Add a way to download full dataset archive (including PDFs) from the web.

4 files changed, 72 insertions, 3 deletions

diff --git a/README.md b/README.md
index 258725c2..41529529 100644
--- a/README.md
+++ b/README.md
@@ -68,8 +68,8 @@ df_2015_and_newer = df.loc[df.year_from > 2014]
 df.year_from.value_counts().sort_index().plot.line()
 ```
 
-<!-- ## Authors
+## Authors
 
 This work is being done at [CRoCS MUNI](https://crocs.fi.muni.cz/) by Adam Janovsky, Jan Jancar, Petr Svenda, Jiri Michalik, Lukasz Chmielewski and other contributors. This work was supported by the Internal grant agency of Masaryk University, CZ.02.2.69/0.0/0.0/19_073/0016943.
 
-![](docs/_static/logolink_OP_VVV_hor_barva_eng.jpg) -->
+![](docs/_static/logolink_OP_VVV_hor_barva_eng.jpg)
diff --git a/src/sec_certs/configuration.py b/src/sec_certs/configuration.py
index 47ac5821..7667a8ec 100644
--- a/src/sec_certs/configuration.py
+++ b/src/sec_certs/configuration.py
@@ -46,6 +46,10 @@ class Configuration(BaseSettings):
         "https://sec-certs.org/cc/dataset.json",
         description="URL from where to fetch the latest snapshot of fully processed CC dataset.",
     )
+    cc_latest_full_archive: AnyHttpUrl = Field(
+        "https://sec-certs.org/cc/cc.tar.gz",
+        description="URL from where to fetch the latest full archive of fully processed CC dataset.",
+    )
     cc_maintenances_latest_snapshot: AnyHttpUrl = Field(
         "https://sec-certs.org/cc/maintenance_updates.json",
         description="URL from where to fetch the latest snapshot of CC maintenance updates",
@@ -57,6 +61,10 @@ class Configuration(BaseSettings):
     fips_latest_snapshot: AnyHttpUrl = Field(
         "https://sec-certs.org/fips/dataset.json", description="URL for the latest snapshot of FIPS dataset."
     )
+    fips_latest_full_archive: AnyHttpUrl = Field(
+        "https://sec-certs.org/fips/fips.tar.gz",
+        description="URL from where to fetch the latest full archive of fully processed FIPS dataset.",
+    )
     fips_iut_dataset: AnyHttpUrl = Field(
         "https://sec-certs.org/fips/iut/dataset.json", description="URL for the dataset of FIPS IUT data."
     )
diff --git a/src/sec_certs/dataset/cc.py b/src/sec_certs/dataset/cc.py
index ebffd912..ec125542 100644
--- a/src/sec_certs/dataset/cc.py
+++ b/src/sec_certs/dataset/cc.py
@@ -3,6 +3,7 @@ from __future__ import annotations
 import itertools
 import locale
 import shutil
+import tarfile
 import tempfile
 from collections.abc import Iterator
 from dataclasses import dataclass
@@ -253,6 +254,34 @@ class CCDataset(Dataset[CCCertificate, CCAuxiliaryDatasets], ComplexSerializable
         """
         return cls.from_web(config.cc_latest_snapshot, "Downloading CC Dataset", "cc_latest_dataset.json")
 
+    @classmethod
+    def from_web_latest_full(cls, path: str | Path) -> CCDataset:
+        """
+        Fetches the full (and fresh) archive of the CCDataset from sec-certs.org, including the PDFs and auxiliary datasets.
+
+        Note that this is quite large (several gigabytes).
+        """
+        if not path:
+            raise ValueError("Path needs to be defined.")
+        path = Path(path)
+        if not path.exists():
+            path.mkdir(parents=True)
+        if not path.is_dir():
+            raise ValueError("Path needs to be a directory.")
+        with tempfile.TemporaryDirectory() as tmp_dir:
+            dset_path = Path(tmp_dir) / "cc.tar.gz"
+            res = helpers.download_file(
+                config.cc_latest_full_archive,
+                dset_path,
+                show_progress_bar=True,
+                progress_bar_desc="Downloading CC archive",
+            )
+            if res != constants.RESPONSE_OK:
+                raise ValueError("Download failed.")
+            with tarfile.open(dset_path, "r:gz") as tar:
+                tar.extractall(path)
+            return cls.from_json(path / "dataset.json")
+
     def _set_local_paths(self):
         super()._set_local_paths()
 
@@ -262,6 +291,9 @@ class CCDataset(Dataset[CCCertificate, CCAuxiliaryDatasets], ComplexSerializable
         if self.auxiliary_datasets.mu_dset:
             self.auxiliary_datasets.mu_dset.root_dir = self.mu_dataset_dir
 
+        if self.auxiliary_datasets.scheme_dset:
+            self.auxiliary_datasets.scheme_dset.json_path = self.scheme_dataset_path
+
         for cert in self:
             cert.set_local_paths(
                 self.reports_pdf_dir,
@@ -271,7 +303,6 @@ class CCDataset(Dataset[CCCertificate, CCAuxiliaryDatasets], ComplexSerializable
                 self.targets_txt_dir,
                 self.certificates_txt_dir,
             )
-        # TODO: This forgets to set local paths for other auxiliary datasets
 
     def _merge_certs(self, certs: dict[str, CCCertificate], cert_source: str | None = None) -> None:
         """
diff --git a/src/sec_certs/dataset/fips.py b/src/sec_certs/dataset/fips.py
index 77f38754..d279f407 100644
--- a/src/sec_certs/dataset/fips.py
+++ b/src/sec_certs/dataset/fips.py
@@ -4,6 +4,8 @@ import datetime
 import itertools
 import logging
 import shutil
+import tarfile
+import tempfile
 from pathlib import Path
 from typing import Final
 
@@ -221,6 +223,34 @@ class FIPSDataset(Dataset[FIPSCertificate, FIPSAuxiliaryDatasets], ComplexSerial
         """
         return cls.from_web(config.fips_latest_snapshot, "Downloading FIPS Dataset", "fips_latest_dataset.json")
 
+    @classmethod
+    def from_web_latest_full(cls, path: str | Path) -> FIPSDataset:
+        """
+        Fetches the full (and fresh) archive of the FIPSDataset from sec-certs.org, including the PDFs and auxiliary datasets.
+
+        Note that this is quite large (several gigabytes).
+        """
+        if not path:
+            raise ValueError("Path needs to be defined.")
+        path = Path(path)
+        if not path.exists():
+            path.mkdir(parents=True)
+        if not path.is_dir():
+            raise ValueError("Path needs to be a directory.")
+        with tempfile.TemporaryDirectory() as tmp_dir:
+            dset_path = Path(tmp_dir) / "fips.tar.gz"
+            res = helpers.download_file(
+                config.fips_latest_full_archive,
+                dset_path,
+                show_progress_bar=True,
+                progress_bar_desc="Downloading FIPS archive",
+            )
+            if res != constants.RESPONSE_OK:
+                raise ValueError("Download failed.")
+            with tarfile.open(dset_path, "r:gz") as tar:
+                tar.extractall(path)
+            return cls.from_json(path / "dataset.json")
+
     def _set_local_paths(self) -> None:
         super()._set_local_paths()
         if self.auxiliary_datasets.algorithm_dset: