feat: add edu-industry platform demos

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-24 11:19:43 +08:00
commit 92515928d9
80 changed files with 29880 additions and 0 deletions
@@ -0,0 +1,20 @@
+# 数据契约目录
+
+所有契约使用 JSON Schema Draft 2020-12。
+
+## 发布要求
+
+1. 契约名称和版本必须唯一；
+2. 兼容变更提升次版本，修订说明或约束修复提升补丁版本；
+3. 删除字段、改变类型或收紧必填要求属于破坏性变更，必须提升主版本；
+4. 发布前执行历史样本回放、来源映射测试和下游影响分析；
+5. 交付包必须绑定精确契约版本，不允许只引用“最新版本”；
+6. Schema、样例、字段说明、代码字典和变更日志作为同一发布物。
+
+## 当前契约
+
+| 契约 | 版本 | 适用范围 |
+|---|---|---|
+| `JOB-SIGNAL` | 3.0.0 | 商业招聘平台、公共就业平台、活动聚合平台 |
+| `SCHOOL-EMPLOYMENT` | 2.2.0 | 学校就业管理系统、数据库视图、API和标准文件 |
+| `PACKAGE-MANIFEST` | 1.2.0 | 导入、导出、租户交付和归档；新增可选发布候选编号与状态 |
@@ -0,0 +1,266 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.edu-industry.cn/job-signal/3.0.0/schema.json",
+  "title": "JOB-SIGNAL V3.0 外部招聘岗位信号",
+  "description": "商业招聘平台、公共就业平台与招聘活动平台统一岗位信号契约。",
+  "type": "object",
+  "additionalProperties": false,
+  "required": [
+    "record_id",
+    "source_platform",
+    "source_record_id",
+    "source_url",
+    "collector_task_id",
+    "collector_version",
+    "raw_snapshot_id",
+    "collected_at",
+    "first_seen_at",
+    "last_seen_at",
+    "status",
+    "job_title_raw",
+    "job_description",
+    "enterprise_name",
+    "region_code",
+    "employment_type",
+    "source_payload_hash",
+    "content_hash",
+    "data_version"
+  ],
+  "properties": {
+    "record_id": {
+      "type": "string",
+      "format": "uuid",
+      "description": "平台生成的全局唯一记录标识。"
+    },
+    "source_platform": {
+      "type": "string",
+      "pattern": "^[A-Z][A-Z0-9_]{1,31}$",
+      "description": "来源平台代码，例如 BOSS、ZHAOPIN、BRZP、NCSS、MOHRSS。"
+    },
+    "source_record_id": {
+      "type": "string",
+      "minLength": 1,
+      "maxLength": 256,
+      "description": "来源平台内的记录标识，与 source_platform 组成幂等键。"
+    },
+    "source_url": {
+      "type": "string",
+      "format": "uri",
+      "maxLength": 2048,
+      "description": "可回溯的来源页面或接口定位。"
+    },
+    "collector_task_id": {
+      "type": "string",
+      "pattern": "^JOB-[A-Za-z0-9-]{8,64}$",
+      "description": "生产采集任务追踪编号。"
+    },
+    "collector_version": {
+      "type": "string",
+      "minLength": 1,
+      "maxLength": 128,
+      "description": "采集器名称、语义版本与代码提交摘要。"
+    },
+    "raw_snapshot_id": {
+      "type": "string",
+      "pattern": "^RAW-[A-Za-z0-9-]{8,96}$",
+      "description": "原始响应或页面快照编号。"
+    },
+    "collected_at": {
+      "type": "string",
+      "format": "date-time",
+      "description": "平台实际采集时间，必须包含时区。"
+    },
+    "first_seen_at": {
+      "type": "string",
+      "format": "date-time",
+      "description": "平台首次发现该岗位的时间。"
+    },
+    "last_seen_at": {
+      "type": "string",
+      "format": "date-time",
+      "description": "平台最近一次确认该岗位仍存在的时间。"
+    },
+    "published_at": {
+      "type": ["string", "null"],
+      "format": "date-time",
+      "description": "来源平台显示的岗位发布时间。"
+    },
+    "status": {
+      "type": "string",
+      "enum": ["active", "inactive", "expired", "unknown"],
+      "description": "岗位在当前数据版本中的状态。"
+    },
+    "job_title_raw": {
+      "type": "string",
+      "minLength": 1,
+      "maxLength": 200,
+      "description": "来源岗位名称原文。"
+    },
+    "job_title_normalized": {
+      "type": ["string", "null"],
+      "maxLength": 200,
+      "description": "映射到统一岗位词典后的标准名称。"
+    },
+    "job_code": {
+      "type": ["string", "null"],
+      "pattern": "^[A-Z0-9.-]{2,32}$",
+      "description": "统一岗位分类代码。"
+    },
+    "job_description": {
+      "type": "string",
+      "minLength": 1,
+      "maxLength": 30000,
+      "description": "去除展示标记与联系方式后的岗位职责和要求文本。"
+    },
+    "enterprise_name": {
+      "type": "string",
+      "minLength": 1,
+      "maxLength": 300,
+      "description": "来源企业名称原文。"
+    },
+    "enterprise_id": {
+      "type": ["string", "null"],
+      "maxLength": 128,
+      "description": "平台企业归一标识。"
+    },
+    "enterprise_credit_code": {
+      "type": ["string", "null"],
+      "pattern": "^[0-9A-Z]{18}$",
+      "description": "可公开确认时使用的统一社会信用代码。"
+    },
+    "enterprise_industry_code": {
+      "type": ["string", "null"],
+      "maxLength": 32,
+      "description": "企业所属行业代码。"
+    },
+    "enterprise_scale": {
+      "type": ["string", "null"],
+      "enum": ["micro", "small", "medium", "large", "unknown", null],
+      "description": "统一企业规模分组。"
+    },
+    "region_code": {
+      "type": "string",
+      "pattern": "^[0-9]{6}$",
+      "description": "GB/T 2260 六位行政区划代码。"
+    },
+    "workplace": {
+      "type": ["string", "null"],
+      "maxLength": 500,
+      "description": "来源工作地点文本。"
+    },
+    "employment_type": {
+      "type": "string",
+      "enum": ["full_time", "internship", "part_time", "contract", "campus", "other"],
+      "description": "统一用工或招聘类型。"
+    },
+    "recruitment_count": {
+      "type": ["integer", "null"],
+      "minimum": 0,
+      "maximum": 1000000,
+      "description": "明确披露时记录计划招聘人数。"
+    },
+    "education_level": {
+      "type": ["string", "null"],
+      "enum": ["none", "secondary", "vocational", "associate", "bachelor", "master", "doctor", "unknown", null],
+      "description": "最低学历要求。"
+    },
+    "experience_min_years": {
+      "type": ["number", "null"],
+      "minimum": 0,
+      "maximum": 60,
+      "description": "最低工作经验年限。"
+    },
+    "salary_min": {
+      "type": ["number", "null"],
+      "minimum": 0,
+      "maximum": 10000000,
+      "description": "统一折算后的税前月薪下限，单位为 salary_currency。"
+    },
+    "salary_max": {
+      "type": ["number", "null"],
+      "minimum": 0,
+      "maximum": 10000000,
+      "description": "统一折算后的税前月薪上限。"
+    },
+    "salary_currency": {
+      "type": ["string", "null"],
+      "pattern": "^[A-Z]{3}$",
+      "description": "ISO 4217 币种代码，境内岗位通常为 CNY。"
+    },
+    "salary_period": {
+      "type": ["string", "null"],
+      "enum": ["month", "year", "day", "hour", "negotiable", "unknown", null],
+      "description": "来源薪资周期，统一月薪字段与原始周期同时保留。"
+    },
+    "benefits": {
+      "type": "array",
+      "maxItems": 100,
+      "items": {
+        "type": "string",
+        "maxLength": 100
+      },
+      "uniqueItems": true,
+      "description": "福利标签。"
+    },
+    "skills": {
+      "type": "array",
+      "maxItems": 200,
+      "items": {
+        "type": "string",
+        "maxLength": 100
+      },
+      "uniqueItems": true,
+      "description": "基于技能词典提取并归一的技能标签。"
+    },
+    "keywords": {
+      "type": "array",
+      "maxItems": 200,
+      "items": {
+        "type": "string",
+        "maxLength": 100
+      },
+      "uniqueItems": true,
+      "description": "用于检索的业务关键词。"
+    },
+    "source_payload_hash": {
+      "type": "string",
+      "pattern": "^[a-f0-9]{64}$",
+      "description": "原始响应载荷 SHA-256。"
+    },
+    "content_hash": {
+      "type": "string",
+      "pattern": "^[a-f0-9]{64}$",
+      "description": "规范化业务内容 SHA-256，用于内容去重。"
+    },
+    "parsing_version": {
+      "type": ["string", "null"],
+      "maxLength": 128,
+      "description": "解析规则版本。"
+    },
+    "normalized_at": {
+      "type": ["string", "null"],
+      "format": "date-time",
+      "description": "岗位和技能归一完成时间。"
+    },
+    "data_version": {
+      "type": "string",
+      "pattern": "^V[0-9]{4}\\.[0-9]{2}\\.[0-9]{2}(?:\\.[0-9]+)?$",
+      "description": "进入分析层的数据版本。"
+    }
+  },
+  "allOf": [
+    {
+      "if": {
+        "required": ["salary_min", "salary_max"]
+      },
+      "then": {
+        "properties": {
+          "salary_max": {
+            "type": "number",
+            "minimum": 0
+          }
+        }
+      }
+    }
+  ]
+}
@@ -0,0 +1,185 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.edu-industry.cn/package-manifest/1.2.0/schema.json",
+  "title": "PACKAGE-MANIFEST V1.2 数据交付包清单",
+  "description": "数据导入、导出和租户交付使用的版本、范围、文件、质量与血缘清单。",
+  "type": "object",
+  "additionalProperties": false,
+  "required": [
+    "manifest_version",
+    "package_id",
+    "data_product",
+    "data_version",
+    "contract_name",
+    "contract_version",
+    "data_as_of",
+    "tenant_scope",
+    "record_count",
+    "quality_score",
+    "lineage_snapshot",
+    "files",
+    "generated_at",
+    "generated_by"
+  ],
+  "properties": {
+    "manifest_version": {
+      "type": "string",
+      "const": "1.2.0"
+    },
+    "package_id": {
+      "type": "string",
+      "pattern": "^EDU-PKG-[0-9]{8}-[A-Z0-9]{2,24}$",
+      "description": "数据交付包唯一编号。"
+    },
+    "release_id": {
+      "type": "string",
+      "pattern": "^REL-[0-9]{8}-[A-Z0-9-]{2,32}$",
+      "description": "生成此 Manifest 的发布候选编号。"
+    },
+    "release_status": {
+      "type": "string",
+      "enum": ["DRAFT", "PENDING_APPROVAL", "APPROVED", "REJECTED", "PUBLISHED", "ROLLED_BACK"],
+      "description": "Manifest 生成时的候选或发布状态。"
+    },
+    "data_product": {
+      "type": "string",
+      "minLength": 1,
+      "maxLength": 200,
+      "description": "平台数据产品名称或代码。"
+    },
+    "data_version": {
+      "type": "string",
+      "minLength": 1,
+      "maxLength": 128,
+      "description": "业务数据版本。"
+    },
+    "contract_name": {
+      "type": "string",
+      "pattern": "^[A-Z][A-Z0-9-]{2,63}$",
+      "description": "绑定的数据契约名称。"
+    },
+    "contract_version": {
+      "type": "string",
+      "pattern": "^[0-9]+\\.[0-9]+\\.[0-9]+$",
+      "description": "精确的数据契约版本。"
+    },
+    "data_as_of": {
+      "type": "string",
+      "format": "date",
+      "description": "交付数据业务截止日期。"
+    },
+    "tenant_scope": {
+      "type": "array",
+      "minItems": 1,
+      "maxItems": 10000,
+      "uniqueItems": true,
+      "items": {
+        "type": "string",
+        "minLength": 1,
+        "maxLength": 128
+      },
+      "description": "允许接收此交付包的租户或数据范围代码。"
+    },
+    "output_format": {
+      "type": ["string", "null"],
+      "enum": ["parquet", "csv_utf8", "jsonl", "xlsx", null],
+      "description": "主数据文件格式。"
+    },
+    "record_count": {
+      "type": "integer",
+      "minimum": 0,
+      "description": "有效业务记录总数。"
+    },
+    "quality_score": {
+      "type": "number",
+      "minimum": 0,
+      "maximum": 100,
+      "description": "与质量报告一致的综合质量评分。"
+    },
+    "quality_report_path": {
+      "type": ["string", "null"],
+      "maxLength": 1024,
+      "description": "质量报告在交付包中的相对路径。"
+    },
+    "lineage_snapshot": {
+      "type": "string",
+      "pattern": "^LINEAGE-[A-Z0-9-]{8,96}$",
+      "description": "数据血缘快照编号。"
+    },
+    "previous_stable_version": {
+      "type": ["string", "null"],
+      "maxLength": 128,
+      "description": "上一稳定版本，用于回滚和版本对比。"
+    },
+    "files": {
+      "type": "array",
+      "minItems": 1,
+      "maxItems": 10000,
+      "items": {
+        "$ref": "#/$defs/file"
+      },
+      "description": "交付包内全部文件和校验信息。"
+    },
+    "generated_at": {
+      "type": "string",
+      "format": "date-time",
+      "description": "交付包生成时间。"
+    },
+    "generated_by": {
+      "type": "string",
+      "minLength": 1,
+      "maxLength": 128,
+      "description": "生成任务、服务账号或操作人。"
+    },
+    "approval_reference": {
+      "type": ["string", "null"],
+      "maxLength": 256,
+      "description": "生产发布审批记录编号。"
+    },
+    "notes": {
+      "type": ["string", "null"],
+      "maxLength": 4000,
+      "description": "交付说明、限制和已知问题。"
+    }
+  },
+  "$defs": {
+    "file": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["path", "media_type", "bytes", "sha256"],
+      "properties": {
+        "path": {
+          "type": "string",
+          "pattern": "^(?!/)(?!.*\\.\\.).+$",
+          "maxLength": 1024,
+          "description": "包内相对路径，不允许绝对路径和父目录穿越。"
+        },
+        "media_type": {
+          "type": "string",
+          "maxLength": 128,
+          "description": "IANA 媒体类型。"
+        },
+        "bytes": {
+          "type": "integer",
+          "minimum": 0,
+          "description": "文件字节数。"
+        },
+        "sha256": {
+          "type": "string",
+          "pattern": "^[a-f0-9]{64}$",
+          "description": "文件 SHA-256 完整值。"
+        },
+        "record_count": {
+          "type": ["integer", "null"],
+          "minimum": 0,
+          "description": "数据文件的记录数。"
+        },
+        "compression": {
+          "type": ["string", "null"],
+          "enum": ["none", "gzip", "zstd", "zip", null],
+          "description": "文件压缩方式。"
+        }
+      }
+    }
+  }
+}
@@ -0,0 +1,228 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.edu-industry.cn/school-employment/2.2.0/schema.json",
+  "title": "SCHOOL-EMPLOYMENT V2.2 校内就业事实",
+  "description": "职业院校毕业生就业事实统一契约，采用租户隔离和身份最小化设计。",
+  "type": "object",
+  "additionalProperties": false,
+  "required": [
+    "tenant_id",
+    "record_id",
+    "student_token",
+    "cohort",
+    "college_code",
+    "program_code",
+    "employment_status",
+    "destination_type",
+    "confirmed_at",
+    "confirmation_role",
+    "source_system",
+    "source_record_id",
+    "created_at",
+    "updated_at",
+    "data_version",
+    "content_hash"
+  ],
+  "properties": {
+    "tenant_id": {
+      "type": "string",
+      "pattern": "^TENANT-[A-Z0-9-]{4,64}$",
+      "description": "学校租户标识，所有存储、任务和查询必须同时校验。"
+    },
+    "record_id": {
+      "type": "string",
+      "format": "uuid",
+      "description": "平台全局唯一记录标识。"
+    },
+    "student_token": {
+      "type": "string",
+      "pattern": "^STU_[A-Za-z0-9_-]{32,128}$",
+      "description": "学校侧生成的学生不可逆令牌，禁止传输姓名、身份证和明文学号。"
+    },
+    "cohort": {
+      "type": "integer",
+      "minimum": 2000,
+      "maximum": 2100,
+      "description": "毕业届次。"
+    },
+    "college_code": {
+      "type": "string",
+      "minLength": 1,
+      "maxLength": 64,
+      "description": "学校内部学院代码。"
+    },
+    "program_code": {
+      "type": "string",
+      "pattern": "^[0-9A-Z]{4,12}$",
+      "description": "教育部职业教育专业目录代码。"
+    },
+    "class_code": {
+      "type": ["string", "null"],
+      "maxLength": 64,
+      "description": "学校内部教学班代码。"
+    },
+    "employment_status": {
+      "type": "string",
+      "enum": [
+        "employed",
+        "self_employed",
+        "further_study",
+        "military",
+        "flexible",
+        "unemployed",
+        "pending_confirmation"
+      ],
+      "description": "统一就业状态。"
+    },
+    "destination_type": {
+      "type": "string",
+      "enum": [
+        "enterprise",
+        "public_institution",
+        "government",
+        "further_study",
+        "entrepreneurship",
+        "military",
+        "other"
+      ],
+      "description": "毕业去向类型。"
+    },
+    "job_title": {
+      "type": ["string", "null"],
+      "maxLength": 200,
+      "description": "就业岗位业务原文。"
+    },
+    "job_code": {
+      "type": ["string", "null"],
+      "maxLength": 32,
+      "description": "映射到统一岗位词典后的岗位代码。"
+    },
+    "enterprise_token": {
+      "type": ["string", "null"],
+      "pattern": "^ENT_[A-Za-z0-9_-]{24,128}$",
+      "description": "企业统一标识令牌。"
+    },
+    "enterprise_name": {
+      "type": ["string", "null"],
+      "maxLength": 300,
+      "description": "用于业务核验的企业名称；导出时按数据范围策略处理。"
+    },
+    "enterprise_industry_code": {
+      "type": ["string", "null"],
+      "maxLength": 32,
+      "description": "企业行业代码。"
+    },
+    "region_code": {
+      "type": ["string", "null"],
+      "pattern": "^[0-9]{6}$",
+      "description": "就业地区 GB/T 2260 六位代码。"
+    },
+    "salary_monthly": {
+      "type": ["number", "null"],
+      "minimum": 0,
+      "maximum": 10000000,
+      "description": "确认后的税前月薪，单位元。"
+    },
+    "salary_confirmed": {
+      "type": ["boolean", "null"],
+      "description": "薪资是否经过业务确认。"
+    },
+    "job_relevance": {
+      "type": ["string", "null"],
+      "enum": ["high", "medium", "low", "unconfirmed", null],
+      "description": "就业岗位与专业培养方向相关度。"
+    },
+    "employment_start_date": {
+      "type": ["string", "null"],
+      "format": "date",
+      "description": "就业开始日期。"
+    },
+    "contract_signed": {
+      "type": ["boolean", "null"],
+      "description": "是否签署就业协议或劳动合同。"
+    },
+    "evidence_type": {
+      "type": ["string", "null"],
+      "enum": ["contract", "offer", "registration", "enterprise_confirmation", "student_confirmation", "other", null],
+      "description": "就业确认材料类型，不在平台保存原始敏感附件。"
+    },
+    "evidence_reference": {
+      "type": ["string", "null"],
+      "maxLength": 256,
+      "description": "学校系统内的材料引用编号。"
+    },
+    "confirmed_at": {
+      "type": "string",
+      "format": "date-time",
+      "description": "业务确认时间。"
+    },
+    "confirmation_role": {
+      "type": "string",
+      "enum": ["employment_office", "college", "student", "enterprise", "system"],
+      "description": "执行确认的业务角色。"
+    },
+    "source_system": {
+      "type": "string",
+      "maxLength": 128,
+      "description": "学校来源系统代码。"
+    },
+    "source_record_id": {
+      "type": "string",
+      "minLength": 1,
+      "maxLength": 256,
+      "description": "校内来源系统记录标识。"
+    },
+    "source_updated_at": {
+      "type": ["string", "null"],
+      "format": "date-time",
+      "description": "校内来源系统业务更新时间，建议作为增量水位。"
+    },
+    "created_at": {
+      "type": "string",
+      "format": "date-time",
+      "description": "平台记录创建时间。"
+    },
+    "updated_at": {
+      "type": "string",
+      "format": "date-time",
+      "description": "平台记录更新时间。"
+    },
+    "data_version": {
+      "type": "string",
+      "pattern": "^SCH-EMP-[0-9]{8}(?:-[0-9]{2})?$",
+      "description": "校内就业数据版本。"
+    },
+    "is_deleted": {
+      "type": "boolean",
+      "default": false,
+      "description": "版本化软删除标识。"
+    },
+    "content_hash": {
+      "type": "string",
+      "pattern": "^[a-f0-9]{64}$",
+      "description": "去除非业务差异后的记录内容 SHA-256。"
+    }
+  },
+  "allOf": [
+    {
+      "if": {
+        "properties": {
+          "destination_type": {
+            "const": "enterprise"
+          }
+        },
+        "required": ["destination_type"]
+      },
+      "then": {
+        "anyOf": [
+          {
+            "required": ["enterprise_token"]
+          },
+          {
+            "required": ["enterprise_name"]
+          }
+        ]
+      }
+    }
+  ]
+}