From 1bceebfc50610a4746c8f8cbd3cca21327608358 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Joan=20H=C3=A9risson?= <joan.herisson@univ-evry.fr>
Date: Tue, 21 Jun 2022 10:48:25 +0200
Subject: [PATCH] feat: add --data-path arg

---
 selenzy_wrapper/Args.py            | 16 ++++++++++++++++
 selenzy_wrapper/__main__.py        |  1 +
 selenzy_wrapper/selenzy_wrapper.py | 28 ++++++++++++----------------
 3 files changed, 29 insertions(+), 16 deletions(-)

diff --git a/selenzy_wrapper/Args.py b/selenzy_wrapper/Args.py
index 7379d75..6dcc29e 100644
--- a/selenzy_wrapper/Args.py
+++ b/selenzy_wrapper/Args.py
@@ -1,7 +1,11 @@
 from argparse  import ArgumentParser
+from os import (
+    path as os_path,
+)
 from typing import (
     Callable,
 )
+
 from selenzy_wrapper._version import __version__
 from brs_utils import add_logger_args
 
@@ -9,6 +13,11 @@
 DEFAULT_NB_IDS = -1
 DEFAULT_HOST = '83333'
 DEFAULT_MAX_NB_GENES = 5
+__PACKAGE_FOLDER = os_path.dirname(
+    os_path.realpath(__file__)
+)
+DEFAULT_DATA_FOLDER = __PACKAGE_FOLDER
+
 
 def build_args_parser(
     prog: str,
@@ -109,4 +118,11 @@ def add_arguments(parser: ArgumentParser) -> ArgumentParser:
         default=None,
         help='''Comma separated taxon IDs of output enzyme sequences'''
     )
+    parser.add_argument(
+        '--data-path',
+        type=str,
+        default=DEFAULT_DATA_FOLDER,
+        help='''Path of the data directory. If does not exist,
+        a 'data' folder will be created (default in package directory)'''
+    )
     return parser
diff --git a/selenzy_wrapper/__main__.py b/selenzy_wrapper/__main__.py
index 9a2c74f..82c301d 100644
--- a/selenzy_wrapper/__main__.py
+++ b/selenzy_wrapper/__main__.py
@@ -63,6 +63,7 @@ def entry_point():
         taxonIDs=taxonIDs,
         nb_targets=args.nb_targets,
         nb_ids=args.nb_ids,
+        datadir=args.data_path,
         logger=logger
     )
 
diff --git a/selenzy_wrapper/selenzy_wrapper.py b/selenzy_wrapper/selenzy_wrapper.py
index a410076..b5a668c 100644
--- a/selenzy_wrapper/selenzy_wrapper.py
+++ b/selenzy_wrapper/selenzy_wrapper.py
@@ -20,10 +20,9 @@
 from .Args import (
     DEFAULT_NB_TARGETS,
     DEFAULT_NB_IDS,
-    DEFAULT_HOST
-)
-__PACKAGE_FOLDER = os_path.dirname(
-    os_path.realpath(__file__)
+    DEFAULT_HOST,
+    DEFAULT_DATA_FOLDER,
+    __PACKAGE_FOLDER
 )
 __SELENZY_FOLDER = 'selenzy'
 sys_path.insert(
@@ -36,29 +35,26 @@
 from .selenzy.Selenzy import readData
 from .selenzy.newtax import newtax
 
-
 __DATA_URL = 'https://gitlab.com/breakthewall/rrcache-data/-/raw/master/selenzy/data.tar.gz'
-__DATA_FOLDER = os_path.join(
-    __PACKAGE_FOLDER,
-    'data'
-)
-
 
 def selenzy_pathway(
     pathway: rpPathway = None,
     taxonIDs: str = DEFAULT_HOST,
     nb_targets: int = DEFAULT_NB_TARGETS,
     nb_ids: int = DEFAULT_NB_IDS,
+    datadir: str = DEFAULT_DATA_FOLDER,
     logger: Logger = getLogger(__name__)
 ) -> Dict:
-    if not os_path.exists(__DATA_FOLDER):
-        logger.info(f'Downloading databases into {__DATA_FOLDER}...')
+
+    datadir_data = os_path.join(datadir, 'data')
+    if not os_path.exists(datadir_data):
+        logger.info(f'Downloading databases into \'{os_path.abspath(datadir)}\'...')
         download_and_extract_tar_gz(
             __DATA_URL,
-            __PACKAGE_FOLDER
+            datadir
         )
-    logger.info('Reading databases...')
-    pc = readData(__DATA_FOLDER)
+    logger.info(f'Reading databases from \'{os_path.abspath(datadir)}\'...')
+    pc = readData(datadir_data)
 
     result_ids = {}
     for rxn_id, rxn in pathway.get_reactions().items():
@@ -68,7 +64,7 @@ def selenzy_pathway(
                     smarts=True,
                     rxn=rxn.get_smiles(),
                     taxonIDs=taxonIDs,
-                    datadir=__DATA_FOLDER,
+                    datadir=datadir_data,
                     outdir=tmpOutputFolder,
                     nb_targets=nb_targets,
                     pc=pc,