feature: 北向接口:支持通过模板创建清洗任务 (#111)

feature: 北向接口:支持通过模板创建清洗任务
This commit is contained in:
hhhhsc701
2025-11-26 17:30:54 +08:00
committed by GitHub
parent 0ca5f29885
commit 91390cace0
15 changed files with 312 additions and 253 deletions

View File

@@ -209,7 +209,7 @@ endif
.PHONY: uninstall
uninstall:
ifeq ($(origin INSTALLER), undefined)
$(call prompt-uninstaller,milvus-$$INSTALLER-uninstall label-studio-$$INSTALLER-uninstall datamate-$$INSTALLER-uninstall)
$(call prompt-uninstaller,milvus-$$INSTALLER-uninstall datamate-$$INSTALLER-uninstall)
else
@echo "Delete volumes? (This will remove all data)"; \
echo "1. Yes - Delete volumes"; \

View File

@@ -248,4 +248,8 @@ public class CleaningTaskService {
public void stopTask(String taskId) {
taskScheduler.stopTask(taskId);
}
public List<OperatorInstanceDto> getInstanceByTemplateId(String templateId) {
return operatorInstanceRepo.findInstanceByInstanceId(templateId);
}
}

View File

@@ -3,6 +3,7 @@ package com.datamate.cleaning.application;
import com.datamate.cleaning.domain.repository.CleaningTemplateRepository;
import com.datamate.cleaning.domain.repository.OperatorInstanceRepository;
import com.datamate.cleaning.infrastructure.validator.CleanTaskValidator;
import com.datamate.cleaning.interfaces.dto.*;
import com.datamate.cleaning.domain.model.entity.TemplateWithInstance;
import com.datamate.operator.domain.repository.OperatorViewRepository;
@@ -28,6 +29,8 @@ public class CleaningTemplateService {
private final OperatorViewRepository operatorViewRepo;
private final CleanTaskValidator cleanTaskValidator;
public List<CleaningTemplateDto> getTemplates(String keywords) {
List<OperatorDto> allOperators =
operatorViewRepo.findOperatorsByCriteria(null, null, null, null, null);
@@ -59,6 +62,7 @@ public class CleaningTemplateService {
@Transactional
public CleaningTemplateDto createTemplate(CreateCleaningTemplateRequest request) {
cleanTaskValidator.checkInputAndOutput(request.getInstance());
CleaningTemplateDto template = new CleaningTemplateDto();
String templateId = UUID.randomUUID().toString();
template.setId(templateId);

View File

@@ -13,4 +13,6 @@ public interface OperatorInstanceRepository extends IRepository<OperatorInstance
void deleteByInstanceId(String instanceId);
List<OperatorDto> findOperatorByInstanceId(String instanceId);
List<OperatorInstanceDto> findInstanceByInstanceId(String instanceId);
}

View File

@@ -8,6 +8,7 @@ import com.datamate.common.infrastructure.exception.SystemErrorCode;
import com.datamate.operator.domain.model.OperatorView;
import com.datamate.operator.interfaces.dto.OperatorDto;
import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.core.type.TypeReference;
import com.fasterxml.jackson.databind.ObjectMapper;
import org.mapstruct.Mapper;
import org.mapstruct.Mapping;
@@ -23,20 +24,39 @@ import java.util.Map;
public interface OperatorInstanceConverter {
OperatorInstanceConverter INSTANCE = Mappers.getMapper(OperatorInstanceConverter.class);
ObjectMapper OBJECT_MAPPER = new ObjectMapper();
@Mapping(target = "settingsOverride", source = "overrides", qualifiedByName = "mapToString")
@Mapping(target = "operatorId", source = "id")
OperatorInstance fromDtoToEntity(OperatorInstanceDto instance);
@Mapping(target = "overrides", source = "settingsOverride", qualifiedByName = "stringToMap")
@Mapping(target = "id", source = "operatorId")
OperatorInstanceDto fromEntityToDto(OperatorInstance instance);
List<OperatorInstanceDto> fromEntityToDtoList(List<OperatorInstance> instance);
@Named("mapToString")
static String mapToString(Map<String, Object> objects) {
ObjectMapper objectMapper = new ObjectMapper();
try {
return objectMapper.writeValueAsString(objects);
return OBJECT_MAPPER.writeValueAsString(objects);
} catch (JsonProcessingException e) {
throw BusinessException.of(SystemErrorCode.UNKNOWN_ERROR);
}
}
@Named("stringToMap")
static Map<String, Object> stringToMap(String json) {
if (json == null) {
return Collections.emptyMap();
}
try {
return OBJECT_MAPPER.readValue(json, new TypeReference<>() {});
} catch (JsonProcessingException e) {
throw BusinessException.of(SystemErrorCode.UNKNOWN_ERROR);
}
}
@Mapping(target = "categories", source = "categories", qualifiedByName = "stringToList")
OperatorDto fromEntityToDto(OperatorView operator);

View File

@@ -42,4 +42,12 @@ public class OperatorInstanceRepositoryImpl extends CrudRepository<OperatorInsta
public List<OperatorDto> findOperatorByInstanceId(String instanceId) {
return OperatorInstanceConverter.INSTANCE.fromEntityToDto(mapper.findOperatorByInstanceId(instanceId));
}
@Override
public List<OperatorInstanceDto> findInstanceByInstanceId(String instanceId) {
LambdaQueryWrapper<OperatorInstance> lambdaWrapper = new LambdaQueryWrapper<>();
lambdaWrapper.eq(OperatorInstance::getInstanceId, instanceId)
.orderByAsc(OperatorInstance::getOpIndex);
return OperatorInstanceConverter.INSTANCE.fromEntityToDtoList(mapper.selectList(lambdaWrapper));
}
}

View File

@@ -27,6 +27,8 @@ public class CreateCleaningTaskRequest {
private String destDatasetType;
private String templateId;
private List<OperatorInstanceDto> instance = new ArrayList<>();
}

View File

@@ -1,12 +1,10 @@
package com.datamate.cleaning.interfaces.rest;
import com.datamate.cleaning.application.CleaningTaskService;
import com.datamate.cleaning.interfaces.dto.CleaningResultDto;
import com.datamate.cleaning.interfaces.dto.CleaningTaskDto;
import com.datamate.cleaning.interfaces.dto.CleaningTaskLog;
import com.datamate.cleaning.interfaces.dto.CreateCleaningTaskRequest;
import com.datamate.cleaning.interfaces.dto.*;
import com.datamate.common.interfaces.PagedResponse;
import lombok.RequiredArgsConstructor;
import org.apache.commons.lang3.StringUtils;
import org.springframework.web.bind.annotation.*;
import java.util.List;
@@ -31,6 +29,9 @@ public class CleaningTaskController {
@PostMapping
public CleaningTaskDto cleaningTasksPost(@RequestBody CreateCleaningTaskRequest request) {
if (request.getInstance().isEmpty() && StringUtils.isNotBlank(request.getTemplateId())) {
request.setInstance(cleaningTaskService.getInstanceByTemplateId(request.getTemplateId()));
}
return cleaningTaskService.createTask(request);
}
@@ -57,6 +58,13 @@ public class CleaningTaskController {
return taskId;
}
@DeleteMapping
public void cleaningTasksDelete(@RequestParam List<String> taskIds) {
for (String taskId : taskIds) {
cleaningTaskService.deleteTask(taskId);
}
}
@GetMapping("/{taskId}/result")
public List<CleaningResultDto> cleaningTasksTaskIdGetResult(@PathVariable("taskId") String taskId) {
return cleaningTaskService.getTaskResults(taskId);

View File

@@ -102,261 +102,261 @@ spec:
{{- end }}
containers:
{{- $replicaCount := int .Values.replicaCount }}
{{- $peerPort := int .Values.containerPorts.peer }}
{{- $etcdFullname := include "common.names.fullname" . }}
{{- $releaseNamespace := .Release.Namespace }}
{{- $etcdHeadlessServiceName := (printf "%s-%s" $etcdFullname "headless" | trunc 63 | trimSuffix "-") }}
{{- $clusterDomain := .Values.clusterDomain }}
{{- $etcdPeerProtocol := include "etcd.peerProtocol" . }}
{{- $etcdClientProtocol := include "etcd.clientProtocol" . }}
- name: etcd
image: {{ include "etcd.image" . }}
imagePullPolicy: {{ .Values.image.pullPolicy | quote }}
{{- if .Values.containerSecurityContext.enabled }}
securityContext: {{- omit .Values.containerSecurityContext "enabled" | toYaml | nindent 12 }}
{{- $peerPort := int .Values.containerPorts.peer }}
{{- $etcdFullname := include "common.names.fullname" . }}
{{- $releaseNamespace := .Release.Namespace }}
{{- $etcdHeadlessServiceName := (printf "%s-%s" $etcdFullname "headless" | trunc 63 | trimSuffix "-") }}
{{- $clusterDomain := .Values.clusterDomain }}
{{- $etcdPeerProtocol := include "etcd.peerProtocol" . }}
{{- $etcdClientProtocol := include "etcd.clientProtocol" . }}
- name: etcd
image: {{ include "etcd.image" . }}
imagePullPolicy: {{ .Values.image.pullPolicy | quote }}
{{- if .Values.containerSecurityContext.enabled }}
securityContext: {{- omit .Values.containerSecurityContext "enabled" | toYaml | nindent 14 }}
{{- end }}
{{- if .Values.diagnosticMode.enabled }}
command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 14 }}
{{- else if .Values.command }}
command: {{- include "common.tplvalues.render" (dict "value" .Values.command "context" $) | nindent 14 }}
{{- end }}
{{- if .Values.diagnosticMode.enabled }}
args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 14 }}
{{- else if .Values.args }}
args: {{- include "common.tplvalues.render" (dict "value" .Values.args "context" $) | nindent 14 }}
{{- end }}
env:
- name: BITNAMI_DEBUG
value: {{ ternary "true" "false" (or .Values.image.debug .Values.diagnosticMode.enabled) | quote }}
- name: MY_POD_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
- name: MY_POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: MY_STS_NAME
value: {{ include "common.names.fullname" . | quote }}
- name: ETCDCTL_API
value: "3"
- name: ETCD_ON_K8S
value: "yes"
- name: ETCD_START_FROM_SNAPSHOT
value: {{ ternary "yes" "no" .Values.startFromSnapshot.enabled | quote }}
- name: ETCD_DISASTER_RECOVERY
value: {{ ternary "yes" "no" .Values.disasterRecovery.enabled | quote }}
- name: ETCD_NAME
value: "$(MY_POD_NAME)"
- name: ETCD_DATA_DIR
value: "/bitnami/etcd/data"
- name: ETCD_LOG_LEVEL
value: {{ ternary "debug" .Values.logLevel .Values.image.debug | quote }}
- name: ALLOW_NONE_AUTHENTICATION
value: {{ ternary "yes" "no" (and (not (or .Values.auth.rbac.create .Values.auth.rbac.enabled)) .Values.auth.rbac.allowNoneAuthentication) | quote }}
{{- if or .Values.auth.rbac.create .Values.auth.rbac.enabled }}
- name: ETCD_ROOT_PASSWORD
valueFrom:
secretKeyRef:
name: {{ include "etcd.secretName" . }}
key: {{ include "etcd.secretPasswordKey" . }}
{{- end }}
{{- if .Values.diagnosticMode.enabled }}
command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 14 }}
{{- else if .Values.command }}
command: {{- include "common.tplvalues.render" (dict "value" .Values.command "context" $) | nindent 14 }}
{{- if .Values.auth.token.enabled }}
- name: ETCD_AUTH_TOKEN
{{- if eq .Values.auth.token.type "jwt" }}
value: {{ printf "jwt,priv-key=/opt/bitnami/etcd/certs/token/%s,sign-method=%s,ttl=%s" .Values.auth.token.privateKey.filename .Values.auth.token.signMethod .Values.auth.token.ttl | quote }}
{{- else if eq .Values.auth.token.type "simple" }}
value: "simple"
{{- end }}
{{- end }}
{{- if .Values.diagnosticMode.enabled }}
args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 14 }}
{{- else if .Values.args }}
args: {{- include "common.tplvalues.render" (dict "value" .Values.args "context" $) | nindent 14 }}
# 警告:以下 Env Vars 依赖 StatefulSet 命名 (headless service 和 ordered names)
# 在 Deployment 中如果不修改副本数为 1,这些配置会导致集群发现失败。
- name: ETCD_ADVERTISE_CLIENT_URLS
value: "{{ $etcdClientProtocol }}://$(MY_POD_NAME).{{ $etcdHeadlessServiceName }}.{{ .Release.Namespace }}.svc.{{ $clusterDomain }}:{{ .Values.containerPorts.client }},{{ $etcdClientProtocol }}://{{ $etcdFullname }}.{{ .Release.Namespace }}.svc.{{ $clusterDomain }}:{{ coalesce .Values.service.ports.client .Values.service.port }}"
