fix pylint warnings

Gerit Wagner · Gerit Wagner · commit dc30decf9a10 · 2025-10-26T19:53:29.000+01:00
diff --git a/colrev/packages/colrev_project/src/colrev_project.py b/colrev/packages/colrev_project/src/colrev_project.py
@@ -107,9 +107,10 @@ def _load_records_to_import(self, *, project_url: str, project_name: str) -> dic
         Repo.clone_from(project_url, temp_path, depth=1)
 
         try:
-            import colrev.review_manager
+            # pylint: disable=import-outside-toplevel
+            import colrev.review_manager as colrev_review_manager
 
-            project_review_manager = colrev.review_manager.ReviewManager(
+            project_review_manager = colrev_review_manager.ReviewManager(
                 path_str=str(temp_path)
             )
         except colrev_exceptions.RepoSetupError as exc:
diff --git a/colrev/packages/dblp/src/dblp.py b/colrev/packages/dblp/src/dblp.py
@@ -41,7 +41,6 @@ class DBLPSearchSourceSettings(colrev.search_file.ExtendedSearchFile, BaseModel)
     filepath: Path
     search_type: SearchType
     search_parameters: dict
-    version: typing.Optional[str]
     comment: typing.Optional[str]
 
     _details = {
diff --git a/colrev/packages/files_dir/src/files_dir.py b/colrev/packages/files_dir/src/files_dir.py
@@ -41,8 +41,6 @@ class FilesSearchSource(base_classes.SearchSourcePackageBaseClass):
 
     CURRENT_SYNTAX_VERSION = "0.1.0"
 
-    # pylint: disable=too-many-instance-attributes
-
     endpoint = "colrev.files_dir"
     source_identifier = Fields.FILE
     search_types = [SearchType.FILES]
@@ -84,6 +82,13 @@ def __init__(
 
         self.local_index = colrev.env.local_index.LocalIndex()
 
+        # SearchSource only supported in the context of a CoLRev project
+        # pylint: disable=import-outside-toplevel
+        import colrev.review_manager as colrev_review_manager
+
+        self.review_manager = colrev_review_manager.ReviewManager()
+        colrev.ops.check.CheckOperation(self.review_manager)
+
     def _update_if_pdf_renamed(
         self,
         *,
@@ -641,12 +646,6 @@ def _run_dir_search(
     def search(self, rerun: bool) -> None:
         """Run a search of a Files directory"""
 
-        # TODO / TBD: replace review_manager?
-        import colrev.review_manager
-
-        self.review_manager = colrev.review_manager.ReviewManager()
-        colrev.ops.check.CheckOperation(self.review_manager)
-
         self.rerun = rerun
         self._validate_source()
 
diff --git a/colrev/packages/github/README.md b/colrev/packages/github/README.md
@@ -6,7 +6,7 @@
 
 ### API search
 
-ℹ️ Restriction: API searches require an GitHub access token to retrieve all the relevant meta data.
+ℹ️ Restriction: API searches require an GitHub access token to retrieve all the relevant meta data. Store the token in the `GITHUB_API_TOKEN` environment variable (for example with `export GITHUB_API_TOKEN="<your-token>"`). If it is not set you will be prompted to enter the token and it will be stored for the current session.
 
 In your GitHub account, a classic [personal access tokens](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens) can be created. It is not necessary to select any scopes.
 
diff --git a/colrev/packages/github/src/github_search_source.py b/colrev/packages/github/src/github_search_source.py
@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import logging
+import os
 import re
 import typing
 from multiprocessing import Lock
@@ -155,8 +156,7 @@ def add_endpoint(
 
     @classmethod
     def _get_api_key(cls) -> str:
-        env_man = colrev.env.environment_manager.EnvironmentManager()
-        api_key = env_man.get_settings_by_key(cls.SETTINGS["api_key"])
+        api_key = os.getenv("GITHUB_API_TOKEN")
         if api_key is not None and is_github_api_key({}, api_key):
             return api_key
 
@@ -169,8 +169,8 @@ def _get_api_key(cls) -> str:
         ]
         answers = inquirer.prompt(questions)
         input_key = answers["github_api_key"]
-        env_man.update_registry(cls.SETTINGS["api_key"], input_key)
-        print("API key saved in environment settings.")
+        os.environ["GITHUB_API_TOKEN"] = input_key
+        print("API key saved in environment variables.")
         return input_key
 
     def _run_api_search(
@@ -190,6 +190,8 @@ def _run_api_search(
         github_connection = Github(auth=auth)
 
         # Searching on Github
+        # TODO : check: does not seem to retrieve all repositories?!
+        # (e.g., for "colrev", it should be 25, but only 19 are retrieved)
         repositories = github_connection.search_repositories(query=query)
 
         # Saving search results
diff --git a/colrev/packages/github/src/record_transformer.py b/colrev/packages/github/src/record_transformer.py
@@ -90,15 +90,13 @@ def _update_record_based_on_citation_cff(
     try:
         content = repo.get_contents("CITATION.cff")
         citation_data = content.decoded_content.decode("utf-8")
-
         _set_title(record_dict=record_dict, citation_data=citation_data)
         _set_authors(record_dict=record_dict, citation_data=citation_data)
         _set_year_and_release_date(record_dict=record_dict, citation_data=citation_data)
         _set_version(record_dict, citation_data)
         _set_url(record_dict=record_dict, citation_data=citation_data)
-
     except GithubException:
-        record_dict = {}
+        pass
     return record_dict
 
 
@@ -107,7 +105,6 @@ def repo_to_record(
 ) -> colrev.record.record.Record:
     """Convert a GitHub repository to a record"""
 
-    # Set default values
     record_dict = {
         Fields.ENTRYTYPE: "software",
         Fields.TITLE: repo.name,
@@ -126,6 +123,5 @@ def repo_to_record(
     # Use data from CITATION.cff file (if available)
     _update_record_based_on_citation_cff(record_dict, repo)
 
-    record_dict = {k: v for k, v in record_dict.items() if v}
-
+    record_dict = {k: v for k, v in record_dict.items() if v not in (None, "", [], {})}
     return colrev.record.record.Record(data=record_dict)
diff --git a/colrev/packages/ieee/README.md b/colrev/packages/ieee/README.md
@@ -20,7 +20,7 @@ colrev search --add colrev.ieee -p "https://ieeexploreapi.ieee.org/api/v1/search
 
 All configured metadata fields, the abstract and the document text are queried.
 
-It is not necessary to pass an API key as a parameter here. In order to keep the key secret, you will be prompted to enter it through user input if it is not already stored in the settings. The api key can be requested via the [IEEE Xplore API Portal](https://developer.ieee.org/member/register).
+It is not necessary to pass an API key as a parameter here. In order to keep the key secret, set it in the `IEEE_API_KEY` environment variable (for example with `export IEEE_API_KEY="<your-api-key>"`). The api key can be requested via the [IEEE Xplore API Portal](https://developer.ieee.org/member/register). If the variable is not defined, colrev will prompt for the key and store it for the current session.
 
 Specific parameters can also be searched for, such as issn, isbn, doi, article_number, author, publication_year. For each of these, append "parameter=value" to the URL.
 
diff --git a/colrev/packages/ieee/src/ieee.py b/colrev/packages/ieee/src/ieee.py
@@ -3,13 +3,13 @@
 from __future__ import annotations
 
 import logging
+import os
 import typing
 from pathlib import Path
 
 import pandas as pd
 from pydantic import Field
 
-import colrev.env.environment_manager
 import colrev.ops.prep
 import colrev.ops.search_api_feed
 import colrev.package_manager.package_base_classes as base_classes
@@ -60,8 +60,6 @@ def __init__(
         self.logger = logger or logging.getLogger(__name__)
         self.verbose_mode = verbose_mode
 
-        self.environment_manager = colrev.env.environment_manager.EnvironmentManager()
-
         if search_file:
             self.search_source = search_file
         else:
@@ -192,10 +190,13 @@ def search(self, rerun: bool) -> None:
             raise NotImplementedError
 
     def _get_api_key(self) -> str:
-        api_key = self.environment_manager.get_settings_by_key(self.SETTINGS["api_key"])
-        if api_key is None or len(api_key) != 24:
-            api_key = input("Please enter api key: ")
-            self.environment_manager.update_registry(self.SETTINGS["api_key"], api_key)
+        api_key = os.getenv("IEEE_API_KEY")
+        if api_key and len(api_key) == 24:
+            return api_key
+
+        api_key = input("Please enter api key: ")
+        if api_key:
+            os.environ["IEEE_API_KEY"] = api_key
         return api_key
 
     def _run_api_search(
diff --git a/colrev/packages/importer/src/importer.py b/colrev/packages/importer/src/importer.py
@@ -1,5 +1,6 @@
 #! /usr/bin/env python
 """Importer"""
+import shutil
 from pathlib import Path
 
 import inquirer
@@ -104,6 +105,8 @@ def _import_prescreening_decisions(
     *,
     other_review_manager: colrev.review_manager.ReviewManager,
 ) -> None:
+
+    # pylint: disable=colrev-records-variable-naming-convention
     colrev.ops.check.CheckOperation(other_review_manager)
     other_records = other_review_manager.dataset.load_records_dict()
     review_manager.get_prescreen_operation()
@@ -163,6 +166,7 @@ def _import_records(
     colrev.ops.check.CheckOperation(review_manager)
     colrev.ops.check.CheckOperation(other_review_manager)
 
+    # pylint: disable=colrev-records-variable-naming-convention
     other_records = other_review_manager.dataset.load_records_dict()
     records = review_manager.dataset.load_records_dict()
 
@@ -226,7 +230,6 @@ def _import_records(
     print()
 
     matched_df = match(blocked_df, verbosity_level=0)
-    # TODO : mechanism in bib-dedupe to make sure that the cluster function is called?! (data structure!)
     duplicate_id_sets = cluster(matched_df, verbosity_level=0)
 
     for duplicate_id_set in duplicate_id_sets:
@@ -250,7 +253,6 @@ def _import_records(
                 if not target_path.parent.is_dir():
                     target_path.parent.mkdir(parents=True, exist_ok=True)
                 if not target_path.is_file():
-                    import shutil
 
                     shutil.copyfile(original_path, target_path)
                 else:
diff --git a/colrev/packages/local_index/src/local_index.py b/colrev/packages/local_index/src/local_index.py
@@ -864,9 +864,14 @@ def _apply_correction(self, *, source_url: str, change_list: list) -> None:
 
         # TBD: other modes of accepting changes?
         # e.g., only-metadata, no-changes, all(including optional fields)
-        import colrev.review_manager
 
-        check_review_manager = colrev.review_manager.ReviewManager(path_str=source_url)
+        # SearchSource only supported in the context of a CoLRev project
+        # pylint: disable=import-outside-toplevel
+        import colrev.review_manager as colrev_review_manager
+
+        # self.review_manager = colrev_review_manager.ReviewManager()
+
+        check_review_manager = colrev_review_manager.ReviewManager(path_str=source_url)
         check_operation = colrev.ops.check.CheckOperation(check_review_manager)
 
         git_repo = check_review_manager.dataset.git_repo
diff --git a/colrev/packages/open_citations_forward_search/src/open_citations_forward_search.py b/colrev/packages/open_citations_forward_search/src/open_citations_forward_search.py
@@ -51,10 +51,11 @@ def __init__(
         self.verbose_mode = verbose_mode
         self.search_source = search_file
 
-        # TODO / TBD: replace review_manager?
-        import colrev.review_manager
+        # SearchSource only supported in the context of a CoLRev project
+        # pylint: disable=import-outside-toplevel
+        import colrev.review_manager as colrev_review_manager
 
-        self.review_manager = colrev.review_manager.ReviewManager()
+        self.review_manager = colrev_review_manager.ReviewManager()
         colrev.ops.check.CheckOperation(self.review_manager)
         self.api = open_citations_api.OpenCitationsAPI()
 
diff --git a/colrev/packages/osf/README.md b/colrev/packages/osf/README.md
@@ -16,7 +16,7 @@ colrev search --add colrev.osf -p "https://api.osf.io/v2/nodes/?filter[title]=re
 
 The retrieved data, including detailed project metadata and resources, is processed and made available for further actions within CoLRev, such as analysis or reporting.
 
-It is not necessary to pass an API key as a parameter here. In order to keep the key secret, you will be prompted to enter it through user input if it is not already stored in the settings. The api key can be requested via the [OSF settings page](https://accounts.osf.io/login?service=https://osf.io/settings/tokens/).
+It is not necessary to pass an API key as a parameter here. In order to keep the key secret, set it in the `OSF_API_KEY` environment variable (for example with `export OSF_API_KEY="<your-api-key>"`). The api key can be requested via the [OSF settings page](https://accounts.osf.io/login?service=https://osf.io/settings/tokens/). If the variable is not defined, colrev will prompt for the key and store it for the current session.
 
 The search can be filtered by changing the filter parameter to one of the following parameters: title, id, type, category, year, description, tags, data_created. For each of these, change "filter[parameter]=value" in the URL.
 
diff --git a/colrev/packages/osf/src/osf.py b/colrev/packages/osf/src/osf.py
@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import logging
+import os
 import typing
 from pathlib import Path
 
@@ -137,11 +138,13 @@ def add_endpoint(
         return search_source
 
     def _get_api_key(self) -> str:
-        env_man = colrev.env.environment_manager.EnvironmentManager()
-        api_key = env_man.get_settings_by_key(self.SETTINGS["api_key"])
-        if api_key is None or len(api_key) == 0:
-            api_key = input("Please enter api key: ")
-            env_man.update_registry(self.SETTINGS["api_key"], api_key)
+        api_key = os.getenv("OSF_API_KEY")
+        if api_key:
+            return api_key
+
+        api_key = input("Please enter api key: ")
+        if api_key:
+            os.environ["OSF_API_KEY"] = api_key
         return api_key
 
     def search(self, rerun: bool) -> None:
diff --git a/colrev/packages/pdf_backward_search/src/pdf_backward_search.py b/colrev/packages/pdf_backward_search/src/pdf_backward_search.py
@@ -64,10 +64,11 @@ def __init__(
         self.logger = logger or logging.getLogger(__name__)
         self.verbose_mode = verbose_mode
 
-        # TODO / TBD: replace review_manager?
-        import colrev.review_manager
+        # SearchSource only supported in the context of a CoLRev project
+        # pylint: disable=import-outside-toplevel
+        import colrev.review_manager as colrev_review_manager
 
-        self.review_manager = colrev.review_manager.ReviewManager()
+        self.review_manager = colrev_review_manager.ReviewManager()
 
         if "min_intext_citations" not in search_file.search_parameters:
             search_file.search_parameters["min_intext_citations"] = 3
diff --git a/colrev/packages/pubmed/src/pubmed.py b/colrev/packages/pubmed/src/pubmed.py
@@ -98,14 +98,13 @@ def validate_source(
 
         if search_source.search_type == SearchType.DB:
             print(f"Validating search string: {search_source.search_string}")
-            # TODO : TBD: pass version to search-query?
             parse(search_source.search_string, platform="pubmed")
 
         # if search_source.search_type == SearchType.API:
         #     print(f'Validating search string: {search_source.search_parameters}')
         #     parse(search_source.search_parameters, platform="pubmed_api")
 
-        print("SearchSource %s validated", search_source.search_results_path)
+        print(f"SearchSource {search_source.search_results_path} validated")
 
     @classmethod
     def heuristic(cls, filename: Path, data: str) -> dict:
diff --git a/colrev/packages/pubmed/src/pubmed_api.py b/colrev/packages/pubmed/src/pubmed_api.py
@@ -97,6 +97,7 @@ def _get_abstract_string(cls, *, root: Element) -> str:
         return ""
 
     # pylint: disable=colrev-missed-constant-usage
+    # pylint: disable=too-many-branches
     @classmethod
     def _pubmed_xml_to_record(cls, *, root: Element) -> dict:
         retrieved_record_dict: dict = {Fields.ENTRYTYPE: "misc"}
diff --git a/colrev/packages/semanticscholar/README.md b/colrev/packages/semanticscholar/README.md
@@ -64,7 +64,7 @@ If the user decides to conduct a search without entering any search parameters,
 
 #### API search: API key for SemanticScholar
 
-While it is not necessary to enter an API key to conduct a search in SemanticScholar, we highly recommend it. Without an API key, SemanticScholar only allows limited access attempts per minute. This might lead to the site being unavailable for a short time. An API key can be requested via the SemanticScholar API (link below). Once a valid API key was entered, it will be saved in the `SETTINGS` file. Subsequent searches of SematicScholar will now include this API key. Every time a new search is conducted, the user will have the opportunity to change or delete the stored API key via the user interface.
+While it is not necessary to enter an API key to conduct a search in SemanticScholar, we highly recommend it. Without an API key, SemanticScholar only allows limited access attempts per minute. This might lead to the site being unavailable for a short time. An API key can be requested via the SemanticScholar API (link below). Store the key in the environment variable `SEMANTIC_SCHOLAR_API_KEY` (for example by running `export SEMANTIC_SCHOLAR_API_KEY="<your-api-key>"`). If the variable is not set, the search interface will prompt for the key and store it for the current session.
 
 #### API search: Search results
 
diff --git a/colrev/packages/semanticscholar/src/semanticscholar_search_source.py b/colrev/packages/semanticscholar/src/semanticscholar_search_source.py
@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import logging
+import os
 import typing
 from multiprocessing import Lock
 from pathlib import Path
@@ -55,6 +56,7 @@ class SemanticScholarSearchSource(base_classes.SearchSourcePackageBaseClass):
     SETTINGS = {
         "api_key": "packages.search_source.colrev.semanticscholar.api_key",
     }
+    _ENV_API_KEY = "SEMANTIC_SCHOLAR_API_KEY"
 
     _availability_exception_message = (
         f"Semantic Scholar ({Colors.ORANGE}check "
@@ -255,25 +257,15 @@ def author_search(self, *, params: dict, rerun: bool) -> PaginatedResults:
 
     def _get_api_key(self) -> str:
         """Method to request an API key from the settings file - or, if empty, from user input"""
-        api_key = (
-            colrev.env.environment_manager.EnvironmentManager().get_settings_by_key(
-                self.SETTINGS["api_key"]
-            )
-        )
+        api_key = os.getenv(self._ENV_API_KEY, "")
 
         if api_key:
-            api_key = self._s2_UI.get_api_key(api_key)
-        else:
-            api_key = self._s2_UI.get_api_key()
+            return api_key
+
+        api_key = self._s2_UI.get_api_key()
 
         if api_key:
-            colrev.env.environment_manager.EnvironmentManager().update_registry(
-                self.SETTINGS["api_key"], api_key
-            )
-        else:
-            colrev.env.environment_manager.EnvironmentManager().update_registry(
-                self.SETTINGS["api_key"], ""
-            )
+            os.environ[self._ENV_API_KEY] = api_key
 
         return api_key
 
diff --git a/colrev/packages/toc_sync/src/toc_sync.py b/colrev/packages/toc_sync/src/toc_sync.py
diff --git a/colrev/packages/unpaywall/README.md b/colrev/packages/unpaywall/README.md
diff --git a/colrev/packages/unpaywall/src/api.py b/colrev/packages/unpaywall/src/api.py
diff --git a/colrev/packages/unpaywall/src/utils.py b/colrev/packages/unpaywall/src/utils.py
diff --git a/colrev/record/record.py b/colrev/record/record.py
diff --git a/colrev/search_file.py b/colrev/search_file.py
diff --git a/tests/3_packages_search/api_search_pubmed_test.py b/tests/3_packages_search/api_search_pubmed_test.py
diff --git a/tests/review_manager/3_packages_prep/unpaywall_test.py b/tests/review_manager/3_packages_prep/unpaywall_test.py
