Documenting differences in ontology files (attempt 2)

.github/workflows/ontology_diff.yml

@@ -0,0 +1,139 @@
+name: 'Create OAK diffs on Pull requests'
+
+on:
+    # Triggers the workflow on pull request events for the master branch
+    pull_request:
+        branches: [ master ]
+
+    # Allows you to run this workflow manually from the Actions tab
+    workflow_dispatch:
+
+# A workflow run is made up of one or more jobs that can run sequentially or in parallel
+jobs:
+  build_branch:
+    runs-on: ubuntu-latest
+    container: obolibrary/odkfull:v1.5
+    steps:
+      - uses: actions/checkout@v4
+      - name: Build ontology
+        run: |
+          cd src/ontology; make IMP=FALSE PAT=FALSE MIR=FALSE hp.obo -B
+          cp hp.obo tmp/hp-branch.obo
+      - name: Upload tmp/hp-branch.obo
+        uses: actions/upload-artifact@v4
+        with:
+          name: hp-branch.obo
+          path: src/ontology/tmp/hp-branch.obo
+          retention-days: 1
+  build_main:
+    runs-on: ubuntu-latest
+    container: obolibrary/odkfull:v1.5
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: master
+      - name: Classify ontology
+        run: |
+          cd src/ontology; make IMP=FALSE PAT=FALSE MIR=FALSE hp.obo -B
+          cp hp.obo tmp/hp-main.obo
+      - name: Upload tmp/hp-main.obo
+        uses: actions/upload-artifact@v4
+        with:
+          name: hp-main.obo
+          path: src/ontology/tmp/hp-main.obo
+          retention-days: 1
+  diff:
+    needs:
+      - build_branch
+      - build_main
+    runs-on: ubuntu-latest
+    container: obolibrary/odkfull:v1.5
+    steps:
+      - uses: actions/checkout@v4
+      - name: Download main build
+        uses: actions/download-artifact@v4
+        with:
+          name: hp-main.obo
+          path: src/ontology/tmp/
+      - name: Download branch build
+        uses: actions/download-artifact@v4
+        with:
+          name: hp-branch.obo
+          path: src/ontology/tmp/
+      - name: Diff classification
+        run: | 
+            pip install -U oaklib
+            cd src/ontology;
+            runoak -i simpleobo:tmp/hp-main.obo diff -X simpleobo:tmp/hp-branch.obo -o reports/difference_main-branch_base.md --output-type md 
+      - name: Upload diff
+        uses: actions/upload-artifact@v4
+        with:
+          name: difference_main-branch_base.md
+          path: src/ontology/reports/difference_main-branch_base.md
+  post_comment:
+    needs: diff
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Download reasoned diff
+        uses: actions/download-artifact@v4
+        with:
+          name: difference_main-branch_base.md
+          path: src/ontology/reports/
+      # - name: Prepare reasoned comment
+      #   run: "echo \"<details>\n <summary> Here's a diff of how these changes impact the classified ontology: </summary> \n\" >comment.md; cat src/ontology/reports/difference_main-branch_base.md >>comment.md"
+      # - name: Post reasoned comment
+      #   env:
+      #     GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      #   uses: NejcZdovc/[email protected]
+      #   with:
+      #     github_token: ${{ secrets.GITHUB_TOKEN }}
+      #     file: "../../comment.md"
+      #     identifier: "REASONED"
+      # Post or update comment on pull request if difference_md.md exists
+      - name: Post or update comment on pull request
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const fs = require('fs');
+            const path = 'src/ontology/reports/difference_main-branch_base.md'; 
+            if (fs.existsSync(path)) {
+                let content = fs.readFileSync(path, 'utf8');
+                if (content) {
+                    // GitHub's max issue body size is approximately 65536 characters
+                    const maxBodySize = 65536;
+                    const truncateMsg = '\n</details>\n\n ### WARNING: This diff is too large and has been truncated. For full diff see [here](https://github.com/${{ github.repository }}/blob/${{ github.head_ref }}/src/ontology/reports/difference_main-branch_base.md).';
+                    if (content.length > maxBodySize) {
+                        // Truncate the content to fit within the GitHub comment size limit
+                        content = content.substring(0, maxBodySize - truncateMsg.length) + truncateMsg;
+                    }
+
+                    const { owner, repo } = context.repo;
+                    const { number } = context.issue;
+                    const existingComments = await github.rest.issues.listComments({
+                        owner,
+                        repo,
+                        issue_number: number
+                    });
+                    const existingComment = existingComments.data.find(comment => comment.user.login === 'github-actions[bot]');
+                    if (existingComment) {
+                        await github.rest.issues.updateComment({
+                            owner,
+                            repo,
+                            comment_id: existingComment.id,
+                            body: content
+                        });
+                    } else {
+                        await github.rest.issues.createComment({
+                            owner,
+                            repo,
+                            issue_number: number,
+                            body: content
+                        });
+                    }
+                } else {
+                    console.log("The markdown file is empty."); // Debug print if the file is empty
+                }
+            } else {
+                console.log("The markdown file does not exist."); // Debug print if the file does not exist
+            }

src/ontology/hp.Makefile

@@ -577,3 +577,33 @@ $(TMPDIR)/hp-%-merged.owl: hp-base.owl tmp/%.owl
 
 mappings: 
 	$(MAKE_FAST) ../mappings/hp-snomed.lexmatch.sssom.tsv
+
+##################
+### KGCL Diff ####
+##################
+
+.PHONY: kgcl-diff
+kgcl-diff: kgcl-diff-release-base
+
+.PHONY: kgcl-diff-md-release-base kgcl-diff-table-release-base kgcl-diff-txt-release-base kgcl-diff-yaml-release-base 
+kgcl-diff-md-release-base: reports/difference_release_base.md
+kgcl-diff-table-release-base: reports/difference_release_base.tsv
+kgcl-diff-txt-release-base: reports/difference_release_base.txt
+kgcl-diff-yaml-release-base: reports/difference_release_base.yaml
+kgcl-diff-release-base: kgcl-diff-md-release-base kgcl-diff-table-release-base kgcl-diff-txt-release-base kgcl-diff-yaml-release-base
+
+tmp/hp-released.obo:
+	wget http://purl.obolibrary.org/obo/hp.obo -O tmp/hp-released.obo
+
+reports/difference_release_base.md: tmp/hp-released.obo hp.obo
+	runoak -i simpleobo:tmp/hp-released.obo diff -X simpleobo:hp.obo -o $@ --output-type md
+
+reports/difference_release_base.tsv: tmp/hp-released.obo hp.obo
+	runoak -i simpleobo:tmp/hp-released.obo diff -X simpleobo:hp.obo \
+	-o $@ --output-type csv --statistics --group-by-property oio:hasOBONamespace
+
+reports/difference_release_base.txt: tmp/hp-released.obo hp.obo
+	runoak -i simpleobo:tmp/hp-released.obo diff -X simpleobo:hp.obo -o $@ --output-type kgcl
+
+reports/difference_release_base.yaml: tmp/hp-released.obo hp.obo
+	runoak -i simpleobo:tmp/hp-released.obo diff -X simpleobo:hp.obo -o $@ --output-type yaml