refactor logging control (#243)

* add dependency `rich`

* remove logging NullHandler from modules

* add function `setup_logging`

* use standard logging instead of `LogConfig`

* replace print with logger.info

* Delete logconfig.py

* remove dependency tqdm

use rich.progress instead

* replace tqdm with rich.progress for displaying progress bar

* update nplinker configs for logging

- update comments
- rename `to_stdout` to `use_console`

- Remove `cast=Path` for `log.file`, as the config variable is first cast, then examined on its type.

* update logging setup in NPLinker class

* print out configs when initializing NPLinker class

* change log message from debug to info

* Update __init__.py

pyproject.toml

@@ -36,9 +36,9 @@ dependencies = [
     "numpy",
     "pandas",
     "pyteomics",
+    "rich",
     "scipy",
     "sortedcontainers",
-    "tqdm",
 ]
 
 [project.optional-dependencies]

src/nplinker/__init__.py

@@ -6,3 +6,45 @@
 __author__ = "Cunliang Geng"
 __email__ = "c.geng@esciencecenter.nl"
 __version__ = "2.0.0-alpha.1"
+
+
+def setup_logging(level: str = "INFO", file: str = "", use_console: bool = True) -> None:
+    """Setup logging configuration for the ancestor logger "nplinker".
+
+    Args:
+        level: The log level, use the logging module's log level constants. Valid levels are:
+            "NOTSET", "DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL".
+        file: The file to write the log to. If the file does not exist, it will be created. The log
+            will be written to the file in append mode. If the file is an empty string (by default),
+            the log will not be written to a file.
+        use_console: Whether to log to the console.
+    """
+    from rich.console import Console
+    from rich.logging import RichHandler
+
+    # Get the acncestor logger "nplinker"
+    logger = logging.getLogger(__name__)
+    logger.setLevel(level)
+
+    # File handler
+    if file:
+        logger.addHandler(
+            RichHandler(
+                console=Console(file=open(file, "a"), width=120),  # force the line width to 120
+                omit_repeated_times=False,
+                rich_tracebacks=True,
+                tracebacks_show_locals=True,
+                log_time_format="[%Y-%m-%d %X]",
+            )
+        )
+
+    # Console handler
+    if use_console:
+        logger.addHandler(
+            RichHandler(
+                omit_repeated_times=False,
+                rich_tracebacks=True,
+                tracebacks_show_locals=True,
+                log_time_format="[%Y-%m-%d %X]",
+            )
+        )

src/nplinker/class_info/chem_classes.py

@@ -11,16 +11,15 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-
 import glob
+import logging
 import os
 from collections import Counter
 from canopus import Canopus
 from canopus.classifications_to_gnps import analyse_canopus
-from ..logconfig import LogConfig
 
 
-logger = LogConfig.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 
 # load Chem_class_predictions (canopus, molnetenhancer are loaded)
@@ -264,7 +263,7 @@ class prediction for a level. When no class is present, instead of Tuple it will
 
             # use canopus_treemap to produce NPClassifier classes
             # TODO: probably change when sirius v5 comes out
-            logger.debug("Using canopus_treemap to get NPC classes")
+            logger.info("Using canopus_treemap to get NPC classes")
             canopus_workspace = Canopus(sirius=self._canopus_dir)
             npc_file = os.path.join(self._canopus_dir, "npc_summary.tsv")
             canopus_workspace.npcSummary().to_csv(npc_file, sep=sep)

src/nplinker/class_info/class_matches.py

@@ -11,15 +11,14 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-
+import logging
 import os
 from collections import Counter
 from collections import defaultdict
 import pandas as pd
-from ..logconfig import LogConfig
 
 
-logger = LogConfig.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 
 class ClassMatches:

src/nplinker/class_info/runcanopus.py

@@ -11,14 +11,13 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-
+import logging
 import os
 import subprocess
 import sys
-from ..logconfig import LogConfig
 
 
-logger = LogConfig.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 
 def run_canopus(mgf_file, output_path, extra_params="--maxmz 600 formula zodiac structure canopus"):

src/nplinker/config.py

@@ -39,16 +39,16 @@
     Validator("podp_id", required=True, when=Validator("mode", eq="podp")),
     Validator("podp_id", required=False, when=Validator("mode", eq="local")),
     # Log
-    ## `loglevel` must be a string and must be one of the supported levels. It is transformed to
+    ## `level` must be a string and must be one of the supported levels. It is transformed to
     ## uppercase to avoid case sensitivity.
     Validator(
         "log.level",
         is_type_of=str,
         cast=lambda v: v.upper(),
         is_in=["NOTSET", "DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
     ),
-    Validator("log.file", is_type_of=str, cast=Path),
-    Validator("log.to_stdout", is_type_of=bool),
+    Validator("log.file", is_type_of=str),
+    Validator("log.use_console", is_type_of=bool),
     #  Mibig
     Validator("mibig.to_use", required=True, is_type_of=bool),
     Validator(

src/nplinker/data/nplinker.toml

@@ -18,16 +18,17 @@ podp_id = ""
 
 [log]
 # Log level. The available levels are same as the levels in python package `logging`:
-# "NOTSET", "DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL".
+# "DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL".
 # The default value is "INFO".
 level = "INFO"
-# Redirect the log messages from stdout to a log file. If not set, the log messages will only be
-# printed to stdout.
-# The value is optional and must be a full path if set.
+# The log file to append log messages.
+# The value is optional. 
+# If not set or use empty string, log messages will not be written to a file.
+# The file will be created if it does not exist. Log messages will be appended to the file if it exists.
 file = "path/to/logfile"
-# Whether to print log messages to stdout in addition to writing to the logfile.
+# Whether to write log meesages to console.
 # The default value is true.
-to_stdout = true
+use_console = true
 
 
 [mibig]

src/nplinker/genomics/__init__.py

@@ -1,10 +1,7 @@
-import logging
 from .bgc import BGC
 from .gcf import GCF
 
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
-
 __all__ = [
     "BGC",
     "GCF",

src/nplinker/genomics/antismash/__init__.py

@@ -1,4 +1,3 @@
-import logging
 from .antismash_downloader import download_and_extract_antismash_data
 from .antismash_loader import AntismashBGCLoader
 from .antismash_loader import parse_bgc_genbank
@@ -7,8 +6,6 @@
 from .podp_antismash_downloader import podp_download_and_extract_antismash_data
 
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
-
 __all__ = [
     "download_and_extract_antismash_data",
     "AntismashBGCLoader",

src/nplinker/genomics/antismash/antismash_downloader.py

@@ -1,15 +1,15 @@
 from __future__ import annotations
+import logging
 import os
 import shutil
 from os import PathLike
 from pathlib import Path
-from nplinker.logconfig import LogConfig
 from nplinker.utils import download_and_extract_archive
 from nplinker.utils import list_dirs
 from nplinker.utils import list_files
 
 
-logger = LogConfig.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 # urls to be given to download antismash data
 ANTISMASH_DB_DOWNLOAD_URL = "https://antismash-db.secondarymetabolites.org/output/{}/{}"

src/nplinker/genomics/antismash/antismash_loader.py

@@ -1,17 +1,17 @@
 from __future__ import annotations
 import fnmatch
+import logging
 import os
 from Bio import SeqIO
 from Bio import SeqRecord
 from nplinker.genomics import BGC
-from nplinker.logconfig import LogConfig
 from nplinker.strain import Strain
 from nplinker.utils import list_dirs
 from nplinker.utils import list_files
 from ..abc import BGCLoaderBase
 
 
-logger = LogConfig.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 
 class AntismashBGCLoader:

src/nplinker/genomics/antismash/podp_antismash_downloader.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 import json
+import logging
 import re
 import time
 from os import PathLike
@@ -11,11 +12,10 @@
 from jsonschema import validate
 from nplinker.defaults import GENOME_STATUS_FILENAME
 from nplinker.genomics.antismash import download_and_extract_antismash_data
-from nplinker.logconfig import LogConfig
 from nplinker.schemas import GENOME_STATUS_SCHEMA
 
