词光 · Word Atlas — Illustrated IELTS vocabulary with 7,298 words, UK/US audio and FSRS review. Open-source app + CC BY 4.0 dataset.
TypeScript chinesedatasetenglish-learningflashcardsfsrsieltslanguage-learningpwareactspaced-repetitionvocabularywebgl
"""Generate original learner entries for every headword (CC BY 4.0 content).
Usage: python3 scripts/atlas/gen_text.py [--limit N] [--workers W] [--batch B]
Output: .local/forge/text/<batch>.json (resumable)
"""
import argparse
import concurrent.futures as cf
import json
import re
import sys
from common import FORGE, load_env, stream_chat, with_retry
TOPICS = [
"education", "work", "technology", "science", "environment", "health",
"society", "government", "economy", "media", "arts", "travel", "city",
"nature", "daily", "emotion", "thinking", "sport", "history",
]
SYSTEM = """You are the lead lexicographer of an open-source English vocabulary atlas for Chinese learners preparing for IELTS (band 5.5-7.5).
Write ORIGINAL content in your own words. The raw notes you receive are only a hint for which senses matter; never copy them.
Accuracy beats creativity: IPA, part of speech, Chinese meanings and grammar must be correct. Prefer standard British IPA for ipa_uk and General American for ipa_us, with slashes.
Return strict JSON only: {"entries":[...]} with one entry per input word, same order, using exactly this shape:
{
"w": headword exactly as given (fix only obvious typos, and then set "flag"),
"uk": "/IPA/", "us": "/IPA/",
"senses": [{"pos": "n.|v.|adj.|adv.|prep.|conj.|pron.|phr.|num.|int.|det.", "zh": "简洁中文释义,可用;分隔,≤14字", "en": "learner-friendly English definition, ≤12 words"}], // 1-3 senses, most IELTS-useful first
"ex": [
{"en": "Everyday sentence, 7-13 words, natural, vivid, uses the headword exactly or an inflected form", "zh": "自然的中文翻译"},
{"en": "IELTS-style sentence, 12-22 words, academic/discussion register on an IELTS topic", "zh": "自然的中文翻译"}
],
"col": ["2-4 high-value collocations, each as 'english phrase|中文'"],
"fam": ["0-4 word-family members as 'word (pos)'"],
"syn": ["0-3 synonyms"], "ant": ["0-2 antonyms"],
"tip": "≤36字中文:最有用的一条用法/辨析/记忆提示。不得编造词源;没有可靠词源就讲用法或易混词。",
"cefr": "A1|A2|B1|B2|C1|C2",
"topic": one of [TOPICS],
"scene": "Depicting the FIRST sense: one concrete, visually clear illustration idea (≤28 words, English) that makes the core meaning obvious at a glance: a single moment with people/objects/places. Abstract words become a clear metaphorical scene. Never mention text, letters, signs, labels or numbers.",
"flag": "" or short note if the headword is malformed, offensive, or not a real English word
}
Sentences must be safe for all ages, culturally neutral, and must not mention real brands or living public figures. Do not reuse the same names across entries; avoid 'Tom' and 'Mary'."""
def prompt_for(batch):
lines = []
for g in batch:
raw = " / ".join(g["raw"])[:160]
lines.append(f'- {g["word"]} (notes: {raw})')
return "Words:\n" + "\n".join(lines)
def run_batch(env, model, idx, batch, outdir):
out = outdir / f"{idx:04d}.json"
if out.exists():
return idx, "cached"
payload = {
"model": model,
"messages": [
{"role": "system", "content": SYSTEM.replace("[TOPICS]", json.dumps(TOPICS))},
{"role": "user", "content": prompt_for(batch)},
],
}
def call():
text = stream_chat(env, payload)
text = re.sub(r"^```(?:json)?|```$", "", text.strip()).strip()
data = json.loads(text)
entries = data["entries"]
if len(entries) != len(batch):
raise ValueError(f"expected {len(batch)} got {len(entries)}")
return entries
entries = with_retry(call, tries=4, base=5)
for g, e in zip(batch, entries):
e["hid"] = g["hid"]
e["src"] = g["word"]
out.write_text(json.dumps(entries, ensure_ascii=False))
return idx, "ok"
def main():
ap = argparse.ArgumentParser()
ap.add_argument("--limit", type=int, default=0)
ap.add_argument("--start", type=int, default=0)
ap.add_argument("--workers", type=int, default=8)
ap.add_argument("--batch", type=int, default=20)
ap.add_argument("--model", default="gpt-6")
ap.add_argument("--out", default="text")
a = ap.parse_args()
env = load_env()
hw = json.loads((FORGE / "headwords.json").read_text())
hw = hw[a.start:]
if a.limit:
hw = hw[: a.limit]
outdir = FORGE / a.out
outdir.mkdir(parents=True, exist_ok=True)
batches = [hw[i : i + a.batch] for i in range(0, len(hw), a.batch)]
base = a.start // a.batch
done = fail = 0
with cf.ThreadPoolExecutor(a.workers) as ex:
futs = {ex.submit(run_batch, env, a.model, base + i, b, outdir): base + i for i, b in enumerate(batches)}
for f in cf.as_completed(futs):
try:
f.result()
done += 1
except Exception as e:
fail += 1
print("FAIL", futs[f], str(e)[:200], flush=True)
if (done + fail) % 10 == 0:
print(f"progress {done+fail}/{len(batches)} fail={fail}", flush=True)
print(f"finished ok={done} fail={fail}", flush=True)
if __name__ == "__main__":
sys.exit(main())