Files
knowledge-governance/internal/connectors/pp/plan.go
T
zheromiku dcdc8d1ddd feat: 知识治理平台(含已验证发布/回滚契约)
全栈知识治理平台首次入库(P1-P10 + 发布链路模拟验证闭环):

- 治理核心:源目录/变更集/人工审核/发布批次/发布执行(fail-closed 闸口)
- 测试通道:WeKnora 测试 KB 上传/轮询/验收;poll 完成时写入
  parser_generation/index_generation,修复 manual/seed 路径发布闸口永久拦截
- 发布适配器 v071(本地 source=测试角色 / 云端 target=生产角色 模拟验证通过):
  * ES 导出/导入 mapping 自适应(.keyword 子字段、可选 tenant_id)
  * OSS locator 支持嵌套 scheme;chunks.seq_id 由目标序列分配
  * bundle 归档同身份重试原子替换;verifier 按 bundle chunk_type 计数
  * 回滚 job payload 支持 prior_execution_id(strict 解码)
- 三通道发布+回滚演练实测:publish 4/4 verified,检索命中,
  rollback 4/4 rolled_back,目标端 PG is_enabled=false、ES is_enabled=false
- 前端 A·Data-console 风格全站统一,120 用例通过
- 门禁:go vet / go test 全包通过,gofmt 干净
2026-09-30 10:54:06 +08:00

151 lines
4.8 KiB
Go

package pp
import (
"crypto/sha256"
"encoding/hex"
"encoding/json"
"fmt"
"sort"
"strconv"
"knowledge-governance/internal/governance"
)
type ImportPlan struct {
Connection governance.SourceConnection
SourceItems []governance.SourceItem
ContentObjects []governance.ContentObject
Versions []governance.SourceItemVersion
Publications []governance.Publication
}
func BuildImportPlan(snapshot Snapshot) (ImportPlan, error) {
if err := ValidateSnapshot(snapshot); err != nil {
return ImportPlan{}, err
}
connectionID := stableID("sc", snapshot.KBID)
plan := ImportPlan{
Connection: governance.SourceConnection{
ID: connectionID,
Type: governance.SourceTypePP,
Name: "PP legacy " + connectionID,
SecretRef: "",
Enabled: false,
},
SourceItems: make([]governance.SourceItem, 0, len(snapshot.Items)),
ContentObjects: make([]governance.ContentObject, 0),
Versions: make([]governance.SourceItemVersion, 0, len(snapshot.Items)),
Publications: make([]governance.Publication, 0),
}
contentBySHA := make(map[string]governance.ContentObject)
publicationByKnowledgeID := make(map[string]struct{})
for _, item := range snapshot.Items {
itemID := stableID("si", connectionID, item.SourceURLHash)
sizeBytes := item.Bytes
revision := item.SHA256
if item.Status == StatusOverLimit {
revision = metadataRevision(item)
}
plan.SourceItems = append(plan.SourceItems, governance.SourceItem{
ID: itemID,
SourceConnectionID: connectionID,
StableExternalID: item.SourceURLHash,
CanonicalURIHash: item.SourceURLHash,
Title: "",
ItemType: governance.ItemTypeDocument,
SizeBytes: &sizeBytes,
Revision: revision,
Visibility: governance.VisibilityExternal,
VisibilityOrigin: governance.VisibilityOriginPPPublicTag,
SourceChange: governance.SourceChangeUnchanged,
})
rawSummary := map[string]any{
"legacy_status": item.Status,
"source_ids": item.SourceIDs,
}
if item.Status == StatusContentAlias {
rawSummary["canonical_source_url_hash"] = item.CanonicalSourceURLHash
}
rawJSON, err := json.Marshal(rawSummary)
if err != nil {
return ImportPlan{}, fmt.Errorf("marshal legacy record summary: %w", err)
}
versionID := stableID("sv", itemID, revision)
if item.Status == StatusOverLimit {
plan.Versions = append(plan.Versions, governance.SourceItemVersion{
ID: versionID,
SourceItemID: itemID,
Revision: revision,
ContentState: governance.ContentOverLimit,
DownloadError: "legacy_50_mib_limit",
RawRecordSummary: rawJSON,
})
continue
}
content, ok := contentBySHA[item.SHA256]
if !ok {
content = governance.ContentObject{
ID: stableID("co", item.SHA256),
SHA256: item.SHA256,
SizeBytes: item.Bytes,
State: governance.ContentVerified,
}
contentBySHA[item.SHA256] = content
plan.ContentObjects = append(plan.ContentObjects, content)
} else if content.SizeBytes != item.Bytes {
return ImportPlan{}, fmt.Errorf("same SHA-256 has conflicting byte sizes")
}
contentID := content.ID
plan.Versions = append(plan.Versions, governance.SourceItemVersion{
ID: versionID,
SourceItemID: itemID,
Revision: item.SHA256,
ContentObjectID: &contentID,
ContentState: governance.ContentVerified,
RawRecordSummary: rawJSON,
})
if item.Status != StatusCompleted {
continue
}
if _, exists := publicationByKnowledgeID[item.KnowledgeID]; exists {
return ImportPlan{}, fmt.Errorf("completed records share a knowledge ID")
}
publicationByKnowledgeID[item.KnowledgeID] = struct{}{}
plan.Publications = append(plan.Publications, governance.Publication{
ID: stableID("tp", snapshot.KBID, item.KnowledgeID),
SourceItemVersionID: versionID,
TestKBID: snapshot.KBID,
KnowledgeID: item.KnowledgeID,
IngestState: governance.IngestUploaded,
ProcessingState: governance.ProcessingCompleted,
RetrievalState: governance.RetrievalUnpublished,
})
}
return plan, nil
}
func stableID(prefix string, parts ...string) string {
digest := sha256.New()
for _, part := range parts {
_, _ = digest.Write([]byte{0})
_, _ = digest.Write([]byte(part))
}
return prefix + "-" + hex.EncodeToString(digest.Sum(nil))[:32]
}
func metadataRevision(item Item) string {
sourceIDs := append([]string(nil), item.SourceIDs...)
sort.Strings(sourceIDs)
parts := []string{item.SourceURLHash, strconv.FormatInt(item.Bytes, 10)}
parts = append(parts, sourceIDs...)
digest := sha256.New()
for _, part := range parts {
_, _ = digest.Write([]byte{0})
_, _ = digest.Write([]byte(part))
}
return "metadata-sha256:" + hex.EncodeToString(digest.Sum(nil))
}