanmeng-gke-dev","zone":"us-central1-a"},"type":"container"},"severity":"INFO","textPayload":"The kustomize index already exists\n","timestamp":"2020-01-06T23:32:46.628930547Z"}

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

@@ -1,7 +0,0 @@
-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

@@ -1,49 +0,0 @@
-package main
-
-import (
-	"bufio"
-	"encoding/json"
-	"fmt"
-	"log"
-	"os"
-)
-
-func main() {
-	if len(os.Args) != 2 {
-		log.Fatalf("The usage of the command is: \n\t%s <log-file.json>", os.Args[0])
-	}
-
-	file, err := os.Open(os.Args[1])
-	if err != nil {
-		log.Fatal(err)
-	}
-
-	closeFile := func(file *os.File) {
-		if err := file.Close(); err != nil {
-			log.Fatal(err)
-		}
-	}
-	defer closeFile(file)
-
-	scanner := bufio.NewScanner(file)
-	for scanner.Scan() {
-		line := scanner.Text()
-
-		var entry interface{}
-		if err := json.Unmarshal([]byte(line), &entry); err != nil {
-			log.Printf("failed to unmarshal a log entry: %s\n", line)
-		}
-
-		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)
-		}
-	}
-
-	if err := scanner.Err(); err != nil {
-		log.Fatal(err)
-	}
-}

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

@@ -1,5 +0,0 @@
-configmapGenerator:
-- name: elasticsearch-config
-  literals:
-  - es-url="http://esbasic-master:9200"
-  - plugin-index-name="plugin"

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

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

api/internal/crawl/config/crawler/base/github_api_secret.txt

@@ -1,2 +0,0 @@
-<ADD YOUR GITHUB PERSONAL ACCESS TOKEN HERE WITHOUT A TRAILING NEWLINE>
-Run: printf "<your-token>" > github_api_secret.txt

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

@@ -1,15 +0,0 @@
-resources:
-- ../../base
-
-configmapGenerator:
-- name: crawler-http-cache
-  literals:
-  - redis-cache-url="redis://redis-http-cache:6379"
-- name: redis-keystore
-  literals:
-  - keystore-url="redis://redis-docs-keystore:6379"
-
-secretGenerator:
-- name: github-access-token
-  files:
-  - token=github_api_secret.txt

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

@@ -1,34 +0,0 @@
-apiVersion: batch/v1beta1
-kind: CronJob
-metadata:
-  name: crawler-cronjob
-spec:
-  # run the cronjob at 00:00 every 7 days
-  schedule: "0 0 */7 * *"
-  jobTemplate:
-    spec:
-      template:
-        spec:
-          restartPolicy: OnFailure
-          containers:
-          - name: crawler
-            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
-              valueFrom:
-                secretKeyRef:
-                  name: github-access-token
-                  key: token
-            - name: ELASTICSEARCH_URL
-              valueFrom:
-                configMapKeyRef:
-                  name: elasticsearch-config
-                  key: es-url
-            - name: REDIS_URL
-              valueFrom:
-                configMapKeyRef:
-                  name: crawler-http-cache
-                  key: redis-cache-url

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

@@ -1,3 +0,0 @@
-resources:
-- ../base
-- cronjob.yaml

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

@@ -1,53 +0,0 @@
-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
-
-This is the default setting of the crawler job. The `command` and `args` field
-of the container should be:
-
-```
-        command: ["/crawler"]
-```
-
-Or
-
-```
-        command: ["/crawler"]
-        args: ["--mode=index+github"]
-```
-
-# Crawling all the documents in the index
-
-The `command` and `args` field of the container should be:
-
-```
-        command: ["/crawler"]
-        args: ["--mode=index"]
-```
-
-# Crawling all the kustomization files on Github
-
-The `command` and `args` field of the container should be:
-
-```
-        command: ["/crawler"]
-        args: ["--mode=github"]
-```
-
-# Crawling all the kustomization files in a Github repo
-
-The `command` and `args` field of the container should be like:
-
-```
-        command: ["/crawler"]
-        args: ["--mode=github-repo", "--github-repo=kubernetes-sigs/kustomize"]
-```
-
-# Crawling all the kustomization files in all the repositories of a Github user
-
-The `command` and `args` field of the container should be like:
-
-```
-        command: ["/crawler"]
-        args: ["--github-user", "--github-user=kubernetes-sigs"]
-```

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

@@ -1,35 +0,0 @@
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: crawler
-spec:
-  template:
-    spec:
-      restartPolicy: OnFailure
-      containers:
-      - name: crawler
-        image: gcr.io/haiyanmeng-gke-dev/crawler:v1
-        imagePullPolicy: Always
-        command: ["/crawler"]
-        args: ["--mode=github-repo", "--github-repo=kubernetes-sigs/kustomize", "--index=kustomize"]
-        env:
-        - name: GITHUB_ACCESS_TOKEN
-          valueFrom:
-            secretKeyRef:
-              name: github-access-token
-              key: token
-        - name: ELASTICSEARCH_URL
-          valueFrom:
-            configMapKeyRef:
-              name: elasticsearch-config
-              key: es-url
-        - name: REDIS_CACHE_URL
-          valueFrom:
-            configMapKeyRef:
-              name: crawler-http-cache
-              key: redis-cache-url
-        - name: REDIS_KEY_URL
-          valueFrom:
-            configMapKeyRef:
-              name: redis-keystore
-              key: keystore-url

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

@@ -1,3 +0,0 @@
-resources:
-- ../base
-- job.yaml

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

@@ -1,20 +0,0 @@
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: kustomize-stats
-spec:
-  template:
-    spec:
-      restartPolicy: OnFailure
-      containers:
-      - name: kustomize-stats
-        image: gcr.io/haiyanmeng-gke-dev/kustomize_stats:v1
-        imagePullPolicy: Always
-        command: ["/kustomize_stats"]
-        args: ["--index=kustomize", "--kinds=51", "--identifiers=50", "--kustomize-features=50"]
-        env:
-        - name: ELASTICSEARCH_URL
-          valueFrom:
-            configMapKeyRef:
-              name: elasticsearch-config
-              key: es-url

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

@@ -1,3 +0,0 @@
-resources:
-- ../base
-- job.yaml

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

@@ -1,23 +0,0 @@
-# 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

@@ -1,51 +0,0 @@
-# ESCluster is depended by ESBackup and ESRestore.
-apiVersion: elasticsearch.cloud.google.com/v1alpha1
-kind: ESCluster
-metadata:
-  name: esbasic
-spec:
-  plugin:
-   pluginList:
-    - 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
-  nodegroups:
-    - name: di
-      replicas: 2
-      data: true
-      ingest: true
-      config:
-        jvm:
-          - Djava.net.preferIPv4Stack=true
-          - Xms2g
-          - Xmx2g
-        es:
-          path.repo: '["/tmp/es_backup_basic"]'
-      affinity:
-        podAntiAffinity:
-          requiredDuringSchedulingIgnoredDuringExecution:
-          - topologyKey: kubernetes.io/hostname
-            labelSelector:
-              matchLabels:
-                es/nodegroup: di
-      resources:
-        requests:
-          memory: 3Gi
-        limits:
-          memory: 3Gi
-    - name: m
-      replicas: 2
-      master: true
-      config:
-        es:
-          path.repo: '["/tmp/es_backup_basic"]'

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

@@ -1,19 +0,0 @@
-# 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

@@ -1,23 +0,0 @@
-# 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/config/redis/document_keystore/kustomization.yaml

@@ -1,7 +0,0 @@
-resources:
-- redis.yaml
-- service.yaml
-
-commonLabels:
-  app: redis
-  tier: document-keystore

api/internal/crawl/config/redis/document_keystore/redis.yaml

@@ -1,37 +0,0 @@
-apiVersion: apps/v1
-kind: StatefulSet
-metadata:
-  name: redis-docs-keystore
-spec:
-  serviceName: "redis-docs-keystore"
-  template:
-    spec:
-      containers:
-      - name: redis
-        image: redis:5-alpine
-        imagePullPolicy: Always
-        args:
-          - "--save"
-          - "900"
-          - "1"
-          - "--save"
-          - "30"
-          - "100"
-          - "--appendonly"
-          - "yes"
-        ports:
-        - name: redis-docs-port
-          containerPort: 6379
-        volumeMounts:
-        - mountPath: /data
-          name: redis-docs-keystore-data
-      restartPolicy: Always
-  volumeClaimTemplates:
-  - metadata:
-      name: redis-docs-keystore-data
-    spec:
-      accessModes:
-      - ReadWriteOnce
-      resources:
-        requests:
-          storage: 4Gi

api/internal/crawl/config/redis/document_keystore/service.yaml

@@ -1,10 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: redis-docs-keystore
-spec:
-  clusterIP: None
-  ports:
-  - protocol: "TCP"
-    port: 6379
-    targetPort: redis-docs-port

api/internal/crawl/config/redis/http_cache/kustomization.yaml

@@ -1,7 +0,0 @@
-resources:
-- redis.yaml
-- service.yaml
-
-commonLabels:
-  app: redis
-  tier: http-cache

api/internal/crawl/config/redis/http_cache/redis.yaml

@@ -1,16 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: redis-http-cache
-spec:
-  template:
-    spec:
-      containers:
-      - name: redis
-        image: redis:5-alpine
-        imagePullPolicy: Always
-        # see redis.io/topics/lru-cache for other policy options.
-        args: ["--maxmemory", "1gb", "--maxmemory-policy", "allkeys-lru"]
-        ports:
-        - name: http-cache-port
-          containerPort: 6379

api/internal/crawl/config/redis/http_cache/service.yaml

@@ -1,10 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: redis-http-cache
-spec:
-  clusterIP: None
-  ports:
-  - protocol: "TCP"
-    port: 6379
-    targetPort: http-cache-port

api/internal/crawl/config/webapp/backend/deployment.yaml

@@ -1,35 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: kustomize-search
-spec:
-  selector:
-    matchLabels:
-      app: kustomize-search
-      tier: backend
-  replicas: 1
-  template:
-    metadata:
-      labels:
-        app: kustomize-search
-        tier: backend
-    spec:
-      containers:
-      - name: kustomize-search
-        image: gcr.io/kustomize-search/backend:latest
-        imagePullPolicy: Always
-        livenessProbe:
-          httpGet:
-            path: /liveness
-            port: backend-port
-        ports:
-        - name: backend-port
-          containerPort: 8080
-        env:
-        - name: ELASTICSEARCH_URL
-          valueFrom:
-            configMapKeyRef:
-              name: elasticsearch-config
-              key: es-url
-        - name: PORT
-          value: "8080"

api/internal/crawl/config/webapp/backend/kustomization.yaml

@@ -1,4 +0,0 @@
-resources:
-- ../../base
-- deployment.yaml
-- service.yaml

api/internal/crawl/config/webapp/backend/service.yaml

@@ -1,14 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: kustomize-search
-spec:
-  selector:
-    app: kustomize-search
-    tier: backend
-  ports:
-  - protocol: "TCP"
-    port: 80
-    targetPort: backend-port
-  type: LoadBalancer
-  loadBalancerIP: ""

api/internal/crawl/config/webapp/frontend/deployment.yaml

@@ -1,23 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: kustomize-search-ui
-spec:
-  selector:
-    matchLabels:
-      app: kustomize-search
-      tier: frontend
-  replicas: 1
-  template:
-    metadata:
-      labels:
-        app: kustomize-search
-        tier: frontend
-    spec:
-      containers:
-      - name: frontend
-        image: gcr.io/kustomize-search/frontend:latest
-        imagePullPolicy: Always
-        ports:
-        - name: frontend-port
-          containerPort: 80

api/internal/crawl/config/webapp/frontend/kustomization.yaml

@@ -1,4 +0,0 @@
-resources:
-- ../../base
-- deployment.yaml
-- service.yaml

api/internal/crawl/config/webapp/frontend/service.yaml

@@ -1,14 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: kustomize-search-ui
-spec:
-  selector:
-    app: kustomize-search
-    tier: frontend
-  ports:
-  - protocol: "TCP"
-    port: 80
-    targetPort: frontend-port
-  type: LoadBalancer
-  loadBalancerIP: ""

api/internal/crawl/crawler/crawler.go

@@ -1,365 +0,0 @@
-// Package crawler provides helper methods and defines an interface for lauching
-// source repository crawlers that retrieve files from a source and forwards
-// to a channel for indexing and retrieval.
-package crawler
-
-import (
-	"context"
-	"fmt"
-	"log"
-	"os"
-	"sync"
-
-	"sigs.k8s.io/kustomize/api/internal/crawl/utils"
-
-	"sigs.k8s.io/kustomize/api/internal/crawl/index"
-
-	_ "github.com/gomodule/redigo/redis"
-
-	"sigs.k8s.io/kustomize/api/internal/crawl/doc"
-)
-
-var (
-	logger = log.New(os.Stdout, "Crawler: ", log.LstdFlags|log.LUTC|log.Llongfile)
-)
-
-// Crawler forwards documents from source repositories to index and store them
-// for searching. Each crawler is responsible for querying it's source of
-// information, and forwarding files that have not been seen before or that need
-// updating.
-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, 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
-}
-
-type CrawledDocument interface {
-	ID() string
-	GetDocument() *doc.Document
-	// Get all the Documents directly referred in a Document.
-	// 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
-}
-
-type CrawlSeed []*doc.Document
-
-type IndexFunc func(CrawledDocument, index.Mode) error
-type Converter func(*doc.Document) (CrawledDocument, error)
-
-func logIfErr(err error) {
-	if err == nil {
-		return
-	}
-	logger.Println("error: ", err)
-}
-
-func findMatch(d *doc.Document, crawlers []Crawler) Crawler {
-	for _, crawl := range crawlers {
-		if crawl.Match(d) {
-			return crawl
-		}
-	}
-	return nil
-}
-
-func addBranches(cdoc CrawledDocument, match Crawler, indx IndexFunc,
-	seen utils.SeenMap, stack *CrawlSeed) {
-
-	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 doc(%s): %v",
-			cdoc.GetDocument().Path(), err)
-		return
-	}
-
-	deps, err := cdoc.GetResources(true, true, true)
-	if err != nil {
-		logger.Println(err)
-		return
-	}
-
-	for _, dep := range deps {
-		if seen.Seen(dep.ID()) && seen.Value(dep.ID()) == dep.FileType {
-			continue
-		}
-		*stack = append(*stack, dep)
-	}
-}
-
-func doCrawl(ctx context.Context, docsPtr *CrawlSeed, crawlers []Crawler, conv Converter, indx IndexFunc,
-	seen utils.SeenMap, stack *CrawlSeed, refreshDoc bool, updateFileType bool) {
-
-	UpdatedDocCount := 0
-	seenDocCount := 0
-	cachedDocCount := 0
-	findMatchErrCount := 0
-	FetchDocumentErrCount := 0
-	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 {
-		// get the last Document in (*docPtr), which will be crawled in this iteration.
-		tail := (*docsPtr)[len(*docsPtr)-1]
-
-		// remove the last Document in (*docPtr)
-		*docsPtr = (*docsPtr)[:(len(*docsPtr) - 1)]
-
-		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("doc(%s) is cached already", tail.Path())
-			cachedDocCount++
-			continue
-		}
-
-		match := findMatch(tail, crawlers)
-		if match == nil {
-			logIfErr(fmt.Errorf("%v could not match any crawler", tail))
-			findMatchErrCount++
-			continue
-		}
-
-		if tail.User == "" {
-			tail.User = doc.UserName(tail.RepositoryURL)
-		}
-
-		// 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 doc(%s): %v", tail.Path(), err)
-			convErrCount++
-		}
-
-		UpdatedDocCount++
-		addBranches(cdoc, match, indx, seen, stack)
-	}
-	logger.Printf("Summary of doCrawl:\n")
-	logger.Printf("\t%d documents were updated\n", UpdatedDocCount)
-	logger.Printf("\t%d documents were seen by the crawler already and skipped\n", seenDocCount)
-	logger.Printf("\t%d documents were cached already and skipped\n", cachedDocCount)
-	logger.Printf("\t%d documents didn't have a matching crawler and skipped\n", findMatchErrCount)
-	logger.Printf("\t%d documents cannot be fetched, %d out of them are deleted\n",
-		FetchDocumentErrCount, deleteDocCount)
-	logger.Printf("\t%d documents cannot update its creation time but still were inserted or updated in the index\n", SetCreatedErrCount)
-	logger.Printf("\t%d documents cannot be converted but still were inserted or updated in the index\n", convErrCount)
-}
-
-// CrawlFromSeedIterator iterates all the documents in the index and call CrawlFromSeed for each document.
-func CrawlFromSeedIterator(ctx context.Context, it *index.KustomizeIterator, crawlers []Crawler,
-	conv Converter, indx IndexFunc, seen utils.SeenMap) {
-	docCount := 0
-	for it.Next() {
-		for _, hit := range it.Value().Hits.Hits {
-			docCount++
-			logger.Printf("updating document %d from seed\n", docCount)
-
-			singleSeed := CrawlSeed{&(hit.Document.Document)}
-			CrawlFromSeed(ctx, singleSeed, crawlers, conv, indx, seen)
-		}
-	}
-	if err := it.Err(); err != nil {
-		log.Fatalf("Error iterating the index: %v\n", err)
-	}
-}
-
-// 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 utils.SeenMap) {
-
-	// stack tracks the documents directly referred in the seed.
-	stack := make(CrawlSeed, 0)
-
-	// each unique document in seed will be crawled once.
-	doCrawl(ctx, &seed, crawlers, conv, indx, seen, &stack, true, false)
-
-	logger.Printf("crawling %d new documents referred by doc\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, false, true)
-}
-
-// CrawlGithubRunner is a blocking function and only returns once all of the
-// crawlers are finished with execution.
-//
-// This function uses the output channel to forward kustomization documents
-// from a list of crawlers. The output is to be consumed by a database/search
-// indexer for later retrieval.
-//
-// The return value is an array of errors in which each index represents the
-// index of the crawler that emitted the error. Although the errors themselves
-// can be nil, the array will always be exactly the size of the crawlers array.
-//
-// CrawlGithubRunner takes in a seed, which represents the documents stored in an
-// index somewhere. The document data is not required to be populated. If there
-// are many documents, this is preferable. The order of iteration over the seed
-// is not guaranteed, but the CrawlGithub does guarantee that every element
-// from the seed will be processed before any other documents from the
-// crawlers.
-func CrawlGithubRunner(ctx context.Context, output chan<- CrawledDocument,
-	crawlers []Crawler, seen utils.SeenMap) []error {
-
-	errs := make([]error, len(crawlers))
-	wg := sync.WaitGroup{}
-
-	for i, crawler := range crawlers {
-		// Crawler implementations get their own channels to prevent a
-		// crawler from closing the main output channel.
-		docs := make(chan CrawledDocument)
-		wg.Add(2)
-
-		// Forward all of the documents from this crawler's channel to
-		// the main output channel.
-		go func(docs <-chan CrawledDocument) {
-			defer wg.Done()
-			for d := range docs {
-				output <- d
-			}
-		}(docs)
-
-		// Run this crawler and capture its returned error.
-		go func(idx int, crawler Crawler,
-			docs chan<- CrawledDocument) {
-
-			defer func() {
-				wg.Done()
-				if r := recover(); r != nil {
-					errs[idx] = fmt.Errorf(
-						"%+v panicked: %v, additional error %v",
-						crawler, r, errs[idx],
-					)
-				}
-			}()
-			defer close(docs)
-			errs[idx] = crawler.Crawl(ctx, docs, seen)
-		}(i, crawler, docs) // Copies the index and the crawler
-	}
-
-	wg.Wait()
-	return errs
-}
-
-// CrawlGithub crawls all the kustomization files on Github.
-func CrawlGithub(ctx context.Context, crawlers []Crawler, conv Converter,
-	indx IndexFunc, seen utils.SeenMap) {
-
-	// ch is channel where all the crawlers sends the crawled documents to.
-	ch := make(chan CrawledDocument, 1<<10)
-
-	wg := sync.WaitGroup{}
-
-	wg.Add(1)
-	go func() {
-		defer wg.Done()
-		docCount := 0
-		for cdoc := range ch {
-			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)
-			if match == nil {
-				logIfErr(fmt.Errorf(
-					"%v could not match any crawler", cdoc))
-				continue
-			}
-
-			// stack tracks the documents directly referred in the document.
-			stack := make(CrawlSeed, 0)
-
-			addBranches(cdoc, match, indx, seen, &stack)
-
-			if len(stack) > 0 {
-				// here the documents referred in a kustomization file are crawled separately,
-				// to avoid accumulating all the referred documents into a single gigantic
-				// mem-inentive stack.
-				logger.Printf("crawling the %d new documents referred in doc %d",
-					len(stack), docCount)
-				doCrawl(ctx, &stack, crawlers, conv, indx, seen, &stack, false, true)
-			}
-		}
-	}()
-
-	logger.Println("processing the documents found from crawling github")
-	if errs := CrawlGithubRunner(ctx, ch, crawlers, seen); errs != nil {
-		for _, err := range errs {
-			logIfErr(err)
-		}
-	}
-	close(ch)
-	wg.Wait()
-}

