fix for cases where the Filesystem data overflows the column length (happens on older versions of df)

jc/parsers/df.py

@@ -92,13 +92,14 @@ Examples:
       ...
     ]
 """
+import hashlib
 import jc.utils
 import jc.parsers.universal
 
 
 class info():
     """Provides parser metadata (version, author, etc.)"""
-    version = '1.7'
+    version = '1.8'
     description = '`df` command parser'
     author = 'Kelly Brazil'
     author_email = 'kellyjonbrazil@gmail.com'
@@ -165,6 +166,29 @@ def _process(proc_data):
     return proc_data
 
 
+def _long_filesystem_hash(header, line):
+    """Returns truncated hash and value of the filesystem field if it is too long for the column"""
+    filesystem_field = line.split()[0]
+
+    # get length of filesystem column
+    space_count = 0
+    for char in header[10:]:
+        if char == ' ':
+            space_count += 1
+            continue
+
+        break
+
+    filesystem_col_len = space_count + 9
+
+    # return the hash and value if the field data is longer than the column length
+    if len(filesystem_field) > filesystem_col_len:
+        truncated_hash = hashlib.sha256(filesystem_field.encode('utf-8')).hexdigest()[:filesystem_col_len]
+        return truncated_hash, filesystem_field
+
+    return None, None
+
+
 def parse(data, raw=False, quiet=False):
     """
     Main text parsing function
@@ -184,7 +208,9 @@ def parse(data, raw=False, quiet=False):
         jc.utils.compatibility(__name__, info.compatible)
 
     cleandata = data.splitlines()
+    fix_data = []
     raw_output = []
+    filesystem_map = {}
 
     if jc.utils.has_data(data):
 
@@ -193,8 +219,25 @@ def parse(data, raw=False, quiet=False):
         cleandata[0] = cleandata[0].replace('-', '_')
         cleandata[0] = cleandata[0].replace('mounted on', 'mounted_on')
 
+        # fix long filesystem data in some older versions of df
+        header = cleandata[0]
+        fix_data.append(header)
+        for line in cleandata[1:]:
+            field_hash, field_value = _long_filesystem_hash(header, line)
+            if field_hash:
+                filesystem_map.update({field_hash: field_value})
+                newline = line.replace(field_value, field_hash)
+                fix_data.append(newline)
+            else:
+                fix_data.append(line)
+
         # parse the data
-        raw_output = jc.parsers.universal.sparse_table_parse(cleandata)
+        raw_output = jc.parsers.universal.sparse_table_parse(fix_data)
+
+        # replace hash values with real values to fix long filesystem data in some older versions of df
+        for item in raw_output:
+            if item['filesystem'] in filesystem_map:
+                item['filesystem'] = filesystem_map[item['filesystem']]
 
     if raw:
         return raw_output

tests/fixtures/generic/df-long-filesystem.json

@@ -0,0 +1 @@
+[{"filesystem":"/dev/mapper/VolGroup00-LogVol00","type":"ext3","1024_blocks":6030784,"used":1147932,"available":4571556,"mounted_on":"/","capacity_percent":21},{"filesystem":"proc","type":"proc","1024_blocks":0,"used":0,"available":0,"mounted_on":"/proc","capacity_percent":null},{"filesystem":"sysfs","type":"sysfs","1024_blocks":0,"used":0,"available":0,"mounted_on":"/sys","capacity_percent":null}]

tests/fixtures/generic/df-long-filesystem.out

@@ -0,0 +1,4 @@
+Filesystem    Type 1024-blocks      Used Available Capacity Mounted on
+/dev/mapper/VolGroup00-LogVol00 ext3     6030784   1147932   4571556      21% /
+proc          proc           0         0         0       -  /proc
+sysfs        sysfs           0         0         0       -  /sys

tests/test_df.py

@@ -34,6 +34,9 @@ class MyTests(unittest.TestCase):
         with open(os.path.join(THIS_DIR, os.pardir, 'tests/fixtures/osx-10.14.6/df-h.out'), 'r', encoding='utf-8') as f:
             self.osx_10_14_6_df_h = f.read()
 
+        with open(os.path.join(THIS_DIR, os.pardir, 'tests/fixtures/generic/df-long-filesystem.out'), 'r', encoding='utf-8') as f:
+            self.generic_df_long_filesystem = f.read()
+
         # output
         with open(os.path.join(THIS_DIR, os.pardir, 'tests/fixtures/centos-7.7/df.json'), 'r', encoding='utf-8') as f:
             self.centos_7_7_df_json = json.loads(f.read())
@@ -59,6 +62,9 @@ class MyTests(unittest.TestCase):
         with open(os.path.join(THIS_DIR, os.pardir, 'tests/fixtures/osx-10.14.6/df-h.json'), 'r', encoding='utf-8') as f:
             self.osx_10_14_6_df_h_json = json.loads(f.read())
 
+        with open(os.path.join(THIS_DIR, os.pardir, 'tests/fixtures/generic/df-long-filesystem.json'), 'r', encoding='utf-8') as f:
+            self.generic_df_long_filesystem_json = json.loads(f.read())
+
     def test_df_nodata(self):
         """
         Test plain 'df' with no data
@@ -113,6 +119,12 @@ class MyTests(unittest.TestCase):
         """
         self.assertEqual(jc.parsers.df.parse(self.osx_10_14_6_df_h, quiet=True), self.osx_10_14_6_df_h_json)
 
+    def test_df_long_filesystem(self):
+        """
+        Test older version of 'df' with long filesystem data
+        """
+        self.assertEqual(jc.parsers.df.parse(self.generic_df_long_filesystem, quiet=True), self.generic_df_long_filesystem_json)
+
 
 if __name__ == '__main__':
     unittest.main()