=
197 lines
7.7 KiB
Python
197 lines
7.7 KiB
Python
# Copyright (C) 2025 James Brotosky, Brandon Wickline
|
|
#
|
|
# This program is free software: you can redistribute it and/or modify
|
|
# it under the terms of the GNU Affero General Public License as published
|
|
# by the Free Software Foundation, either version 3 of the License, or
|
|
# (at your option) any later version.
|
|
#
|
|
# This program is distributed in the hope that it will be useful,
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
# GNU Affero General Public License for more details.
|
|
#
|
|
# You should have received a copy of the GNU Affero General Public License
|
|
# along with this program. If not, see <https://www.gnu.org/licenses/>.
|
|
|
|
#Local Imports
|
|
import utils.pathfunctions as pathf
|
|
import utils.pretty as ct
|
|
from AirlockTools import tryToReadCSV
|
|
|
|
#Standard Libary Imports:
|
|
import ast
|
|
import gc
|
|
import os
|
|
import re
|
|
|
|
#3rd Party Imports:
|
|
import pandas as pd
|
|
|
|
def split_filepaths_grouped(df, col="filename", group_parts=4, min_parts=4):
|
|
def clean_split(path):
|
|
parts = os.path.normpath(path).split(os.sep)
|
|
# Remove leading empty strings caused by UNC paths
|
|
parts = [p for p in parts if p]
|
|
return parts
|
|
|
|
df = df.copy()
|
|
split_paths = df[col].apply(clean_split)
|
|
|
|
# Filter out paths with fewer than `min_parts` components
|
|
df = df[split_paths.apply(lambda parts: len(parts) >= min_parts)].copy()
|
|
split_paths = split_paths[df.index] # Update split_paths to match filtered df
|
|
|
|
df["group_key"] = split_paths.apply(lambda parts: os.sep.join(parts[:group_parts]))
|
|
grouped = df.groupby("group_key")
|
|
new_rows = []
|
|
|
|
for _, group_df in grouped:
|
|
paths = group_df[col].tolist()
|
|
split_parts = [clean_split(p) for p in paths]
|
|
|
|
def longest_common_prefix(paths):
|
|
if not paths:
|
|
return []
|
|
prefix = paths[0]
|
|
for path in paths[1:]:
|
|
prefix = [a for a, b in zip(prefix, path) if a == b]
|
|
if not prefix:
|
|
break
|
|
return prefix
|
|
|
|
common_prefix = longest_common_prefix(split_parts)
|
|
prefix_str = os.sep.join(common_prefix)
|
|
|
|
for i, parts in enumerate(split_parts):
|
|
filename = parts[-1]
|
|
middle = os.sep.join(parts[len(common_prefix):-1]) if len(parts) > len(common_prefix) + 1 else ""
|
|
row = group_df.iloc[i].copy()
|
|
row["longestcfp"] = prefix_str
|
|
row["middle"] = middle
|
|
row["filename_only"] = filename
|
|
row["file_extension"] = os.path.splitext(filename)[1].tolower()
|
|
new_rows.append(row)
|
|
|
|
return pd.DataFrame(new_rows).drop(columns=["group_key"])
|
|
|
|
def mask_from_csv(df, csv_path, filepath_col):
|
|
"""
|
|
Reads reviewed CSV of groups, keeps only files in approved groups.
|
|
"""
|
|
review_df = pd.read_csv(csv_path)
|
|
|
|
def parse_paths(val):
|
|
if isinstance(val, str):
|
|
try:
|
|
# Try to parse as a list
|
|
parsed = ast.literal_eval(val)
|
|
# If it's not a list, wrap it
|
|
return parsed if isinstance(parsed, list) else [parsed]
|
|
except (ValueError, SyntaxError):
|
|
# If parsing fails, treat it as a single path
|
|
return [val]
|
|
return [val]
|
|
|
|
review_df[filepath_col] = review_df[filepath_col].apply(parse_paths)
|
|
|
|
# Flatten all approved file paths into a set for masking
|
|
approved_files = set()
|
|
for paths in review_df[filepath_col]:
|
|
approved_files.update(paths)
|
|
|
|
# Keep only rows in df that are in approved_files
|
|
masked_df = df[df[filepath_col].isin(approved_files)].copy()
|
|
remainder = df[~df[filepath_col].isin(approved_files)].copy()
|
|
return remainder
|
|
|
|
def filter_and_drop(approved, eligiblepaths, min_hashes):
|
|
"""
|
|
Filters eligiblepaths to rows where all hashes are in approved,
|
|
then drops rows with fewer than min_hashes hashes.
|
|
"""
|
|
approved_hashes = set(approved['sha256'])
|
|
|
|
def all_hashes_approved(row):
|
|
return all(h in approved_hashes for h in row['sha256'])
|
|
|
|
filtered = eligiblepaths[eligiblepaths.apply(all_hashes_approved, axis=1)]
|
|
filtered = filtered[filtered['sha256'].apply(len) >= min_hashes]
|
|
|
|
return filtered
|
|
|
|
def inspect_parquet(path):
|
|
try:
|
|
df = pd.read_parquet(path)
|
|
print(f"✅ Successfully read: {path}")
|
|
print(f"📄 Columns: {df.columns.tolist()}")
|
|
print(f"🔢 Rows: {len(df)}")
|
|
return df
|
|
except Exception as e:
|
|
print(f"❌ Error reading {path}: {e}")
|
|
return pd.DataFrame()
|
|
|
|
|
|
def regulator(paths, case_insensitive=True):
|
|
"""
|
|
Build a regex pattern that matches any of the given Windows path fragments.
|
|
"""
|
|
escaped = [re.escape(p) for p in paths]
|
|
pattern = "(?:" + "|".join(escaped) + ")"
|
|
if case_insensitive:
|
|
pattern = "(?i)" + pattern # Add inline case-insensitive flag
|
|
print(f"Regulator is providing: {pattern}")
|
|
return pattern
|
|
|
|
def generatePathReview(first_policy, second_policy, badpathparts, min_files_for_path):
|
|
|
|
if not os.path.exists(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet"):
|
|
|
|
df1 = tryToReadCSV(f"approved\\hashes_rep_unknown_{first_policy}_{second_policy}.csv")
|
|
df2 = tryToReadCSV(f"approved\\hashes_rep_good_{first_policy}_{second_policy}.csv")
|
|
|
|
all_approved_hashes = pd.concat([df1 , df2], ignore_index=True).sort_values(by=['filename'])
|
|
|
|
|
|
|
|
print(ct.colorText(f"Approved hash lists have been combined","green"))
|
|
|
|
all_approved_hashes.to_parquet(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet", index=False)
|
|
del all_approved_hashes
|
|
gc.collect()
|
|
|
|
if not os.path.exists(f"parquet\\path_needs_approved_{first_policy}_{second_policy}.parquet"):
|
|
all_approved_hashes = pd.read_parquet(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet")
|
|
print(ct.colorText(f"Beginning calculating longest common filepaths for path exceptions","green"))
|
|
|
|
haslcp = pathf.split_filepaths_grouped(all_approved_hashes)
|
|
haslcp.drop_duplicates()
|
|
|
|
forbidden = pathf.regulator(badpathparts, True)
|
|
forbidden_lcfp = haslcp["longestcfp"].str.contains(forbidden, na=False)
|
|
|
|
|
|
print(ct.colorText("Removing forbidden filepaths for path exceptions", "green"))
|
|
|
|
# Make a real DataFrame copy before modifying
|
|
lcp_not_forbidden = haslcp[~forbidden_lcfp].copy()
|
|
|
|
#For the review, drop down to only the columns we care, and then group by the commmon file path, consolidating and dropping dupes
|
|
lcp_not_forbidden_review = lcp_not_forbidden[['longestcfp', 'middle', 'filename_only', 'file_extension', 'sha256']]
|
|
|
|
# Count unique sha256 per longestcfp
|
|
unique_sha_counts = lcp_not_forbidden_review.groupby('longestcfp')['sha256'].nunique().reset_index()
|
|
unique_sha_counts.columns = ['longestcfp', 'unique_sha256_count']
|
|
|
|
# Merge the count back into the original DataFrame
|
|
lcp_not_forbidden_review = lcp_not_forbidden_review.merge(unique_sha_counts, on='longestcfp', how='left')
|
|
lcp_not_forbidden_review = lcp_not_forbidden_review[lcp_not_forbidden_review['unique_sha256_count'] >= min_files_for_path]
|
|
|
|
lcp_not_forbidden_review.to_parquet(f"parquet\\path_needs_approved_{first_policy}_{second_policy}.parquet",index=False)
|
|
lcp_not_forbidden_review.to_csv(f"needs_approved\\path_needs_approved_{first_policy}_{second_policy}.csv",index=False)
|
|
ct.style_dataframe_dark(lcp_not_forbidden_review,f"needs_approved\\path_needs_approved_{first_policy}_{second_policy}.html", True)
|
|
|
|
del lcp_not_forbidden
|
|
del unique_sha_counts
|
|
del lcp_not_forbidden_review
|
|
|