Sweep: Update to G1rN/v8

[marcosfelt]

Update .github/workflows/ci.yml to use Gr1N/setup-poetry@v8 instead of v7

[sweep-ai]

Hey @marcosfelt,

I've started working on this issue. The plan is to update the version of setup-poetry action used in our GitHub workflow from v7 to v8. This change will be made in two places within the workflow file, specifically in the build and publish jobs.

Give me a minute!

Some code snippets I looked at (click to expand). If some file is missing from here, you can mention the path in the ticket description.

pura/tests/test_resolvers.py

Lines 91 to 128 in e208bca

	# # )
	# # correct_inchi = "ULNUEACLWYUUMO-UHFFFAOYSA-N"
	# # # correct_smiles = Chem.CanonSmiles(correct_smiles)
	# # input_compound, resolved_identifiers = resolved[0]
	# # assert resolved_identifiers[0].value == correct_inchi
	# def test_resolve_backup_identifiers():
	# logging.basicConfig(
	# level=logging.DEBUG,
	# format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
	# )
	# logger = logging.getLogger(__name__)
	# resolved = resolve_identifiers(
	# [
	# "Pd(OAc)2",
	# # "Josiphos SL-J001-1",
	# # "Rh(NBD)2BF4",
	# # "Dichloro(p-cymene)ruthenium(II) dimer",
	# # "DuPhos",
	# ],
	# input_identifer_type=CompoundIdentifierType.NAME,
	# output_identifier_type=CompoundIdentifierType.SMILES,
	# backup_identifier_types=[
	# CompoundIdentifierType.INCHI_KEY,
	# CompoundIdentifierType.CAS_NUMBER,
	# ],
	# services=[PubChem(autocomplete=False), CIR(), CAS()],
	# agreement=1,
	# silent=True,
	# )
	# print("\nResults\n")
	# for input_compound, resolved_identifiers in resolved:
	# print(input_compound, resolved_identifiers, "\n")
	# # Josiphos SL-J001-1 [CompoundIdentifier(identifier_type=<CompoundIdentifierType.SMILES: 2>, value='C1CCCC1.CC(C1CCCC1P(c1ccccc1)c1ccccc1)P(C1CCCCC1)C1CCCCC1.[Fe]', details=None)]

pura/manual_canonicalization.py

Lines 184 to 208 in e208bca

	def main():
	# loop = asyncio.new_event_loop()
	# asyncio.set_event_loop(loop)
	# loop.run_until_complete(_main())
	results = resolve_identifiers(
	list(catalyst_replacements.keys())[:2],
	output_identifier_type=CompoundIdentifierType.SMILES,
	input_identifer_type=CompoundIdentifierType.NAME,
	services=[LocalDatabase(return_canonical_only=True)],
	)
	for res in results:
	print(res)
	if __name__ == "__main__":
	# import logging
	# logging.basicConfig(level=logging.DEBUG)
	main()
	# from rdkit import Chem
	# for name, smi in catalyst_replacements.items():

pura/pura/services/db.py

Lines 1 to 46 in e208bca

	import logging
	from pura.services import Service
	from pura.compound import CompoundIdentifier, CompoundIdentifierType
	from aiohttp import ClientSession
	from typing import List, Optional, Tuple, Union
	from databases import Database as AsyncDatabase
	import sqlalchemy
	import pandas as pd
	import asyncio
	import nest_asyncio
	from rdkit import Chem
	from sqlalchemy.dialects.sqlite import insert
	from importlib_resources import files
	import pathlib
	DATA_PATH = pathlib.Path(files("pura.data").joinpath("pura.db"))
	metadata = sqlalchemy.MetaData()
	dialect = sqlalchemy.dialects.sqlite.dialect()
	# Schema
	# compound
	# --------------
	# id: INT, KEY
	# inchi_key: STR
	# identifiers
	# --------------
	# id: INT, KEY
	# identifier_type: ENUM
	# identifier_value: STR
	# compound_id: Foreign Key to compound(id)
	# canonical: BOOL -> True if this is the canonical identifier for the compound
	metadata = sqlalchemy.MetaData()
	compound_table = sqlalchemy.Table(
	"compound",
	metadata,
	sqlalchemy.Column("id", sqlalchemy.Integer, primary_key=True),
	sqlalchemy.Column("inchi", sqlalchemy.String, nullable=False),
	sqlalchemy.UniqueConstraint("inchi", sqlite_on_conflict="IGNORE"),
	)

pura/pura/resolvers.py

Lines 260 to 327 in e208bca

	)
	)
	async def _resolve(
	self,
	input_compounds: List[Compound],
	output_identifier_type: CompoundIdentifierType,
	backup_identifier_types: Optional[List[CompoundIdentifierType]] = None,
	agreement: Optional[int] = 1,
	batch_size: Optional[int] = None,
	n_retries: Optional[int] = 3,
	**kwargs,
	) -> List[Tuple[Compound, Union[List[CompoundIdentifier], None]]]:
	"""This is the async function with the same API as resolve"""
	# Run setup for services
	for service in self.services:
	await service.setup()
	n_identifiers = len(input_compounds)
	if batch_size is None:
	batch_size = 10 if n_identifiers >= 10 else n_identifiers
	n_batches = n_identifiers // batch_size
	n_batches += 0 if n_identifiers % batch_size == 0 else 1
	resolved_identifiers = []
	backup_identifier_types = (
	backup_identifier_types if backup_identifier_types is not None else []
	)
	progress_bar_type = kwargs.get("progress_bar_type", "tqdm")
	if progress_bar_type == "tqdm":
	progress_bar = tqdm
	elif progress_bar_type == "streamlit":
	from stqdm import stqdm
	progress_bar = stqdm
	# Iterate through batches
	for batch in progress_bar(range(n_batches), position=0, desc="Batch"):
	# Get subset of data
	start = batch * batch_size
	batch_identifiers = input_compounds[start : start + batch_size]
	# Start aiohttp session
	async with ClientSession() as session:
	# Create series of tasks to run in parallel
	tasks = [
	self._resolve_one_compound(
	session,
	compound_identifier,
	output_identifier_type,
	backup_identifier_types,
	agreement,
	n_retries=n_retries,
	)
	for compound_identifier in batch_identifiers
	]
	batch_bar = progress_bar(
	asyncio.as_completed(tasks),
	total=len(tasks),
	desc=f"Batch {batch} Progress",
	position=1,
	leave=True,
	)
	resolved_identifiers.extend([await f for f in batch_bar])
	batch_bar.clear()
	for service in self.services:
	await service.teardown()

pura/.github/workflows/ci.yml

Lines 1 to 149 in e208bca

	name: Test and Publish
	on:
	push:
	pull_request:
	branches:
	# Branches from forks have the form 'user:branch-name' so we only run
	# this job on pull_request events for branches that look like fork
	# branches. Without this we would end up running this job twice for non
	# forked PRs, once for the push and then once for opening the PR.
	- '**:**'
	jobs:
	# Build the package
	build:
	runs-on: ubuntu-latest
	steps:
	- name: Checkout repository
	uses: actions/checkout@v2
	- name: Install python
	uses: actions/setup-python@v2
	with:
	python-version: '3.9'
	- name: Install poetry
	uses: Gr1N/setup-poetry@v7
	- name: Build package
	run: poetry build
	- name: Upload built package
	uses: actions/upload-artifact@v3
	with:
	name: dist
	path: dist/
	retention-days: 1
	# Run pytest using built package
	test:
	needs: build
	runs-on: ubuntu-latest
	strategy:
	matrix:
	python: ["3.8", "3.9", "3.10"]
	steps:
	- name: Checkout repository
	uses: actions/checkout@v2
	- name: Install python
	uses: actions/setup-python@v2
	with:
	python-version: ${{ matrix.python }}
	cache: 'pip'
	cache-dependency-path: "poetry.lock"
	- name: Download built package
	uses: actions/download-artifact@v3
	with:
	name: dist
	- name: Install pura and pytest
	shell: bash
	run: |
	WHL_NAME=$(ls pura-*.whl)
	pip install ${WHL_NAME}[experiments,entmoot] pytest
	- name: Run tests
	shell: bash
	run: pytest
	# Publish to pypi on version change
	# This is based on https://github.com/coveooss/pypi-publish-with-poetry
	publish:
	needs: test
	runs-on: ubuntu-latest
	steps:
	- name: Checkout repository
	uses: actions/checkout@v2
	- name: Install python
	uses: actions/setup-python@v2
	with:
	python-version: '3.9'
	- name: Download built package
	uses: actions/download-artifact@v3
	with:
	name: dist
	path: dist/
	- name: Install poetry
	uses: Gr1N/setup-poetry@v7
	- name: Install coveo-pypi-cli
	run: pip install coveo-pypi-cli
	- name: Determine the version for this release from the build
	id: current
	run: |
	BUILD_VER="$(ls dist/pura-*.tar.gz)"
	echo "Path: $BUILD_VER"
	if [[ $BUILD_VER =~ (pura-)([^,][0-9.]{4}) ]]; then
	echo "::set-output name=version::${BASH_REMATCH[2]}"
	echo "Version of build: ${BASH_REMATCH[2]}"
	else
	echo "No version found found"
	fi
	- name: Get latest published version
	id: published
	run: |
	PUB_VER="$(pypi current-version pura)"
	echo "::set-output name=version::$PUB_VER"
	echo "Latest published version: $PUB_VER"
	- name: Publish to pypi if new version
	if: (steps.current.outputs.version != steps.published.outputs.version)
	shell: bash
	run: |
	poetry config pypi-token.pypi ${{ secrets.PYPI_TOKEN }}
	if [[ '${{ github.ref_name }}' == 'main' ]]; then
	poetry publish
	else
	echo "Dry run of publishing the package"
	poetry publish --dry-run
	fi
	- name: Tag repository
	shell: bash
	id: get-next-tag
	if: (steps.current.outputs.version != steps.published.outputs.version)
	run: |
	TAG_NAME=${{ steps.current.outputs.version }}
	echo "::set-output name=tag-name::$TAG_NAME"
	echo "This release will be tagged as $TAG_NAME"
	git config user.name "github-actions"
	git config user.email "[email protected]"
	git tag --annotate --message="Automated tagging system" $TAG_NAME ${{ github.sha }}
	- name: Push the tag
	if: (steps.current.outputs.version != steps.published.outputs.version)
	env:
	TAG_NAME: ${{ steps.current.outputs.version }}
	run: |
	if [[ ${{ github.ref_name }} == 'main' ]]; then
	git push origin $TAG_NAME
	else
	echo "If this was the main branch, I would push a new tag named $TAG_NAME"

---

I'm a bot that handles simple bugs and feature requests but I might make mistakes. Please be kind!

[sweep-ai]

Hey @marcosfelt,

I've started working on the PR for this issue. The plan is pretty straightforward: I'll be updating the version of Gr1N/setup-poetry from v7 to v8 in the .github/workflows/ci.yml file.

Give me a minute!

Best,
Sweep bot

Some code snippets I looked at (click to expand). If some file is missing from here, you can mention the path in the ticket description.

pura/manual_canonicalization.py

Lines 1 to 3 in e208bca

	# Dictionary for manual canonicalization
	# initialize a dict that maps catalysts to the humanly cleaned smiles

pura/pura/resolvers.py

Line 1 in e208bca

from pura.compound import (

pura/pura/services/db.py

Lines 1 to 39 in e208bca

	import logging
	from pura.services import Service
	from pura.compound import CompoundIdentifier, CompoundIdentifierType
	from aiohttp import ClientSession
	from typing import List, Optional, Tuple, Union
	from databases import Database as AsyncDatabase
	import sqlalchemy
	import pandas as pd
	import asyncio
	import nest_asyncio
	from rdkit import Chem
	from sqlalchemy.dialects.sqlite import insert
	from importlib_resources import files
	import pathlib
	DATA_PATH = pathlib.Path(files("pura.data").joinpath("pura.db"))
	metadata = sqlalchemy.MetaData()
	dialect = sqlalchemy.dialects.sqlite.dialect()
	# Schema
	# compound
	# --------------
	# id: INT, KEY
	# inchi_key: STR
	# identifiers
	# --------------
	# id: INT, KEY
	# identifier_type: ENUM
	# identifier_value: STR
	# compound_id: Foreign Key to compound(id)
	# canonical: BOOL -> True if this is the canonical identifier for the compound
	metadata = sqlalchemy.MetaData()
	compound_table = sqlalchemy.Table(

pura/pura/services/pubchem.py

Lines 272 to 301 in e208bca

	if isinstance(identifier, int):
	identifier = str(identifier)
	if not isinstance(identifier, text_types):
	identifier = ",".join(str(x) for x in identifier)
	# Filter None values from kwargs
	kwargs = dict((k, v) for k, v in kwargs.items() if v is not None)
	# Build API URL
	urlid, postdata = None, {}
	if namespace == "sourceid":
	identifier = identifier.replace("/", ".")
	if (
	namespace in ["listkey", "formula", "sourceid"]
	or searchtype == "xref"
	or (searchtype and namespace == "cid")
	or domain == "sources"
	):
	urlid = quote(identifier.encode("utf8"))
	else:
	# postdata = urlencode([(namespace, identifier)]).encode("utf8")
	postdata = {namespace: identifier}
	comps = filter(
	None, [api_base, domain, searchtype, namespace, urlid, operation, output]
	)
	apiurl = "/".join(comps)
	if kwargs:
	apiurl += "?%s" % urlencode(kwargs)
	# Make request
	logger.debug("Request URL: %s", apiurl)
	logger.debug("Request data: %s", postdata)

pura/.github/workflows/ci.yml

Lines 1 to 149 in e208bca

	name: Test and Publish
	on:
	push:
	pull_request:
	branches:
	# Branches from forks have the form 'user:branch-name' so we only run
	# this job on pull_request events for branches that look like fork
	# branches. Without this we would end up running this job twice for non
	# forked PRs, once for the push and then once for opening the PR.
	- '**:**'
	jobs:
	# Build the package
	build:
	runs-on: ubuntu-latest
	steps:
	- name: Checkout repository
	uses: actions/checkout@v2
	- name: Install python
	uses: actions/setup-python@v2
	with:
	python-version: '3.9'
	- name: Install poetry
	uses: Gr1N/setup-poetry@v7
	- name: Build package
	run: poetry build
	- name: Upload built package
	uses: actions/upload-artifact@v3
	with:
	name: dist
	path: dist/
	retention-days: 1
	# Run pytest using built package
	test:
	needs: build
	runs-on: ubuntu-latest
	strategy:
	matrix:
	python: ["3.8", "3.9", "3.10"]
	steps:
	- name: Checkout repository
	uses: actions/checkout@v2
	- name: Install python
	uses: actions/setup-python@v2
	with:
	python-version: ${{ matrix.python }}
	cache: 'pip'
	cache-dependency-path: "poetry.lock"
	- name: Download built package
	uses: actions/download-artifact@v3
	with:
	name: dist
	- name: Install pura and pytest
	shell: bash
	run: |
	WHL_NAME=$(ls pura-*.whl)
	pip install ${WHL_NAME}[experiments,entmoot] pytest
	- name: Run tests
	shell: bash
	run: pytest
	# Publish to pypi on version change
	# This is based on https://github.com/coveooss/pypi-publish-with-poetry
	publish:
	needs: test
	runs-on: ubuntu-latest
	steps:
	- name: Checkout repository
	uses: actions/checkout@v2
	- name: Install python
	uses: actions/setup-python@v2
	with:
	python-version: '3.9'
	- name: Download built package
	uses: actions/download-artifact@v3
	with:
	name: dist
	path: dist/
	- name: Install poetry
	uses: Gr1N/setup-poetry@v7
	- name: Install coveo-pypi-cli
	run: pip install coveo-pypi-cli
	- name: Determine the version for this release from the build
	id: current
	run: |
	BUILD_VER="$(ls dist/pura-*.tar.gz)"
	echo "Path: $BUILD_VER"
	if [[ $BUILD_VER =~ (pura-)([^,][0-9.]{4}) ]]; then
	echo "::set-output name=version::${BASH_REMATCH[2]}"
	echo "Version of build: ${BASH_REMATCH[2]}"
	else
	echo "No version found found"
	fi
	- name: Get latest published version
	id: published
	run: |
	PUB_VER="$(pypi current-version pura)"
	echo "::set-output name=version::$PUB_VER"
	echo "Latest published version: $PUB_VER"
	- name: Publish to pypi if new version
	if: (steps.current.outputs.version != steps.published.outputs.version)
	shell: bash
	run: |
	poetry config pypi-token.pypi ${{ secrets.PYPI_TOKEN }}
	if [[ '${{ github.ref_name }}' == 'main' ]]; then
	poetry publish
	else
	echo "Dry run of publishing the package"
	poetry publish --dry-run
	fi
	- name: Tag repository
	shell: bash
	id: get-next-tag
	if: (steps.current.outputs.version != steps.published.outputs.version)
	run: |
	TAG_NAME=${{ steps.current.outputs.version }}
	echo "::set-output name=tag-name::$TAG_NAME"
	echo "This release will be tagged as $TAG_NAME"
	git config user.name "github-actions"
	git config user.email "[email protected]"
	git tag --annotate --message="Automated tagging system" $TAG_NAME ${{ github.sha }}
	- name: Push the tag
	if: (steps.current.outputs.version != steps.published.outputs.version)
	env:
	TAG_NAME: ${{ steps.current.outputs.version }}
	run: |
	if [[ ${{ github.ref_name }} == 'main' ]]; then
	git push origin $TAG_NAME
	else
	echo "If this was the main branch, I would push a new tag named $TAG_NAME"

---

I'm a bot that handles simple bugs and feature requests but I might make mistakes. Please be kind!