#!/usr/bin/env python3
"""Build the embedded English-phonetic dataset.

Petal's writer is a native Mandarin speaker learning English, so the useful
pronunciation aid is *how to say the English word* — shown in the word popover
beside the 🔊 read-aloud button. (Pinyin would annotate Chinese she already
reads fluently, so it isn't built.) The phonetic spelling comes from the same
ECDICT source as the Chinese gloss, which already carries a `phonetic` column.

Two modes:

  # Full build from ECDICT (same CSV used by build_gloss.py):
  curl -sL https://raw.githubusercontent.com/skywind3000/ECDICT/master/ecdict.csv -o ecdict.csv
  python3 scripts/build_phonetic.py ecdict.csv internal/lexicon/data/phonetic.json.gz

  # Write just the built-in common-word seed (no CSV needed — what ships in-repo
  # so the feature works out of the box until a full build is run):
  python3 scripts/build_phonetic.py --seed internal/lexicon/data/phonetic.json.gz
"""
import csv
import gzip
import json
import re
import sys

# Same frequency gate as the gloss build, so coverage matches the words an ESL
# writer actually meets and the asset stays small.
MAX_RANK = 50000

# Single English word (letters with internal apostrophe/hyphen).
WORD_RE = re.compile(r"^[a-z][a-z'\-]*[a-z]$|^[a-z]$")

# A small, hand-checked seed of common words → IPA. This ships in the repo so the
# phonetic line is live immediately; a full ECDICT build overwrites it with broad
# coverage. Kept deliberately short and correct rather than large and shaky.
SEED = {
    "hello": "həˈloʊ", "world": "wɜːrld", "people": "ˈpiːpl", "water": "ˈwɔːtər",
    "river": "ˈrɪvər", "house": "haʊs", "school": "skuːl", "friend": "frɛnd",
    "family": "ˈfæməli", "mother": "ˈmʌðər", "father": "ˈfɑːðər", "woman": "ˈwʊmən",
    "language": "ˈlæŋɡwɪdʒ", "english": "ˈɪŋɡlɪʃ", "write": "raɪt", "writing": "ˈraɪtɪŋ",
    "read": "riːd", "word": "wɜːrd", "sentence": "ˈsɛntəns", "beautiful": "ˈbjuːtɪfl",
    "happy": "ˈhæpi", "love": "lʌv", "thought": "θɔːt", "through": "θruː",
    "though": "ðoʊ", "enough": "ɪˈnʌf", "question": "ˈkwɛstʃən", "answer": "ˈænsər",
    "because": "bɪˈkɔːz", "people's": "ˈpiːplz", "important": "ɪmˈpɔːrtnt",
    "different": "ˈdɪfərənt", "remember": "rɪˈmɛmbər", "together": "təˈɡɛðər",
    "morning": "ˈmɔːrnɪŋ", "tonight": "təˈnaɪt", "yesterday": "ˈjɛstərdeɪ",
    "tomorrow": "təˈmɒroʊ", "weather": "ˈwɛðər", "color": "ˈkʌlər", "colour": "ˈkʌlər",
    "favourite": "ˈfeɪvərɪt", "favorite": "ˈfeɪvərɪt", "comfortable": "ˈkʌmftəbl",
    "vegetable": "ˈvɛdʒtəbl", "interesting": "ˈɪntrəstɪŋ", "necessary": "ˈnɛsəsɛri",
    "february": "ˈfɛbruɛri", "wednesday": "ˈwɛnzdeɪ",
    "island": "ˈaɪlənd", "knife": "naɪf", "know": "noʊ", "knee": "niː",
    "hour": "ˈaʊər", "honest": "ˈɒnɪst", "listen": "ˈlɪsn", "castle": "ˈkæsl",
    "thank": "θæŋk", "think": "θɪŋk", "thing": "θɪŋ", "three": "θriː",
    "voice": "vɔɪs", "choice": "tʃɔɪs", "nature": "ˈneɪtʃər", "picture": "ˈpɪktʃər",
    "future": "ˈfjuːtʃər", "culture": "ˈkʌltʃər", "measure": "ˈmɛʒər",
    "usually": "ˈjuːʒuəli", "decision": "dɪˈsɪʒn", "delicious": "dɪˈlɪʃəs",
}


def clean_phonetic(p: str) -> str:
    """Normalize an ECDICT phonetic field: trim, strip wrapping slashes/brackets."""
    p = p.strip().strip("/[]").strip()
    return p


def build_from_csv(src: str) -> dict:
    out = {}
    with open(src, newline="", encoding="utf-8") as fh:
        for row in csv.DictReader(fh):
            word = (row.get("word") or "").strip().lower()
            phon = clean_phonetic(row.get("phonetic") or "")
            if not word or not phon or not WORD_RE.match(word):
                continue
            try:
                rank = int(row.get("frq") or 0) or int(row.get("bnc") or 0)
            except ValueError:
                rank = 0
            if rank <= 0 or rank > MAX_RANK:
                continue
            out[word] = phon
    # Make sure the curated seed is always present (and authoritative).
    out.update(SEED)
    return out


def main() -> None:
    args = sys.argv[1:]
    if not args:
        sys.exit(__doc__)
    if args[0] == "--seed":
        data, dest = dict(SEED), args[1]
    else:
        src, dest = args[0], args[1]
        data = build_from_csv(src)
    with gzip.open(dest, "wt", encoding="utf-8") as fh:
        json.dump(data, fh, ensure_ascii=False, separators=(",", ":"))
    print(f"wrote {len(data)} phonetic entries to {dest}")


if __name__ == "__main__":
    main()