* basecrawl refactor: make crawls db more generic, supporting different types of 'base crawls': crawls, uploads, manual archives - move shared functionality to basecrawl.py - create a base BaseCrawl object, which contains start / finish time, metadata and files array - create BaseCrawlOps, base class for CrawlOps, which supports base crawl deletion, querying and collection add/remove * uploads api: (part of #929) - new UploadCrawl object which extends BaseCrawl, has name and description - support multipart form data data upload to /uploads/formdata - support streaming upload of a single file via /uploads/stream, using botocore multipart upload to upload to s3-endpoint in parts - require 'filename' param to set upload filename for streaming uploads (otherwise use form data names) - sanitize filename, place uploads in /uploads/<uuid>/<sanitized-filename>-<random>.wacz - uploads have internal id 'upload-<uuid>' - create UploadedCrawl object with CrawlFiles pointing to the newly uploaded files, set state to 'complete' - handle upload failures, abort multipart upload - ensure uploads added within org bucket path - return id / added when adding new UploadedCrawl - support listing, deleting, and patch /uploads - support upload details via /replay.json to support for replay - add support for 'replaceId=<id>', which would remove all previous files in upload after new upload succeeds. if replaceId doesn't exist, create new upload. (only for stream endpoint so far). - support patching upload metadata: notes, tags and name on uploads (UpdateUpload extends UpdateCrawl and adds 'name') * base crawls api: Add /all-crawls list and delete endpoints for all crawl types (without resources) - support all-crawls/<id>/replay.json with resources - Use ListCrawlOut model for /all-crawls list endpoint - Extend BaseCrawlOut from ListCrawlOut, add type - use 'type: crawl' for crawls and 'type: upload' for uploads - migration: ensure all previous crawl objects / missing type are set to 'type: crawl' - indexes: add db indices on 'type' field and with 'type' field and oid, cid, finished, state * tests: add test for multipart and streaming upload, listing uploads, deleting upload - add sample WACZ for upload testing: 'example.wacz' and 'example-2.wacz' * collections: support adding and remove both crawls and uploads via base crawl - include collection_ids in /all-crawls list - collections replay.json can include both crawls and uploads bump version to 1.6.0-beta.2 --------- Co-authored-by: Tessa Walsh <tessa@bitarchivist.net>
109 lines
2.8 KiB
YAML
109 lines
2.8 KiB
YAML
{{- if .Values.ingress.host }}
|
|
|
|
---
|
|
apiVersion: networking.k8s.io/v1
|
|
kind: Ingress
|
|
metadata:
|
|
name: ingress-main
|
|
namespace: {{ .Release.Namespace }}
|
|
annotations:
|
|
kubernetes.io/ingress.class: {{ .Values.ingress_class | default "nginx" }}
|
|
nginx.ingress.kubernetes.io/ssl-redirect: "true"
|
|
nginx.ingress.kubernetes.io/rewrite-target: /$1
|
|
nginx.ingress.kubernetes.io/enable-cors: "true"
|
|
nginx.ingress.kubernetes.io/cors-allow-origin: "*"
|
|
nginx.ingress.kubernetes.io/proxy-body-size: "0"
|
|
nginx.ingress.kubernetes.io/proxy-request-buffering: "off"
|
|
nginx.ingress.kubernetes.io/proxy-buffering: "off"
|
|
{{- if .Values.ingress.tls }}
|
|
cert-manager.io/cluster-issuer: "cert-main"
|
|
{{- end }}
|
|
nginx.ingress.kubernetes.io/upstream-vhost: "{{ .Values.ingress.host }}"
|
|
nginx.ingress.kubernetes.io/configuration-snippet: |
|
|
proxy_set_header X-Forwarded-Proto {{ .Values.ingress.scheme | default "https" }};
|
|
|
|
spec:
|
|
{{- if .Values.ingress.tls }}
|
|
tls:
|
|
- hosts:
|
|
- {{ .Values.ingress.host }}
|
|
secretName: cert-main
|
|
{{- end }}
|
|
|
|
rules:
|
|
- host: {{ .Values.ingress.host }}
|
|
http:
|
|
paths:
|
|
- path: /(api/.*)
|
|
pathType: Prefix
|
|
backend:
|
|
service:
|
|
name: browsertrix-cloud-backend
|
|
port:
|
|
number: 8000
|
|
|
|
- path: /(.*)
|
|
pathType: Prefix
|
|
backend:
|
|
service:
|
|
name: browsertrix-cloud-frontend
|
|
port:
|
|
number: 80
|
|
|
|
{{ if .Values.signer.enabled }}
|
|
{{ if .Values.signer.host }}
|
|
---
|
|
apiVersion: networking.k8s.io/v1
|
|
kind: Ingress
|
|
metadata:
|
|
name: ingress-authsign
|
|
namespace: {{ .Release.Namespace }}
|
|
annotations:
|
|
kubernetes.io/ingress.class: {{ .Values.ingress_class | default "nginx" }}
|
|
nginx.ingress.kubernetes.io/ssl-redirect: "false"
|
|
nginx.ingress.kubernetes.io/rewrite-target: /$1
|
|
nginx.ingress.kubernetes.io/upstream-vhost: "{{ .Values.signer.host }}"
|
|
|
|
spec:
|
|
rules:
|
|
- host: {{ .Values.signer.host }}
|
|
http:
|
|
paths:
|
|
- path: /(.*)
|
|
pathType: Prefix
|
|
backend:
|
|
service:
|
|
name: auth-signer
|
|
port:
|
|
number: 80
|
|
|
|
{{ end }}
|
|
{{ end }}
|
|
|
|
|
|
{{ if .Values.ingress.tls }}
|
|
---
|
|
|
|
apiVersion: cert-manager.io/v1
|
|
kind: ClusterIssuer
|
|
metadata:
|
|
name: cert-main
|
|
namespace: cert-manager
|
|
spec:
|
|
acme:
|
|
# The ACME server URL
|
|
server: https://acme-v02.api.letsencrypt.org/directory
|
|
# Email address used for ACME registration
|
|
email: {{ .Values.ingress.cert_email }}
|
|
# Name of a secret used to store the ACME account private key
|
|
privateKeySecretRef:
|
|
name: cert-main
|
|
# Enable the HTTP-01 challenge provider
|
|
solvers:
|
|
- http01:
|
|
ingress:
|
|
class: {{ .Values.ingress_class | default "nginx" }}
|
|
|
|
{{ end }}
|
|
{{ end }}
|