Add docs about dataset layout.

4 files changed, 73 insertions, 5 deletions

diff --git a/src/sec_certs/dataset/cc.py b/src/sec_certs/dataset/cc.py
index 1bf25994..b6f4caa5 100644
--- a/src/sec_certs/dataset/cc.py
+++ b/src/sec_certs/dataset/cc.py
@@ -44,8 +44,46 @@ from sec_certs.utils.profiling import staged
 
 class CCDataset(Dataset[CCCertificate], ComplexSerializableType):
     """
-    Class that holds CCCertificate. Serializable into json, pandas, dictionary. Conveys basic certificate manipulations
+    Class that holds :class:`sec_certs.sample.cc.CCCertificate` samples.
+
+    Serializable into json, pandas, dictionary. Conveys basic certificate manipulations
     and dataset transformations. Many private methods that perform internal operations, feel free to exploit them.
+
+    The dataset directory looks like this:
+
+        ├── auxiliary_datasets
+        │   ├── cpe_dataset.json
+        │   ├── cve_dataset.json
+        │   ├── cpe_match.json
+        │   ├── cc_scheme.json
+        │   ├── protection_profiles
+        │   │   ├── reports
+        │   │   │   ├── pdf
+        │   │   │   └── txt
+        │   │   ├── pps
+        │   │   │   ├── pdf
+        │   │   │   └── txt
+        │   │   └── pp.json
+        │   └── maintenances
+        │       ├── certs
+        │       │   ├── reports
+        │       │   │   ├── pdf
+        │       │   │   └── txt
+        │       │   └── targets
+        │       │       ├── pdf
+        │       │       └── txt
+        │       └── maintenance_updates.json
+        ├── certs
+        │   ├── reports
+        │   │   ├── pdf
+        │   │   └── txt
+        │   ├── targets
+        │   │   ├── pdf
+        │   │   └── txt
+        │   └── certificates
+        │       ├── pdf
+        │       └── txt
+        └── dataset.json
     """
 
     FULL_ARCHIVE_URL: ClassVar[AnyHttpUrl] = config.cc_latest_full_archive
diff --git a/src/sec_certs/dataset/dataset.py b/src/sec_certs/dataset/dataset.py
index bd7fff51..7a9c92ed 100644
--- a/src/sec_certs/dataset/dataset.py
+++ b/src/sec_certs/dataset/dataset.py
@@ -253,6 +253,7 @@ class Dataset(Generic[CertSubType], ComplexSerializableType, ABC):
     def move_dataset(self, new_root_dir: str | Path) -> None:
         """
         Moves all dataset files to `new_root_dir` and adjusts all paths internally. Deletes the artifacts from the original location.
+
         :param str | Path new_root_dir: path to directory where the new dataset shall be stored.
         """
         new_root_dir = Path(new_root_dir)
@@ -267,6 +268,7 @@ class Dataset(Generic[CertSubType], ComplexSerializableType, ABC):
     def copy_dataset(self, new_root_dir: str | Path) -> None:
         """
         Copies all dataset files to `new_root_dir` and adjusts all paths internally. Keeps the artifacts from the original location.
+
         :param str | Path new_root_dir: path to directory where the new dataset shall be stored.
         """
         new_root_dir = Path(new_root_dir)
diff --git a/src/sec_certs/dataset/fips.py b/src/sec_certs/dataset/fips.py
index 4c6ee16f..34b1147d 100644
--- a/src/sec_certs/dataset/fips.py
+++ b/src/sec_certs/dataset/fips.py
@@ -36,7 +36,22 @@ logger = logging.getLogger(__name__)
 
 class FIPSDataset(Dataset[FIPSCertificate], ComplexSerializableType):
     """
-    Class for processing of FIPSCertificate samples. Inherits from `ComplexSerializableType` and base abstract `Dataset` class.
+    Class for processing of :class:`sec_certs.sample.fips.FIPSCertificate` samples.
+
+    Inherits from `ComplexSerializableType` and base abstract `Dataset` class.
+
+    The dataset directory looks like this:
+
+        ├── auxiliary_datasets
+        │   ├── cpe_dataset.json
+        │   ├── cve_dataset.json
+        │   ├── cpe_match.json
+        │   └── algorithms.json
+        ├── certs
+        │   └── targets
+        │       ├── pdf
+        │       └── txt
+        └── dataset.json
     """
 
     FULL_ARCHIVE_URL: ClassVar[AnyHttpUrl] = config.fips_latest_full_archive
diff --git a/src/sec_certs/dataset/protection_profile.py b/src/sec_certs/dataset/protection_profile.py
index 4d92ac00..2295191a 100644
--- a/src/sec_certs/dataset/protection_profile.py
+++ b/src/sec_certs/dataset/protection_profile.py
@@ -18,6 +18,22 @@ from sec_certs.utils.profiling import staged
 
 
 class ProtectionProfileDataset(Dataset[ProtectionProfile], ComplexSerializableType):
+    """
+    Class for processing :class:`sec_certs.sample.protection_profile.ProtectionProfile` samples.
+
+    Inherits from `ComplexSerializableType` and base abstract `Dataset` class.
+
+    The dataset directory looks like this:
+
+        ├── reports
+        │   ├── pdf
+        │   └── txt
+        ├── pps
+        │   ├── pdf
+        │   └── txt
+        └── pp.json
+    """
+
     FULL_ARCHIVE_URL: ClassVar[AnyHttpUrl] = config.pp_latest_full_archive
     SNAPSHOT_URL: ClassVar[AnyHttpUrl] = config.pp_latest_snapshot
 
@@ -38,9 +54,6 @@ class ProtectionProfileDataset(Dataset[ProtectionProfile], ComplexSerializableTy
         self.state = state if state else self.DatasetInternalState()
         self.aux_handlers = aux_handlers
         self.root_dir = Path(root_dir)
-        """
-        Class for processing ProtectionProfile samples. Inherits from `ComplexSerializableType` and base abstract `Dataset` class.
-        """
 
     @property
     def json_path(self) -> Path: