Add optional logger support (#673)

* Use standard logging

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: geritwagner

colrev/packages/abi_inform_proquest/src/abi_inform_proquest.py

@@ -5,6 +5,7 @@
 import logging
 import re
 from pathlib import Path
+from typing import Optional
 
 from pydantic import Field
 
@@ -36,8 +37,13 @@ class ABIInformProQuestSearchSource(base_classes.SearchSourcePackageBaseClass):
     db_url = "https://search.proquest.com/abicomplete/advanced"
 
     def __init__(
-        self, *, source_operation: colrev.process.operation.Operation, settings: dict
+        self,
+        *,
+        source_operation: colrev.process.operation.Operation,
+        settings: dict,
+        logger: Optional[logging.Logger] = None,
     ) -> None:
+        self.logger = logger or logging.getLogger(__name__)
         self.review_manager = source_operation.review_manager
         self.search_source = self.settings_class(**settings)
         self.source_operation = source_operation

colrev/packages/acm_digital_library/src/acm_digital_library.py

@@ -4,6 +4,7 @@
 
 import logging
 from pathlib import Path
+from typing import Optional
 
 from pydantic import Field
 
@@ -34,8 +35,13 @@ class ACMDigitalLibrarySearchSource(base_classes.SearchSourcePackageBaseClass):
     db_url = "https://dl.acm.org/"
 
     def __init__(
-        self, *, source_operation: colrev.process.operation.Operation, settings: dict
+        self,
+        *,
+        source_operation: colrev.process.operation.Operation,
+        settings: dict,
+        logger: Optional[logging.Logger] = None,
     ) -> None:
+        self.logger = logger or logging.getLogger(__name__)
         self.search_source = self.settings_class(**settings)
         self.review_manager = source_operation.review_manager
         self.operation = source_operation

colrev/packages/add_journal_ranking/src/add_journal_ranking.py

@@ -2,6 +2,9 @@
 """Adding of journal rankings to metadata"""
 from __future__ import annotations
 
+import logging
+from typing import Optional
+
 from pydantic import Field
 
 import colrev.env.local_index
@@ -27,7 +30,9 @@ def __init__(
         *,
         prep_operation: colrev.ops.prep.Prep,  # pylint: disable=unused-argument
         settings: dict,
+        logger: Optional[logging.Logger] = None,
     ) -> None:
+        self.logger = logger or logging.getLogger(__name__)
         self.settings = self.settings_class(**settings)
         self.local_index = colrev.env.local_index.LocalIndex()
 

colrev/packages/ais_library/src/aisel.py

@@ -6,6 +6,7 @@
 import re
 import urllib.parse
 from pathlib import Path
+from typing import Optional
 from urllib.parse import urlparse
 
 import requests
@@ -67,8 +68,13 @@ class AISeLibrarySearchSource(base_classes.SearchSourcePackageBaseClass):
     }
 
     def __init__(
-        self, *, source_operation: colrev.process.operation.Operation, settings: dict
+        self,
+        *,
+        source_operation: colrev.process.operation.Operation,
+        settings: dict,
+        logger: Optional[logging.Logger] = None,
     ) -> None:
+        self.logger = logger or logging.getLogger(__name__)
         self.search_source = self.settings_class(**settings)
         self.review_manager = source_operation.review_manager
         self.quality_model = self.review_manager.get_qm()
@@ -208,14 +214,14 @@ def _validate_source(self) -> None:
 
         source = self.search_source
 
-        self.review_manager.logger.debug(f"Validate SearchSource {source.filename}")
+        self.logger.debug(f"Validate SearchSource {source.filename}")
 
         if source.search_type == SearchType.API:
             if "query" not in source.search_parameters:
                 # if "search_terms" not in source.search_parameters["query"]:
                 raise colrev_exceptions.InvalidQueryException("query parameter missing")
 
-        self.review_manager.logger.debug(f"SearchSource {source.filename} validated")
+        self.logger.debug(f"SearchSource {source.filename} validated")
 
     def _get_ais_query_return(self) -> list:
         def query_from_params(params: dict) -> str:
@@ -260,7 +266,7 @@ def query_from_params(params: dict) -> str:
             id_labeler=ais_load_utils.enl_id_labeler,
             entrytype_setter=ais_load_utils.enl_entrytype_setter,
             field_mapper=ais_load_utils.enl_field_mapper,
-            logger=self.review_manager.logger,
+            logger=self.logger,
         )
 
         return list(records.values())
@@ -274,9 +280,7 @@ def _run_api_search(
         # pylint: disable=too-many-branches
 
         if rerun:
-            self.review_manager.logger.info(
-                "Performing a search of the full history (may take time)"
-            )
+            self.logger.info("Performing a search of the full history (may take time)")
 
         try:
             for record_dict in self._get_ais_query_return():

colrev/packages/arxiv/src/arxiv.py

@@ -6,6 +6,7 @@
 import typing
 from multiprocessing import Lock
 from pathlib import Path
+from typing import Optional
 from urllib.parse import urlparse
 
 import feedparser
@@ -46,7 +47,9 @@ def __init__(
         *,
         source_operation: colrev.process.operation.Operation,
         settings: typing.Optional[dict] = None,
+        logger: Optional[logging.Logger] = None,
     ) -> None:
+        self.logger = logger or logging.getLogger(__name__)
         self.review_manager = source_operation.review_manager
         if settings:
             # arXiv as a search_source
@@ -133,9 +136,7 @@ def validate_source(
     ) -> None:
         """Validate the SearchSource (parameters etc.)"""
 
-        search_operation.review_manager.logger.debug(
-            f"Validate SearchSource {source.filename}"
-        )
+        self.logger.debug(f"Validate SearchSource {source.filename}")
 
         if source.filename.name != self._arxiv_md_filename.name:
             if "query" not in source.search_parameters:
@@ -146,9 +147,7 @@ def validate_source(
             # if "query_file" in source.search_parameters:
             # ...
 
-        search_operation.review_manager.logger.debug(
-            f"SearchSource {source.filename} validated"
-        )
+        self.logger.debug(f"SearchSource {source.filename} validated")
 
     def check_availability(
         self, *, source_operation: colrev.process.operation.Operation
@@ -200,11 +199,11 @@ def check_availability(
     #         headers = {"user-agent": f"{__name__} (mailto:{self.email})"}
     #         session = self.review_manager.get_cached_session()
 
-    #         # review_manager.logger.debug(url)
+    #         # self.logger.debug(url)
     #         ret = session.request("GET", url, headers=headers, timeout=timeout)
     #         ret.raise_for_status()
     #         if ret.status_code != 200:
-    #             # review_manager.logger.debug(
+    #             # self.logger.debug(
     #             #     f"crossref_query failed with status {ret.status_code}"
     #             # )
     #             return {"arxiv_id": arxiv_id}
@@ -264,9 +263,7 @@ def _run_parameter_search(
         rerun: bool,
     ) -> None:
         if rerun:
-            self.review_manager.logger.info(
-                "Performing a search of the full history (may take time)"
-            )
+            self.logger.info("Performing a search of the full history (may take time)")
 
         try:
             for record_dict in self._get_arxiv_query_return():
@@ -275,9 +272,7 @@ def _run_parameter_search(
                     if "" == record_dict.get(
                         Fields.AUTHOR, ""
                     ) and "" == record_dict.get(Fields.TITLE, ""):
-                        self.review_manager.logger.warning(
-                            f"Skipped record: {record_dict}"
-                        )
+                        self.logger.warning(f"Skipped record: {record_dict}")
                         continue
 
                     prep_record = colrev.record.record_prep.PrepRecord(record_dict)

colrev/packages/bibliography_export/src/bibliography_export.py

@@ -3,8 +3,10 @@
 from __future__ import annotations
 
 import copy
+import logging
 from enum import Enum
 from pathlib import Path
+from typing import Optional
 
 import inquirer
 from pydantic import BaseModel
@@ -64,7 +66,9 @@ def __init__(
         *,
         data_operation: colrev.ops.data.Data,
         settings: dict,
+        logger: Optional[logging.Logger] = None,
     ) -> None:
+        self.logger = logger or logging.getLogger(__name__)
         self.review_manager = data_operation.review_manager
 
         if "bib_format" not in settings:
@@ -77,7 +81,7 @@ def __init__(
         self.endpoint_path = self.review_manager.paths.output
 
     def _export(self, *, selected_records: dict) -> None:
-        self.review_manager.logger.info(f"Export {self.settings.bib_format.name}")
+        self.logger.info(f"Export {self.settings.bib_format.name}")
 
         if self.settings.bib_format is BibFormats.zotero:
             export_filepath = self.endpoint_path / Path("zotero.bib")
@@ -189,9 +193,7 @@ def update_data(
             self._export(selected_records=selected_records)
 
         except NotImplementedError:
-            self.review_manager.logger.info(
-                f"Not yet implemented ({self.settings.bib_format})"
-            )
+            self.logger.info(f"Not yet implemented ({self.settings.bib_format})")
 
     def update_record_status_matrix(
         self,

colrev/packages/blank/src/blank.py

@@ -1,5 +1,8 @@
 #! /usr/bin/env python
 """Blank literature review"""
+import logging
+from typing import Optional
+
 from pydantic import Field
 
 import colrev.ops.search
@@ -20,8 +23,13 @@ class BlankReview(base_classes.ReviewTypePackageBaseClass):
     ci_supported: bool = Field(default=True)
 
     def __init__(
-        self, *, operation: colrev.process.operation.Operation, settings: dict
+        self,
+        *,
+        operation: colrev.process.operation.Operation,
+        settings: dict,
+        logger: Optional[logging.Logger] = None,
     ) -> None:
+        self.logger = logger or logging.getLogger(__name__)
         self.settings = self.settings_class(**settings)
 
     def __str__(self) -> str:

colrev/packages/cli_prep_man/src/cli_prep_man_prep_man.py

@@ -1,6 +1,8 @@
 #! /usr/bin/env python
 """CliPrepMan"""
+import logging
 import typing
+from typing import Optional
 
 import inquirer
 
@@ -18,8 +20,13 @@ class CliPrepMan(PrepManPackageBaseClass):
     """CLI for manual preparation of records"""
 
     def __init__(
-        self, *, prep_man_operation: colrev.ops.prep_man.PrepMan, settings: dict
+        self,
+        *,
+        prep_man_operation: colrev.ops.prep_man.PrepMan,
+        settings: dict,
+        logger: Optional[logging.Logger] = None,
     ) -> "None":
+        self.logger = logger or logging.getLogger(__name__)
         """Initialize self.  See help(type(self)) for accurate signature."""
 
     def _get_choices(

colrev/packages/colrev_cli_pdf_get_man/src/pdf_get_man_cli.py

@@ -2,9 +2,11 @@
 """CLI interface for manual retrieval of PDFs"""
 from __future__ import annotations
 
+import logging
 import shutil
 import urllib.parse
 from pathlib import Path
+from typing import Optional
 
 from pydantic import Field
 
@@ -34,7 +36,9 @@ def __init__(
         *,
         pdf_get_man_operation: colrev.ops.pdf_get_man.PDFGetMan,
         settings: dict,
+        logger: Optional[logging.Logger] = None,
     ) -> None:
+        self.logger = logger or logging.getLogger(__name__)
         self.settings = self.settings_class(**settings)
         self.review_manager = pdf_get_man_operation.review_manager
         self.pdf_get_man_operation = pdf_get_man_operation
@@ -211,7 +215,7 @@ def _pdf_get_man_record_cli(
         *,
         record: colrev.record.record.Record,
     ) -> None:
-        # self.review_manager.logger.debug(
+        # self.logger.debug(
         #     f"called pdf_get_man_cli for {record}"
         # )
 
@@ -229,7 +233,7 @@ def _pdf_get_man_record_cli(
 
         filepath = self._get_filepath(record=record)
         for retrieval_script in retrieval_scripts.values():
-            # self.review_manager.logger.debug(
+            # self.logger.debug(
             #     f'{script_name}({record.data[Fields.ID]}) called'
             # )
             record = retrieval_script(record)
@@ -260,7 +264,7 @@ def _pdf_get_man_record_cli(
     def pdf_get_man(self, records: dict) -> dict:
         """Get the PDF manually based on a cli"""
 
-        self.review_manager.logger.info("Retrieve PDFs manually")
+        self.logger.info("Retrieve PDFs manually")
         pdf_get_operation = self.review_manager.get_pdf_get_operation()
         pdf_dir = self.pdf_dir
 
@@ -278,9 +282,7 @@ def pdf_get_man(self, records: dict) -> dict:
         self.pdf_get_man_operation.export_retrieval_table(records)
         pdf_get_man_data = self.pdf_get_man_operation.get_data()
         if pdf_get_man_data["nr_tasks"] == 0:
-            self.review_manager.logger.info(
-                "No tasks for PDF retrieval (run colrev pdf-get )."
-            )
+            self.logger.info("No tasks for PDF retrieval (run colrev pdf-get ).")
             return records
         print(
             "\nInstructions\n\n      "
@@ -304,7 +306,7 @@ def pdf_get_man(self, records: dict) -> dict:
                     manual_author=True,
                 )
         else:
-            self.review_manager.logger.info(
+            self.logger.info(
                 "Retrieve PDFs manually and copy the files to "
                 f"the {pdf_dir}. Afterwards, use "
                 "colrev pdf-get-man"