Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 8e548287e9 | |||
| e85902bf18 | |||
| e82abec4c7 |
@@ -117,8 +117,6 @@ CI 在已授权的远程 runner 上运行测试、构建 wheel,并从源码目
|
||||
|
||||
已导入整卷的逐条轨道修正见 [edition-tracks 维护流程](docs/edition-tracks.md):按完整证据生成只读计划,保留原投稿和决定 ID,事务性修正 edition、标识与覆盖,并防止旧整卷刷新覆盖分类。
|
||||
|
||||
完整出版来源的新旧版本导致分轨或摘要变化时,使用 [source-revisions 流程](docs/source-revisions.md):核对同一 DOI 全集,保存完整修正前数据与版本链,支持已有记录的目标 track,按新版本重算分区覆盖数,并阻止旧版元数据刷新。普通增量导入仍禁止缩小预期数量。
|
||||
|
||||
入库前可使用通用的[来源身份只读预检](docs/source-identity-audit.md),导出候选论文、稳定标识和既有投稿决定证据;候选结果需要审核,不会自动批准导入。
|
||||
|
||||
RSS 2026 已独立适配官方论文集与录用表;使用方法和与 2025 demo 分类的区别见 [RSS 2026 来源说明](docs/rss2026-proceedings.md)。
|
||||
|
||||
@@ -202,3 +202,5 @@ IJCAI 联办届次的逐条后续核查见 [2018/2022 分区与目录差集](ijc
|
||||
[早期NLP来源范围复核](historical-source-scope-2026-11-09.md)保留3份官方网页的响应哈希,排除4个COLING卷对ACL缺口的误匹配,并区分会议举办记录、目录可获取性与论文级覆盖;尚未导入或关闭这些年度缺口。
|
||||
|
||||
- [MM 2026 官方节目来源状态](../mm2026-source-status.md):完整官方日程 JSON、重复展示盘点、28 个来源 track、缺失作者/摘要和四条匿名决定路径的 403 证据;这些不是已导入或公开拒稿全集。
|
||||
|
||||
- [2026-11-18 公开负面来源核查](public-negative-source-audit-2026-11-18.md):ResearchArcade 930 条非 ICLR 声明的当前库比对、5 条未绑定声明及原始接口访问证据;不把镜像差集算作新增拒稿。
|
||||
|
||||
@@ -1493,7 +1493,7 @@
|
||||
},
|
||||
"TMLR_current20261108": {
|
||||
"url": "https://www.jmlr.org/tmlr/faq.html",
|
||||
"finding": "Additionalnonconferencevenuealreadyinregistry:accepted/rejected/withdrawn/retractedallpublic; deskrejectedneverpublic. Authorshiddenonnotyetacceptedpapers; donotinferanonymousidentities. Continuousjournal; eventcertification/journal-to-conferencepresentationnotanotherindependentreviewacceptance."
|
||||
"finding": "Additionalnonconferencepolicyreference; TMLR is not in the current 43-conference registry:accepted/rejected/withdrawn/retractedallpublic; deskrejectedneverpublic. Authorshiddenonnotyetacceptedpapers; donotinferanonymousidentities. Continuousjournal; eventcertification/journal-to-conferencepresentationnotanotherindependentreviewacceptance."
|
||||
}
|
||||
},
|
||||
"public_negative_recovery_notes": {
|
||||
@@ -1507,6 +1507,12 @@
|
||||
"original_rejection_notes_obtained": false,
|
||||
"prior_decisions_inserted": 0,
|
||||
"requires": "Per-paper primary original identifiers/decisions or an explicitly distinguished policy-supported relation; never manufacture an original note."
|
||||
},
|
||||
"researcharcade_20261118": {
|
||||
"audit": "public-negative-source-audit-2026-11-18.json",
|
||||
"summary": "930 non-ICLR 2020+ mirror claims:925 scoped ID matches all have rejected status;5 held,3 with equal title+source abstract but distinct unverified note IDs. No writes or new rejections approved.",
|
||||
"access": "NeurIPS2021 and EMNLP2023 original note queries403; stopped, no bypass.",
|
||||
"next": "Seek independent primary evidence for note.id/forum relationships and final decisions; no title-only merge or duplicate-rejection import. No full-public-set coverage claim."
|
||||
}
|
||||
},
|
||||
"restore_rules": [
|
||||
|
||||
@@ -0,0 +1,320 @@
|
||||
{
|
||||
"version": 1,
|
||||
"as_of": "2026-11-18",
|
||||
"scope": "930 cached ResearchArcade non-ICLR negative claims, NeurIPS 2021–2025 and EMNLP 2023; not a conference-completeness audit",
|
||||
"database_snapshot": {
|
||||
"database": "foundry_data",
|
||||
"schema": "research",
|
||||
"at": "2026-11-18 03:48:34.65659+00",
|
||||
"snapshot": "1048885:1048885:"
|
||||
},
|
||||
"database_written": false,
|
||||
"approved_for_import": 0,
|
||||
"claims": 930,
|
||||
"known_same_scope_attempt_claims": 925,
|
||||
"all_925_have_rejected_status": true,
|
||||
"without_same_scope_attempt_claims": 5,
|
||||
"by_venue_year": [
|
||||
{
|
||||
"venue": "EMNLP",
|
||||
"year": 2023,
|
||||
"claims": 10
|
||||
},
|
||||
{
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"claims": 136
|
||||
},
|
||||
{
|
||||
"venue": "NeurIPS",
|
||||
"year": 2022,
|
||||
"claims": 153
|
||||
},
|
||||
{
|
||||
"venue": "NeurIPS",
|
||||
"year": 2023,
|
||||
"claims": 176
|
||||
},
|
||||
{
|
||||
"venue": "NeurIPS",
|
||||
"year": 2024,
|
||||
"claims": 201
|
||||
},
|
||||
{
|
||||
"venue": "NeurIPS",
|
||||
"year": 2025,
|
||||
"claims": 254
|
||||
}
|
||||
],
|
||||
"evidence": {
|
||||
"diff_report_sha256": "d49361a8622f3b3f59e824690ceb8bf1c878be35c3e3758366d3b46a407673f5",
|
||||
"candidate_packets_sha256": "3b21df27e0f30e56b81086d16d3943c4563bbe382200e866b15de14510e07472",
|
||||
"dataset_revision": "c61bb99b0452429c32f85b1e392f3afdb65731c4",
|
||||
"dataset_parquet_sha256": "bb6e165ee152a95d91a7ffa16abc9d4a6effbdfcf59183b3bb819d09171689d1",
|
||||
"candidate_jsonl_sha256": "848e646596e8c747e0c636c2381a139978aff8f2c19f01ad49c98e7f4270c5e6",
|
||||
"collector_repository": "https://github.com/ulab-uiuc/research-arcade",
|
||||
"collector_revision": "ecf9c7c2490840b029bd2add4f02d04aca1d014e",
|
||||
"collector_openreview_crawler_sha256": "4539d951ca05b20785169638eab3884148aa6c354a34c5ecc04e15c84a5910fe",
|
||||
"collector_revision_proven_to_generate_dataset": false
|
||||
},
|
||||
"collector_semantics": {
|
||||
"legacy_2020_2022": "Reads Blind_Submission note.id; first reply with content.decision, no invitation/signature verification. Not a verified final-decision note.",
|
||||
"legacy_2019": "Reads first recommendation, which must not be promoted to a final decision. Outside active 2020+ backfill.",
|
||||
"modern_branch": "Reads Submission note.id and last venueid component; Conference replaced by venue literal. Withdrawn_Submission skipped.",
|
||||
"identity": "The exported field paper_openreview_id is note.id; forum equality or equivalence to another mirror ID is not independently proved.",
|
||||
"coverage": "Six-field table has no authors or decision signatures; no completeness inference for public withdrawn/rejected records."
|
||||
},
|
||||
"held_claims": [
|
||||
{
|
||||
"source_row": 33219,
|
||||
"note_id_claim": "FSf9h6t152",
|
||||
"venue": "NeurIPS",
|
||||
"year": 2025,
|
||||
"raw_decision": "Rejected_Submission",
|
||||
"title": "Hierarchical Restructuring of Graph Neural Networks for Robust Learning under Edge Perturbations",
|
||||
"same_scope_identifier_match": false,
|
||||
"exact_title_candidates": [],
|
||||
"approved_for_import": false,
|
||||
"disposition": "hold_no_exact_title_candidate_not_proof_of_novelty"
|
||||
},
|
||||
{
|
||||
"source_row": 44669,
|
||||
"note_id_claim": "Pk972F7J8Um",
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"raw_decision": "Reject",
|
||||
"title": "Differential Privacy of Dirichlet Posterior Sampling",
|
||||
"same_scope_identifier_match": false,
|
||||
"exact_title_candidates": [
|
||||
{
|
||||
"paper_id": 3527429,
|
||||
"existing_identifiers": [
|
||||
{
|
||||
"scheme": "openreview",
|
||||
"value": "fgBxcKcz9ea",
|
||||
"paper_id": 3527429
|
||||
},
|
||||
{
|
||||
"scheme": "papercopilot_openreview",
|
||||
"value": "nips/2021/fgBxcKcz9ea",
|
||||
"paper_id": 3527429
|
||||
}
|
||||
],
|
||||
"source_abstract_exact_equal": true,
|
||||
"existing_attempts": [
|
||||
{
|
||||
"id": 444666,
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"source_submission_id": "nips/2021/fgBxcKcz9ea",
|
||||
"statuses": [
|
||||
"rejected"
|
||||
]
|
||||
}
|
||||
],
|
||||
"attempts_truncated": false,
|
||||
"identity_approved": false,
|
||||
"id_alias_approved": false
|
||||
}
|
||||
],
|
||||
"approved_for_import": false,
|
||||
"disposition": "hold_distinct_note_ids_even_with_equal_title_and_abstract"
|
||||
},
|
||||
{
|
||||
"source_row": 44696,
|
||||
"note_id_claim": "ki4eJ1fSJNq",
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"raw_decision": "Reject",
|
||||
"title": "Fitting large mixture models using stochastic component selection",
|
||||
"same_scope_identifier_match": false,
|
||||
"exact_title_candidates": [
|
||||
{
|
||||
"paper_id": 1545058,
|
||||
"existing_identifiers": [
|
||||
{
|
||||
"scheme": "arxiv",
|
||||
"value": "2110.04776",
|
||||
"paper_id": 1545058
|
||||
},
|
||||
{
|
||||
"scheme": "openreview",
|
||||
"value": "ZS394D3djsg",
|
||||
"paper_id": 1545058
|
||||
},
|
||||
{
|
||||
"scheme": "papercopilot_openreview",
|
||||
"value": "nips/2021/ZS394D3djsg",
|
||||
"paper_id": 1545058
|
||||
}
|
||||
],
|
||||
"source_abstract_exact_equal": true,
|
||||
"existing_attempts": [
|
||||
{
|
||||
"id": 444652,
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"source_submission_id": "nips/2021/ZS394D3djsg",
|
||||
"statuses": [
|
||||
"rejected"
|
||||
]
|
||||
}
|
||||
],
|
||||
"attempts_truncated": false,
|
||||
"identity_approved": false,
|
||||
"id_alias_approved": false
|
||||
}
|
||||
],
|
||||
"approved_for_import": false,
|
||||
"disposition": "hold_distinct_note_ids_even_with_equal_title_and_abstract"
|
||||
},
|
||||
{
|
||||
"source_row": 45757,
|
||||
"note_id_claim": "bDP7I2fYwLj",
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"raw_decision": "Reject",
|
||||
"title": "WeaveNet for Approximating Assignment Problems",
|
||||
"same_scope_identifier_match": false,
|
||||
"exact_title_candidates": [
|
||||
{
|
||||
"paper_id": 3527390,
|
||||
"existing_identifiers": [
|
||||
{
|
||||
"scheme": "openreview",
|
||||
"value": "2rAiDBJgR_",
|
||||
"paper_id": 3527390
|
||||
},
|
||||
{
|
||||
"scheme": "papercopilot_openreview",
|
||||
"value": "nips/2021/2rAiDBJgR_",
|
||||
"paper_id": 3527390
|
||||
}
|
||||
],
|
||||
"source_abstract_exact_equal": true,
|
||||
"existing_attempts": [
|
||||
{
|
||||
"id": 444580,
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"source_submission_id": "nips/2021/2rAiDBJgR_",
|
||||
"statuses": [
|
||||
"rejected"
|
||||
]
|
||||
}
|
||||
],
|
||||
"attempts_truncated": false,
|
||||
"identity_approved": false,
|
||||
"id_alias_approved": false
|
||||
}
|
||||
],
|
||||
"approved_for_import": false,
|
||||
"disposition": "hold_distinct_note_ids_even_with_equal_title_and_abstract"
|
||||
},
|
||||
{
|
||||
"source_row": 49327,
|
||||
"note_id_claim": "yB8cQIICqe",
|
||||
"venue": "EMNLP",
|
||||
"year": 2023,
|
||||
"raw_decision": "Desk_Rejected_Submission",
|
||||
"title": "EZ-STANCE: A Large Dataset for Zero-Shot Stance Detection",
|
||||
"same_scope_identifier_match": false,
|
||||
"exact_title_candidates": [],
|
||||
"approved_for_import": false,
|
||||
"disposition": "hold_possible_later_publication_with_changed_title_and_dataset_size_no_identity_or_author_transfer",
|
||||
"later_publication_retrieval_lead": {
|
||||
"url": "https://aclanthology.org/2024.acl-long.838/",
|
||||
"http_status": 200,
|
||||
"bytes": 40557,
|
||||
"response_sha256": "b50dd55c48e31e4c10e97927ce01679369735834aa2c0f8d9f41f8e8e02fc776",
|
||||
"checked_at": "2026-11-18T04:07:03.699767+00:00",
|
||||
"anthology_id": "2024.acl-long.838",
|
||||
"doi": "10.18653/v1/2024.acl-long.838",
|
||||
"title": "EZ-STANCE: A Large Dataset for English Zero-Shot Stance Detection",
|
||||
"venue": "ACL",
|
||||
"year": 2024,
|
||||
"publication_verified": true,
|
||||
"link_to_anonymous_rejection_verified": false,
|
||||
"authors_transferred_to_anonymous_claim": false,
|
||||
"dataset_pairs_published_version": 47316,
|
||||
"dataset_pairs_rejection_mirror_version": 30606,
|
||||
"database_written": false,
|
||||
"current_database_evidence": {
|
||||
"snapshot": {
|
||||
"at": "2026-11-18 04:09:23.720956+00",
|
||||
"snapshot": "1051887:1051887:"
|
||||
},
|
||||
"paper_id": 2131805,
|
||||
"verified_identifiers": [
|
||||
{
|
||||
"scheme": "acl",
|
||||
"value": "2024.acl-long.838",
|
||||
"paper_id": 2131805
|
||||
},
|
||||
{
|
||||
"scheme": "acl_anthology",
|
||||
"value": "2024.acl-long.838",
|
||||
"paper_id": 2131805
|
||||
},
|
||||
{
|
||||
"scheme": "doi",
|
||||
"value": "10.18653/v1/2024.acl-long.838",
|
||||
"paper_id": 2131805
|
||||
}
|
||||
],
|
||||
"existing_attempts": [
|
||||
{
|
||||
"venue": "ACL",
|
||||
"year": 2024,
|
||||
"track": "main",
|
||||
"statuses": [
|
||||
"accepted"
|
||||
]
|
||||
}
|
||||
],
|
||||
"packet_file_sha256": "de5dfa658177adef87134cf7723afc086bd7395405a31166ff9597b03b3c8af3",
|
||||
"original_rejection_link_verified": false
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"access_probes": [
|
||||
{
|
||||
"local_evidence": "researcharcade-neurips2021-original-note-check-v1/report.json",
|
||||
"sha256": "746d752535b516abba43b0e8e6ad901bf39c07da532188dfa97ff911869084ae",
|
||||
"receipt_summary": {},
|
||||
"results": [
|
||||
{
|
||||
"requested_note_id": "Pk972F7J8Um",
|
||||
"status": 403,
|
||||
"url": "https://api.openreview.net/notes?id=Pk972F7J8Um&select=id%2Cforum%2Cinvitation%2Creaders%2Csignatures%2Ccontent.title%2Ccontent.abstract%2Ccontent.venue%2Ccontent.venueid",
|
||||
"sha256": "b0113384cebc9d724284062f776b45044d22450219112342721d8f9683571c08",
|
||||
"checked_at": "2026-11-18T04:01:58.643552+00:00"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"local_evidence": "emnlp2023-primary-public-metadata-probe-v1/notes-probe.json",
|
||||
"sha256": "47799dc4520e113d6a2e7c9ea2f362577bb21e3ad583ee02149a36c21cf6ea9d",
|
||||
"receipt_summary": {
|
||||
"url": "https://api.openreview.net/notes?invitation=EMNLP%2F2023%2FConference%2F-%2FSubmission&limit=1&select=id%2Cnumber%2Cforum%2Cinvitation%2Creaders%2Csignatures%2Ccdate%2Ctcdate%2Cmdate%2Ctmdate%2Ccontent.title%2Ccontent.abstract%2Ccontent.authors%2Ccontent.venue%2Ccontent.venueid%2Ccontent.keywords",
|
||||
"http_status": 403,
|
||||
"response_sha256": "798e964735eb1eff1e4954d5c9e79aad2afd40c3f88dcb82f8ef5bbc55cc0a61",
|
||||
"response_bytes": 546,
|
||||
"at": "2026-11-18T03:38:50.112624+00:00"
|
||||
}
|
||||
},
|
||||
{
|
||||
"local_evidence": "emnlp2023-primary-public-metadata-probe-v1/group-access.json",
|
||||
"sha256": "8fcb9ccd5615a737c17ef0eeedc9121e85a84ebd63667e83df0bda9ffb83d792",
|
||||
"receipt_summary": {
|
||||
"url": "https://api.openreview.net/groups?id=EMNLP%2F2023%2FConference",
|
||||
"http_status": 200,
|
||||
"response_sha256": "7c0cc75e2e8be1c18dffc96a9ceabea34f0f7810139c0a990a6bb117d66f6456",
|
||||
"response_bytes": 13143,
|
||||
"at": "2026-11-18T03:38:49.929085+00:00"
|
||||
}
|
||||
}
|
||||
],
|
||||
"access_limit": "NeurIPS 2021 first original note request and EMNLP 2023 source-declared Submission query returned 403. Requests stopped. No alternate API version, endpoint, authentication, or challenge bypass. 403 does not prove zero public records."
|
||||
}
|
||||
@@ -0,0 +1,50 @@
|
||||
# 公开负面来源核查:2026-11-18
|
||||
|
||||
本次检查 ResearchArcade 缓存中 NeurIPS 2021–2025、EMNLP 2023 的 930 条负面声明,不包括 ICLR 或 2020 年以前的补漏。原始候选文件未重新下载,PostgreSQL 查询为只读。逐条待办、来源哈希与数据库快照见[机器可读记录](public-negative-source-audit-2026-11-18.json)。没有新增论文、决定、ID 别名或合并。
|
||||
|
||||
## 当前库比对
|
||||
|
||||
925 条声明通过同会议、同年份的 OpenReview 标识匹配到投稿,且每条都有 rejected 决定。这里只证明对应拒稿已记录,未核验这些论文的所有后续录用历史,也未证明会议公开拒稿全集完整。
|
||||
|
||||
另 5 条没有同届标识匹配:
|
||||
|
||||
|来源 note.id 声明|会议|标题或识别信息|处置|
|
||||
|---|---|---|---|
|
||||
|FSf9h6t152|NeurIPS 2025|Hierarchical Restructuring of Graph Neural Networks for Robust Learning under Edge Perturbations|无精确标题候选;不是已证明的新论文|
|
||||
|Pk972F7J8Um|NeurIPS 2021|Differential Privacy of Dirichlet Posterior Sampling|候选 paper 3527429,已有同届 rejected,原 ID fgBxcKcz9ea|
|
||||
|ki4eJ1fSJNq|NeurIPS 2021|Fitting large mixture models using stochastic component selection|候选 paper 1545058,已有同届 rejected,原 ID ZS394D3djsg;另保留 arXiv 2110.04776|
|
||||
|bDP7I2fYwLj|NeurIPS 2021|WeaveNet for Approximating Assignment Problems|候选 paper 3527390,已有同届 rejected,原 ID 2rAiDBJgR_|
|
||||
|yB8cQIICqe|EMNLP 2023|EZ-STANCE: A Large Dataset for Zero-Shot Stance Detection|镜像称 Desk_Rejected_Submission;原始公开范围及身份未核验|
|
||||
|
||||
三个标题候选的镜像摘要都与已有 PaperCopilot 来源摘要逐字相等,但来源 ID 不同。相等文本不能独立证明两个 note.id 指向同一个 forum,也不能据此创建第二次投稿或批准 ID 别名。现有实体包没有截断投稿列表,均只有已记录的 NeurIPS 2021 拒稿;这不代表从未在其他地方录用。
|
||||
|
||||
## 采集器证据与使用限制
|
||||
|
||||
作者仓库 [research-arcade](https://github.com/ulab-uiuc/research-arcade) 固定版本 `ecf9c7c2490840b029bd2add4f02d04aca1d014e` 的 `openreview_crawler.py` 显示:
|
||||
|
||||
- 2020–2022 的旧接口路径读取 Blind_Submission 的 `note.id`,从 replies 中取第一个带 `decision` 字段的值,未验证决定 invitation 或签名。
|
||||
- 2019 路径取第一个 `recommendation`,不能将其升级为正式决定。该年度属于保留线索的范围,本轮不补导。
|
||||
- 新接口路径读取 Submission 的 `note.id`,用 `venueid` 尾段作为标签;遇 Conference 再取 `venue`,并跳过 Withdrawn_Submission。
|
||||
|
||||
三个源码文件均核对 Git blob SHA-1 和完整文件 SHA-256;没有执行第三方采集器。源码版本早于数据集版本,但未证明该提交实际生成了此数据集。数据集仅有六个元数据字段,缺少作者和决定签名,因此既不能证明完整 withdrawn 覆盖,也不能将导出的 ID 无条件认作已验证 forum。
|
||||
|
||||
## 原始来源访问结果
|
||||
|
||||
EMNLP 2023 官方分组元数据返回 200,其声明的 Submission invitation 与既有配置一致;对该 invitation 的匿名元数据查询返回 403。NeurIPS 2021 对第一条候选 note `Pk972F7J8Um` 的匿名元数据查询同样返回 403,余下五个 ID 未发请求。均已停止对应来源查询,没有换接口版本、登录或绕过访问限制。403 不能说明没有公开投稿;未保留完整错误正文,也不将具体拒绝原因猜测为已知。
|
||||
|
||||
[EMNLP 2023 官方政策](https://2023.emnlp.org/blog/EMNLP-2023-openreview/)说明公开录用稿件与选择公开的拒稿,现有 9 条 rejected 或本镜像的 1 条 desk-rejected 均不能证明完整公开集合。
|
||||
|
||||
## EZ-STANCE 后续发表线索
|
||||
|
||||
独立的 [ACL Anthology 官方条目](https://aclanthology.org/2024.acl-long.838/)确认相近标题的 EZ-STANCE 在 ACL 2024 Long Papers 发表,DOI `10.18653/v1/2024.acl-long.838`。正式标题多了 English,数据集由拒稿镜像中的 30,606 对变为 47,316 对。已保存官方 HTML 的完整哈希,登记为版本关系核查线索;尚未证明与匿名 EMNLP 2023 声明属于同一投稿或同一科学工作,没有把已发表作者转填到匿名记录,也没有写入关联或第二份论文。后续必须核验版本关系并保留各自的投稿决定证据。
|
||||
|
||||
当前 PostgreSQL 的正式标题变体查询命中已有 paper `2131805`,其 ACL/DOI 标识与官方条目一致,已有 `ACL / 2024 / main / accepted` 投稿历史。该实体无需重复新建。匿名 EMNLP 声明与该实体的关系仍未批准,不能把这条线索表述为已经确认的“先拒后录”。快照、标识及完整实体包哈希已记入机器记录。
|
||||
|
||||
## 下次从哪里继续
|
||||
|
||||
1. 保留五条候选及旧 ID,等待可验证的原始公开元数据或独立可靠来源;不要反复重放已拒绝的原始接口请求。
|
||||
2. 对三对 ID 分歧先取得 note/forum 关系证据,再独立审核科学工作身份与逐次投稿关系;保留已有拒稿及以后发现的录用。
|
||||
3. 两条没有精确标题候选的记录仍需标题变体、作者及摘要交叉核查;匿名元数据不能用于推断作者身份。
|
||||
4. 继续其余会议与年度的公开负面可用性核查,不将这 930 条当作全会、全年份覆盖,也不将 accepted-only 镜像算作拒稿补全。
|
||||
|
||||
另修正交接记录:TMLR 是额外的期刊政策线索,当前 43 个会议的 registry 中没有 TMLR;没有因此更改会议分母。2000–2019 已发现线索仍保留。
|
||||
@@ -1,57 +0,0 @@
|
||||
# 出版来源版本与覆盖修正
|
||||
|
||||
`paper-atlas maintain source-revisions` 用于同一出版清单的新版本:稳定 DOI 全集、标题、作者和决定不变,但官方分轨、摘要或对应来源证据已经过重新核对。它不导入新论文、不合并实体、不推断拒稿,不把出版分类当成研究类型。
|
||||
|
||||
例如,同一清单的“未分类”由 192 条减少到 166 条,而主会等分区增加。直接放松增量导入的计数保护会隐藏清单丢失。本命令先核验完整的新旧清单及数据库快照,再单独修正版本;普通 `import records` 的单调计数规则保持原样。
|
||||
|
||||
## 准备完整证据
|
||||
|
||||
在工作区外保存 inventory JSON,包含以下字段:
|
||||
|
||||
| 字段 | 内容 |
|
||||
| --- | --- |
|
||||
| `format` | `1` |
|
||||
| `source`, `venue`, `year`, `event_key`, `list_url` | 明确的已有来源、会议缩写、年份、事件键和 HTTPS 出版清单地址 |
|
||||
| `previous_rows`, `rows` | 完整旧版、新版规范化来源记录数组,每版最多 10,000 条;每条包含稳定 DOI、来源字段、作者、摘要、track、决定、标签、原始来源 metadata |
|
||||
| `evidence` | 一个或多个 `{ "url": "https://…", "sha256": "…" }`,绑定已独立核验的原始证据文件 |
|
||||
|
||||
两版必须有完全相同的 DOI 集合;仅允许 `abstract`、`track`、`tags`、`metadata` 的有据变化。必须保留 collector 原始字段,不能将工作身份核查产生的额外锚点混入原始来源版本。只有明确 `accepted` 的出版观察可进入本流程。证据 URL/hash 是审核输入,本命令不联网确认它们;执行者必须另行验证文件哈希、完整性及对应关系。
|
||||
|
||||
数据库可以部分导入,甚至各分区的预期数暂时来自不同版本。现有覆盖必须为 `partial`、无错误,导入数与实际来源记录一致;预期数必须恰好属于旧版或新版的同一分区。已有目标 edition 和对应覆盖记录必须存在,目标中可以有其他来源及既有投稿。本版本不会新建 edition,也不会处理共享来源投稿、多次既有 scope curation 的再迁移,或成员集合变化;遇到这些情况会拒绝并要求单独核查。
|
||||
|
||||
## 先生成只读计划
|
||||
|
||||
```sh
|
||||
paper-atlas maintain source-revisions \
|
||||
--pg-service foundry-research --pg-schema research \
|
||||
--inventory /data/paper-index/validation/reviewed-source-version.json \
|
||||
--out /data/paper-index/validation/source-revision-plan.json
|
||||
```
|
||||
|
||||
计划包含明确数据库身份、两个完整来源版本、当前版本父节点、覆盖表原值和修正值、逐条变更,以及受影响会议 scope 内所有论文的规范记录、稳定标识、全部跨会议投稿和决定、来源关系、标签与已存在的 annotation。拒稿后录用的历史也在保护范围内,不能只校验当前会议的录用观察。
|
||||
|
||||
计划和原始证据应保存到服务器与独立恢复位置,核对完整差异及计划文件 SHA-256。执行前重新核对生产保护基线与单写入安排。输出文件必须是不存在的新路径,禁止覆盖旧报告。
|
||||
|
||||
## 按文件哈希应用并验收
|
||||
|
||||
```sh
|
||||
paper-atlas maintain source-revisions \
|
||||
--pg-service foundry-research --pg-schema research \
|
||||
--plan /data/paper-index/validation/source-revision-plan.json \
|
||||
--plan-sha256 <已审核的计划文件SHA256> \
|
||||
--out /data/paper-index/validation/source-revision-result.json
|
||||
```
|
||||
|
||||
应用时重新生成计划并要求完全一致;PostgreSQL 使用已有 writer 锁及相关表写锁,SQLite 使用立即事务。任何保护数据、当前版本或目标标识冲突都使操作失败。操作保留投稿和决定 ID、原始决定证据、规范论文文本、全部稳定标识、来源关系和现有标签;只修改计划列出的投稿/投稿标识 edition,以及来源记录的摘要与 metadata 当前投影。旧投影完整保存在版本历史中,来源原始获取时间不会伪造为修正时间。
|
||||
|
||||
覆盖只调整明确分区的预期数和来源观察数,保留 `partial`、cursor、成功时间和错误字段原值。尚未导入的分区不产生虚构投稿或来源观察。覆盖数不能被解读为科学作品数量,或所有 track、摘要、负面决定已完整。
|
||||
|
||||
同一事务显式增加可共享的可选表 `source_scope_revisions`,保持原 21 张业务表的身份。每个版本存储新来源全集、父版本、完整计划及修正前数据;应用接口只追加版本,不更新或删除旧版本。没有新建 PostgreSQL 实例。该表纳入 SQLite→PostgreSQL 的可选表迁移、全量内容哈希、约束与计数验收。`version_sha256` 是规范化计划内容哈希;CLI 的 `--plan-sha256` 是计划文件字节哈希,二者用途不同。
|
||||
|
||||
提交前在同一事务比较全部保护数据与明确预期的变更;失败则全部回滚,包括新增表和版本记录。相同计划的重放还会重新验收当前状态;如后续数据已变化则拒绝,不会重复迁移或恢复旧状态。完整计划与 before-image 用于审查和恢复准备,本命令没有自动回滚历史版本的入口;不得手工删除版本来绕开刷新保护。
|
||||
|
||||
## 后续刷新及限制
|
||||
|
||||
`import records` 检查当前版本的逐条完整来源字段;`Store.record` 也检查原始文本、作者、来源 metadata 和基础标识,防止直接调用绕回旧版摘要。来源字段必须与当前版本相符,可以额外携带已经核验的工作身份/curation 证据,不能替换来源自身字段。相同来源、会议事件和清单地址下未登记的成员必须另行核验新版本。
|
||||
|
||||
版本表通过包内接口追加,未声明数据库管理员的任意 SQL 为安全接口。新来源或新版本在导入前仍需要独立工作身份核查;姓名、标题或无候选都不证明作品身份。实现测试和版本修正验收也不替代所有导入结束后的全库去重、标识冲突、近似标题/作者、摘要、来源覆盖与查询审计。
|
||||
@@ -46,7 +46,6 @@ COMMANDS = {
|
||||
('import','arxiv'): ('paper_atlas.ingestion.arxiv', {}, '导入 arXiv 元数据 ZIP'),
|
||||
('import','records'): ('paper_atlas.ingestion.records', {}, '导入核验过的会议文件'),
|
||||
('maintain','edition-tracks'): ('paper_atlas.ingestion.edition_tracks', {}, '按逐条来源证据修正既有投稿轨道并保护刷新'),
|
||||
('maintain','source-revisions'): ('paper_atlas.ingestion.source_revisions', {}, '按完整来源版本核验并修正出版分轨与覆盖数,保留历史并阻止旧版刷新'),
|
||||
('maintain','joint-editions'): ('paper_atlas.ingestion.joint_editions', {}, '按已核验计划修正既有联合会议届次归属'),
|
||||
('maintain','event-identity'): ('paper_atlas.ingestion.event_identity', {}, '按核验计划增加同年会议事件身份'),
|
||||
('maintain','merge'): ('paper_atlas.ingestion.maintenance', {}, '协调单写入合并与恢复'),
|
||||
|
||||
@@ -1,128 +0,0 @@
|
||||
"""Versioned publication-source scopes and guards against stale source refreshes."""
