Add compact CLI e2e fixtures and golden deposit XML

.gitignore

@@ -34,6 +34,7 @@ yarn-error.log*
 _build
 
 src/version.ts
+tests/fixtures/.tmp-deposit.xml
 
 .yalc
 yalc.lock

README.md

@@ -6,6 +6,8 @@
 
 Utilities for creating crossref.org deposit metadata from node or the command line.
 
+CLI e2e fixtures and golden XML: [`docs/e2e-fixtures.md`](./docs/e2e-fixtures.md).
+
 To use from the command line, use the `-g` to create a global install.
 
 ```

docs/e2e-fixtures.md

@@ -0,0 +1,65 @@
+# CLI end-to-end fixtures
+
+Regression fixtures for `crossref deposit` (and later `validate`). Kept **compact and owned** by this repo — shaped like SciPy proceedings papers, not wholesale copies of [scipy_proceedings/papers](https://github.com/scipy-conference/scipy_proceedings/tree/2025/papers).
+
+## Goals
+
+- Exercise real CLI → MyST load → deposit XML path
+- Capture **golden XML from `main`** for regression against refactors (e.g. monorepo split)
+- Stay small and maintainable (< ~100KB text)
+
+## Layout
+
+```
+tests/fixtures/
+  shared/
+    proceedings.yml          # SciPy-like venue / volume / editors (synthetic)
+  conference/
+    paper-a/                 # ORCID, affiliations, pages, abstract, DOI cites
+    paper-b/                 # equal_contributor, funding, subtitle
+  journal/
+    article/
+  preprint/
+    article/
+  dataset/
+    item/
+  golden/                    # Normalized XML baselines
+    conference.xml
+    journal.xml
+    preprint.xml
+    dataset.xml
+```
+
+## Coverage matrix
+
+| Fixture                          | `--type`     | What it covers                                                                                              |
+| -------------------------------- | ------------ | ----------------------------------------------------------------------------------------------------------- |
+| `conference/paper-a` + `paper-b` | `conference` | Multi-paper batch, venue/volume/editors, pages, abstract, ORCID, funding, equal contributors, DOI citations |
+| `journal/article`                | `journal`    | Journal title/DOI, volume/issue                                                                             |
+| `preprint/article`               | `preprint`   | Standalone posted content                                                                                   |
+| `dataset/item`                   | `dataset`    | Database venue + dataset record                                                                             |
+
+## Design choices
+
+- **From scratch** (not vendored SciPy trees): flatten `extends`, no images/templates, fake names/emails/ORCIDs.
+- **DOIs always present** in frontmatter so deposits are non-interactive (no DOI checkbox prompts).
+- **Stable batch id** via `--id` in tests; **normalize** `timestamp` (and any remaining UUIDs) before comparing to goldens.
+- Depositor flags use CLI defaults or explicit `--name` / `--email` / `--registrant`.
+
+## Running
+
+```bash
+npm test                  # unit + e2e (builds CLI for e2e)
+npm run test:unit         # unit only
+npm run test:e2e          # e2e only (builds CLI first)
+npm run test:e2e:record   # regenerates tests/fixtures/golden/*.xml
+```
+
+`test:e2e:record` should only be used intentionally (e.g. when deposit XML shape changes on purpose).
