You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
70 lines
2.2 KiB
70 lines
2.2 KiB
|
|
from Util.EmbeddingUtil import text_to_embedding # 修改导入
|
|
from Config.Config import ES_CONFIG
|
|
from elasticsearch import Elasticsearch
|
|
import re
|
|
from tqdm import tqdm
|
|
import datetime
|
|
import logging
|
|
|
|
# 在文件开头添加logger配置
|
|
logger = logging.getLogger(__name__)
|
|
logger.setLevel(logging.INFO)
|
|
|
|
# 创建控制台handler并设置格式
|
|
handler = logging.StreamHandler()
|
|
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
|
handler.setFormatter(formatter)
|
|
logger.addHandler(handler)
|
|
|
|
def split_sentences(text):
|
|
"""按句分割文本"""
|
|
paragraphs = [p.strip() for p in text.split('\n\n') if p.strip()]
|
|
# 使用jieba进行分句
|
|
sentences = re.split(r'[。！？；\n]', text) # 添加这行定义sentences
|
|
return [s.strip() for s in sentences if s.strip()]
|
|
|
|
def save_to_es(text):
|
|
"""保存向量化文本和原始文本到ES"""
|
|
vector = text_to_embedding(text)
|
|
|
|
if vector is None:
|
|
logger.warning(f"跳过无法生成向量的文本: {text}")
|
|
return
|
|
|
|
doc = {
|
|
'text': text,
|
|
'vector': vector,
|
|
'timestamp': datetime.datetime.now().isoformat(),
|
|
'analyzer': 'ik_smart'
|
|
}
|
|
|
|
try:
|
|
es.index(index='knowledge_base', body=doc)
|
|
es.index(index='raw_texts', body={'raw_text': text})
|
|
except Exception as e:
|
|
logger.error(f"保存文本到ES失败: {e}")
|
|
|
|
def process_file(file_path):
|
|
"""处理文本文件"""
|
|
with open(file_path, 'r', encoding='utf-8') as f:
|
|
content = f.read()
|
|
|
|
sentences = split_sentences(content)
|
|
|
|
# 添加进度条
|
|
for sentence in tqdm(sentences, desc='处理进度', unit='句'):
|
|
save_to_es(sentence)
|
|
|
|
print(f"\n处理完成，共保存{len(sentences)}个句子")
|
|
|
|
if __name__ == '__main__':
|
|
es = Elasticsearch(
|
|
hosts=[ES_CONFIG['hosts']],
|
|
basic_auth=ES_CONFIG['basic_auth'],
|
|
verify_certs=ES_CONFIG['verify_certs'],
|
|
ssl_show_warn=ES_CONFIG['ssl_show_warn']
|
|
)
|
|
|
|
file_path = 'Txt/人口变化趋势对云南教育的影响.txt'
|
|
process_file(file_path) |