# thptqg2017 data/ — 63 .xls files from baotintuc.vn (current generation).
#
# sheet_mode = "all": Hà Nội and HCM overflow into Sheet2 (65k Excel row cap).
# SBD validation: no numeric guard — build-database.js did not apply ^\d+$.
# strip_blank_rows = false: no blank-row anomaly in this dataset.
#
# Table shape, INSERT and subject regexes are canonical — see parser/internal/schema/schema.go.

reader:
  sheet_mode: all
  strip_blank_rows: false

columns:
  ho_ten: 0
  ngay_sinh: 1
  so_bao_danh: 2
  diem_thi: 3

validation:
  require_numeric_sbd: false
  require_nonempty_name: true
  require_nonempty_sbd: true

header:
  tokens: ["HO_TEN", "HỌ TÊN", "STT"]