|
||||
import json
|
||||
import re
|
||||
|
||||
TABLE = 'source_scope_revisions'
|
||||
MARKER = 'source_scope_revisions_v1'
|
||||
COLUMNS = ('version_sha256', 'source_id', 'venue_id', 'year', 'event_key', 'list_url',
|
||||
'parent_sha256', 'records_json', 'plan_json', 'applied_at')
|
||||
|
||||
|
||||
def available(c):
|
||||
if getattr(c, 'postgres', False):
|
||||
return bool(c.execute("SELECT 1 FROM information_schema.tables WHERE table_schema=current_schema() AND table_name=?", (TABLE,)).fetchone())
|
||||
return bool(c.execute("SELECT 1 FROM sqlite_master WHERE type='table' AND name=?", (TABLE,)).fetchone())
|
||||
|
||||
|
||||
def initialize(c):
|
||||
exists = available(c)
|
||||
marker = bool(c.execute('SELECT 1 FROM schema_migrations WHERE name=?', (MARKER,)).fetchone())
|
||||
if exists != marker:
|
||||
raise ValueError('Source revision table/marker mismatch')
|
||||
if exists:
|
||||
result = c.execute('SELECT * FROM source_scope_revisions LIMIT 0')
|
||||
description = result.cursor.description if getattr(c, 'postgres', False) else result.description
|
||||
if tuple(x[0] for x in description) != COLUMNS:
|
||||
raise ValueError('Unexpected source revision schema')
|
||||
return
|
||||
ddl = '''CREATE TABLE source_scope_revisions (
|
||||
version_sha256 TEXT PRIMARY KEY,
|
||||
source_id INTEGER NOT NULL REFERENCES sources(id),
|
||||
venue_id INTEGER NOT NULL REFERENCES venues(id),
|
||||
year INTEGER NOT NULL, event_key TEXT NOT NULL, list_url TEXT NOT NULL,
|
||||
parent_sha256 TEXT UNIQUE REFERENCES source_scope_revisions(version_sha256),
|
||||
records_json TEXT NOT NULL, plan_json TEXT NOT NULL,
|
||||
applied_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP)'''
|
||||
if getattr(c, 'postgres', False):
|
||||
ddl = re.sub(r'\bINTEGER\b', 'BIGINT', ddl)
|
||||
ddl = re.sub(r'\bTEXT\b', 'TEXT COLLATE "C"', ddl)
|
||||
c.execute(ddl)
|
||||
c.execute('CREATE INDEX source_scope_revisions_scope ON source_scope_revisions(source_id,venue_id,year,event_key,list_url)')
|
||||
c.execute('INSERT INTO schema_migrations(name) VALUES(?)', (MARKER,))
|
||||
|
||||
|
||||
def heads(c, source_id):
|
||||
if not available(c):
|
||||
return []
|
||||
if not c.execute('SELECT 1 FROM schema_migrations WHERE name=?', (MARKER,)).fetchone():
|
||||
raise ValueError('Source revision table/marker mismatch')
|
||||
return c.execute('''SELECT v.version_sha256,v.venue_id,v.year,v.event_key,v.list_url
|
||||
FROM source_scope_revisions v WHERE v.source_id=? AND NOT EXISTS
|
||||
(SELECT 1 FROM source_scope_revisions child WHERE child.parent_sha256=v.version_sha256)
|
||||
ORDER BY v.version_sha256''', (source_id,)).fetchall()
|
||||
|
||||
|
||||
def current_rows(c, source_id, cache):
|
||||
active = heads(c, source_id)
|
||||
signatures = tuple(r[0] for r in active)
|
||||
# A new head invalidates the cache, even when maintenance uses the same Store.
|
||||
if cache.get('signatures') != (source_id, signatures):
|
||||
records = {}; scopes = {}
|
||||
for signature in signatures:
|
||||
raw = c.execute('SELECT records_json FROM source_scope_revisions WHERE version_sha256=?', (signature,)).fetchone()[0]
|
||||
scopes[signature] = json.loads(raw)
|
||||
for row in scopes[signature]:
|
||||
ext = row['external_id']
|
||||
if ext in records and records[ext] != row:
|
||||
raise ValueError('Conflicting active source snapshots')
|
||||
records[ext] = row
|
||||
cache.clear()
|
||||
cache.update(signatures=(source_id, signatures), records=records, scopes=scopes)
|
||||
return cache['records']
|
||||
|
||||
|
||||
def subset(expected, actual):
|
||||
"""Reviewed source fields must survive additional work-identity/curation evidence."""
|
||||
return isinstance(actual, dict) and all(k in actual and actual[k] == v for k, v in expected.items())
|
||||
|
||||
|
||||
def require_record(c, source_id, external, url, title, abstract, authors, identifiers, metadata, cache):
|
||||
expected = current_rows(c, source_id, cache).get(external)
|
||||
if expected is None:
|
||||
return
|
||||
actual = {'url': url, 'title': title, 'abstract': abstract, 'authors': authors}
|
||||
if any(actual[k] != expected.get(k) for k in actual):
|
||||
raise ValueError('Stale source snapshot: reconcile the source version before refresh')
|
||||
if not subset(expected.get('metadata', {}), metadata or {}) or not subset(expected.get('identifiers', {}), identifiers or {}):
|
||||
raise ValueError('Stale source snapshot metadata or identifiers')
|
||||
|
||||
|
||||
def scope_head(c, source_id, manifest):
|
||||
venue = c.execute('SELECT id FROM venues WHERE acronym=?', (manifest.get('venue'),)).fetchone()
|
||||
if not venue:
|
||||
return None
|
||||
matches = [r for r in heads(c, source_id)
|
||||
if [r[i] for i in range(1, 5)] == [venue[0], manifest.get('year'), manifest.get('event_key', ''), manifest.get('list_url')]]
|
||||
if len(matches) > 1:
|
||||
raise ValueError('Forked source revision history')
|
||||
return matches[0][0] if matches else None
|
||||
|
||||
|
||||
def require_manifest(c, source_id, manifest, cache):
|
||||
current_rows(c, source_id, cache)
|
||||
signature = scope_head(c, source_id, manifest)
|
||||
if signature is None:
|
||||
return
|
||||
expected = sum(r['track'] == manifest.get('track') for r in cache['scopes'][signature])
|
||||
bound = manifest.get('coverage_expected_count') if manifest.get('coverage_mode') == 'incremental' else manifest.get('count')
|
||||
if expected < 1 or bound != expected or manifest.get('status') != 'partial':
|
||||
raise ValueError('Source coverage manifest differs from current source snapshot')
|
||||
|
||||
|
||||
def require_row(c, source_id, row, manifest, cache):
|
||||
expected = current_rows(c, source_id, cache).get(row['external_id'])
|
||||
scoped_manifest = {**manifest, 'venue': row['venue'], 'year': row['year'], 'event_key': row.get('event_key', '')}
|
||||
signature = scope_head(c, source_id, scoped_manifest)
|
||||
if expected is None:
|
||||
if signature is not None:
|
||||
raise ValueError('Publication absent from current source snapshot; reconcile source membership first')
|
||||
return
|
||||
if signature is None or not any(r['external_id'] == row['external_id'] for r in cache['scopes'][signature]):
|
||||
raise ValueError('Source listing differs from current source snapshot')
|
||||
for key, value in expected.items():
|
||||
if key in ('metadata', 'identifiers'):
|
||||
okay = subset(value, row.get(key))
|
||||
else:
|
||||
okay = row.get(key) == value
|
||||
if not okay:
|
||||
raise ValueError('Stale source snapshot field: ' + key)
|
||||
@@ -96,10 +96,6 @@ class Store:
|
||||
if found:
|
||||
matches.add(found[0])
|
||||
old = c.execute('SELECT paper_id,title,abstract,retrieved_at,metadata_json FROM source_records WHERE source_id=? AND external_id=?',(source_id:=self.source(source,url),external_id)).fetchone()
|
||||
from paper_atlas.db.source_revisions import require_record
|
||||
if not hasattr(self, '_source_revision_cache'):
|
||||
self._source_revision_cache = {}
|
||||
require_record(c, source_id, external_id, url, title, abstract, authors, identifiers, metadata, self._source_revision_cache)
|
||||
from paper_atlas.db.edition_scopes import preserve
|
||||
metadata = preserve(dict(metadata or {}), old[4] if old else None)
|
||||
if old:
|
||||
|
||||
@@ -101,9 +101,6 @@ def ingest_file(db,path, *, pg_service=None, pg_schema=None):
|
||||
c.commit()
|
||||
if incremental is not None:
|
||||
require_incremental_parent(c, source_id, manifest, incremental)
|
||||
from paper_atlas.db.source_revisions import require_manifest
|
||||
store._source_revision_cache = {}
|
||||
require_manifest(c, source_id, manifest, store._source_revision_cache)
|
||||
digest = hashlib.sha256()
|
||||
with path.open('rb') as stream:
|
||||
for line in stream:
|
||||
@@ -116,10 +113,6 @@ def ingest_file(db,path, *, pg_service=None, pg_schema=None):
|
||||
require_track_record(row, manifest)
|
||||
from paper_atlas.db.events import validate_event_key
|
||||
validate_event_key(row.get('event_key'))
|
||||
from paper_atlas.db.source_revisions import require_row
|
||||
if not hasattr(store, '_source_revision_cache'):
|
||||
store._source_revision_cache = {}
|
||||
require_row(c, source_id, row, manifest, store._source_revision_cache)
|
||||
external = row['external_id']
|
||||
if external in seen:
|
||||
raise ValueError('Duplicate external ID in one collected file: '+external)
|
||||
|
||||
@@ -1,327 +0,0 @@
|
||||
"""Plan-bound publication scope revisions with complete before-images, never reimport."""
|
||||
import argparse
|
||||
from collections import Counter
|
||||
from contextlib import closing
|
||||
import copy
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import re
|
||||
|
||||
from paper_atlas.db import source_revisions as versions
|
||||
from paper_atlas.db.backend import database_arguments, open_read_connection, open_store
|
||||
from paper_atlas.db.edition_scopes import KEY
|
||||
from paper_atlas.ingestion.edition_tracks import curation
|
||||
from paper_atlas.ingestion.event_identity import database_identity, digest, values
|
||||
|
||||
MAX_ROWS = 10000
|
||||
|
||||
|
||||
def validate(inventory):
|
||||
required = {'format', 'source', 'venue', 'year', 'event_key', 'list_url',
|
||||
'previous_rows', 'rows', 'evidence'}
|
||||
if not isinstance(inventory, dict) or set(inventory) != required or inventory['format'] != 1:
|
||||
raise ValueError('Unsupported source revision inventory')
|
||||
if (type(inventory['year']) is not int or inventory['year'] < 2000
|
||||
or not all(isinstance(inventory[k], str) and inventory[k] for k in ('source', 'venue', 'list_url'))
|
||||
or not isinstance(inventory['event_key'], str)):
|
||||
raise ValueError('Explicit publication source scope required')
|
||||
if not inventory['list_url'].startswith('https://'):
|
||||
raise ValueError('HTTPS source listing required')
|
||||
evidence = inventory['evidence']
|
||||
if not isinstance(evidence, list) or not 1 <= len(evidence) <= 100:
|
||||
raise ValueError('Bounded source evidence required')
|
||||
for item in evidence:
|
||||
if (not isinstance(item, dict) or set(item) != {'url', 'sha256'}
|
||||
or not isinstance(item['url'], str) or not item['url'].startswith('https://')
|
||||
or not isinstance(item['sha256'], str) or not re.fullmatch('[0-9a-f]{64}', item['sha256'])):
|
||||
raise ValueError('Source evidence URL/hash required')
|
||||
snapshots = []
|
||||
for key in ('previous_rows', 'rows'):
|
||||
items = inventory[key]
|
||||
if not isinstance(items, list) or not 1 <= len(items) <= MAX_ROWS:
|
||||
raise ValueError('Complete bounded source snapshots required')
|
||||
records = {}
|
||||
for row in items:
|
||||
if not isinstance(row, dict) or any(row.get(k) != inventory[k] for k in ('source', 'venue', 'year')):
|
||||
raise ValueError('Source snapshot scope mismatch')
|
||||
ext = row.get('external_id')
|
||||
if (not isinstance(ext, str) or ext in records or row.get('status') != 'accepted'
|
||||
or not re.fullmatch(r'10\.\d{4,9}/\S+', ext)
|
||||
or row.get('identifiers', {}).get('doi') != ext
|
||||
or not isinstance(row.get('track'), str) or not row['track']
|
||||
or row.get('event_key', '') != inventory['event_key']
|
||||
or not isinstance(row.get('title'), str) or not row['title']
|
||||
or not isinstance(row.get('authors'), list)
|
||||
or not isinstance(row.get('metadata'), dict)):
|
||||
raise ValueError('Unique DOI-bearing accepted publication records required')
|
||||
records[ext] = row
|
||||
snapshots.append(records)
|
||||
previous, current = snapshots
|
||||
if set(previous) != set(current):
|
||||
raise ValueError('Source membership changed; this operation cannot add or remove publications')
|
||||
for ext, row in current.items():
|
||||
before = previous[ext]
|
||||
stable = (set(before) | set(row)) - {'abstract', 'track', 'tags', 'metadata'}
|
||||
if any(before.get(k) != row.get(k) for k in stable):
|
||||
raise ValueError('Stable publication identity or decision changed')
|
||||
return previous, current
|
||||
|
||||
|
||||
def bounded(c, sql, params):
|
||||
result = values(c.execute(sql + ' LIMIT 100001', params))
|
||||
if len(result) > 100000:
|
||||
raise ValueError('Source revision protection exceeds bounded scope')
|
||||
return result
|
||||
|
||||
|
||||
def capture(c, inventory):
|
||||
previous, current = validate(inventory)
|
||||
source = c.execute('SELECT id FROM sources WHERE name=?', (inventory['source'],)).fetchone()
|
||||
venue = c.execute('SELECT id FROM venues WHERE acronym=?', (inventory['venue'],)).fetchone()
|
||||
if not source or not venue:
|
||||
raise ValueError('Existing source and venue required')
|
||||
sid, vid = source[0], venue[0]
|
||||
editions = bounded(c, 'SELECT * FROM editions WHERE venue_id=? AND year=? AND event_key=? ORDER BY id',
|
||||
(vid, inventory['year'], inventory['event_key']))
|
||||
by_track = {r[3]: r[0] for r in editions}
|
||||
# The reviewed scope includes all its existing target attempts, even when
|
||||
# they originate from another source. No empty-target shortcut is used.
|
||||
scope_subs = 'SELECT s.id FROM submissions s JOIN editions e ON e.id=s.edition_id WHERE e.venue_id=? AND e.year=? AND e.event_key=?'
|
||||
scope_params = (vid, inventory['year'], inventory['event_key'])
|
||||
scoped = bounded(c, 'SELECT * FROM submissions WHERE id IN (' + scope_subs + ') ORDER BY id', scope_params)
|
||||
own_records = bounded(c, '''SELECT DISTINCT r.* FROM source_records r JOIN submission_sources ss ON ss.source_record_id=r.id
|
||||
WHERE r.source_id=? AND ss.submission_id IN (''' + scope_subs + ') ORDER BY r.id', (sid, *scope_params))
|
||||
if not own_records:
|
||||
raise ValueError('Existing source observations required')
|
||||
if any(r[2] not in current for r in own_records):
|
||||
raise ValueError('Snapshot omits an existing source observation')
|
||||
pids = sorted({r[1] for r in scoped})
|
||||
if not pids or len(pids) > MAX_ROWS:
|
||||
raise ValueError('Bounded nonempty protected paper scope required')
|
||||
marks = ','.join('?' for _ in pids)
|
||||
papers = 'SELECT id FROM papers WHERE id IN (' + marks + ')'
|
||||
subs = 'SELECT id FROM submissions WHERE paper_id IN (' + papers + ')'
|
||||
decisions = 'SELECT id FROM decisions WHERE submission_id IN (' + subs + ')'
|
||||
queries = {
|
||||
'papers': 'SELECT * FROM papers WHERE id IN (' + papers + ') ORDER BY id',
|
||||
'identifiers': 'SELECT * FROM identifiers WHERE paper_id IN (' + papers + ') ORDER BY scheme,value',
|
||||
'source_records': 'SELECT * FROM source_records WHERE paper_id IN (' + papers + ') ORDER BY id',
|
||||
'submissions': 'SELECT * FROM submissions WHERE paper_id IN (' + papers + ') ORDER BY id',
|
||||
'decisions': 'SELECT * FROM decisions WHERE submission_id IN (' + subs + ') ORDER BY id',
|
||||
'submission_sources': 'SELECT * FROM submission_sources WHERE submission_id IN (' + subs + ') ORDER BY submission_id,source_record_id,source_submission_id',
|
||||
'submission_identifiers': 'SELECT * FROM submission_identifiers WHERE submission_id IN (' + subs + ') ORDER BY edition_id,scheme,value',
|
||||
'decision_sources': 'SELECT * FROM decision_sources WHERE decision_id IN (' + decisions + ') ORDER BY decision_id,source_record_id,source_decision_id',
|
||||
'paper_tags': 'SELECT * FROM paper_tags WHERE paper_id IN (' + papers + ') ORDER BY paper_id,tag_id,evidence_key',
|
||||
}
|
||||
from paper_atlas.curation.annotations import available
|
||||
if available(c):
|
||||
queries['annotation_events'] = 'SELECT * FROM annotation_events WHERE paper_id IN (' + papers + ') ORDER BY id'
|
||||
packet = {k: bounded(c, q, pids) for k, q in queries.items()}
|
||||
coverage = bounded(c, '''SELECT es.* FROM edition_sources es JOIN editions e ON e.id=es.edition_id
|
||||
WHERE es.source_id=? AND e.venue_id=? AND e.year=? AND e.event_key=? ORDER BY es.edition_id,es.list_url''', (sid, *scope_params))
|
||||
if not coverage or any(r[2] != inventory['list_url'] for r in coverage):
|
||||
raise ValueError('Unambiguous source listing required')
|
||||
if len({r[0] for r in coverage}) != len(coverage):
|
||||
raise ValueError('One source coverage entry per edition required')
|
||||
heads = [[r[i] for i in range(len(r))] for r in versions.heads(c, sid)]
|
||||
own_heads = [r for r in heads if r[1:] == [vid, inventory['year'], inventory['event_key'], inventory['list_url']]]
|
||||
if len(own_heads) > 1:
|
||||
raise ValueError('Forked source revision history')
|
||||
parent = own_heads[0][0] if own_heads else None
|
||||
return {'source_id': sid, 'venue_id': vid, 'editions': editions, 'coverage': coverage,
|
||||
'packet': packet, 'own_records': own_records, 'revision_heads': heads,
|
||||
'parent_sha256': parent, 'by_track': by_track,
|
||||
'venue_names': sorted({inventory['venue']} | {r[0] for r in c.execute('SELECT alias FROM venue_aliases WHERE venue_id=?', (vid,))})}
|
||||
|
||||
|
||||
def changes(c, inventory, before):
|
||||
previous, current = validate(inventory)
|
||||
packet = before['packet']; result = []; sid = before['source_id']
|
||||
editions = {r[0]: r for r in before['editions']}
|
||||
for raw in before['own_records']:
|
||||
ext = raw[2]; old = previous[ext]; new = current[ext]
|
||||
metadata = json.loads(raw[8])
|
||||
candidates = [old, new]
|
||||
if not any(raw[4] == r['url'] and raw[5] == r['title'] and raw[6] == r.get('abstract')
|
||||
and json.loads(raw[7]) == r['authors'] and versions.subset(r['metadata'], metadata) for r in candidates):
|
||||
raise ValueError('Current raw source differs from both reviewed snapshots')
|
||||
if metadata.get('record_identifiers', {}).get('doi') != ext:
|
||||
raise ValueError('Current stable DOI differs from source evidence')
|
||||
attempts = [s for s in packet['submissions'] if s[3] == raw[0] and s[2] in editions]
|
||||
if len(attempts) != 1:
|
||||
raise ValueError('Exactly one publication attempt per source record required')
|
||||
sub = attempts[0]; origin = editions[sub[2]]
|
||||
if origin[3] not in {old['track'], new['track']} or sub[4] != ext or sub[1] != raw[3]:
|
||||
raise ValueError('Current source attempt identity/scope differs')
|
||||
if [x for x in packet['submission_sources'] if x[0] == sub[0]] != [[sub[0], raw[0], ext]]:
|
||||
raise ValueError('Shared-source attempt requires separate reconciliation')
|
||||
decisions = [d for d in packet['decisions'] if d[1] == sub[0]]
|
||||
if not decisions or any(d[2] != 'accepted' for d in decisions):
|
||||
raise ValueError('Only accepted publication observations can be revised')
|
||||
target = before['by_track'].get(new['track'])
|
||||
if target is None:
|
||||
raise ValueError('Reviewed target edition must already exist')
|
||||
identities = [x for x in packet['submission_identifiers'] if x[3] == sub[0]]
|
||||
if not identities or any(x[0] != sub[2] for x in identities):
|
||||
raise ValueError('Inconsistent scoped submission identifiers')
|
||||
for _, scheme, value, _ in identities:
|
||||
conflict = c.execute('SELECT submission_id FROM submission_identifiers WHERE edition_id=? AND scheme=? AND value=?', (target, scheme, value)).fetchone()
|
||||
if conflict and conflict[0] != sub[0]:
|
||||
raise ValueError('Target submission identifier collision')
|
||||
replacement = copy.deepcopy(metadata); replacement.update(new['metadata'])
|
||||
if sub[2] != target and KEY in metadata:
|
||||
raise ValueError('An already curated attempt needs explicit scope-chain reconciliation')
|
||||
if sub[2] != target or raw[6] != new.get('abstract') or replacement != metadata:
|
||||
result.append({'source_record_id': raw[0], 'paper_id': raw[3], 'submission_id': sub[0],
|
||||
'external_id': ext, 'from_edition_id': sub[2], 'target_edition_id': target,
|
||||
'from_track': origin[3], 'track': new['track'],
|
||||
'new_abstract': new.get('abstract'), 'metadata': replacement})
|
||||
old_expected = Counter(r['track'] for r in previous.values()); new_expected = Counter(r['track'] for r in current.values())
|
||||
observed = Counter()
|
||||
own_ids = {r[0] for r in before['own_records']}
|
||||
for s in packet['submissions']:
|
||||
if s[3] in own_ids and s[2] in editions:
|
||||
observed[s[2]] += 1
|
||||
coverage = []
|
||||
for raw in before['coverage']:
|
||||
track = editions[raw[0]][3]
|
||||
if raw[3] != 'partial' or raw[8] is not None or raw[5] != observed[raw[0]]:
|
||||
raise ValueError('Coverage parent is not the verified partial source observation count')
|
||||
if raw[4] not in {old_expected[track], new_expected[track]}:
|
||||
raise ValueError('Coverage expected count differs from both source versions')
|
||||
count = raw[5] + sum((r['target_edition_id'] == raw[0]) - (r['from_edition_id'] == raw[0]) for r in result)
|
||||
if count < 0 or count > new_expected[track]:
|
||||
raise ValueError('Corrected coverage exceeds current source membership')
|
||||
coverage.append({'before': raw, 'expected_count': new_expected[track], 'imported_count': count})
|
||||
covered = {r['before'][0] for r in coverage}
|
||||
if any(r['target_edition_id'] not in covered for r in result):
|
||||
raise ValueError('Target source coverage must already exist')
|
||||
return result, coverage
|
||||
|
||||
|
||||
def proposal(c, inventory, identity):
|
||||
before = capture(c, inventory)
|
||||
if before['parent_sha256']:
|
||||
saved = json.loads(c.execute('SELECT records_json FROM source_scope_revisions WHERE version_sha256=?', (before['parent_sha256'],)).fetchone()[0])
|
||||
if sorted(saved, key=lambda r: r['external_id']) != sorted(inventory['previous_rows'], key=lambda r: r['external_id']):
|
||||
raise ValueError('Previous snapshot differs from active source version')
|
||||
records, coverage = changes(c, inventory, before)
|
||||
return {'format': 1, 'database': identity, 'inventory': inventory, 'before': before,
|
||||
'changes': records, 'coverage': coverage}
|
||||
|
||||
|
||||
def verify(c, plan, signature):
|
||||
after = capture(c, plan['inventory']); expected = copy.deepcopy(plan['before']['packet'])
|
||||
for change in plan['changes']:
|
||||
for row in expected['submissions']:
|
||||
if row[0] == change['submission_id']:
|
||||
row[2] = change['target_edition_id']
|
||||
for row in expected['submission_identifiers']:
|
||||
if row[3] == change['submission_id']:
|
||||
row[0] = change['target_edition_id']
|
||||
for row in expected['source_records']:
|
||||
if row[0] == change['source_record_id']:
|
||||
row[6] = change['new_abstract']
|
||||
row[8] = encoded_metadata(plan, change, signature)
|
||||
expected['submission_identifiers'].sort(key=lambda r: (r[0], r[1], r[2]))
|
||||
if after['packet'] != expected:
|
||||
raise ValueError('Protected profiles/history/tags/identifiers differ; roll back')
|
||||
if after['editions'] != plan['before']['editions']:
|
||||
raise ValueError('Edition identities changed')
|
||||
expected_heads = [r for r in plan['before']['revision_heads'] if r[0] != plan['before']['parent_sha256']]
|
||||
inventory = plan['inventory']
|
||||
expected_heads.append([signature, plan['before']['venue_id'], inventory['year'], inventory['event_key'], inventory['list_url']])
|
||||
if after['revision_heads'] != sorted(expected_heads):
|
||||
raise ValueError('Active source version differs')
|
||||
expected_coverage = []
|
||||
for item in plan['coverage']:
|
||||
row = item['before'][:]; row[4] = item['expected_count']; row[5] = item['imported_count']
|
||||
expected_coverage.append(row)
|
||||
if after['coverage'] != expected_coverage:
|
||||
raise ValueError('Reconciled coverage differs; roll back')
|
||||
stored = c.execute('SELECT records_json,plan_json,parent_sha256 FROM source_scope_revisions WHERE version_sha256=?', (signature,)).fetchone()
|
||||
if (not stored or json.loads(stored[0]) != plan['inventory']['rows']
|
||||
or json.loads(stored[1]) != plan or stored[2] != plan['before']['parent_sha256']):
|
||||
raise ValueError('Versioned source or complete before-images changed')
|
||||
return {'records_changed': len(plan['changes']), 'events_moved': sum(r['from_edition_id'] != r['target_edition_id'] for r in plan['changes']),
|
||||
'protected_papers': len(expected['papers']), 'protected_decisions': len(expected['decisions'])}
|
||||
|
||||
|
||||
def encoded_metadata(plan, change, signature):
|
||||
metadata = copy.deepcopy(change['metadata'])
|
||||
if change['from_edition_id'] != change['target_edition_id']:
|
||||
inventory = plan['inventory']
|
||||
evidence = inventory['evidence'][0]
|
||||
row = {**change, 'source': inventory['source'], 'doi': change['external_id'],
|
||||
'venue_id': plan['before']['venue_id'], 'year': inventory['year'],
|
||||
'event_key': inventory['event_key'], 'venue_names': plan['before']['venue_names'],
|
||||
'section': change['track'], 'evidence_url': evidence['url'], 'evidence_sha256': evidence['sha256']}
|
||||
metadata[KEY] = [curation(row, change['target_edition_id'], signature)]
|
||||
return json.dumps(metadata, ensure_ascii=False)
|
||||
|
||||
|
||||
def apply_plan(c, plan):
|
||||
if plan.get('format') != 1:
|
||||
raise ValueError('Unsupported source revision plan')
|
||||
if not getattr(c, 'postgres', False) and not c.in_transaction:
|
||||
c.execute('BEGIN IMMEDIATE')
|
||||
signature = digest(plan)
|
||||
if versions.available(c) and c.execute('SELECT 1 FROM source_scope_revisions WHERE version_sha256=?', (signature,)).fetchone():
|
||||
return {'status': 'already_applied', 'version_sha256': signature, **verify(c, plan, signature)}
|
||||
if getattr(c, 'postgres', False):
|
||||
c.execute('LOCK TABLE sources,papers,identifiers,source_records,venues,venue_aliases,editions,edition_sources,submissions,decisions,submission_sources,submission_identifiers,decision_sources,tags,paper_tags IN SHARE ROW EXCLUSIVE MODE')
|
||||
if proposal(c, plan['inventory'], plan['database']) != plan:
|
||||
raise ValueError('Stale source revision plan; create and review a fresh plan')
|
||||
versions.initialize(c)
|
||||
for row in plan['changes']:
|
||||
if row['from_edition_id'] != row['target_edition_id']:
|
||||
c.execute('UPDATE submission_identifiers SET edition_id=? WHERE submission_id=?', (row['target_edition_id'], row['submission_id']))
|
||||
c.execute('UPDATE submissions SET edition_id=? WHERE id=? AND edition_id=?', (row['target_edition_id'], row['submission_id'], row['from_edition_id']))
|
||||
c.execute('UPDATE source_records SET abstract=?,metadata_json=? WHERE id=?',
|
||||
(row['new_abstract'], encoded_metadata(plan, row, signature), row['source_record_id']))
|
||||
for row in plan['coverage']:
|
||||
before = row['before']
|
||||
c.execute('UPDATE edition_sources SET expected_count=?,imported_count=? WHERE edition_id=? AND source_id=? AND list_url=?',
|
||||
(row['expected_count'], row['imported_count'], before[0], before[1], before[2]))
|
||||
inventory = plan['inventory']
|
||||
c.execute('''INSERT INTO source_scope_revisions(version_sha256,source_id,venue_id,year,event_key,list_url,parent_sha256,records_json,plan_json)
|
||||
VALUES(?,?,?,?,?,?,?,?,?)''', (signature, plan['before']['source_id'], plan['before']['venue_id'], inventory['year'], inventory['event_key'],
|
||||
inventory['list_url'], plan['before']['parent_sha256'], json.dumps(inventory['rows'], ensure_ascii=False), json.dumps(plan, ensure_ascii=False)))
|
||||
return {'status': 'applied', 'version_sha256': signature, **verify(c, plan, signature)}
|
||||
|
||||
|
||||
def run(db, out, *, pg_service=None, pg_schema=None, inventory=None, plan=None, plan_sha256=None):
|
||||
out = Path(out)
|
||||
if out.exists() or not out.parent.is_dir():
|
||||
raise ValueError('New output in existing directory required')
|
||||
if bool(inventory) == bool(plan) or bool(plan) != bool(plan_sha256):
|
||||
raise ValueError('Choose inventory preflight or plan plus exact file hash')
|
||||
if inventory:
|
||||
with closing(open_read_connection(db, pg_service=pg_service, pg_schema=pg_schema)) as c:
|
||||
result = proposal(c, json.loads(Path(inventory).read_bytes()), database_identity(c, db))
|
||||
else:
|
||||
raw = Path(plan).read_bytes()
|
||||
if hashlib.sha256(raw).hexdigest() != plan_sha256:
|
||||
raise ValueError('Plan file hash differs')
|
||||
proposed = json.loads(raw)
|
||||
with closing(open_store(db, pg_service=pg_service, pg_schema=pg_schema).conn) as c:
|
||||
try:
|
||||
if proposed['database'] != database_identity(c, db):
|
||||
raise ValueError('Plan belongs to another database')
|
||||
if not getattr(c, 'postgres', False):
|
||||
c.commit(); c.execute('BEGIN IMMEDIATE')
|
||||
result = apply_plan(c, proposed); c.commit()
|
||||
except BaseException:
|
||||
c.rollback(); raise
|
||||
out.write_text(json.dumps(result, ensure_ascii=False, indent=2) + '\n')
|
||||
return result
|
||||
|
||||
|
||||
def main(argv=None, *, prog=None):
|
||||
parser = argparse.ArgumentParser(prog=prog); database_arguments(parser)
|
||||
parser.add_argument('--inventory'); parser.add_argument('--plan'); parser.add_argument('--plan-sha256'); parser.add_argument('--out', required=True)
|
||||
args = parser.parse_args(argv)
|
||||
report = run(args.db, args.out, pg_service=args.pg_service, pg_schema=args.pg_schema,
|
||||
inventory=args.inventory, plan=args.plan, plan_sha256=args.plan_sha256)
|
||||
print(json.dumps({'status': report.get('status', 'planned'), 'out': args.out}), flush=True)
|
||||
@@ -8,7 +8,7 @@ TABLES = ('sources', 'papers', 'identifiers', 'source_records', 'venues', 'editi
|
||||
'submission_sources', 'submission_identifiers', 'decision_sources',
|
||||
'submission_merges', 'decision_merges', 'schema_migrations', 'tags',
|
||||
'paper_tags', 'match_candidates', 'paper_merges', 'ingest_runs')
|
||||
OPTIONAL_TABLES = ('annotation_events', 'source_scope_revisions')
|
||||
OPTIONAL_TABLES = ('annotation_events',)
|
||||
CHECKS = {
|
||||
'annotation_events': ["kind IN ('tag','research_type')", 'retracts_id IS NULL OR retracts_id<>id'],
|
||||
'venues': ["venue_type IN ('conference','journal','review_platform')"],
|
||||
|
||||
@@ -1,209 +0,0 @@
|
||||
"""Whole-source scope correction, stale refresh, full history and atomicity on both engines."""
|
||||
from contextlib import closing, redirect_stdout
|
||||
import copy
|
||||
import hashlib
|
||||
import io
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import tempfile
|
||||
import unittest
|
||||
from unittest.mock import patch
|
||||
import uuid
|
||||
|
||||
from paper_atlas.db.backend import open_store
|
||||
from paper_atlas.db.edition_scopes import KEY
|
||||
from paper_atlas.db.source_revisions import available, require_row, require_manifest
|
||||
from paper_atlas.db.store import Store
|
||||
from paper_atlas.ingestion.source_revisions import proposal, apply_plan, run, validate
|
||||
from paper_atlas.ingestion.event_identity import database_identity, digest, values
|
||||
from paper_atlas.ingestion.records import coverage_options, ingest_file
|
||||
from paper_atlas.postgres.client import connect
|
||||
from paper_atlas.postgres.migration import migrate
|
||||
from paper_atlas.postgres.schema import quote
|
||||
|
||||
URL = 'https://example.org/volume'
|
||||
|
||||
|
||||
def seed(path):
|
||||
old = []
|
||||
for i in range(4):
|
||||
doi = '10.1234/publication'+str(i)
|
||||
old.append({'source': 'fixture', 'venue': 'MM', 'year': 2026, 'track': 'main' if i == 0 else 'unclassified',
|
||||
'external_id': doi, 'url': 'https://doi.org/'+doi, 'title': 'Distinct publication '+str(i),
|
||||
'authors': ['Alice Author', 'Bob Writer'], 'abstract': None if i == 1 else 'Source abstract '+str(i),
|
||||
'identifiers': {'doi': doi}, 'submission_identifiers': {'publication_doi': doi},
|
||||
'status': 'accepted', 'raw_decision': 'Publication observation', 'evidence_url': URL,
|
||||
'observed_at': '2026-06-01T00:00:00Z', 'tags': [{'namespace': 'fixture:track', 'value': 'main' if i == 0 else 'unclassified'}],
|
||||
'metadata': {'original': i, 'program': None, 'scientific_work_identity_approved': False}})
|
||||
current = copy.deepcopy(old)
|
||||
current[1].update(track='main', abstract='Reviewed program abstract with NUL\x00 and SOH\x01')
|
||||
current[1]['metadata']['program'] = {'id': 'p1', 'evidence_url': URL}
|
||||
current[1]['tags'][0]['value'] = 'main'
|
||||
store = Store(path)
|
||||
for row in old[:3]:
|
||||
p, r = store.record(row['source'], row['external_id'], row['url'], row['title'], row['abstract'], row['authors'], row['identifiers'], row['metadata'])
|
||||
store.decision(p, r, 'MM', 2026, row['track'], row['external_id'], URL, 'accepted', row['raw_decision'],
|
||||
identities=[('publication_doi', row['external_id'])], observed_at=row['observed_at'])
|
||||
store.record_tags(p, r, 'fixture', row['tags'])
|
||||
if row == old[1]:
|
||||
store.conn.execute('UPDATE papers SET abstract=? WHERE id=?', ('Canonical preprint abstract', p))
|
||||
p, other = store.record('prior', 'old-forum', 'https://example.org/prior', row['title'], 'Canonical preprint abstract', row['authors'], row['identifiers'])
|
||||
store.decision(p, other, 'PRIOR', 2025, 'main', 'old-forum', 'https://example.org/prior', 'rejected', 'Reject', observed_at='2025-01-01T00:00:00Z')
|
||||
# An unrelated source already has an attempt in the populated target edition.
|
||||
p, r = store.record('other', 'other', 'https://example.org/other', 'Unrelated target paper', 'Other abstract', ['Someone Else'])
|
||||
store.decision(p, r, 'MM', 2026, 'main', 'other', 'https://example.org/other', 'accepted', 'Published')
|
||||
sid = store.conn.execute("SELECT id FROM sources WHERE name='fixture'").fetchone()[0]
|
||||
for track, expected, imported in [('main', 1, 1), ('unclassified', 3, 2)]:
|
||||
eid = store.conn.execute('SELECT id FROM editions WHERE year=2026 AND track=?', (track,)).fetchone()[0]
|
||||
store.conn.execute("INSERT INTO edition_sources VALUES(?,?,?,'partial',?,?,?,'2026-06-01',NULL)", (eid, sid, URL, expected, imported, 'checkpoint'))
|
||||
store.conn.commit(); store.conn.close()
|
||||
return {'format': 1, 'source': 'fixture', 'venue': 'MM', 'year': 2026, 'event_key': '', 'list_url': URL,
|
||||
'previous_rows': old, 'rows': current, 'evidence': [{'url': URL, 'sha256': 'a'*64}]}
|
||||
|
||||
|
||||
class RevisionCases:
|
||||
def store(self):
|
||||
return open_store(**self.target)
|
||||
|
||||
def plan(self, c):
|
||||
return proposal(c, self.inventory, database_identity(c, self.target.get('db')))
|
||||
|
||||
def test_move_to_populated_target_preserves_full_history_and_before_images(self):
|
||||
with closing(self.store().conn) as c:
|
||||
plan = self.plan(c); self.assertEqual(len(plan['changes']), 1)
|
||||
self.assertEqual(len(plan['before']['packet']['submissions']), 5)
|
||||
before_papers = plan['before']['packet']['papers']
|
||||
before_tags = plan['before']['packet']['paper_tags']
|
||||
result = apply_plan(c, plan); c.commit()
|
||||
self.assertEqual((result['events_moved'], result['records_changed']), (1, 1))
|
||||
self.assertEqual(result['protected_decisions'], 5)
|
||||
self.assertEqual(values(c.execute('SELECT * FROM papers ORDER BY id')), before_papers)
|
||||
self.assertEqual(values(c.execute('SELECT * FROM paper_tags ORDER BY paper_id,tag_id,evidence_key')), before_tags)
|
||||
self.assertEqual(c.execute("SELECT count(*) FROM decisions WHERE status='rejected'").fetchone()[0], 1)
|
||||
self.assertEqual(values(c.execute('SELECT status,expected_count,imported_count,cursor,last_success_at,last_error FROM edition_sources ORDER BY edition_id')),
|
||||
[['partial', 2, 2, 'checkpoint', '2026-06-01', None], ['partial', 2, 1, 'checkpoint', '2026-06-01', None]])
|
||||
saved = json.loads(c.execute('SELECT plan_json FROM source_scope_revisions').fetchone()[0])
|
||||
self.assertEqual(saved, plan)
|
||||
self.assertEqual(apply_plan(c, plan)['status'], 'already_applied')
|
||||
self.assertEqual(c.execute('SELECT count(*) FROM source_scope_revisions').fetchone()[0], 1)
|
||||
|
||||
def test_stale_direct_store_and_jsonl_refresh_fail_but_current_refresh_succeeds(self):
|
||||
with closing(self.store().conn) as c:
|
||||
plan = self.plan(c); apply_plan(c, plan); c.commit()
|
||||
with closing(self.store().conn) as c:
|
||||
store = object.__new__(Store); store.conn = c; store.event_identity = True
|
||||
old = self.inventory['previous_rows'][1]
|
||||
with self.assertRaisesRegex(ValueError, 'Stale source'):
|
||||
store.record('fixture', old['external_id'], old['url'], old['title'], old['abstract'], old['authors'], old['identifiers'], old['metadata'])
|
||||
c.rollback()
|
||||
row = self.inventory['rows'][1]
|
||||
p, r = store.record('fixture', row['external_id'], row['url'], row['title'], row['abstract'], row['authors'], row['identifiers'], row['metadata'])
|
||||
self.assertEqual(c.execute('SELECT abstract FROM papers WHERE id=?', (p,)).fetchone()[0], 'Canonical preprint abstract')
|
||||
self.assertEqual(json.loads(c.execute('SELECT metadata_json FROM source_records WHERE id=?', (r,)).fetchone()[0])[KEY][0]['target']['track'], 'main')
|
||||
c.rollback()
|
||||
path = self.root/'old.jsonl'; raw = (json.dumps(old)+'\n').encode(); path.write_bytes(raw)
|
||||
path.with_suffix('.manifest.json').write_text(json.dumps({'source': 'fixture', 'venue': 'MM', 'year': 2026,
|
||||
'track': 'unclassified', 'list_url': URL, 'status': 'partial', 'count': 1, 'file_sha256': hashlib.sha256(raw).hexdigest()}))
|
||||
with self.assertRaisesRegex(ValueError, 'source snapshot'):
|
||||
ingest_file(self.target.get('db'), path, **{k: v for k, v in self.target.items() if k != 'db'})
|
||||
|
||||
def test_unregistered_member_and_changed_program_metadata_are_rejected(self):
|
||||
with closing(self.store().conn) as c:
|
||||
apply_plan(c, self.plan(c)); c.commit()
|
||||
sid = c.execute("SELECT id FROM sources WHERE name='fixture'").fetchone()[0]
|
||||
cache = {}; unknown = copy.deepcopy(self.inventory['rows'][0]); unknown['external_id'] = '10.1234/unlisted'
|
||||
with self.assertRaisesRegex(ValueError, 'absent from current'):
|
||||
require_row(c, sid, unknown, {'list_url': URL}, cache)
|
||||
bad = copy.deepcopy(self.inventory['rows'][1]); bad['metadata']['program'] = None
|
||||
with self.assertRaisesRegex(ValueError, 'Stale source'):
|
||||
require_row(c, sid, bad, {'list_url': URL}, cache)
|
||||
good = copy.deepcopy(self.inventory['rows'][1]); good['metadata']['verified_work_anchor'] = {'reason': 'extra evidence'}
|
||||
require_row(c, sid, good, {'list_url': URL}, cache)
|
||||
with self.assertRaisesRegex(ValueError, 'coverage manifest'):
|
||||
require_manifest(c, sid, {'venue': 'MM', 'year': 2026, 'track': 'main', 'list_url': URL, 'count': 1, 'status': 'partial'}, cache)
|
||||
require_manifest(c, sid, {'venue': 'MM', 'year': 2026, 'track': 'main', 'list_url': URL, 'count': 2, 'status': 'partial'}, cache)
|
||||
|
||||
def test_stale_plan_and_target_identifier_collision_prevent_writes(self):
|
||||
with closing(self.store().conn) as c:
|
||||
plan = self.plan(c)
|
||||
c.execute("UPDATE decisions SET raw_value='Additional evidence' WHERE status='rejected'")
|
||||
with self.assertRaisesRegex(ValueError, 'Stale'):
|
||||
apply_plan(c, plan)
|
||||
c.rollback()
|
||||
move = plan['changes'][0]
|
||||
target_sub = c.execute('SELECT id FROM submissions WHERE edition_id=? LIMIT 1', (move['target_edition_id'],)).fetchone()[0]
|
||||
c.execute('INSERT INTO submission_identifiers VALUES(?,?,?,?)', (move['target_edition_id'], 'publication_doi', move['external_id'], target_sub))
|
||||
with self.assertRaisesRegex(ValueError, 'collision'):
|
||||
self.plan(c)
|
||||
c.rollback()
|
||||
self.assertFalse(available(c))
|
||||
|
||||
def test_failed_postcheck_rolls_back_rows_extension_and_coverage(self):
|
||||
with closing(self.store().conn) as c:
|
||||
plan = self.plan(c)
|
||||
with patch('paper_atlas.ingestion.source_revisions.verify', side_effect=ValueError('Injected verification failure')):
|
||||
with self.assertRaisesRegex(ValueError, 'Injected'):
|
||||
apply_plan(c, plan)
|
||||
c.rollback()
|
||||
self.assertFalse(available(c))
|
||||
self.assertEqual(self.plan(c), plan)
|
||||
|
||||
def test_cli_binds_database_and_file_hash_without_writing_during_preflight(self):
|
||||
inventory = self.root/'inventory.json'; inventory.write_text(json.dumps(self.inventory))
|
||||
path = self.root/'plan.json'
|
||||
args = {k: v for k, v in self.target.items() if k != 'db'}
|
||||
run(self.target.get('db'), path, inventory=inventory, **args)
|
||||
with closing(self.store().conn) as c:
|
||||
self.assertFalse(available(c))
|
||||
with self.assertRaisesRegex(ValueError, 'hash'):
|
||||
run(self.target.get('db'), self.root/'bad.json', plan=path, plan_sha256='0'*64, **args)
|
||||
report = run(self.target.get('db'), self.root/'applied.json', plan=path, plan_sha256=hashlib.sha256(path.read_bytes()).hexdigest(), **args)
|
||||
self.assertEqual(report['events_moved'], 1)
|
||||
|
||||
def test_membership_identity_changes_and_incremental_shrink_remain_forbidden(self):
|
||||
for mutate in [lambda x: x['rows'].pop(), lambda x: x['rows'][0].update(title='Different work'),
|
||||
lambda x: x['rows'][0].update(status='rejected')]:
|
||||
bad = copy.deepcopy(self.inventory); mutate(bad)
|
||||
with self.assertRaises(ValueError):
|
||||
validate(bad)
|
||||
with self.assertRaisesRegex(ValueError, 'incremental'):
|
||||
coverage_options({'coverage_mode': 'incremental', 'venue': 'MM', 'year': 2026, 'track': 'unclassified',
|
||||
'status': 'partial', 'count': 1, 'coverage_previous_count': 2,
|
||||
'coverage_previous_expected_count': 3, 'coverage_expected_count': 2})
|
||||
|
||||
|
||||
class SQLiteSourceRevisionTests(RevisionCases, unittest.TestCase):
|
||||
def setUp(self):
|
||||
temp = tempfile.TemporaryDirectory(); self.addCleanup(temp.cleanup); self.root = Path(temp.name)
|
||||
db = self.root/'source.sqlite'; self.inventory = seed(db); self.target = {'db': db}
|
||||
|
||||
@unittest.skipUnless(os.environ.get('PAPER_ATLAS_TEST_PG_SERVICE'), 'Requires approved remote PostgreSQL service')
|
||||
def test_optional_revision_table_migrates_with_full_history(self):
|
||||
with closing(self.store().conn) as c:
|
||||
plan = self.plan(c); apply_plan(c, plan); c.commit()
|
||||
service = os.environ['PAPER_ATLAS_TEST_PG_SERVICE']; schema = 'pa_rev_copy_'+uuid.uuid4().hex[:10]
|
||||
self.addCleanup(drop_schema, service, schema)
|
||||
with redirect_stdout(io.StringIO()):
|
||||
migrate(self.target['db'], service, self.root/'copied.json', schema=schema, min_free_gib=0)
|
||||
with closing(open_store(pg_service=service, pg_schema=schema).conn) as c:
|
||||
self.assertEqual(json.loads(c.execute('SELECT plan_json FROM source_scope_revisions').fetchone()[0]), plan)
|
||||
self.assertEqual(c.execute('SELECT count(*) FROM source_scope_revisions').fetchone()[0], 1)
|
||||
|
||||
|
||||
def drop_schema(service, schema):
|
||||
with connect(service) as c:
|
||||
for name, in c.execute('SELECT nspname FROM pg_namespace WHERE starts_with(nspname,%s)', (schema,)):
|
||||
c.execute('DROP SCHEMA '+quote(name)+' CASCADE')
|
||||
|
||||
|
||||
@unittest.skipUnless(os.environ.get('PAPER_ATLAS_TEST_PG_SERVICE'), 'Requires approved remote PostgreSQL service')
|
||||
class PostgreSQLSourceRevisionTests(RevisionCases, unittest.TestCase):
|
||||
def setUp(self):
|
||||
temp = tempfile.TemporaryDirectory(); self.addCleanup(temp.cleanup); self.root = Path(temp.name)
|
||||
db = self.root/'source.sqlite'; self.inventory = seed(db)
|
||||
service = os.environ['PAPER_ATLAS_TEST_PG_SERVICE']; schema = 'pa_rev_'+uuid.uuid4().hex[:12]
|
||||
self.addCleanup(drop_schema, service, schema)
|
||||
with redirect_stdout(io.StringIO()):
|
||||
migrate(db, service, self.root/'migration.json', schema=schema, min_free_gib=0)
|
||||
self.target = {'pg_service': service, 'pg_schema': schema}
|
||||
Reference in New Issue
Block a user