Mike Swanson
5359e7c49e
Recovered Darv's VB6 source for the Valley Wide Plastering Orders application from the D: backup drive (label "Backup", 8 TB, 5.3 TB used). This is the first time we've had the actual source — prior session only had a single frmPayroll.frm from the AD server. Three project variants identified across two snapshots: - Full-Project/ (2,129 files, 124 MB) — D:\Office-Estimates\Darv\Full\Project\ - Kingston-Project/ (2,189 files, 130 MB) — D:\Office-Estimates\Darv\Kingston\Project\ - Source/ (170 files, 559 MB) — D:\Office-Estimates\Darv\Source\ wholesale - SOURCE-HOLD/ (3 files, 1 MB) — D:\Office-Estimates\Darv\SOURCE HOLD\ Latest ORDERS_C.vbp date is 2020-06-09 (Kingston snapshot). Production Orders_10A.exe was live as of April 2024 — open question whether newer source exists on other backup drives Mike will scan next. Also includes per-category and per-keyword analysis CSVs from a WizTree file-list export, plus the analyzer script that produced them (re-runnable for the next drive's CSV). VMs (VWIN7-DW.vdi 8.3 GB + XP-for-ORDERS_copy.vdi 2.8 GB), the live VWP.mdb, and the 393 MB raw WizTree CSV stay on disk only — gitignored. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
53 lines
2.0 KiB
Python
53 lines
2.0 KiB
Python
"""Size up candidate source folders we might want to copy off D:.
|
|
Match by exact-leaf-name; print all matches per leaf, sorted by size.
|
|
"""
|
|
import csv, sys, os
|
|
from collections import defaultdict
|
|
|
|
CSV = sys.argv[1] if len(sys.argv) > 1 else 'clients/valleywide/app-modernization/WizTree_20260516172207.csv'
|
|
|
|
# Match folders whose leaf name (the last path component) is in this set
|
|
LEAVES_OF_INTEREST = {
|
|
'project', 'source', 'source hold', 'virtualbox', 'vm_vdi',
|
|
'vwp_current', 'vwp_update', 'vwp_inv', 'vwp_current_0317',
|
|
'kingston', 'full', 'recovery', 'darv',
|
|
'virtual box', 'virtual box copy', 'xp box',
|
|
}
|
|
|
|
groups = defaultdict(list) # leaf -> [(size, files, folders, modified, path)]
|
|
|
|
with open(CSV, encoding='utf-8-sig', errors='replace') as f:
|
|
r = csv.reader(f)
|
|
next(r) # banner
|
|
next(r) # header
|
|
for row in r:
|
|
if not row or len(row) < 7:
|
|
continue
|
|
p = row[0]
|
|
if not p.endswith('\\'):
|
|
continue
|
|
leaf = p.rstrip('\\').rsplit('\\', 1)[-1].lower()
|
|
if leaf in LEAVES_OF_INTEREST:
|
|
try:
|
|
sz = int(row[1])
|
|
files = int(row[5]) if row[5].strip() else 0
|
|
folders = int(row[6]) if row[6].strip() else 0
|
|
except (ValueError, IndexError):
|
|
continue
|
|
groups[leaf].append((sz, files, folders, row[3], p))
|
|
|
|
print(f'{"GB":>8} {"Files":>8} {"Folders":>7} Modified Path')
|
|
print('-' * 140)
|
|
# Order: source code targets first, then VMs
|
|
order = ['vwp_current', 'vwp_update', 'vwp_inv', 'vwp_current_0317',
|
|
'project', 'source', 'source hold', 'kingston', 'full', 'recovery',
|
|
'virtualbox', 'vm_vdi', 'virtual box', 'virtual box copy', 'xp box',
|
|
'darv']
|
|
for leaf in order:
|
|
items = sorted(groups.get(leaf, []), reverse=True)
|
|
if not items:
|
|
continue
|
|
print(f'\n--- leaf "{leaf}" ({len(items)} match{"es" if len(items)!=1 else ""}) ---')
|
|
for sz, files, folders, mod, p in items[:10]:
|
|
print(f'{sz/1024/1024/1024:>8.2f} {files:>8} {folders:>7} {mod:<19} {p}')
|