linkml-reference-validator 0.2.0__tar.gz → 0.2.1__tar.gz

linkml_reference_validator-0.2.1/.github/workflows/claude-code-review.yml

@@ -0,0 +1,61 @@
+name: Claude Code Review
+
+on:
+  pull_request:
+    types: [opened, synchronize]
+    # Optional: Only run on specific file changes
+    # paths:
+    #   - "src/**/*.ts"
+    #   - "src/**/*.tsx"
+    #   - "src/**/*.js"
+    #   - "src/**/*.jsx"
+
+jobs:
+  claude-review:
+    # Optional: Filter by PR author
+    # if: |
+    #   github.event.pull_request.user.login == 'external-contributor' ||
+    #   github.event.pull_request.user.login == 'new-developer' ||
+    #   github.event.pull_request.author_association == 'FIRST_TIME_CONTRIBUTOR'
+    
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+    
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v6
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code Review
+        id: claude-review
+        uses: anthropics/claude-code-action@v1
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+
+          # In v1, providing a `prompt` runs in automation mode, which does NOT
+          # post a comment by default. track_progress restores the v0.x
+          # "post the review as a PR comment" behavior and auto-injects PR context.
+          track_progress: true
+
+          # Prompt for the automated review (no @claude mention needed).
+          prompt: |
+            Please review this pull request and provide feedback on:
+            - Code quality and best practices
+            - Potential bugs or issues
+            - Performance considerations
+            - Security concerns
+            - Test coverage
+
+            Be constructive and helpful in your feedback.
+
+          # Args passed through to the Claude CLI. Use the `opus` alias rather
+          # than a dated model id so the workflow tracks the current Opus and
+          # won't 404 when a specific version is retired.
+          claude_args: |
+            --model opus
+

{linkml_reference_validator-0.2.0 → linkml_reference_validator-0.2.1}/.github/workflows/claude-ontology-review.yml

@@ -35,15 +35,23 @@ jobs:
 
       - name: Run Claude Code Ontology Review
         id: claude-review
-        uses: anthropics/claude-code-action@beta
+        uses: anthropics/claude-code-action@v1
         with:
           claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
 
-          # Optional: Specify model (commenting defaults to Claude Sonnet 4)
-          model: "claude-opus-4-1-20250805"
+          # In v1, providing a `prompt` runs in automation mode, which does NOT
+          # post a comment by default. track_progress restores the v0.x
+          # "post the review as a PR comment" behavior and auto-injects PR context.
+          track_progress: true
 
-          # Direct prompt for automated review (no @claude mention needed)
-          direct_prompt: |
+          # Model is passed through to the Claude CLI via claude_args. Use the
+          # `opus` alias so the workflow tracks the current Opus and won't 404
+          # when a specific dated model id is retired.
+          claude_args: |
+            --model opus
+
+          # Prompt for the automated review (no @claude mention needed)
+          prompt: |
             REPO: ${{ github.repository }}
             PR NUMBER: ${{ github.event.pull_request.number }}
 
@@ -90,26 +98,4 @@ jobs:
 
           # Optional: Use sticky comments to make Claude reuse the same comment on subsequent pushes to the same PR
           use_sticky_comment: true
-          
-          # Optional: Customize review based on file types
-          # direct_prompt: |
-          #   Review this PR focusing on:
-          #   - For TypeScript files: Type safety and proper interface usage
-          #   - For API endpoints: Security, input validation, and error handling
-          #   - For React components: Performance, accessibility, and best practices
-          #   - For tests: Coverage, edge cases, and test quality
-          
-          # Optional: Different prompts for different authors
-          # direct_prompt: |
-          #   ${{ github.event.pull_request.author_association == 'FIRST_TIME_CONTRIBUTOR' && 
-          #   'Welcome! Please review this PR from a first-time contributor. Be encouraging and provide detailed explanations for any suggestions.' ||
-          #   'Please provide a thorough code review focusing on our coding standards and best practices.' }}
-          
-          # Optional: Add specific tools for running tests or linting
-          # allowed_tools: "Bash(npm run test),Bash(npm run lint),Bash(npm run typecheck)"
-          
-          # Optional: Skip review for certain conditions
-          # if: |
-          #   !contains(github.event.pull_request.title, '[skip-review]') &&
-          #   !contains(github.event.pull_request.title, '[WIP]')
 

{linkml_reference_validator-0.2.0 → linkml_reference_validator-0.2.1}/.github/workflows/claude.yml

@@ -39,52 +39,24 @@ jobs:
 
       - name: Run Claude Code
         id: claude
-        uses: anthropics/claude-code-action@beta
-        
+        uses: anthropics/claude-code-action@v1
+
         with:
           claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
-          mcp_config: |
-            {
-              "mcpServers": {
-                "ols": {
-                  "command": "uvx",
-                  "args": [
-                    "ols-mcp"
-                  ]
-                },
-                "sequential-thinking": {
-                  "command": "npx",
-                  "args": [
-                    "-y",
-                    "@modelcontextprotocol/server-sequential-thinking"
-                  ]
-                }
-              }
-            }
 
           # This is an optional setting that allows Claude to read CI results on PRs
           additional_permissions: |
             actions: read
-          
-          # Optional: Specify model (defaults to Claude Sonnet 4, uncomment for Claude Opus 4.1)
-          # model: "claude-opus-4-1-20250805"
-          
+
+          # In v1 the model, MCP servers, and allowed tools are passed through to
+          # the Claude CLI via claude_args (the v0.x model / mcp_config /
+          # allowed_tools inputs were removed). The `opus` alias tracks the
+          # current Opus so this won't 404 when a dated model id is retired.
+          claude_args: |
+            --model opus
+            --mcp-config '{"mcpServers":{"ols":{"command":"uvx","args":["ols-mcp"]},"sequential-thinking":{"command":"npx","args":["-y","@modelcontextprotocol/server-sequential-thinking"]}}}'
+            --allowedTools "Bash(*),FileEdit,Edit,MultiEdit,WebSearch,WebFetch,mcp__ols_mcp__search_all_ontologies,mcp__ols_mcp__get_terms_from_ontology"
+
           # Optional: Customize the trigger phrase (default: @claude)
           # trigger_phrase: "/claude"
-          
-          # Optional: Trigger when specific user is assigned to an issue
-          # assignee_trigger: "claude-bot"
-          
-          # Optional: Allow Claude to run specific commands
-          allowed_tools: "Bash(*),FileEdit,Edit,MultiEdit,WebSearch,WebFetch,mcp__ols_mcp__search_all_ontologies,mcp__ols_mcp__get_terms_from_ontology"
-          
-          # Optional: Add custom instructions for Claude to customize its behavior for your project
-          # custom_instructions: |
-          #   Follow our coding standards
-          #   Ensure all new code has tests
-          #   Use TypeScript for new files
-          
-          # Optional: Custom environment variables for Claude
-          # claude_env: |
-          #   NODE_ENV: test
 

{linkml_reference_validator-0.2.0 → linkml_reference_validator-0.2.1}/.github/workflows/dragon-ai.yml

@@ -29,7 +29,7 @@ jobs:
         
       - name: Check for qualifying mention
         id: check
-        uses: actions/github-script@v8
+        uses: actions/github-script@v9
         with:
           github-token: ${{ secrets.PAT_FOR_PR }}  # Use PAT instead of default token
           script: |

linkml_reference_validator-0.2.0/README.md → linkml_reference_validator-0.2.1/PKG-INFO

@@ -1,3 +1,24 @@
+Metadata-Version: 2.4
+Name: linkml_reference_validator
+Version: 0.2.1
+Summary: Validation of supporting text from references and publications
+Author-email: Chris Mungall <cjmungall@lbl.gov>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Requires-Python: <4.0,>=3.10
+Requires-Dist: beautifulsoup4>=4.9.0
+Requires-Dist: biopython>=1.80
+Requires-Dist: jsonpath-ng>=1.6.0
+Requires-Dist: linkml-runtime>=1.9.4
+Requires-Dist: lxml>=4.9.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: pypdf>=4.0.0
+Requires-Dist: rapidfuzz>=3.14.3
+Requires-Dist: requests>=2.28.0
+Requires-Dist: ruamel-yaml>=0.18.0
+Requires-Dist: typer>=0.9.0
+Description-Content-Type: text/markdown
+
 # linkml-reference-validator
 
 [![Tests](https://img.shields.io/badge/tests-91%20passing-brightgreen)]()
@@ -374,10 +395,36 @@ reference:
 - `PMID:12345678`
 - `12345678` (assumes PMID)
 
-### Coming Soon
+#### Preprints
+
+Preprints are supported as first-class references:
+
+```yaml
+reference:
+  id: DOI:10.1101/2024.01.01.573333   # by DOI
+  supporting_text: "the kinase phosphorylates the substrate in vitro"
+```
 
-- **DOI** - `DOI:10.1038/nature12345`
-- **URLs** - Web pages and online documents
+```yaml
+reference:
+  id: PPR:PPR123456                    # by Europe PMC preprint id
+  supporting_text: "the kinase phosphorylates the substrate in vitro"
+```
+
+**Fetches:**
+- Abstract and metadata (title, authors, server, year, DOI)
+- Full-text body via the Europe PMC `fulltextRepo` PDF route (`epmc_preprint`
+  provider), for the Europe-PMC-ingested subset
+- `is_preprint` / `peer_review_status` flags, so downstream KBs can apply
+  "not sole support" policies
+
+**ID Formats:**
+- `DOI:10.1101/...` (Crossref `posted-content` is detected as a preprint)
+- `PPR:PPR123456` (Europe PMC `SRC:PPR` id)
+- NIH Preprint Pilot preprints carry real PMIDs and resolve via the `PMID:` path
+
+See the [full-text guide](docs/how-to/fetch-full-text-and-pdfs.md#preprints) for
+details and coverage caveats.
 
 ---
 
@@ -496,6 +543,24 @@ supporting_text: "protein [X] functions in cell cycle regulation"
 - `[gene name]` - Clarifications
 - `[...]` - Omitted content markers
 
+If your corpus uses square brackets as literal source text, configure patterns
+that should be preserved instead of stripped:
+
+```yaml
+validation:
+  literal_bracket_patterns:
+    - "\\d"       # keep [2Fe-2S], [+21], [30S], [Ca2+]
+    - "[()+]"     # keep notation with parens/charges, e.g. [poly(A)+]
+```
+
+Patterns are matched against the content inside `[...]`. If any pattern matches,
+that bracketed text is preserved (not stripped) before normalization and validation.
+
+Keep patterns **specific** to your notation. A pattern broad enough to also match
+ordinary editorial notes will preserve those too — for example `^\S` matches any
+note that doesn't start with a space, so it would keep `[important]` as well as
+`[poly(A)+]`.
+
 ### Omitted Text `...`
 
 Use ellipsis for gaps in quoted text:

linkml_reference_validator-0.2.0/PKG-INFO → linkml_reference_validator-0.2.1/README.md

@@ -1,23 +1,3 @@
-Metadata-Version: 2.4
-Name: linkml_reference_validator
-Version: 0.2.0
-Summary: Validation of supporting text from references and publications
-Author-email: Chris Mungall <cjmungall@lbl.gov>
-License-Expression: Apache-2.0
-License-File: LICENSE
-Requires-Python: <4.0,>=3.10
-Requires-Dist: beautifulsoup4>=4.9.0
-Requires-Dist: biopython>=1.80
-Requires-Dist: jsonpath-ng>=1.6.0
-Requires-Dist: linkml-runtime>=1.9.4
-Requires-Dist: lxml>=4.9.0
-Requires-Dist: pydantic>=2.0.0
-Requires-Dist: rapidfuzz>=3.14.3
-Requires-Dist: requests>=2.28.0
-Requires-Dist: ruamel-yaml>=0.18.0
-Requires-Dist: typer>=0.9.0
-Description-Content-Type: text/markdown
-
 # linkml-reference-validator
 
 [![Tests](https://img.shields.io/badge/tests-91%20passing-brightgreen)]()
@@ -394,10 +374,36 @@ reference:
 - `PMID:12345678`
 - `12345678` (assumes PMID)
 