api/internal/crawl/crawler/crawler_test.go

@@ -1,343 +0,0 @@
-package crawler
-
-import (
-	"context"
-	"errors"
-	"fmt"
-	"log"
-	"reflect"
-	"sort"
-	"strings"
-	"sync"
-	"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"
-	"sigs.k8s.io/kustomize/api/konfig"
-)
-
-const (
-	kustomizeRepo = "https://github.com/kubernetes-sigs/kustomize"
-)
-
-// Simple crawler that forwards it's list of documents to a provided channel and
-// returns it's error to the caller.
-type testCrawler struct {
-	matchPrefix string
-	err         error
-	docs        []doc.KustomizationDocument
-	lukp        map[string]int
-}
-
-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
-		return nil
-	}
-	for _, suffix := range konfig.RecognizedKustomizationFileNames() {
-		savedFilePath := d.FilePath
-		d.FilePath += "/" + suffix
-		i, ok := c.lukp[d.ID()]
-		if !ok {
-			d.FilePath = savedFilePath
-			continue
-		}
-		d.DocumentData = c.docs[i].DocumentData
-		return nil
-	}
-	return fmt.Errorf("document %v does not exist for matcher: %s",
-		d, c.matchPrefix)
-}
-
-func (c testCrawler) SetCreated(_ context.Context, d *doc.Document) error {
-	d.CreationTime = &time.Time{}
-	return nil
-}
-
-func newCrawler(matchPrefix string, err error,
-	docs []doc.KustomizationDocument) testCrawler {
-	c := testCrawler{
-		matchPrefix: matchPrefix,
-		err:         err,
-		docs:        docs,
-		lukp:        make(map[string]int),
-	}
-	for i, d := range docs {
-		c.lukp[d.ID()] = i
-	}
-	return c
-}
-
-// Crawl implements the Crawler interface for testing.
-func (c testCrawler) Crawl(_ context.Context,
-	output chan<- CrawledDocument, _ utils.SeenMap) error {
-
-	for i, d := range c.docs {
-		isResource := true
-		for _, suffix := range konfig.RecognizedKustomizationFileNames() {
-			if strings.HasSuffix(d.FilePath, suffix) {
-				isResource = false
-				break
-			}
-		}
-		if isResource {
-			continue
-		}
-		output <- &c.docs[i]
-	}
-	return c.err
-}
-
-// Used to make sure that we're comparing documents in order. This is needed
-// since these documents will be sent concurrently.
-type sortableDocs []doc.KustomizationDocument
-
-func (s sortableDocs) Less(i, j int) bool {
-	return s[i].FilePath < s[j].FilePath
-}
-
-func (s sortableDocs) Swap(i, j int) {
-	s[i], s[j] = s[j], s[i]
-}
-
-func (s sortableDocs) Len() int {
-	return len(s)
-}
-
-func TestCrawlGithubRunner(t *testing.T) {
-	log.Println("testing CrawlGithubRunner")
-	tests := []struct {
-		tc   []Crawler
-		errs []error
-		docs sortableDocs
-	}{
-		{
-			tc: []Crawler{
-				testCrawler{
-					docs: []doc.KustomizationDocument{
-						{Document: doc.Document{
-							FilePath: "crawler1/doc1/kustomization.yaml",
-						}},
-						{Document: doc.Document{
-							FilePath: "crawler1/doc2/kustomization.yaml",
-						}},
-						{Document: doc.Document{
-							FilePath: "crawler1/doc3/kustomization.yaml",
-						}},
-					},
-				},
-				testCrawler{err: errors.New("crawler2")},
-				testCrawler{},
-				testCrawler{
-					docs: []doc.KustomizationDocument{
-						{Document: doc.Document{
-							FilePath: "crawler4/doc1/kustomization.yaml",
-						}},
-						{Document: doc.Document{
-							FilePath: "crawler4/doc2/kustomization.yaml",
-						}},
-					},
-					err: errors.New("crawler4"),
-				},
-			},
-			errs: []error{
-				nil,
-				errors.New("crawler2"),
-				nil,
-				errors.New("crawler4"),
-			},
-			docs: sortableDocs{
-				{Document: doc.Document{
-					FilePath: "crawler1/doc1/kustomization.yaml",
-				}},
-				{Document: doc.Document{
-					FilePath: "crawler1/doc2/kustomization.yaml",
-				}},
-				{Document: doc.Document{
-					FilePath: "crawler1/doc3/kustomization.yaml",
-				}},
-				{Document: doc.Document{
-					FilePath: "crawler4/doc1/kustomization.yaml",
-				}},
-				{Document: doc.Document{
-					FilePath: "crawler4/doc2/kustomization.yaml",
-				}},
-			},
-		},
-	}
-
-	for _, test := range tests {
-		output := make(chan CrawledDocument)
-		wg := sync.WaitGroup{}
-		wg.Add(1)
-
-		// Run the Crawler runner with a list of crawlers.
-		go func() {
-			defer close(output)
-			defer wg.Done()
-
-			seen := utils.NewSeenMap()
-			errs := CrawlGithubRunner(context.Background(),
-				output, test.tc, seen)
-
-			// Check that errors are returned as they should be.
-			if !reflect.DeepEqual(errs, test.errs) {
-				t.Errorf("Expected errs (%v) to equal (%v)",
-					errs, test.errs)
-			}
-
-		}()
-
-		// Iterate over the output channel of Crawler runner.
-		returned := make(sortableDocs, 0, len(test.docs))
-		for o := range output {
-			d, ok := o.(*doc.KustomizationDocument)
-			if !ok || d == nil {
-				t.Errorf("%T not expected type (%T)",
-					o, d)
-			}
-			returned = append(returned, *d)
-		}
-
-		// Check that all documents are received.
-		sort.Sort(returned)
-		if !reflect.DeepEqual(returned, test.docs) {
-			t.Errorf("Expected docs (%v) to equal (%v)\n",
-				returned, test.docs)
-		}
-
-		wg.Wait()
-	}
-}
-
-func TestCrawlFromSeed(t *testing.T) {
-	log.Println("testing CrawlFromSeed")
-
-	tests := []struct {
-		seed    CrawlSeed
-		matcher string
-		corpus  []doc.KustomizationDocument
-	}{
-		{
-			seed: CrawlSeed{
-				{
-					RepositoryURL: kustomizeRepo,
-					FilePath:      "examples/helloWorld/kustomization.yaml",
-				},
-				{
-					RepositoryURL: kustomizeRepo,
-					FilePath:      "examples/other/kustomization.yaml",
-				},
-			},
-			matcher: kustomizeRepo,
-			corpus: []doc.KustomizationDocument{
-				// Visited from the seed, will be ignored in the crawl.
-				{Document: doc.Document{
-					RepositoryURL: kustomizeRepo,
-					FilePath:      "examples/helloWorld/kustomization.yaml",
-					DocumentData: `
-resources:
-- deployment.yaml
-`,
-				}},
-				// Also visited from the seed as a relative resource.
-				{Document: doc.Document{
-					RepositoryURL: kustomizeRepo,
-					FilePath:      "examples/helloWorld/deployment.yaml",
-					DocumentData: `
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: hello
-`,
-				}},
-				// Visited from the seed. Has a remote import.
-				{Document: doc.Document{
-					RepositoryURL: kustomizeRepo,
-					FilePath:      "examples/other/kustomization.yaml",
-					DocumentData: `
-resources:
-- https://github.com/kubernetes-sigs/kustomize/examples/other/overlay
-- service.yaml
-`,
-				}},
-				// Imported as a base from the seed.
-				{Document: doc.Document{
-					RepositoryURL: kustomizeRepo,
-					FilePath:      "examples/other/overlay/kustomization.yaml",
-					DocumentData: `
-resources:
-- https://github.com/kubernetes-sigs/kustomize/examples/seedcrawl1
-- https://github.com/kubernetes-sigs/kustomize/examples/seedcrawl2
-`,
-				}},
-				// Imported as a resource from the seed.
-				{Document: doc.Document{
-					RepositoryURL: kustomizeRepo,
-					FilePath:      "examples/other/service.yaml",
-				}},
-				// Visited from crawling seed.
-				{Document: doc.Document{
-					RepositoryURL: kustomizeRepo,
-					FilePath:      "examples/seedcrawl1/kustomization.yml",
-				}},
-				// Visited from crawling seed.
-				{Document: doc.Document{
-					RepositoryURL: kustomizeRepo,
-					FilePath:      "examples/seedcrawl2/kustomization.yaml",
-					DocumentData: `
-resources:
-- ../base
-- job.yaml
-`,
-				}},
-				// Visited from crawling seed.
-				{Document: doc.Document{
-					RepositoryURL: kustomizeRepo,
-					FilePath:      "examples/base/kustomization.yml",
-				}},
-				// Visited from crawling seed imported as resource.
-				{Document: doc.Document{
-					RepositoryURL: kustomizeRepo,
-					FilePath:      "examples/seedcrawl2/job.yaml",
-				}},
-			},
-		},
-	}
-
-	for _, tc := range tests {
-		cr := newCrawler(tc.matcher, nil, tc.corpus)
-		visited := make(map[string]int)
-		CrawlFromSeed(context.Background(), tc.seed, []Crawler{cr},
-			func(d *doc.Document) (CrawledDocument, error) {
-				return &doc.KustomizationDocument{
-					Document: *d,
-				}, nil
-			},
-			func(d CrawledDocument, mode index.Mode) error {
-				visited[d.ID()]++
-				return nil
-			},
-			utils.NewSeenMap(),
-		)
-		if lv, lc := len(visited), len(tc.corpus); lv != lc {
-			t.Errorf("error: %d of %d documents visited.", lv, lc)
-			t.Errorf("\nvisited (%v)\nexpected (%v).", visited, cr.lukp)
-		}
-		for id, cnt := range visited {
-			if cnt != 1 {
-				t.Errorf("%s not visited once (%d)", id, cnt)
-			}
-		}
-	}
-}

