Merge pull request #110 from rigdenlab/update-stats

Update stats

README.rst

@@ -10,7 +10,7 @@ Sequence Independent Molecular Replacement Based on Available Database
    :target: https://landscape.io/github/rigdenlab/SIMBAD/master
    :alt: Code Health
 
-.. image:: https://img.shields.io/badge/solution%20count-6-blue.svg?style=flat
+.. image:: https://img.shields.io/badge/solution%20count-8-blue.svg?style=flat
    :alt: Solution count
 
 .. image:: https://img.shields.io/badge/DOI-10.1107/S2059798318005752-blue.svg

scripts/stats.py

@@ -1,39 +1,51 @@
-#!/usr/bin/env ccp4-python
+#!/usr/bin/env python
 
 """Script to compute some SIMBAD statistics --- work in progress"""
-
 from __future__ import print_function
 
 __author__ = "Felix Simkovic"
-__date__ = "30 Mar 2018"
-__version__ = "1.0"
+__date__ = "21 Jul 2019"
+__version__ = "2.0"
+
+import logging
 
+logging.basicConfig(level=logging.INFO)
 import os
 import re
+import requests
 import urllib2
 
-url = 'http://www.rcsb.org/pdb/rest/search'
-data = """
+LOG = logging.getLogger(__name__)
+BASE_URL = "http://www.rcsb.org/pdb/rest/"
+PAYLOAD = """
 <orgPdbQuery>
 <queryType>org.pdb.query.simple.AdvancedKeywordQuery</queryType>
 <description>Text Search for: simbad</description>
 <keywords>simbad</keywords>
 </orgPdbQuery>
 """
-header = {'Content-Type': 'application/x-www-form-urlencoded'}
-
-req = urllib2.Request(url, data, header)
-response = urllib2.urlopen(req)
-
-if response.getcode() == 200:
-    entries = response.readlines()
-    count = len(entries)
-    print("SIMBAD solved {} structures".format(count))
-else:
-    raise Exception("Could not retrieve data")
-readme = os.path.join(os.path.dirname(__file__), "..", "README.rst")
-with open(readme, "r") as f_in:
-    data = f_in.read()
-    data = re.sub(r"solution\%20count-\d+-blue", "solution%20count-{}-blue".format(count), data)
-with open(readme, "w") as f_out:
-    f_out.write(data)
+
+
+def update_readme(n_sols):
+    readme = os.path.join(os.path.dirname(__file__), "..", "README.rst")
+    with open(readme, "r") as fh:
+        text = fh.read()
+    text = re.sub(
+        r"solution\%20count-\d+-blue", "solution%20count-{}-blue".format(n_sols), text
+    )
+    with open(readme, "w") as fh:
+        fh.write(text)
+
+
+if __name__ == "__main__":
+    header = {"Content-Type": "application/x-www-form-urlencoded"}
+    url = requests.compat.urljoin(BASE_URL, "search")
+
+    response = requests.post(url, data=PAYLOAD, headers=header)
+    response.raise_for_status()
+
+    entries = response.content.splitlines()
+
+    n_solutions = len(entries)
+    LOG.info("Found %s solutions", n_solutions)
+    update_readme(n_solutions)

simbad/db/__init__.py

@@ -32,8 +32,10 @@ def find_simbad_dat_files(directory):
        A list of paths to the files
     """
     return [
-        os.path.join(root, filename) for root, _, files in os.walk(directory) for filename in files
-        if filename.endswith('.dat')
+        os.path.join(root, filename)
+        for root, _, files in os.walk(directory)
+        for filename in files
+        if filename.endswith(".dat")
     ]
 
 
@@ -48,7 +50,7 @@ def convert_dat_to_pdb(infile, outfile):
         Path to the output pdb file
 
     """
-    with open(infile, 'rb') as f_in, open(outfile, 'w') as f_out:
+    with open(infile, "rb") as f_in, open(outfile, "w") as f_out:
         f_out.write(_from_dat(f_in))
 
 
@@ -83,9 +85,10 @@ def is_valid_dat(infile):
     with open(infile, "rb") as f_in:
         try:
             _from_dat(f_in)
-            is_valid = True
         except:
             is_valid = False
+        else:
+            is_valid = True
     return is_valid