NatLibFi · juhoinkinen · Mar 25, 2024 · Feb 23, 2024 · Feb 23, 2024 · Feb 23, 2024
diff --git a/.git-blame-ignore-revs b/.git-blame-ignore-revs
@@ -2,3 +2,5 @@
 3bc18907354a40f1d89dca1833a2719ba7fb0933
 # Reorder import statements with isort
 68a72c5a603283f70abce2651dcde9c6f0177c41
+# Migrate code style to Black 24
+d4dbd73fe6a91964af82fbf6e6cb8d70b77569a3
diff --git a/.github/workflows/cicd.yml b/.github/workflows/cicd.yml
@@ -10,7 +10,7 @@ on:
 env:
   PIPX_HOME: "/home/runner/.cache/pipx"
   PIPX_BIN_DIR: "/home/runner/.local/bin"
-  POETRY_VERSION: "1.5.1"
+  POETRY_VERSION: "1.8.0"
 permissions:
   contents: read
 jobs:

diff --git a/annif/analyzer/__init__.py b/annif/analyzer/__init__.py
@@ -1,4 +1,5 @@
 """Collection of language-specific analyzers and analyzer registry for Annif"""
+
 from __future__ import annotations
 
 import re

diff --git a/annif/analyzer/analyzer.py b/annif/analyzer/analyzer.py
@@ -1,4 +1,5 @@
 """Common functionality for analyzers."""
+
 from __future__ import annotations
 
 import abc

diff --git a/annif/analyzer/simple.py b/annif/analyzer/simple.py
@@ -1,4 +1,5 @@
 """Simple analyzer for Annif. Only folds words to lower case."&q
F438
uot;"
+
 from __future__ import annotations
 
 from . import analyzer

diff --git a/annif/analyzer/simplemma.py b/annif/analyzer/simplemma.py
@@ -1,4 +1,5 @@
 """Simplemma analyzer for Annif, based on simplemma lemmatizer."""
+
 from __future__ import annotations
 
 import simplemma

diff --git a/annif/analyzer/snowball.py b/annif/analyzer/snowball.py
@@ -1,4 +1,5 @@
 """Snowball analyzer for Annif, based on nltk Snowball stemmer."""
+
 from __future__ import annotations
 
 import functools

diff --git a/annif/analyzer/spacy.py b/annif/analyzer/spacy.py
@@ -1,4 +1,5 @@
 """spaCy analyzer for Annif which uses spaCy for lemmatization"""
+
 from __future__ import annotations
 
 import annif.util

diff --git a/annif/analyzer/voikko.py b/annif/analyzer/voikko.py
@@ -1,4 +1,5 @@
 """Voikko analyzer for Annif, based on libvoikko library."""
+
 from __future__ import annotations
 
 import functools

diff --git a/annif/backend/__init__.py b/annif/backend/__init__.py
@@ -1,4 +1,5 @@
 """Registry of backend types for Annif"""
+
 from __future__ import annotations
 
 from typing import TYPE_CHECKING, Type

diff --git a/annif/backend/backend.py b/annif/backend/backend.py
@@ -1,4 +1,5 @@
 """Common functionality for backends."""
+
 from __future__ import annotations
 
 import abc

diff --git a/annif/backend/dummy.py b/annif/backend/dummy.py
@@ -1,4 +1,5 @@
 """Dummy backend for testing basic interaction of projects and backends"""
+
 from __future__ import annotations
 
 from typing import TYPE_CHECKING, Any

diff --git a/annif/backend/ensemble.py b/annif/backend/ensemble.py
@@ -1,4 +1,5 @@
 """Ensemble backend that combines results from multiple projects"""
+
 from __future__ import annotations
 
 from typing import TYPE_CHECKING, Any

diff --git a/annif/backend/fasttext.py b/annif/backend/fasttext.py
@@ -1,4 +1,5 @@
 """Annif backend using the fastText classifier"""
+
 from __future__ import annotations
 
 import collections

diff --git a/annif/backend/http.py b/annif/backend/http.py
@@ -1,5 +1,6 @@
 """HTTP/REST client backend that makes calls to a web service
 and returns the results"""
+
 from __future__ import annotations
 
 import importlib

diff --git a/annif/backend/hyperopt.py b/annif/backend/hyperopt.py
@@ -1,4 +1,5 @@
 """Hyperparameter optimization functionality for backends"""
+
 from __future__ import annotations
 
 import abc

diff --git a/annif/backend/mixins.py b/annif/backend/mixins.py
@@ -1,4 +1,5 @@
 """Annif backend mixins that can be used to implement features"""
+
 from __future__ import annotations
 
 import abc

diff --git a/annif/backend/mllm.py b/annif/backend/mllm.py
@@ -1,4 +1,5 @@
 """Maui-like Lexical Matching backend"""
+
 from __future__ import annotations
 
 import os.path

diff --git a/annif/backend/nn_ensemble.py b/annif/backend/nn_ensemble.py
@@ -1,5 +1,6 @@
 """Neural network based ensemble backend that combines results from multiple
 projects."""
+
 from __future__ import annotations
 
 import os.path

diff --git a/annif/backend/omikuji.py b/annif/backend/omikuji.py
@@ -1,4 +1,5 @@
 """Annif backend using the Omikuji classifier"""
+
 from __future__ import annotations
 
 import os.path

diff --git a/annif/backend/pav.py b/annif/backend/pav.py
@@ -2,6 +2,7 @@
 learns which concept suggestions from each backend are trustworthy using the
 PAV algorithm, a.k.a. isotonic regression, to turn raw scores returned by
 individual backends into probabilities."""
+
 from __future__ import annotations
 
 import os.path
@@ -69,13 +70,15 @@ def _merge_source_batches(
             reg_models = self._get_model(project_id)
             pav_batch = [
                 [
-                    SubjectSuggestion(
-                        subject_id=sugg.subject_id,
-                        score=reg_models[sugg.subject_id].predict([sugg.score])[0],
-                    )
-                    if sugg.subject_id in reg_models
-                    else SubjectSuggestion(
-                        subject_id=sugg.subject_id, score=sugg.score
+                    (
+                        SubjectSuggestion(
+                            subject_id=sugg.subject_id,
+                            score=reg_models[sugg.subject_id].predict([sugg.score])[0],
+                        )
+                        if sugg.subject_id in reg_models
+                        else SubjectSuggestion(
+                            subject_id=sugg.subject_id, score=sugg.score
+                        )
                     )  # default to raw score
                     for sugg in result
                 ]

diff --git a/annif/backend/svc.py b/annif/backend/svc.py
@@ -1,4 +1,5 @@
 """Annif backend using a SVM classifier"""
+
 from __future__ import annotations
 
 import os.path

diff --git a/annif/backend/tfidf.py b/annif/backend/tfidf.py
@@ -1,5 +1,6 @@
 """Backend that returns most similar subjects based on similarity in sparse
 TF-IDF normalized bag-of-words vector space"""
+
 from __future__ import annotations
 
 import os.path

diff --git a/annif/backend/yake.py b/annif/backend/yake.py
@@ -1,4 +1,5 @@
 """Annif backend using Yake keyword extraction"""
+
 # For license remarks of this backend see README.md:
 # https://github.com/NatLibFi/Annif#license.
 from __future__ import annotations

diff --git a/annif/cli.py b/annif/cli.py
@@ -1,7 +1,6 @@
 """Definitions for command-line (Click) commands for invoking Annif
 operations and printing the results to console."""
 
-
 import collections
 import importlib
 import json

diff --git a/annif/cli_util.py b/annif/cli_util.py
@@ -1,4 +1,5 @@
 """Utility functions for Annif CLI commands"""
+
 from __future__ import annotations
 
 import collections

diff --git a/annif/config.py b/annif/config.py
@@ -1,4 +1,5 @@
 """Configuration file handling"""
+
 from __future__ import annotations
 
 import configparser

diff --git a/annif/corpus/__init__.py b/annif/corpus/__init__.py
@@ -1,6 +1,5 @@
 """Annif corpus operations"""
 
-
 from .combine import CombinedCorpus
 from .document import (
     DocumentDirectory,

diff --git a/annif/corpus/combine.py b/annif/corpus/combine.py
@@ -1,4 +1,5 @@
 """Class for combining multiple corpora so they behave like a single corpus"""
+
 from __future__ import annotations
 
 import itertools

diff --git a/annif/corpus/document.py b/annif/corpus/document.py
@@ -1,4 +1,5 @@
 """Clases for supporting document corpora"""
+
 from __future__ import annotations
 
 import glob

diff --git a/annif/corpus/skos.py b/annif/corpus/skos.py
@@ -1,4 +1,5 @@
 """Support for subjects loaded from a SKOS/RDF file"""
+
 from __future__ import annotations
 
 import collections
@@ -83,11 +84,15 @@ def languages(self) -> set[str]:
     def _concept_labels(self, concept: URIRef) -> dict[str, str]:
         by_lang = self.get_concept_labels(concept, self.PREF_LABEL_PROPERTIES)
         return {
-            lang: by_lang[lang][0]
-            if by_lang[lang]  # correct lang
-            else by_lang[None][0]
-            if by_lang[None]  # no language
-            else self.graph.namespace_manager.qname(concept)
+            lang: (
+                by_lang[lang][0]
+                if by_lang[lang]  # correct lang
+                else (
+                    by_lang[None][0]
+                    if by_lang[None]  # no language
+                    else self.graph.namespace_manager.qname(concept)
+                )
+            )
             for lang in self.languages
         }
 

diff --git a/annif/corpus/subject.py b/annif/corpus/subject.py
@@ -1,4 +1,5 @@
 """Classes for supporting subject corpora expressed as directories or files"""
+
 from __future__ import annotations
 
 import csv

diff --git a/annif/corpus/types.py b/annif/corpus/types.py
@@ -1,4 +1,5 @@
 """Basic types for document and subject corpora"""
+
 from __future__ import annotations
 
 import abc

diff --git a/annif/datadir.py b/annif/datadir.py
@@ -1,4 +1,5 @@
 """Mixin class for types that need a data directory"""
+
 from __future__ import annotations
 
 import os

diff --git a/annif/eval.py b/annif/eval.py
@@ -1,4 +1,5 @@
 """Evaluation metrics for Annif"""
+
 from __future__ import annotations
 
 import warnings
@@ -63,10 +64,10 @@ def ndcg_score(y_true: csr_array, y_pred: csr_array, limit: int | None = None) -
 
     scores = np.ones(y_true.shape[0], dtype=np.float32)
     for i in range(y_true.shape[0]):
-        true = y_true.getrow(i)
+        true = y_true[[i]]
         idcg = dcg_score(true, true, limit)
         if idcg > 0:
-            pred = y_pred.getrow(i)
+            pred = y_pred[[i]]
             dcg = dcg_score(true, pred, limit)
             scores[i] = dcg / idcg
 
@@ -86,9 +87,9 @@ def __init__(self, subject_index: SubjectIndex) -> None:
 
     def evaluate_many(
         self,
-        suggestion_batch: list[list[SubjectSuggestion]]
-        | SuggestionBatch
-        | list[Iterator],
+        suggestion_batch: (
+            list[list[SubjectSuggestion]] | SuggestionBatch | list[Iterator]
+        ),
         gold_subject_batch: Sequence[SubjectSet],
     ) -> None:
         if not isinstance(suggestion_batch, SuggestionBatch):

diff --git a/annif/exception.py b/annif/exception.py
@@ -1,4 +1,5 @@
 """Custom exceptions used by Annif"""
+
 from __future__ import annotations
 
 from click import ClickException

diff --git a/annif/lexical/mllm.py b/annif/lexical/mllm.py
@@ -1,4 +1,5 @@
 """MLLM (Maui-like Lexical Matchin) model for Annif""&
10000
quot;
+
 from __future__ import annotations
 
 import collections

diff --git a/annif/lexical/tokenset.py b/annif/lexical/tokenset.py
@@ -1,4 +1,5 @@
 """Index for fast matching of token sets."""
+
 from __future__ import annotations
 
 import collections

diff --git a/annif/lexical/util.py b/annif/lexical/util.py
@@ -1,4 +1,5 @@
 """Utility methods for lexical algorithms"""
+
 from __future__ import annotations
 
 import collections

diff --git a/annif/openapi/validation.py b/annif/openapi/validation.py
@@ -1,4 +1,5 @@
 """Custom validator for the Annif API."""
+
 from __future__ import annotations
 
 import logging

diff --git a/annif/parallel.py b/annif/parallel.py
@@ -1,4 +1,5 @@
 """Parallel processing functionality for Annif"""
+
 from __future__ import annotations
 
 import multiprocessing

diff --git a/annif/project.py b/annif/project.py
@@ -1,4 +1,5 @@
 """Project management functionality for Annif"""
+
 from __future__ import annotations
 
 import enum

diff --git a/annif/registry.py b/annif/registry.py
@@ -1,4 +1,5 @@
 """Registry that keeps track of Annif projects"""
+
 from __future__ import annotations
 
 import re

diff --git a/annif/rest.py b/annif/rest.py
@@ -1,5 +1,6 @@
 """Definitions for REST API operations. These are wired via Connexion to
 methods defined in the OpenAPI specification."""
+
 from __future__ import annotations
 
 import importlib

diff --git a/annif/suggestion.py b/annif/suggestion.py
@@ -1,4 +1,5 @@
 """Representing suggested subjects."""
+
 from __future__ import annotations
 
 import collections
@@ -38,7 +39,7 @@ def filter_suggestion(
 
     data, rows, cols = [], [], []
     for row in range(preds.shape[0]):
-        arow = preds.getrow(row)
+        arow = preds[[row]]
         if limit is not None and limit < len(arow.data):
             topk_idx = arow.data.argpartition(-limit)[-limit:]
         else:

diff --git a/annif/transform/__init__.py b/annif/transform/__init__.py
@@ -1,4 +1,5 @@
 """Functionality for obtaining text transformation from string specification"""
+
 from __future__ import annotations
 
 import re

diff --git a/annif/transform/inputlimiter.py b/annif/transform/inputlimiter.py
@@ -1,5 +1,6 @@
 """A simple transformation that truncates the text of input documents to a
 given character length."""
+
 from __future__ import annotations
 
 from typing import TYPE_CHECKING

diff --git a/annif/transform/langfilter.py b/annif/transform/langfilter.py
@@ -1,5 +1,6 @@
 """Transformation filtering out parts of a text that are in a language
 different from the language of the project."""
+
 from __future__ import annotations
 
 from typing import TYPE_CHECKING

diff --git a/annif/transform/transform.py b/annif/transform/transform.py
@@ -1,4 +1,5 @@
 """Common functionality for transforming text of input documents."""
+
 from __future__ import annotations
 
 import abc

diff --git a/annif/util.py b/annif/util.py
@@ -1,4 +1,5 @@
 """Utility functions for Annif"""
+
 from __future__ import annotations
 
 import glob

diff --git a/annif/vocab.py b/annif/vocab.py
@@ -1,4 +1,5 @@
 """Vocabulary management functionality for Annif"""
+
 from __future__ import annotations
 
 import os.path