From 2c1b91fc68e730892f5d4798442d49c1ff2cbfbd Mon Sep 17 00:00:00 2001
From: Driven-Element <129630760+Driven-Element@users.noreply.github.com>
Date: Wed, 20 Aug 2025 22:46:55 -0400
Subject: [PATCH] first draft of pathfunctions

---
 AirlockTools.py                               |  10 +++++
 utils/__pycache__/allowlist.cpython-313.pyc   | Bin 2728 -> 2688 bytes
 .../getdeviceevents.cpython-313.pyc           | Bin 3125 -> 3085 bytes
 .../__pycache__/hashfunctions.cpython-313.pyc | Bin 4753 -> 4708 bytes
 .../__pycache__/pathfunctions.cpython-313.pyc | Bin 0 -> 2436 bytes
 utils/hashfunctions.py                        |  40 ------------------
 utils/pathfunctions.py                        |  39 +++++++++++++++++
 7 files changed, 49 insertions(+), 40 deletions(-)
 create mode 100644 utils/__pycache__/pathfunctions.cpython-313.pyc
 create mode 100644 utils/pathfunctions.py

diff --git a/AirlockTools.py b/AirlockTools.py
index 4bb59a5..db86f5f 100644
--- a/AirlockTools.py
+++ b/AirlockTools.py
@@ -3,6 +3,7 @@ import os
 import utils.getdeviceevents
 import utils.allowlist
 import utils.hashfunctions
+import utils.pathfunctions
 import urllib3
 import pandas as pd
 
@@ -46,6 +47,15 @@ def menu():
 			categorized[0].to_html("needsreview.html", index=False)
 			categorized[1].to_html("approved.html", index=False)
 			categorized[2].to_html("remaining.html", index=False)
+		if choice == '4':
+			html_file = "augmentedlist.html"
+			augmented_df = pd.read_html(html_file)
+			print(augmented_df)
+
+			combined_df = pd.concat(augmented_df, ignore_index=True)
+			test = utils.pathfunctions.filepathInitalGroup(combined_df)
+			test.to_html("testgroup2.html", index=False)
+			
 
 
 if __name__ == "__main__":
diff --git a/utils/__pycache__/allowlist.cpython-313.pyc b/utils/__pycache__/allowlist.cpython-313.pyc
index b9c9af85d3e20277cb6e778e52cbbb050543995e..52a66d4d13e912aee3af23d6c43067ac125577e7 100644
GIT binary patch
delta 73
zcmZ1>+91mHnU|M~0SJzzZsa<_YT%S?6%$&VT2vg9k{aWZpIn-onpaXB<Cs~Llb@U&
PlAoW0%Gs>NR>uMWdVU$8

delta 113
zcmZn=T_MW#nU|M~0SK}UH*%d|jmS#2iU}=FEh>&F&rHtF$;?Ylit*1&bt%d$OI6TS
z2oDSORZvs#2zHKf$xklLP0cGQjtMBr&q_@OG8{9Da`Kb2L-O-;;G7Z=N7ryO6I&e%
E06nB8!~g&Q

diff --git a/utils/__pycache__/getdeviceevents.cpython-313.pyc b/utils/__pycache__/getdeviceevents.cpython-313.pyc
index 6613a363b1b63ffab7b2c78c13d534acd02b3ebd..f6c0a32f7567c44095a812451a1b301c350c37b9 100644
GIT binary patch
delta 56
zcmdlg(JR6InU|M~0SJzzF5Ad`nnT1R*(xTqIJKxaCM7k-B|o_|H#Kjv0H-)>NPd1!
K@n$_vc4h$dOA&Pd

delta 114
zcmeB`*eb#OnU|M~0SMAxE#1g{nj@kh*(xTqIJKxaraUt_J0~+QH7UkFFV&?evn*9X
zS0Ows)K@`G!6Vo?#w9<wG&eP`q&Oy^C_gJT8OU(VEXv7G&JM}X&w+DFKpb7e&1{_P
F%mCT3C))r3

diff --git a/utils/__pycache__/hashfunctions.cpython-313.pyc b/utils/__pycache__/hashfunctions.cpython-313.pyc
index 0bcb08cfbe43b1edb11d34af07df5713d80eca2d..1f2c5c29d48a0b023936b924dc385f3291e3145e 100644
GIT binary patch
delta 76
zcmbQJ`b35AGcPX}0}$-aUY7BMXCt2(vxr-=RZM7cYEf}aN@|QtesXDUYTo2JW^vY#
e{QR8a&2yN$`50p+YY0VgePs}1G$|4UY6k$aW*061

delta 138
zcmaE&GEtT9GcPX}0}ynWFUu$p+{kCf9Fdo76%$&VT2vfUo|&ATlbM&A6yu+l>Qa<h
zma3qu5FQrltDvUf5$qh}lAm0fo0?Zr91~EKpOu;nWH@FP<>V)4hvetyz&Rx#j;`V6
d66S6`#>7cNQT$&R#28IJ7^yOH6bS+?2LOxvEnxrv

diff --git a/utils/__pycache__/pathfunctions.cpython-313.pyc b/utils/__pycache__/pathfunctions.cpython-313.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..c645a8650a7bbe1691d061c3d1cfc960e5c1e3d4
GIT binary patch
literal 2436
zcmd5-O>7fK6rTNaY$r}q;&{OY>OvqfarqI!6oeugsA(D!T5sG&ikoC(Z_JkUt~<LH
z39W=VHK>&U2}F8oPgQavkt)$+4?WOc@XA6)lUAzKUV2LvAyqx~&DzGqj_9=`?aZ5>
z_ulv3d~bHs=kp?H4?h3)a$G>@cRHyxzA9{vfp8B=NMc41W}K15ti&dnxT|)!K1$s7
z>jS*R2hqno<}*xK_>(G(5jH(XTv)O4SWhu^8wju<4!%tni_jD|#ZL)<0DO<2Eboj=
zR)CQmVc+GlTnHtQ#8IWV`vogiG2Ys|Ch;e#{-|az97v$JZ<}+RBuK7Ptp0Kj9nG32
zs!MhIRfMlJpH1)yVStrdAV2OGaJehE{!`D>py#c|)79)r;*Ky<>nVoD6ZbdoccFJ)
zM@VN9jO0Fj6`?fbe-!dJ!8qC72D{W2L^aG44D~#^AE8zRcft)Yl8<83S@0${dz0K!
zyVP-tjqhsSORzPo6l)I(caC8IgTf3EQkP{_C*C<#Q*=42OwSW0G7cMUYDPD(GOg-q
zWqu2xD4A$FHZ|x5*?VZ5jf2$K_JOOK+rH|i{3=4@Oq}{|XtZP+TV1~g2-|~J*fD~_
z91(QG(q+QuWa~0%NvoIwU*QNdPguhwY%Xn5jG;n-#8Rh|2~)vlGOZ-f8>xI&(JeFi
zmWnkab!FTzw1!FEQelZ&p3CbgOEq-!aBhLP&uDUXHZ2d512j`~e^^&7S-XIZeD3fW
zuqJEfAPALXlny41`tJgI6n{MN^F;B34<AqdG`Wf&UR}HT@cP>IA3iCa94?-mDNfBm
zze$599tcKBSq5JCe`Flfau0KuRx@s=2;H-?=@12X!nBrWOykAfv<pB-1@jPeP0`Oj
z%&cX~(U={LLHyC-V$_L0I)f>tiMvKaAYe<%(DGT`+>#0UkUHFpf^ZK_K7Z&EX!1F$
zPE@7mtb;kFeF7b!EMmsOEb*$Qs+*Rqrxe0#s%eE8Oe@l)7DEm3?4cV$=nCk&)8ETK
z`pd^-_VL)VTs(Z~(fg0i!QkNE0+kZlfog#;$h-&^3WgH2q1EYLD;u4u2RK>#hoE>%
zgCa~5OiiaY_8`0$Ho`m(!9aX-*vL++mV)J34MI+<DGSmKi&vBd6N<_ORiY{;;pa5j
z!t`fUx!h2}Ne1zyjO?tcE7LStCOP!dGT3sK`Zpuc0ULhl=(_!O+23pXdzW1$|B+J1
z(MA4`j;_1s?~mRY{idhn?=5xo72SPKK4U-ww`^A4ps)|`03*bell8Q05)Tc=q803*
zC7fwtBA7W%wMdIHpVN%A0&@$iIU>lpoVEZ_V<U%mQ!6bQTDY?dgp)IwunW`sARJH*
z(`VPQ=(xl53Qd}hP$+cv?Ab~(y0(cP)4vqGbQ1xG{wbh!-nY(+zw)nbxX{kvQp6T}
z%VNJR_Ls$Dws>rHe@ToMh6<nAydO?@+inGK25(<nwibg$&p=^ld##dqysjheTH0*~
z4weHEI}myD#!M+7!{(<qE<NoQm)h*^1Lf|1ySx8MWTw<jcdp$St9TM`ic68Dy^CVe
z)8}~V+;QvLm)91#r>*U``=7M#c^cSxCv!i0Cu{dyDh1wK9QxwIUjph3KJ#)yc*9#m
zJF<L$qCHyn4A`E5)sIS^bA_SbT789K=l;S1rmujL!^-7(&dZh@!|+}^=~_X~xk^&q
zXR<~*uPKB0O;DnBXdZ-agJT$G9d)fE&xUIs)4nwH^~J9)ZXghs;}4Q6$!An_?EDMI
CA?_*w

literal 0
HcmV?d00001

diff --git a/utils/hashfunctions.py b/utils/hashfunctions.py
index 65a7150..7ab2d8d 100644
--- a/utils/hashfunctions.py
+++ b/utils/hashfunctions.py
@@ -91,43 +91,3 @@ def categorizeHashes(aug_df: pd.DataFrame, threat_tolerance: int, untrusted_publ
    remaining_df = df[~(mask_needsreview | mask_approved)]
 
    return needsreview_df, approved_df, remaining_df
-
- 
-"""
-def categorizeHashes(aug_df: pd.DataFrame, threat_tolerance: int, untrusted_publishers: list):
-    
-    Categorize hashes into needsreview, approved, and remaining based on publisher and threat level.
-    
-    
-    if untrusted_publishers is None:
-        untrusted_publishers = []
-
-    # Flatten threatlevel from nested reputation dict
-    df = aug_df.copy()  
-
-    # Masks for each category
-    mask_needsreview = ((df["publisher_y"] == "Not Signed") & reputationtool(df)) 
-
-    print(mask_needsreview)
-
-    mask_approved = (df["publisher_y"] != "Not Signed") & (~df["publisher_y"].isin(untrusted_publishers))
-
-    print(mask_approved)
-
-    # Create DataFrames for each category
-    needsreview_df = df[mask_needsreview]
-    approved_df = df[mask_approved]
-    remaining_df = df[~(mask_needsreview | mask_approved)]
-
-    return needsreview_df, approved_df, remaining_df
-
-def approvehashes(approved_df: pd.DataFrame):
-    pass
-
-def reputationtool(df):
-    if df["reputation_scannermatch"] == "N/A":
-        return True
-    if df["reputation_scannermatch"].astype(int) > 3:
-        return True
-    return False
-    """
\ No newline at end of file
diff --git a/utils/pathfunctions.py b/utils/pathfunctions.py
new file mode 100644
index 0000000..ec618e5
--- /dev/null
+++ b/utils/pathfunctions.py
@@ -0,0 +1,39 @@
+import pandas as pd
+import os
+
+
+def filepathInitalGroup(df: pd.DataFrame) -> pd.DataFrame:
+    import os
+    import pandas as pd
+    from itertools import chain
+
+    # 1. Split comma-separated filenames into lists
+    df["filename_x"] = df["filename_x"].str.split(",")
+
+    # 2. Explode so each filename has its own row
+    df = df.explode("filename_x", ignore_index=True)
+
+    # 3. Strip whitespace from filenames
+    df["filename_x"] = df["filename_x"].str.strip()
+
+    # 4. Split into directory and filename
+    df["directory"] = df["filename_x"].apply(lambda x: os.path.dirname(x) if pd.notna(x) else "")
+    df["filename"] = df["filename_x"].apply(lambda x: os.path.basename(x) if pd.notna(x) else "")
+
+    # 5. Drop the original column
+    df = df.drop(columns=["filename_x"])
+
+    # 6. Ensure all columns are lists (except directory, which is the key)
+    for col in df.columns:
+        if col != "directory":
+            df[col] = df[col].apply(lambda x: x if isinstance(x, list) else [x])
+
+    # 7. Combine rows with the same directory, flatten lists, deduplicate
+    def combine_lists(series):
+        flat = list(chain.from_iterable(series))
+        # deduplicate while preserving order
+        return list(dict.fromkeys(flat))
+
+    df = df.groupby("directory", as_index=False).agg(combine_lists)
+
+    return df