ls fixes

changelog.txt

@@ -1,13 +1,10 @@
 jc changelog
 
-2019xxxx v0.5.0
+20191018 v0.5.4
 - Fix netstat -p parsing for Ubuntu
 - Add ps parser
 - Add route parser
-+ Change some ifconfig fields to integers
+- ls parser fixes
-+ Use maxsplit option in split in ls.py line 109... otherwise filenames with multiple spaces
-    between words can be incorrectly represented with the .join operation
-+ Use list(filter(None, cleandata)) or list comprehension to clean any blank entries in ls.py line 98
 
 20191017 v0.2.0
 - ifconfig, ls, and netstat support

jc/parsers/ls.py

@@ -89,43 +89,43 @@ import re
 def parse(data):
     output = []
 
-    cleandata = data.splitlines()
+    linedata = data.splitlines()
 
     # Delete first line if it starts with 'total'
-    if cleandata[0].find('total') == 0:
+    if linedata[0].find('total') == 0:
-        cleandata.pop(0)
+        linedata.pop(0)
 
-    # Delete last line if it is blank
+    # Clear any blank lines
-    if cleandata[-1] == '':
+    cleandata = list(filter(None, linedata))
-        cleandata.pop(-1)
 
-    # Check if -l was used to parse extra data
+    if cleandata:
-    if re.match('^[-dclpsbDCMnP?]([-r][-w][-xsS]){2}([-r][-w][-xtT])[+]?', cleandata[0]):
+        # Check if -l was used to parse extra data
-        for entry in cleandata:
+        if re.match('^[-dclpsbDCMnP?]([-r][-w][-xsS]){2}([-r][-w][-xtT])[+]?', cleandata[0]):
-            output_line = {}
+            for entry in cleandata:
+                output_line = {}
 
-            parsed_line = entry.split()
+                parsed_line = entry.split(maxsplit=8)
 
-            # split filenames and links
+                # split filenames and links
-            filename_field = ' '.join(parsed_line[8:]).split(' -> ')
+                filename_field = parsed_line[8].split(' -> ')
 
-            # create list of dictionaries
+                # create list of dictionaries
-            output_line['filename'] = filename_field[0]
+                output_line['filename'] = filename_field[0]
 
-            if len(filename_field) > 1:
+                if len(filename_field) > 1:
-                output_line['link_to'] = filename_field[1]
+                    output_line['link_to'] = filename_field[1]
 
-            output_line['flags'] = parsed_line[0]
+                output_line['flags'] = parsed_line[0]
-            output_line['links'] = int(parsed_line[1])
+                output_line['links'] = int(parsed_line[1])
-            output_line['owner'] = parsed_line[2]
+                output_line['owner'] = parsed_line[2]
-            output_line['group'] = parsed_line[3]
+                output_line['group'] = parsed_line[3]
-            output_line['bytes'] = int(parsed_line[4])
+                output_line['bytes'] = int(parsed_line[4])
-            output_line['date'] = ' '.join(parsed_line[5:8])
+                output_line['date'] = ' '.join(parsed_line[5:8])
-            output.append(output_line)
+                output.append(output_line)
-    else:
+        else:
-        for entry in cleandata:
+            for entry in cleandata:
-            output_line = {}
+                output_line = {}
-            output_line['filename'] = entry
+                output_line['filename'] = entry
-            output.append(output_line)
+                output.append(output_line)
 
     return output

setup.py

@@ -5,7 +5,7 @@ with open('README.md', 'r') as f:
 
 setuptools.setup(
     name='jc',
-    version='0.5.3',
+    version='0.5.4',
     author='Kelly Brazil',
     author_email='kellyjonbrazil@gmail.com',
     description='This tool serializes the output of popular command line tools to structured JSON output.',