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

@@ -1,768 +0,0 @@
-// Package github implements the crawler.Crawler interface, getting data
-// from the Github search API.
-package github
-
-import (
-	"context"
-	"encoding/json"
-	"fmt"
-	"io/ioutil"
-	"log"
-	"math"
-	"net/http"
-	"os"
-	"regexp"
-	"strconv"
-	"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"
-	"sigs.k8s.io/kustomize/api/internal/git"
-	"sigs.k8s.io/kustomize/api/konfig"
-)
-
-var logger = log.New(os.Stdout, "Github Crawler: ",
-	log.LstdFlags|log.LUTC|log.Llongfile)
-
-// Implements crawler.Crawler.
-type githubCrawler struct {
-	client GhClient
-	query  Query
-	// branchMap maps github repositories to their default branches
-	branchMap map[string]string
-}
-
-type GhClient struct {
-	RequestConfig
-	retryCount  uint64
-	client      *http.Client
-	accessToken string
-}
-
-func NewCrawler(accessToken string, retryCount uint64, client *http.Client,
-	query Query) githubCrawler {
-
-	return githubCrawler{
-		client: GhClient{
-			retryCount: retryCount,
-			client:     client,
-			RequestConfig: RequestConfig{
-				perPage: githubMaxPageSize,
-			},
-			accessToken: accessToken,
-		},
-		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, seen utils.SeenMap) error {
-
-	ranges := []RangeWithin{
-		{
-			start: uint64(0),
-			end:   githubMaxFileSize,
-		},
-	}
-
-	errs := make(multiError, 0)
-	for len(ranges) > 0 {
-		logger.Printf("Current ranges: %v (len: %d)\n", ranges, len(ranges))
-		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,
-		client:        &http.Client{Timeout: gc.client.client.Timeout},
-		retryCount:    gc.client.retryCount,
-		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.
-	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 reProcessQueryRanges, fmt.Errorf("could not split %v into ranges, %v\n",
-			gc.query, err)
-	}
-
-	logger.Println("ranges: ", ranges)
-
-	// Query each range for files.
-	errs := make(multiError, 0)
-	queryResult := RangeQueryResult{}
-	for _, query := range ranges {
-		reProcessQuery, rangeResult, err := processQuery(ctx, gc.client, query, output, seen, gc.branchMap)
-		if err != nil {
-			errs = append(errs, err)
-		}
-		queryResult.Add(rangeResult)
-		if reProcessQuery {
-			// if the size of a range is 0, such as [245, 245], and reProcessQuery is true,
-			// it means that there are more than 1000 results for the query range.
-			// Reprocessing the query range will not help because the GitHub Search API
-			// only provides up to 1,000 results for each search.
-			if RangeSizes(query).Size() == 0 {
-				logger.Printf("range size is 0 includes more than 1000 results: %s", query)
-			} else {
-				reProcessQueryRanges = append(reProcessQueryRanges, RangeSizes(query))
-			}
-		}
-	}
-
-	logger.Printf("Summary of Crawl: %s", queryResult.String())
-
-	if len(errs) > 0 {
-		return reProcessQueryRanges, errs
-	}
-
-	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 {
-	repoURL := d.RepositoryURL + "/" + d.FilePath + "?ref=" + d.DefaultBranch
-	repoSpec, err := git.NewRepoSpecFromUrl(repoURL)
-	if err != nil {
-		return fmt.Errorf("invalid repospec: %v", err)
-	}
-
-	url := "https://raw.githubusercontent.com/" + repoSpec.OrgRepo +
-		"/" + repoSpec.Ref + "/" + repoSpec.Path
-
-	handle := func(resp *http.Response, err error, path string) error {
-		if resp == nil {
-			return fmt.Errorf("empty http response (url: %s; path: %s), error: %v",
-				url, path, err)
-		}
-		if err == nil && resp.StatusCode == http.StatusOK {
-			d.IsSame = httpclient.FromCache(resp.Header)
-			defer CloseResponseBody(resp)
-			data, err := ioutil.ReadAll(resp.Body)
-			if err != nil {
-				return err
-			}
-			d.DocumentData = string(data)
-			d.FilePath = d.FilePath + path
-			return nil
-		}
-
-		return err
-	}
-	resp, errGetRawUserContent := gc.client.GetRawUserContent(url)
-	if err := handle(resp, errGetRawUserContent, ""); err == nil {
-		return nil
-	}
-
-	for _, file := range konfig.RecognizedKustomizationFileNames() {
-		resp, errGetRawUserContent = gc.client.GetRawUserContent(url + "/" + file)
-		if err = handle(resp, errGetRawUserContent, "/"+file); err == nil {
-			return nil
-		}
-	}
-	return fmt.Errorf("file not found: %s, error: %v", url, err)
-}
-
-func (gc githubCrawler) SetCreated(_ context.Context, d *doc.Document) error {
-	fs := GhFileSpec{
-		Path: d.FilePath,
-		Repository: GitRepository{
-			FullName: d.RepositoryFullName(),
-		},
-	}
-	creationTime, err := gc.client.GetFileCreationTime(fs)
-	if err != nil {
-		return err
-	}
-	d.CreationTime = &creationTime
-	return nil
-}
-
-func (gc githubCrawler) Match(d *doc.Document) bool {
-	url := d.RepositoryURL + "/" + d.FilePath + "?ref=" + "/" +
-		d.DefaultBranch
-	repoSpec, err := git.NewRepoSpecFromUrl(url)
-	if err != nil {
-		return false
-	}
-
-	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, seen utils.SeenMap,
-	branchMap map[string]string) (bool, RangeQueryResult, error) {
-
-	queryPages := make(chan GhResponseInfo)
-
-	go func() {
-		// Forward the document metadata to the retrieval channel.
-		// This separation allows for concurrent requests for the code
-		// search, and the retrieval portions of the API.
-		err := gcl.ForwardPaginatedQuery(ctx, query, queryPages)
-		if err != nil {
-			// TODO(damienr74) handle this error with redis?
-			logger.Println(err)
-		}
-		close(queryPages)
-	}()
-
-	reProcessQuery := false
-
-	errs := make(multiError, 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, seen, branchMap)
-			if err != nil {
-				logger.Printf("kustomizationResultAdapter failed: %v", err)
-				errs = append(errs, err)
-				pageResult.errorCnt++
-			}
-			if k != nil {
-				pageResult.newDocCnt++
-				output <- k
-			} else {
-				pageResult.seenDocCnt++
-			}
-			pageResult.totalDocCnt++
-		}
-
-		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
-		}
-	}
-
-	logger.Printf("Summary of processQuery: %s", result.String())
-
-	return reProcessQuery, result, errs
-}
-
-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, 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)
-	if err != nil {
-		logger.Printf("GetFileCreationTime failed: %v", err)
-		return &d, err
-	}
-	d.CreationTime = &creationTime
-
-	if err := d.ParseYAML(); err != nil {
-		logger.Printf("ParseYAML failed: %v", err)
-		return &d, err
-	}
-
-	return &d, nil
-}
-
-// ForwardPaginatedQuery follows the links to the next pages and performs all of
-// the queries for a given search query, relaying the data from each request
-// back to an output channel.
-func (gcl GhClient) ForwardPaginatedQuery(ctx context.Context, query string,
-	output chan<- GhResponseInfo) error {
-
-	logger.Println("querying: ", query)
-	response := gcl.parseGithubResponseWithRetry(query)
-
-	if response.Error != nil {
-		return response.Error
-	}
-
-	output <- response
-
-	for response.LastURL != "" && response.NextURL != "" {
-		select {
-		case <-ctx.Done():
-			return nil
-		default:
-			response = gcl.parseGithubResponseWithRetry(response.NextURL)
-			if response.Error != nil {
-				return response.Error
-			}
-
-			output <- response
-		}
-	}
-
-	return nil
-}
-
-// GetFileData gets the bytes from a file.
-func (gcl GhClient) GetFileData(k GhFileSpec) ([]byte, error) {
-
-	url := gcl.ContentsRequest(k.Repository.FullName, k.Path)
-
-	resp, err := gcl.GetReposData(url)
-	if err != nil {
-		return nil, fmt.Errorf("%+v: could not get '%s' metadata: %v",
-			k, url, err)
-	}
-
-	data, err := ioutil.ReadAll(resp.Body)
-	if err != nil {
-		return nil, fmt.Errorf("%+v: could not read '%s' metadata: %v",
-			k, url, err)
-	}
-
-	if err := resp.Body.Close(); err != nil {
-		return nil, err
-	}
-
-	type githubContentRawURL struct {
-		DownloadURL string `json:"download_url,omitempty"`
-	}
-	var rawURL githubContentRawURL
-	err = json.Unmarshal(data, &rawURL)
-	if err != nil {
-		return nil, fmt.Errorf(
-			"%+v: could not get 'download_url' from '%s' response: %v",
-			k, data, err)
-	}
-
-	resp, err = gcl.GetRawUserContent(rawURL.DownloadURL)
-	if err != nil {
-		return nil, fmt.Errorf("%+v: could not fetch file raw data '%s': %v",
-			k, rawURL.DownloadURL, err)
-	}
-
-	defer CloseResponseBody(resp)
-	data, err = ioutil.ReadAll(resp.Body)
-	return data, err
-}
-
-func CloseResponseBody(resp *http.Response) {
-	if err := resp.Body.Close(); err != nil {
-		log.Printf("failed to close response body: %v", err)
-	}
-}
-
-// 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(
-			"'%s' could not get default_branch: %v", url, err)
-	}
-	defer CloseResponseBody(resp)
-	data, err := ioutil.ReadAll(resp.Body)
-	if err != nil {
-		return "", fmt.Errorf(
-			"could not read default_branch: %v", err)
-	}
-
-	type defaultBranch struct {
-		DefaultBranch string `json:"default_branch,omitempty"`
-	}
-	var branch defaultBranch
-	err = json.Unmarshal(data, &branch)
-	if err != nil {
-		return "", fmt.Errorf(
-			"default_branch json malformed: %v", err)
-	}
-
-	return branch.DefaultBranch, nil
-}
-
-// GetFileCreationTime gets the earliest date of a file.
-func (gcl GhClient) GetFileCreationTime(
-	k GhFileSpec) (time.Time, error) {
-
-	url := gcl.CommitsRequest(k.Repository.FullName, k.Path)
-
-	defaultTime := time.Now()
-
-	resp, err := gcl.GetReposData(url)
-	if err != nil {
-		return defaultTime, fmt.Errorf(
-			"%+v: '%s' could not get metadata: %v", k, url, err)
-	}
-
-	type DateSpec struct {
-		Commit struct {
-			Author struct {
-				Date string `json:"date,omitempty"`
-			} `json:"author,omitempty"`
-		} `json:"commit,omitempty"`
-	}
-
-	_, lastURL := parseGithubLinkFormat(resp.Header.Get("link"))
-	if lastURL != "" {
-		resp, err = gcl.GetReposData(lastURL)
-		if err != nil {
-			return defaultTime, fmt.Errorf(
-				"%+v: '%s' could not get metadata: %v",
-				k, lastURL, err)
-		}
-	}
-
-	defer CloseResponseBody(resp)
-	data, err := ioutil.ReadAll(resp.Body)
-	if err != nil {
-		return defaultTime, fmt.Errorf(
-			"%+v: failed to read metadata: %v", k, err)
-	}
-	var earliestDate []DateSpec
-	err = json.Unmarshal(data, &earliestDate)
-	size := len(earliestDate)
-	if err != nil || size == 0 {
-		return defaultTime, fmt.Errorf(
-			"%+v: server response '%s' not in expected format: %v",
-			k, data, err)
-	}
-
-	return time.Parse(time.RFC3339, earliestDate[size-1].Commit.Author.Date)
-}
-
-// TODO(damienr74) change the tickers to actually check api rate limits, reset
-// times, and throttle requests dynamically based off of current utilization,
-// instead of hardcoding the documented values, these calls are not quota'd.
-// This is now especially important, since caching the API requests will reduce
-// API quota use (so we can actually make more requests in the allotted time
-// period).
-//
-// See https://developer.github.com/v3/rate_limit/ for details.
-var (
-	searchRateTicker  = time.NewTicker(time.Second * 2)
-	contentRateTicker = time.NewTicker(time.Second * 1)
-)
-
-func throttleSearchAPI() {
-	<-searchRateTicker.C
-}
-
-func throttleRepoAPI() {
-	<-contentRateTicker.C
-}
-
-type multiError []error
-
-func (e multiError) Error() string {
-	size := len(e) + 2
-	strs := make([]string, size)
-	strs[0] = "Errors ["
-	for i, err := range e {
-		strs[i+1] = "\t" + err.Error()
-	}
-	strs[size-1] = "]"
-	return strings.Join(strs, "\n")
-}
-
-type GitRepository struct {
-	API      string `json:"url,omitempty"`
-	URL      string `json:"html_url,omitempty"`
-	FullName string `json:"full_name,omitempty"`
-}
-
-type GhFileSpec struct {
-	Path       string        `json:"path,omitempty"`
-	Repository GitRepository `json:"repository,omitempty"`
-}
-
-type githubResponse struct {
-	// MaxUint is reserved as a sentinel value.
-	// 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"`
-}
-
-type GhResponseInfo struct {
-	*http.Response
-	Parsed  *githubResponse
-	Error   error
-	NextURL string
-	LastURL string
-}
-
-func parseGithubLinkFormat(links string) (string, string) {
-	const (
-		linkNext    = "next"
-		linkLast    = "last"
-		linkInfoURL = 1
-		linkInfoRel = 2
-	)
-
-	next, last := "", ""
-	linkInfo := regexp.MustCompile(`<(.*)>.*; rel="(last|next)"`)
-
-	for _, link := range strings.Split(links, ",") {
-		linkParse := linkInfo.FindStringSubmatch(link)
-		if len(linkParse) != 3 {
-			continue
-		}
-
-		url := linkParse[linkInfoURL]
-		switch linkParse[linkInfoRel] {
-		case linkNext:
-			next = url
-		case linkLast:
-			last = url
-		default:
-		}
-	}
-
-	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{
-		Response: resp,
-		Error:    err,
-		Parsed:   nil,
-	}
-
-	if err != nil || resp == nil {
-		return requestInfo
-	}
-
-	var data []byte
-	defer CloseResponseBody(resp)
-	data, requestInfo.Error = ioutil.ReadAll(resp.Body)
-	if requestInfo.Error != nil {
-		return requestInfo
-	}
-
-	if resp.StatusCode != http.StatusOK {
-		logger.Println("query: ", getRequest)
-		logger.Println("status not OK at the source")
-		logger.Println("header dump", resp.Header)
-		logger.Println("body dump", string(data))
-		requestInfo.Error = fmt.Errorf("request rejected, status '%s'",
-			resp.Status)
-		return requestInfo
-	}
-
-	requestInfo.NextURL, requestInfo.LastURL =
-		parseGithubLinkFormat(resp.Header.Get("link"))
-
-	resultCount := githubResponse{
-		TotalCount: math.MaxUint64,
-	}
-	requestInfo.Error = json.Unmarshal(data, &resultCount)
-	if requestInfo.Error != nil {
-		return requestInfo
-	}
-
-	requestInfo.Parsed = &resultCount
-
-	return requestInfo
-
-}
-
-// SearchGithubAPI performs a search query and handles rate limitting for
-// the 'search/code?' endpoint as well as timed retries in the case of abuse
-// prevention.
-func (gcl GhClient) SearchGithubAPI(query string) (*http.Response, error) {
-	throttleSearchAPI()
-	return gcl.getWithRetry(query)
-}
-
-// GetReposData performs a search query and handles rate limitting for
-// the '/repos' endpoint as well as timed retries in the case of abuse
-// prevention.
-func (gcl GhClient) GetReposData(query string) (*http.Response, error) {
-	throttleRepoAPI()
-	return gcl.getWithRetry(query)
-}
-
-// User content (file contents) is not API rate limited, so there's no use in
-// throttling this call.
-func (gcl GhClient) GetRawUserContent(query string) (*http.Response, error) {
-	return gcl.getWithRetry(query)
-}
-
-func (gcl GhClient) Do(query string) (*http.Response, error) {
-	req, err := http.NewRequest("GET", query, nil)
-	if err != nil {
-		return nil, err
-	}
-	req.Header.Add("Authorization", fmt.Sprintf("token %s", gcl.accessToken))
-
-	// 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)
-	if resp != nil && resp.StatusCode != http.StatusOK {
-		err = fmt.Errorf("GhClient.Do(%s) failed with response code: %d",
-			query, resp.StatusCode)
-	}
-	return resp, err
-}
-
-func (gcl GhClient) getWithRetry(
-	query string) (resp *http.Response, err error) {
-
-	resp, err = gcl.Do(query)
-
-	retryCount := gcl.retryCount
-
-	for resp != nil && resp.StatusCode == http.StatusForbidden && retryCount > 0 {
-		retryTime := resp.Header.Get("Retry-After")
-		i, errAtoi := strconv.Atoi(retryTime)
-		if errAtoi != nil {
-			return resp, fmt.Errorf(
-				"query '%s' forbidden without 'Retry-After'", query)
-		}
-		logger.Printf(
-			"status forbidden, retring %d more times\n", retryCount)
-
-		logger.Printf("waiting %d seconds before retrying\n", i)
-		time.Sleep(time.Second * time.Duration(i))
-		retryCount--
-		resp, err = gcl.Do(query)
-	}
-
-	if err != nil {
-		return resp, fmt.Errorf("query '%s' could not be processed, %v",
-			query, err)
-	}
-
-	return resp, err
-}

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

@@ -1,231 +0,0 @@
-package github
-
-import (
-	"fmt"
-	"net/url"
-	"strings"
-)
-
-const (
-	perPageArg = "per_page"
-)
-
-const githubMaxPageSize = 100
-
-// Implementation detail, not important to external API.
-type queryField struct {
-	name  string
-	value interface{}
-}
-
-// Formats a query field.
-func (qf queryField) String() string {
-	var value string
-	switch v := qf.value.(type) {
-	case string:
-		value = v
-	case rangeFormatter:
-		value = v.RangeString()
-	default:
-		value = fmt.Sprint(v)
-	}
-
-	if qf.name == "" {
-		return value
-	}
-	return fmt.Sprint(qf.name, ":", value)
-}
-
-// Example of formating a query:
-// QueryWith(
-//	Filename("kustomization.yaml"),
-//	Filesize(RangeWithin{64, 192}),
-//	Keyword("copyright"),
-//	Keyword("2019"),
-// ).String()
-//
-// Outputs "q=filename:kustomization.yaml+size:64..192+copyright+2018" which
-// would search for files that have [64, 192] bytes (inclusive range) and that
-// contain the keywords 'copyright' and '2019' somewhere in the file.
-type Query []queryField
-
-func QueryWith(qfs ...queryField) Query {
-	return qfs
-}
-
-func (q Query) String() string {
-	strs := make([]string, 0, len(q))
-	for _, elem := range q {
-		str := elem.String()
-		if str == "" {
-			continue
-		}
-		strs = append(strs, str)
-	}
-
-	query := strings.Join(strs, "+")
-	if query == "" {
-		return query
-	}
-	return "q=" + query
-}
-
-// Keyword takes a single word, and formats it according to the Github API.
-func Keyword(k string) queryField {
-	return queryField{value: k}
-}
-
-// Filesize takes a rangeFormatter and formats it according to the Github API.
-func Filesize(r rangeFormatter) queryField {
-	return queryField{name: "size", value: r}
-}
-
-// Filename takes a filename and formats it according to the Github API.
-func Filename(f string) queryField {
-	return queryField{name: "filename", value: f}
-}
-
-// Path takes a filepath and formats it according to the Github API.
-func Path(p string) queryField {
-	return queryField{name: "path", value: p}
-}
-
-// Repo takes a repository (i.e., kubernetes-sigs/kustomize) and formats
-// it according to the Github API.
-func Repo(r string) queryField {
-	return queryField{name: "repo", value: r}
-}
-
-// Path takes a github username and formats it according to the Github API.
-func User(u string) queryField {
-	return queryField{name: "user", value: u}
-}
-
-// RequestConfig stores common variables that must be present for the queries.
-// - CodeSearchRequests: ask Github to check the code indices given a query.
-// - ContentsRequests: ask Github where to download a resource given a repo and a
-// file path.
-// - CommitsRequests: asks Github to list commits made one a file. Useful to
-// determine the date of a file.
-type RequestConfig struct {
-	perPage uint64
-}
-
-// CodeSearchRequestWith given a list of query parameters that specify the
-// (patial) query, returns a request object with the (parital) query. Must call
-// the URL method to get the string value of the URL. See request.CopyWith, to
-// understand why the request object is useful.
-func (rc RequestConfig) CodeSearchRequestWith(query Query) request {
-	vals := url.Values{
-		"sort":  []string{"indexed"},
-		"order": []string{"desc"},
-	}
-	req := rc.makeRequest("search/code", query, vals)
-	return req
-}
-
-// ContentsRequest given the repo name, and the filepath returns a formatted
-// query for the Github API to find the dowload information of this filepath.
-func (rc RequestConfig) ContentsRequest(fullRepoName, path string) string {
-	uri := fmt.Sprintf("repos/%s/contents/%s", fullRepoName, path)
-	return rc.makeRequest(uri, Query{}, url.Values{}).URL()
-}
-
-func (rc RequestConfig) ReposRequest(fullRepoName string) string {
-	uri := fmt.Sprintf("repos/%s", fullRepoName)
-	return rc.makeRequest(uri, Query{}, url.Values{}).URL()
-}
-
-// CommitsRequest given the repo name, and a filepath returns a formatted query
-// for the Github API to find the commits that affect this file.
-func (rc RequestConfig) CommitsRequest(fullRepoName, path string) string {
-	uri := fmt.Sprintf("repos/%s/commits", fullRepoName)
-	vals := url.Values{
-		"path": []string{path},
-	}
-	return rc.makeRequest(uri, Query{}, vals).URL()
-}
-
-func (rc RequestConfig) makeRequest(path string, query Query, vals url.Values) request {
-	vals.Set(perPageArg, fmt.Sprint(rc.perPage))
-
-	return request{
-		url: url.URL{
-			Scheme: "https",
-			Host:   "api.github.com",
-			Path:   path,
-		},
-		vals:  vals,
-		query: query,
-	}
-}
-
-type request struct {
-	url   url.URL
-	vals  url.Values
-	query Query
-}
-
-// 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
-	cpy.query = append(cpy.query, queryParams...)
-	return cpy
-}
-
-// URL encodes the variables and the URL representation into a string.
-func (r request) URL() string {
-	// Github does not handle URL encoding properly in its API for the
-	// q='...', so the query parameter is added without any encoding
-	// manually.
-	encoded := r.vals.Encode()
-	query := r.query.String()
-	sep := "&"
-	if query == "" {
-		sep = ""
-	}
-	if encoded == "" && query != "" {
-		sep = "?"
-	}
-	r.url.RawQuery = query + sep + encoded
-	return r.url.String()
-}
-
-// Allows to define a range of numbers and print it in the github range
-// query format https://help.github.com/en/articles/understanding-the-search-syntax.
-type rangeFormatter interface {
-	RangeString() string
-}
-
-// RangeLessThan is a range of values strictly less than (<) size.
-type RangeLessThan struct {
-	size uint64
-}
-
-func (r RangeLessThan) RangeString() string {
-	return fmt.Sprintf("<%d", r.size)
-}
-
-// RangeLessThan is a range of values strictly greater than (>) size.
-type RangeGreaterThan struct {
-	size uint64
-}
-
-func (r RangeGreaterThan) RangeString() string {
-	return fmt.Sprintf(">%d", r.size)
-}
-
-// RangeWithin is an inclusive range from start to end.
-type RangeWithin struct {
-	start uint64
-	end   uint64
-}
-
-func (r RangeWithin) RangeString() string {
-	return fmt.Sprintf("%d..%d", r.start, r.end)
-}
-
-func (r RangeWithin) Size() uint64 {
-	return r.end - r.start
-}

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

@@ -1,140 +0,0 @@
-package github
-
-import (
-	"testing"
-)
-
-func TestQueryFields(t *testing.T) {
-	testCases := []struct {
-		formatter queryField
-		expected  string
-	}{
-		{
-			formatter: Keyword("keyword"),
-			expected:  "keyword",
-		},
-		{
-			formatter: Filesize(RangeLessThan{23}),
-			expected:  "size:<23",
-		},
-		{
-			formatter: Filesize(RangeWithin{24, 64}),
-			expected:  "size:24..64",
-		},
-		{
-			formatter: Filesize(RangeGreaterThan{64}),
-			expected:  "size:>64",
-		},
-		{
-			formatter: Path("some/path/to/file"),
-			expected:  "path:some/path/to/file",
-		},
-		{
-			formatter: Filename("kustomization.yaml"),
-			expected:  "filename:kustomization.yaml",
-		},
-	}
-
-	for _, test := range testCases {
-		if result := test.formatter.String(); result != test.expected {
-			t.Errorf("got (%#v = %s), expected %s", test.formatter, result, test.expected)
-		}
-	}
-}
-
-func TestQueryType(t *testing.T) {
-	testCases := []struct {
-		query    Query
-		expected string
-	}{
-		{
-			query: QueryWith(
-				Filesize(RangeWithin{24, 64}),
-				Filename("kustomization.yaml"),
-				Keyword("keyword1"),
-				Keyword("keyword2"),
-				Repo("user1/repo1"),
-				User("user1"),
-			),
-			expected: "q=size:24..64+filename:kustomization.yaml+keyword1+keyword2+" +
-				"repo:user1/repo1+user:user1",
-		},
-	}
-
-	for _, test := range testCases {
-		if queryStr := test.query.String(); queryStr != test.expected {
-			t.Errorf("got (%#v = %s), expected %s", test.query, queryStr, test.expected)
-		}
-
-	}
-}
-
-func TestGithubSearchQuery(t *testing.T) {
-	const (
-		perPage = 100
-	)
-
-	testCases := []struct {
-		rc                    RequestConfig
-		codeQuery             Query
-		fullRepoName          string
-		path                  string
-		expectedCodeQuery     string
-		expectedContentsQuery string
-		expectedCommitsQuery  string
-	}{
-		{
-			rc: RequestConfig{
-				perPage: perPage,
-			},
-			codeQuery: Query{
-				Filename("kustomization.yaml"),
-				Filesize(RangeWithin{64, 128}),
-			},
-			fullRepoName: "kubernetes-sigs/kustomize",
-			path:         "examples/helloWorld/kustomization.yaml",
-
-			expectedCodeQuery: "https://api.github.com/search/code?" +
-				"q=filename:kustomization.yaml+size:64..128&order=desc&per_page=100&sort=indexed",
-
-			expectedContentsQuery: "https://api.github.com/repos/kubernetes-sigs/kustomize/contents/" +
-				"examples/helloWorld/kustomization.yaml?per_page=100",
-
-			expectedCommitsQuery: "https://api.github.com/repos/kubernetes-sigs/kustomize/commits?" +
-				"path=examples%2FhelloWorld%2Fkustomization.yaml&per_page=100",
-		},
-		{
-			rc: RequestConfig{
-				perPage: perPage,
-			},
-			codeQuery: Query{
-				Filename("kustomization.yaml"),
-				Filesize(RangeWithin{64, 128}),
-			},
-			fullRepoName: "kubernetes-sigs/kustomize",
-			path:         "examples 1/helloWorld/kustomization.yaml",
-
-			expectedCodeQuery: "https://api.github.com/search/code?" +
-				"q=filename:kustomization.yaml+size:64..128&order=desc&per_page=100&sort=indexed",
-
-			expectedContentsQuery: "https://api.github.com/repos/kubernetes-sigs/kustomize/contents/" +
-				"examples%201/helloWorld/kustomization.yaml?per_page=100",
-
-			expectedCommitsQuery: "https://api.github.com/repos/kubernetes-sigs/kustomize/commits?" +
-				"path=examples+1%2FhelloWorld%2Fkustomization.yaml&per_page=100",
-		},
-	}
-
-	for _, test := range testCases {
-		if result := test.rc.CodeSearchRequestWith(test.codeQuery).URL(); result != test.expectedCodeQuery {
-			t.Errorf("Got code query: %s, expected %s", result, test.expectedCodeQuery)
-		}
-
-		if result := test.rc.ContentsRequest(test.fullRepoName, test.path); result != test.expectedContentsQuery {
-			t.Errorf("Got contents query: %s, expected %s", result, test.expectedContentsQuery)
-		}
-		if result := test.rc.CommitsRequest(test.fullRepoName, test.path); result != test.expectedCommitsQuery {
-			t.Errorf("Got commits query: %s, expected %s", result, test.expectedCommitsQuery)
-		}
-	}
-}

