Merge branch 'develop' of https://github.com/easybuilders/easybuild-e…

…asyconfigs into wxWidgets-3.2.6

.github/workflows/tagbot.py

@@ -1,9 +1,11 @@
+# NOTE: In order to write comment and edit labels, this script requires workflows with write permissions.
+# It should not use any untrusted third party code, or any code checked into the repository itself
+# as that could indirectly grant PRs the ability to edit labels and comments on PRs.
+
 import os
 import git
 import requests
 import json
-import difflib
-from datetime import datetime
 from pathlib import Path
 
 
@@ -12,8 +14,7 @@ def get_first_commit_date(repo, file_path):
     if commits:
         return commits[-1].committed_date
     else:
-        print(f"{file_path} has no commit info, putting it last")
-        return datetime.datetime.min
+        raise ValueError(f'{file_path} has no commit info, this should not happen')
 
 
 def sort_by_added_date(repo, file_paths):
@@ -27,17 +28,6 @@ def similar_easyconfigs(repo, new_file):
     return sort_by_added_date(repo, possible_neighbours)
 
 
-def diff(old, new):
-    with open(old, 'r') as old_file, open(new, 'r') as new_file:
-        old_lines = list(old_file)
-        new_lines = list(new_file)
-        return ''.join(difflib.unified_diff(
-            old_lines,
-            new_lines,
-            fromfile=str(old),
-            tofile=str(new)))
-
-
 def pr_ecs(pr_diff):
     new_ecs = []
     changed_ecs = []
@@ -51,33 +41,38 @@ def pr_ecs(pr_diff):
 
 
 GITHUB_API_URL = 'https://api.github.com'
-event_path = os.getenv("GITHUB_EVENT_PATH")
-token = os.getenv("GH_TOKEN")
-repo = os.getenv("GITHUB_REPOSITORY")
-base_branch_name = os.getenv("GITHUB_BASE_REF")
-pr_ref_name = os.getenv("GITHUB_REF_NAME")
+event_path = os.getenv('GITHUB_EVENT_PATH')
+token = os.getenv('GH_TOKEN')
+repo = os.getenv('GITHUB_REPOSITORY')
+base_branch_name = os.getenv('GITHUB_BASE_REF')
 
 with open(event_path) as f:
     data = json.load(f)
 
 pr_number = data['pull_request']['number']
+# Can't rely on merge_commit_sha for pull_request_target as it might be outdated
+# merge_commit_sha = data['pull_request']['merge_commit_sha']
 
 print("PR number:", pr_number)
-print("Repo:", repo)
 print("Base branch name:", base_branch_name)
-print("PR ref:", pr_ref_name)
-
-gitrepo = git.Repo(".")
 
+# Change into "pr" checkout directory to allow diffs and glob to work on the same content
+os.chdir('pr')
+gitrepo = git.Repo('.')
 
 target_commit = gitrepo.commit('origin/' + base_branch_name)
-pr_commit = gitrepo.commit('pull/' + pr_ref_name)
-pr_diff = target_commit.diff(pr_commit)
+print("Target commit ref:", target_commit)
+merge_commit = gitrepo.head.commit
+print("Merge commit:", merge_commit)
+pr_diff = target_commit.diff(merge_commit)
 
 new_ecs, changed_ecs = pr_ecs(pr_diff)
+modified_workflow = any(item.a_path.startswith('.github/workflows/') for item in pr_diff)
+
 
-print("Changed ECs:", changed_ecs)
-print("Newly added ECs:", new_ecs)
+print("Changed ECs:", ', '.join(str(p) for p in changed_ecs))
+print("Newly added ECs:", ', '.join(str(p) for p in new_ecs))
+print("Modified workflow:", modified_workflow)
 
 new_software = 0
 updated_software = 0
@@ -116,15 +111,20 @@ def pr_ecs(pr_diff):
             comment += f'<summary>Diff against <code>{neighbour.name}</code></summary>\n\n'
             comment += f'[{neighbour}](https://github.com/{repo}/blob/{base_branch_name}/{neighbour})\n\n'
             comment += '```diff\n'
-            comment += diff(neighbour, new_file)
-            comment += '```\n</details>\n\n'
+            comment += gitrepo.git.diff(f'HEAD:{neighbour}', f'HEAD:{new_file}')
+            comment += '\n```\n</details>\n\n'
 
 print("Adjusting labels")
 current_labels = [label['name'] for label in data['pull_request']['labels']]
 
+label_checks = [(changed_ecs, 'change'),
+                (new_software, 'new'),
+                (updated_software, 'update'),
+                (modified_workflow, 'workflow')]
+
 labels_add = []
 labels_del = []
-for condition, label in [(changed_ecs, 'change'), (new_software, 'new'), (updated_software, 'update')]:
+for condition, label in label_checks:
     if condition and label not in current_labels:
         labels_add.append(label)
     elif not condition and label in current_labels:

.github/workflows/tagbot.yml

@@ -1,19 +1,43 @@
 name: Tagbot
-on: [pull_request]
+on: [pull_request_target]
+
+concurrency:
+  group: "${{ github.workflow }}-${{ github.event.pull_request.number }}"
+  cancel-in-progress: true
 
 jobs:
   tagbot:
+    # Note: can't rely on github.event.pull_request.merge_commit_sha because pull_request_target
+    # does not wait for github mergability check, and the value is outdated.
+    # Instead we merge manually in a temporary subdir "pr"
     runs-on: ubuntu-24.04
     permissions:
       pull-requests: write
     steps:
-    - uses: actions/checkout@v4
+    - name: Checkout base branch for workflow scripts
+      uses: actions/checkout@v4
+
+    - name: Checkout PR for computing diff into "pr" subdirectory
+      uses: actions/checkout@v4
       with:
+        ref: "${{ github.event.pull_request.head.sha }}"
+        path: 'pr'
         fetch-depth: 0
+
+    - name: Attempt test merge
+      id: merge
+      run: |
+        git config user.name "github-workflow"
+        git config user.email "github-workflow@github.com"
+        git merge --no-edit --no-ff origin/${{ github.event.pull_request.base.ref }}
+      continue-on-error: true
+      working-directory: pr
 
-    - run: |
-        # Make sure the script is unmodified
-        echo "8be2d295e8436ce557acc8a4d3b82a639913ae65de0d1a76871f21359b4e8d9f .github/workflows/tagbot.py"|sha256sum --check --status
+    - name: Abort if merge failed
+      if: steps.merge.outcome == 'failure'
+      run: |
+        echo "Merge conflict detected, failing job."
+        exit 1
 
     - name: set up Python
       uses: actions/setup-python@v5

easybuild/easyconfigs/a/ASE/ASE-3.23.0-gfbf-2023b.eb

@@ -0,0 +1,48 @@
+easyblock = 'PythonBundle'
+
+name = 'ASE'
+version = '3.23.0'
+
+homepage = 'https://wiki.fysik.dtu.dk/ase'
+description = """ASE is a python package providing an open source Atomic Simulation Environment
+ in the Python scripting language.
+
+From version 3.20.1 we also include the ase-ext package, it contains optional reimplementations
+in C of functions in ASE.  ASE uses it automatically when installed."""
+
+toolchain = {'name': 'gfbf', 'version': '2023b'}
+
+dependencies = [
+    ('Python', '3.11.5'),
+    ('Python-bundle-PyPI', '2023.10'),
+    ('SciPy-bundle', '2023.11'),
+    ('Flask', '3.0.0'),
+    ('matplotlib', '3.8.2'),
+    ('Tkinter', '%(pyver)s'),     # Needed by GUI of ASE
+    ('spglib-python', '2.5.0'),  # optional
+]
+
+use_pip = True
+sanity_pip_check = True
+
+exts_list = [
+    ('pytest-mock', '3.14.0', {
+        'checksums': ['2719255a1efeceadbc056d6bf3df3d1c5015530fb40cf347c0f9afac88410bd0'],
+    }),
+    ('ase', version, {
+        'checksums': ['91a2aa31d89bd90b0efdfe4a7e84264f32828b2abfc9f38e65e041ad76fec8ae'],
+    }),
+    ('ase-ext', '20.9.0', {
+        'checksums': ['a348b0e42cf9fdd11f04b3df002b0bf150002c8df2698ff08d3c8fc7a1223aed'],
+    }),
+]
+
+sanity_check_paths = {
+    'files': ['bin/ase'],
+    'dirs': ['lib/python%(pyshortver)s/site-packages'],
+}
+
+# make sure Tkinter is available, otherwise 'ase gui' will not work
+sanity_check_commands = ["python -c 'import tkinter' "]
+
+moduleclass = 'chem'

easybuild/easyconfigs/b/BCFtools/BCFtools-1.21-GCC-13.3.0.eb

@@ -0,0 +1,40 @@
+# This file is an EasyBuild reciPY as per https://github.com/easybuilders/easybuild
+#
+# Author: Jonas Demeulemeester
+# The Francis Crick Insitute, London, UK
+# Updated to 1.21 jpecar / EMBL
+
+easyblock = 'ConfigureMake'
+
+name = 'BCFtools'
+version = '1.21'
+
+homepage = 'https://www.htslib.org/'
+description = """Samtools is a suite of programs for interacting with high-throughput sequencing data.
+ BCFtools - Reading/writing BCF2/VCF/gVCF files and calling/filtering/summarising SNP and short indel sequence
+ variants"""
+
+toolchain = {'name': 'GCC', 'version': '13.3.0'}
+toolchainopts = {'pic': True}
+
+source_urls = ['https://github.com/samtools/%(namelower)s/releases/download/%(version)s']
+sources = [SOURCELOWER_TAR_BZ2]
+checksums = ['528a4cc1d3555368db75a700b22a3c95da893fd1827f6d304716dfd45ea4e282']
+
+dependencies = [
+    ('zlib', '1.3.1'),
+    ('HTSlib', '1.21'),
+    ('bzip2', '1.0.8'),
+    ('XZ', '5.4.5'),
+    ('GSL', '2.8'),
+]
+
+configopts = "--with-htslib=$EBROOTHTSLIB --enable-libgsl"
+
+
+sanity_check_paths = {
+    'files': ['bin/%(namelower)s', 'bin/plot-vcfstats', 'bin/vcfutils.pl'],
+    'dirs': ['libexec/%(namelower)s'],
+}
+
+moduleclass = 'bio'

easybuild/easyconfigs/d/Dask-ML/Dask-ML-2024.4.4-foss-2023a.eb

@@ -0,0 +1,50 @@
+easyblock = 'PythonBundle'
+
+name = 'Dask-ML'
+version = '2024.4.4'
+
+homepage = 'http://ml.dask.org/'
+description = """
+Dask-ML provides scalable machine learning in Python using Dask alongside popular machine
+learning libraries like Scikit-Learn, XGBoost, and others.
+"""
+
+toolchain = {'name': 'foss', 'version': '2023a'}
+
+builddependencies = [('hatchling', '1.18.0')]
+
+dependencies = [
+    ('Python', '3.11.3'),
+    ('scikit-learn', '1.3.1'),
+    ('dask', '2023.9.2'),
+    ('numba', '0.58.1'),
+    ('SciPy-bundle', '2023.07'),
+]
+
+use_pip = True
+sanity_pip_check = True
+
+exts_list = [
+    ('sparse', '0.15.4', {
+        # replace use of 'version_file' (which requires setuptools-scm >= 8.0) with 'write_to'
+        'preinstallopts': "sed -i 's/^version_file/write_to/' pyproject.toml && ",
+        'checksums': ['d4b1c57d24ff0f64f2fd5b5a95b49b7fb84ed207a26d7d58ce2764dcc5c72b84'],
+    }),
+    ('dask-glm', '0.3.2', {
+        'checksums': ['c947a566866698a01d79978ae73233cb5e838ad5ead6085143582c5e930b9a4a'],
+    }),
+    ('distributed', '2023.9.2', {
+        'checksums': ['b76b43be6a297c6cc6dc4eac7f5a05a8c6834aaf025ed37395d1d830448d540e'],
+    }),
+    ('multipledispatch', '1.0.0', {
+        'checksums': ['5c839915465c68206c3e9c473357908216c28383b425361e5d144594bf85a7e0'],
+    }),
+    ('packaging', '24.1', {
+        'checksums': ['026ed72c8ed3fcce5bf8950572258698927fd1dbda10a5e981cdf0ac37f4f002'],
+    }),
+    ('dask_ml', version, {
+        'checksums': ['7956910a49e1e31944280fdb311adf245da11ef410d67deb7a05c67c7d0c4498'],
+    }),
+]
+
+moduleclass = 'ai'

easybuild/easyconfigs/g/GSL/GSL-2.8-GCC-13.3.0.eb

@@ -0,0 +1,25 @@
+easyblock = 'ConfigureMake'
+
+name = 'GSL'
+version = '2.8'
+
+homepage = 'https://www.gnu.org/software/gsl/'
+description = """The GNU Scientific Library (GSL) is a numerical library for C and C++ programmers.
+ The library provides a wide range of mathematical routines such as random number generators, special functions
+ and least-squares fitting."""
+
+toolchain = {'name': 'GCC', 'version': '13.3.0'}
+toolchainopts = {'unroll': True, 'pic': True}
+
+source_urls = [GNU_SOURCE]
+sources = [SOURCELOWER_TAR_GZ]
+checksums = ['6a99eeed15632c6354895b1dd542ed5a855c0f15d9ad1326c6fe2b2c9e423190']
+
+sanity_check_paths = {
+    'files': ['bin/%s' % x for x in ['gsl-config', 'gsl-histogram', 'gsl-randist']] +
+             ['include/gsl/gsl_types.h'] +
+             ['lib/lib%s.%s' % (x, SHLIB_EXT) for x in ['gsl', 'gslcblas']],
+    'dirs': [],
+}
+
+moduleclass = 'numlib'

easybuild/easyconfigs/g/GTDB-Tk/GTDB-Tk-2.4.0-foss-2023a.eb

@@ -19,7 +19,7 @@ dependencies = [
     ('prodigal', '2.6.3'),
     ('HMMER', '3.4'),
     ('pplacer', '1.1.alpha19', '', SYSTEM),
-    ('FastANI', '1.34'),
+    ('skani', '0.2.2'),
     ('FastTree', '2.1.11'),
     ('Mash', '2.3'),
     ('tqdm', '4.66.1'),