# thptqg2016 data/ — 4 .xls + 115 .xlsx mixed files.
#
# Four column layouts exist across the 119 files; the binary selects the
# right one per-sheet at runtime via format_detection: thptqg2016:
#
#   separate-scores  header SBD(0)/HOTEN(1)/TOAN(2)...  — dhhanghai files
#   mapped           header SOBAODANH|SBD + DIEM_THI     — most provinces
#   subject-columns  header names >=3 subject columns    — dhcantho, dhcnthucpham
#   default          no header; positional 6-col layout  — remaining files
#
# This is the only dataset that populates ten_cum_thi and gioi_tinh, and the
# only one whose files carry Tiếng Đức / Tiếng Nhật scores.
#
# sheet_mode = "all": several provinces overflow into Sheet2 (65k Excel row cap).
# strip_blank_rows = false: no blank-row anomaly observed in this dataset.
#
# Table shape, INSERT and subject regexes are canonical — see parser/internal/schema/schema.go.

format_detection: thptqg2016

reader:
  sheet_mode: all
  strip_blank_rows: false

validation:
  require_numeric_sbd: false
  require_nonempty_name: true
  require_nonempty_sbd: true

header:
  # Tokens that identify a header row by first-cell content (uppercased).
  # Covers both SOBAODANH-style and SBD-style headers.
  tokens: ["SOBAODANH", "SBD", "HO_TEN", "HOTEN", "HỌ TÊN", "STT"]