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

@@ -1,379 +0,0 @@
-package github
-
-// GitHub only returns at most 1000 results per search query,
-// this is problematic if you want to retrieve all the results for a given
-// search query. However, GitHub allows you to specify as much as you want per
-// query to make things more specific. Specifically for files, GitHub allows
-// you to specify their sizes with range queries. This is very convenient
-// since it allows us to split the search into disjoint sets/shards of results
-// from the different file size ranges.
-//
-// Some important factors to consider:
-//
-// -  These queries are rate limited by the API to roughly once query every two
-//    seconds.
-//
-// -  The search space for file sizes is in bytes, from 0B to < 512KiB (this is
-//    a huge search space that cannot be probed linearly in a timely manner if
-//    granularity is to be expected).
-//
-// -  If you have K files there will likely be ~K/1000 sets that you have find
-//    from this search space in order to get all of the results.
-//
-// -  If you have O(K) sets it is unlikely that they are all of the same size,
-//    since (most files are power law distributed). That means that the range
-//    might be significantly smaller for 1000 small files, than it is for
-//    1000 large files.
-//
-// -  This method is a best effort approach. There are some limitations to what
-//    it can and can't do, so please note the following:
-//
-//    +  There may very well be a filesize that has more than 1000 results.
-//       this method cannot help in this case. However, requerying over time
-//       (days/weeks/months) while sorting by last indexed values may be
-//       sufficient to eventually get all of the results.
-//
-//    +  It's possible that the github API returns inconsistent counts. This
-//       is problematic in most cases, since it can cause many issues if the
-//       case is not handled properly. For instance, if you requested the
-//       number of files of an interval from size:0..64 and get that there
-//       are 900 results, you may query at size:0..96 and get that there
-//       are 800 results. To guarantee that this approach completes and does
-//       not get into a query loop over the same intervals, it will retry a few
-//       times and take the largest of the results or the largest previously
-//       queried value from another range (in this case, the implementation
-//       could decide that size:0..96 must have 900) results. This makes the
-//       approach best effort even if there are no single file sizes of over
-//       1000 results.
-//
-//
-// The approach that was taken to solve this problem is the following:
-//
-// 1. Determine the total number of results by querying from the lower bound
-//    to the upper bound (size:0..max). If there are less than 1000 files,
-//    return a single range of values (size:0..max) since all results can be
-//    retrieved.
-//
-// 2. Otherwise, set a target number of files to be 1000.
-//
-// 3. Binary search for the range from 0..r that provides a file count that is
-//    less than or equal to the target. Once this value is found, store the
-//    upper bound of range (r). If r is the same as the previous value, (or 0)
-//    increase r by one (this guarantees progress, but will miss out on some
-//    results).
-//
-// 4. Increase the target by 1000.
-//
-// 5. Repeat steps 3 and 4 until the target is at or exceeds the total number
-//    of files.
-//
-//
-// In general there are other ways to get all of the files from GitHub. In
-// some cases it would be sufficient to just get the files that are being
-// updated/indexed by github periodically to update the corpus, so this
-// complicated approach does not have to be run every time. However, for
-// some searches, there may be too many results on a time interval to do
-// this simple update search limited to only 1000 results.
-//
-// There is also a more sophisticated approach that may yield better
-// performance:
-// -  Perform this search once and create a prior distribution of file sizes.
-//    Each time you want to retrieve the results of the query, scale the
-//    prior of expected ranges to the current number of files. From each
-//    expected range of 1000 files, perform a exponential search to find the
-//    lower bound of the range. This would likely reduce the total number
-//    of queries by a significant amount since it would only have to search
-//    for a small set of values around each likely range boundary.
-//
-// However, actually retrieving the files will be the bottleneck operation
-// since the number of queries to find the ranges will be close to:
-//   log2(maxFileSize) * totalResults / 1000 ~= totalResults / 50
-// whereas the number of queries to actually get all of the search results
-// are close to:
-//   apiCallsPerResult * 10(pages) * 100(resultsPerPage) * totalResults / 1000
-//   = apiCallsPerResult * totalResults.
-//
-// 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
-// https://help.github.com/en/articles/searching-code#considerations-for-code-search
-const (
-	githubMaxFileSize        = uint64(1 << 19)
-	githubMaxResultsPerQuery = uint64(1000)
-)
-
-// Interface instead of struct for testing purposes.
-// Not expecting to have multiple implementations.
-type cachedSearch interface {
-	CountResults(uint64, uint64) (uint64, error)
-	RequestString(filesize rangeFormatter) string
-}
-
-// cachedSearch is a simple data structure that maps the upper bound (r) of a
-// range from 0 to r to the number of files that have between 0 and r files
-// (inclusive). It also guarantees that the counts are monotonically increasing
-// (not strict) as the value for r increases, by looking at the maximal
-// previous file count for the value that precedes r in the cache.
-//
-// It uses a bit trick to be more efficient in detecting
-// inconsistencies in the returned data from the Github API.
-// Therefore, the cache expects a search to always start at 0, and
-// it expects the max file size to be a power of 2. If this is to be changed
-// there are a few considerations to keep in mind:
-//
-// 1. The cache is only efficient if the queries can be reused, so if
-//    the first chunk of files lives in the range 0..x, continuing the
-//    search for the next chunk from x+1..max (while asymptotically sane)
-//    may actually be less efficient since the cache is essentially reset
-//    at every interval. This leads to a larger number of requests in
-//    practice, and requests are what's expensive (rate limits).
-//
-// 2. The github API is not perfectly monotonic.. (this is somewhat
-//    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 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
-//    by iterating over cached values. So this trick is not crucial to the
-//    cache's performance.
-type githubCachedSearch struct {
-	cache       map[uint64]uint64
-	gcl         GhClient
-	baseRequest request
-}
-
-func newCache(client GhClient, query Query) githubCachedSearch {
-	return githubCachedSearch{
-		cache: map[uint64]uint64{
-			0: 0,
-		},
-		gcl:         client,
-		baseRequest: client.CodeSearchRequestWith(query),
-	}
-}
-
-func (c githubCachedSearch) CountResults(lowerBound, upperBound uint64) (uint64, error) {
-	count, cached := c.cache[upperBound]
-	if cached {
-		return count, nil
-	}
-
-	sizeRange := RangeWithin{lowerBound, upperBound}
-	rangeRequest := c.RequestString(sizeRange)
-
-	result := c.gcl.parseGithubResponseWithRetry(rangeRequest)
-	if result.Error != nil {
-		return count, result.Error
-	}
-
-	// As range search uses powers of 2 for binary search, the previously
-	// cached value is easy to find by removing the least significant set
-	// bit from the current upperBound, since each step of the search adds
-	// least significant set bit.
-	//
-	// Finding the predecessor could also be implemented by iterating over
-	// the map to find the largest key that is smaller than upperBound if
-	// this approach deemed too complex.
-	trail := bits.TrailingZeros64(upperBound)
-	prev := uint64(0)
-	if trail != 64 {
-		prev = upperBound - (1 << uint64(trail))
-	}
-
-	// Sometimes the github API is not monotonically increasing, or ouputs
-	// an erroneous value of 0, or 1. This logic makes sure that it was not
-	// erroneous, and that the sequence continues to be monotonic by setting
-	// the current query count to match the previous value. which at least
-	// guarantees that the range search terminates.
-	//
-	// On the other hand, if files are added, then we way loose out on some
-	// files in a reviously completed range, but these files should be there
-	// the next time the crawler runs, so this is not really problematic.
-	retryMonotonicCount := 4
-	for result.Parsed.TotalCount < c.cache[prev] {
-		logger.Printf(
-			"Retrying query... current lower bound: %d, got: %d\n",
-			c.cache[prev], result.Parsed.TotalCount)
-
-		result = c.gcl.parseGithubResponseWithRetry(rangeRequest)
-		if result.Error != nil {
-			return count, result.Error
-		}
-
-		retryMonotonicCount--
-		if retryMonotonicCount <= 0 {
-			result.Parsed.TotalCount = c.cache[prev]
-			logger.Println(
-				"Retries for monotonic check exceeded,",
-				" setting value to match predecessor")
-		}
-	}
-
-	count = result.Parsed.TotalCount
-	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
-}
-
-func (c githubCachedSearch) RequestString(filesize rangeFormatter) string {
-	return c.baseRequest.CopyWith(Filesize(filesize)).URL()
-}
-
-// Outputs a (possibly incomplete) list of ranges to query to find most search
-// results as permissible by the search github search API. Github search only
-// allows 1,000 results per query (paginated).
-// Source: https://developer.github.com/v3/search/
-//
-// This leaves the possibility of having file sizes with more than 1000 results,
-// 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, lowerBound, upperBound uint64) ([]string, error) {
-	totalFiles, err := cache.CountResults(lowerBound, upperBound)
-	if err != nil {
-		return nil, err
-	}
-	logger.Println("total kustomization files: ", totalFiles)
-
-	if githubMaxResultsPerQuery >= totalFiles {
-		return []string{
-			cache.RequestString(RangeWithin{lowerBound, upperBound}),
-		}, nil
-	}
-
-	// Find all the ranges of file sizes such that all files are queryable
-	// using the Github API. This does not compute an optimal ranges, since
-	// the number of queries needed to get the information required to
-	// compute an optimal range is expected to be much larger than the
-	// number of queries performed this way.
-	//
-	// The number of ranges is k = (number of files)/1000, and finding a
-	// range is logarithmic in the max file size (n = filesize). This means
-	// that preprocessing takes O(k * lg n) queries to find the ranges with
-	// a binary search over file sizes.
-	//
-	// My intuition is that this approach is competitive to a perfectly
-	// optimal solution, but I didn't actually take the time to do a
-	// rigorous proof. Intuitively, since files sizes are typically power
-	// law distibuted the binary search will be very skewed towards the
-	// smaller file ranges. This means that in practice this approach will
-	// make fewer than (#files/1000)*(log(n) = 19) queries for
-	// preprocessing, since it reuses a lot of the queries in the denser
-	// ranges. Furthermore, because of the distribution, it should be very
-	// easy to find ranges that are very close to the upper bound, up to
-	// the limiting factor of having no more than 1000 files accessible per
-	// range.
-	filesAccessible := uint64(0)
-	sizes := make([]uint64, 0)
-	sizes = append(sizes, lowerBound)
-	for filesAccessible < totalFiles {
-		target := filesAccessible + githubMaxResultsPerQuery
-		if target >= totalFiles {
-			break
-		}
-
-		logger.Printf("%d accessible files, next target = %d\n",
-			filesAccessible, 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] == size {
-			size++
-		}
-
-		nextAccessible, err := cache.CountResults(lowerBound, size)
-		if err != nil {
-			return nil, fmt.Errorf(
-				"cache should be populated at %d already, got %v",
-				size, err)
-		}
-		if nextAccessible < filesAccessible {
-			return nil, fmt.Errorf(
-				"number of results dropped from %d to %d within range search",
-				filesAccessible, nextAccessible)
-		}
-
-		filesAccessible = nextAccessible
-		if nextAccessible < totalFiles {
-			sizes = append(sizes, size)
-		}
-	}
-	sizes = append(sizes, upperBound)
-	return formatFilesizeRanges(cache, sizes), nil
-}
-
-// 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 FindFileSize(
-	cache cachedSearch, targetFileCount, lowerBound, upperBound uint64) (uint64, error) {
-
-	// Binary search for file sizes that make up the next <=1000 element
-	// chunk.
-	cur := lowerBound
-	increase := (upperBound - lowerBound) / 2
-
-	for increase > 0 {
-		mid := cur + increase
-
-		count, err := cache.CountResults(lowerBound, mid)
-		if err != nil {
-			return count, err
-		}
-
-		if count <= targetFileCount {
-			cur = mid
-		}
-
-		if count == targetFileCount {
-			break
-		}
-
-		increase /= 2
-	}
-
-	return cur, nil
-}
-
-func formatFilesizeRanges(cache cachedSearch, sizes []uint64) []string {
-	n := len(sizes)
-	if n < 2 {
-		return []string{}
-	}
-
-	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