- name: ETCD_LISTEN_CLIENT_URLS
value: "{{ $etcdClientProtocol }}://0.0.0.0:{{ .Values.containerPorts.client }}"
- name: ETCD_INITIAL_ADVERTISE_PEER_URLS
value: "{{ $etcdPeerProtocol }}://$(MY_POD_NAME).{{ $etcdHeadlessServiceName }}.{{ .Release.Namespace }}.svc.{{ $clusterDomain }}:{{ .Values.containerPorts.peer }}"
- name: ETCD_LISTEN_PEER_URLS
value: "{{ $etcdPeerProtocol }}://0.0.0.0:{{ .Values.containerPorts.peer }}"
{{- if .Values.autoCompactionMode }}
- name: ETCD_AUTO_COMPACTION_MODE
value: {{ .Values.autoCompactionMode | quote }}
{{- end }}
env:
- name: BITNAMI_DEBUG
value: {{ ternary "true" "false" (or .Values.image.debug .Values.diagnosticMode.enabled) | quote }}
- name: MY_POD_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
- name: MY_POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: MY_STS_NAME
value: {{ include "common.names.fullname" . | quote }}
- name: ETCDCTL_API
value: "3"
- name: ETCD_ON_K8S
value: "yes"
- name: ETCD_START_FROM_SNAPSHOT
value: {{ ternary "yes" "no" .Values.startFromSnapshot.enabled | quote }}
- name: ETCD_DISASTER_RECOVERY
value: {{ ternary "yes" "no" .Values.disasterRecovery.enabled | quote }}
- name: ETCD_NAME
value: "$(MY_POD_NAME)"
- name: ETCD_DATA_DIR
value: "/bitnami/etcd/data"
- name: ETCD_LOG_LEVEL
value: {{ ternary "debug" .Values.logLevel .Values.image.debug | quote }}
- name: ALLOW_NONE_AUTHENTICATION
value: {{ ternary "yes" "no" (and (not (or .Values.auth.rbac.create .Values.auth.rbac.enabled)) .Values.auth.rbac.allowNoneAuthentication) | quote }}
{{- if or .Values.auth.rbac.create .Values.auth.rbac.enabled }}
- name: ETCD_ROOT_PASSWORD
valueFrom:
secretKeyRef:
name: {{ include "etcd.secretName" . }}
key: {{ include "etcd.secretPasswordKey" . }}
{{- end }}
{{- if .Values.auth.token.enabled }}
- name: ETCD_AUTH_TOKEN
{{- if eq .Values.auth.token.type "jwt" }}
value: {{ printf "jwt,priv-key=/opt/bitnami/etcd/certs/token/%s,sign-method=%s,ttl=%s" .Values.auth.token.privateKey.filename .Values.auth.token.signMethod .Values.auth.token.ttl | quote }}
{{- else if eq .Values.auth.token.type "simple" }}
value: "simple"
{{- end }}
{{- end }}
# 警告:以下 Env Vars 依赖 StatefulSet 命名 (headless service 和 ordered names)
# 在 Deployment 中如果不修改副本数为 1,这些配置会导致集群发现失败。
- name: ETCD_ADVERTISE_CLIENT_URLS
value: "{{ $etcdClientProtocol }}://$(MY_POD_NAME).{{ $etcdHeadlessServiceName }}.{{ .Release.Namespace }}.svc.{{ $clusterDomain }}:{{ .Values.containerPorts.client }},{{ $etcdClientProtocol }}://{{ $etcdFullname }}.{{ .Release.Namespace }}.svc.{{ $clusterDomain }}:{{ coalesce .Values.service.ports.client .Values.service.port }}"
- name: ETCD_LISTEN_CLIENT_URLS
value: "{{ $etcdClientProtocol }}://0.0.0.0:{{ .Values.containerPorts.client }}"
- name: ETCD_INITIAL_ADVERTISE_PEER_URLS
value: "{{ $etcdPeerProtocol }}://$(MY_POD_NAME).{{ $etcdHeadlessServiceName }}.{{ .Release.Namespace }}.svc.{{ $clusterDomain }}:{{ .Values.containerPorts.peer }}"
- name: ETCD_LISTEN_PEER_URLS
value: "{{ $etcdPeerProtocol }}://0.0.0.0:{{ .Values.containerPorts.peer }}"
{{- if .Values.autoCompactionMode }}
- name: ETCD_AUTO_COMPACTION_MODE
value: {{ .Values.autoCompactionMode | quote }}
{{- end }}
{{- if .Values.autoCompactionRetention }}
- name: ETCD_AUTO_COMPACTION_RETENTION
value: {{ .Values.autoCompactionRetention | quote }}
{{- end }}
{{- if .Values.maxProcs }}
- name: GOMAXPROCS
value: {{ .Values.maxProcs }}
{{- end }}
{{- if gt $replicaCount 1 }}
- name: ETCD_INITIAL_CLUSTER_TOKEN
value: "etcd-cluster-k8s"
- name: ETCD_INITIAL_CLUSTER_STATE
value: {{ default (ternary "new" "existing" .Release.IsInstall) .Values.initialClusterState | quote }}
{{- $initialCluster := list }}
{{- range $e, $i := until $replicaCount }}
{{- $initialCluster = append $initialCluster (printf "%s-%d=%s://%s-%d.%s.%s.svc.%s:%d" $etcdFullname $i $etcdPeerProtocol $etcdFullname $i $etcdHeadlessServiceName $releaseNamespace $clusterDomain $peerPort) }}
{{- end }}
- name: ETCD_INITIAL_CLUSTER
value: {{ join "," $initialCluster | quote }}
{{- end }}
- name: ETCD_CLUSTER_DOMAIN
value: {{ printf "%s.%s.svc.%s" $etcdHeadlessServiceName $releaseNamespace $clusterDomain | quote }}
{{- if and .Values.auth.client.secureTransport .Values.auth.client.useAutoTLS }}
- name: ETCD_AUTO_TLS
value: "true"
{{- else if .Values.auth.client.secureTransport }}
- name: ETCD_CERT_FILE
value: "/opt/bitnami/etcd/certs/client/{{ .Values.auth.client.certFilename }}"
- name: ETCD_KEY_FILE
value: "/opt/bitnami/etcd/certs/client/{{ .Values.auth.client.certKeyFilename }}"