+
+## Out of scope (v1)
+
+- Inquirer / path-discovery flows
+- DOI generation UI
+- Submodule clone of full SciPy proceedings
+- Schema validation e2e (separate; needs schema bundles)

package.json

@@ -32,7 +32,10 @@
     "unlink": "npm uninstall -g crossref-utils;",
     "link": "npm run unlink; npm link;",
     "dev": "npm run copy:version && npm run link && esbuild src/cli/index.ts --bundle --outfile=dist/crossref.cjs --platform=node --external:fsevents --watch",
-    "test": "npm run copy:version && vitest run",
+    "test": "npm run copy:version && vitest run && npm run test:e2e",
+    "test:unit": "npm run copy:version && vitest run",
+    "test:e2e": "npm run build && npm run copy:version && vitest run --config vitest.e2e.config.ts",
+    "test:e2e:record": "npm run build && npm run copy:version && RECORD_GOLDEN=1 vitest run --config vitest.e2e.config.ts",
     "test:watch": "npm run copy:version && vitest watch",
     "lint": "eslint \"src/**/*.ts*\" -c ./.eslintrc.cjs",
     "lint:format": "prettier --check \"src/**/*.{ts,tsx,md}\"",

tests/cli.e2e.spec.ts

@@ -0,0 +1,134 @@
+import fs from 'node:fs';
+import path from 'node:path';
+import { spawnSync } from 'node:child_process';
+import { describe, test, expect, beforeAll } from 'vitest';
+
+const fixturesRoot = path.join(process.cwd(), 'tests/fixtures');
+const goldenRoot = path.join(fixturesRoot, 'golden');
+const cliBin = path.join(process.cwd(), 'dist/crossref.cjs');
+const repoRoot = process.cwd();
+
+const RECORD = process.env.RECORD_GOLDEN === '1';
+
+/** Strip nondeterministic deposit head fields for stable comparisons. */
+export function normalizeDepositXml(xml: string): string {
+  return xml
+    .replace(/<doi_batch_id>[^<]*<\/doi_batch_id>/g, '<doi_batch_id>FIXED_BATCH_ID</doi_batch_id>')
+    .replace(/<timestamp>[^<]*<\/timestamp>/g, '<timestamp>0</timestamp>')
+    .replace(/\r\n/g, '\n')
+    .trim();
+}
+
+function runDeposit(args: string[]): string {
+  const result = spawnSync(process.execPath, [cliBin, 'deposit', ...args], {
+    cwd: repoRoot,
+    encoding: 'utf8',
+    env: { ...process.env, NO_COLOR: '1' },
+  });
+  if (result.status !== 0) {
+    throw new Error(
+      `crossref deposit failed (${result.status}):\n${result.stdout}\n${result.stderr}`,
+    );
+  }
+  return result.stdout;
+}
+
+function depositToNormalizedXml(args: string[]): string {
+  const outFile = path.join(fixturesRoot, '.tmp-deposit.xml');
+  try {
+    runDeposit([...args, '--id', 'FIXED_BATCH_ID', '-o', outFile]);
+    const xml = fs.readFileSync(outFile, 'utf8');
+    return normalizeDepositXml(xml);
+  } finally {
+    if (fs.existsSync(outFile)) fs.unlinkSync(outFile);
+  }
+}
+
+function assertOrRecord(name: string, actual: string) {
+  const goldenPath = path.join(goldenRoot, name);
+  if (RECORD) {
+    fs.mkdirSync(goldenRoot, { recursive: true });
+    fs.writeFileSync(goldenPath, `${actual}\n`);
+    return;
+  }
+  if (!fs.existsSync(goldenPath)) {
+    throw new Error(`Missing golden ${goldenPath}. Run with RECORD_GOLDEN=1 to create baselines.`);
+  }
+  const expected = normalizeDepositXml(fs.readFileSync(goldenPath, 'utf8'));
+  expect(actual).toBe(expected);
+}
+
+describe('CLI e2e deposit fixtures', () => {
+  beforeAll(() => {
+    if (!fs.existsSync(cliBin)) {
+      throw new Error(`CLI not built: ${cliBin}. Run npm run build first.`);
+    }
+  });
+
+  test('conference multi-paper deposit', () => {
+    const paperA = path.join(fixturesRoot, 'conference/paper-a');
+    const paperB = path.join(fixturesRoot, 'conference/paper-b');
+    const actual = depositToNormalizedXml([
+      '--type',
+      'conference',
+      '--name',
+      'Fixture Depositor',
+      '--email',
+      'depositor@example.org',
+      paperA,
+      paperB,
+    ]);
+    assertOrRecord('conference.xml', actual);
+    expect(actual).toContain('conference_paper');
+    expect(actual).toContain('10.99999/fixture.paper-a');
+    expect(actual).toContain('10.99999/fixture.paper-b');
+  }, 120000);
+
+  test('journal deposit', () => {
+    const article = path.join(fixturesRoot, 'journal/article');
+    const actual = depositToNormalizedXml([
+      '--type',
+      'journal',
+      '--name',
+      'Fixture Depositor',
+      '--email',
+      'depositor@example.org',
+      article,
+    ]);
+    assertOrRecord('journal.xml', actual);
+    expect(actual).toContain('journal_article');
+    expect(actual).toContain('10.99999/fixture.journal-article');
+  }, 120000);
+
+  test('preprint deposit', () => {
+    const article = path.join(fixturesRoot, 'preprint/article');
+    const actual = depositToNormalizedXml([
+      '--type',
+      'preprint',
+      '--name',
+      'Fixture Depositor',
+      '--email',
+      'depositor@example.org',
+      article,
+    ]);
+    assertOrRecord('preprint.xml', actual);
+    expect(actual).toContain('posted_content');
+    expect(actual).toContain('10.99999/fixture.preprint');
+  }, 120000);
+
+  test('dataset deposit', () => {
+    const item = path.join(fixturesRoot, 'dataset/item');
+    const actual = depositToNormalizedXml([
+      '--type',
+      'dataset',
+      '--name',
+      'Fixture Depositor',
+      '--email',
+      'depositor@example.org',
+      item,
+    ]);
+    assertOrRecord('dataset.xml', actual);
+    expect(actual).toContain('dataset');
+    expect(actual).toContain('10.99999/fixture.dataset');
+  }, 120000);
+});

tests/fixtures/conference/paper-a/main.md

@@ -0,0 +1,10 @@
+---
+title: Compact fixtures for Crossref conference deposits
+abstract: |
+  This synthetic abstract exercises deposit metadata extraction for conference papers.
+  It references a well-known paper with a DOI [](doi:10.25080/issn.2575-9752).
+---
+
+# Introduction
+
+A short body paragraph with a citation to ensure DOI citations are collected [](doi:10.1038/nature14539).

tests/fixtures/conference/paper-a/myst.yml

@@ -0,0 +1,31 @@
+version: 1
+extends: ../../shared/proceedings.yml
+project:
+  title: Compact fixtures for Crossref conference deposits
+  subtitle: A short synthetic article
+  description: |
+    Synthetic fixture abstract used for CLI end-to-end regression tests.
+  first_page: 1
+  last_page: 8
+  doi: 10.99999/fixture.paper-a
+  date: 2025-07-10
+  authors:
+    - name: Ada Author
+      email: ada@example.org
+      orcid: 0000-0001-2345-6789
+      corresponding: true
+      affiliations:
+        - Example University
+    - name: Blake Writer
+      email: blake@example.org
+      orcid: 0000-0002-3456-7890
+      affiliations:
+        - Example Lab
+  affiliations:
+    - id: Example University
+      name: Example University
+      ror: https://ror.org/05ggc9x63
+    - id: Example Lab
+      name: Example Lab
+  toc:
+    - file: main.md

tests/fixtures/conference/paper-b/main.md

@@ -0,0 +1,9 @@
+---
+title: Second fixture paper with funding
+abstract: |
+  Synthetic abstract for funding and equal-contributor coverage in conference deposits.
+---
+
+# Notes
+
+Body text for paper B.

tests/fixtures/conference/paper-b/myst.yml

@@ -0,0 +1,38 @@
+version: 1
+extends: ../../shared/proceedings.yml
+project:
+  title: Second fixture paper with funding
+  subtitle: Equal contributors and awards
+  description: Second synthetic article for multi-paper conference deposits.
+  first_page: 9
+  last_page: 12
+  doi: 10.99999/fixture.paper-b
+  date: 2025-07-10
+  authors:
+    - name: Casey Coauthor
+      email: casey@example.org
+      orcid: 0000-0003-4567-8901
+      equal_contributor: true
+      affiliations:
+        - Example Institute
+    - name: Dana Coauthor
+      email: dana@example.org
+      orcid: 0000-0004-5678-9012
+      equal_contributor: true
+      affiliations:
+        - Example Institute
+  affiliations:
+    - id: Example Institute
+      name: Example Institute
+      ror: https://ror.org/02mhbdp94
+    - id: Example Fund
+      name: Example Fund
+      institution: Example Funding Agency
+  funding:
+    - statement: Supported by Example Fund.
+      awards:
+        - id: EF-2025-001
+          sources:
+            - Example Fund
+  toc:
+    - file: main.md

tests/fixtures/dataset/item/main.md

@@ -0,0 +1,9 @@
+---
+title: Compact dataset fixture
+abstract: |
+  Synthetic dataset description used as deposit abstract/description.
+---
+
+# Data
+
+Dataset fixture notes.

tests/fixtures/dataset/item/myst.yml

@@ -0,0 +1,20 @@
+version: 1
+project:
+  title: Compact dataset fixture
+  description: Synthetic dataset record for CLI e2e tests.
+  doi: 10.99999/fixture.dataset
+  date: 2025-02-01
+  zenodo: https://zenodo.org/records/9999999
+  venue:
+    title: Example Research Data Repository
+    doi: 10.99999/example-data
+  authors:
+    - name: Sam Scientist
+      email: sam@example.org
+      affiliations:
+        - Example Data Lab
+  affiliations:
+    - id: Example Data Lab
+      name: Example Data Lab
+  toc:
+    - file: main.md

tests/fixtures/golden/conference.xml

@@ -0,0 +1 @@
+<doi_batch xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" version="5.3.1" xmlns="http://www.crossref.org/schema/5.3.1" xmlns:jats="http://www.ncbi.nlm.nih.gov/JATS1" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:fr="http://www.crossref.org/fundref.xsd" xmlns:ai="http://www.crossref.org/AccessIndicators.xsd" xsi:schemaLocation="http://www.crossref.org/schema/5.3.1 http://www.crossref.org/schemas/crossref5.3.1.xsd"><head><doi_batch_id>FIXED_BATCH_ID</doi_batch_id><timestamp>0</timestamp><depositor><depositor_name>Fixture Depositor</depositor_name><email_address>depositor@example.org</email_address></depositor><registrant>Crossref</registrant></head><body><conference><contributors><person_name sequence="first" contributor_role="editor"><given_name>Alex</given_name><surname>Editor</surname><affiliations><institution><institution_name>Example University</institution_name><institution_id type="ror">https://ror.org/05ggc9x63</institution_id></institution></affiliations><alt-name><string-name>Alex Editor</string-name></alt-name></person_name><person_name sequence="additional" contributor_role="editor"><given_name>Blair</given_name><surname>Chair</surname><affiliations><institution><institution_name>Example Lab</institution_name></institution></affiliations><alt-name><string-name>Blair Chair</string-name></alt-name></person_name></contributors><event_metadata><conference_name>Example Science Conference, 2025</conference_name><conference_acronym>ExSci</conference_acronym><conference_number>1st</conference_number><conference_location>Example City</conference_location><conference_date>July 1 - July 5, 2025</conference_date></event_metadata><proceedings_series_metadata><series_metadata><titles><title>Proceedings of the Example Science Conference</title><original_language_title>Proceedings of the Example Science Conference</original_language_title></titles><issn>0000-0000</issn><doi_data><doi>10.99999/issn.0000-0000</doi><resource>https://doi.curvenote.com/10.99999/issn.0000-0000</resource></doi_data></series_metadata><proceedings_title>Proceedings of the 1st Example Science Conference</proceedings_title><proceedings_subject>Scientific Computing</proceedings_subject><publisher><publisher_name>Example Proceedings Press</publisher_name></publisher><publication_date media_type="online"><month>07</month><day>10</day><year>2025</year></publication_date><noisbn reason="simple_series"></noisbn><doi_data><doi>10.99999/proc.2025</doi><resource>https://doi.curvenote.com/10.99999/proc.2025</resource></doi_data></proceedings_series_metadata><conference_paper><contributors><person_name sequence="first" contributor_role="author"><given_name>Ada</given_name><surname>Author</surname><affiliations><institution><institution_name>Example University</institution_name><institution_id type="ror">https://ror.org/05ggc9x63</institution_id></institution></affiliations><ORCID>https://orcid.org/0000-0001-2345-6789</ORCID><alt-name><string-name>Ada Author</string-name></alt-name></person_name><person_name sequence="additional" contributor_role="author"><given_name>Blake</given_name><surname>Writer</surname><affiliations><institution><institution_name>Example Lab</institution_name></institution></affiliations><ORCID>https://orcid.org/0000-0002-3456-7890</ORCID><alt-name><string-name>Blake Writer</string-name></alt-name></person_name></contributors><titles><title>Compact fixtures for Crossref conference deposits</title><subtitle>A short synthetic article</subtitle></titles><jats:abstract><jats:p>Synthetic fixture abstract used for CLI end-to-end regression tests.</jats:p></jats:abstract><publication_date media_type="online"><month>07</month><day>10</day><year>2025</year></publication_date><pages><first_page>1</first_page><last_page>8</last_page></pages><ai:program name="AccessIndicators"><ai:free_to_read></ai:free_to_read><ai:license_ref applies_to="vor">https://creativecommons.org/licenses/by/4.0/</ai:license_ref></ai:program><doi_data><doi>10.99999/fixture.paper-a</doi><resource content_version="vor">https://doi.curvenote.com/10.99999/fixture.paper-a</resource></doi_data><citation_list><citation key="LeCun_2015"><doi>10.1038/nature14539</doi></citation></citation_list></conference_paper><conference_paper><contributors><person_name sequence="first" contributor_role="author"><given_name>Casey</given_name><surname>Coauthor</surname><affiliations><institution><institution_name>Example Institute</institution_name><institution_id type="ror">https://ror.org/02mhbdp94</institution_id></institution></affiliations><ORCID>https://orcid.org/0000-0003-4567-8901</ORCID><alt-name><string-name>Casey Coauthor</string-name></alt-name></person_name><person_name sequence="first" contributor_role="author"><given_name>Dana</given_name><surname>Coauthor</surname><affiliations><institution><institution_name>Example Institute</institution_name><institution_id type="ror">https://ror.org/02mhbdp94</institution_id></institution></affiliations><ORCID>https://orcid.org/0000-0004-5678-9012</ORCID><alt-name><string-name>Dana Coauthor</string-name></alt-name></person_name></contributors><titles><title>Second fixture paper with funding</title><subtitle>Equal contributors and awards</subtitle></titles><jats:abstract><jats:p>Second synthetic article for multi-paper conference deposits.</jats:p></jats:abstract><publication_date media_type="online"><month>07</month><day>10</day><year>2025</year></publication_date><pages><first_page>9</first_page><last_page>12</last_page></pages><ai:program name="AccessIndicators"><ai:free_to_read></ai:free_to_read><ai:license_ref applies_to="vor">https://creativecommons.org/licenses/by/4.0/</ai:license_ref></ai:program><doi_data><doi>10.99999/fixture.paper-b</doi><resource content_version="vor">https://doi.curvenote.com/10.99999/fixture.paper-b</resource></doi_data></conference_paper></conference></body></doi_batch>

tests/fixtures/golden/dataset.xml

@@ -0,0 +1 @@
+<doi_batch xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" version="5.3.1" xmlns="http://www.crossref.org/schema/5.3.1" xmlns:jats="http://www.ncbi.nlm.nih.gov/JATS1" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:fr="http://www.crossref.org/fundref.xsd" xmlns:ai="http://www.crossref.org/AccessIndicators.xsd" xsi:schemaLocation="http://www.crossref.org/schema/5.3.1 http://www.crossref.org/schemas/crossref5.3.1.xsd"><head><doi_batch_id>FIXED_BATCH_ID</doi_batch_id><timestamp>0</timestamp><depositor><depositor_name>Fixture Depositor</depositor_name><email_address>depositor@example.org</email_address></depositor><registrant>Crossref</registrant></head><body><database><database_metadata language="en"><titles><title>Example Research Data Repository</title></titles></database_metadata><dataset dataset_type="other"><contributors><person_name sequence="first" contributor_role="author"><given_name>Sam</given_name><surname>Scientist</surname><affiliations><institution><institution_name>Example Data Lab</institution_name></institution></affiliations><alt-name><string-name>Sam Scientist</string-name></alt-name></person_name></contributors><titles><title>Compact dataset fixture</title></titles><database_date><creation_date media_type="online"><month>02</month><day>01</day><year>2025</year></creation_date></database_date><description>Synthetic dataset record for CLI e2e tests.</description><program name="relations" xmlns="http://www.crossref.org/relations.xsd"><related_item><inter_work_relation relationship-type="isPartOf" identifier-type="doi">10.99999/example-data</inter_work_relation></related_item></program><doi_data><doi>10.99999/fixture.dataset</doi><resource content_version="vor">https://zenodo.org/records/9999999</resource></doi_data></dataset></database></body></doi_batch>