Release prep: harden annotation wrapper coverage and CI

.github/workflows/production-release.yml

@@ -24,6 +24,7 @@ jobs:
     runs-on: ubuntu-latest
     outputs:
       tag: ${{ steps.tag.outputs.tag }}
+      release_version: ${{ steps.tag.outputs.release_version }}
       tag_exists: ${{ steps.check.outputs.exists }}
 
     steps:
@@ -39,7 +40,24 @@ jobs:
           echo "Error: Tag must be in format v1.0.0, 1.0.0, or CalVer like 25.5.28"
           exit 1
         fi
+
+        RELEASE_VERSION="${TAG#v}"
+        PACKAGE_VERSION=$(python3 - <<'PY'
+        import pathlib
+        import tomllib
+
+        pyproject = tomllib.loads(pathlib.Path("pyproject.toml").read_text())
+        print(pyproject["project"]["version"])
+        PY
+        )
+
+        if [ "$RELEASE_VERSION" != "$PACKAGE_VERSION" ]; then
+          echo "Error: Tag version ($RELEASE_VERSION) does not match pyproject.toml version ($PACKAGE_VERSION)"
+          exit 1
+        fi
+
         echo "tag=$TAG" >> $GITHUB_OUTPUT
+        echo "release_version=$RELEASE_VERSION" >> $GITHUB_OUTPUT
 
     - name: Check if tag exists
       id: check
@@ -128,7 +146,7 @@ jobs:
           echo "Checking if version exists on PyPI..."
 
           # Check if package exists on PyPI
-          if curl -s "https://pypi.org/pypi/funannotate2-addons/${{ needs.validate-tag.outputs.tag }}/json" | grep -q "Not Found"; then
+          if curl -s "https://pypi.org/pypi/funannotate2-addons/${{ needs.validate-tag.outputs.release_version }}/json" | grep -q "Not Found"; then
             echo "❌ Version does not exist on PyPI - this is a real error"
             exit 1
           else
@@ -162,21 +180,31 @@ jobs:
     - name: Generate release notes
       id: release_notes
       run: |
-        # Get the previous tag
-        PREV_TAG=$(git describe --tags --abbrev=0 ${{ needs.validate-tag.outputs.tag }}^)
+        # Get the previous tag if one exists (initial releases may not have one)
+        PREV_TAG=$(git tag --merged "${{ needs.validate-tag.outputs.tag }}" --sort=-creatordate | grep -vx "${{ needs.validate-tag.outputs.tag }}" | head -n 1 || true)
 
         echo "Generating release notes for ${{ needs.validate-tag.outputs.tag }}"
-        echo "Previous tag: $PREV_TAG"
+        if [ -n "$PREV_TAG" ]; then
+          echo "Previous tag: $PREV_TAG"
+        else
+          echo "Previous tag: none (initial release)"
+        fi
         echo ""
 
         # Generate changelog
         echo "## Changes" > release_notes.md
         echo "" >> release_notes.md
 
-        # Get all commits between previous tag and current tag, excluding version bump commits
-        git log --pretty=format:"- %s (%h)" $PREV_TAG..${{ needs.validate-tag.outputs.tag }} \
-          --grep="bump version" --grep="version bump" --grep="update version" \
-          --invert-grep >> release_notes.md
+        # Get all commits since the previous tag, excluding version bump commits
+        if [ -n "$PREV_TAG" ]; then
+          git log --pretty=format:"- %s (%h)" "$PREV_TAG..${{ needs.validate-tag.outputs.tag }}" \
+            --grep="bump version" --grep="version bump" --grep="update version" \
+            --invert-grep >> release_notes.md
+        else
+          git log --pretty=format:"- %s (%h)" "${{ needs.validate-tag.outputs.tag }}" \
+            --grep="bump version" --grep="version bump" --grep="update version" \
+            --invert-grep >> release_notes.md
+        fi
 
         # Check if we have any commits
         if [ ! -s release_notes.md ] || [ $(wc -l < release_notes.md) -le 2 ]; then
@@ -187,7 +215,11 @@ jobs:
 
         echo "" >> release_notes.md
         echo "" >> release_notes.md
-        echo "**Full Changelog**: https://github.com/${{ github.repository }}/compare/$PREV_TAG...${{ needs.validate-tag.outputs.tag }}" >> release_notes.md
+        if [ -n "$PREV_TAG" ]; then
+          echo "**Full Changelog**: https://github.com/${{ github.repository }}/compare/$PREV_TAG...${{ needs.validate-tag.outputs.tag }}" >> release_notes.md
+        else
+          echo "**Full Changelog**: Initial release" >> release_notes.md
+        fi
 
         echo "Generated release notes:"
         cat release_notes.md

funannotate2_addons/emapper.py

@@ -2,7 +2,6 @@
 
 import os
 import sys
-import uuid
 import subprocess
 import argparse
 import json
@@ -905,7 +904,7 @@ def run_emapper_cli(args):
     input_file = get_input_file(args, "proteins") if args.input else args.file
 
     if not input_file:
-        log.error("No protein FASTA file found")
+        logger.error("No protein FASTA file found")
         return
 
     # Get output directory
@@ -922,8 +921,8 @@ def run_emapper_cli(args):
     # Create output directory if it doesn't exist
     os.makedirs(output_dir, exist_ok=True)
 
-    # Set output prefix
-    output_prefix = os.path.join(output_dir, f"emapper_{uuid.uuid4().hex[:6]}")
+    # Use a stable prefix so repeated runs can reuse the same output set.
+    output_prefix = os.path.join(output_dir, "emapper")
 
     # Set up logging
     log_file = f"{output_prefix}.log"

funannotate2_addons/iprscan.py

@@ -93,7 +93,7 @@ def run_iprscan(
         "--input",
         input_file,
         "-o",
-        os.path.basename(f"{output_prefix}.{format.lower()}"),
+        f"{output_prefix}.{format.lower()}",
         "-f",
         format,
         "-cpu",
@@ -169,15 +169,32 @@ def parse_iprscan_xml(input_file, output_file=None, gene_dict=None):
         logger.error(f"Error parsing XML file: {e}")
         return None
 
-    # Define namespaces
-    ns = {"ns": "http://www.ebi.ac.uk/interpro/resources/schemas/interproscan5"}
+    # Detect namespace from the document so we can support current and older
+    # InterProScan XML schema URLs.
+    namespace = root.tag.split("}")[0].strip("{") if root.tag.startswith("{") else ""
+
+    def qname(tag):
+        return f"{{{namespace}}}{tag}" if namespace else tag
+
+    def unique_by_id(items, item_id):
+        return item_id not in [item["id"] for item in items]
 
     # Parse annotations
     annotations = {}
 
     # Iterate through protein matches
-    for protein in root.findall(".//ns:protein", ns):
+    for protein in root.findall(f".//{qname('protein')}"):
         protein_id = protein.attrib.get("id", "")
+        if not protein_id:
+            xref = protein.find(qname("xref"))
+            if xref is not None:
+                protein_id = xref.attrib.get("id", "")
+        if not protein_id:
+            sequence = protein.find(qname("sequence"))
+            if sequence is not None and sequence.text:
+                protein_id = sequence.text.strip()
+        if not protein_id:
+            continue
 
         if protein_id not in annotations:
             annotations[protein_id] = {
@@ -187,33 +204,40 @@ def parse_iprscan_xml(input_file, output_file=None, gene_dict=None):
                 "signatures": [],
             }
 
+        matches = protein.find(qname("matches"))
+        if matches is None:
+            continue
+
         # Get matches
-        for match in protein.findall(".//ns:match", ns):
-            signature = match.find(".//ns:signature", ns)
+        for match in matches:
+            if not match.tag.split("}")[-1].endswith("-match"):
+                continue
+
+            signature = match.find(qname("signature"))
             if signature is not None:
                 sig_acc = signature.attrib.get("ac", "")
                 sig_desc = signature.attrib.get("desc", "")
                 sig_name = signature.attrib.get("name", "")
 
                 # Add to signatures
-                if sig_acc and sig_acc not in [
-                    s["id"] for s in annotations[protein_id]["signatures"]
-                ]:
+                if sig_acc and unique_by_id(
+                    annotations[protein_id]["signatures"], sig_acc
+                ):
                     annotations[protein_id]["signatures"].append(
                         {"id": sig_acc, "name": sig_name, "description": sig_desc}
                     )
 
                 # Get InterPro domains
-                entry = match.find(".//ns:entry", ns)
+                entry = signature.find(qname("entry"))
                 if entry is not None:
                     entry_acc = entry.attrib.get("ac", "")
                     entry_desc = entry.attrib.get("desc", "")
                     entry_name = entry.attrib.get("name", "")
 
                     # Add to InterPro domains
-                    if entry_acc and entry_acc not in [
-                        d["id"] for d in annotations[protein_id]["interpro_domains"]
-                    ]:
+                    if entry_acc and unique_by_id(
+                        annotations[protein_id]["interpro_domains"], entry_acc
+                    ):
                         annotations[protein_id]["interpro_domains"].append(
                             {
                                 "id": entry_acc,
@@ -223,29 +247,35 @@ def parse_iprscan_xml(input_file, output_file=None, gene_dict=None):
                         )
 
                 # Get GO terms
-                for go_term in match.findall(".//ns:go-term", ns):
+                go_terms = signature.findall(f".//{qname('go-xref')}")
+                if not go_terms:
+                    go_terms = match.findall(f".//{qname('go-term')}")
+                for go_term in go_terms:
                     go_id = go_term.attrib.get("id", "")
                     go_name = go_term.attrib.get("name", "")
                     go_category = go_term.attrib.get("category", "")
 
                     # Add to GO terms
-                    if go_id and go_id not in [
-                        g["id"] for g in annotations[protein_id]["go_terms"]
-                    ]:
+                    if go_id and unique_by_id(
+                        annotations[protein_id]["go_terms"], go_id
+                    ):
                         annotations[protein_id]["go_terms"].append(
                             {"id": go_id, "name": go_name, "category": go_category}
                         )
 
                 # Get pathways
-                for pathway in match.findall(".//ns:pathway", ns):
+                pathways = signature.findall(f".//{qname('pathway-xref')}")
+                if not pathways:
+                    pathways = match.findall(f".//{qname('pathway')}")
+                for pathway in pathways:
                     pathway_id = pathway.attrib.get("id", "")
                     pathway_name = pathway.attrib.get("name", "")
                     pathway_db = pathway.attrib.get("db", "")
 
                     # Add to pathways
-                    if pathway_id and pathway_id not in [
-                        p["id"] for p in annotations[protein_id]["pathways"]
-                    ]:
+                    if pathway_id and unique_by_id(
+                        annotations[protein_id]["pathways"], pathway_id
+                    ):
                         annotations[protein_id]["pathways"].append(
                             {
                                 "id": pathway_id,