make lsattr more robust

CHANGELOG

@@ -1,12 +1,14 @@
 jc changelog
 
-20260330 v1.25.7
+20260417 v1.25.7
 - Add `typeset` and `declare` Bash internal command parser to convert variables
   simple arrays, and associative arrays along with object metadata
 - Enhance `pip-show` command parser to add `-f` show files support
 - Enhance `rsync` and `rsync-s` parsers to add `--stats` or `--info=stats[1-3]` fields
 - Fix `hashsum` command parser to correctly parse the `mode` indicator
 - Fix `dir` command parser for incorrect stripping of the `D:` drive letter
+- Fix `lsattr` command parser for filenames with spaces (newlines in filenames are
+  still not supported)
 - Fix `proc-pid-smaps` proc parser when unknown VmFlags are output
 - Fix `ifconfig` command parser for incorrect stripping of leading zeros in some hex numbers
 - Fix `iptables` command parser when Target is blank and verbose output is used

jc/parsers/lsattr.py

@@ -1,5 +1,7 @@
 r"""jc - JSON Convert `lsattr` command output parser
 
+> Note: filenames with newlines are not supported.
+
 Usage (cli):
 
     $ lsattr | jc --lsattr
@@ -57,6 +59,7 @@ Examples:
         }
       ]
 """
+import re
 from typing import List, Dict
 from jc.jc_types import JSONDictType
 import jc.utils
@@ -64,7 +67,7 @@ import jc.utils
 
 class info():
     """Provides parser metadata (version, author, etc.)"""
-    version = '1.0'
+    version = '1.1'
     description = '`lsattr` command parser'
     author = 'Mark Rotner'
     author_email = 'rotner.mr@gmail.com'
@@ -76,7 +79,7 @@ class info():
 __version__ = info.version
 
 
-ERROR_PREFIX = "lsattr:"
+LINE_RE = re.compile(r'(?P<attributes>[BZXsuSDiadAcEjItTeCFNPV-]{20}) (?P<filename>.*)')
 
 # https://github.com/mirror/busybox/blob/2d4a3d9e6c1493a9520b907e07a41aca90cdfd94/e2fsprogs/e2fs_lib.c#L40
 # https://github.com/landley/toybox/blob/f1682dc79fd75f64042b5438918fe5a507977e1c/toys/other/lsattr.c#L97
@@ -107,6 +110,28 @@ ATTRIBUTES = {
 }
 
 
+def _process(proc_data: List[JSONDictType]) -> List[JSONDictType]:
+    """
+    Final processing to conform to the schema.
+
+    Parameters:
+
+        proc_data:   (List of Dictionaries) raw structured data to process
+
+    Returns:
+
+        List of Dictionaries. Structured to conform to the schema.
+    """
+    for item in proc_data:
+        if 'attributes' in item:
+            for attribute in item['attributes']:
+                attribute_key = ATTRIBUTES.get(attribute)
+                if attribute_key:
+                    item[attribute_key] = True
+            del item['attributes']
+    return proc_data
+
+
 def parse(
     data: str,
     raw: bool = False,
@@ -135,32 +160,18 @@ def parse(
         return output
 
     for line in cleandata:
-        # -R flag returns the output in the format:
-        # Folder:
-        #   attributes file_in_folder
-        if line.endswith(':'):
-            continue
-
-        # lsattr: Operation not supported ....
-        if line.startswith(ERROR_PREFIX):
-            continue
-
-        line_output: Dict = {}
-
-        # attributes file
         # --------------e----- /etc/passwd
-        # Use maxsplit=1 to handle filenames with spaces (e.g. "./ok ok ok ok ok")
-        parts = line.split(maxsplit=1)
-        if len(parts) != 2:
-            continue
-        attributes, file = parts
-        line_output['file'] = file
-        for attribute in list(attributes):
-            attribute_key = ATTRIBUTES.get(attribute)
-            if attribute_key:
-                line_output[attribute_key] = True
+        line_split = re.match(LINE_RE, line)
 
-        if line_output:
-            output.append(line_output)
+        if line_split:
+            attributes = line_split['attributes']
+            file = line_split['filename']
 
-    return output
+            line_output: Dict = {}
+            line_output['file'] = file
+            line_output['attributes'] = attributes
+
+            if line_output:
+                output.append(line_output)
+
+    return output if raw else _process(output)