removed outdated newline chars

hgtector/analyze.py

@@ -274,7 +274,7 @@ def read_search_results(file, maxhits=None):
         data = []
         with read_file(file) as f:
             for line in f:
-                line = line.rstrip('\r\n')
+                line = line.rstrip()
                 m = p.match(line)
                 if m:
                     if m.group(1) == 'ID':

hgtector/database.py

@@ -596,7 +596,7 @@ def write_prot():
                 fin = gzip.open(file, 'r')
             cp = None
             for line in fin:
-                line = line.rstrip('\r\n')
+                line = line.rstrip()
                 if line.startswith('>'):
                     write_prot()
                     p, name = line[1:].split(None, 1)
@@ -708,7 +708,7 @@ def build_taxdump(self):
             fo = open(join(dir_, fname), 'w')
             fi = open(join(self.tmpdir, fname), 'r')
             for line in fi:
-                x = line.rstrip('\r\n').replace('\t|', '').split('\t')
+                x = line.rstrip().replace('\t|', '').split('\t')
                 if x[0] in ancs:
                     if key == 'nodes' or 'scientific name' in x:
                         fo.write(line)

hgtector/search.py

@@ -576,7 +576,7 @@ def input_wf(self):
                 scores = {}
                 with open(file, 'r') as f:
                     for line in f:
-                        line = line.rstrip('\r\n')
+                        line = line.rstrip()
                         if not line or line.startswith('#'):
                             continue
                         id_, score = line.split('\t')
@@ -1125,7 +1125,7 @@ def parse_prev_results(fp, prots):
         with open(fp, 'r') as f:
             for line in f:
                 if line.startswith('# ID: '):
-                    done.append(line[6:].rstrip('\r\n'))
+                    done.append(line[6:].rstrip())
         doneset = set(done)
         for prot in prots:
             if prot['id'] in doneset:
@@ -1684,7 +1684,7 @@ def parse_hit_table(self, file, lenmap=None):
         lines = []
         with open(file, 'r') as f:
             for line in f:
-                line = line.rstrip('\r\n')
+                line = line.rstrip()
                 if line and not line.startswith('#'):
                     lines.append(line)
                     if ism8 is None:
@@ -1711,7 +1711,7 @@ def parse_def_table(self, lines):
         ths = {x: getattr(self, x, 0) for x in (
             'evalue', 'identity', 'coverage', 'maxhits')}
         for line in lines:
-            line = line.rstrip('\r\n')
+            line = line.rstrip()
             if not line or line.startswith('#'):
                 continue
             x = line.split('\t')
@@ -1765,7 +1765,7 @@ def parse_m8_table(self, lines, lenmap):
         ths = {x: getattr(self, x, 0) for x in (
             'evalue', 'identity', 'coverage', 'maxhits')}
         for line in lines:
-            line = line.rstrip('\r\n')
+            line = line.rstrip()
             if not line or line.startswith('#'):
                 continue
             x = line.split('\t')
@@ -2235,7 +2235,7 @@ def parse_self_m8(lines):
         res = []
         used = set()
         for line in lines:
-            x = line.rstrip('\r\n').split('\t')
+            x = line.rstrip().split('\t')
             if x[0].startswith('#'):
                 continue
             if len(x) < 12:

hgtector/util.py

@@ -311,7 +311,7 @@ def read_input_prots(fp):
     lines = []
     with read_file(fp) as f:
         for line in f:
-            line = line.rstrip('\r\n')
+            line = line.rstrip()
             if not line or line.startswith('#'):
                 continue
 
@@ -360,7 +360,7 @@ def read_fasta(lines):
     """
     seqs = []
     for line in lines:
-        line = line.rstrip('\r\n')
+        line = line.rstrip()
         if line.startswith('>'):
             x = line[1:].split(None, 1)
             seqs.append([x[0], get_product(x[1]) if len(x) > 1 else '', ''])
@@ -564,11 +564,11 @@ def read_taxdump(dir_):
     taxdump = {}
     with open(join(dir_, 'nodes.dmp'), 'r') as f:
         for line in f:
-            x = line.rstrip('\r\n').replace('\t|', '').split('\t')
+            x = line.rstrip().replace('\t|', '').split('\t')
             taxdump[x[0]] = {'parent': x[1], 'rank': x[2]}
     with open(join(dir_, 'names.dmp'), 'r') as f:
         for line in f:
-            x = line.rstrip('\r\n').replace('\t|', '').split('\t')
+            x = line.rstrip().replace('\t|', '').split('\t')
             if len(x) < 4 or x[3] == 'scientific name':
                 try:
                     taxdump[x[0]]['name'] = x[1]
@@ -600,7 +600,7 @@ def read_prot2taxid(file):
     res = {}
     with read_file(file) as f:
         for line in f:
-            x = line.rstrip('\r\n').split()
+            x = line.rstrip().split()
             if len(x) == 1:
                 continue
             if isncbi is None: