Merge pull request #52 from mdshw5/mtime_reindex

Changes for v0.3.6. Fixes #50 and adds testing improvements in #51.

.travis.yml

@@ -1,17 +1,20 @@
 language: python
-sudo: false
 python:
-- '3.4'
-- '3.3'
-- '3.2'
-- '2.7'
-- '2.6'
-- pypy
-- pypy3
+    - '3.4'
+    - '3.3'
+    - '3.2'
+    - '2.7'
+    - '2.6'
+    - pypy
+    - pypy3
 install:
-- pip install biopython || true
-- pip install -e .
-- pip install coveralls
+    - pip install biopython || true
+    - pip install -e .
+    - pip install coveralls
+before_script:
+    - sudo apt-get update -qq
+    - sudo apt-get install -y python-biopython
+    - if [ ! -e "tests/data/genes.fasta" ]; then /usr/bin/python tests/data/download_gene_fasta.py; fi
 script: nosetests --with-coverage --cover-package=pyfaidx
 deploy:
   provider: pypi
@@ -25,5 +28,7 @@ deploy:
     repo: mdshw5/pyfaidx
 cache:
     - wheelhouse
+    - tests/data
+    - apt
 after_success:
     - coveralls

pyfaidx/__init__.py

@@ -6,6 +6,7 @@
 
 from __future__ import division
 import os
+from os.path import getmtime
 from six import PY2, PY3, string_types
 from six.moves import zip_longest
 try:
@@ -20,7 +21,7 @@
 
 dna_bases = re.compile(r'([ACTGNactgnYRWSKMDVHBXyrwskmdvhbx]+)')
 
-__version__ = '0.3.5'
+__version__ = '0.3.6'
 
 
 class FastaIndexingError(Exception):
@@ -44,7 +45,7 @@ def __init__(self, msg=None):
 class RegionError(Exception):
     def __init__(self, msg=None):
         self.msg = 'Malformed region! Format = rname:start-end.\n' if not msg else msg
-        super(RegionError, self).__init__(self.msg)        
+        super(RegionError, self).__init__(self.msg)
 
 
 class Sequence(object):
@@ -203,7 +204,7 @@ def __init__(self, filename, default_seq=None, key_function=None,
 
         self.mutable = mutable
 
-        if os.path.exists(self.indexname):
+        if os.path.exists(self.indexname) and getmtime(self.indexname) > getmtime(self.filename):
             self.read_fai(split_char)
         else:
             try:
@@ -295,7 +296,7 @@ def check_bad_lines(rname, bad_lines, i):
                         # only one short line should be allowed
                         # before we hit the next header, and it
                         # should be the last line in the entry
-                        if line_blen != blen or line_blen == 0:
+                        if line_blen != blen or line_blen == 1:
                             bad_lines.append(i)
                         offset += line_blen
                         rlen += line_clen
@@ -420,6 +421,9 @@ def to_file(self, rname, start, end, seq):
                     m += line_len
                 self.file.write(seq[n:].encode())
 
+    def close(self):
+        self.__exit__()
+
     def __enter__(self):
         return self
 

tests/data/download_gene_fasta.py

@@ -0,0 +1,31 @@
+#!/usr/bin/env python
+import os.path
+
+def fetch_fasta(filename):
+    from Bio import Entrez
+    Entrez.email = "mdshw5@gmail.com"
+
+    id_list = ['563317589', '557361099', '557361097', '543583796',
+               '543583795', '543583794', '543583788', '543583786',
+               '543583785', '543583740', '543583738', '530384540',
+               '530384538', '530384536', '530384534', '530373237',
+               '530373235', '530364726', '530364725', '530364724']
+
+    search_results = Entrez.read(Entrez.epost("nucleotide", id=",".join(id_list)))
+
+    webenv = search_results["WebEnv"]
+    query_key = search_results["QueryKey"]
+
+    records = Entrez.efetch(db="nucleotide", rettype="fasta", retmode="text", webenv=webenv, query_key=query_key)
+
+    with open(filename, 'w') as fasta:
+        for line in records:
+            if len(line) > 1:  # skip lines with only \n
+                fasta.write(line)
+
+
+if __name__ == "__main__":
+    path = os.path.dirname(__file__)
+    os.chdir(path)
+    fasta_name = "genes.fasta"
+    fetch_fasta(fasta_name)