Spaces:
Running
Running
File size: 2,871 Bytes
1e165e2 cf14f69 1e165e2 cf14f69 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 |
import sqlite3
import os
from vocab import get_word_info
from ai_sentence import generate_sentence
from tqdm import tqdm
DATA_DIR = "./data"
DB_PATH = os.path.join(DATA_DIR, "sentences.db")
def init_db():
conn = sqlite3.connect(DB_PATH)
c = conn.cursor()
c.execute('''
CREATE TABLE IF NOT EXISTS sentences (
word TEXT,
phonetic TEXT,
sentence TEXT,
source TEXT,
model TEXT,
created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
PRIMARY KEY (word, source, model)
)
''')
conn.commit()
conn.close()
def get_sentences_by_word(word):
conn = sqlite3.connect(DB_PATH)
c = conn.cursor()
c.execute('SELECT word, phonetic, sentence, source, model FROM sentences WHERE word=?', (word,))
results = c.fetchall()
conn.close()
return results
def save_sentence(word, phonetic, sentence, source, model):
conn = sqlite3.connect(DB_PATH)
c = conn.cursor()
c.execute('''
INSERT INTO sentences (word, phonetic, sentence, source, model)
VALUES (?, ?, ?, ?, ?)
ON CONFLICT(word, source, model) DO UPDATE SET sentence=excluded.sentence, phonetic=excluded.phonetic
''', (word, phonetic, sentence, source, model))
conn.commit()
conn.close()
def generate_sentences(words, source, use_ai, model_name):
result_display = ""
status_log = []
for word in tqdm(words, desc="處理單字"):
# 1. 查單字音標
word_info = get_word_info(source, word)
phonetic = word_info['phonetic'] if word_info else "無"
# 2. 查句庫
sentence_records = get_sentences_by_word(word)
# 3. 判斷是否用AI
if use_ai or not sentence_records:
try:
sentence = generate_sentence(word, model_name)
save_sentence(word, phonetic, sentence, 'ai', model_name)
source_used = 'ai'
model_used = model_name
except Exception as e:
sentence = f"[AI生成失敗：{e}]"
source_used = "error"
model_used = None
else:
# 取第一筆句庫資料
sentence = sentence_records[0][2]
source_used = sentence_records[0][3]
model_used = sentence_records[0][4]
# 4. 組裝顯示內容
result_display += f"""
<div style="margin-bottom: 10px; padding: 8px; border-left: 4px solid #4CAF50; background-color: #f9f9f9;">
<strong>單字：</strong> {word} <br>
<strong>音標：</strong> {phonetic} <br>
<strong>句子：</strong> {sentence} <br>
<strong>來源：</strong> {source_used} {f"({model_used})" if model_used else ""}
</div>
"""
status_log.append(f"✅ {word}：{source_used}")
return result_display, "\n".join(status_log)
|