# -*- coding: utf-8 -*-
"""Doi chieu tu khoa nha cung cap / doi thu giua T39 va T40 (dem + ngu canh)."""
import re
from docx import Document

T39 = r"C:\Claw 2\Bao cao - Hanh chinh\Dac-Phai-VIen-KT\Bao-Cao-Tuan\T39\Bao_cao_tong_hop_Tuan39_21-09_27-09-2026.docx"
T40 = r"C:\Users\admin\AppData\Local\hermes\cache\documents\doc_825c2646f6b1_Bao_cao_tong_hop_Tuan40_28-09_04-10-2026.docx"

KW = ["AkzoNobel", "MTH", "Syncoat", "Tân Hồng Phát", "Poly Poxy", "Brochem", "Visan", "Xinpan",
      "nhà cung cấp", "NCC", "đối thủ", "cạnh tranh", "copy", "test màu"]

def body(p):
    d = Document(p)
    parts = [x.text for x in d.paragraphs]
    for t in d.tables:
        for r in t.rows:
            parts.append(" | ".join(c.text for c in r.cells))
    return "\n".join(parts)

b39, b40 = body(T39), body(T40)
print("%-18s %6s %6s" % ("TU KHOA", "T39", "T40"))
for k in KW:
    print("%-18s %6d %6d" % (k, len(re.findall(re.escape(k), b39, re.I)), len(re.findall(re.escape(k), b40, re.I))))

print("\n### NGU CANH cac muc CHI CO o T39 (khong thay o T40) ###")
for k in ["Syncoat", "Brochem", "Xinpan"]:
    n39 = len(re.findall(re.escape(k), b39, re.I))
    n40 = len(re.findall(re.escape(k), b40, re.I))
    print("\n== %s: T39=%d | T40=%d" % (k, n39, n40))
    for m in re.finditer(re.escape(k), b39, re.I):
        seg = b39[max(0, m.start()-150):m.start()+200].replace("\n", " ")
        print("   T39 ...", seg[:330])
    for m in re.finditer(re.escape(k), b40, re.I):
        seg = b40[max(0, m.start()-150):m.start()+200].replace("\n", " ")
        print("   T40 ...", seg[:330])

print("\n### T40: MOI xuat hien 'nhà cung cấp' / Visan ###")
for m in re.finditer(r"nhà cung cấp|Visan", b40, re.I):
    print("   ...", b40[max(0, m.start()-200):m.start()+240].replace("\n", " ")[:420])