starbuck 0.2.0__tar.gz

starbuck-0.2.0/.github/workflows/release.yml

@@ -0,0 +1,35 @@
+# Publishes to PyPI when the version in pyproject.toml is not on PyPI yet, then tags
+# the commit (vX.Y.Z). Runs on pushes to main that change pyproject.toml, on version
+# tags, and by hand. Needs a trusted publisher on PyPI: owner tiagojct, repository
+# starbuck, workflow release.yml, environment pypi.
+name: release
+on:
+  push:
+    branches: [main]
+    paths: [pyproject.toml]
+    tags: ["v*"]
+  workflow_dispatch:
+jobs:
+  pypi:
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      contents: write
+      id-token: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v6
+      - id: version
+        run: |
+          v=$(python3 -c "import tomllib; print(tomllib.load(open('pyproject.toml','rb'))['project']['version'])")
+          echo "version=$v" >> "$GITHUB_OUTPUT"
+          if curl -sf "https://pypi.org/pypi/starbuck/$v/json" > /dev/null; then
+            echo "published=true" >> "$GITHUB_OUTPUT"
+            echo "starbuck $v is already on PyPI; nothing to publish."
+          fi
+      - if: steps.version.outputs.published != 'true'
+        run: uv build && uv publish --trusted-publishing always
+      - if: steps.version.outputs.published != 'true'
+        run: |
+          v=${{ steps.version.outputs.version }}
+          git ls-remote --exit-code --tags origin "refs/tags/v$v" > /dev/null || (git tag "v$v" && git push origin "v$v")

starbuck-0.2.0/.github/workflows/tests.yml

@@ -0,0 +1,16 @@
+name: tests
+on:
+  push:
+  pull_request:
+jobs:
+  test:
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v6
+      - run: uv sync
+      - run: uv run pytest -q

starbuck-0.2.0/.gitignore

@@ -0,0 +1,9 @@
+.venv/
+__pycache__/
+*.pyc
+.pytest_cache/
+dist/
+.DS_Store
+_starbuck/
+validation/.cache/
+PLAN.md

starbuck-0.2.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Tiago Jacinto
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