{{- if .Values.auth.client.enableAuthentication }}
- name: ETCD_CLIENT_CERT_AUTH
value: "true"
- name: ETCD_TRUSTED_CA_FILE
value: "/opt/bitnami/etcd/certs/client/{{ .Values.auth.client.caFilename | default "ca.crt" }}"
{{- else if .Values.auth.client.caFilename }}
- name: ETCD_TRUSTED_CA_FILE
value: "/opt/bitnami/etcd/certs/client/{{ .Values.auth.client.caFilename | default "ca.crt" }}"
{{- end }}
{{- end }}
{{- if and .Values.auth.peer.secureTransport .Values.auth.peer.useAutoTLS }}
- name: ETCD_PEER_AUTO_TLS
value: "true"
{{- else if .Values.auth.peer.secureTransport }}
- name: ETCD_PEER_CERT_FILE
value: "/opt/bitnami/etcd/certs/peer/{{ .Values.auth.peer.certFilename }}"
- name: ETCD_PEER_KEY_FILE
value: "/opt/bitnami/etcd/certs/peer/{{ .Values.auth.peer.certKeyFilename }}"
{{- if .Values.auth.peer.enableAuthentication }}
- name: ETCD_PEER_CLIENT_CERT_AUTH
value: "true"
- name: ETCD_PEER_TRUSTED_CA_FILE
value: "/opt/bitnami/etcd/certs/peer/{{ .Values.auth.peer.caFilename | default "ca.crt" }}"
{{- else if .Values.auth.peer.caFilename }}
- name: ETCD_PEER_TRUSTED_CA_FILE
value: "/opt/bitnami/etcd/certs/peer/{{ .Values.auth.peer.caFilename | default "ca.crt" }}"
{{- end }}
{{- end }}
{{- if .Values.startFromSnapshot.enabled }}
- name: ETCD_INIT_SNAPSHOT_FILENAME
value: {{ .Values.startFromSnapshot.snapshotFilename | quote }}
- name: ETCD_INIT_SNAPSHOTS_DIR
value: {{ ternary "/snapshots" "/init-snapshot" (and .Values.disasterRecovery.enabled (not .Values.disasterRecovery.pvc.existingClaim)) | quote }}
{{- end }}
{{- if .Values.extraEnvVars }}
{{- include "common.tplvalues.render" (dict "value" .Values.extraEnvVars "context" $) | nindent 14 }}
{{- end }}
envFrom:
{{- if .Values.extraEnvVarsCM }}
- configMapRef:
name: {{ include "common.tplvalues.render" (dict "value" .Values.extraEnvVarsCM "context" $) }}
{{- end }}
{{- if .Values.extraEnvVarsSecret }}
- secretRef:
name: {{ include "common.tplvalues.render" (dict "value" .Values.extraEnvVarsSecret "context" $) }}
{{- end }}
ports:
- name: client
containerPort: {{ .Values.containerPorts.client }}
protocol: TCP
- name: peer
containerPort: {{ .Values.containerPorts.peer }}
protocol: TCP
{{- if not .Values.diagnosticMode.enabled }}
{{- if .Values.customLivenessProbe }}
livenessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.customLivenessProbe "context" $) | nindent 14 }}
{{- else if .Values.livenessProbe.enabled }}
livenessProbe:
{{- if .Values.autoCompactionRetention }}
- name: ETCD_AUTO_COMPACTION_RETENTION
value: {{ .Values.autoCompactionRetention | quote }}
{{- end }}
{{- if .Values.maxProcs }}
- name: GOMAXPROCS
value: {{ .Values.maxProcs }}
{{- end }}
{{- if gt $replicaCount 1 }}
- name: ETCD_INITIAL_CLUSTER_TOKEN
value: "etcd-cluster-k8s"
- name: ETCD_INITIAL_CLUSTER_STATE
value: {{ default (ternary "new" "existing" .Release.IsInstall) .Values.initialClusterState | quote }}
{{- $initialCluster := list }}
{{- range $e, $i := until $replicaCount }}
{{- $initialCluster = append $initialCluster (printf "%s-%d=%s://%s-%d.%s.%s.svc.%s:%d" $etcdFullname $i $etcdPeerProtocol $etcdFullname $i $etcdHeadlessServiceName $releaseNamespace $clusterDomain $peerPort) }}
{{- end }}
- name: ETCD_INITIAL_CLUSTER
value: {{ join "," $initialCluster | quote }}
{{- end }}
- name: ETCD_CLUSTER_DOMAIN
value: {{ printf "%s.%s.svc.%s" $etcdHeadlessServiceName $releaseNamespace $clusterDomain | quote }}
{{- if and .Values.auth.client.secureTransport .Values.auth.client.useAutoTLS }}
- name: ETCD_AUTO_TLS
value: "true"
{{- else if .Values.auth.client.secureTransport }}
- name: ETCD_CERT_FILE
value: "/opt/bitnami/etcd/certs/client/{{ .Values.auth.client.certFilename }}"
- name: ETCD_KEY_FILE
value: "/opt/bitnami/etcd/certs/client/{{ .Values.auth.client.certKeyFilename }}"
{{- if .Values.auth.client.enableAuthentication }}
- name: ETCD_CLIENT_CERT_AUTH
value: "true"
- name: ETCD_TRUSTED_CA_FILE
value: "/opt/bitnami/etcd/certs/client/{{ .Values.auth.client.caFilename | default "ca.crt" }}"
{{- else if .Values.auth.client.caFilename }}
- name: ETCD_TRUSTED_CA_FILE
value: "/opt/bitnami/etcd/certs/client/{{ .Values.auth.client.caFilename | default "ca.crt" }}"
{{- end }}
{{- end }}
{{- if and .Values.auth.peer.secureTransport .Values.auth.peer.useAutoTLS }}
- name: ETCD_PEER_AUTO_TLS
value: "true"
{{- else if .Values.auth.peer.secureTransport }}
- name: ETCD_PEER_CERT_FILE
value: "/opt/bitnami/etcd/certs/peer/{{ .Values.auth.peer.certFilename }}"
- name: ETCD_PEER_KEY_FILE
value: "/opt/bitnami/etcd/certs/peer/{{ .Values.auth.peer.certKeyFilename }}"
