Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 564821d883 |
+17
-16
@@ -12,7 +12,7 @@ jobs:
|
||||
- name: Verify metadata storage and query commands
|
||||
run: |
|
||||
python3 -B - <<'PY'
|
||||
import gzip, io, json, os, pathlib, re, subprocess, tarfile, tempfile, urllib.request
|
||||
import base64, gzip, io, json, os, pathlib, re, subprocess, tarfile, tempfile, urllib.request
|
||||
sha = os.environ['ARCHIVE_SHA']
|
||||
if not re.fullmatch(r'[0-9a-fA-F]{40,64}', sha):
|
||||
raise SystemExit('Invalid source commit')
|
||||
@@ -77,6 +77,22 @@ jobs:
|
||||
eccv_literal_row = next(row for row in eccv_rows if row['external_id'] == '2026/3844')
|
||||
assert eccv_literal_row['title'] == eccv_literal['gold']['visible_title']
|
||||
assert '&' in eccv_literal_row['title']
|
||||
icassp_fixture = json.loads(gzip.decompress((src/'tests/fixtures/icassp2026-source.json.gz').read_bytes()))
|
||||
icassp_snapshots = root/'icassp2026-snapshots'
|
||||
icassp_snapshots.mkdir()
|
||||
for name, encoded in icassp_fixture['files'].items():
|
||||
target = icassp_snapshots/name
|
||||
target.parent.mkdir(parents=True,exist_ok=True)
|
||||
target.write_bytes(base64.b64decode(encoded))
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','collect','icassp2026-registry','--snapshots',str(icassp_snapshots),'--out',str(root/'installed-icassp2026')],cwd=outside,check=True)
|
||||
icassp_report = json.loads((root/'installed-icassp2026/collection-report.json').read_text())
|
||||
assert icassp_report['records'] == 4582 and icassp_report['missing_abstract_count'] == 4582
|
||||
assert icassp_report['single_name_author_fields'] == 23
|
||||
assert len(icassp_report['excluded_nonpaper_items']) == 7 and len(icassp_report['excluded_other_conference_dois']) == 56
|
||||
assert not icassp_report['database_written'] and icassp_report['network_requests'] == 0 and icassp_report['approved_for_import'] == 0
|
||||
icassp_rows = [json.loads(line) for line in pathlib.Path(icassp_report['files'][0]['file']).read_text().splitlines()]
|
||||
assert [{'doi':r['external_id'],'title':r['title'],'authors':r['authors']} for r in icassp_rows] == sorted(icassp_fixture['independent_gold'],key=lambda r:r['doi'])
|
||||
assert all(r['abstract'] is None and r['track'] == 'proceedings_unclassified' for r in icassp_rows)
|
||||
sdm_fixture = json.loads(gzip.decompress((src/'tests/fixtures/sdm2026-source.json.gz').read_bytes()))
|
||||
sdm_snapshots = root/'sdm2026-snapshots'
|
||||
for name, text in sdm_fixture['files'].items():
|
||||
@@ -94,21 +110,6 @@ jobs:
|
||||
sdm_observations = [json.loads(line) for line in pathlib.Path(sdm_report['program_observations']['file']).read_text().splitlines()]
|
||||
assert sum(row['cancelled_presentation'] for row in sdm_observations) == 1
|
||||
assert all('status' not in row and 'identifiers' not in row for row in sdm_observations)
|
||||
icdm_fixture = json.loads(gzip.decompress((src/'tests/fixtures/icdm2026-source.json.gz').read_bytes()))
|
||||
icdm_snapshots = root/'icdm2026-snapshots'
|
||||
for name, text in icdm_fixture['files'].items():
|
||||
target = icdm_snapshots/name
|
||||
target.parent.mkdir(parents=True, exist_ok=True)
|
||||
target.write_bytes(text.encode('utf-8'))
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','collect','icdm2026-program','--snapshots',str(icdm_snapshots),'--out',str(root/'installed-icdm2026')],cwd=outside,check=True)
|
||||
icdm_report = json.loads((root/'installed-icdm2026/collection-report.json').read_text())
|
||||
assert icdm_report['records'] == 324 and icdm_report['missing_abstract_count'] == 324
|
||||
assert icdm_report['track_counts'] == {'research':241,'applied':83}
|
||||
assert icdm_report['presentation_counts'] == {'long':168,'short':156}
|
||||
assert not icdm_report['database_written'] and icdm_report['network_requests'] == 0
|
||||
icdm_rows = [json.loads(line) for f in icdm_report['files'] for line in pathlib.Path(f['file']).read_text().splitlines()]
|
||||
assert len(icdm_rows) == 324 and all(row['abstract'] is None and not row['identifiers'] and not row['submission_identifiers'] for row in icdm_rows)
|
||||
assert all(row['metadata']['paper_type'] is None and not row['metadata']['original_decision_signature_verified'] for row in icdm_rows)
|
||||
icaps_fixture = json.loads(gzip.decompress((src/'tests/fixtures/icaps2026-source.json.gz').read_bytes()))
|
||||
icaps_snapshots = root/'icaps2026-snapshots'
|
||||
icaps_snapshots.mkdir()
|
||||
|
||||
@@ -131,6 +131,6 @@ ICAPS 2026 也提供独立的 `collect icaps2026-registry`,保留 Crossref 卷
|
||||
|
||||
ECCV 2026 的[暂定节目采集器](docs/eccv2026-program.md)合并重复节目 ID,并以不可变缓存断点采集公开元数据;保留摘要原文、来源关键词及未分类 track,始终待身份审核,不自动入库。
|
||||
|
||||
`collect sdm2026-proceedings` 核验 53 个 Crossref 论文章节,并单独保留 53 项日程观察及 52 页摘要。作者差异、取消展示和摘要缺失分别保留,不自动拼接来源或绑定作品;见 [SDM 2026 使用与恢复说明](docs/sdm2026-proceedings.md)。
|
||||