starbuck-0.2.0/PKG-INFO

@@ -0,0 +1,277 @@
+Metadata-Version: 2.5
+Name: starbuck
+Version: 0.2.0
+Summary: Reference-integrity checks for manuscripts: do the cited works exist, match their citations, and still stand?
+Project-URL: Repository, https://github.com/tiagojct/starbuck
+Project-URL: Issues, https://github.com/tiagojct/starbuck/issues
+Author: Tiago Jacinto
+License-Expression: MIT
+License-File: LICENSE
+Keywords: citations,crossref,mcp,pubmed,quarto,references,research integrity,retractions
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Education
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.11
+Requires-Dist: httpx>=0.27
+Requires-Dist: mcp<3,>=2.2
+Requires-Dist: pyyaml>=6
+Description-Content-Type: text/markdown
+
+# Starbuck
+
+Reference-integrity checks for manuscripts. Starbuck reads a Markdown or Quarto
+manuscript with its bibliography and checks each cited reference against public
+scholarly records. It writes a Quarto report that renders to HTML or Word.
+
+> *"I will have no man in my boat," said Starbuck, "who is not afraid of a whale."*
+> Herman Melville, *Moby-Dick*, chapter 26
+
+## What it checks
+
+| Level | Question | Sources |
+|---|---|---|
+| 1. Exists | Does the DOI, PMID, arXiv ID or ISBN resolve? Without an identifier, can the work be found? | Crossref, DataCite, doi.org, PubMed, arXiv, Open Library, Crossref search |
+| 2. Matches | Do the cited title, first author and year agree with the record? | The record from level 1 |
+| 3. Stands | Is the work retracted, under an expression of concern or corrected? Is it a notice itself? Was a cited preprint published? | Crossref (with Retraction Watch data), PubMed, OpenAlex, arXiv |
+| 4. Supports (optional) | Does the source support the sentence that cites it? | Europe PMC open-access full text or the abstract (PubMed, Europe PMC, Crossref, OpenAlex); a language model judges |
+
+Each reference gets one result:
+
+| Result | Meaning |
+|---|---|
+| Fail | The identifier does not exist, belongs to a different work, two identifiers disagree, or the work was retracted. |
+| Check | A person should look: a field differs, an expression of concern, a possible match only, an unreachable web page. |
+| Note | Information that needs no change in most cases: a correction, a published version of a preprint, a DOI found by search. |
+| Pass | Nothing found. |
+| Not checked | A service did not answer. Run the check again later. |
+
+The report also lists citations without a bibliography entry, entries that
+the text does not cite, and sentences that state a finding without a citation.
+A sentence is listed when it has at least 50 characters, cites nothing, and
+has a number with a unit or a percentage, an effect measure (OR, HR, RR, CI)
+or a claim word such as found, showed, increased, reduced, associated with,
+risk or prevalence. Headings, tables, figures, captions, code, the reference
+list and sections headed Methods or Results are left out: the authors' own
+methods and data need no citation. The rules are simple and English only, so
+the list is for a person to read; it never makes a reference Fail or Check.
+The JSON keeps the first 50 sentences under `uncited_sentences` (the key
+`uncited` lists the bibliography entries that are not cited).
+
+Level 4 adds a verdict for each citing sentence: Supported, Partly supported,
+Not supported or Cannot assess. Level 4 never makes a reference Fail: Not
+supported is Check and Partly supported is Note, so a person decides. See
+[Level 4](#level-4-claim-support).
+
+## Install
+
+Starbuck needs Python 3.11 or later and [uv](https://docs.astral.sh/uv/).
+For HTML and Word reports, install [Quarto](https://quarto.org). If Quarto is
+not installed, Starbuck uses Pandoc when it is available.
+
+1. Install Starbuck:
+
+   ```sh
+   uv tool install starbuck
+   ```
+
+2. Set a contact address. The services give faster, more reliable access to
+   requests that identify their sender:
+
+   ```sh
+   export STARBUCK_EMAIL=you@example.org
+   ```
+
+3. Check the installation:
+
+   ```sh
+   starbuck --version
+   ```
+
+## Use
+
+Check a manuscript. The bibliography comes from the `bibliography:` field in the
+YAML header:
+
+```sh
+starbuck check paper.qmd
+```
+
+Starbuck writes the report to a folder named `_starbuck` next to the manuscript.
+Quarto ignores folders that start with an underscore, so the report does not
+become part of a Quarto project.
+
+More options:
+
+```sh
+starbuck check paper.qmd --to html,docx      # HTML and Word
+starbuck check paper.md --bib refs.bib       # bibliography not in the YAML header
+starbuck check paper.qmd --all-entries       # also check entries that are not cited
+starbuck check paper.qmd --out reports/      # another report folder
+starbuck ids 10.1183/09031936.00080312 arXiv:1706.03762
+starbuck check paper.qmd --claims            # also level 4 (see below)
+```
+
+To check a Word manuscript, convert it to Markdown first:
+
+```sh
+quarto pandoc paper.docx -o paper.md
+```
+
+### Input
+
+Starbuck reads two citation styles:
+
+- Citation keys: Pandoc citations such as `[@key]`, `[see @key, p. 3; @other]`
+  and `@key` in running text. The bibliography can be BibTeX or BibLaTeX
+  (`.bib`), CSL JSON (`.json`) or CSL YAML (`.yaml`), or `references:` in the
+  YAML header.
+- Numbered references: `[1]`, `[2, 5]`, `[3-4]` in the text, with a numbered list
+  under a heading such as References or Sources. AI research agents often write
+  this format.
+
+### Output
+
+| File | Contents |
+|---|---|
+| `<name>-references.qmd` | The report. Edit it or render it again with Quarto. |
+| `<name>-references.html` | The report as one self-contained web page. |
+| `<name>-references.docx` | The report for Word, with `--to docx`. |
+| `<name>-references.json` | Every result, finding and record, for other tools. |
+| `<name>-claims.json` | Level 4 only: passages, source texts and the model's answers. |
+
+The report starts with a summary, then the references that need attention, each
+with the reason, the cited and the recorded metadata side by side, the sentence
+that cites it, and a suggested action. A section at the end states the rules and
+the services used.
+
+### Exit codes
+
+| Code | Meaning |
+|---|---|
+| 0 | No reference failed. |
+| 1 | At least one reference failed, or a cited key has no entry. |
+| 2 | The check could not run (for example, no citations found). |
+| 3 | No reference failed, but some checks did not run. |
+
+## Level 4: claim support
+
+For each sentence that cites a source, Starbuck takes the best text of that
+source: a local text file you give, open-access full text from Europe PMC, or
+otherwise the abstract. It ranks the passages of that text against the
+sentence (BM25) and gives the best five to a language model. The model answers
+Supported, Partly supported, Not supported or Cannot assess, and quotes the
+passage it relies on. Starbuck then checks that the quotation appears word for
+word in the source text. A quotation that is not there is rejected, and the
+verdict becomes Cannot assess. The report states for each verdict whether it
+rests on the full text or on the abstract only.
+
+The report also gives two scores over the judged citations (Cannot assess is
+left out). Citation recall: the share of citing sentences with at least one
+citation judged Supported or Partly supported. Citation precision: the share
+of citations judged Supported or Partly supported. A citation judged Not
+supported in a sentence that another of its sources supports gets a Note
+(overcitation): it adds no support. The idea comes from ScholarQABench
+(OpenScholar).
+
+1. Set the model. Any OpenAI-compatible endpoint works (a hosted provider, or a
+   local server such as Ollama):
+
+   ```sh
+   export STARBUCK_JUDGE_URL=https://api.example.org/v1
+   export STARBUCK_JUDGE_MODEL=model-name
+   export STARBUCK_JUDGE_KEY=...        # if the endpoint needs a key
+   ```
+
+2. Run the check with `--claims`:
+
+   ```sh
+   starbuck check paper.qmd --claims
+   starbuck check paper.qmd --claims --text smith2020=smith2020.txt   # full text you have
+   ```
+
+Without `--claims`, or without the model settings, level 4 does not run and the
+report says so. Level 4 sends the citing sentences and the source passages to
+the model's provider. The file `<name>-claims.json` in `_starbuck` keeps the
+passages, the source texts and the model's answers.
+
+A language model can be wrong. Read the source before you change the text.
+
+## Settings
+
+| Variable | Purpose |
+|---|---|
+| `STARBUCK_EMAIL` | Contact address for the services. `ZOTERO_CONTACT_EMAIL` also works. |
+| `NCBI_API_KEY` | Higher request rate for PubMed. |
+| `OPENALEX_API_KEY` | OpenAlex API key. |
+| `QUARTO_PATH` | Path to Quarto when it is not on the PATH. |
+| `STARBUCK_JUDGE_URL`, `STARBUCK_JUDGE_MODEL`, `STARBUCK_JUDGE_KEY` | Level 4 model (OpenAI-compatible endpoint). |
+
+## Use from an agent (MCP)
+
+`starbuck-mcp` is an MCP server with four tools:
+
+- `check_manuscript`: checks a manuscript and writes the report.
+- `check_references`: checks references given directly (an identifier, citation
+  details, or both). An agent can use it to check the sources of a text it wrote.
+- `prepare_claims`: level 4, step 1. Checks the references and returns each
+  citing sentence with the best passages of its source. A local full text can
+  be given per citation key.
+- `record_claims`: level 4, step 2. Takes the agent's verdicts, checks the
+  quoted passages and adds level 4 to the report.
+
+Inside an agent, the agent's own model judges, so no `STARBUCK_JUDGE_*`
+settings are needed.
+
+In [Sub-Sub](https://github.com/tiagojct/subsub), turn on reference checks in
+`subsub init` or with the switch in the web view; Sub-Sub then runs Starbuck as
+its `verify` server.
+
+Example configuration for an MCP client:
+
+```json
+{
+  "mcpServers": {
+    "starbuck": {
+      "command": "uvx",
+      "args": ["--from", "starbuck", "starbuck-mcp"],
+      "env": { "STARBUCK_EMAIL": "you@example.org" }
+    }
+  }
+}
+```
+
+## Privacy
+
+Starbuck sends identifiers and reference details (title, authors, year, or the
+reference as written) to the services listed above, and it opens cited web
+pages. Levels 1 to 3 do not send the manuscript text. Level 4 (only with
+`--claims`) sends the citing sentences and source passages to the model you
+set. Starbuck collects no usage data.
+
+## Demo
+
+`examples/demo.qmd` cites real works, each set up to show one kind of result:
+a correct reference, a wrong year, a DOI that belongs to another paper, a DOI
+that does not exist, a retracted paper, a reference without a DOI, an arXiv
+preprint and a citation without an entry.
+
+```sh
+starbuck check examples/demo.qmd --to html,docx
+```
+
+## Development
+
+```sh
+uv sync
+uv run pytest -q
+```
+
+The tests use canned service responses and do not need the network.
+
+## License
+
+[MIT](LICENSE) © Tiago Jacinto

starbuck-0.2.0/README.md

@@ -0,0 +1,254 @@
+# Starbuck
+
+Reference-integrity checks for manuscripts. Starbuck reads a Markdown or Quarto
+manuscript with its bibliography and checks each cited reference against public
+scholarly records. It writes a Quarto report that renders to HTML or Word.
+
+> *"I will have no man in my boat," said Starbuck, "who is not afraid of a whale."*
+> Herman Melville, *Moby-Dick*, chapter 26
+
+## What it checks
+
+| Level | Question | Sources |
+|---|---|---|
+| 1. Exists | Does the DOI, PMID, arXiv ID or ISBN resolve? Without an identifier, can the work be found? | Crossref, DataCite, doi.org, PubMed, arXiv, Open Library, Crossref search |
+| 2. Matches | Do the cited title, first author and year agree with the record? | The record from level 1 |
+| 3. Stands | Is the work retracted, under an expression of concern or corrected? Is it a notice itself? Was a cited preprint published? | Crossref (with Retraction Watch data), PubMed, OpenAlex, arXiv |
+| 4. Supports (optional) | Does the source support the sentence that cites it? | Europe PMC open-access full text or the abstract (PubMed, Europe PMC, Crossref, OpenAlex); a language model judges |
+
+Each reference gets one result:
+
+| Result | Meaning |
+|---|---|
+| Fail | The identifier does not exist, belongs to a different work, two identifiers disagree, or the work was retracted. |
+| Check | A person should look: a field differs, an expression of concern, a possible match only, an unreachable web page. |
+| Note | Information that needs no change in most cases: a correction, a published version of a preprint, a DOI found by search. |
+| Pass | Nothing found. |
+| Not checked | A service did not answer. Run the check again later. |
+
+The report also lists citations without a bibliography entry, entries that
+the text does not cite, and sentences that state a finding without a citation.
+A sentence is listed when it has at least 50 characters, cites nothing, and
+has a number with a unit or a percentage, an effect measure (OR, HR, RR, CI)
+or a claim word such as found, showed, increased, reduced, associated with,
+risk or prevalence. Headings, tables, figures, captions, code, the reference
+list and sections headed Methods or Results are left out: the authors' own
+methods and data need no citation. The rules are simple and English only, so
+the list is for a person to read; it never makes a reference Fail or Check.
+The JSON keeps the first 50 sentences under `uncited_sentences` (the key
+`uncited` lists the bibliography entries that are not cited).
+
+Level 4 adds a verdict for each citing sentence: Supported, Partly supported,
+Not supported or Cannot assess. Level 4 never makes a reference Fail: Not
+supported is Check and Partly supported is Note, so a person decides. See
+[Level 4](#level-4-claim-support).
+
+## Install
+
+Starbuck needs Python 3.11 or later and [uv](https://docs.astral.sh/uv/).
+For HTML and Word reports, install [Quarto](https://quarto.org). If Quarto is
+not installed, Starbuck uses Pandoc when it is available.
+
+1. Install Starbuck:
+
+   ```sh
+   uv tool install starbuck
+   ```
+
+2. Set a contact address. The services give faster, more reliable access to
+   requests that identify their sender:
+
+   ```sh
+   export STARBUCK_EMAIL=you@example.org
+   ```
+
+3. Check the installation:
+
+   ```sh
+   starbuck --version
+   ```
+
+## Use
+
+Check a manuscript. The bibliography comes from the `bibliography:` field in the
+YAML header:
+
+```sh
+starbuck check paper.qmd
+```
+
+Starbuck writes the report to a folder named `_starbuck` next to the manuscript.
+Quarto ignores folders that start with an underscore, so the report does not
+become part of a Quarto project.
+
+More options:
+
+```sh
+starbuck check paper.qmd --to html,docx      # HTML and Word
+starbuck check paper.md --bib refs.bib       # bibliography not in the YAML header
+starbuck check paper.qmd --all-entries       # also check entries that are not cited
+starbuck check paper.qmd --out reports/      # another report folder
+starbuck ids 10.1183/09031936.00080312 arXiv:1706.03762
+starbuck check paper.qmd --claims            # also level 4 (see below)
+```
+
+To check a Word manuscript, convert it to Markdown first:
+
+```sh
+quarto pandoc paper.docx -o paper.md
+```
+
+### Input
+
+Starbuck reads two citation styles:
+
+- Citation keys: Pandoc citations such as `[@key]`, `[see @key, p. 3; @other]`
+  and `@key` in running text. The bibliography can be BibTeX or BibLaTeX
+  (`.bib`), CSL JSON (`.json`) or CSL YAML (`.yaml`), or `references:` in the
+  YAML header.
+- Numbered references: `[1]`, `[2, 5]`, `[3-4]` in the text, with a numbered list
+  under a heading such as References or Sources. AI research agents often write
+  this format.
+
+### Output
+
+| File | Contents |
+|---|---|
+| `<name>-references.qmd` | The report. Edit it or render it again with Quarto. |
+| `<name>-references.html` | The report as one self-contained web page. |
+| `<name>-references.docx` | The report for Word, with `--to docx`. |
+| `<name>-references.json` | Every result, finding and record, for other tools. |
+| `<name>-claims.json` | Level 4 only: passages, source texts and the model's answers. |
+
+The report starts with a summary, then the references that need attention, each
+with the reason, the cited and the recorded metadata side by side, the sentence
+that cites it, and a suggested action. A section at the end states the rules and
+the services used.
+
+### Exit codes
+
+| Code | Meaning |
+|---|---|
+| 0 | No reference failed. |
+| 1 | At least one reference failed, or a cited key has no entry. |
+| 2 | The check could not run (for example, no citations found). |
+| 3 | No reference failed, but some checks did not run. |
+
+## Level 4: claim support
+
+For each sentence that cites a source, Starbuck takes the best text of that
+source: a local text file you give, open-access full text from Europe PMC, or
+otherwise the abstract. It ranks the passages of that text against the
+sentence (BM25) and gives the best five to a language model. The model answers
+Supported, Partly supported, Not supported or Cannot assess, and quotes the
+passage it relies on. Starbuck then checks that the quotation appears word for
+word in the source text. A quotation that is not there is rejected, and the
+verdict becomes Cannot assess. The report states for each verdict whether it
+rests on the full text or on the abstract only.
+
+The report also gives two scores over the judged citations (Cannot assess is
+left out). Citation recall: the share of citing sentences with at least one
+citation judged Supported or Partly supported. Citation precision: the share
+of citations judged Supported or Partly supported. A citation judged Not
+supported in a sentence that another of its sources supports gets a Note
+(overcitation): it adds no support. The idea comes from ScholarQABench
+(OpenScholar).
+
+1. Set the model. Any OpenAI-compatible endpoint works (a hosted provider, or a
+   local server such as Ollama):
+
+   ```sh
+   export STARBUCK_JUDGE_URL=https://api.example.org/v1
+   export STARBUCK_JUDGE_MODEL=model-name
+   export STARBUCK_JUDGE_KEY=...        # if the endpoint needs a key
+   ```
+
+2. Run the check with `--claims`:
+
+   ```sh
+   starbuck check paper.qmd --claims
+   starbuck check paper.qmd --claims --text smith2020=smith2020.txt   # full text you have
+   ```
+
+Without `--claims`, or without the model settings, level 4 does not run and the
+report says so. Level 4 sends the citing sentences and the source passages to
+the model's provider. The file `<name>-claims.json` in `_starbuck` keeps the
+passages, the source texts and the model's answers.
+
+A language model can be wrong. Read the source before you change the text.
+
+## Settings
+
+| Variable | Purpose |
+|---|---|
+| `STARBUCK_EMAIL` | Contact address for the services. `ZOTERO_CONTACT_EMAIL` also works. |
+| `NCBI_API_KEY` | Higher request rate for PubMed. |
+| `OPENALEX_API_KEY` | OpenAlex API key. |
+| `QUARTO_PATH` | Path to Quarto when it is not on the PATH. |
+| `STARBUCK_JUDGE_URL`, `STARBUCK_JUDGE_MODEL`, `STARBUCK_JUDGE_KEY` | Level 4 model (OpenAI-compatible endpoint). |
+
+## Use from an agent (MCP)
+
+`starbuck-mcp` is an MCP server with four tools:
+
+- `check_manuscript`: checks a manuscript and writes the report.
+- `check_references`: checks references given directly (an identifier, citation
+  details, or both). An agent can use it to check the sources of a text it wrote.
+- `prepare_claims`: level 4, step 1. Checks the references and returns each
+  citing sentence with the best passages of its source. A local full text can
+  be given per citation key.
+- `record_claims`: level 4, step 2. Takes the agent's verdicts, checks the
+  quoted passages and adds level 4 to the report.
+
+Inside an agent, the agent's own model judges, so no `STARBUCK_JUDGE_*`
+settings are needed.
+
+In [Sub-Sub](https://github.com/tiagojct/subsub), turn on reference checks in
+`subsub init` or with the switch in the web view; Sub-Sub then runs Starbuck as
+its `verify` server.
+
+Example configuration for an MCP client:
+
+```json
+{
+  "mcpServers": {
+    "starbuck": {
+      "command": "uvx",
+      "args": ["--from", "starbuck", "starbuck-mcp"],
+      "env": { "STARBUCK_EMAIL": "you@example.org" }
+    }
+  }
+}
+```
+
+## Privacy
+
+Starbuck sends identifiers and reference details (title, authors, year, or the
+reference as written) to the services listed above, and it opens cited web
+pages. Levels 1 to 3 do not send the manuscript text. Level 4 (only with
+`--claims`) sends the citing sentences and source passages to the model you
+set. Starbuck collects no usage data.
+
+## Demo
+
+`examples/demo.qmd` cites real works, each set up to show one kind of result:
+a correct reference, a wrong year, a DOI that belongs to another paper, a DOI
+that does not exist, a retracted paper, a reference without a DOI, an arXiv
+preprint and a citation without an entry.
+
+```sh
+starbuck check examples/demo.qmd --to html,docx
+```
+
+## Development
+
+```sh
+uv sync
+uv run pytest -q
+```
+
+The tests use canned service responses and do not need the network.
+
+## License
+
+[MIT](LICENSE) © Tiago Jacinto

starbuck-0.2.0/examples/demo.bib

@@ -0,0 +1,69 @@
+% Demo bibliography. Each entry is set up to show one kind of result.
+
+@article{miller2005,
+  title = {Standardisation of spirometry},
+  author = {Miller, M. R. and Hankinson, J. and Brusasco, V.},
+  journal = {European Respiratory Journal},
+  year = {2005},
+  doi = {10.1183/09031936.05.00034805}
+}
+
+@article{quanjer2012,
+  title = {Multi-ethnic reference values for spirometry for the 3--95-yr age range: the global lung function 2012 equations},
+  author = {Quanjer, Philip H. and Stanojevic, Sanja and Cole, Tim J.},
+  journal = {European Respiratory Journal},
+  year = {2012},
+  doi = {10.1183/09031936.00080312}
+}
+
+% Expected: Check (the year is wrong)
+@article{graham2019,
+  title = {Standardization of Spirometry 2019 Update. An Official American Thoracic Society and European Respiratory Society Technical Statement},
+  author = {Graham, Brian L. and Steenbruggen, Irene},
+  journal = {American Journal of Respiratory and Critical Care Medicine},
+  year = {2017},
+  doi = {10.1164/rccm.201908-1590ST}
+}
+
+% Expected: Fail (the DOI belongs to Miller et al. 2005)
+@article{gli2012wrong,
+  title = {Multi-ethnic reference values for spirometry for the 3--95-yr age range: the global lung function 2012 equations},
+  author = {Quanjer, Philip H.},
+  journal = {European Respiratory Journal},
+  year = {2012},
+  doi = {10.1183/09031936.05.00034805}
+}
+
+% Expected: Fail (the DOI does not exist)
+@article{invented2024,
+  title = {Deep learning interpretation of spirometry in 40,000 astronauts},
+  author = {Nobody, A.},
+  journal = {European Respiratory Journal},
+  year = {2024},
+  doi = {10.1183/09031936.99999999}
+}
+
+% Expected: Fail (retracted in 2010)
+@article{wakefield1998,
+  title = {Ileal-lymphoid-nodular hyperplasia, non-specific colitis, and pervasive developmental disorder in children},
+  author = {Wakefield, A. J.},
+  journal = {The Lancet},
+  year = {1998},
+  doi = {10.1016/S0140-6736(97)11096-0}
+}
+
+% Expected: Note (no DOI given; Crossref search should find it)
+@article{millernodoi,
+  title = {Standardisation of spirometry},
+  author = {Miller, M. R.},
+  journal = {European Respiratory Journal},
+  year = {2005}
+}
+
+@online{vaswani2017,
+  title = {Attention Is All You Need},
+  author = {Vaswani, Ashish},
+  year = {2017},
+  eprint = {1706.03762},
+  eprinttype = {arxiv}
+}