Merge pull request #132 from inab/131-errors-in-downloading-from-skul…

…lsecurityorg-during-installation 131 errors in downloading from skullsecurityorg during installation
inab · Dec 3, 2024 · 2fd054a · 2fd054a
2 parents 812c060 + 25778aa
commit 2fd054a
Show file tree

Hide file tree

Showing 4 changed files with 44 additions and 28 deletions.
diff --git a/CITATION.cff b/CITATION.cff
@@ -28,5 +28,5 @@ repository-code: "https://github.com/inab/WfExS-backend"
 repository-artifact: "https://github.com/inab/WfExS-backend/pkgs/container/wfexs-backend"
 type: software
 title: "WfExS-backend"
-version: 1.0.0rc1
-date-released: "2024-10-16"
+version: 1.0.0rc2
+date-released: "2024-12-03"
diff --git a/WfExS-config-replicator.py b/WfExS-config-replicator.py
@@ -110,13 +110,13 @@ def loadXLSXParams(paramsFilename: "str") -> "Sequence[Mapping[str, Any]]":
         # by latest openpyxl annotations
         sheet = cast("Worksheet", sheet_raw)  # type: ignore[redundant-cast]
         gotHeader = False
-        headerMap: "MutableMapping[int,str]" = {}
+        headerMap: "MutableMapping[Optional[int],str]" = {}
         for cells_in_row in sheet.iter_rows():
             # Either get the header or the data
             if gotHeader:
                 params: "MutableMapping[str, MutableSequence[Any]]" = dict()
                 for cell in cells_in_row:
-                    headerName = headerMap.get(cell.col_idx)
+                    headerName = headerMap.get(cell.column)
                     if headerName is not None:
                         theVal = cell.value
                         params.setdefault(headerName, []).append(theVal)
@@ -129,7 +129,7 @@ def loadXLSXParams(paramsFilename: "str") -> "Sequence[Mapping[str, Any]]":
                         if len(headerName) > 0:
                             gotHeader = True
                             # The column index is 1-based
-                            headerMap[cell.col_idx] = headerName
+                            headerMap[cell.column] = headerName
 
     return paramsArray
 

diff --git a/wfexs_backend/__init__.py b/wfexs_backend/__init__.py
@@ -21,7 +21,7 @@
 __license__ = "Apache 2.0"
 
 # https://www.python.org/dev/peps/pep-0396/
-__version__ = "1.0.0rc1"
+__version__ = "1.0.0rc2"
 __url__ = "https://github.com/inab/WfExS-backend"
 __official_name__ = "WfExS-backend"
 

diff --git a/wfexs_backend/utils/passphrase_wrapper.py b/wfexs_backend/utils/passphrase_wrapper.py
@@ -17,6 +17,8 @@
 # limitations under the License.
 from __future__ import absolute_import
 
+import inspect
+import logging
 import os
 import pathlib
 import random
@@ -77,9 +79,11 @@ class WfExSPassphraseGenerator:
             )
         ],
         "cain": [
+            # Originally
             # https://wiki.skullsecurity.org/index.php/Passwords
+            # and http://downloads.skullsecurity.org/passwords/cain.txt.bz2
             RemoteWordlistResource(
-                "http://downloads.skullsecurity.org/passwords/cain.txt.bz2"
+                "https://github.com/duyet/bruteforce-database/raw/233b5e59a87b96ec696ddcb33b8a37709ca6aa8a/cain.txt"
             ),
         ],
         "adjectives": [
@@ -115,6 +119,12 @@ def __init__(
         cacheDir: "Optional[pathlib.Path]" = None,
         word_sets: "Mapping[str, Sequence[RemoteWordlistResource]]" = DEFAULT_WORD_SETS,
     ):
+        self.logger = logging.getLogger(
+            dict(inspect.getmembers(self))["__module__"]
+            + "::"
+            + self.__class__.__name__
+        )
+
         # The cache is an integral part, as it is where the
         # different components are going to be fetched
         self.cacheHandler = cacheHandler
@@ -167,31 +177,37 @@ def _materialize_word_sets(
                     pass
 
                 if indexed_filename is None:
-                    # Time to fetch the wordlist
-                    i_cached_content = self.cacheHandler.fetch(
-                        cast("URIType", word_set_uri),
-                        destdir=self.cacheDir,
-                        offline=False,
-                    )
-
-                    # Prepare the compressed index
-                    with tempfile.NamedTemporaryFile() as tmp_indexed_filename:
-                        CompressedIndexedText.IndexTextFile(
-                            i_cached_content.path.as_posix(),
-                            tmp_indexed_filename.name,
-                            substart=remote_wordlist.substart,
-                            subend=remote_wordlist.subend,
-                        )
-                        # And inject it in the cache
-                        indexed_filename, _ = self.cacheHandler.inject(
-                            wordlist_internal_uri,
+                    try:
+                        # Time to fetch the wordlist
+                        i_cached_content = self.cacheHandler.fetch(
+                            cast("URIType", word_set_uri),
                             destdir=self.cacheDir,
-                            tempCachedFilename=pathlib.Path(tmp_indexed_filename.name),
+                            offline=False,
                         )
 
-                assert indexed_filename is not None
+                        # Prepare the compressed index
+                        with tempfile.NamedTemporaryFile() as tmp_indexed_filename:
+                            CompressedIndexedText.IndexTextFile(
+                                i_cached_content.path.as_posix(),
+                                tmp_indexed_filename.name,
+                                substart=remote_wordlist.substart,
+                                subend=remote_wordlist.subend,
+                            )
+                            # And inject it in the cache
+                            indexed_filename, _ = self.cacheHandler.inject(
+                                wordlist_internal_uri,
+                                destdir=self.cacheDir,
+                                tempCachedFilename=pathlib.Path(
+                                    tmp_indexed_filename.name
+                                ),
+                            )
+                    except Exception as e:
+                        self.logger.error(
+                            f"Unable to index {word_set_uri} (exception {e.__class__.__name__}). It might impact passphrase generation. Skipping"
+                        )
 
-                indexed_filenames.append(indexed_filename)
+                if indexed_filename is not None:
+                    indexed_filenames.append(indexed_filename)
 
             word_sets[wordlist_tag] = CompressedIndexedText(
                 cfiles=list(map(lambda infil: infil.as_posix(), indexed_filenames))