fix mypy errors

src/nplinker/genomics/antismash/antismash_downloader.py

@@ -76,12 +76,12 @@ def download_and_extract_antismash_data(
         raise e
 
 
-def _check_roots(download_root: PathLike, extract_root: PathLike):
+def _check_roots(download_root: Path, extract_root: Path):
     if download_root == extract_root:
         raise ValueError("Identical path of download directory and extract directory")
 
 
-def _check_extract_path(extract_path: PathLike):
+def _check_extract_path(extract_path: Path):
     # check if extract_path is empty
-    if any(os.scandir(extract_path)):
+    if any(extract_path.iterdir()):
         raise ValueError(f'Nonempty directory: "{extract_path}"')

src/nplinker/genomics/antismash/podp_antismash_downloader.py

@@ -303,7 +303,7 @@ def _resolve_genbank_accession(genbank_id: str) -> str:
     # run a search using the GenBank accession ID
     try:
         dl_element = _ncbi_genbank_search(genbank_id)
-        if dl_element is None:
+        if dl_element is None or isinstance(dl_element, NavigableString):
             raise Exception("Unknown HTML format")
 
         refseq_idx = -1

src/nplinker/genomics/gcf.py

@@ -47,7 +47,7 @@ def __str__(self) -> str:
     def __repr__(self) -> str:
         return str(self)
 
-    def __eq__(self, other: GCF) -> bool:
+    def __eq__(self, other) -> bool:
         if isinstance(other, GCF):
             return self.gcf_id == other.gcf_id and self.bgcs == other.bgcs
         return NotImplemented

src/nplinker/genomics/utils.py

@@ -52,8 +52,8 @@ def generate_mappings_genome_id_bgc_id(
 
     # sort mappings by genome_id and construct json data
     genome_bgc_mappings = dict(sorted(genome_bgc_mappings.items()))
-    json_data = [{"genome_ID": k, "BGC_ID": v} for k, v in genome_bgc_mappings.items()]
-    json_data = {"mappings": json_data, "version": "1.0"}
+    json_data_mappings = [{"genome_ID": k, "BGC_ID": v} for k, v in genome_bgc_mappings.items()]
+    json_data = {"mappings": json_data_mappings, "version": "1.0"}
 
     # validate json data
     validate(instance=json_data, schema=GENOME_BGC_MAPPINGS_SCHEMA)
@@ -210,7 +210,7 @@ def extract_mappings_strain_id_original_genome_id(
         PODP platform. For example, for project MSV000079284, its json file is
         https://pairedomicsdata.bioinformatics.nl/api/projects/4b29ddc3-26d0-40d7-80c5-44fb6631dbf9.4.
     """
-    mappings_dict = {}
+    mappings_dict: dict[str, set[str]] = {}
     with open(podp_project_json_file, "r") as f:
         json_data = json.load(f)
 

src/nplinker/loader.py

@@ -1,4 +1,5 @@
 import os
+from importlib.resources import files
 from deprecated import deprecated
 from nplinker import globals
 from nplinker.config import config
@@ -26,11 +27,6 @@
 from nplinker.strain.utils import load_user_strains
 
 
-try:
-    from importlib.resources import files
-except ImportError:
-    from importlib_resources import files
-
 logger = LogConfig.getLogger(__name__)
 
 NPLINKER_APP_DATA_DIR = files("nplinker").joinpath("data")

src/nplinker/metabolomics/gnps/gnps_file_mapping_loader.py

@@ -67,7 +67,7 @@ def mapping_reversed(self) -> dict[str, set[str]]:
         Returns:
             Mapping from file name to all spectra ids that occur in this file.
         """
-        mapping_reversed = {}
+        mapping_reversed: dict[str, set[str]] = {}
         for spectrum_id, ms_filenames in self._mapping.items():
             for filename in ms_filenames:
                 if filename in mapping_reversed:

src/nplinker/metabolomics/gnps/gnps_format.py

@@ -6,7 +6,6 @@
 from pathlib import Path
 import httpx
 from bs4 import BeautifulSoup
-from bs4 import Tag
 from nplinker.utils import get_headers
 
 
@@ -46,10 +45,12 @@ def gnps_format_from_task_id(task_id: str) -> GNPSFormat:
     """
     task_html = httpx.get(GNPS_TASK_URL.format(task_id))
     soup = BeautifulSoup(task_html.text, features="html.parser")
-    tags = soup.find_all("th")
-    workflow_tag: Tag = list(filter(lambda x: x.contents == ["Workflow"], tags))[0]
-    workflow_format_tag: Tag = workflow_tag.parent.contents[3]
-    workflow_format = workflow_format_tag.contents[0].strip()
+    try:
+        # find the td tag that follows the th tag containing 'Workflow'
+        workflow_tag = soup.find("th", string="Workflow").find_next_sibling("td")  # type: ignore
+        workflow_format = workflow_tag.contents[0].strip()  # type: ignore
+    except AttributeError:
+        return GNPSFormat.Unknown
 
     if workflow_format == GNPSFormat.FBMN.value:
         return GNPSFormat.FBMN

src/nplinker/metabolomics/gnps/gnps_spectrum_loader.py

@@ -98,7 +98,7 @@ def _load(self):
             )
             self._spectra.append(spectrum)
 
-    def _get_precursor_charge(self, charges: list) -> int:
+    def _get_precursor_charge(self, charges: list[int]) -> int:
         """Get the precursor charge from the charge list.
 
         Args:

src/nplinker/metabolomics/utils.py

@@ -144,7 +144,7 @@ def extract_mappings_strain_id_ms_filename(
         PODP platform. For example, for project MSV000079284, its json file is
         https://pairedomicsdata.bioinformatics.nl/api/projects/4b29ddc3-26d0-40d7-80c5-44fb6631dbf9.4.
     """
-    mappings_dict = {}
+    mappings_dict: dict[str, set[str]] = {}
     with open(podp_project_json_file, "r") as f:
         json_data = json.load(f)