Removed bel library dependency

.vscode/settings.json

@@ -0,0 +1,23 @@
+{
+    "workbench.colorCustomizations": {
+        "activityBar.background": "#60e75a",
+        "activityBar.activeBorder": "#7479eb",
+        "activityBar.foreground": "#15202b",
+        "activityBar.inactiveForeground": "#15202b99",
+        "activityBarBadge.background": "#7479eb",
+        "activityBarBadge.foreground": "#15202b",
+        "titleBar.activeBackground": "#35e12d",
+        "titleBar.inactiveBackground": "#35e12d99",
+        "titleBar.activeForeground": "#15202b",
+        "titleBar.inactiveForeground": "#15202b99",
+        "statusBar.background": "#35e12d",
+        "statusBarItem.hoverBackground": "#23c01b",
+        "statusBar.foreground": "#15202b"
+    },
+    "peacock.remoteColor": "#35e12d",
+    "python.pythonPath": ".venv/bin/python",
+    "python.testing.promptToConfigure": false,
+    "python.testing.pytestEnabled": false,
+    "python.testing.unittestEnabled": false,
+    "python.testing.nosetestsEnabled": false
+}

README.rst → README.md

@@ -1,6 +1,11 @@
-BEL Resource tools
-==============
+# BEL Resource tools
 
 This repository contains scripts to create standardized load files for BEL Resources for use with the BEL.bio API.
 
 `Documentation <http://bel-resources.readthedocs.io/en/latest/>`_
+
+## Install/setup
+
+Run
+
+    bin/

tools/backbone/gene2protein.py → app/backbone/gene2protein.py

@@ -8,21 +8,17 @@
                         m() and r() translatedTo p()
 """
 
-import json
 import gzip
+import json
 
-from tools.utils.Config import config
-
-import tools.setup_logging
+import app.settings as settings
 import structlog
 
 log = structlog.getLogger(__name__)
 
-eg_datafile = f'{config["bel_resources"]["file_locations"]["data"]}/namespaces/eg.jsonl.gz'
-backbone_fn = (
-    f'{config["bel_resources"]["file_locations"]["data"]}/backbone/eg_backbone_nanopubs.jsonl.gz'
-)
-backbone_hmrz_fn = f'{config["bel_resources"]["file_locations"]["data"]}/backbone/eg_backbone_nanopubs_hmrz.jsonl.gz'
+eg_datafile = f"{settings.DATA_DIR}/namespaces/eg.jsonl.gz"
+backbone_fn = f"{settings.DATA_DIR}/backbone/eg_backbone_nanopubs.jsonl.gz"
+backbone_hmrz_fn = f"{settings.DATA_DIR}/backbone/eg_backbone_nanopubs_hmrz.jsonl.gz"
 
 hmrz_species = ["TAX:9606", "TAX:10090", "TAX:10116", "TAX:7955"]
 

tools/namespaces/TEMPLATE.py → app/namespaces/TEMPLATE.py

@@ -6,22 +6,23 @@
 
 """
 
-import sys
-import re
-import os
-import tempfile
-import json
-import yaml
-import datetime
 import copy
+import datetime
 import gzip
-from typing import List, Mapping, Any, Iterable
+import json
+import os
+import re
+import sys
+import tempfile
+from typing import Any, Iterable, List, Mapping
 
-import tools.utils.utils as utils
-from tools.utils.Config import config
+import yaml
 
-import tools.setup_logging
+import app.settings as settings
+import app.setup_logging
+import app.utils as utils
 import structlog
+
 log = structlog.getLogger(__name__)
 
 """
@@ -31,42 +32,44 @@
 3.  Dataset preprocessing - e.g. double check term names for duplicates if you
     plan on using them for IDs, pre-collect information needed to build the term record
 4.  Process terms and write them to terms_fp file
-    filter out species not in config['bel_resources']['species_list'] unless empty list
+    filter out species not in settings.SPECIES_LIST unless empty list
 """
 
 # Globals ###################################################################
-namespace_key = 'REPLACEME'  # namespace key into namespace definitions file
-namespace_def = utils.get_namespace(namespace_key, config)
-ns_prefix = namespace_def['namespace']
+namespace_key = "REPLACEME"  # namespace key into namespace definitions file
+namespace_def = settings.NAMESPACE_DEFINITIONS[namespace_key]
+ns_prefix = namespace_def[namespace_key]["namespace"]
 
 # FTP options
-server = 'REPLACEME'
-source_data_fp = 'REPLACEME'  # may have multiple files to be downloaded
+server = "REPLACEME"
+source_data_fp = "REPLACEME"  # may have multiple files to be downloaded
 # Web file options
-url = 'REPLACEME'  # may have multiple files to be downloaded
+url = "REPLACEME"  # may have multiple files to be downloaded
 
 # Local data filepath setup
 basename = os.path.basename(source_data_fp)
 
-if not re.search('.gz$', basename):  # we basically gzip everything retrieved that isn't already gzipped
-    basename = f'{basename}.gz'
+if not re.search(
+    ".gz$", basename
+):  # we basically gzip everything retrieved that isn't already gzipped
+    basename = f"{basename}.gz"
 
 # Pick one of the two following options
-local_data_fp = f'{config["bel_resources"]["file_locations"]["downloads"]}/{namespace_key}_{basename}'
-# local_data_fp = f'{config["bel_resources"]["file_locations"]["downloads"]}/{basename}'  # if namespace_key already is prefixed to basename
+local_data_fp = f"{settings.DOWNLOAD_DIR}/{namespace_key}_{basename}"
+# local_data_fp = f'{settings.DOWNLOAD_DIR}/{basename}'  # if namespace_key already is prefixed to basename
 
 
 def get_metadata():
     # Setup metadata info - mostly captured from namespace definition file which
     # can be overridden in belbio_conf.yml file
     dt = datetime.datetime.now().replace(microsecond=0).isoformat()
     metadata = {
-        "name": namespace_def['namespace'],
-        "namespace": namespace_def['namespace'],
-        "description": namespace_def['description'],
+        "name": namespace_def["namespace"],
+        "namespace": namespace_def["namespace"],
+        "description": namespace_def["description"],
         "version": dt,
-        "src_url": namespace_def['src_url'],
-        "url_template": namespace_def['template_url'],
+        "src_url": namespace_def["src_url"],
+        "url_template": namespace_def["template_url"],
     }
 
     return metadata
@@ -81,59 +84,58 @@ def update_data_files() -> bool:
         bool: files updated = True, False if not
     """
 
-    update_cycle_days = config['bel_resources']['update_cycle_days']
-    # Can override/hard-code update_cycle_days in each term collection file if desired
+    # Can override/hard-code settings.UPDATE_CYCLE_DAYS in each term collection file if desired
 
     # This is all customizable - but here are some of the most common options
 
     # Get ftp file - but not if local downloaded file is newer
-    # result = utils.get_ftp_file(server, source_data_fp, local_data_fp, days_old=update_cycle_days)
+    # result = utils.get_ftp_file(server, source_data_fp, local_data_fp, days_old=settings.UPDATE_CYCLE_DAYS)
 
     # Get web file - but not if local downloaded file is newer
-    # (changed_flag, msg) = utils.get_web_file(url, local_data_fp, days_old=update_cycle_days)
+    # (changed_flag, msg) = utils.get_web_file(url, local_data_fp, days_old=settings.UPDATE_CYCLE_DAYS)
     # log.info(msg)
 
 
 def build_json(force: bool = False):
     """Build term JSONL file"""
 
     # Terminology JSONL output filename
-    data_fp = config["bel_resources"]["file_locations"]["data"]
-    terms_fp = f'{data_fp}/namespaces/{namespace_key}.jsonl.gz'
+    data_fp = settings.DATA_DIR
+    terms_fp = f"{data_fp}/namespaces/{namespace_key}.jsonl.gz"
 
     # used if you need a tmp dir to do some processing
     # tmpdir = tempfile.TemporaryDirectory()
 
     # Don't rebuild file if it's newer than downloaded source file
     if not force:
         if utils.file_newer(terms_fp, local_data_fp):
-            log.info('Will not rebuild data file as it is newer than downloaded source files')
+            log.info("Will not rebuild data file as it is newer than downloaded source files")
             return False
 
-    with gzip.open(local_data_fp, 'rt') as fi, gzip.open(terms_fp, 'wt') as fo:
+    with gzip.open(local_data_fp, "rt") as fi, gzip.open(terms_fp, "wt") as fo:
 
         # Header JSONL record for terminology
         metadata = get_metadata()
-        fo.write("{}\n".format(json.dumps({'metadata': metadata})))
+        fo.write("{}\n".format(json.dumps({"metadata": metadata})))
 
         for row in fi:
 
             # review https://github.com/belbio/schemas/blob/master/schemas/terminology-0.1.0.yaml
             # for what should go in here
             term = {
-                'namespace': ns_prefix,
-                'src_id': '',
-                'id': '',
-                'alt_ids': [],
-                'label': '',
-                'name': '',
-                'synonyms': copy.copy(list(set([]))),
-                'entity_types': [],
-                'equivalences': [],
+                "namespace": ns_prefix,
+                "src_id": "",
+                "id": "",
+                "alt_ids": [],
+                "label": "",
+                "name": "",
+                "synonyms": copy.copy(list(set([]))),
+                "entity_types": [],
+                "equivalences": [],
             }
 
             # Add term to JSONLines file
-            fo.write("{}\n".format(json.dumps({'term': term})))
+            fo.write("{}\n".format(json.dumps({"term": term})))
 
 
 def main():
@@ -142,5 +144,5 @@ def main():
     build_json()
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()