`collect icassp2026-registry` 从冻结的 10 页 Crossref 元数据核验 4,582 条论文,明确排除 7 条非论文及 56 条其他会议记录;保留摘要缺失和单字段作者姓名,不自动融合节目表。见 [ICASSP 2026 采集与恢复说明](docs/icassp2026-registry.md)。
|
||||
|
||||
`collect icdm2026-program` 离线核验 324 条 ICDM2026 官方线下日程,按明确的研究/应用标签输出 241/83 条;展示长短、缺失摘要及未核实出版身份分别保留,不自动入库。见 [ICDM2026 使用与恢复说明](docs/icdm2026-program.md)。
|
||||
`collect sdm2026-proceedings` 核验 53 个 Crossref 论文章节,并单独保留 53 项日程观察及 52 页摘要。作者差异、取消展示和摘要缺失分别保留,不自动拼接来源或绑定作品;见 [SDM 2026 使用与恢复说明](docs/sdm2026-proceedings.md)。
|
||||
|
||||
@@ -0,0 +1,40 @@
|
||||
# ICASSP 2026 注册元数据采集
|
||||
|
||||
这是长期维护项目中的可重复运行采集器,按需离线处理冻结的公开元数据;不会启动数据库导入、联网或下载论文 PDF。命令仅输出待身份审查的来源版本。
|
||||
|
||||
## 输入与使用
|
||||
|
||||
2026-11-17 在数据服务器采集 Crossref 公开 REST API。先从正式节目表抽查的两篇标题确定注册会议名称和 DOI 前缀,再依据 IEEE DOI 前缀、proceedings-article 类型及注册的活动开始日期 `2026-05-03` 分页获取;日期过滤并不意味着所有结果都属于 ICASSP。
|
||||
|
||||
需要服务器 `/data/paper-index/collected/icassp2026-registry-capture-v1` 下的 `manifest.json` 与 `page-001.json` 至 `page-010.json`。将其父目录传给:
|
||||
|
||||
```sh
|
||||
paper-atlas collect icassp2026-registry \
|
||||
--snapshots /data/paper-index/collected \
|
||||
--out /data/paper-index/collected/icassp2026-normalized-<new-run>
|
||||
```
|
||||
|
||||
输出目录必须不存在。复跑前先检查原任务和产物,不能覆盖成功或失败输出。采集器验证固定清单 SHA256、全部页面原始字节、HTTP 回执、时区、页面数量、总数及唯一 DOI,再生成 JSONL、导入格式的部分覆盖清单、全部原始来源证据和采集报告。导入格式不代表身份审查通过;本命令批准导入数始终为零。
|
||||
|
||||
## 数据范围
|
||||
|
||||
- 10 页共有 4,645 个唯一 DOI;56 个属于 ICPEA,明确排除。
|
||||
- ICASSP 的 4,589 个注册条目中,7 个是封面、目录、作者索引、委员会和审稿人名单;依据已审查的准确 DOI、标题和页码排除,不以“没有作者”泛化排除论文。
|
||||
- 剩余 **4,582 条论文**全部缺少注册摘要,输出 `null`。保留完整注册字段、作者顺序、机构、原始标题、日期及原始来源哈希。
|
||||
- 23 个作者条目只提供单个姓名字段,原样保留并标记;不猜测名字拆分、拼音边界或人物别名。
|
||||
- `accepted` 表示已登记在该会议论文集中的发表观察,并非原始签名录用决定。DOI 用 `publication_doi`,不复制先前投稿系统的 ID。
|
||||
- track 为 `proceedings_unclassified`,不从技术主题推断 main、special session、workshop 或研究类型;没有自造标签。
|
||||
|
||||
正式节目表有 4,589 个编号和标题,与注册条目不是已证明的一一对应关系。独立标题规范化比较得到 4,415 个来源候选和 174 个未匹配节目标题;标题匹配不是作品身份批准,未匹配不等于拒稿、撤稿或未发表。节目表作者与注册作者的版本也不应自动拼接。
|
||||
|
||||
注册活动日期为 5 月 3–8 日,会议网站为 5 月 4–8 日,两者原始值均保留。Crossref 记录中的链接只是原始字段,不会访问 PDF。IEEE Open Preview 入口读取遇到 HTTP 418,未绕过访问限制。公开拒稿元数据是否可得仍为 unknown,本批不是拒稿覆盖证明,也不是第 14 项整体完成证明。
|
||||
|
||||
## 证据与恢复
|
||||
|
||||
注册来源清单 SHA256:`1f8ffa040b1f682a4b65f476f4115cb95629056d8de5c324c8417d823846ae93`。
|
||||
|
||||
原始证据恢复包在服务器 `/data/paper-index/validation/icassp2026-registry-capture-v1-recovery.tar.gz`,本地备份位于 `/Users/zzyang/Documents/Codex/2026-11-06/paper-index/` 同名文件,SHA256 为 `cdc506e95800fb8d37ed87f85740e96f56150f2d96daa971de21a5a7a9ab8388`。安全解包并核验后使用上述命令;测试夹具也冻结了全部 10 页及独立论文清单,供远程 CI 验证。
|
||||
|
||||
本批还需生产规范化验收、数据库当前 DOI/作品关联及历次投稿审查。所有导入结束后仍须执行全库去重、覆盖、摘要和历史完整性审计。编译、打包及测试均交给用户指定的 `ces-control:host` runner。
|
||||
|
||||
参考:[Crossref 筛选器文档](https://www.crossref.org/documentation/retrieve-metadata/rest-api/rest-api-filters/)、[正式录用标题表](https://cmsworkshops.com/ICASSP2026/papers/accepted_papers.php)、[会议日程](https://2026.ieeeicassp.org/technical-program/)、[发表和展示类型说明](https://2026.ieeeicassp.org/publishing-and-paper-presentation-options/)。
|
||||
@@ -1,46 +0,0 @@
|
||||
# ICDM2026 冻结日程适配器
|
||||
|
||||
这是长期维护、按需运行的来源模块。它读取已经冻结的官方页面,离线生成可审阅的标准记录,不连接数据库、不请求网络、不下载论文 PDF;后续入库仍需作品身份、发表版本和旧投稿历史核查。
|
||||
|
||||
```sh
|
||||
paper-atlas collect icdm2026-program \
|
||||
--snapshots /data/paper-index/collected \
|
||||
--out /data/paper-index/collected/icdm2026-normalized-pass01
|
||||
```
|
||||
|
||||
输入根目录下须有 `remaining2026-official-leads-v1/manifest.json`,及 manifest 所列的三个 ICDM HTML:`icdm-detailed-sessions.html`、`icdm-research-policy.html`、`icdm-applied-policy.html`。共享研究 manifest 也保留其他会议的入口回执,但本适配器只读取并验证 ICDM 的三个明确 URL,不要求复制其他会议文件。固定 manifest SHA-256 为 `0e13313d94e3bff17f071d3a1384f6ed83ece156239fe5bc4633cc7a34fb8e04`。
|
||||
|
||||
适配器核对每个回执的 URL、HTTP 200、HTML 内容类型、时区时间戳、原始字节数和哈希;保留 CRLF。来源更新必须另存版本并重新审阅,不能修改旧 manifest 来冒充旧快照。源码测试 fixture 同时保存原始页面、回执和使用另一解析方法得到的独立逐行盘点。
|
||||
|
||||
## 两个明确来源轨道
|
||||
|
||||
[官方详细日程](https://icdm2026.neu.edu.cn/DetailedSessions/list.htm)自称为线下展示清单,日期为 2026 年 11 月 13–15 日,34 个分会场、324 个不同节目编号。适配器分别输出:
|
||||
|
||||
| 输出文件 | 官方明确标签 | 记录数 |
|
||||
| --- | --- | ---: |
|
||||
| icdm-program-2026-research.jsonl | research / Research Track | 241 |
|
||||
| icdm-program-2026-applied.jsonl | applied / Applied Track | 83 |
|
||||
|
||||
`data-track` 属性必须与可见标签一致;轨道来自这两份明确证据,不根据标题、会场名称或研究主题推测。`data-format` 和可见 Long/Short 标签、展示说明必须一致;168 个 long 和 156 个 short 仅表示演讲形式,**不自动转成论文长短、position、findings 或研究类型**。日程主题也不生成自定义人物或研究分类。
|
||||
|
||||
每条保留日程显示标题、原始作者文字、分号分隔的来源姓名顺序、节目编号、分会场、时间、地点、全局来源位置、来源回执和对应原文文件。作者仅标为日程报告的姓名,不声称为最终出版社完整作者版本,也不生成姓名别名。
|
||||
|
||||
`2026/DM...` 是 `icdm_program` 来源下的节目定位键;页面锚点只是来源定位,不能当 DOI、arXiv 或原始签名投稿/决定标识。`identifiers` 和 `submission_identifiers` 都为空。`status=accepted` 表示列入官方研究/应用日程的来源观察,`raw_decision` 明确其并非原始签名决定或已核验出版社记录;不根据该状态生成原始决定日期。每条 `original_decision_signature_verified=false`。
|
||||
|
||||
## 始终保留范围限制
|
||||
|
||||
324 条日程记录都没有摘要,输出 `abstract=null`,每个文件的 `missing_abstract_count` 如实填写。manifest 始终为 partial;`source_expected_count` 仅对应这个冻结线下日程分区,不能当作所有录用、正式出版或线上展示的应有总数。其他页面的 workshop、博士论坛、BlueSky、demo 等不在本次输入范围内,也不能假定不存在。
|
||||
|
||||
标签使用 `icdm_program:session_track` 与 `icdm_program:presentation` namespace;它们是平台来源证据,不与其他来源标签或用户自定义标签混为一谈。`paper_type` 保留为空。
|
||||
|
||||
[研究轨政策](https://icdm2026.neu.edu.cn/CallforResearchTrack/list.htm)描述 triple-blind 审稿,[应用轨政策](https://icdm2026.neu.edu.cn/CallforAppliedTrack/list.htm)描述 single-blind 审稿,并指向 CyberChair 投稿系统。这些是审稿期间政策,**不能据此断言最终拒稿元数据不公开**。报告保留 `public_rejected_metadata=unknown_no_public_export_verified`;未访问登录资料、未绕过限制,也未从日程缺席推断 rejected、desk_rejected 或 withdrawn。
|
||||
|
||||
## 验证与恢复
|
||||
|
||||
完整测试在已授权 `ces-control:host` 远程 runner 执行,包含全部 324 条与独立盘点逐字段对照、轨道/展示属性与可见文字冲突、重复或变化的节目编号、会场计数、空作者、原始字节/回执校验和失败输出保护。CI 另在安装 wheel 后、工作目录外运行真实 CLI,检查 241/83 两个输出及缺失摘要、未生成稳定标识等边界。构建和测试不在用户本机运行;实际结果见对应提交的远程 CI。
|
||||
|
||||
输出目录必须不存在。输入校验失败时不会创建输出;输出生成失败会保存 `failed.json`,成功报告最后原子发布为 `collection-report.json`。遇到已有目录,先核对原操作,不覆盖、不盲目重放。
|
||||
|
||||
原始来源恢复包为 `/data/paper-index/validation/remaining2026-official-leads-v1-recovery.tar.gz`,SHA-256 为 `0be8c84bb5c591e5afaaa5f95dd5334bf13a9be1671cb942e46e998f502495bb`。独立盘点为 `/data/paper-index/validation/icdm2026-independent-program-inventory-v1.json`,SHA-256 为 `e13eaea0a158dcaafdf5dfb4af7948e4793b0e98041ec87d42b52513acfdc5f6`;本机工作记录目录也保留同名备份。
|
||||
|
||||
下次继续先验证源码版本、原始证据和实际输出,再寻找可公开取得的摘要与正式出版记录,核查逐篇版本、稳定标识及旧投稿历史,准备新的只读预检和可审阅入库队列。完成日程规范化不意味着 ICDM2026 整届出版覆盖、公开负面决定普查或最终全库去重完成。
|
||||
+1
-1
@@ -25,7 +25,7 @@ COMMANDS = {
|
||||
('collect','mlsys'): ('paper_atlas.collectors.proceedings', {'source':'mlsys'}, 'MLSys 官方历年标题与摘要'),
|
||||
('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','icdm2026-program'): ('paper_atlas.collectors.icdm2026', {}, '核验 ICDM2026 冻结日程及明确的研究/应用轨道'),
|
||||
('collect','icassp2026-registry'): ('paper_atlas.collectors.icassp2026', {}, '核验 ICASSP 2026 冻结注册论文元数据'),
|
||||
('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'),
|
||||
('collect','icaps2026-program'): ('paper_atlas.collectors.icaps2026', {}, '核验 ICAPS 2026 官方录用名单并分开既有论文展示'),
|
||||
('collect','rss2026-proceedings'): ('paper_atlas.collectors.rss2026', {}, '核验 RSS 2026 官方论文集与独立录用表'),
|
||||
|
||||
@@ -0,0 +1,172 @@
|
||||
"""Normalize the frozen ICASSP 2026 Crossref census without network or database writes."""
|
||||
import argparse
|
||||
from datetime import datetime
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import re
|
||||
|
||||
from paper_atlas.io.html import clean
|
||||
|
||||
SOURCE = 'crossref_icassp_registry'
|
||||
TRACK = 'proceedings_unclassified'
|
||||
SNAPSHOT = 'icassp2026-registry-capture-v1'
|
||||
MANIFEST_SHA = '1f8ffa040b1f682a4b65f476f4115cb95629056d8de5c324c8417d823846ae93'
|
||||
CONTAINER = 'ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)'
|
||||
OTHER_CONTAINER = '2026 IEEE 6th International Conference in Power Engineering Applications (ICPEA)'
|
||||
PREFIX = '10.1109/icassp55912.2026.'
|
||||
NONPAPERS = {
|
||||
PREFIX+'11463724': ('ICASSP 2026 Reviewers', 'xii-lxxxvi'),
|
||||
PREFIX+'11464828': ('Author Index', 'A-1-A-152'),
|
||||
PREFIX+'11464776': ('Title Page', 'i-ii'),
|
||||
PREFIX+'11462944': ('ICASSP 2026 Committees', 'vi-xii'),
|
||||
PREFIX+'11464852': ('ICASSP 2026 Organizing Committee', 'iii-iii'),
|
||||
PREFIX+'11460797': ('ICASSP 2026 Cover Page', 'c1-c1'),
|
||||
PREFIX+'11463523': ('Table of Contents', 'xlix-cdlxii'),
|
||||
}
|
||||
|
||||
|
||||
def digest(raw):
|
||||
return hashlib.sha256(raw).hexdigest()
|
||||
|
||||
|
||||
def load_snapshot(root):
|
||||
root = Path(root); directory = root/SNAPSHOT; path = directory/'manifest.json'
|
||||
if root.is_symlink() or directory.is_symlink() or path.is_symlink() or path.stat().st_size > 128*1024:
|
||||
raise ValueError('Unsafe snapshot manifest')
|
||||
raw = path.read_bytes()
|
||||
if digest(raw) != MANIFEST_SHA:
|
||||
raise ValueError('Reviewed manifest hash changed')
|
||||
manifest = json.loads(raw)
|
||||
if (manifest['status'] != 'registry_census_completed_not_import_approval'
|
||||
or manifest['records_captured'] != 4645 or manifest['unique_dois'] != 4645
|
||||
or manifest['database_written'] is not False or manifest['approved_for_import'] != 0
|
||||
or len(manifest['pages']) != 10):
|
||||
raise ValueError('Incomplete frozen census receipt')
|
||||
files = {'manifest.json': raw}; rows = []
|
||||
for index, receipt in enumerate(manifest['pages'], 1):
|
||||
name = receipt['file']; path = directory/name
|
||||
if (name != f'page-{index:03}.json' or path.is_symlink()
|
||||
or path.stat().st_size > 4*1024**2):
|
||||
raise ValueError('Unsafe snapshot page')
|
||||
body = path.read_bytes()
|
||||
if (receipt['http_status'] != 200 or receipt['url'] != receipt['final_url']
|
||||
or not receipt['url'].startswith('https://api.crossref.org/works?')