 
-logger = LogConfig.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 NCBI_LOOKUP_URL = "https://www.ncbi.nlm.nih.gov/assembly/?term={}"
 JGI_GENOME_LOOKUP_URL = (
@@ -248,7 +248,7 @@ def _ncbi_genbank_search(genbank_id: str, retry_times: int = 3) -> Tag | Navigab
     url = NCBI_LOOKUP_URL.format(genbank_id)
     retry = 1
     while retry <= retry_times:
-        logger.debug(f"Looking up GenBank data for {genbank_id} at {url}")
+        logger.info(f"Looking up GenBank data for {genbank_id} at {url}")
         resp = httpx.get(url, follow_redirects=True)
         if resp.status_code == httpx.codes.OK:
             # the page should contain a <dl> element with class "assembly_summary_new". retrieving
@@ -298,7 +298,7 @@ def _resolve_genbank_accession(genbank_id: str) -> str:
 
     # get rid of any extraneous whitespace
     genbank_id = genbank_id.strip()
-    logger.debug(f'Parsed GenBank ID to "{genbank_id}"')
+    logger.info(f'Parsed GenBank ID to "{genbank_id}"')
 
     # run a search using the GenBank accession ID
     try:

src/nplinker/genomics/bgc.py

@@ -1,15 +1,15 @@
 from __future__ import annotations
+import logging
 from typing import TYPE_CHECKING
 from deprecated import deprecated
-from nplinker.logconfig import LogConfig
 from .aa_pred import predict_aa
 
 
 if TYPE_CHECKING:
     from ..strain import Strain
     from .gcf import GCF
 
-logger = LogConfig.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 
 class BGC:

src/nplinker/genomics/bigscape/__init__.py

@@ -1,9 +1,6 @@
-import logging
 from .bigscape_loader import BigscapeGCFLoader
 from .bigscape_loader import BigscapeV2GCFLoader
 from .runbigscape import run_bigscape
 
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
-
 __all__ = ["BigscapeGCFLoader", "BigscapeV2GCFLoader", "run_bigscape"]

src/nplinker/genomics/bigscape/bigscape_loader.py

@@ -1,13 +1,13 @@
 from __future__ import annotations
 import csv
+import logging
 import sqlite3
 from os import PathLike
-from nplinker.logconfig import LogConfig
 from ..abc import GCFLoaderBase
 from ..gcf import GCF
 
 
-logger = LogConfig.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 
 class BigscapeGCFLoader:

src/nplinker/genomics/bigscape/runbigscape.py

@@ -1,12 +1,12 @@
 from __future__ import annotations
+import logging
 import os
 import subprocess
 import sys
 from os import PathLike
-from ...logconfig import LogConfig
 
 
-logger = LogConfig.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 PFAM_PATH = os.path.join(sys.prefix, "nplinker_lib")
 

src/nplinker/genomics/gcf.py

@@ -1,14 +1,14 @@
 from __future__ import annotations
+import logging
 from typing import TYPE_CHECKING
-from nplinker.logconfig import LogConfig
 from nplinker.strain import StrainCollection
 
 
 if TYPE_CHECKING:
     from nplinker.strain import Strain
     from .bgc import BGC
 
-logger = LogConfig.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 
 class GCF:

src/nplinker/genomics/mibig/__init__.py

@@ -1,12 +1,9 @@
-import logging
 from .mibig_downloader import download_and_extract_mibig_metadata
 from .mibig_loader import MibigLoader
 from .mibig_loader import parse_bgc_metadata_json
 from .mibig_metadata import MibigMetadata
 
 
-logging.getLogger(__name__).addHandler(logging.NullHandler())
-
 __all__ = [
     "download_and_extract_mibig_metadata",
     "MibigLoader",

src/nplinker/genomics/mibig/mibig_downloader.py

@@ -1,14 +1,14 @@
 from __future__ import annotations
+import logging
 import os
 import shutil
 from pathlib import Path
-from nplinker.logconfig import LogConfig
 from nplinker.utils import download_and_extract_archive
 from nplinker.utils import list_dirs
 from nplinker.utils import list_files
 
 
-logger = LogConfig.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 MIBIG_METADATA_URL = "https://dl.secondarymetabolites.org/mibig/mibig_json_{version}.tar.gz"
 

src/nplinker/genomics/mibig/mibig_loader.py

@@ -1,13 +1,13 @@
+import logging
 import os.path
-from nplinker.logconfig import LogConfig
 from nplinker.strain import Strain
 from nplinker.utils import list_files
 from ..abc import BGCLoaderBase
 from ..bgc import BGC
 from .mibig_metadata import MibigMetadata
 
 
-logger = LogConfig.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 
 class MibigLoader: