Integration with Infinity (#2894)

### What problem does this PR solve?

Integration with Infinity

- Replaced ELASTICSEARCH with dataStoreConn
- Renamed deleteByQuery with delete
- Renamed bulk to upsertBulk
- getHighlight, getAggregation
- Fix KGSearch.search
- Moved Dealer.sql_retrieval to es_conn.py


### Type of change

- [x] Refactoring

rag/app/presentation.py

@@ -20,6 +20,7 @@ from rag.nlp import tokenize, is_english
 from rag.nlp import rag_tokenizer
 from deepdoc.parser import PdfParser, PptParser, PlainParser
 from PyPDF2 import PdfReader as pdf2_read
+import json
 
 
 class Ppt(PptParser):
@@ -107,9 +108,9 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
             d = copy.deepcopy(doc)
             pn += from_page
             d["image"] = img
-            d["page_num_int"] = [pn + 1]
-            d["top_int"] = [0]
-            d["position_int"] = [(pn + 1, 0, img.size[0], 0, img.size[1])]
+            d["page_num_list"] = json.dumps([pn + 1])
+            d["top_list"] = json.dumps([0])
+            d["position_list"] = json.dumps([(pn + 1, 0, img.size[0], 0, img.size[1])])
             tokenize(d, txt, eng)
             res.append(d)
         return res
@@ -123,10 +124,10 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
             pn += from_page
             if img:
                 d["image"] = img
-            d["page_num_int"] = [pn + 1]
-            d["top_int"] = [0]
-            d["position_int"] = [
-                (pn + 1, 0, img.size[0] if img else 0, 0, img.size[1] if img else 0)]
+            d["page_num_list"] = json.dumps([pn + 1])
+            d["top_list"] = json.dumps([0])
+            d["position_list"] = json.dumps([
+                (pn + 1, 0, img.size[0] if img else 0, 0, img.size[1] if img else 0)])
             tokenize(d, txt, eng)
             res.append(d)
         return res

rag/app/table.py

@@ -74,7 +74,7 @@ class Excel(ExcelParser):
 def trans_datatime(s):
     try:
         return datetime_parse(s.strip()).strftime("%Y-%m-%d %H:%M:%S")
-    except Exception as e:
+    except Exception:
         pass
 
 
@@ -112,7 +112,7 @@ def column_data_type(arr):
             continue
         try:
             arr[i] = trans[ty](str(arr[i]))
-        except Exception as e:
+        except Exception:
             arr[i] = None
     # if ty == "text":
     #    if len(arr) > 128 and uni / len(arr) < 0.1:
@@ -182,7 +182,7 @@ def chunk(filename, binary=None, from_page=0, to_page=10000000000,
         "datetime": "_dt",
         "bool": "_kwd"}
     for df in dfs:
-        for n in ["id", "_id", "index", "idx"]:
+        for n in ["id", "index", "idx"]:
             if n in df.columns:
                 del df[n]
         clmns = df.columns.values