|
||||
or datetime.fromisoformat(receipt['at']).utcoffset() is None
|
||||
or receipt['bytes'] != len(body) or receipt['sha256'] != digest(body)):
|
||||
raise ValueError('Snapshot receipt/body disagree')
|
||||
data = json.loads(body); message = data['message']
|
||||
expected = 500 if index < 10 else 145
|
||||
if data['status'] != 'ok' or message['total-results'] != 4645 or len(message['items']) != expected:
|
||||
raise ValueError('Incomplete registry page')
|
||||
files[name] = body
|
||||
for original in message['items']:
|
||||
rows.append((original, receipt))
|
||||
return manifest, files, rows
|
||||
|
||||
|
||||
def registry_papers(rows):
|
||||
seen = set(); papers = []; nonpapers = []; other = []
|
||||
for original, receipt in rows:
|
||||
doi = original.get('DOI')
|
||||
if not isinstance(doi, str) or doi in seen:
|
||||
raise ValueError('Missing or repeated registry DOI')
|
||||
seen.add(doi)
|
||||
if original.get('container-title') == [OTHER_CONTAINER]:
|
||||
if doi.startswith(PREFIX):
|
||||
raise ValueError('Conference DOI/container conflict')
|
||||
other.append(doi)
|
||||
continue
|
||||
if (original.get('container-title') != [CONTAINER]
|
||||
or original.get('event', {}).get('name') != CONTAINER
|
||||
or not re.fullmatch(re.escape(PREFIX)+r'[0-9]+', doi)
|
||||
or original.get('publisher') != 'IEEE' or original.get('type') != 'proceedings-article'
|
||||
or original.get('URL') != 'https://doi.org/'+doi
|
||||
or original.get('published') != {'date-parts': [[2026, 5, 3]]}
|
||||
or original.get('event', {}).get('start') != {'date-parts': [[2026, 5, 3]]}
|
||||
or original.get('event', {}).get('end') != {'date-parts': [[2026, 5, 8]]}):
|
||||
raise ValueError('Wrong registered conference, DOI, publisher or dates')
|
||||
if doi in NONPAPERS:
|
||||
title, page = NONPAPERS[doi]
|
||||
if original.get('title') != [title] or original.get('page') != page or original.get('author'):
|
||||
raise ValueError('Changed reviewed nonpaper evidence')
|
||||
nonpapers.append({'doi': doi, 'title': title, 'page': page})
|
||||
continue
|
||||
titles = original.get('title')
|
||||
if not isinstance(titles, list) or len(titles) != 1 or not isinstance(titles[0], str) or not clean(titles[0]):
|
||||
raise ValueError('Missing registry title')
|
||||
authors = original.get('author')
|
||||
if not isinstance(authors, list) or not authors or original.get('abstract'):
|
||||
raise ValueError('Missing authors or changed abstract availability')
|
||||
names = []; flags = []
|
||||
for position, author in enumerate(authors):
|
||||
if (not isinstance(author, dict) or not isinstance(author.get('family'), str)
|
||||
or not clean(author['family']) or ('given' in author and not isinstance(author['given'], str))
|
||||
or author.get('sequence') != ('first' if position == 0 else 'additional')):
|
||||
raise ValueError('Incomplete registry author or sequence')
|
||||
name = clean(' '.join(x for x in (author.get('given'), author['family']) if x))
|
||||
if not name or '@' in name or name.casefold() == 'anonymous':
|
||||
raise ValueError('Unreviewed author identity')
|
||||
if not author.get('given'):
|
||||
flags.append({'kind': 'registry_single_name_field_not_split', 'author_position': position+1})
|
||||
names.append(name)
|
||||
papers.append({'original': original, 'receipt': receipt, 'title': clean(titles[0]), 'authors': names, 'review_flags': flags})
|
||||
if len(seen) != 4645 or len(papers) != 4582 or len(other) != 56 or {r['doi'] for r in nonpapers} != set(NONPAPERS):
|
||||
raise ValueError('Incomplete reviewed registry partition')
|
||||
return sorted(papers, key=lambda p: p['original']['DOI']), nonpapers, other
|
||||
|
||||
|
||||
def collect(out, *, snapshots):
|
||||
out = Path(out)
|
||||
if out.exists():
|
||||
raise ValueError('Output exists; inspect previous operation before retrying')
|
||||
out.mkdir(parents=True)
|
||||
try:
|
||||
manifest, files, items = load_snapshot(snapshots)
|
||||
papers, nonpapers, other = registry_papers(items)
|
||||
evidence_dir = out/'evidence'; evidence_dir.mkdir()
|
||||
for name, body in files.items():
|
||||
(evidence_dir/name).write_bytes(body)
|
||||
rows = []
|
||||
for paper in papers:
|
||||
original = paper['original']; receipt = paper['receipt']; doi = original['DOI']
|
||||
rows.append({'source': SOURCE, 'external_id': doi, 'url': original['URL'],
|
||||
'title': paper['title'], 'authors': paper['authors'], 'abstract': None,
|
||||
'identifiers': {'doi': doi}, 'submission_identifiers': [{'scheme': 'publication_doi', 'value': doi}],
|
||||
'venue': 'ICASSP', 'year': 2026, 'track': TRACK, 'status': 'accepted',
|
||||
'raw_decision': 'Publication registered in Crossref ICASSP 2026 proceedings; not an original signed decision.',
|
||||
'evidence_url': receipt['url'], 'observed_at': receipt['at'], 'tags': [],
|
||||
'metadata': {'registry_fields': original, 'review_flags': paper['review_flags'],
|
||||
'source_evidence': {'file': 'evidence/'+receipt['file'], 'sha256': receipt['sha256'], 'url': receipt['url']},
|
||||
'source_manifest': {'file': 'evidence/manifest.json', 'sha256': MANIFEST_SHA},
|
||||
'original_decision_signature_verified': False,
|
||||
'abstract_availability': 'Absent in frozen registry deposit; no abstract inferred or fused from program versions.',
|
||||
'author_transform': 'Whitespace normalization of given + family in registered order; single fields retained, not guessed or split; all original author fields retained.',
|
||||
'publication_dates': {k: original[k] for k in ('published', 'published-print', 'published-online') if k in original},
|
||||
'date_scope': 'Registered event starts May 3; conference website says May 4–8. Source values preserved without substitution.',
|
||||
'scope': 'Registered publication version only. Requires work/DOI/history review before import. No automatic program match, aliases, track/type or public-negative inference.'}})
|
||||
path = out/'icassp-crossref-registry-2026-unclassified.jsonl'
|
||||
raw = ''.join(json.dumps(r, ensure_ascii=False)+'\n' for r in rows).encode(); path.write_bytes(raw)
|
||||
file_manifest = {'source': SOURCE, 'parser_version': 1, 'venue': 'ICASSP', 'year': 2026, 'track': TRACK,
|
||||
'count': len(rows), 'file': str(path), 'file_sha256': digest(raw), 'list_url': manifest['pages'][0]['url'],
|
||||
'status': 'partial', 'missing_abstract_count': len(rows)}
|
||||
path.with_suffix('.manifest.json').write_text(json.dumps(file_manifest, indent=2)+'\n')
|
||||
report = {'status': 'collected_pending_identity_review', 'records': len(rows), 'files': [file_manifest],
|
||||
'filtered_registry_records': 4645, 'excluded_nonpaper_items': nonpapers, 'excluded_other_conference_dois': other,
|
||||
'missing_abstract_count': len(rows), 'single_name_author_fields': sum(len(p['review_flags']) for p in papers),
|
||||
'database_written': False, 'network_requests': 0, 'pdfs_downloaded': False, 'approved_for_import': 0,
|
||||
'public_rejected_availability': 'unknown', 'source_manifest_sha256': MANIFEST_SHA,
|
||||
'scope': 'Registry census, not completeness of program, abstracts, tracks, negative decisions or work identities. Official program has4589 titles;174 unmatched normalized title candidates remain separate source discrepancies, not rejection or withdrawal evidence.'}
|
||||
part = out/'collection-report.json.part'; part.write_text(json.dumps(report, ensure_ascii=False, indent=2)+'\n'); part.replace(out/'collection-report.json')
|
||||
return report
|
||||
except Exception as error:
|
||||
(out/'failed.json').write_text(json.dumps({'status': 'failed_not_complete', 'error_type': type(error).__name__, 'database_written': False})+'\n')
|
||||
raise
|
||||
|
||||
|
||||
def main(argv=None, *, prog=None):
|
||||
parser = argparse.ArgumentParser(prog=prog, description=__doc__)
|
||||
parser.add_argument('--snapshots', required=True)
|
||||
parser.add_argument('--out', required=True)
|
||||
args = parser.parse_args(argv)
|
||||
print(json.dumps(collect(args.out, snapshots=args.snapshots), ensure_ascii=False))
|
||||
@@ -1,191 +0,0 @@
|
||||
"""Frozen ICDM2026 in-person program, with explicit source track evidence."""
|
||||
import argparse
|
||||
from collections import Counter
|
||||
from datetime import datetime
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import re
|
||||
|
||||
from paper_atlas.io.html import Document, Node, clean
|
||||
|
||||
SOURCE = 'icdm_program'
|
||||
SNAPSHOT = 'remaining2026-official-leads-v1'
|
||||
MANIFEST_SHA = '0e13313d94e3bff17f071d3a1384f6ed83ece156239fe5bc4633cc7a34fb8e04'
|
||||
PROGRAM = 'https://icdm2026.neu.edu.cn/DetailedSessions/list.htm'
|
||||
PAGES = {
|
||||
'detailed-sessions': PROGRAM,
|
||||
'research-policy': 'https://icdm2026.neu.edu.cn/CallforResearchTrack/list.htm',
|
||||
'applied-policy': 'https://icdm2026.neu.edu.cn/CallforAppliedTrack/list.htm',
|
||||
}
|
||||
|
||||
|
||||
def digest(raw):
|
||||
return hashlib.sha256(raw).hexdigest()
|
||||
|
||||
|
||||
def one(items):
|
||||
if len(items) != 1:
|
||||
raise ValueError('Expected exactly one reviewed field')
|
||||
return items[0]
|
||||
|
||||
|
||||
def has_class(node, name):
|
||||
return name in node.attrs.get('class', '').split()
|
||||
|
||||
|
||||
def field(node, name):
|
||||
return clean(one([n for n in node.walk() if has_class(n, name)]).text())
|
||||
|
||||
|
||||
def load_snapshot(root):
|
||||
root = Path(root); folder = root/SNAPSHOT; manifest = folder/'manifest.json'
|
||||
if root.is_symlink() or folder.is_symlink() or manifest.is_symlink() or manifest.stat().st_size > 256*1024:
|
||||
raise ValueError('Unsafe source manifest')
|
||||
raw = manifest.read_bytes()
|
||||
if digest(raw) != MANIFEST_SHA:
|
||||
raise ValueError('Frozen manifest hash changed')
|
||||
data = json.loads(raw)
|
||||
if data['status'] != 'research_completed_not_coverage_approval' or data['year'] != 2026:
|
||||
raise ValueError('Wrong source edition or incomplete research run')
|
||||
receipts = [r for r in data['entries'] if r['venue'] == 'ICDM']
|
||||
if len(receipts) != 3 or {r['label'] for r in receipts} != PAGES.keys():
|
||||
raise ValueError('Incomplete ICDM source set')
|
||||
files = {'manifest.json': raw}; indexed = {}
|
||||
for receipt in receipts:
|
||||
filename = receipt['file']; path = folder/filename
|
||||
if Path(filename).name != filename or path.is_symlink() or path.stat().st_size > 8*1024**2:
|
||||
raise ValueError('Unsafe source file')
|
||||
body = path.read_bytes()
|
||||
if (receipt['url'] != PAGES[receipt['label']] or receipt['final_url'] != receipt['url']
|
||||
or receipt['http_status'] != 200 or receipt['bytes'] != len(body)
|
||||
or receipt['sha256'] != digest(body)
|
||||
or not receipt['content_type'].lower().startswith('text/html')
|
||||
or datetime.fromisoformat(receipt['at']).utcoffset() is None):
|
||||
raise ValueError('Source receipt/body mismatch')
|
||||
if filename in files:
|
||||
raise ValueError('Repeated source filename')
|
||||
files[filename] = body; indexed[receipt['label']] = receipt
|
||||
return indexed, files
|
||||
|
||||
|
||||
def parse_program(raw):
|
||||
doc = Document(raw.decode('utf-8'))
|
||||
main = one([n for n in doc.root.walk() if n.tag == 'main' and n.attrs.get('id') == 'session-details'])
|
||||
text = clean(main.text())
|
||||
if ('IEEE ICDM 2026' not in text or 'November 13–15, 2026' not in text
|
||||
or 'In-person session presentation list.' not in text or '34 sessions · 324 papers' not in text):
|
||||
raise ValueError('Wrong edition or unreviewed program scope')
|
||||
sessions = [n for n in main.walk() if n.tag == 'details' and has_class(n, 'sd-session')]
|
||||
expected = {f'L{i}' for i in range(1, 21)} | {f'S{i}' for i in range(1, 15)}
|
||||
if len(sessions) != 34 or {n.attrs.get('data-session-id') for n in sessions} != expected:
|
||||
raise ValueError('Incomplete or repeated session census')
|
||||
records = []; seen = set()
|
||||
for session in sessions:
|
||||
sid = session.attrs['data-session-id']; track = session.attrs.get('data-track')
|
||||
form = session.attrs.get('data-format')
|
||||
if (session.attrs.get('id') != sid or track not in ('research', 'applied')
|
||||
or form not in ('long', 'short')):
|
||||
raise ValueError('Invalid session ID, track or presentation label')
|
||||
label = 'Research Track' if track == 'research' else 'Applied Track'
|
||||
if field(session, 'sd-track') != label:
|
||||
raise ValueError('Visible track and source attribute disagree')
|
||||
count = re.fullmatch(r'(Long|Short) · ([1-9][0-9]*) papers', field(session, 'sd-format'))
|
||||
if count is None or count[1].lower() != form:
|
||||
raise ValueError('Visible presentation label disagrees')
|
||||
rows = [n for n in session.walk() if n.tag == 'tr' and 'data-paper-id' in n.attrs]
|
||||
if len(rows) != int(count[2]):
|
||||
raise ValueError('Session paper count changed')
|
||||
note = field(session, 'sd-table-note')
|
||||
if not note.startswith(f'{form.title()} Presentation ({len(rows)} papers) · '):
|
||||
raise ValueError('Unreviewed presentation-note semantics')
|
||||
context = {'id': sid, 'track_literal': track, 'presentation_literal': form,
|
||||
'title': field(session, 'sd-session-title'),
|
||||
'time_literal': field(session, 'sd-session-time'), 'room_literal': field(session, 'sd-room')}
|
||||
for row in rows:
|
||||
pid = row.attrs['data-paper-id']
|
||||
cells = [n for n in row.children if isinstance(n, Node) and n.tag in ('th', 'td')]
|
||||
if (not re.fullmatch(r'DM[1-9][0-9]*', pid) or pid in seen
|
||||
or row.attrs.get('id') != 'paper-'+pid or len(cells) != 4
|
||||
or [clean(n.text()) for n in cells] != [field(row, k) for k in
|
||||
('sd-time', 'sd-paper-id', 'sd-paper-title', 'sd-authors')]
|
||||
or field(row, 'sd-paper-id') != pid):
|
||||
raise ValueError('Repeated/malformed program paper identity or cells')
|
||||
seen.add(pid)
|
||||
title = field(row, 'sd-paper-title'); authors_literal = field(row, 'sd-authors')
|
||||
authors = [name.strip() for name in authors_literal.split(';')]
|
||||
if not title or any(not name for name in authors):
|
||||
raise ValueError('Missing program title or author')
|
||||
records.append({'paper_id_literal': pid, 'title': title, 'authors_literal': authors_literal,
|
||||
'source_reported_authors': authors, 'time_literal': field(row, 'sd-time'),
|
||||
'session': context.copy(), 'source_position': len(records)+1})
|
||||
if (len(records) != 324 or len([n for n in main.walk() if 'data-paper-id' in n.attrs]) != 324
|
||||
or Counter(r['session']['track_literal'] for r in records) != {'research': 241, 'applied': 83}
|
||||
or Counter(r['session']['presentation_literal'] for r in records) != {'long': 168, 'short': 156}):
|
||||
raise ValueError('Incomplete reviewed paper/track/presentation census')
|
||||
return records
|
||||
|
||||
|
||||
def collect(out, *, snapshots):
|
||||
out = Path(out)
|
||||
if out.exists():
|
||||
raise ValueError('Output exists; inspect previous operation before retrying')
|
||||
receipts, files = load_snapshot(snapshots)
|
||||
program = receipts['detailed-sessions']; observations = parse_program(files[program['file']])
|
||||
out.mkdir(parents=True)
|
||||
try:
|
||||
evidence = []; directory = out/'evidence'; directory.mkdir()
|
||||
for name, raw in files.items():
|
||||
rel = 'evidence/'+digest(raw)+Path(name).suffix; (out/rel).write_bytes(raw)
|
||||
evidence.append({'file': name, 'output_file': rel, 'sha256': digest(raw)})
|
||||
outputs = []
|
||||
for track in ('research', 'applied'):
|
||||
rows = []
|
||||
for item in observations:
|
||||
if item['session']['track_literal'] != track:
|
||||
continue
|
||||
pid = item['paper_id_literal']; url = PROGRAM+'#paper-'+pid
|
||||
rows.append({'source': SOURCE, 'external_id': '2026/'+pid, 'url': url,
|
||||
'title': item['title'], 'authors': item['source_reported_authors'], 'abstract': None,
|
||||
'venue': 'ICDM', 'year': 2026, 'track': track, 'status': 'accepted',
|
||||
'identifiers': {}, 'submission_identifiers': [], 'observed_at': program['at'],
|
||||
'evidence_url': url,
|
||||
'raw_decision': 'Listed in official ICDM2026 in-person '+track+' program; not an original signed decision or verified publisher record.',
|
||||
'tags': [{'namespace': SOURCE+':session_track', 'value': track},
|
||||
{'namespace': SOURCE+':presentation', 'value': item['session']['presentation_literal']}],
|
||||
'metadata': {'program_fields': item, 'program_receipt': program,
|
||||
'original_decision_signature_verified': False,
|
||||
'program_id_scope': 'Source program locator only; not asserted original submission ID or publication DOI.',
|
||||
'author_scope': 'Source-reported program names; no publisher completeness or person alias assertion.',
|
||||
'abstract_availability': 'No abstracts in this frozen program table.',
|
||||
'track_evidence': 'Explicit data-track attribute agrees with visible session label; not inferred from topic.',
|
||||
'paper_type': None,
|
||||
'scope': 'In-person program only; excludes other program sections. Long/short describe presentation format. Requires work/version and publication review before import.'}})
|
||||
path = out/f'icdm-program-2026-{track}.jsonl'
|
||||
payload = ''.join(json.dumps(row, ensure_ascii=False)+'\n' for row in rows).encode(); path.write_bytes(payload)
|
||||
manifest = {'source': SOURCE, 'parser_version': 1, 'venue': 'ICDM', 'year': 2026,
|
||||
'track': track, 'count': len(rows), 'file': str(path), 'file_sha256': digest(payload),
|
||||
'list_url': PROGRAM, 'status': 'partial', 'missing_abstract_count': len(rows),
|
||||
'source_expected_count': len(rows), 'scope': 'Frozen in-person program section, not all accepted/published papers.'}
|
||||
path.with_suffix('.manifest.json').write_text(json.dumps(manifest, indent=2)+'\n'); outputs.append(manifest)
|
||||
report = {'status': 'collected_pending_identity_review', 'records': 324, 'sessions': 34,
|
||||
'files': outputs, 'track_counts': {'research': 241, 'applied': 83},
|
||||
'presentation_counts': {'long': 168, 'short': 156}, 'missing_abstract_count': 324,
|
||||
'evidence': evidence, 'public_rejected_metadata': 'unknown_no_public_export_verified',
|
||||
'negative_policy_scope': 'Research triple-blind and applied single-blind concern review-time visibility; neither proves final public decision coverage.',
|
||||
'database_written': False, 'network_requests': 0, 'pdfs_downloaded': False,
|
||||
'scope': 'In-person program observations only. No work merge, inferred author alias, publication identity, original signed decision or final whole-database audit.'}
|
||||
temporary = out/'collection-report.json.part'; temporary.write_text(json.dumps(report, indent=2)+'\n')
|
||||
temporary.replace(out/'collection-report.json')
|
||||
return report
|
||||
except Exception as error:
|
||||
(out/'failed.json').write_text(json.dumps({'status': 'failed', 'error_type': type(error).__name__, 'database_written': False})+'\n')
|
||||
raise
|
||||
|
||||
|
||||
def main(argv=None, *, prog=None):
|
||||
parser = argparse.ArgumentParser(prog=prog, description=__doc__)
|
||||
parser.add_argument('--snapshots', required=True, type=Path)
|
||||
parser.add_argument('--out', required=True, type=Path)
|
||||
args = parser.parse_args(argv)
|
||||
print(json.dumps(collect(args.out, snapshots=args.snapshots), ensure_ascii=False))
|
||||
BIN
Binary file not shown.
BIN
Binary file not shown.
@@ -0,0 +1,95 @@
|
||||
import base64
|
||||
import copy
|
||||
import gzip
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import tempfile
|
||||
import unittest
|
||||
|
||||
from paper_atlas.collectors import icassp2026 as c
|
||||
|
||||
|
||||
class ICASSP2026Test(unittest.TestCase):
|
||||
@classmethod
|
||||
def setUpClass(cls):
|
||||
cls.fixture = json.loads(gzip.decompress((Path(__file__).parent/'fixtures/icassp2026-source.json.gz').read_bytes()))
|
||||
cls.files = {name: base64.b64decode(body) for name, body in cls.fixture['files'].items()}
|
||||
cls.items = []
|
||||
cls.manifest = json.loads(cls.files[c.SNAPSHOT+'/manifest.json'])
|
||||
for receipt in cls.manifest['pages']:
|
||||
cls.items.extend((r, receipt) for r in json.loads(cls.files[c.SNAPSHOT+'/'+receipt['file']])['message']['items'])
|
||||
|
||||
def materialize(self, root):
|
||||
for name, body in self.files.items():
|
||||
path = root/name; path.parent.mkdir(parents=True, exist_ok=True); path.write_bytes(body)
|
||||
|
||||
def test_full_census_matches_independent_gold_and_preserves_source(self):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root = Path(tmp); src = root/'src'; self.materialize(src)
|
||||
report = c.collect(root/'out', snapshots=src)
|
||||
self.assertEqual((report['records'],report['missing_abstract_count'],report['single_name_author_fields']), (4582,4582,23))
|
||||
self.assertEqual(len(report['excluded_nonpaper_items']),7); self.assertEqual(len(report['excluded_other_conference_dois']),56)
|
||||
self.assertFalse(report['database_written']); self.assertFalse(report['pdfs_downloaded']); self.assertEqual(report['network_requests'],0)
|
||||
self.assertEqual(report['approved_for_import'],0); self.assertEqual(report['public_rejected_availability'],'unknown')
|
||||
manifest, = report['files']; path = Path(manifest['file']); raw = path.read_bytes()
|
||||
self.assertEqual(hashlib.sha256(raw).hexdigest(),manifest['file_sha256']); self.assertEqual(manifest['status'],'partial')
|
||||
rows = [json.loads(l) for l in raw.splitlines()]
|
||||
actual = [{'doi':r['external_id'],'title':r['title'],'authors':r['authors']} for r in rows]
|
||||
gold = sorted(self.fixture['independent_gold'],key=lambda r:r['doi'])
|
||||
self.assertEqual(actual,gold)
|
||||
original = {r['DOI']:r for r,_ in self.items}
|
||||
evidence_hashes = {str(p.relative_to(root/'out')):hashlib.sha256(p.read_bytes()).hexdigest() for p in (root/'out/evidence').iterdir()}
|
||||
for r in rows:
|
||||
doi = r['external_id']; self.assertEqual(r['metadata']['registry_fields'],original[doi])
|
||||
self.assertEqual(r['identifiers'],{'doi':doi}); self.assertEqual(r['submission_identifiers'],[{'scheme':'publication_doi','value':doi}])
|
||||
self.assertEqual(r['track'],'proceedings_unclassified'); self.assertFalse(r['tags']); self.assertFalse(r['abstract'])
|
||||
self.assertFalse(r['metadata']['original_decision_signature_verified'])
|
||||
evidence = r['metadata']['source_evidence']
|
||||
self.assertEqual(evidence_hashes[evidence['file']],evidence['sha256'])
|
||||
self.assertIn('Fareedha',next(r for r in rows if r['external_id'].endswith('.11461474'))['authors'])
|
||||
with self.assertRaisesRegex(ValueError,'Output exists'):
|
||||
c.collect(root/'out',snapshots=src)
|
||||
|
||||
def test_wrong_conference_doi_date_and_unexpected_abstract_rejected(self):
|
||||
for kind in ('container','event','doi','date','author','sequence','abstract'):
|
||||
with self.subTest(kind=kind):
|
||||
items = copy.deepcopy(self.items); r = next(r for r,_ in items if r.get('author') and r['DOI'].startswith(c.PREFIX))
|
||||
if kind=='container': r['container-title']=['Foreign']
|
||||
if kind=='event': r['event']['name']='Other'
|
||||
if kind=='doi': r['DOI']='10.1109/foreign.2026.1'
|
||||
if kind=='date': r['published']['date-parts']=[[2025,5,3]]
|
||||
if kind=='author': r['author']=[]
|
||||
if kind=='sequence': r['author'][0]['sequence']='additional'
|
||||
if kind=='abstract': r['abstract']='new source version'
|
||||
with self.assertRaises(ValueError): c.registry_papers(items)
|
||||
|
||||
def test_nonpaper_exclusion_requires_exact_reviewed_evidence(self):
|
||||
for kind in ('title','page','author'):
|
||||
items = copy.deepcopy(self.items); r = next(r for r,_ in items if r['DOI'] in c.NONPAPERS)
|
||||
if kind=='title': r['title']=['A research paper']
|
||||
if kind=='page': r['page']='1-5'
|
||||
if kind=='author': r['author']=[{'family':'Smith'}]
|
||||
with self.assertRaisesRegex(ValueError,'nonpaper'): c.registry_papers(items)
|
||||
|
||||
def test_duplicate_and_incomplete_census_rejected(self):
|
||||
with self.assertRaisesRegex(ValueError,'repeated'): c.registry_papers(self.items+[self.items[0]])
|
||||
with self.assertRaisesRegex(ValueError,'partition'): c.registry_papers(self.items[:-1])
|
||||
|
||||
def test_corruption_and_partial_input_preserve_failure_without_success(self):
|
||||
for kind in ('manifest','body','missing'):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root=Path(tmp); src=root/'src'; self.materialize(src)
|
||||
path=src/c.SNAPSHOT/('manifest.json' if kind=='manifest' else 'page-002.json')
|
||||
if kind=='missing': path.unlink()
|
||||
else: path.write_bytes(path.read_bytes()+b' ')
|
||||
with self.assertRaises((ValueError,FileNotFoundError)): c.collect(root/'out',snapshots=src)
|
||||
self.assertTrue((root/'out/failed.json').exists()); self.assertFalse((root/'out/collection-report.json').exists())
|
||||
|
||||
def test_symlink_page_and_snapshot_rejected(self):
|
||||
for kind in ('page','directory'):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root=Path(tmp); src=root/'src'; self.materialize(src)
|
||||
path=src/c.SNAPSHOT/('page-001.json' if kind=='page' else '')
|
||||
renamed=path.with_name(path.name+'-original'); path.rename(renamed); path.symlink_to(renamed,target_is_directory=kind=='directory')
|
||||
with self.assertRaisesRegex(ValueError,'Unsafe'): c.collect(root/'out',snapshots=src)
|
||||
@@ -1,113 +0,0 @@
|
||||
import gzip
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import tempfile
|
||||
import unittest
|
||||
|
||||
from paper_atlas.collectors import icdm2026 as c
|
||||
|
||||
|
||||
class ICDM2026Tests(unittest.TestCase):
|
||||
@classmethod
|
||||
def setUpClass(cls):
|
||||
cls.fixture = json.loads(gzip.decompress((Path(__file__).parent/'fixtures/icdm2026-source.json.gz').read_bytes()))
|
||||
cls.raw = cls.fixture['files'][c.SNAPSHOT+'/icdm-detailed-sessions.html'].encode()
|
||||
cls.gold = cls.fixture['independent_inventory']
|
||||
|
||||
def snapshots(self, root):
|
||||
for name, text in self.fixture['files'].items():
|
||||
path = root/name; path.parent.mkdir(parents=True, exist_ok=True); path.write_bytes(text.encode())
|
||||
|
||||
def test_all_rows_match_separately_parsed_frozen_inventory(self):
|
||||
result = c.parse_program(self.raw)
|
||||
self.assertEqual(len(result), len(self.gold['entries']))
|
||||
for position, (row, gold) in enumerate(zip(result, self.gold['entries']), 1):
|
||||
for field in ('paper_id_literal', 'title', 'authors_literal', 'source_reported_authors', 'time_literal'):
|
||||
self.assertEqual(row[field], gold[field])
|
||||
self.assertEqual(row['source_position'], position)
|
||||
for field, value in gold['session'].items():
|
||||
self.assertEqual(row['session'][field], value)
|
||||
|
||||
def test_instantiable_collection_retains_scope_fields_and_source_bytes(self):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root = Path(tmp); self.snapshots(root/'src')
|
||||
report = c.collect(root/'out', snapshots=root/'src')
|
||||
self.assertEqual(report['track_counts'], self.gold['track_counts_literal'])
|
||||
self.assertEqual(report['presentation_counts'], self.gold['presentation_counts_literal'])
|
||||
self.assertEqual((report['records'], report['missing_abstract_count']), (324, 324))
|
||||
self.assertFalse(report['database_written']); self.assertEqual(report['network_requests'], 0)
|
||||
self.assertEqual(report['public_rejected_metadata'], 'unknown_no_public_export_verified')
|
||||
all_rows = []
|
||||
for manifest in report['files']:
|
||||
path = Path(manifest['file']); raw = path.read_bytes()
|
||||
self.assertEqual(hashlib.sha256(raw).hexdigest(), manifest['file_sha256'])
|
||||
self.assertEqual(manifest['status'], 'partial')
|
||||
rows = [json.loads(line) for line in raw.splitlines()]
|
||||
self.assertEqual(len(rows), manifest['missing_abstract_count'])
|
||||
for row in rows:
|
||||
self.assertEqual((row['venue'], row['year'], row['track']), ('ICDM', 2026, manifest['track']))
|
||||
self.assertIsNone(row['abstract']); self.assertIsNone(row['metadata']['paper_type'])
|
||||
self.assertEqual(row['identifiers'], {}); self.assertEqual(row['submission_identifiers'], [])
|
||||
self.assertFalse(row['metadata']['original_decision_signature_verified'])
|
||||
self.assertEqual(row['external_id'], '2026/'+row['metadata']['program_fields']['paper_id_literal'])
|
||||
self.assertTrue(row['url'].startswith(c.PROGRAM+'#paper-DM'))
|
||||
self.assertTrue(all(t['namespace'].startswith(c.SOURCE+':') for t in row['tags']))
|
||||
self.assertNotIn('doi', row['metadata']); self.assertNotIn('decision_date', row)
|
||||
all_rows.extend(rows)
|
||||
self.assertEqual(len({r['external_id'] for r in all_rows}), 324)
|
||||
for item in report['evidence']:
|
||||
raw = (root/'out'/item['output_file']).read_bytes()
|
||||
self.assertEqual(raw, self.fixture['files'][c.SNAPSHOT+'/'+item['file']].encode())
|
||||
self.assertTrue((root/'out/collection-report.json').is_file())
|
||||
self.assertFalse((root/'out/collection-report.json.part').exists())
|
||||
with self.assertRaisesRegex(ValueError, 'Output exists'):
|
||||
c.collect(root/'out', snapshots=root/'src')
|
||||
|
||||
def test_stale_or_different_conference_rejected(self):
|
||||
for old, new in [(b'IEEE ICDM 2026', b'IEEE ICDM 2025'),
|
||||
(b'In-person session presentation list.', b'Workshop presentation list.')]:
|
||||
with self.subTest(old=old), self.assertRaises(ValueError):
|
||||
c.parse_program(self.raw.replace(old, new))
|
||||
|
||||
def test_track_attribute_must_agree_with_visible_label(self):
|
||||
changed = self.raw.replace(b'data-track="research"', b'data-track="applied"', 1)
|
||||
with self.assertRaisesRegex(ValueError, 'track'):
|
||||
c.parse_program(changed)
|
||||
|
||||
def test_presentation_attribute_is_not_inferred_from_session_id(self):
|
||||
changed = self.raw.replace(b'data-format="long"', b'data-format="short"', 1)
|
||||
with self.assertRaisesRegex(ValueError, 'presentation'):
|
||||
c.parse_program(changed)
|
||||
|
||||
def test_repeated_paper_and_source_locator_disagreement_rejected(self):
|
||||
for old, new in [(b'DM1278', b'DM827'), (b'id="paper-DM827"', b'id="paper-DM99999"')]:
|
||||
with self.subTest(old=old), self.assertRaises(ValueError):
|
||||
c.parse_program(self.raw.replace(old, new))
|
||||
|
||||
def test_lost_session_or_changed_session_counts_rejected(self):
|
||||
for old, new in [(b'data-session-id="L1"', b'data-session-id="L2"'),
|
||||
(b'Long \xc2\xb7 7 papers', b'Long \xc2\xb7 6 papers')]:
|
||||
with self.subTest(old=old), self.assertRaises(ValueError):
|
||||
c.parse_program(self.raw.replace(old, new, 1))
|
||||
|
||||
def test_empty_author_is_not_silently_dropped(self):
|
||||
changed = self.raw.replace(b'Qishuang Fu; Andreas Deppeler;', b'Qishuang Fu;;', 1)
|
||||
with self.assertRaisesRegex(ValueError, 'author'):
|
||||
c.parse_program(changed)
|
||||
|
||||
def test_snapshot_manifest_and_body_corruption_rejected_before_output(self):
|
||||
for name in ('manifest.json', 'icdm-detailed-sessions.html', 'icdm-research-policy.html', 'icdm-applied-policy.html'):
|
||||
with self.subTest(name=name), tempfile.TemporaryDirectory() as tmp:
|
||||
root = Path(tmp); self.snapshots(root/'src'); path = root/'src'/c.SNAPSHOT/name
|
||||
path.write_bytes(path.read_bytes()+b' ')
|
||||
with self.assertRaises(ValueError):
|
||||
c.collect(root/'out', snapshots=root/'src')
|
||||
self.assertFalse((root/'out').exists())
|
||||
|
||||
def test_snapshot_source_symlink_rejected(self):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root = Path(tmp); self.snapshots(root/'src'); path = root/'src'/c.SNAPSHOT/'icdm-detailed-sessions.html'
|
||||
real = root/'real.html'; path.rename(real); path.symlink_to(real)
|
||||
with self.assertRaisesRegex(ValueError, 'Unsafe source'):
|
||||
c.collect(root/'out', snapshots=root/'src')
|
||||
Reference in New Issue
Block a user