zheromiku
dcdc8d1ddd
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
92 lines
3.0 KiB
Go
92 lines
3.0 KiB
Go
package pp
|
|
|
|
import (
|
|
"crypto/sha256"
|
|
"encoding/hex"
|
|
"encoding/json"
|
|
"fmt"
|
|
"io"
|
|
"os"
|
|
|
|
"knowledge-governance/internal/governance"
|
|
)
|
|
|
|
type RecoveryReport struct {
|
|
Recovered int
|
|
VerifiedBytes int64
|
|
}
|
|
|
|
const LegacyMaxBytes int64 = 50 * 1024 * 1024
|
|
|
|
type manifestDocument struct {
|
|
Results []manifestItem `json:"results"`
|
|
}
|
|
|
|
type manifestItem struct {
|
|
URL string `json:"url"`
|
|
LocalPath string `json:"local_path"`
|
|
Bytes int64 `json:"bytes"`
|
|
SHA256 string `json:"sha256"`
|
|
Status string `json:"status"`
|
|
SourceIDs []string `json:"source_ids"`
|
|
}
|
|
|
|
func RecoverMissingSHA256(snapshot Snapshot, reader io.Reader) (Snapshot, RecoveryReport, error) {
|
|
var manifest manifestDocument
|
|
if err := json.NewDecoder(reader).Decode(&manifest); err != nil {
|
|
return Snapshot{}, RecoveryReport{}, fmt.Errorf("decode download manifest: %w", err)
|
|
}
|
|
bySourceHash := make(map[string]manifestItem, len(manifest.Results))
|
|
for _, item := range manifest.Results {
|
|
digest := sha256.Sum256([]byte(item.URL))
|
|
bySourceHash[hex.EncodeToString(digest[:])] = item
|
|
}
|
|
|
|
result := snapshot
|
|
result.Items = append([]Item(nil), snapshot.Items...)
|
|
report := RecoveryReport{}
|
|
for index := range result.Items {
|
|
item := &result.Items[index]
|
|
if item.SHA256 != "" {
|
|
continue
|
|
}
|
|
artifact, ok := bySourceHash[item.SourceURLHash]
|
|
if !ok {
|
|
return Snapshot{}, RecoveryReport{}, fmt.Errorf("missing manifest artifact for source hash %s", item.SourceURLHash)
|
|
}
|
|
if !governance.ValidSHA256(artifact.SHA256) {
|
|
return Snapshot{}, RecoveryReport{}, fmt.Errorf("manifest artifact has invalid SHA-256 for source hash %s", item.SourceURLHash)
|
|
}
|
|
if artifact.Bytes != item.Bytes {
|
|
return Snapshot{}, RecoveryReport{}, fmt.Errorf("manifest size differs from ledger for source hash %s", item.SourceURLHash)
|
|
}
|
|
if artifact.Bytes > LegacyMaxBytes {
|
|
return Snapshot{}, RecoveryReport{}, fmt.Errorf("manifest artifact exceeds the legacy 50 MiB limit for source hash %s", item.SourceURLHash)
|
|
}
|
|
file, err := os.Open(artifact.LocalPath)
|
|
if err != nil {
|
|
return Snapshot{}, RecoveryReport{}, fmt.Errorf("open manifest artifact for source hash %s: %w", item.SourceURLHash, err)
|
|
}
|
|
digest := sha256.New()
|
|
bytesRead, copyErr := io.Copy(digest, file)
|
|
closeErr := file.Close()
|
|
if copyErr != nil {
|
|
return Snapshot{}, RecoveryReport{}, fmt.Errorf("hash manifest artifact for source hash %s: %w", item.SourceURLHash, copyErr)
|
|
}
|
|
if closeErr != nil {
|
|
return Snapshot{}, RecoveryReport{}, fmt.Errorf("close manifest artifact for source hash %s: %w", item.SourceURLHash, closeErr)
|
|
}
|
|
if bytesRead != artifact.Bytes {
|
|
return Snapshot{}, RecoveryReport{}, fmt.Errorf("manifest artifact size mismatch for source hash %s", item.SourceURLHash)
|
|
}
|
|
actual := hex.EncodeToString(digest.Sum(nil))
|
|
if actual != artifact.SHA256 {
|
|
return Snapshot{}, RecoveryReport{}, fmt.Errorf("manifest artifact SHA-256 mismatch for source hash %s", item.SourceURLHash)
|
|
}
|
|
item.SHA256 = actual
|
|
report.Recovered++
|
|
report.VerifiedBytes += bytesRead
|
|
}
|
|
return result, report, nil
|
|
}
|