@@ -1,101 +0,0 @@
-package github
-
-import (
-	"fmt"
-	"log"
-	"reflect"
-	"testing"
-)
-
-type testCachedSearch struct {
-	cache map[uint64]uint64
-}
-
-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)
-	}
-	return count, nil
-}
-
-func (c testCachedSearch) RequestString(filesize rangeFormatter) string {
-	return filesize.RangeString()
-}
-
-// TODO(damienr74) make tests easier to write.. I'm thinking I can make the test
-// cache take in a list of (filesize, count) pairs and it can populate the cache
-// without relying on how the implementation will create queries. This was only
-// a quick and dirty test to make sure that modifications are not going to break
-// the functionality.
-func TestRangeSplitting(t *testing.T) {
-	// Keys follow the binary search depending on whether or not the range
-	// is too small/large to find close to optimal filesize ranges. This
-	// test is heavily tied to the fact that the search is using powers of two
-	// to make progress in the search (hence the use of hexadecimal values).
-	cache := testCachedSearch{
-		map[uint64]uint64{
-			0x80000: 5000,
-			0x40000: 5000,
-			0x20000: 5000,
-			0x10000: 5000,
-			0x08000: 5000,
-			0x04000: 5000,
-			0x02000: 5000,
-			0x01000: 5000,
-			0x00fff: 3950,
-			0x00ffe: 3950,
-			0x00ffc: 3950,
-			0x00ff8: 3950,
-			0x00ff0: 3950,
-			0x00fe0: 3950,
-			0x00fc0: 3950,
-			0x00f80: 3950,
-			0x00f00: 3950,
-			0x00e00: 3950,
-			0x00c00: 3950,
-			0x00800: 3950,
-			0x00400: 3950,
-			0x00200: 3688,
-			0x00180: 3028,
-			0x00100: 2999,
-			0x000c0: 2448,
-			0x00080: 1999,
-			0x00070: 1600,
-			0x0006c: 1003,
-			0x0006b: 1001,
-			0x0006a: 999,
-			0x00068: 999,
-			0x00060: 999,
-			0x00040: 999,
-			0x00000: 0,
-		},
-	}
-
-	requests, err := FindRangesForRepoSearch(cache, 0, 524288)
-	if err != nil {
-		t.Errorf("Error while finding ranges: %v", err)
-	}
-	expected := []string{
-		"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

@@ -1,268 +0,0 @@
-package doc
-
-import (
-	"fmt"
-	"log"
-	"path/filepath"
-	"sort"
-	"strings"
-
-	"sigs.k8s.io/kustomize/api/konfig"
-	"sigs.k8s.io/kustomize/api/provider"
-	"sigs.k8s.io/kustomize/api/resource"
-	"sigs.k8s.io/kustomize/api/types"
-	"sigs.k8s.io/yaml"
-)
-
-// This document is meant to be used at the elasticsearch document type.
-// Fields are serialized as-is to elasticsearch, where indices are built
-// to facilitate text search queries. Identifiers, Values, FilePath,
-// RepositoryURL and DocumentData are meant to be searched for text queries
-// directly, while the other fields can either be used as a filter, or as
-// additional metadata displayed in the UI.
-//
-// The fields of the document and their purpose are listed below:
-// - DocumentData contains the contents of the kustomization file.
-// - Kinds Represents the kubernetes Kinds that are in this file.
-// - Identifiers are a list of (partial and full) identifier paths that can be
-//   found by users. Each part of a path is delimited by ":" e.g. spec:replicas.
-// - Values are a list of identifier paths and their values that can be found by
-//   search queries. The path is delimited by ":" and the value follows the "="
-//   symbol e.g. spec:replicas=4.
-// - FilePath is the path of the file.
-// - RepositoryURL is the URL of the source repository.
-// - CreationTime is the time at which the file was created.
-//
-// Representing each Identifier and Value as a flat string representation
-// facilitates the use of complex text search features from elasticsearch such
-// as fuzzy searching, regex, wildcards, etc.
-type KustomizationDocument struct {
-	Document
-	Kinds       []string `json:"kinds,omitempty"`
-	Identifiers []string `json:"identifiers,omitempty"`
-	Values      []string `json:"values,omitempty"`
-	resFactory  *resource.Factory
-}
-
-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,
-		resFactory:  provider.NewDefaultDepProvider().GetResourceFactory(),
-	}
-}
-
-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))
-}
-
-// 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
-}
-
-// Implements the CrawlerDocument interface.
-func (doc *KustomizationDocument) GetResources(
-	includeResources, includeTransformers, includeGenerators bool) ([]*Document, error) {
-	if !IsKustomizationFile(doc.FilePath) {
-		return []*Document{}, nil
-	}
-
-	content := []byte(doc.DocumentData)
-	content, err := FixKustomizationPreUnmarshallingNonFatal(content)
-	if err != nil {
-		return nil, fmt.Errorf("could not fix kustomize file: %v", err)
-	}
-
-	var k types.Kustomization
-	err = yaml.Unmarshal(content, &k)
-	if err != nil {
-		return nil, fmt.Errorf(
-			"could not parse kustomization: %v", err)
-	}
-	k.FixKustomizationPostUnmarshalling()
-
-	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 {
-			log.Printf("CollectDocuments error: %v\n", err)
-			continue
-		}
-		next.FileType = fileType
-		docs = append(docs, &next)
-	}
-	return docs
-}
-
-func (doc *KustomizationDocument) readBytes() ([]map[string]interface{}, error) {
-	data := []byte(doc.DocumentData)
-
-	for _, suffix := range konfig.RecognizedKustomizationFileNames() {
-		if !strings.HasSuffix(doc.FilePath, "/"+suffix) {
-			continue
-		}
-		var config map[string]interface{}
-		err := yaml.Unmarshal(data, &config)
-		if err != nil {
-			return nil, fmt.Errorf(
-				"unable to parse kustomization: %v", err)
-		}
-		return []map[string]interface{}{config}, nil
-	}
-
-	configs := make([]map[string]interface{}, 0)
-	ks, err := doc.resFactory.SliceFromBytes(data)
-	if err != nil {
-		return nil, fmt.Errorf("unable to parse resource: %v", err)
-	}
-	for _, k := range ks {
-		configs = append(configs, k.Map())
-	}
-
-	return configs, nil
-}
-
-// ParseYAML parses doc.Document and sets the following fields of doc:
-// Kinds, Values, Identifiers.
-func (doc *KustomizationDocument) ParseYAML() error {
-	doc.Identifiers = make([]string, 0)
-	doc.Values = make([]string, 0)
-	doc.Kinds = make([]string, 0, 1)
-
-	identifierSet := make(set)
-	valueSet := make(set)
-	kindSet := make(set)
-
-	getKind := func(m map[string]interface{}) string {
-		const defaultStr = "Kustomization"
-		kind, ok := m["kind"]
-		if !ok {
-			return defaultStr
-		}
-		if str, ok := kind.(string); ok && str != "" {
-			return str
-		}
-		return defaultStr
-	}
-
-	ks, err := doc.readBytes()
-	if err != nil {
-		return err
-	}
-
-	for _, contents := range ks {
-		kindSet[getKind(contents)] = struct{}{}
-		createFlatStructure(identifierSet, valueSet, contents)
-	}
-
-	for val := range kindSet {
-		doc.Kinds = append(doc.Kinds, val)
-	}
-
-	for val := range valueSet {
-		doc.Values = append(doc.Values, val)
-	}
-
-	for key := range identifierSet {
-		doc.Identifiers = append(doc.Identifiers, key)
-	}
-
-	// Without sorting these fields, every time when the string order in these fields changes,
-	// the document in the index will be updated.
-	// Sorting these fields are necessary to avoid a document being updated unnecessarily.
-	sort.Strings(doc.Kinds)
-	sort.Strings(doc.Values)
-	sort.Strings(doc.Identifiers)
-
-	return nil
-}
-
-func createFlatStructure(identifierSet set, valueSet set, contents map[string]interface{}) {
-	type Map struct {
-		data   map[string]interface{}
-		prefix string
-	}
-
-	toVisit := []Map{
-		{
-			data:   contents,
-			prefix: "",
-		},
-	}
-
-	for i := 0; i < len(toVisit); i++ {
-		visiting := toVisit[i]
-		for k, v := range visiting.data {
-			identifier := fmt.Sprintf("%s:%s", visiting.prefix, k)
-			// noop after the first iteration.
-			identifier = strings.TrimLeft(identifier, ":")
-
-			// Recursive function traverses structure to find
-			// identifiers and values. These later get formatted
-			// into doc.Identifiers and doc.Values respectively.
-			var traverseStructure func(interface{})
-			traverseStructure = func(arg interface{}) {
-				switch value := arg.(type) {
-				case map[string]interface{}:
-					toVisit = append(toVisit, Map{
-						data:   value,
-						prefix: identifier,
-					})
-				case []interface{}:
-					for _, val := range value {
-						traverseStructure(val)
-					}
-				case interface{}:
-					esc := fmt.Sprintf("%v", value)
-
-					valuePath := fmt.Sprintf("%s=%v",
-						identifier, esc)
-					valueSet[valuePath] = struct{}{}
-				}
-			}
-			traverseStructure(v)
-
-			identifierSet[identifier] = struct{}{}
-		}
-	}
-}

