Compare commits
6 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 6d35a2e567 | |||
| 4e071ca0f1 | |||
| f97852b630 | |||
| a980b1a1df | |||
| 3754545003 | |||
| e38b2f1ca8 |
@@ -273,6 +273,23 @@ jobs:
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','collect','iclr-archive','--help'],cwd=outside,check=True)
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','collect','acl','--help'],cwd=outside,check=True)
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','collect','springer-selected','--help'],cwd=outside,check=True)
|
||||
publisher_fixture = "\n".join((
|
||||
"import pathlib, runpy, sys",
|
||||
"fixture = runpy.run_path(sys.argv[1])",
|
||||
"root = pathlib.Path(sys.argv[2])",
|
||||
"root.mkdir()",
|
||||
"fixture['snapshots'](root)",
|
||||
))
|
||||
publisher_input = root/'eccv-publisher-snapshots'
|
||||
subprocess.run([python,'-I','-B','-c',publisher_fixture,
|
||||
str(src/'tests/test_eccv2026_publications.py'),str(publisher_input)],cwd=outside,check=True)
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','collect','eccv2026-publications',
|
||||
'--toc-snapshots',str(publisher_input/'toc'),
|
||||
'--chapter-snapshots',str(publisher_input/'chapters'),
|
||||
'--out',str(root/'installed-eccv-publisher')],cwd=outside,check=True)
|
||||
publisher_report = json.loads((root/'installed-eccv-publisher/collection-report.json').read_bytes())
|
||||
assert publisher_report['records'] == 1 and publisher_report['toc_chapters'] == 2835
|
||||
assert not publisher_report['database_written']
|
||||
springer = json.loads(gzip.decompress((src/'tests/fixtures/springer-aistats1993-fixture.json.gz').read_bytes()))
|
||||
for group in ('toc','chapters'):
|
||||
folder = root/'springer-snapshots'/group
|
||||
|
||||
@@ -148,3 +148,5 @@ ECCV 2026 的[暂定节目采集器](docs/eccv2026-program.md)合并重复节目
|
||||
`collect mm2026-program` 从已冻结官方快照恢复全部 28 个来源 track 的 2,143 个节目 ID,保留 4,326 次展示的来源位置与场次上下文,单列 216 个摘要缺失项;输出供贡献类型、出版及作品身份核查使用,不是可直接导入的论文/决定队列。见 [MM 2026 使用、来源和恢复说明](docs/mm2026-source-status.md)。
|
||||
|
||||
`collect mm2026-publications` 核验完整论文集的 1,918 个注册出版 DOI,并单独关联节目分轨、展示上下文和摘要。1,743 份节目摘要明确标注来源(其中 26 份来自已复核的标题排版对应),166 项标题/作者版本差异保留为待核;所有节目及未匹配项均保留。注册文章类型不等于研究类型,输出尚需数据库身份/历史审查。见 [MM 2026 出版条目采集与恢复](docs/mm2026-publications.md)。
|
||||
|
||||
ECCV 2026 已归档 Springer 目录和章节可通过 [正式出版采集流程](docs/eccv2026-publications.md)整理为带 DOI 和可复核证据的 JSONL。
|
||||
|
||||
@@ -204,5 +204,3 @@ IJCAI 联办届次的逐条后续核查见 [2018/2022 分区与目录差集](ijc
|
||||
- [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。
|
||||
|
||||
- [ECCV 2026 出版目录与节目单对账](eccv2026-publisher-crosswalk-2026-11-18.md)记录 Springer 78 卷的 DOI、节目单差异及 PostgreSQL 只读绑定核查。
|
||||
|
||||
@@ -0,0 +1,35 @@
|
||||
# 2020 起补漏状态:2026-11-18
|
||||
|
||||
总体仍为 **13/17,第 14 步未完成**。主动补漏从 2020 年起,2000–2019 年已发现线索仍保留,43 个早期历史缺口仍为延期,没有据此算作补齐。更早状态页保留为历史快照。
|
||||
|
||||
## 当前生产结果
|
||||
|
||||
ISMIR 两批累计31项已关联到现有论文,新增论文实体为0。第二批新增来源记录、独立投稿、录用观察各21条及173条来源标签证据;两批累计267条标签证据。覆盖 `partial31/140`,109项仍待核验。详见[来源说明](../ismir2026-program.md)、[首批验收](ismir2026-import10-2026-11-18.json)和[第二批逐条验收](ismir2026-import21-2026-11-18.json)。
|
||||
|
||||
最新精确计数:论文实体 **3,568,022**,来源记录 **3,815,534**,投稿 **532,223**,决定来源观察 **571,775**。实体数量不是已经完成最终科学工作去重的数量;同一次投稿可能有多条决定来源观察。
|
||||
|
||||
paper `2757497` 保留 ICLR2026 一次拒稿投稿下的两条来源观察,并新增 ISMIR2026 录用投稿;实际 CLI 查询显示已知录用,旧拒稿历史仍可查询。不将两条来源观察计作两次拒稿,也不将来源采集时间当作决定时间。
|
||||
|
||||
## 固定范围存在性盘点
|
||||
|
||||
只读快照 `2026-11-18 06:46:44.099675+00`,范围仍为 43 会、278 个目标年度槽位:**274 个至少有一条投稿,4 个完全为空**,均为 2026 年的 **CIKM、ECCV、ICDM、IROS**。首批ISMIR使空槽从5降至4;第二批只增加同届来源覆盖,空槽数不变。
|
||||
|
||||
这只统计“该年度至少有数据”,不是逐篇、逐 track、摘要或公开拒稿覆盖完整。2020–2025 没有整年空槽,仍有来源完整性和公开负面历史缺口。
|
||||
|
||||
|证据(相对服务器 `/data/paper-index/`)|SHA256|
|
||||
|---|---|
|
||||
|`collected/active-scope-census-20261118-v22/summary.json`|`ee4ec2e6d6eaed55ce3475e735bfba9bd94e512893cd3c3024035b48b744f475`|
|
||||
|`collected/active-scope-census-20261118-v22/snapshot.json`|`5aabc91217ad787946ba50d6a670296b1e3152a54f5ecaa0e3a9b3a952b63fa7`|
|
||||
|`validation/active-scope-fixed278-v1.json`|`a835bef5b9c3a0f76069d840cecdb9a6bcf65d3a38796d70dbfdfd4b49242264`|
|
||||
|
||||
本机使用固定分母、会议别名和逐 edition 快照独立重算 274/278;没有使用 `max(id)` 代替计数。
|
||||
|
||||
## 尚待完成
|
||||
|
||||
- ISMIR 仍有109项;62项无精确标题候选不等于新作品,6项作者部分匹配仍待审查。31项摘要逐字一致候选已分两批审查并消费;其余候选不能仅凭标题、作者或摘要检索结果算作已批准。
|
||||
- MM 已验收572项来源观察,注册清单1918项中仍有1346项待处理。已有134个暂建索引实体仍须后续身份审计;H2AL 来源及轨道纠正、版本化来源覆盖方案尚未用于生产,不能把不同版本轨道预期数相加当完整分母。
|
||||
- ECCV 的初步节目、ICDM 的研究/应用来源和缺失摘要仍需作品及出版核查;CIKM 缺实际逐篇目录;IROS 官方访问403仍保留限制,不重试绕过。各来源的采集、批准和导入状态必须分开。
|
||||
- 公开 rejected、desk-rejected、withdrawn 继续按会议、年份、track核查。ISMIR 的101组自愿公开评审来自录用节目,不是101条拒稿;UAI accepted-only 镜像与 EMNLP/NeurIPS 原始接口403均不能关闭拒稿缺口。近期镜像差集核查见 [PR #72](https://gitea.entroia.com/Zayden-Jung/paper-atlas/pulls/72)。
|
||||
- 后续仍需完成跨会作品与历史、独立类型和标签关系(第15步);全部导入结束后的全库去重、标识冲突、近似标题作者、摘要/约束/查询及覆盖审计(第16步);长期运行与恢复文档最终整理(第17步)。
|
||||
|
||||
已消费输入不得重放。下次从[ISMIR 当前增量父状态和恢复说明](../ismir2026-program.md)及 `work-state.json` 的本批已接受回执继续;保留旧 SQLite 只读备份,不因查询超时重新执行导入。
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,20 +0,0 @@
|
||||
# ECCV 2026 出版目录与节目单对账
|
||||
|
||||
2026-11-18 核验了 Springer LNCS 17001–17078 的全部 78 卷。会议索引显示 **2,835 条**,逐卷目录合计也有 **2,835 条带 DOI 的章节**,另有 156 项卷首或卷末资料。出版方卷册简介及大会节目单均为 **2,834 条**。两个来源仍有逐条差异,汇总数量相差一条的原因待核。逐卷数字、目录页哈希和只读数据库回执见[机器可读清单](eccv2026-publisher-crosswalk-2026-11-18.json)。[Springer 会议索引](https://link.springer.com/conference/eccv) · [第一卷](https://link.springer.com/book/10.1007/978-3-032-36984-0) · [大会节目单](https://eccv.ecva.net/Conferences/2026/AcceptedPapers)
|
||||
|
||||
## 逐篇对账
|
||||
|
||||
|核对对象|唯一标题且完整作者顺序一致|唯一标题且目录所显示作者顺序一致|标题对得上、作者有差异|标题待核|
|
||||
|---|---:|---:|---:|---:|
|
||||
|全部 2,834 条节目记录|1,332|709|535|258|
|
||||
|首批已入库的 30 条节目记录|23|3|4|0|
|
||||
|本次只读核验通过的 248 条既有论文候选|173|72|2|1|
|
||||
|20 篇有既往拒稿、桌拒或撤回的优先论文|12|7|1|0|
|
||||
|
||||
目录作者栏有时只显示前六人。作者差异包括缩写、姓名文字变化与排列变化。原始名单、顺序和来源保留,前缀匹配与作者差异需查章节作者页。节目单与出版目录的摘要、分轨及公开负面决定覆盖仍待分别核查。
|
||||
|
||||
## 当前库核对
|
||||
|
||||
只读核对了全部 2,835 个出版 DOI,68 个已有论文绑定。对账后另检查 271 个已知论文关联,涵盖 245 个本次候选和 26 个已入库节目记录。其中 14 个 DOI 已指向同一论文,257 个 DOI 尚未绑定。245 个候选内有 10 篇带既往负面决定。
|
||||
|
||||
下一批准备以出版 DOI、正式分轨和完整作者证据复核关联。首批 30 条节目记录保留原投稿、决定和来源。确认同届同一投稿后,再补充出版证据,避免重复创建 ECCV 投稿。本次核查未写入数据库。
|
||||
@@ -0,0 +1,247 @@
|
||||
{
|
||||
"as_of": "2026-11-18",
|
||||
"goal_progress": "13/17; stage14 incomplete",
|
||||
"source": "ismir_program",
|
||||
"scope": "First10 reviewed existing-work source links, partial10/140, not public-rejection completeness or final deduplication",
|
||||
"database_acceptance": {
|
||||
"status": "passed",
|
||||
"at": "2026-11-18 05:15:27.565655+00:00",
|
||||
"writer_commit": "12f95cff91813a2143bc8fab5bc3e89df1bd0fdb",
|
||||
"before_counts": {
|
||||
"papers": {
|
||||
"rows": 3568022,
|
||||
"max_id": 3568595
|
||||
},
|
||||
"source_records": {
|
||||
"rows": 3815503,
|
||||
"max_id": 3815504
|
||||
},
|
||||
"submissions": {
|
||||
"rows": 532192,
|
||||
"max_id": 532193
|
||||
},
|
||||
"decisions": {
|
||||
"rows": 571744,
|
||||
"max_id": 571744
|
||||
}
|
||||
},
|
||||
"after_counts": {
|
||||
"papers": {
|
||||
"rows": 3568022,
|
||||
"max_id": 3568595
|
||||
},
|
||||
"source_records": {
|
||||
"rows": 3815513,
|
||||
"max_id": 3815514
|
||||
},
|
||||
"submissions": {
|
||||
"rows": 532202,
|
||||
"max_id": 532203
|
||||
},
|
||||
"decisions": {
|
||||
"rows": 571754,
|
||||
"max_id": 571754
|
||||
}
|
||||
},
|
||||
"new_papers": 0,
|
||||
"new_sources": 1,
|
||||
"new_editions": 1,
|
||||
"new_source_records": 10,
|
||||
"new_attempts": 10,
|
||||
"new_decisions": 10,
|
||||
"source_id": 123160,
|
||||
"source_tag_evidence_links": 94,
|
||||
"protected_papers": 6394,
|
||||
"all_protected_old_profiles_sources_tags_identifiers_preserved": true,
|
||||
"source_observations": 10,
|
||||
"source_expected": 140,
|
||||
"source_remaining": 130,
|
||||
"coverage": "partial",
|
||||
"foundry_readyz": [
|
||||
200
|
||||
],
|
||||
"sqlite_frozen": true,
|
||||
"imported": [
|
||||
{
|
||||
"external_id": "2026/3",
|
||||
"paper_id": 2813483,
|
||||
"record_id": 3815505,
|
||||
"submission_id": 532194,
|
||||
"decision_id": 571745,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/12",
|
||||
"paper_id": 2785459,
|
||||
"record_id": 3815506,
|
||||
"submission_id": 532195,
|
||||
"decision_id": 571746,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/35",
|
||||
"paper_id": 2757859,
|
||||
"record_id": 3815507,
|
||||
"submission_id": 532196,
|
||||
"decision_id": 571747,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/51",
|
||||
"paper_id": 2752643,
|
||||
"record_id": 3815508,
|
||||
"submission_id": 532197,
|
||||
"decision_id": 571748,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/74",
|
||||
"paper_id": 2762340,
|
||||
"record_id": 3815509,
|
||||
"submission_id": 532198,
|
||||
"decision_id": 571749,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/75",
|
||||
"paper_id": 2757480,
|
||||
"record_id": 3815510,
|
||||
"submission_id": 532199,
|
||||
"decision_id": 571750,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/78",
|
||||
"paper_id": 2768260,
|
||||
"record_id": 3815511,
|
||||
"submission_id": 532200,
|
||||
"decision_id": 571751,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/84",
|
||||
"paper_id": 2740614,
|
||||
"record_id": 3815512,
|
||||
"submission_id": 532201,
|
||||
"decision_id": 571752,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/87",
|
||||
"paper_id": 2752271,
|
||||
"record_id": 3815513,
|
||||
"submission_id": 532202,
|
||||
"decision_id": 571753,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/363",
|
||||
"paper_id": 2757497,
|
||||
"record_id": 3815514,
|
||||
"submission_id": 532203,
|
||||
"decision_id": 571754,
|
||||
"edition_id": 104044
|
||||
}
|
||||
]
|
||||
},
|
||||
"history_protection": {
|
||||
"submissions": {
|
||||
"rows": 532192,
|
||||
"sha256": "34e2fe27cccf89e6e80228318212a846369fdd315c4cfe67d7d535013eac8298"
|
||||
},
|
||||
"decisions": {
|
||||
"rows": 571744,
|
||||
"sha256": "efbda4e91950c5c7298f536bc5967f7fee57d8b20a7843e00dc69871b1553bd1"
|
||||
},
|
||||
"decision_sources": {
|
||||
"rows": 571744,
|
||||
"sha256": "1d8899b16b40e9f37ac84dc601efc3e7906af5c06bca49946100697f22c96174"
|
||||
},
|
||||
"submission_sources": {
|
||||
"rows": 581976,
|
||||
"sha256": "ab3ab200c4abbfef39bc5a2a757550191441c703ae505372d38d9afa9a4daf65"
|
||||
},
|
||||
"submission_identifiers": {
|
||||
"rows": 383956,
|
||||
"sha256": "0e8f514e186e08bd00a65f8e14fc7f63db6add76722271e0111e14f5d27b9dbe"
|
||||
}
|
||||
},
|
||||
"evidence": {
|
||||
"accepted_report": "/data/paper-index/collected/ismir2026-import10-v1/postgresql-postcheck-v1.json",
|
||||
"accepted_report_sha256": "8a08015bbd725b400de53477837e850ca92a50479d7f86f2cfed56d50bb22577",
|
||||
"baseline": "/data/paper-index/collected/ismir2026-baseline10-v1/baseline.json",
|
||||
"baseline_sha256": "a0b5b8c2c21ee567cf80152b16f66643309bbe33ee9cd67d19da33d6b6337656",
|
||||
"baseline_archive_sha256": "eb94f99cb53c9a30f63d34ea11b23c11759e45b571b7efce2dcbe8cb4fe52fb8",
|
||||
"preparation_sha256": "0d9fad74640ab57fc8bea8aaf72ba07202a40b174d05253db7348b14455a0462",
|
||||
"acceptance_archive": "/data/paper-index/validation/ismir2026-import10-acceptance-recovery-v1.tar.gz",
|
||||
"acceptance_archive_sha256": "138e1fb986f5aa6a42794eed982fdc91ae994b8be82f8bf25360db2f7ba6c70c",
|
||||
"fresh_packets_sha256": "88e423aede0ea83b9f736891c09b12d0cb24f2f8b70508e4863cd07760de5e0d",
|
||||
"local_acceptance_check_sha256": "42d31337c76b96f93505011db7c797123b67ce2eec7defd0175ea0e9c1df2089",
|
||||
"census_summary_sha256": "2157035b72d351e2fe91f2bc0c6ebb305f91d95f8772ab9a088076ce4b86e1c2"
|
||||
},
|
||||
"native_query_example": {
|
||||
"paper_id": 2757497,
|
||||
"publication_outcome": "accepted",
|
||||
"prior_venue": "ICLR",
|
||||
"prior_year": 2026,
|
||||
"prior_submission_id": 131721,
|
||||
"prior_negative_attempts": 1,
|
||||
"prior_negative_observations": 2,
|
||||
"prior_decision_ids": [
|
||||
133086,
|
||||
538172
|
||||
],
|
||||
"later_observed_venue": "ISMIR",
|
||||
"later_observed_year": 2026,
|
||||
"original_ismir_signed_decision_verified": false,
|
||||
"ismir_decision_date": null,
|
||||
"observation_time_is_not_decision_time": true
|
||||
},
|
||||
"presence_census": {
|
||||
"snapshot_at": "2026-11-18 05:20:48.641315+00",
|
||||
"scope": "Fixed278 venue-year presence only, not paper/track/abstract/public-negative completeness or final deduplication. Legacy43 gaps deferred, not filled.",
|
||||
"target_venues": 43,
|
||||
"expected_slots": 278,
|
||||
"populated_slots": 274,
|
||||
"missing_slots": 4,
|
||||
"missing": [
|
||||
{
|
||||
"venue": "CIKM",
|
||||
"year": 2026
|
||||
},
|
||||
{
|
||||
"venue": "ECCV",
|
||||
"year": 2026
|
||||
},
|
||||
{
|
||||
"venue": "ICDM",
|
||||
"year": 2026
|
||||
},
|
||||
{
|
||||
"venue": "IROS",
|
||||
"year": 2026
|
||||
}
|
||||
],
|
||||
"delta_from_v20": {
|
||||
"newly_present": [
|
||||
{
|
||||
"venue": "ISMIR",
|
||||
"year": 2026
|
||||
}
|
||||
],
|
||||
"previous_missing": 5,
|
||||
"current_missing": 4
|
||||
},
|
||||
"snapshot_sha256": "c14bab883c5fcab33b450fcf240dec7225f2f17bc04c3e728b5583657b4ad23b",
|
||||
"fixed_scope_sha256": "a835bef5b9c3a0f76069d840cecdb9a6bcf65d3a38796d70dbfdfd4b49242264",
|
||||
"accepted_import_sha256": "8a08015bbd725b400de53477837e850ca92a50479d7f86f2cfed56d50bb22577",
|
||||
"database_written": false
|
||||
},
|
||||
"consumed_queue": "/data/paper-index/collected/ismir2026-prepared10-v1: NEVER REPLAY",
|
||||
"next": [
|
||||
"Review130 remaining source observations, including31 total verbatim-abstract candidates of which10 consumed; do not count a title/author screen as identity approval.",
|
||||
"Fresh incremental parent must be partial10/140; old preparation0/140 is consumed.",
|
||||
"Continue all venue/year/track public negative availability and formal source coverage.",
|
||||
"Finish cross-venue identities/types, then final whole-DB dedup/identifier/abstract/constraints/query audit after imports."
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,330 @@
|
||||
{
|
||||
"as_of": "2026-11-18",
|
||||
"goal_progress": "13/17; stage14 incomplete",
|
||||
"source": "ismir_program",
|
||||
"scope": "21 additional reviewed existing-work source links; cumulativepartial31/140, not public-rejection completeness or final deduplication",
|
||||
"database_acceptance": {
|
||||
"status": "passed",
|
||||
"at": "2026-11-18 06:38:55.148539+00:00",
|
||||
"writer_commit": "3754545003e1f96b88c6533cc3a69dc557f07305",
|
||||
"before_counts": {
|
||||
"papers": {
|
||||
"rows": 3568022,
|
||||
"max_id": 3568595
|
||||
},
|
||||
"source_records": {
|
||||
"rows": 3815513,
|
||||
"max_id": 3815514
|
||||
},
|
||||
"submissions": {
|
||||
"rows": 532202,
|
||||
"max_id": 532203
|
||||
},
|
||||
"decisions": {
|
||||
"rows": 571754,
|
||||
"max_id": 571754
|
||||
}
|
||||
},
|
||||
"after_counts": {
|
||||
"papers": {
|
||||
"rows": 3568022,
|
||||
"max_id": 3568595
|
||||
},
|
||||
"source_records": {
|
||||
"rows": 3815534,
|
||||
"max_id": 3815535
|
||||
},
|
||||
"submissions": {
|
||||
"rows": 532223,
|
||||
"max_id": 532224
|
||||
},
|
||||
"decisions": {
|
||||
"rows": 571775,
|
||||
"max_id": 571775
|
||||
}
|
||||
},
|
||||
"new_papers": 0,
|
||||
"new_sources": 0,
|
||||
"new_editions": 0,
|
||||
"new_source_records": 21,
|
||||
"new_attempts": 21,
|
||||
"new_decisions": 21,
|
||||
"source_id": 123160,
|
||||
"source_tag_evidence_links": 173,
|
||||
"protected_papers": 6415,
|
||||
"all_protected_old_profiles_sources_tags_identifiers_preserved": true,
|
||||
"source_observations": 31,
|
||||
"source_expected": 140,
|
||||
"source_remaining": 109,
|
||||
"coverage": "partial",
|
||||
"foundry_readyz": [
|
||||
200
|
||||
],
|
||||
"sqlite_frozen": true,
|
||||
"imported": [
|
||||
{
|
||||
"external_id": "2026/148",
|
||||
"paper_id": 2755057,
|
||||
"record_id": 3815515,
|
||||
"submission_id": 532204,
|
||||
"decision_id": 571755,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/184",
|
||||
"paper_id": 2752723,
|
||||
"record_id": 3815516,
|
||||
"submission_id": 532205,
|
||||
"decision_id": 571756,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/196",
|
||||
"paper_id": 2784571,
|
||||
"record_id": 3815517,
|
||||
"submission_id": 532206,
|
||||
"decision_id": 571757,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/240",
|
||||
"paper_id": 2738896,
|
||||
"record_id": 3815518,
|
||||
"submission_id": 532207,
|
||||
"decision_id": 571758,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/251",
|
||||
"paper_id": 2753889,
|
||||
"record_id": 3815519,
|
||||
"submission_id": 532208,
|
||||
"decision_id": 571759,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/258",
|
||||
"paper_id": 2662030,
|
||||
"record_id": 3815520,
|
||||
"submission_id": 532209,
|
||||
"decision_id": 571760,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/270",
|
||||
"paper_id": 2769109,
|
||||
"record_id": 3815521,
|
||||
"submission_id": 532210,
|
||||
"decision_id": 571761,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/298",
|
||||
"paper_id": 2752114,
|
||||
"record_id": 3815522,
|
||||
"submission_id": 532211,
|
||||
"decision_id": 571762,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/317",
|
||||
"paper_id": 2765378,
|
||||
"record_id": 3815523,
|
||||
"submission_id": 532212,
|
||||
"decision_id": 571763,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/318",
|
||||
"paper_id": 2764935,
|
||||
"record_id": 3815524,
|
||||
"submission_id": 532213,
|
||||
"decision_id": 571764,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/342",
|
||||
"paper_id": 2738585,
|
||||
"record_id": 3815525,
|
||||
"submission_id": 532214,
|
||||
"decision_id": 571765,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/370",
|
||||
"paper_id": 2830871,
|
||||
"record_id": 3815526,
|
||||
"submission_id": 532215,
|
||||
"decision_id": 571766,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/371",
|
||||
"paper_id": 2858445,
|
||||
"record_id": 3815527,
|
||||
"submission_id": 532216,
|
||||
"decision_id": 571767,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/373",
|
||||
"paper_id": 2820562,
|
||||
"record_id": 3815528,
|
||||
"submission_id": 532217,
|
||||
"decision_id": 571768,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/409",
|
||||
"paper_id": 2522863,
|
||||
"record_id": 3815529,
|
||||
"submission_id": 532218,
|
||||
"decision_id": 571769,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/418",
|
||||
"paper_id": 2750749,
|
||||
"record_id": 3815530,
|
||||
"submission_id": 532219,
|
||||
"decision_id": 571770,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/468",
|
||||
"paper_id": 2846824,
|
||||
"record_id": 3815531,
|
||||
"submission_id": 532220,
|
||||
"decision_id": 571771,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/518",
|
||||
"paper_id": 2761686,
|
||||
"record_id": 3815532,
|
||||
"submission_id": 532221,
|
||||
"decision_id": 571772,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/524",
|
||||
"paper_id": 2784543,
|
||||
"record_id": 3815533,
|
||||
"submission_id": 532222,
|
||||
"decision_id": 571773,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/539",
|
||||
"paper_id": 2761760,
|
||||
"record_id": 3815534,
|
||||
"submission_id": 532223,
|
||||
"decision_id": 571774,
|
||||
"edition_id": 104044
|
||||
},
|
||||
{
|
||||
"external_id": "2026/552",
|
||||
"paper_id": 2758575,
|
||||
"record_id": 3815535,
|
||||
"submission_id": 532224,
|
||||
"decision_id": 571775,
|
||||
"edition_id": 104044
|
||||
}
|
||||
]
|
||||
},
|
||||
"history_protection": {
|
||||
"submissions": {
|
||||
"rows": 532202,
|
||||
"sha256": "9d41955c80fc91dae4f65d65e0f69198ce2d79508ceebfe943bdc19825983df8"
|
||||
},
|
||||
"decisions": {
|
||||
"rows": 571754,
|
||||
"sha256": "c8dc762d089d1656ee1308dacec9109605e1a4be7e5fcfa8f95013e77a0cb55c"
|
||||
},
|
||||
"decision_sources": {
|
||||
"rows": 571754,
|
||||
"sha256": "231f15b4c70435977d6ab784112ff5c748541eeb4d54c28bb861f8835f1eba10"
|
||||
},
|
||||
"submission_sources": {
|
||||
"rows": 581986,
|
||||
"sha256": "b9d8c39e945df340daf1c695a6359cfb549b8bd2f391cb139dabba2c16afa242"
|
||||
},
|
||||
"submission_identifiers": {
|
||||
"rows": 383956,
|
||||
"sha256": "0e8f514e186e08bd00a65f8e14fc7f63db6add76722271e0111e14f5d27b9dbe"
|
||||
}
|
||||
},
|
||||
"evidence": {
|
||||
"parent_acceptance_sha256": "8a08015bbd725b400de53477837e850ca92a50479d7f86f2cfed56d50bb22577",
|
||||
"accepted_report": "/data/paper-index/collected/ismir2026-import21-v1/postgresql-postcheck-v1.json",
|
||||
"accepted_report_sha256": "153ef13dbac9f4243c81bdd2a16d3ade74372d3e45ca5e84acc2b7258bca7bfc",
|
||||
"baseline": "/data/paper-index/collected/ismir2026-baseline21-v1/baseline.json",
|
||||
"baseline_sha256": "204b571b47e164d68930158c2578f609814969940628d421a2b64c3a6ce1b018",
|
||||
"baseline_archive_sha256": "ecac32e1d3890786a5670ff06f88fa7bd92155306cf8133f3164de0cb9f48e6b",
|
||||
"preparation_sha256": "6781edfaa67798d76329fb5c7948d83693607c96352a38eccce0067faa95deaa",
|
||||
"acceptance_archive": "/data/paper-index/validation/ismir2026-import21-acceptance-recovery-v1.tar.gz",
|
||||
"acceptance_archive_sha256": "55e1cc8301548ff0abc195add5f40d7082a06e4f087f6da5838ffd2f6b33339c",
|
||||
"fresh_packets_sha256": "79e0e8187a522478c443d036fdbf2f8d5e6a22c949d46fb0592a664ec1bc22fe",
|
||||
"local_acceptance_check_sha256": "04f4ec6969a71655d70f446347646f63efc56e5a5a8e974b931703482e5e7ceb",
|
||||
"census_summary_sha256": "ee4ec2e6d6eaed55ce3475e735bfba9bd94e512893cd3c3024035b48b744f475",
|
||||
"ci_run": 1257,
|
||||
"ci_tests": 556,
|
||||
"ci_proof_sha256": "5ad08aa907caec5a1ca63df5e7345db4802dab4e3a91293a0303bf481a903ff8"
|
||||
},
|
||||
"consumed_queue": "/data/paper-index/collected/ismir2026-prepared21-v2: NEVER REPLAY",
|
||||
"previous_consumed_queue": "/data/paper-index/collected/ismir2026-prepared10-v1: NEVER REPLAY",
|
||||
"query_example_rechecked": {
|
||||
"paper_id": 2757497,
|
||||
"publication_outcome": "accepted",
|
||||
"rejected_attempts": 1,
|
||||
"rejection_source_observations": 2,
|
||||
"distinct_ismir_accepted_attempts": 1,
|
||||
"original_ismir_signed_decision_verified": false,
|
||||
"ismir_decision_date": null
|
||||
},
|
||||
"new_batch_prior_negative_attempts": 0,
|
||||
"new_batch_prior_negative_observations": 0,
|
||||
"source_tag_links_cumulative": 267,
|
||||
"presence_census": {
|
||||
"snapshot_at": "2026-11-18 06:46:44.099675+00",
|
||||
"scope": "Fixed278 venue-year presence only, not paper/track/abstract/public-negative completeness or final deduplication. Legacy43 gaps deferred, not filled.",
|
||||
"target_venues": 43,
|
||||
"expected_slots": 278,
|
||||
"populated_slots": 274,
|
||||
"missing_slots": 4,
|
||||
"missing": [
|
||||
{
|
||||
"venue": "CIKM",
|
||||
"year": 2026
|
||||
},
|
||||
{
|
||||
"venue": "ECCV",
|
||||
"year": 2026
|
||||
},
|
||||
{
|
||||
"venue": "ICDM",
|
||||
"year": 2026
|
||||
},
|
||||
{
|
||||
"venue": "IROS",
|
||||
"year": 2026
|
||||
}
|
||||
],
|
||||
"delta_from_v21": {
|
||||
"newly_present": [],
|
||||
"previous_missing": 4,
|
||||
"current_missing": 4,
|
||||
"ISMIR_source_observations": 31
|
||||
},
|
||||
"snapshot_sha256": "5aabc91217ad787946ba50d6a670296b1e3152a54f5ecaa0e3a9b3a952b63fa7",
|
||||
"fixed_scope_sha256": "a835bef5b9c3a0f76069d840cecdb9a6bcf65d3a38796d70dbfdfd4b49242264",
|
||||
"accepted_import_sha256": "153ef13dbac9f4243c81bdd2a16d3ade74372d3e45ca5e84acc2b7258bca7bfc",
|
||||
"database_written": false
|
||||
},
|
||||
"next": [
|
||||
"Remaining109 observations require review;31 exact-source-abstract candidates are now consumed, not reusable queues.",
|
||||
"Future increments require a fresh partial31/140 parent and new preservation baseline.",
|
||||
"Keep raw authors/title/abstract/keyword versions; no numeric miniconf-to-OpenReview-ID assumption, global person aliases or inferred research types.",
|
||||
"Continue all43 venue/year/track formal-source and public-negative availability audits, then final whole-DB dedup after imports."
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,16 @@
|
||||
# ECCV 2026 正式出版章节采集
|
||||
|
||||
`collect eccv2026-publications` 读取已归档的 Springer LNCS 17001–17078 目录及所选章节的公开 HTML,输出可复核的 Paper Atlas 记录。目录覆盖 2,835 个章节 DOI。会议节目单与出版方卷册简介均为 2,834 条,逐条差异仍待核。Workshop 论文集另行处理。
|
||||
|
||||
```sh
|
||||
paper-atlas collect eccv2026-publications \
|
||||
--toc-snapshots /data/paper-index/collected/eccv2026-springer-toc-v1 \
|
||||
--chapter-snapshots /data/paper-index/validation/eccv-verified-chapter-pages \
|
||||
--out /data/paper-index/collected/eccv-publisher-metadata
|
||||
```
|
||||
|
||||
目录归档含 `receipts.jsonl`、`volume-checkpoint.json`、`summary.json` 及 156 页 HTML。摘要在章节详情页读取,章节归档沿用 `springer-selected` 的 `receipts.json` 格式。两类归档都按响应大小和 SHA-256 校验。目录卷号、分页、章节 DOI 归属、标题及 2026 年出处需要一致。已有输出目录需另查回执或换新空目录后运行。
|
||||
|
||||
输出含规范化 JSONL、manifest、采集回执以及所选章节的内容寻址存证。每条保留出版 DOI、卷号、页码、按顺序的完整作者及公开摘要。目录证据用 URL 和哈希连接到输入归档,保存归档以便复核。主会出版观察依据 Springer 正式论文集,原始投稿号、决定日期及签名仍未知。工具仅处理已归档的公开 HTML。
|
||||
|
||||
生成的文件待做论文身份复核后方可导入。准备生产批次时核实每个 DOI 与现有 arXiv 标识的绑定,保持两者的来源证据。对已存在的同届节目投稿需先核对投稿身份及轨道,再附加出版来源,避免因直接导入创建重复投稿。具有 ICLR 等既往决定的论文须保留原记录。新的增量导入 manifest 需以当前实际来源覆盖为父版本,留存待核差集和独立验收回执。
|
||||
@@ -48,3 +48,36 @@ paper-atlas collect ismir2026-program \
|
||||
正式名单与政策恢复包:同目录 `remaining2026-listings-research-v2-recovery.tar.gz`,SHA256 为 `f5ef7c2e73d46712146e4d6711ad5ad562e16b8b55c0cd75d1041cd0b81142cb`。安全恢复三个源目录、核验文件后可重跑上述命令。
|
||||
|
||||
完整来源和独立 140 项清单在测试夹具中冻结。测试、构建、打包、安装及实际隔离目录 CLI 验证只在用户指定 `ces-control:host` runner 执行。生产规范化后还需独立核验全部记录,并用 PostgreSQL 只读预检检查候选作品和既往投稿;不自动合并来源差异或人物身份。
|
||||
|
||||
## 2026-11-18:首批 10 条验收(历史阶段)
|
||||
|
||||
本段保留首批历史状态;当前累计结果和增量父状态见下方最新验收段。
|
||||
|
||||
首批 10 项已逐篇核查研究内容,并通过当前数据库实体、作者、摘要及完整历史的只读复核,随后使用已通过远程 CI 的包内 `import records` 导入。新增论文实体 **0**,新增来源记录、投稿、录用观察各 **10**,来源标签证据 **94** 条;规范标题、作者、摘要及旧历史保留。原始来源摘要另存,不覆盖规范摘要。覆盖为 `partial10/140`,还有 **130** 项待核验。数值节目 ID 仍只作为节目定位符,未冒充 OpenReview 投稿 ID,未新增全局人名别名或推断研究类型。
|
||||
|
||||
[逐条验收与恢复记录](coverage/ismir2026-import10-2026-11-18.json)包含生产行 ID、保护基线、归档及证据哈希。服务器基线保护此前 6,384 篇与本批 10 篇的并集 **6,394** 篇,全库旧投稿、决定及来源关系哈希未变;独立新快照的 10 个完整实体包、来源字段、标签和标识也逐项核验。Foundry `/readyz` 返回200,17,987,751,936字节的 SQLite 备份保持只读。该验收不是最终全库科学工作去重。
|
||||
|
||||
例如 paper `2757497`(Learning Music Style for Piano Arrangement Through Cross-Modal Bootstrapping)保留一次 ICLR2026 拒稿投稿和两条拒稿来源观察,并新增独立 ISMIR2026 录用投稿。实际执行以下查询,返回 `publication_outcome=accepted`,同时保留原拒稿历史:
|
||||
|
||||
```sh
|
||||
paper-atlas query --pg-service foundry-research --pg-schema research \
|
||||
--paper 2757497 --outcome accepted
|
||||
```
|
||||
|
||||
ISMIR 的 accepted 来自正式名单和节目,尚无原始签名决定或具体决定日期;不能把采集时间当作决定时间。决定的规范时间使用包内既有毫秒格式,来源回执的原始微秒时间仍保留于元数据。
|
||||
|
||||
**禁止重放** `/data/paper-index/collected/ismir2026-prepared10-v1` 的文件。导入单元 `paper-atlas-ismir2026-import10-v1.service`、invocation `538ce9c9324a4f59b5bb49d3094d5265` 已成功结束;该阶段建立了 `partial10/140` 父状态;后续累计结果见下方最新段,不得沿用已消费的 `0/140` 父状态。保护基线恢复包为 `/data/paper-index/validation/ismir2026-baseline10-recovery-v1.tar.gz`,验收恢复包为 `/data/paper-index/validation/ismir2026-import10-acceptance-recovery-v1.tar.gz`;本机 paper-index 工作目录有同名副本及独立检查记录。
|
||||
|
||||
## 2026-11-18:新增 21 条,累计 31/140
|
||||
|
||||
第二批21项已通过逐篇研究内容审查、新鲜只读父状态检查、保护基线及独立入库验收。新增论文实体、来源和edition均为0;新增来源记录、投稿、录用观察各21条,新增173条来源标签证据。累计31条录用来源观察、267条标签证据,覆盖仍为 `partial31/140`,**109项待核验**。三十一项摘要都保留在原始来源记录中,既有规范资料没有被覆盖。
|
||||
|
||||
本批明确保留不同研究工作,例如UOT-IR音乐压缩与SymphonyGen交响生成,以及AI混合音轨占比回归与BAMM真实广播检测;不因作者或主题相近合并。源关键词和展示方式继续使用各自namespace,没有推断全局人名别名、原始OpenReview投稿ID或研究类型。
|
||||
|
||||
[第二批逐条验收及恢复记录](coverage/ismir2026-import21-2026-11-18.json)包含21组生产行ID、源码提交、全部证据哈希和新计数。保护并核验了6,415篇作品的规范资料、旧来源与标签,以及所有旧全局投稿/决定/来源关系指纹;新快照另导出21个完整实体包逐字段核验。首批10项保留;paper2757497的实际查询仍显示accepted及原ICLR一次拒稿下的两条来源观察。
|
||||
|
||||
本批使用固定源码 `3754545003e1f96b88c6533cc3a69dc557f07305`,已在远程 `ces-control` CI1257通过556项测试,含真实PostgreSQL只读增量门禁回归。该修复解决预检对Mapping行对象切片的错误,未弱化覆盖校验;旧的只读准备v1失败时没有写库,修复后v2重新检查通过。默认运行时未因本批操作切换。
|
||||
|
||||
**禁止重放** `/data/paper-index/collected/ismir2026-prepared21-v2`。服务 `paper-atlas-ismir2026-import21-v1.service`、invocation `78077b901a274426bb161ef8d69963ad` 已成功结束。新批次必须从当前 `partial31/140` 准备,不能再用 `10/140` 或 `0/140`。保护基线恢复包为 `/data/paper-index/validation/ismir2026-baseline21-recovery-v1.tar.gz`,验收恢复包为 `/data/paper-index/validation/ismir2026-import21-acceptance-recovery-v1.tar.gz`;本机paper-index目录有同名副本与独立检查结果。
|
||||
|
||||
新的固定范围盘点仍为274/278个年度有数据;本批提高ISMIR来源覆盖,没有填补其他空年度,也没有关闭公开拒稿或最终全库去重任务。Foundry就绪检查200,SQLite备份继续只读。
|
||||
|
||||
@@ -27,6 +27,7 @@ COMMANDS = {
|
||||
('collect','ismir2026-program'): ('paper_atlas.collectors.ismir2026', {}, '核验 ISMIR 2026 公开节目与录用名单并保留原始摘要、来源差异和自愿公开评审'),
|
||||
('collect','icaps2026-registry'): ('paper_atlas.collectors.icaps_registry2026', {}, '核验 ICAPS 2026 Crossref 注册元数据并保留独立版本'),
|
||||
('collect','eccv2026-program'): ('paper_atlas.collectors.eccv2026', {}, '核验ECCV2026暂定节目并断点采集公开元数据'),
|
||||
('collect','eccv2026-publications'): ('paper_atlas.collectors.eccv2026_publications', {}, '核验ECCV2026 Springer 正式出版章节'),
|
||||
('collect','icassp2026-registry'): ('paper_atlas.collectors.icassp2026', {}, '核验 ICASSP 2026 冻结注册论文元数据'),
|
||||
('collect','icdm2026-program'): ('paper_atlas.collectors.icdm2026', {}, '核验 ICDM2026 冻结日程及明确的研究/应用轨道'),
|
||||
('collect','sdm2026-proceedings'): ('paper_atlas.collectors.sdm2026', {}, '核验 SDM 2026 注册论文并单独保留公开日程版本'),
|
||||
|
||||
@@ -0,0 +1,184 @@
|
||||
"""Normalize frozen ECCV 2026 Springer proceedings and preserve publisher evidence."""
|
||||
import argparse
|
||||
import fcntl
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import re
|
||||
import tempfile
|
||||
|
||||
from paper_atlas.io.html import Document, clean
|
||||
from paper_atlas.io.springer import parse_chapter, read_page, snapshot_index
|
||||
|
||||
SOURCE = 'eccv2026_springer'
|
||||
ORIGIN = 'https://link.springer.com'
|
||||
BOOK_TITLE = 'Computer Vision – ECCV 2026'
|
||||
LIST_URL = ORIGIN + '/conference/eccv'
|
||||
BOOK = re.compile(r'10\.1007/978-3-032-\d{5}-[\dXx]')
|
||||
CHAPTER = re.compile(BOOK.pattern + r'_[1-9]\d*')
|
||||
VOLUMES = set(range(17001, 17079))
|
||||
PUBLICATIONS = 2835
|
||||
|
||||
|
||||
def fingerprint(raw):
|
||||
return hashlib.sha256(raw).hexdigest()
|
||||
|
||||
|
||||
def toc_page(html, book_doi, volume):
|
||||
tree = Document(html).root
|
||||
text = clean(tree.text())
|
||||
if BOOK_TITLE not in text or 'Malmö' not in text or f'(LNCS, volume {volume})' not in text:
|
||||
raise ValueError('Unexpected Springer ECCV volume scope')
|
||||
entries = {}
|
||||
for node in tree.walk():
|
||||
if node.tag != 'li' or node.attrs.get('data-test') != 'chapter':
|
||||
continue
|
||||
headings = [n for n in node.walk() if n.tag == 'h3']
|
||||
if len(headings) != 1:
|
||||
raise ValueError('Ambiguous Springer contents heading')
|
||||
heading, = headings
|
||||
title = clean(heading.text())
|
||||
links = [n.attrs.get('href', '') for n in heading.walk() if n.tag == 'a']
|
||||
if title in ('Front Matter', 'Back Matter') and not links:
|
||||
continue
|
||||
if len(links) != 1 or not title:
|
||||
raise ValueError('Authored contents entry lacks one chapter link')
|
||||
link, = links
|
||||
doi = link.removeprefix('/chapter/')
|
||||
if (not link.startswith('/chapter/') or not CHAPTER.fullmatch(doi)
|
||||
or not doi.startswith(book_doi + '_') or doi in entries):
|
||||
raise ValueError('Unexpected or duplicate Springer chapter DOI')
|
||||
entries[doi] = title
|
||||
if not entries:
|
||||
raise ValueError('Empty Springer contents page')
|
||||
return entries
|
||||
|
||||
|
||||
def publisher_inventory(root):
|
||||
root = Path(root).resolve()
|
||||
receipt_bytes = (root / 'receipts.jsonl').read_bytes()
|
||||
inventory_bytes = (root / 'volume-checkpoint.json').read_bytes()
|
||||
summary = json.loads((root / 'summary.json').read_bytes())
|
||||
volumes = json.loads(inventory_bytes)
|
||||
receipt_rows = [json.loads(line) for line in receipt_bytes.splitlines()]
|
||||
receipts = {row['file']: row for row in receipt_rows}
|
||||
if (summary['raw_receipts_sha256'] != fingerprint(receipt_bytes)
|
||||
or summary['volume_checkpoint_sha256'] != fingerprint(inventory_bytes)
|
||||
or set(volumes) != {str(n) for n in VOLUMES}
|
||||
or len(receipts) != len(receipt_rows)):
|
||||
raise ValueError('Incomplete or inconsistent Springer contents snapshot')
|
||||
entries, used = {}, set()
|
||||
for number, volume in sorted(volumes.items()):
|
||||
book_url = volume['book']
|
||||
book_doi = book_url.removeprefix(ORIGIN + '/book/')
|
||||
if not BOOK.fullmatch(book_doi) or book_url != ORIGIN + '/book/' + book_doi:
|
||||
raise ValueError('Unexpected Springer volume URL')
|
||||
if set(volume['files']) != {'1', '2'}:
|
||||
raise ValueError('Missing reviewed Springer contents page')
|
||||
volume_dois = set()
|
||||
for index, file in volume['files'].items():
|
||||
receipt = receipts[file]
|
||||
path = root / file
|
||||
page_url = book_url + ('?page=2' if index == '2' else '')
|
||||
if (file in used or Path(file).name != file or not path.resolve().is_relative_to(root)
|
||||
or receipt['url'] != page_url or receipt['status'] != 200
|
||||
or not 0 < receipt['bytes'] <= 3_000_000):
|
||||
raise ValueError('Unsafe, reused or mismatched Springer contents receipt')
|
||||
raw = path.read_bytes()
|
||||
if len(raw) != receipt['bytes'] or fingerprint(raw) != receipt['sha256']:
|
||||
raise ValueError('Springer contents bytes disagree with receipt')
|
||||
used.add(file)
|
||||
page_entries = toc_page(raw.decode(), book_doi, int(number))
|
||||
if entries.keys() & page_entries.keys():
|
||||
raise ValueError('Springer chapter repeats across contents pages')
|
||||
volume_dois.update(page_entries)
|
||||
entries.update({doi: {'title': title, 'lncs_volume': int(number), 'book_doi': book_doi,
