fix missing import in bactopia-prepare

Author: rpetit3

.flake8

@@ -1,4 +1,4 @@
 [flake8]
 max-line-length = 88
 # the default ignores minus E704
-ignore = E121,E123,E126,E226,E203,E24,F401,E402,F403,E501,W503,W504
+ignore = E24,E121,E123,E126,E203,E221,E226,E231,E713,F401,E402,F403,E501,W503,W504

CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 1.6.1
+
+- shuffle ncbi related module out of `utils` and into `ncbi`
+- fixed missing import in `bactopia-prepare`
+
+
 ## 1.6.0
 
 - `bactopia-search`

bactopia/cli/prepare.py

@@ -11,7 +11,8 @@
 from rich.logging import RichHandler
 
 import bactopia
-from bactopia.utils import get_ncbi_genome_size, get_taxid_from_species, validate_file
+from bactopia.databases.ncbi import get_ncbi_genome_size, get_taxid_from_species
+from bactopia.utils import validate_file
 
 # Set up Rich
 stderr = rich.console.Console(stderr=True)

bactopia/databases/ncbi.py

@@ -57,6 +57,38 @@ def is_biosample(accession: str) -> bool:
     )
 
 
+def get_taxid_from_species(species: str) -> str:
+    """
+    Convert a species name into a tax_id
+
+    Args:
+        species (str): A species name
+
+    Returns:
+        str: The corresponding tax_id
+    """
+    r = requests.get(
+        f"https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=taxonomy&term={species}"
+    )
+    taxid = None
+    if r.status_code == requests.codes.ok:
+        for line in r.text.split("\n"):
+            line = line.strip()
+            if line.startswith("<Id>"):
+                taxid = line.replace("<Id>", "").replace("</Id>", "")
+        if taxid:
+            logging.debug(f"Found taxon ID ({taxid}) for {species}")
+            return taxid
+        else:
+            logging.error(
+                f"Unable to determine taxon ID from {species}, please check spelling or try again later."
+            )
+            sys.exit(1)
+    else:
+        logging.error("Unexpected error querying NCBI, please try again later.")
+        sys.exit(1)
+
+
 def taxid2name(taxids: list, ncbi_api_key: str, chunk_size: int) -> dict:
     """
     Convert a list of NCBI TaxIDs to species names.

bactopia/utils.py

@@ -40,7 +40,7 @@ def execute(
             check=True,  # Raises CalledProcessError for non-zero exit codes
         )
         logging.debug(f"Exit code: {command.returncode}")
-        logging.debug(f"STDOUT:\n{command.stdout}")
+        logging.debug(f"STDOUT: \n{command.stdout}")
         logging.debug(f"STDERR:\n{command.stderr}")
 
         if capture:
@@ -188,38 +188,6 @@ def remove_keys(results: dict, remove: list) -> dict:
     return removed
 
 
-def get_taxid_from_species(species: str) -> str:
-    """
-    Convert a species name into a tax_id
-
-    Args:
-        species (str): A species name
-
-    Returns:
-        str: The corresponding tax_id
-    """
-    r = requests.get(
-        f"https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=taxonomy&term={species}"
-    )
-    taxid = None
-    if r.status_code == requests.codes.ok:
-        for line in r.text.split("\n"):
-            line = line.strip()
-            if line.startswith("<Id>"):
-                taxid = line.replace("<Id>", "").replace("</Id>", "")
-        if taxid:
-            logging.debug(f"Found taxon ID ({taxid}) for {species}")
-            return taxid
-        else:
-            logging.error(
-                f"Unable to determine taxon ID from {species}, please check spelling or try again later."
-            )
-            sys.exit(1)
-    else:
-        logging.error("Unexpected error querying NCBI, please try again later.")
-        sys.exit(1)
-
-
 def download_url(url: str, save_path: str, show_progress: bool) -> str:
     """
     Download a file from a URL