197 lines
8.7 KiB
Python
197 lines
8.7 KiB
Python
# -*- coding: utf-8 -*-
|
||
from xml.sax.saxutils import escape
|
||
import re, os, zipfile
|
||
|
||
def norm(t):
|
||
return re.sub(r'[\u200c\u200f\u200e]', '', (t or '')).strip()
|
||
|
||
def cell_text(tc):
|
||
return ''.join(re.findall(r'<w:t[^>]*>([^<]*)</w:t>', tc))
|
||
|
||
def para(text):
|
||
ps = ''
|
||
for line in str(text).split('\n'):
|
||
line = line.strip() or ' '
|
||
ps += ('<w:p><w:pPr><w:bidi/><w:spacing w:after="120"/></w:pPr>'
|
||
'<w:r><w:rPr><w:rtl/></w:rPr>'
|
||
'<w:t xml:space="preserve">' + escape(line) + '</w:t></w:r></w:p>')
|
||
return ps
|
||
|
||
def rows_of(tbl):
|
||
return [(m.start(), m.end(), m.group(0)) for m in re.finditer(r'<w:tr[ >].*?</w:tr>', tbl, re.S)]
|
||
|
||
def cells_of(row):
|
||
return re.findall(r'<w:tc>.*?</w:tc>', row, re.S)
|
||
|
||
def insert_into_cell(tc, value):
|
||
pi = tc.find('<w:p')
|
||
if pi == -1:
|
||
return tc.replace('</w:tc>', para(value) + '</w:tc>')
|
||
return tc[:pi] + para(value) + tc[pi:]
|
||
|
||
def fill_by_label(tbl, label_norm, value, any_cell=False):
|
||
"""Insert value into the cell following the label cell (same row), else next row's first empty cell."""
|
||
rs = rows_of(tbl)
|
||
for idx, (s, e, row) in enumerate(rs):
|
||
cells = cells_of(row)
|
||
texts = [norm(cell_text(c)) for c in cells]
|
||
hit = None
|
||
if not any_cell and texts and texts[0] == label_norm and len(cells) >= 2:
|
||
hit = 1
|
||
elif any_cell:
|
||
for i, t in enumerate(texts):
|
||
if t == label_norm:
|
||
hit = i + 1 if i + 1 < len(cells) else i
|
||
break
|
||
if hit is not None:
|
||
new_row = row.replace(cells[hit], insert_into_cell(cells[hit], value), 1)
|
||
return tbl[:s] + new_row + tbl[e:], True
|
||
# value cell on the NEXT row
|
||
if any_cell and label_norm in texts and idx + 1 < len(rs):
|
||
s2, e2, row2 = rs[idx + 1]
|
||
c2 = cells_of(row2)
|
||
if c2:
|
||
t0 = norm(cell_text(c2[0]))
|
||
if t0 == '':
|
||
new_row2 = row2.replace(c2[0], insert_into_cell(c2[0], value), 1)
|
||
return tbl[:s2] + new_row2 + tbl[e2:], True
|
||
return tbl, False
|
||
|
||
def table_id(tbl):
|
||
for s, e, row in rows_of(tbl):
|
||
cells = cells_of(row)
|
||
texts = [norm(cell_text(c)) for c in cells]
|
||
for i, t in enumerate(texts):
|
||
if t.startswith('شناسه الزام') and i + 1 < len(cells):
|
||
return cell_text(cells[i + 1])
|
||
return None
|
||
|
||
def table_field(tbl, label_norm):
|
||
for s, e, row in rows_of(tbl):
|
||
cells = cells_of(row)
|
||
texts = [norm(cell_text(c)) for c in cells]
|
||
for i, t in enumerate(texts):
|
||
if t == label_norm and i + 1 < len(cells):
|
||
return cell_text(cells[i + 1])
|
||
return ''
|
||
|
||
def find_answer(id_text):
|
||
if id_text:
|
||
for ans in A:
|
||
if any(k in id_text for k in ans['keys']):
|
||
return ans
|
||
return None
|
||
|
||
BODIES = {
|
||
'بروز بودن اجزا': ['ابزارها و چارچوب'],
|
||
'سرآیندها': ['Strict Transport Security'],
|
||
'Cookie': ['پیکربندی صحیح Cookie'],
|
||
'Ports': ['درگاههایی'],
|
||
'متدهای ناامن': ['متدهای ناامن'],
|
||
'Anti-CSRF': ['Anti-CSRF'],
|
||
}
|
||
|
||
def find_answer_by_body(body):
|
||
b = norm(body)
|
||
for name, keys in BODIES.items():
|
||
if any(norm(k) in b for k in keys):
|
||
for ans in A:
|
||
if ans['keys'][0] == name:
|
||
return ans
|
||
return None
|
||
|
||
def find_by_name(name):
|
||
n = norm(name)
|
||
for ans in A:
|
||
if any(norm(k) in n for k in ans['keys']):
|
||
return ans
|
||
return None
|
||
|
||
# --- main ---
|
||
os.makedirs(OUT_DIR, exist_ok=True)
|
||
with zipfile.ZipFile(SRC) as z:
|
||
xml = z.read('word/document.xml').decode('utf-8')
|
||
|
||
tables = [(m.start(), m.end(), m.group(0)) for m in re.finditer(r'<w:tbl>.*?</w:tbl>', xml, re.S)]
|
||
report = {'req': 0, 'vuln': 0, 'res': False, 'unmatched': [], 'dupes': []}
|
||
matched = set()
|
||
order = []
|
||
|
||
for start, end, tbl in reversed(tables):
|
||
new_tbl, tid = tbl, table_id(tbl)
|
||
ans = find_answer(tid) if tid else None
|
||
if not tid:
|
||
joined = ' '.join(norm(cell_text(c)) for c in re.findall(r'<w:tc>.*?</w:tc>', tbl, re.S))
|
||
if 'نام متقاضی' in joined:
|
||
for lab, val in [('نام متقاضی', 'Raymand Communications Naqsh Jahan'), ('نام محصول', 'Raymand-CTI'), ('نسخه محصول', '2.0.3'), ('تاریخ تکمیل', '2026-09-16'), ('نسخهی سند', '1.0')]:
|
||
new_tbl, ch = fill_by_label(new_tbl, norm(lab), val, any_cell=True)
|
||
xml = xml[:start] + new_tbl + xml[end:]
|
||
continue
|
||
if 'تعداد هسته' in joined:
|
||
res = A[0]
|
||
for lab, val in [('نوع', 'GNU/Linux (Debian GNU/Linux 12 bookworm)'), ('نسخه', '12 (bookworm)'),
|
||
('تعداد هستهی پردازنده', '4'), ('میزان RAM', '8 GB'), ('حافظه', '100 GB')]:
|
||
new_tbl, ch = fill_by_label(new_tbl, norm(lab), val, any_cell=True)
|
||
report['res'] = report['res'] or ch
|
||
order.append((0, 'منابع مورد نیاز', 'منابع نصب و راهاندازی', res))
|
||
report['res'] = True
|
||
xml = xml[:start] + new_tbl + xml[end:]
|
||
continue
|
||
else:
|
||
joined_txt = ' '.join(norm(cell_text(c)) for c in re.findall(r'<w:tc>.*?</w:tc>', tbl, re.S))
|
||
body = table_field(tbl, norm('متن الزام')) + ' ' + table_field(tbl, norm('نام الزام')) + ' ' + joined_txt
|
||
ans = find_answer_by_body(body)
|
||
if ans is not None:
|
||
key = ans['keys'][0]
|
||
if key in matched: report['dupes'].append(key)
|
||
matched.add(key)
|
||
desc_full = 'وضعیت: ' + ans['status'] + '\n' + ans['desc']
|
||
for lab, val in [('نحوهی دسترسی', ans['access']), ('تصویر', ans['img']), ('توضیحات بیشتر', desc_full)]:
|
||
new_tbl, ch = fill_by_label(new_tbl, norm(lab), val)
|
||
if tid:
|
||
report['req'] += 1
|
||
order.append((len(order) + 1, tid.strip(), table_field(tbl, norm('نام الزام')), ans))
|
||
else:
|
||
report['vuln'] += 1
|
||
order.append((0, '', (find_by_name(key) and '') or key, ans))
|
||
xml = xml[:start] + new_tbl + xml[end:]
|
||
else:
|
||
report['unmatched'].append(((tid or '').strip() or '(no-id-table)')[:60] + ' :: ' + norm(cell_text(tbl))[:80])
|
||
|
||
with zipfile.ZipFile(SRC) as zin, zipfile.ZipFile(OUT, 'w', zipfile.ZIP_DEFLATED) as zout:
|
||
for item in zin.infolist():
|
||
data = zin.read(item.filename)
|
||
if item.filename == 'word/document.xml':
|
||
data = xml.encode('utf-8')
|
||
zout.writestr(item, data)
|
||
|
||
order = [(i + 1, tid, tname, ans) for i, (n, tid, tname, ans) in enumerate(order)]
|
||
md = ['# پاسخنامه سند خودارزیابی — Raymand-CTI نسخه ۲.۰.۳', '',
|
||
'> منبع پاسخها: تحلیل ایستای کد (`cti-app/` فرانت، `p-line/` بکاند) و سند عدمانطباق `docs/markdown/عدمانطباق-الزامات-امنیتی-CTI.md`.',
|
||
'> تاریخ تهیه: 2026-09-16 — نسخه سند خودارزیابی: 1.0', '',
|
||
'## راهنمای وضعیت', '',
|
||
'- **' + S_DONE + '** — شواهد کد موجود است؛ تصویر برای ارزیابی پیوست میشود.',
|
||
'- **' + S_PART + '** — پیادهسازی ناقص یا در دستور کار اصلاح (ارجاع NC).',
|
||
'- **' + S_NO + '** — طبق قواعد پرسشنامه گزینهای انتخاب نمیشود.',
|
||
'- **' + S_NA + '** — قابلیت جزو محصول نیست.', '',
|
||
'## جدول خلاصه', '', '| # | شناسه الزام | نام | وضعیت |', '|---|---|---|---|']
|
||
for i, tid, tname, ans in order:
|
||
md.append('| %d | %s | %s | %s |' % (i, (tid or '—').replace('|', '/'), (tname or '')[:70].replace('|', '/'), ans['status'] if ans else '—'))
|
||
md.append('')
|
||
md.append('## پاسخ تفصیلی')
|
||
for i, tid, tname, ans in order:
|
||
md.append('')
|
||
md.append('### %d — %s' % (i, tid.replace('\n', ' + ') if tid else tname))
|
||
if tname: md.append('**نام الزام:** ' + tname.strip().replace('\n', ' '))
|
||
md.append('**وضعیت:** ' + ans['status'])
|
||
md.append('**نحوهی دسترسی:** ' + ans['access'])
|
||
md.append('**توضیحات:** ' + ans['desc'])
|
||
md.append('**شواهد/تصویر:** ' + ans['img'])
|
||
|
||
open(MD, 'w', encoding='utf-8').write('\n'.join(md))
|
||
print('REQ_FILLED:', report['req'], '| VULN_FILLED:', report['vuln'], '| RESOURCES:', report['res'])
|
||
print('DUPES:', report['dupes'])
|
||
print('UNMATCHED:', report['unmatched'])
|
||
print('OUT:', OUT, os.path.getsize(OUT))
|
||
print('MD:', MD, os.path.getsize(MD))
|