linkml-reference-validator 0.2.0__tar.gz → 0.2.1rc1__tar.gz

linkml_reference_validator-0.2.1rc1/.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-0.2.1rc1}/.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-0.2.1rc1}/.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-0.2.1rc1}/.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-0.2.1rc1/PKG-INFO

@@ -1,3 +1,24 @@
+Metadata-Version: 2.4
+Name: linkml_reference_validator
+Version: 0.2.1rc1
+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)]()
@@ -496,6 +517,24 @@ 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-0.2.1rc1/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)]()
@@ -516,6 +496,24 @@ 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-0.2.1rc1}/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-0.2.1rc1/docs/how-to/fetch-full-text-and-pdfs.md

@@ -0,0 +1,139 @@
+# Fetching Full Text and PDFs
+
+This guide explains how the validator obtains the **full text** of a reference
+(not just its abstract or metadata) by trying a chain of full-text providers,
+optionally downloading and extracting text from PDFs.
+
+## Overview
+
+When a metadata source (Crossref, PubMed, DataCite, etc.) returns only an
+abstract or title, the validator can fall through to a **full-text provider
+chain**. Each provider attempts to *locate* an open-access copy of the
+reference. The first provider that yields usable full text wins; the located
+resource is downloaded and, if it is a PDF, the text is extracted and cached
+alongside the reference.
+
+This behaviour is **on by default**.
+
+## The provider chain
+
+The validator tries providers in order until one returns usable full text.
+The default order is:
+
+```
+pmc → unpaywall → openalex
+```
+
+- **`pmc`** — PubMed Central open-access subset (XML/HTML full text for many
+  biomedical articles).
+- **`unpaywall`** — Unpaywall open-access lookup by DOI (often a publisher or
+  repository PDF).
+- **`openalex`** — OpenAlex open-access location (PDF/HTML).
+
+Providers are skipped silently if they have nothing for a given reference, so
+the chain degrades gracefully: a miss in `pmc` simply moves on to `unpaywall`,
+and so on. If no provider yields full text, the reference keeps whatever
+metadata-only content it already had.
+
+## Configuration
+
+Full-text fetching is controlled by the following configuration keys (set in
+your config YAML or on the `ReferenceValidationConfig` object):
+
+| Key | Default | Description |
+|-----|---------|-------------|
+| `fetch_full_text` | `true` | Attempt to obtain full text via the provider chain when a metadata source does not already return full text. |
+| `full_text_providers` | `[pmc, unpaywall, openalex]` | Ordered list of provider names to try until one yields usable full text. |
+| `pdf_backend` | `pypdf` | Name of the PDF text-extraction backend. |
+| `download_pdfs` | `true` | If true, persist downloaded PDFs to the files cache directory. |
+| `full_text_providers_file` | `null` | Optional path to a YAML file defining custom full-text providers. |
+
+Two existing keys are also reused by the full-text machinery:
+
+| Key | Description |
+|-----|-------------|
+| `email` | Used for "polite pool" access to providers such as Unpaywall and OpenAlex (and for Crossref/Entrez). Set this for more reliable access. |
+| `max_supplementary_file_size` | Upper bound (in bytes) on individual file downloads; a downloaded full-text PDF larger than this limit is not persisted. |
+
+Example config YAML:
+
+```yaml
+email: you@example.org
+fetch_full_text: true
+full_text_providers:
+  - pmc
+  - unpaywall
+  - openalex
+pdf_backend: pypdf
+download_pdfs: true
+```
+
+## CLI flag
+
+Every `validate` subcommand accepts a `--full-text/--no-full-text` flag that
+toggles `fetch_full_text` for that run (default: on):
+
+```bash
+# Default: full-text chain is tried
+linkml-reference-validator validate data data.yaml \
+  --schema schema.yaml --target-class Statement
+
+# Disable full-text fetching (metadata only)
+linkml-reference-validator validate data data.yaml \
+  --schema schema.yaml --target-class Statement --no-full-text
+```
+
+## Custom providers
+
+You can declare your own JSON-API-backed provider in a YAML file and point
+`full_text_providers_file` at it. Each entry under `full_text_providers` is
+keyed by the provider name and must supply a `url_template`. The template may
+reference `{doi}`, `{pmid}`, or `{pmcid}`. `location_field` is a JSONPath into
+the response that holds the URL of the full-text resource; `format_hint` tells
+the validator how to treat it; and `headers` are sent with the request, with
+`${ENV_VAR}` placeholders interpolated from the environment.
+
+```yaml
+full_text_providers:
+  myrepo:
+    url_template: https://api.example.org/fulltext/{doi}
+    location_field: $.links.pdf
+    format_hint: pdf
+    headers:
+      Authorization: Bearer ${MYREPO_TOKEN}
+```
+
+To actually use a custom provider, add its name to the `full_text_providers`
+chain (it is not enabled merely by being defined), for example:
+
+```yaml
+full_text_providers_file: providers.yaml
+full_text_providers:
+  - myrepo
+  - pmc
+  - unpaywall
+  - openalex
+```
+
+## Provenance fields
+
+When a reference is enriched with full text, the cached reference records where
+the text came from. These provenance fields are written alongside the content:
+
+| Field | Description |
+|-------|-------------|
+| `full_text_provider` | Name of the provider that supplied the full text (e.g. `pmc`, `unpaywall`, or a custom name). |
+| `oa_status` | Open-access status reported by the provider (e.g. `gold`, `green`, `bronze`). |
+| `license` | License of the open-access copy, when known. |
+| `local_pdf_path` | Path (relative to the cache directory) to the downloaded PDF, when one was persisted. |
+
+When full text from a PDF is obtained, the reference's `content_type` becomes
+`full_text_pdf` and the extracted text replaces the abstract-only content. The
+downloaded PDF lives under the cache directory and can be located at
+`cache_dir / local_pdf_path`.
+
+## See Also
+
+- [Validating DOIs](validate-dois.md) — DOI metadata sources and supplementary files
+- [Validating Entrez Accessions](validate-entrez.md) — PubMed/PMC references
+- [CLI Reference](../reference/cli.md) — complete command documentation