api/internal/crawl/doc/doc_test.go

@@ -1,379 +0,0 @@
-package doc
-
-import (
-	"reflect"
-	"sort"
-	"strings"
-	"testing"
-)
-
-func TestParseYAML(t *testing.T) {
-	testCases := []struct {
-		identifiers []string
-		values      []string
-		kinds       []string
-		filepath    string
-		yaml        string
-	}{
-		{
-			identifiers: []string{
-				"namePrefix",
-				"metadata",
-				"metadata:name",
-				"kind",
-			},
-			values: []string{
-				"kind=",
-				"namePrefix=dev-",
-				"metadata:name=app",
-			},
-			kinds: []string{
-				"Kustomization",
-			},
-			filepath: "some/path/to/kustomization.yaml",
-			yaml: `
-namePrefix: dev-
-metadata:
-  name: app
-kind: ""
-`,
-		},
-		{
-			identifiers: []string{
-				"namePrefix",
-				"metadata",
-				"metadata:name",
-				"metadata:spec",
-				"metadata:spec:replicas",
-				"kind",
-				"replicas",
-				"replicas:name",
-				"replicas:count",
-				"resource",
-			},
-			values: []string{
-				"namePrefix=dev-",
-				"metadata:name=n1",
-				"metadata:spec:replicas=3",
-				"kind=Kustomization",
-				"replicas:name=n1",
-				"replicas:name=n2",
-				"replicas:count=3",
-				"resource=file1.yaml",
-				"resource=file2.yaml",
-			},
-			kinds: []string{
-				"Kustomization",
-			},
-			filepath: "./kustomization.yaml",
-			yaml: `
-namePrefix: dev-
-# map of map
-metadata:
-  name: n1
-  spec:
-    replicas: 3
-kind: Kustomization
-
-#list of map
-replicas:
-- name: n1
-  count: 3
-- name: n2
-  count: 3
-
-# list
-resource:
-- file1.yaml
-- file2.yaml
-`,
-		},
-		{
-			identifiers: []string{
-				"kind",
-				"metadata",
-				"metadata:name",
-			},
-			values: []string{
-				"kind=Deployment",
-				"kind=Service",
-				"kind=Custom",
-				"metadata:name=app",
-				"metadata:name=app-service",
-				"metadata:name=app-crd",
-			},
-			kinds: []string{
-				"Deployment",
-				"Service",
-				"Custom",
-			},
-			filepath: "resources.yaml",
-			yaml: `
----
-kind: Deployment
-metadata:
-  name: app
----
-kind: Service
-metadata:
-  name: app-service
----
-kind: Custom
-metadata:
-  name: app-crd
-`,
-		},
-		{
-			identifiers: []string{
-				"kind",
-				"metadata",
-				"metadata:name",
-			},
-			values: []string{
-				"kind=Deployment",
-				"kind=Service",
-				"metadata:name=app1",
-				"metadata:name=app2",
-			},
-			kinds: []string{
-				"Deployment",
-				"Service",
-			},
-			filepath: "resources.yaml",
-			yaml: `
----
-kind: Deployment
-metadata:
-  name: app1
----
-kind: Deployment
-metadata:
-  name: app2
----
-kind: Service
-metadata:
-  name: app1
-`,
-		},
-	}
-
-	for _, test := range testCases {
-		doc := KustomizationDocument{
-			Document: Document{
-				DocumentData: test.yaml,
-				FilePath:     test.filepath,
-			},
-		}
-
-		err := doc.ParseYAML()
-		if err != nil {
-			t.Errorf("Document error error: %s", err)
-		}
-
-		cmpStrings := func(got, expected []string, label string) {
-			sort.Strings(got)
-			sort.Strings(expected)
-
-			if !reflect.DeepEqual(got, expected) {
-				t.Errorf("Expected %s (%v) to be equal to (%v)\n",
-					label,
-					strings.Join(got, ","),
-					strings.Join(expected, ","))
-			}
-
-		}
-
-		cmpStrings(doc.Identifiers, test.identifiers, "identifiers")
-		cmpStrings(doc.Values, test.values, "values")
-		cmpStrings(doc.Kinds, test.kinds, "kinds")
-	}
-}
-
-type TestStructForGetResources struct {
-	doc       KustomizationDocument
-	resources []*Document
-}
-
-func TestGetResources(t *testing.T) {
-	tests := []TestStructForGetResources{
-		{
-			doc: KustomizationDocument{
-				Document: Document{
-					RepositoryURL: "sigs.k8s.io/kustomize",
-					FilePath:      "some/path/to/kdir/kustomization.yaml",
-					DocumentData: `
-bases:
-- ../base
-- ../otherbase
-
-resources:
-- file.yaml
-- https://github.com/kubernetes-sigs/kustomize/examples/helloWorld?ref=v3.1.0
-`},
-			},
-			resources: []*Document{
-				{
-					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",
-				},
-			},
-		},
-		{
-			doc: KustomizationDocument{
-				Document: Document{
-					RepositoryURL: "https://github.com/some/repo",
-					FilePath:      "some/resource.yaml",
-					DocumentData: `
-bases:
-- ../base
-- ../overlay
-
-resources:
-- https://github.com/kubernetes-sigs/kustomize/examples/helloWorld?ref=v3.1.0
-- some/file.yaml
-`,
-				},
-			},
-			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(includeResources, includeTransformers, includeGenerators)
-		if err != nil {
-			t.Errorf("Unexpected error: %v\n", err)
-			continue
-		}
-		if len(test.resources) != len(res) {
-			t.Errorf("Number of resources does not match.")
-			continue
-		}
-		cmp := func(docs []*Document) func(i, j int) bool {
-			return func(i, j int) bool {
-				if docs[i].RepositoryURL != docs[j].RepositoryURL {
-					return docs[i].RepositoryURL <
-						docs[j].RepositoryURL
-				}
-
-				if docs[i].FilePath != docs[j].FilePath {
-					return docs[i].FilePath <
-						docs[j].FilePath
-				}
-
-				return docs[i].DefaultBranch < docs[j].DefaultBranch
-			}
-		}
-		sort.Slice(test.resources, cmp(test.resources))
-		sort.Slice(res, cmp(res))
-		for i, r := range test.resources {
-			if !reflect.DeepEqual(res[i], r) {
-				t.Errorf("Expected '%+v' to equal '%+v'\n",
-					res[i], r)
-			}
-		}
-	}
-}
-
-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

@@ -1,124 +0,0 @@
-package doc
-
-import (
-	"crypto/sha256"
-	"fmt"
-	"path"
-	"strings"
-	"time"
-
-	"sigs.k8s.io/kustomize/api/internal/git"
-)
-
-type Document struct {
-	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.
-func (doc *Document) GetDocument() *Document {
-	return doc
-}
-
-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
-}
-
-func (doc *Document) FromRelativePath(newFile string) (Document, error) {
-	repoSpec, err := git.NewRepoSpecFromUrl(newFile)
-	if err == nil {
-		return Document{
-			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.
-
-	ret := Document{
-		RepositoryURL: doc.RepositoryURL,
-		DefaultBranch: doc.DefaultBranch,
-		User:          UserName(doc.RepositoryURL),
-	}
-	ogDir, _ := path.Split(doc.FilePath)
-
-	cleaned := path.Clean(newFile)
-	if !path.IsAbs(cleaned) {
-		cleaned = path.Clean(ogDir + "/" + cleaned)
-	}
-
-	ret.FilePath = cleaned
-	return ret, nil
-}
-
-func (doc *Document) ID() string {
-	sum := sha256.Sum256([]byte(strings.Join(
-		[]string{
-			doc.RepositoryURL,
-			doc.DefaultBranch,
-			doc.FilePath,
-		},
-		"---|---")))
-	return fmt.Sprintf("%x", sum)
-}
-
-func (doc *Document) RepositoryFullName() string {
-	url := TrimUrl(doc.RepositoryURL)
-	sections := strings.Split(url, "/")
-	l := len(sections)
-	if l < 2 {
-		return url
-	}
-	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

@@ -1,150 +0,0 @@
-package doc
-
-import (
-	"reflect"
-	"testing"
-)
-
-func TestFromRelativePath(t *testing.T) {
-	type Case struct {
-		RelativePath string
-		Expected     Document
-	}
-
-	testCases := []struct {
-		BaseDoc Document
-		Cases   []Case
-	}{
-		{
-			BaseDoc: Document{
-				RepositoryURL: "example.com/repo",
-				FilePath:      "path/to/file/kustomization.yaml",
-				DefaultBranch: "master",
-			},
-			Cases: []Case{
-				{
-					RelativePath: "../other/file/resource.yaml",
-					Expected: Document{
-						RepositoryURL: "example.com/repo",
-						FilePath:      "path/to/other/file/resource.yaml",
-						DefaultBranch: "master",
-						User:          "example.com",
-					},
-				},
-				{
-					RelativePath: "../file/../../something/../to/other/file/patch.yaml",
-					Expected: Document{
-						RepositoryURL: "example.com/repo",
-						FilePath:      "path/to/other/file/patch.yaml",
-						DefaultBranch: "master",
-						User:          "example.com",
-					},
-				},
-				{
-					RelativePath: "service.yaml",
-					Expected: Document{
-						RepositoryURL: "example.com/repo",
-						FilePath:      "path/to/file/service.yaml",
-						DefaultBranch: "master",
-						User:          "example.com",
-					},
-				},
-			},
-		},
-	}
-
-	for _, tc := range testCases {
-		for _, c := range tc.Cases {
-			rd, err := tc.BaseDoc.FromRelativePath(c.RelativePath)
-			if err != nil {
-				t.Errorf("unexpected error: %v", err)
-			}
-			if !reflect.DeepEqual(rd, c.Expected) {
-				t.Errorf("document mismatch expected %v, got %v", c.Expected, rd)
-			}
-		}
-	}
-}
-
-func TestDocument_RepositoryFullName(t *testing.T) {
-	testCases := []struct {
-		doc                        Document
-		expectedRepositoryFullName string
-	}{
-		{
-			doc: Document{
-				RepositoryURL: "https://github.com/user/repo",
-			},
-			expectedRepositoryFullName: "user/repo",
-		},
-		{
-			doc: Document{
-				RepositoryURL: "https://github.com//user/repo////",
-			},
-			expectedRepositoryFullName: "user/repo",
-		},
-		{
-			doc: Document{
-				RepositoryURL: "repo/",
-			},
-			expectedRepositoryFullName: "repo",
-		},
-		{
-			doc: Document{
-				RepositoryURL: "",
-			},
-			expectedRepositoryFullName: "",
-		},
-		{
-			doc: Document{
-				RepositoryURL: "git@github.com:user/repo",
-			},
-			expectedRepositoryFullName: "user/repo",
-		},
-	}
-
-	for _, tc := range testCases {
-		returnedRepositoryFullName := tc.doc.RepositoryFullName()
-		if returnedRepositoryFullName != tc.expectedRepositoryFullName {
-			t.Errorf("RepositoryFullName expected %s, got %s",
-				tc.expectedRepositoryFullName,
-				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/kustomize_util.go

@@ -1,51 +0,0 @@
-package doc
-
-import (
-	"fmt"
-	"regexp"
-
-	"sigs.k8s.io/yaml"
-)
-
-func FixKustomizationPreUnmarshallingNonFatal(data []byte) ([]byte, error) {
-	deprecateFieldsMap := map[string]string{
-		"imageTags:": "images:",
-	}
-	for oldname, newname := range deprecateFieldsMap {
-		pattern := regexp.MustCompile(oldname)
-		data = pattern.ReplaceAll(data, []byte(newname))
-	}
-
-	found, err := useLegacyPatch(data)
-	if err == nil && found {
-		pattern := regexp.MustCompile("patches:")
-		data = pattern.ReplaceAll(data, []byte("patchesStrategicMerge:"))
-	}
-
-	return data, err
-}
-
-func useLegacyPatch(data []byte) (bool, error) {
-	found := false
-
-	var object map[string]interface{}
-	err := yaml.Unmarshal(data, &object)
-	if err != nil {
-		return false, fmt.Errorf("invalid content from %s",
-			string(data))
-	}
-	if rawPatches, ok := object["patches"]; ok {
-		patches, ok := rawPatches.([]interface{})
-		if !ok {
-			return false, fmt.Errorf("invalid patches from %v",
-				rawPatches)
-		}
-		for _, p := range patches {
-			_, ok := p.(string)
-			if ok {
-				found = true
-			}
-		}
-	}
-	return found, nil
-}

api/internal/crawl/doc/unique_doc.go

@@ -1,36 +0,0 @@
-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/go.mod

@@ -1,15 +0,0 @@
-module sigs.k8s.io/kustomize/api/internal/crawl
-
-go 1.16
-
-require (
-	github.com/elastic/go-elasticsearch/v6 v6.8.5
-	github.com/gomodule/redigo v2.0.0+incompatible
-	github.com/gorilla/mux v1.7.3
-	github.com/gregjones/httpcache v0.0.0-20190611155906-901d90724c79
-	github.com/rs/cors v1.7.0
-	sigs.k8s.io/kustomize/api v0.0.0
-	sigs.k8s.io/yaml v1.2.0
-)
-
-replace sigs.k8s.io/kustomize/api v0.0.0 => ../../../api

api/internal/crawl/httpclient/httpclient.go

@@ -1,23 +0,0 @@
-package httpclient
-
-import (
-	"net/http"
-	"time"
-
-	"github.com/gomodule/redigo/redis"
-	"github.com/gregjones/httpcache"
-	rediscache "github.com/gregjones/httpcache/redis"
-)
-
-func FromCache(header http.Header) bool {
-	return header.Get(httpcache.XFromCache) != ""
-}
-
-func NewClient(conn redis.Conn) *http.Client {
-	etagCache := rediscache.NewWithClient(conn)
-	tr := httpcache.NewTransport(etagCache)
-	return &http.Client{
-		Transport: tr,
-		Timeout:   10 * time.Second,
-	}
-}