-### Coming Soon
+#### Preprints
+
+Preprints are supported as first-class references:
+
+```yaml
+reference:
+  id: DOI:10.1101/2024.01.01.573333   # by DOI
+  supporting_text: "the kinase phosphorylates the substrate in vitro"
+```
 
-- **DOI** - `DOI:10.1038/nature12345`
-- **URLs** - Web pages and online documents
+```yaml
+reference:
+  id: PPR:PPR123456                    # by Europe PMC preprint id
+  supporting_text: "the kinase phosphorylates the substrate in vitro"
+```
+
+**Fetches:**
+- Abstract and metadata (title, authors, server, year, DOI)
+- Full-text body via the Europe PMC `fulltextRepo` PDF route (`epmc_preprint`
+  provider), for the Europe-PMC-ingested subset
+- `is_preprint` / `peer_review_status` flags, so downstream KBs can apply
+  "not sole support" policies
+
+**ID Formats:**
+- `DOI:10.1101/...` (Crossref `posted-content` is detected as a preprint)
+- `PPR:PPR123456` (Europe PMC `SRC:PPR` id)
+- NIH Preprint Pilot preprints carry real PMIDs and resolve via the `PMID:` path
+
+See the [full-text guide](docs/how-to/fetch-full-text-and-pdfs.md#preprints) for
+details and coverage caveats.
 
 ---
 
@@ -516,6 +522,24 @@ supporting_text: "protein [X] functions in cell cycle regulation"
 - `[gene name]` - Clarifications
 - `[...]` - Omitted content markers
 
+If your corpus uses square brackets as literal source text, configure patterns
+that should be preserved instead of stripped:
+
+```yaml
+validation:
+  literal_bracket_patterns:
+    - "\\d"       # keep [2Fe-2S], [+21], [30S], [Ca2+]
+    - "[()+]"     # keep notation with parens/charges, e.g. [poly(A)+]
+```
+
+Patterns are matched against the content inside `[...]`. If any pattern matches,
+that bracketed text is preserved (not stripped) before normalization and validation.
+
+Keep patterns **specific** to your notation. A pattern broad enough to also match
+ordinary editorial notes will preserve those too — for example `^\S` matches any
+note that doesn't start with a space, so it would keep `[important]` as well as
+`[poly(A)+]`.
+
 ### Omitted Text `...`
 
 Use ellipsis for gaps in quoted text:

{linkml_reference_validator-0.2.0 → linkml_reference_validator-0.2.1}/docs/concepts/editorial-conventions.md

@@ -70,6 +70,34 @@ Nested brackets are not recommended and may not work as expected:
 ✅ "MUC1 [mucin 1, a membrane protein] blocks targeting"
 ```
 
+### Literal Brackets in Source Text
+
+Some corpora use square brackets as part of the quoted source text itself:
+
+```
+Reference: "polyadenylated [poly(A)+] RNA export"
+Quote:     "polyadenylated [poly(A)+] RNA export"
+```
+
+By default, linkml-reference-validator strips all bracketed text for backward
+compatibility. To preserve literal brackets, configure
+`literal_bracket_patterns` in your validation config:
+
+```yaml
+validation:
+  literal_bracket_patterns:
+    - "\\d"       # keep [2Fe-2S], [+21], [30S], [Ca2+]
+    - "[()+]"     # keep notation with parens/charges, e.g. [poly(A)+]
+```
+
+Each pattern is matched against the content inside `[...]`. If any pattern
+matches, that bracketed text is kept during validation. If none match, the
+content is treated as an editorial insertion and stripped.
+
+Keep patterns specific to your notation. A pattern broad enough to also match
+ordinary editorial notes will preserve those too — for example `^\S` (any note
+not starting with a space) would keep `[important]` as well as `[poly(A)+]`.
+
 ## Ellipsis `...`
 
 Use ellipsis (three dots) to indicate **omitted text** between parts of a quote.

linkml_reference_validator-0.2.1/docs/how-to/export-cache-to-zotero.md

@@ -0,0 +1,114 @@
+# Export a Reference Cache to Zotero
+
+This workflow turns a checked-in public reference cache into a Zotero collection,
+asks Zotero to find available PDFs, and then inventories the resulting attachments
+without putting closed manuscripts into the project repository.
+
+The three stores remain separate:
+
+| Store | Purpose | Safe to commit? |
+|---|---|---:|
+| Project `references_cache` | Reproducible public validation evidence | Yes |
+| Zotero library | User-managed references and PDF attachments | No |
+| Private research cache | Extracted user-library text for agent context | No |
+
+Normal validation reads only the first store.
+
+## 1. Export metadata from the public cache
+
+Run the exporter from the `linkml-reference-validator` checkout. For dismech:
+
+```bash
+uv run linkml-reference-validator cache export \
+  --cache-dir /Users/cjm/repos/dismech/references_cache \
+  --needs-full-text \
+  --output /Users/cjm/Downloads/dismech-zotero.json
+```
+
+`--needs-full-text` is the default. It excludes cache entries that already have
+full text, excludes non-publication identifiers, and deduplicates by normalized
+DOI and then PMID. The CSL JSON output uses an explicit metadata allowlist:
+
+- title and authors;
+- journal and year;
+- DOI; or
+- PMID and its public PubMed URL.
+
+It never contains cached article text, excerpts, provenance, PDFs, local paths,
+or private-cache data. The command refuses to replace an existing output file;
+use `--force` only after checking the destination. Use `--all` if you explicitly
+want eligible references that already contain full text.
+
+## 2. Import the file into Zotero
+
+In Zotero:
+
+1. Choose **File → Import**.
+2. Choose **A file**.
+3. Select `dismech-zotero.json`.
+4. Keep the imported records in a project-specific collection such as
+   **dismech**.
+
+CSL JSON is a standard format supported by Zotero. Importing the file adds only
+bibliographic records; it does not copy anything from the validator's caches.
+
+## 3. Ask Zotero to find PDFs
+
+Select one or more top-level journal articles in the center item list,
+right-click the selection, and choose **Find Full Text**. It is a built-in Zotero
+command, not a plugin.
+
+![Zotero Find Full Text processing a batch of imported references](../assets/zotero-find-full-text.png)
+
+The command appears for an eligible parent item that has a DOI and does not
+already have a file attachment. It may also be unavailable in a group library
+where files cannot be added. If it is absent, first test a single article in
+your personal library and confirm that its DOI field is populated.
+
+For a large import, start with a modest batch rather than all records at once.
+Publishers can temporarily rate-limit repeated requests, and a later retry may
+find additional files. Zotero reports **Full Text PDF** or **No file found** for
+each attempted item.
+
+## 4. Inventory the enriched Zotero library
+
+Once Zotero finishes, scan the project cache again:
+
+```bash
+uv run linkml-reference-validator cache enrich \
+  --provider zotero \
+  --cache-dir /Users/cjm/repos/dismech/references_cache \
+  --dry-run
+```
+
+This read-only scan matches exact DOI, PMID, or PMCID identifiers and reports
+which cached references now have usable Zotero text or PDF attachments. It does
+not invoke **Find Full Text** and does not modify Zotero.
+
+After reviewing the matches, materialize them into the separate private research
+cache:
+
+```bash
+uv run linkml-reference-validator cache enrich \
+  --provider zotero \
+  --cache-dir /Users/cjm/repos/dismech/references_cache \
+  --apply
+```
+
+Apply mode leaves `references_cache` unchanged. Private content goes to
+`~/.cache/linkml-reference-validator/private` by default with owner-only
+permissions. Agents may inspect it for context, but validation cannot use it as
+evidence.
+
+## 5. Validate reproducibly
+
+Run validation normally. Results remain reproducible because the validator
+reads the public project cache and accepts only public full-text provider results.
+Neither the contents of Zotero nor the machine-specific private cache affect
+validation.
+
+## See also
+
+- [Fetching Full Text and PDFs](fetch-full-text-and-pdfs.md)
+- [Zotero: importing standardized formats](https://www.zotero.org/support/kb/importing_standardized_formats)
+- [Zotero: adding files to a library](https://www.zotero.org/support/attaching_files)