|
||||
'evidence_url': page_url, 'evidence_sha256': receipt['sha256']}
|
||||
for doi, title in page_entries.items()})
|
||||
if volume_dois != set(volume['chapter_dois']) or len(volume_dois) != len(volume['chapter_dois']):
|
||||
raise ValueError('Springer volume chapter set differs from checkpoint')
|
||||
if used != receipts.keys() or len(entries) != PUBLICATIONS or summary['chapter_link_count'] != PUBLICATIONS:
|
||||
raise ValueError('Springer contents chapter total differs from the reviewed archive')
|
||||
return entries
|
||||
|
||||
|
||||
def publisher_row(chapter, toc, evidence):
|
||||
doi = chapter['doi']
|
||||
if clean(chapter['title']) != toc['title']:
|
||||
raise ValueError('Chapter title differs from Springer contents, review the version')
|
||||
url = ORIGIN + '/chapter/' + doi
|
||||
return {
|
||||
'source': SOURCE, 'external_id': doi, 'url': url,
|
||||
'venue': 'ECCV', 'year': 2026, 'track': 'main',
|
||||
'title': chapter['title'], 'authors': chapter['authors'], 'abstract': chapter['abstract'],
|
||||
'status': 'accepted', 'identifiers': {'doi': doi},
|
||||
'submission_identifiers': [{'scheme': 'publication_doi', 'value': doi}],
|
||||
'evidence_url': url, 'observed_at': evidence['observed_at'],
|
||||
'raw_decision': 'Chapter published in the refereed ECCV 2026 conference proceedings.',
|
||||
'tags': [{'namespace': SOURCE + ':publication_format', 'value': 'proceedings_chapter'}],
|
||||
'metadata': {
|
||||
'book_title': BOOK_TITLE, 'book_doi': toc['book_doi'], 'lncs_volume': toc['lncs_volume'],
|
||||
'authors_citation_raw': chapter['authors_citation_raw'], 'first_page': chapter['first_page'],
|
||||
'last_page': chapter['last_page'], 'publisher_chapter_evidence': evidence,
|
||||
'publisher_contents_evidence': {'url': toc['evidence_url'], 'sha256': toc['evidence_sha256']},
|
||||
'scope': 'Refereed conference proceedings, LNCS 17001–17078.',
|
||||
'original_decision_signature_verified': False,
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def collect(out, *, toc_snapshots, chapter_snapshots):
|
||||
contents = publisher_inventory(toc_snapshots)
|
||||
chapters = snapshot_index(chapter_snapshots)
|
||||
urls = {ORIGIN + '/chapter/' + doi: doi for doi in contents}
|
||||
if not chapters or not chapters.keys() <= urls.keys():
|
||||
raise ValueError('No chapter snapshots or chapter outside reviewed ECCV proceedings')
|
||||
rows, raw = [], {}
|
||||
for url in sorted(chapters):
|
||||
doi = urls[url]
|
||||
body, evidence = read_page(chapters, url)
|
||||
chapter = parse_chapter(body.decode(), doi, book_title=BOOK_TITLE, publication_year=2026)
|
||||
rows.append(publisher_row(chapter, contents[doi], evidence))
|
||||
raw[evidence['file']] = body
|
||||
out = Path(out)
|
||||
out.mkdir(parents=True, exist_ok=True)
|
||||
lock_path = out / 'eccv2026-publications.collect.lock'
|
||||
filename = 'eccv2026-springer-main.jsonl'
|
||||
with lock_path.open('a') as lock:
|
||||
fcntl.flock(lock, fcntl.LOCK_EX | fcntl.LOCK_NB)
|
||||
if any(p != lock_path for p in out.iterdir()):
|
||||
raise FileExistsError('Existing output must be inspected, not overwritten')
|
||||
with tempfile.TemporaryDirectory(prefix='.eccv2026-publications-', dir=out) as temporary:
|
||||
stage = Path(temporary)
|
||||
(stage / 'evidence').mkdir()
|
||||
for path, body in raw.items():
|
||||
(stage / path).write_bytes(body)
|
||||
data = ''.join(json.dumps(row, ensure_ascii=False) + '\n' for row in rows).encode()
|
||||
(stage / filename).write_bytes(data)
|
||||
manifest = {
|
||||
'source': SOURCE, 'venue': 'ECCV', 'year': 2026, 'track': 'main', 'parser_version': 1,
|
||||
'file': str(out / filename), 'file_sha256': fingerprint(data), 'count': len(rows),
|
||||
'list_url': LIST_URL, 'source_expected_count': PUBLICATIONS, 'status': 'partial',
|
||||
'missing_abstract_count': sum(not r['abstract'] for r in rows),
|
||||
}
|
||||
report = {
|
||||
'status': 'collected_pending_identity_review', 'records': len(rows), 'files': [manifest],
|
||||
'toc_chapters': len(contents), 'chapter_details_missing': len(contents) - len(rows),
|
||||
'database_written': False,
|
||||
}
|
||||
metadata = Path(filename).with_suffix('.manifest.json')
|
||||
(stage / metadata).write_text(json.dumps(manifest, indent=2) + '\n')
|
||||
(stage / 'collection-report.json').write_text(json.dumps(report, indent=2) + '\n')
|
||||
for item in ('evidence', filename, metadata, 'collection-report.json'):
|
||||
(stage / item).replace(out / item)
|
||||
return report
|
||||
|
||||
|
||||
def main(argv=None, *, prog=None):
|
||||
parser = argparse.ArgumentParser(prog=prog)
|
||||
parser.add_argument('--toc-snapshots', required=True)
|
||||
parser.add_argument('--chapter-snapshots', required=True)
|
||||
parser.add_argument('--out', required=True)
|
||||
args = parser.parse_args(argv)
|
||||
print(json.dumps(collect(args.out, toc_snapshots=args.toc_snapshots,
|
||||
chapter_snapshots=args.chapter_snapshots), ensure_ascii=False))
|
||||
@@ -1,16 +1,14 @@
|
||||
"""Reviewed postconference selected volumes from frozen public HTML metadata."""
|
||||
import argparse
|
||||
from collections import defaultdict
|
||||
import fcntl
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import re
|
||||
import tempfile
|
||||
from urllib.parse import parse_qs, urlsplit
|
||||
|
||||
from paper_atlas.db.submissions import timestamp
|
||||
from paper_atlas.io.html import Document, clean
|
||||
from paper_atlas.io.springer import parse_chapter as parse_citation_chapter, read_page, snapshot_index
|
||||
|
||||
SOURCE = 'springer_selected_volume'
|
||||
BOOK = '10.1007/978-1-4612-2660-4'
|
||||
@@ -26,50 +24,6 @@ SCOPE = {
|
||||
}
|
||||
|
||||
|
||||
def snapshot_index(root):
|
||||
root = Path(root).resolve()
|
||||
receipts = json.loads((root/'receipts.json').read_bytes())['responses']
|
||||
index = {}
|
||||
for receipt in receipts:
|
||||
url = receipt['url']
|
||||
if url in index:
|
||||
raise ValueError('Duplicate snapshot URL')
|
||||
index[url] = (root, receipt)
|
||||
return index
|
||||
|
||||
|
||||
def read_page(index, url):
|
||||
if url not in index:
|
||||
raise ValueError('Missing required public HTML snapshot: '+url)
|
||||
root, receipt = index[url]
|
||||
filename = Path(receipt['file'])
|
||||
path = root/filename
|
||||
content_type = {k.lower():v for k,v in receipt.get('headers', {}).items()}.get('content-type', '')
|
||||
requested, final = urlsplit(url), urlsplit(receipt.get('final_url', ''))
|
||||
query = parse_qs(final.query, keep_blank_values=True)
|
||||
original_query = parse_qs(requested.query, keep_blank_values=True)
|
||||
# Springer returns the public metadata with an explicit cookie diagnostic.
|
||||
# Retain that final URL verbatim; accept no other redirect or changed page.
|
||||
if query != original_query and requested.netloc == 'link.springer.com':
|
||||
if (query.pop('error', None) != ['cookies_not_supported']
|
||||
or not re.fullmatch(r'[0-9a-f-]{36}', ''.join(query.pop('code', [])))):
|
||||
raise ValueError('Unreviewed Springer redirect query')
|
||||
if (filename.is_absolute() or '..' in filename.parts or not path.resolve().is_relative_to(root)
|
||||
or receipt.get('http_status') != 200
|
||||
or (final.scheme, final.netloc, final.path) != (requested.scheme, requested.netloc, requested.path)
|
||||
or final.fragment or query != original_query
|
||||
or 'text/html' not in content_type.lower()):
|
||||
raise ValueError('Unsafe, redirected or unsuccessful public HTML snapshot')
|
||||
raw = path.read_bytes()
|
||||
digest = hashlib.sha256(raw).hexdigest()
|
||||
if len(raw) > 2_000_000 or len(raw) != receipt['bytes'] or digest != receipt['sha256']:
|
||||
raise ValueError('Snapshot checksum or size differs')
|
||||
evidence = {'url':url, 'sha256':digest, 'bytes':len(raw),
|
||||
'file':'evidence/'+digest+'.html', 'http_status':200,
|
||||
'observed_at':timestamp(receipt['at']), 'response_receipt':receipt}
|
||||
return raw, evidence
|
||||
|
||||
|
||||
def parse_toc(html, *, excluded_materials=None):
|
||||
entries = {}
|
||||
for node in Document(html).root.walk():
|
||||
@@ -97,40 +51,8 @@ def parse_toc(html, *, excluded_materials=None):
|
||||
|
||||
|
||||
def parse_chapter(html, doi):
|
||||
nodes = list(Document(html).root.walk())
|
||||
meta = defaultdict(list)
|
||||
for node in nodes:
|
||||
if node.tag == 'meta' and node.attrs.get('name', '').startswith('citation_'):
|
||||
meta[node.attrs['name']].append(node.attrs.get('content', ''))
|
||||
def one(key):
|
||||
values = meta[key]
|
||||
if len(values) != 1 or not values[0]:
|
||||
raise ValueError('Missing or ambiguous citation field: '+key)
|
||||
return values[0]
|
||||
if (one('citation_doi') != doi or one('citation_inbook_title') != SCOPE['book_title']
|
||||
or one('citation_publication_date') != str(SCOPE['publication_year'])):
|
||||
raise ValueError('Chapter DOI, book or publication year differs from reviewed scope')
|
||||
raw_authors = meta['citation_author']
|
||||
if not raw_authors:
|
||||
raise ValueError('Missing named chapter authors')
|
||||
authors = []
|
||||
for raw in raw_authors:
|
||||
if raw.count(',') != 1:
|
||||
raise ValueError('Unreviewed citation author format')
|
||||
family, given = [clean(s) for s in raw.split(',', 1)]
|
||||
if not family or not given:
|
||||
raise ValueError('Incomplete citation author')
|
||||
authors.append({'given':given, 'family':family})
|
||||
abstract_nodes = [n for n in nodes if n.attrs.get('id') == 'Abs1-content']
|
||||
if len(abstract_nodes) > 1:
|
||||
raise ValueError('Ambiguous abstract section')
|
||||
abstract = clean(abstract_nodes[0].text()) if abstract_nodes else None
|
||||
first, last = one('citation_firstpage'), one('citation_lastpage')
|
||||
if not first.isdigit() or not last.isdigit() or int(first) > int(last):
|
||||
raise ValueError('Invalid chapter pages')
|
||||
return {'doi':doi, 'title':one('citation_title'), 'authors':authors,
|
||||
'authors_citation_raw':list(raw_authors), 'abstract':abstract or None,
|
||||
'first_page':first, 'last_page':last}
|
||||
return parse_citation_chapter(html, doi, book_title=SCOPE['book_title'],
|
||||
publication_year=SCOPE['publication_year'])
|
||||
|
||||
|
||||
def record_for(chapter, evidence, scope_evidence):
|
||||
|
||||
@@ -66,7 +66,7 @@ def require_incremental_parent(c, source, manifest, options):
|
||||
if entries:
|
||||
if len(entries) != 1 or entries[0][0] != manifest['list_url']:
|
||||
raise ValueError('Incremental coverage requires one unambiguous source listing')
|
||||
if tuple(entries[0][1:]) != ('partial', prior_expected, previous):
|
||||
if tuple(entries[0][i] for i in (1, 2, 3)) != ('partial', prior_expected, previous):
|
||||
raise ValueError('Incremental coverage parent changed or is not partial')
|
||||
elif previous != 0 or prior_expected is not None:
|
||||
raise ValueError('Incremental coverage parent is absent')
|
||||
|
||||
@@ -0,0 +1,91 @@
|
||||
"""Frozen Springer public HTML receipts and chapter citation metadata."""
|
||||
from collections import defaultdict
|
||||
import hashlib
|
||||
from pathlib import Path
|
||||
import json
|
||||
import re
|
||||
from urllib.parse import parse_qs, urlsplit
|
||||
|
||||
from paper_atlas.db.submissions import timestamp
|
||||
from paper_atlas.io.html import Document, clean
|
||||
|
||||
|
||||
def snapshot_index(root):
|
||||
root = Path(root).resolve()
|
||||
receipts = json.loads((root/'receipts.json').read_bytes())['responses']
|
||||
index = {}
|
||||
for receipt in receipts:
|
||||
url = receipt['url']
|
||||
if url in index:
|
||||
raise ValueError('Duplicate snapshot URL')
|
||||
index[url] = (root, receipt)
|
||||
return index
|
||||
|
||||
|
||||
def read_page(index, url):
|
||||
if url not in index:
|
||||
raise ValueError('Missing required public HTML snapshot: '+url)
|
||||
root, receipt = index[url]
|
||||
filename = Path(receipt['file'])
|
||||
path = root/filename
|
||||
content_type = {k.lower():v for k,v in receipt.get('headers', {}).items()}.get('content-type', '')
|
||||
requested, final = urlsplit(url), urlsplit(receipt.get('final_url', ''))
|
||||
query = parse_qs(final.query, keep_blank_values=True)
|
||||
original_query = parse_qs(requested.query, keep_blank_values=True)
|
||||
# Springer returns the public metadata with an explicit cookie diagnostic.
|
||||
# Retain that final URL verbatim; accept no other redirect or changed page.
|
||||
if query != original_query and requested.netloc == 'link.springer.com':
|
||||
if (query.pop('error', None) != ['cookies_not_supported']
|
||||
or not re.fullmatch(r'[0-9a-f-]{36}', ''.join(query.pop('code', [])))):
|
||||
raise ValueError('Unreviewed Springer redirect query')
|
||||
if (filename.is_absolute() or '..' in filename.parts or not path.resolve().is_relative_to(root)
|
||||
or receipt.get('http_status') != 200
|
||||
or (final.scheme, final.netloc, final.path) != (requested.scheme, requested.netloc, requested.path)
|
||||
or final.fragment or query != original_query
|
||||
or 'text/html' not in content_type.lower()):
|
||||
raise ValueError('Unsafe, redirected or unsuccessful public HTML snapshot')
|
||||
raw = path.read_bytes()
|
||||
digest = hashlib.sha256(raw).hexdigest()
|
||||
if len(raw) > 2_000_000 or len(raw) != receipt['bytes'] or digest != receipt['sha256']:
|
||||
raise ValueError('Snapshot checksum or size differs')
|
||||
evidence = {'url':url, 'sha256':digest, 'bytes':len(raw),
|
||||
'file':'evidence/'+digest+'.html', 'http_status':200,
|
||||
'observed_at':timestamp(receipt['at']), 'response_receipt':receipt}
|
||||
return raw, evidence
|
||||
|
||||
|
||||
def parse_chapter(html, doi, *, book_title, publication_year):
|
||||
nodes = list(Document(html).root.walk())
|
||||
meta = defaultdict(list)
|
||||
for node in nodes:
|
||||
if node.tag == 'meta' and node.attrs.get('name', '').startswith('citation_'):
|
||||
meta[node.attrs['name']].append(node.attrs.get('content', ''))
|
||||
def one(key):
|
||||
values = meta[key]
|
||||
if len(values) != 1 or not values[0]:
|
||||
raise ValueError('Missing or ambiguous citation field: '+key)
|
||||
return values[0]
|
||||
if (one('citation_doi') != doi or one('citation_inbook_title') != book_title
|
||||
or one('citation_publication_date') != str(publication_year)):
|
||||
raise ValueError('Chapter DOI, book or publication year differs from reviewed scope')
|
||||
raw_authors = meta['citation_author']
|
||||
if not raw_authors:
|
||||
raise ValueError('Missing named chapter authors')
|
||||
authors = []
|
||||
for raw in raw_authors:
|
||||
if raw.count(',') != 1:
|
||||
raise ValueError('Unreviewed citation author format')
|
||||
family, given = [clean(s) for s in raw.split(',', 1)]
|
||||
if not family or not given:
|
||||
raise ValueError('Incomplete citation author')
|
||||
authors.append({'given':given, 'family':family})
|
||||
abstract_nodes = [n for n in nodes if n.attrs.get('id') == 'Abs1-content']
|
||||
if len(abstract_nodes) > 1:
|
||||
raise ValueError('Ambiguous abstract section')
|
||||
abstract = clean(abstract_nodes[0].text()) if abstract_nodes else None
|
||||
first, last = one('citation_firstpage'), one('citation_lastpage')
|
||||
if not first.isdigit() or not last.isdigit() or int(first) > int(last):
|
||||
raise ValueError('Invalid chapter pages')
|
||||
return {'doi':doi, 'title':one('citation_title'), 'authors':authors,
|
||||
'authors_citation_raw':list(raw_authors), 'abstract':abstract or None,
|
||||
'first_page':first, 'last_page':last}
|
||||
@@ -0,0 +1,124 @@
|
||||
"""Checks for published ECCV metadata and preserved submission histories."""
|
||||
from hashlib import sha256
|
||||
import json
|
||||
from pathlib import Path
|
||||
import sqlite3
|
||||
import tempfile
|
||||
import unittest
|
||||
|
||||
from paper_atlas.collectors.eccv2026_publications import BOOK_TITLE, SOURCE, collect
|
||||
from paper_atlas.db.store import Store
|
||||
from paper_atlas.ingestion.records import ingest_file
|
||||
|
||||
|
||||
FIRST_BOOK = '10.1007/978-3-032-10000-0'
|
||||
FIRST_DOI = FIRST_BOOK + '_1'
|
||||
|
||||
|
||||
def snapshots(root):
|
||||
toc, chapters = root / 'toc', root / 'chapters'
|
||||
toc.mkdir()
|
||||
chapters.mkdir()
|
||||
receipts, volumes = [], {}
|
||||
for offset in range(78):
|
||||
volume = 17001 + offset
|
||||
book = f'10.1007/978-3-032-{10000 + offset}-0'
|
||||
book_url = 'https://link.springer.com/book/' + book
|
||||
count = 37 if offset < 27 else 36
|
||||
files, chapter_dois = {}, []
|
||||
for page, indices in ((1, range(1, 20)), (2, range(20, count + 1))):
|
||||
filename = f'{volume}-{page}.html'
|
||||
html = f'<h1>{BOOK_TITLE}</h1><p>Malmö (LNCS, volume {volume})</p>'
|
||||
html += '<li data-test="chapter"><h3>Front Matter</h3></li>'
|
||||
for i in indices:
|
||||
doi = f'{book}_{i}'
|
||||
html += f'<li data-test="chapter"><h3><a href="/chapter/{doi}">Title {volume}-{i}</a></h3></li>'
|
||||
chapter_dois.append(doi)
|
||||
raw = html.encode()
|
||||
(toc / filename).write_bytes(raw)
|
||||
files[str(page)] = filename
|
||||
receipts.append({'file': filename, 'status': 200, 'bytes': len(raw), 'sha256': sha256(raw).hexdigest(),
|
||||
'url': book_url + ('?page=2' if page == 2 else '')})
|
||||
volumes[str(volume)] = {'book': book_url, 'files': files, 'chapter_dois': chapter_dois}
|
||||
data = ''.join(json.dumps(row) + '\n' for row in receipts).encode()
|
||||
(toc / 'receipts.jsonl').write_bytes(data)
|
||||
checkpoint = json.dumps(volumes).encode()
|
||||
(toc / 'volume-checkpoint.json').write_bytes(checkpoint)
|
||||
(toc / 'summary.json').write_text(json.dumps({
|
||||
'raw_receipts_sha256': sha256(data).hexdigest(),
|
||||
'volume_checkpoint_sha256': sha256(checkpoint).hexdigest(),
|
||||
'chapter_link_count': 2835,
|
||||
}))
|
||||
url = 'https://link.springer.com/chapter/' + FIRST_DOI
|
||||
citation = {
|
||||
'citation_doi': FIRST_DOI, 'citation_title': 'Title 17001-1',
|
||||
'citation_inbook_title': BOOK_TITLE, 'citation_publication_date': '2026',
|
||||
'citation_firstpage': '1', 'citation_lastpage': '10',
|
||||
'citation_author': 'Chen, Lei',
|
||||
}
|
||||
body = ''.join(f'<meta name="{k}" content="{v}">' for k, v in citation.items())
|
||||
body += '<div id="Abs1-content"><p>Published abstract.</p></div>'
|
||||
raw = body.encode()
|
||||
(chapters / 'first.html').write_bytes(raw)
|
||||
(chapters / 'receipts.json').write_text(json.dumps({'responses': [{
|
||||
'url': url, 'final_url': url, 'file': 'first.html', 'at': '2026-11-18T00:00:00Z',
|
||||
'http_status': 200, 'bytes': len(raw), 'sha256': sha256(raw).hexdigest(),
|
||||
'headers': {'Content-Type': 'text/html'},
|
||||
}]}))
|
||||
return {'toc_snapshots': toc, 'chapter_snapshots': chapters}
|
||||
|
||||
|
||||
class ECCV2026PublicationsTests(unittest.TestCase):
|
||||
def test_frozen_snapshot_and_existing_history(self):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root = Path(tmp)
|
||||
source = snapshots(root)
|
||||
report = collect(root / 'out', **source)
|
||||
self.assertEqual((report['toc_chapters'], report['chapter_details_missing']), (2835, 2834))
|
||||
manifest, = report['files']
|
||||
self.assertEqual((manifest['track'], manifest['status']), ('main', 'partial'))
|
||||
row = json.loads(Path(manifest['file']).read_text())
|
||||
self.assertEqual(row['identifiers'], {'doi': FIRST_DOI})
|
||||
self.assertEqual(row['submission_identifiers'], [{'scheme': 'publication_doi', 'value': FIRST_DOI}])
|
||||
self.assertEqual(row['authors'], [{'family': 'Chen', 'given': 'Lei'}])
|
||||
self.assertEqual(row['abstract'], 'Published abstract.')
|
||||
self.assertEqual(row['metadata']['lncs_volume'], 17001)
|
||||
self.assertFalse(row['metadata']['original_decision_signature_verified'])
|
||||
detail = row['metadata']['publisher_chapter_evidence']
|
||||
self.assertEqual(sha256((root / 'out' / detail['file']).read_bytes()).hexdigest(), detail['sha256'])
|
||||
db = root / 'example.sqlite'
|
||||
store = Store(db)
|
||||
pid, rid = store.record('prior', 'work', 'https://example.org/work',
|
||||
row['title'], 'Original preprint abstract.', row['authors'],
|
||||
{'arxiv': '2601.00001'})
|
||||
store.decision(pid, rid, 'ICLR', 2026, 'main', 'work', 'https://example.org/decision',
|
||||
'rejected', 'Original ICLR result.')
|
||||
store.conn.commit()
|
||||
store.conn.close()
|
||||
row['identifiers']['arxiv'] = '2601.00001'
|
||||
path = Path(manifest['file'])
|
||||
raw = (json.dumps(row) + '\n').encode()
|
||||
path.write_bytes(raw)
|
||||
manifest['file_sha256'] = sha256(raw).hexdigest()
|
||||
path.with_suffix('.manifest.json').write_text(json.dumps(manifest))
|
||||
ingest_file(db, path)
|
||||
ingest_file(db, path)
|
||||
with sqlite3.connect(db) as conn:
|
||||
self.assertEqual(conn.execute('SELECT id,abstract FROM papers').fetchall(),
|
||||
[(pid, 'Original preprint abstract.')])
|
||||
self.assertEqual(conn.execute('SELECT status FROM decisions ORDER BY id').fetchall(),
|
||||
[('rejected',), ('accepted',)])
|
||||
self.assertEqual(conn.execute('SELECT scheme,value FROM submission_identifiers').fetchall(),
|
||||
[('publication_doi', FIRST_DOI)])
|
||||
self.assertEqual(conn.execute('SELECT name FROM sources ORDER BY id').fetchall(), [('prior',), (SOURCE,)])
|
||||
with self.assertRaises(FileExistsError):
|
||||
collect(root / 'out', **source)
|
||||
|
||||
def test_changed_contents_receipt_stops_before_output(self):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root = Path(tmp)
|
||||
source = snapshots(root)
|
||||
(source['toc_snapshots'] / '17001-1.html').write_text('unverified bytes')
|
||||
with self.assertRaisesRegex(ValueError, 'contents bytes disagree'):
|
||||
collect(root / 'out', **source)
|
||||
self.assertFalse((root / 'out').exists())
|
||||
@@ -15,7 +15,7 @@ from paper_atlas.db.backend import open_store, open_read_connection
|
||||
from paper_atlas.db.store import Store
|
||||
from paper_atlas.ingestion import arxiv
|
||||
from paper_atlas.ingestion.backfill import backfill
|
||||
from paper_atlas.ingestion.records import ingest_file
|
||||
from paper_atlas.ingestion.records import coverage_options, ingest_file, require_incremental_parent
|
||||
from paper_atlas.postgres.client import connect, ReadConnection
|
||||
from paper_atlas.postgres.migration import migrate
|
||||
from paper_atlas.postgres.schema import quote
|
||||
@@ -114,6 +114,36 @@ class PostgreSQLIngestionTests(unittest.TestCase):
|
||||
self.assertEqual(run[0],1)
|
||||
self.assertEqual(json.loads(run[1])['coverage']['imported_count'],3)
|
||||
|
||||
def test_incremental_parent_preflight_uses_readonly_postgres_rows_and_keeps_guards(self):
|
||||
rows = [self.row(source='dblp', external=key, status='accepted', year=2001, venue='UAI')
|
||||
for key in ('preflight1', 'preflight2')]
|
||||
path = self.file('preflight-parent', rows)
|
||||
target = path.with_suffix('.manifest.json')
|
||||
manifest = json.loads(target.read_text())
|
||||
manifest['status'] = 'partial'
|
||||
target.write_text(json.dumps(manifest))
|
||||
self.ingest(path)
|
||||
proposed = dict(manifest, coverage_mode='incremental', count=1,
|
||||
coverage_previous_count=2, coverage_previous_expected_count=2,
|
||||
coverage_expected_count=4)
|
||||
with closing(ReadConnection(self.service, self.schema)) as c:
|
||||
self.assertEqual(c.execute('SHOW transaction_read_only').fetchone()[0], 'on')
|
||||
source = c.execute("SELECT id FROM sources WHERE name='dblp'").fetchone()[0]
|
||||
before = {table: c.execute('SELECT count(*) FROM '+table).fetchone()[0]
|
||||
for table in ('papers', 'source_records', 'submissions', 'decisions', 'ingest_runs')}
|
||||
coverage = [dict(row) for row in c.execute('SELECT * FROM edition_sources ORDER BY edition_id,source_id,list_url')]
|
||||
require_incremental_parent(c, source, proposed, coverage_options(proposed))
|
||||
for changes, error in (({'coverage_previous_count': 1}, 'parent changed'),
|
||||
({'coverage_previous_expected_count': 3}, 'parent changed'),
|
||||
({'list_url': 'https://example.org/other-list'}, 'unambiguous source listing')):
|
||||
with self.subTest(changes=changes):
|
||||
stale = dict(proposed, **changes)
|
||||
with self.assertRaisesRegex(ValueError, error):
|
||||
require_incremental_parent(c, source, stale, coverage_options(stale))
|
||||
self.assertEqual({table: c.execute('SELECT count(*) FROM '+table).fetchone()[0]
|
||||
for table in before}, before)
|
||||
self.assertEqual([dict(row) for row in c.execute('SELECT * FROM edition_sources ORDER BY edition_id,source_id,list_url')], coverage)
|
||||
|
||||
def test_incremental_postgres_bound_failure_rolls_back_rows_and_summary(self):
|
||||
listing='https://example.org/uai/2001'
|
||||
rows=[self.row(source='dblp',external=key,status='accepted',year=2001,venue='UAI')
|
||||
|
||||
Reference in New Issue
Block a user