PyOpenSci REVIEW - config and download default directories

CONTRIBUTING.md

@@ -81,6 +81,11 @@ The documentation is formed by a series of markdown files located in directory [
 This means that, to modify the [API reference](https://robaina.github.io/Pynteny/references/api/), all you need to do is to modify the docstring directly in the source file where the definion/class is located. And, to update the documentation pages, you just have to update the corresponding markdown file in the [docs](https://github.com/Robaina/Pynteny/tree/main/docs) directory. Note that, if you need to change the documentation structure (e.g., add or new pages),you would need to tell mkdocs about this change through its [configuration file](https://github.com/Robaina/Pynteny/blob/main/mkdocs.yml). Or just open an issue and ask for help!
 
 When all the changes are ready to deploy, just open a pull request. After reviewing and merging the changes, the documentation will be automatically deployed.
+
+Run the documentation locally with:
+
+> mkdocs serve
+
 ## Tests on push and pull request to main
 
 Pynteny's repo contains a [GitHub Action](https://github.com/features/actions) to perform build and integration tests which is triggered automatically on push and pull request events to the main brach. Currently the tests include building and installing Pynteny in Ubuntu and MacOS and running the [test](tests) suit.

src/pynteny/cli.py

@@ -482,6 +482,14 @@ def download() -> argparse.ArgumentParser:
             action="store_true",
             help="unpack originally compressed database files",
         )
+        optional.add_argument(
+            "-f",
+            "--force",
+            dest="force",
+            default=False,
+            action="store_true",
+            help="force-download database again if already downloaded",
+        )
         optional.add_argument(
             "-l",
             "--log",

src/pynteny/subcommands.py

@@ -10,12 +10,17 @@
 import shutil
 import logging
 from pathlib import Path
-import wget
 
 from pynteny.filter import SyntenyHits, filter_FASTA_by_synteny_structure
 from pynteny.hmm import PGAP
 import pynteny.parsers.syntenyparser as syntenyparser
-from pynteny.utils import CommandArgs, ConfigParser, is_tar_file, terminal_execute
+from pynteny.utils import (
+    CommandArgs,
+    ConfigParser,
+    is_tar_file,
+    terminal_execute,
+    download_file,
+)
 from pynteny.preprocessing import Database
 
 
@@ -212,11 +217,11 @@ def download_hmms(args) -> None:
     logger = init_logger(args)
     module_dir = Path(__file__).parent
     config = ConfigParser.get_default_config()
-    if config.get_field("data_downloaded"):
+    if (config.get_field("data_downloaded")) and (not args.force):
         logger.info("PGAP database already downloaded. Skipping download")
         sys.exit(1)
     if args.outdir is None:
-        download_dir = Path(module_dir.parent) / "data"
+        download_dir = module_dir / "data"
     else:
         download_dir = Path(args.outdir).absolute()
     if not download_dir.exists():
@@ -231,8 +236,8 @@ def download_hmms(args) -> None:
     try:
         PGAP_file = download_dir / "hmm_PGAP.HMM.tgz"
         meta_file = download_dir / "hmm_PGAP.tsv"
-        wget.download(data_url, PGAP_file.as_posix())
-        wget.download(meta_url, meta_file.as_posix())
+        download_file(data_url, PGAP_file)
+        download_file(meta_url, meta_file)
         logger.info("Database dowloaded successfully\n")
         config.update_config("data_downloaded", True)
         config.update_config("PGAP_database", PGAP_file.as_posix())

src/pynteny/utils.py

@@ -8,6 +8,7 @@
 from __future__ import annotations
 import os
 import sys
+import wget
 import logging
 import shutil
 import subprocess
@@ -46,7 +47,7 @@ def initialize_config_file() -> Path:
         Returns:
             Path: path to generated config file.
         """
-        config_file = Path(__file__).parent.parent / "config.json"
+        config_file = Path(__file__).parent / "config.json"
         if not config_file.exists():
             config = {
                 "database_dir": "",
@@ -187,6 +188,16 @@ def parallelize_over_input_files(
     p.join()
 
 
+def download_file(url: str, output_file: Path) -> None:
+    """Download file from url
+
+    Args:
+        url (str): url where file to be downloaded
+        output_file (Path): path to downloaded file
+    """
+    wget.download(url, output_file.as_posix())
+
+
 def is_tar_file(tar_file: Path) -> bool:
     """Check whether file is tar-compressed.
 
@@ -196,12 +207,7 @@ def is_tar_file(tar_file: Path) -> bool:
     Returns:
         bool: whether file is compressed or not.
     """
-    tar_file_str = tar_file.as_posix()
-    return (
-        (tar_file_str.endswith("tar.gz"))
-        or (tar_file_str.endswith("tgz"))
-        or (tar_file_str.endswith("tar"))
-    )
+    return Path(tar_file).is_file() and tarfile.is_tarfile(tar_file)
 
 
 def extract_tar_file(tar_file: Path, dest_dir: Path = None) -> None:

tests/test_integration_search.py

@@ -11,16 +11,16 @@
 
 from pynteny.api import Search
 
-this_file_dir = Path(__file__).parent
+tests_dir = Path(__file__).parent
 
 
 class TestSyntenySearch(unittest.TestCase):
     def test_search(self):
         with TemporaryDirectory() as tempdir:
             search = Search(
-                data=this_file_dir / "test_data/MG1655.fasta",
+                data=tests_dir / "test_data/MG1655.fasta",
                 synteny_struc="<TIGR00171.1 0 <TIGR00170.1 1 <TIGR00973.1",
-                hmm_dir=this_file_dir / "test_data/hmms",
+                hmm_dir=tests_dir / "test_data/hmms",
                 hmm_meta=None,
                 outdir=Path(tempdir),
                 prefix="",
@@ -31,12 +31,11 @@ def test_search(self):
                 processes=None,
                 unordered=False,
             )
-            hmm_meta = this_file_dir / "test_data/hmm_meta.tsv"
+            hmm_meta = tests_dir / "test_data/hmm_meta.tsv"
             synhits = search.run()
-            # synhits_df = synhits.hits
             synhits = synhits.add_HMM_meta_info_to_hits(hmm_meta)
             synhits_df = synhits.hits
-            config = Path(this_file_dir.parent) / "config.json"
+            config = Path(tests_dir.parent) / "config.json"
             if config.exists():
                 config.unlink()
         hit_labels = [