#!/bin/bash
# Downloads the beginner-level word books. The repo is CC BY-NC-SA 4.0 and its
# own README calls the contents "compiled from public sources, personal use
# only" -- see the note in DATA-NOTE.md before shipping any of this.
set -u
BASE="https://github.com/lilinji/English/raw/main"
enc() { python3 -c "import urllib.parse,sys;print(urllib.parse.quote(sys.argv[1]))" "$1"; }
get() {
  local path="$1" out="src/$2"
  [ -s "$out" ] && { echo "  已有 $2"; return; }
  curl -sL -o "$out" "$BASE/$(enc "$path")"
  if [ -s "$out" ] && head -c2 "$out" | grep -q PK; then echo "  取得 $2 ($(wc -c <"$out") 字节)"
  else echo "  失败 $2"; rm -f "$out"; fi
}
echo "剑桥 KET/PET:"
get "9.其他（更多）/14天攻克KET核心词汇.xlsx"      ket-core.xlsx
get "9.其他（更多）/KET核心词 巧记速练.xlsx"        ket-drill.xlsx
get "9.其他（更多）/21天攻克PET核心词汇.xlsx"       pet-core.xlsx
get "9.其他（更多）/PET核心词 巧记速练.xlsx"        pet-drill.xlsx
get "9.其他（更多）/突破英文基础词汇.xlsx"          basic.xlsx
echo "人教版小学:"
for g in 一 二 三 四 五 六; do
  for t in 上 下; do
    get "1.全国各大教材版本中小学同步/人教版/人教版一年级起点${g}年级${t}.xlsx" "rj-p1-${g}${t}.xlsx"
  done
done
echo "人教版初中(七年级):"
get "1.全国各大教材版本中小学同步/人教版/人教版初中英语七年级上册.xlsx" rj-m7a.xlsx
get "1.全国各大教材版本中小学同步/人教版/人教版初中英语七年级下册.xlsx" rj-m7b.xlsx

# Word frequency, for the order new words are handed out in. These are
# OpenSubtitles counts, i.e. spoken language: a web corpus ranks `ankle` and
# `asleep` far below where a learner of spoken English needs them.
# hermitdave/FrequencyWords is MIT, a cleaner licence than the word books above.
echo "词频表:"
if [ -s src/en_50k.txt ]; then
  echo "  已有 en_50k.txt"
else
  curl -sL -o src/en_50k.txt \
    "https://raw.githubusercontent.com/hermitdave/FrequencyWords/master/content/2018/en/en_50k.txt"
  echo "  取得 en_50k.txt ($(wc -l <src/en_50k.txt) 行)"
fi