{{- if .Values.auth.peer.enableAuthentication }}
- name: ETCD_PEER_CLIENT_CERT_AUTH
value: "true"
- name: ETCD_PEER_TRUSTED_CA_FILE
value: "/opt/bitnami/etcd/certs/peer/{{ .Values.auth.peer.caFilename | default "ca.crt" }}"
{{- else if .Values.auth.peer.caFilename }}
- name: ETCD_PEER_TRUSTED_CA_FILE
value: "/opt/bitnami/etcd/certs/peer/{{ .Values.auth.peer.caFilename | default "ca.crt" }}"
{{- end }}
{{- end }}
{{- if .Values.startFromSnapshot.enabled }}
- name: ETCD_INIT_SNAPSHOT_FILENAME
value: {{ .Values.startFromSnapshot.snapshotFilename | quote }}
- name: ETCD_INIT_SNAPSHOTS_DIR
value: {{ ternary "/snapshots" "/init-snapshot" (and .Values.disasterRecovery.enabled (not .Values.disasterRecovery.pvc.existingClaim)) | quote }}
{{- end }}
{{- if .Values.extraEnvVars }}
{{- include "common.tplvalues.render" (dict "value" .Values.extraEnvVars "context" $) | nindent 14 }}
{{- end }}
envFrom:
{{- if .Values.extraEnvVarsCM }}
- configMapRef:
name: {{ include "common.tplvalues.render" (dict "value" .Values.extraEnvVarsCM "context" $) }}
{{- end }}
{{- if .Values.extraEnvVarsSecret }}
- secretRef:
name: {{ include "common.tplvalues.render" (dict "value" .Values.extraEnvVarsSecret "context" $) }}
{{- end }}
ports:
- name: client
containerPort: {{ .Values.containerPorts.client }}
protocol: TCP
- name: peer
containerPort: {{ .Values.containerPorts.peer }}
protocol: TCP
{{- if not .Values.diagnosticMode.enabled }}
{{- if .Values.customLivenessProbe }}
livenessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.customLivenessProbe "context" $) | nindent 14 }}
{{- else if .Values.livenessProbe.enabled }}
livenessProbe:
exec:
command:
- /opt/bitnami/scripts/etcd/healthcheck.sh
initialDelaySeconds: {{ .Values.livenessProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.livenessProbe.periodSeconds }}
timeoutSeconds: {{ .Values.livenessProbe.timeoutSeconds }}
successThreshold: {{ .Values.livenessProbe.successThreshold }}
failureThreshold: {{ .Values.livenessProbe.failureThreshold }}
{{- end }}
{{- if .Values.customReadinessProbe }}
readinessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.customReadinessProbe "context" $) | nindent 14 }}
{{- else if .Values.readinessProbe.enabled }}
readinessProbe:
exec:
command:
- /opt/bitnami/scripts/etcd/healthcheck.sh
initialDelaySeconds: {{ .Values.readinessProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.readinessProbe.periodSeconds }}
timeoutSeconds: {{ .Values.readinessProbe.timeoutSeconds }}
successThreshold: {{ .Values.readinessProbe.successThreshold }}
failureThreshold: {{ .Values.readinessProbe.failureThreshold }}
{{- end }}
{{- if .Values.customStartupProbe }}
startupProbe: {{- include "common.tplvalues.render" (dict "value" .Values.customStartupProbe "context" $) | nindent 14 }}
{{- else if .Values.startupProbe.enabled }}
startupProbe:
exec:
command:
- /opt/bitnami/scripts/etcd/healthcheck.sh
initialDelaySeconds: {{ .Values.startupProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.startupProbe.periodSeconds }}
timeoutSeconds: {{ .Values.startupProbe.timeoutSeconds }}
successThreshold: {{ .Values.startupProbe.successThreshold }}
failureThreshold: {{ .Values.startupProbe.failureThreshold }}
{{- end }}
{{- if .Values.lifecycleHooks }}
lifecycle: {{- include "common.tplvalues.render" (dict "value" .Values.lifecycleHooks "context" $) | nindent 14 }}
{{- else if and (gt $replicaCount 1) .Values.removeMemberOnContainerTermination }}
lifecycle:
preStop:
exec:
command:
- /opt/bitnami/scripts/etcd/healthcheck.sh
initialDelaySeconds: {{ .Values.livenessProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.livenessProbe.periodSeconds }}
timeoutSeconds: {{ .Values.livenessProbe.timeoutSeconds }}
successThreshold: {{ .Values.livenessProbe.successThreshold }}
failureThreshold: {{ .Values.livenessProbe.failureThreshold }}
- /opt/bitnami/scripts/etcd/prestop.sh
{{- end }}
{{- end }}
{{- if .Values.resources }}
resources: {{- include "common.tplvalues.render" (dict "value" .Values.resources "context" $) | nindent 14 }}
{{- end }}
volumeMounts:
- name: data
mountPath: /bitnami/etcd
{{- if and (eq .Values.auth.token.enabled true) (eq .Values.auth.token.type "jwt") }}
- name: etcd-jwt-token
mountPath: /opt/bitnami/etcd/certs/token/
readOnly: true
{{- end }}
{{- if .Values.customReadinessProbe }}
readinessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.customReadinessProbe "context" $) | nindent 14 }}
{{- else if .Values.readinessProbe.enabled }}
readinessProbe:
exec:
command:
- /opt/bitnami/scripts/etcd/healthcheck.sh
initialDelaySeconds: {{ .Values.readinessProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.readinessProbe.periodSeconds }}
timeoutSeconds: {{ .Values.readinessProbe.timeoutSeconds }}
successThreshold: {{ .Values.readinessProbe.successThreshold }}
failureThreshold: {{ .Values.readinessProbe.failureThreshold }}
{{- if or (and .Values.startFromSnapshot.enabled (not .Values.disasterRecovery.enabled)) (and .Values.disasterRecovery.enabled .Values.startFromSnapshot.enabled .Values.disasterRecovery.pvc.existingClaim) }}
- name: init-snapshot-volume
mountPath: /init-snapshot
{{- end }}
{{- if .Values.customStartupProbe }}
startupProbe: {{- include "common.tplvalues.render" (dict "value" .Values.customStartupProbe "context" $) | nindent 14 }}
{{- else if .Values.startupProbe.enabled }}
startupProbe:
exec:
command:
- /opt/bitnami/scripts/etcd/healthcheck.sh
initialDelaySeconds: {{ .Values.startupProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.startupProbe.periodSeconds }}
timeoutSeconds: {{ .Values.startupProbe.timeoutSeconds }}
successThreshold: {{ .Values.startupProbe.successThreshold }}
failureThreshold: {{ .Values.startupProbe.failureThreshold }}
{{- if or .Values.disasterRecovery.enabled (and .Values.disasterRecovery.enabled .Values.startFromSnapshot.enabled) }}
- name: snapshot-volume
mountPath: /snapshots
{{- if .Values.disasterRecovery.pvc.subPath }}
subPath: {{ .Values.disasterRecovery.pvc.subPath }}
{{- end }}
{{- end }}
{{- if .Values.lifecycleHooks }}
lifecycle: {{- include "common.tplvalues.render" (dict "value" .Values.lifecycleHooks "context" $) | nindent 14 }}
{{- else if and (gt $replicaCount 1) .Values.removeMemberOnContainerTermination }}
lifecycle:
preStop:
exec:
command:
- /opt/bitnami/scripts/etcd/prestop.sh
{{- if or .Values.configuration .Values.existingConfigmap }}
- name: etcd-config
mountPath: /opt/bitnami/etcd/conf/
{{- end }}
{{- if or .Values.auth.client.enableAuthentication (and .Values.auth.client.secureTransport (not .Values.auth.client.useAutoTLS )) }}
- name: etcd-client-certs
mountPath: /opt/bitnami/etcd/certs/client/
readOnly: true
{{- end }}
{{- if .Values.resources }}
resources: {{- include "common.tplvalues.render" (dict "value" .Values.resources "context" $) | nindent 14 }}
{{- if or .Values.auth.peer.enableAuthentication (and .Values.auth.peer.secureTransport (not .Values.auth.peer.useAutoTLS )) }}
- name: etcd-peer-certs
mountPath: /opt/bitnami/etcd/certs/peer/
readOnly: true
{{- end }}
{{- if .Values.extraVolumeMounts }}
{{- include "common.tplvalues.render" (dict "value" .Values.extraVolumeMounts "context" $) | nindent 12 }}
{{- end }}
volumeMounts:
- name: data
mountPath: /bitnami/etcd
{{- if and (eq .Values.auth.token.enabled true) (eq .Values.auth.token.type "jwt") }}
- name: etcd-jwt-token
mountPath: /opt/bitnami/etcd/certs/token/
readOnly: true
{{- end }}
{{- if or (and .Values.startFromSnapshot.enabled (not .Values.disasterRecovery.enabled)) (and .Values.disasterRecovery.enabled .Values.startFromSnapshot.enabled .Values.disasterRecovery.pvc.existingClaim) }}
- name: init-snapshot-volume
mountPath: /init-snapshot
{{- end }}
{{- if or .Values.disasterRecovery.enabled (and .Values.disasterRecovery.enabled .Values.startFromSnapshot.enabled) }}
- name: snapshot-volume
mountPath: /snapshots
{{- if .Values.disasterRecovery.pvc.subPath }}
subPath: {{ .Values.disasterRecovery.pvc.subPath }}
{{- end }}
{{- end }}
{{- if or .Values.configuration .Values.existingConfigmap }}
- name: etcd-config
mountPath: /opt/bitnami/etcd/conf/
{{- end }}
{{- if or .Values.auth.client.enableAuthentication (and .Values.auth.client.secureTransport (not .Values.auth.client.useAutoTLS )) }}
- name: etcd-client-certs
mountPath: /opt/bitnami/etcd/certs/client/
readOnly: true
{{- end }}
{{- if or .Values.auth.peer.enableAuthentication (and .Values.auth.peer.secureTransport (not .Values.auth.peer.useAutoTLS )) }}
- name: etcd-peer-certs
mountPath: /opt/bitnami/etcd/certs/peer/
readOnly: true
{{- end }}
{{- if .Values.extraVolumeMounts }}
{{- include "common.tplvalues.render" (dict "value" .Values.extraVolumeMounts "context" $) | nindent 12 }}
{{- end }}
{{- if .Values.sidecars }}
{{- include "common.tplvalues.render" (dict "value" .Values.sidecars "context" $) | nindent 8 }}
{{- include "common.tplvalues.render" (dict "value" .Values.sidecars "context" $) | nindent 10 }}
{{- end }}
volumes:
{{- if and (eq .Values.auth.token.enabled true) (eq .Values.auth.token.type "jwt") }}

View File

@@ -17,7 +17,7 @@ spec:
- {{ . | quote }}
{{- end }}
persistentVolumeReclaimPolicy: Delete
storageClassName: {{ include "common.storage.class" (dict "persistence" .Values.persistence "global" .Values.global) }}
{{ include "common.storage.class" (dict "persistence" .Values.persistence "global" .Values.global) }}
local: # local类型
path: {{ .Values.persistence.storagePath | default "/opt/milvus/data" }}/etcd
claimRef:

View File

@@ -38,6 +38,8 @@ export default function CleansingTaskCreate() {
...item.defaultParams,
...item.overrides,
},
inputs: item.inputs,
outputs: item.outputs,
})),
};
navigate("/data/cleansing?view=task");

View File

@@ -44,6 +44,8 @@ export default function CleansingTemplateCreate() {
...item.defaultParams,
...item.overrides,
},
inputs: item.inputs,
outputs: item.outputs,
})),
};

View File

@@ -107,7 +107,7 @@ export default function FileTable({result, fetchTaskResult}) {
onFilter: (value: string, record: any) =>
record.srcName.toLowerCase().includes(value.toLowerCase()),
render: (text: string) => (
<span className="font-mono text-sm">{text?.replace(/\.[^/.]+$/, "")}</span>
<span>{text?.replace(/\.[^/.]+$/, "")}</span>
),
},
{

View File

@@ -45,6 +45,13 @@ export default function TemplateList() {
};
const templateColumns = [
{
title: "模板ID",
dataIndex: "id",
key: "id",
fixed: "left",
width: 100,
},
{
title: "模板名称",
dataIndex: "name",

View File

@@ -70,7 +70,7 @@ INSERT IGNORE INTO t_operator
VALUES ('TextFormatter', 'TXT文本抽取', '抽取TXT中的文本。', '1.0.0', 'text', 'text', null, null, '', false),
('UnstructuredFormatter', 'Unstructured文本抽取', '基于Unstructured抽取非结构化文件的文本,目前支持PowerPoint演示文稿、Word文档以及Excel工作簿。', '1.0.0', 'text', 'text', null, null, '', false),
('MineruFormatter', 'MinerU PDF文本抽取', '基于MinerU API,抽取PDF中的文本。', '1.0.0', 'text', 'text', null, null, '', false),
('FileExporter', '落盘算子', '将文件保存到本地目录。', '1.0.0', 'all', 'all', null, null, '', false),
('FileExporter', '落盘算子', '将文件保存到本地目录。', '1.0.0', 'multimodal', 'multimodal', null, null, '', false),
('FileWithHighRepeatPhraseRateFilter', '文档词重复率检查', '去除重复词过多的文档。', '1.0.0', 'text', 'text', null, '{"repeatPhraseRatio": {"name": "文档词重复率", "description": "某个词的统计数/文档总词数 > 设定值,该文档被去除。", "type": "slider", "defaultVal": 0.5, "min": 0, "max": 1, "step": 0.1}, "hitStopwords": {"name": "去除停用词", "description": "统计重复词时,选择是否要去除停用词。", "type": "switch", "defaultVal": false, "required": true, "checkedLabel": "去除", "unCheckedLabel": "不去除"}}', '', 'false'),
('FileWithHighRepeatWordRateFilter', '文档字重复率检查', '去除重复字过多的文档。', '1.0.0', 'text', 'text', null, '{"repeatWordRatio": {"name": "文档字重复率", "description": "某个字的统计数/文档总字数 > 设定值,该文档被去除。", "type": "slider", "defaultVal": 0.5, "min": 0, "max": 1, "step": 0.1}}', '', 'false'),
('FileWithHighSpecialCharRateFilter', '文档特殊字符率检查', '去除特殊字符过多的文档。', '1.0.0', 'text', 'text', null, '{"specialCharRatio": {"name": "文档特殊字符率", "description": "特殊字符的统计数/文档总字数 > 设定值,该文档被去除。", "type": "slider", "defaultVal": 0.3, "min": 0, "max": 1, "step": 0.1}}', '', 'false'),