dissect.target 3.19.dev17__tar.gz → 3.19.dev18__tar.gz

{dissect_target-3.19.dev17/dissect.target.egg-info → dissect_target-3.19.dev18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dissect.target
-Version: 3.19.dev17
+Version: 3.19.dev18
 Summary: This module ties all other Dissect modules together, it provides a programming API and command line tools which allow easy access to various data sources inside disk images or file collections (a.k.a. targets)
 Author-email: Dissect Team <dissect@fox-it.com>
 License: Affero General Public License v3

{dissect_target-3.19.dev17 → dissect_target-3.19.dev18}/dissect/target/helpers/configutil.py

@@ -240,6 +240,33 @@ class Default(ConfigurationParser):
         self.parsed_data = information_dict
 
 
+class CSVish(Default):
+    """Parses CSV-ish config files (does not confirm to CSV standard!)"""
+
+    def __init__(self, *args, fields: tuple[str], **kwargs) -> None:
+        self.fields = fields
+        self.num_fields = len(self.fields)
+        self.maxsplit = self.num_fields - 1
+        super().__init__(*args, **kwargs)
+
+    def parse_file(self, fh: TextIO) -> None:
+        information_dict = {}
+
+        for i, raw_line in enumerate(self.line_reader(fh, strip_comments=True)):
+            line = raw_line.strip()
+            columns = re.split(self.SEPARATOR, line, maxsplit=self.maxsplit)
+
+            if len(columns) < self.num_fields:
+                # keep unparsed lines separate (often env vars)
+                data = {"line": line}
+            else:
+                data = dict(zip(self.fields, columns))
+
+            information_dict[str(i)] = data
+
+        self.parsed_data = information_dict
+
+
 class Ini(ConfigurationParser):
     """Parses an ini file according using the built-in python ConfigParser"""
 
@@ -688,11 +715,12 @@ class ParserConfig:
     collapse_inverse: Optional[bool] = None
     separator: Optional[tuple[str]] = None
     comment_prefixes: Optional[tuple[str]] = None
+    fields: Optional[tuple[str]] = None
 
     def create_parser(self, options: Optional[ParserOptions] = None) -> ConfigurationParser:
         kwargs = {}
 
-        for field_name in ["collapse", "collapse_inverse", "separator", "comment_prefixes"]:
+        for field_name in ["collapse", "collapse_inverse", "separator", "comment_prefixes", "fields"]:
             value = getattr(options, field_name, None) or getattr(self, field_name)
             if value:
                 kwargs.update({field_name: value})
@@ -721,6 +749,7 @@ CONFIG_MAP: dict[tuple[str, ...], ParserConfig] = {
     "toml": ParserConfig(Toml),
 }
 
+
 KNOWN_FILES: dict[str, type[ConfigurationParser]] = {
     "ulogd.conf": ParserConfig(Ini),
     "sshd_config": ParserConfig(Indentation, separator=(r"\s",)),
@@ -730,6 +759,41 @@ KNOWN_FILES: dict[str, type[ConfigurationParser]] = {
     "nsswitch.conf": ParserConfig(Default, separator=(":",)),
     "lsb-release": ParserConfig(Default),
     "catalog": ParserConfig(Xml),
+    "fstab": ParserConfig(
+        CSVish,
+        separator=(r"\s",),
+        comment_prefixes=("#",),
+        fields=("device", "mount", "type", "options", "dump", "pass"),
+    ),
+    "crontab": ParserConfig(
+        CSVish,
+        separator=(r"\s",),
+        comment_prefixes=("#",),
+        fields=("minute", "hour", "day", "month", "weekday", "user", "command"),
+    ),
+    "shadow": ParserConfig(
+        CSVish,
+        separator=(r"\:",),
+        comment_prefixes=("#",),
+        fields=(
+            "username",
+            "password",
+            "lastchange",
+            "minpassage",
+            "maxpassage",
+            "warning",
+            "inactive",
+            "expire",
+            "rest",
+        ),
+    ),
+    "passwd": ParserConfig(
+        CSVish,
+        separator=(r"\:",),
+        comment_prefixes=("#",),
+        fields=("username", "password", "uid", "gid", "gecos", "homedir", "shell"),
+    ),
+    "mime.types": ParserConfig(CSVish, separator=(r"\s+",), comment_prefixes=("#",), fields=("name", "extensions")),
 }
 
 

{dissect_target-3.19.dev17 → dissect_target-3.19.dev18/dissect.target.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dissect.target
-Version: 3.19.dev17
+Version: 3.19.dev18
 Summary: This module ties all other Dissect modules together, it provides a programming API and command line tools which allow easy access to various data sources inside disk images or file collections (a.k.a. targets)
 Author-email: Dissect Team <dissect@fox-it.com>
 License: Affero General Public License v3

{dissect_target-3.19.dev17 → dissect_target-3.19.dev18}/tests/helpers/test_configutil.py

@@ -10,6 +10,7 @@ import pytest
 from dissect.target.exceptions import FileNotFoundError
 from dissect.target.helpers.configutil import (
     ConfigurationParser,
+    CSVish,
     Default,
     Indentation,
     Json,
@@ -268,6 +269,25 @@ def test_json_syntax(data_string: str, expected_data: Union[dict, list]) -> None
     assert parser.parsed_data == expected_data
 
 
+@pytest.mark.parametrize(
+    "fields, separator, comment, data_string, expected_data",
+    [
+        (["a", "b"], (r"\s+",), ("#",), "1 2", {"0": {"a": "1", "b": "2"}}),  # SSV
+        (["a", "b"], (r"\s+",), ("#",), "1 2\n3 4", {"0": {"a": "1", "b": "2"}, "1": {"a": "3", "b": "4"}}),  # SSV-2
+        (["a", "b"], (r"\s+",), ("#",), "1\t2", {"0": {"a": "1", "b": "2"}}),  # TSV
+        (["a", "b"], (r",",), ("#",), "1,2", {"0": {"a": "1", "b": "2"}}),  # CSV
+        (["a", "b"], (r"\|",), ("#",), "1|2", {"0": {"a": "1", "b": "2"}}),  # DSV
+        (["a", "b"], (r"\|",), ("#",), "#9|9\n1|2", {"0": {"a": "1", "b": "2"}}),  # comments
+        (["a", "b"], (r"\s+",), ("#",), "#9 9\n1 2 3", {"0": {"a": "1", "b": "2 3"}}),  # trailing column
+        (["a", "b"], (r"\s+",), ("#",), "x", {"0": {"line": "x"}}),  # unparsed
+    ],
+)
+def test_csv_syntax(fields, separator, comment, data_string: str, expected_data: dict) -> None:
+    parser = CSVish(fields=fields, separator=separator, comment_prefixes=comment)
+    parser.parse_file(StringIO(data_string))
+    assert parser.parsed_data == expected_data
+
+
 def test_parse(target_linux: Target, fs_linux: VirtualFilesystem, tmp_path: Path) -> None:
     # File does not exist on the system in the first place
     with pytest.raises(FileNotFoundError):