aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAlexander_Kabui2024-05-16 14:05:02 +0300
committerAlexander_Kabui2024-05-16 14:05:02 +0300
commit92ab53e9f0b10ebf7423626e37b3fe73eb8c0b65 (patch)
tree59c1f638d6de48a59aca933c94ccaf894e3b0ee7
parent167706bb417627b1d9fcacb7cdcebeafe886c1ba (diff)
downloadgenenetwork3-92ab53e9f0b10ebf7423626e37b3fe73eb8c0b65.tar.gz
Refactor code for llm:response
-rw-r--r--gn3/llms/response.py60
1 files changed, 28 insertions, 32 deletions
diff --git a/gn3/llms/response.py b/gn3/llms/response.py
index 7fce75b..2f00312 100644
--- a/gn3/llms/response.py
+++ b/gn3/llms/response.py
@@ -1,46 +1,42 @@
-
-# pylint: skip-file
+""" Module contains code for parsing references doc_ids """
+# pylint: disable=C0301
import json
import os
-
basedir = os.path.abspath(os.path.dirname(__file__))
class DocIDs():
+ """ Class Method to Parse document id and names"""
def __init__(self):
- # open doc ids for GN refs
- self.doc_ids = self.loadFile("doc_ids.json")
- # open doc ids for Diabetes references
- self.sugar_doc_ids = self.loadFile("all_files.json")
- # format is not what I prefer, it needs to be rebuilt
- self.formatDocIDs(self.sugar_doc_ids)
-
- def loadFile(self, file_name):
+ """
+ init method for Docids
+ * doc_ids.json: opens doc)ids for gn references
+ * sugar_doc_ids: open doci_ids for diabetes references
+ """
+ self.doc_ids = self.load_file("doc_ids.json")
+ self.sugar_doc_ids = self.load_file("all_files.json")
+ self.format_doc_ids(self.sugar_doc_ids)
+
+ def load_file(self, file_name):
+ """Method to load and read doc_id files"""
file_path = os.path.join(basedir, file_name)
if os.path.isfile(file_path):
- f = open(file_path, "rb")
- result = json.load(f)
- f.close()
- return result
+ with open(file_path, "rb") as file_handler:
+ return json.load(file_handler)
else:
- raise Exception("\n{0} -- File does not exist\n".format(file_path))
-
- def formatDocIDs(self, values):
- for _key, _val in values.items():
- if isinstance(_val, list):
- for theObject in _val:
- docName = self.formatDocumentName(theObject['filename'])
- docID = theObject['id']
- self.doc_ids.update({docID: docName})
-
- def formatDocumentName(self, val):
- result = val.removesuffix('.pdf')
- result = result.removesuffix('.txt')
- result = result.replace('_', ' ')
- return result
-
- def getInfo(self, doc_id):
+ raise FileNotFoundError(f"{file_path}-- FIle does not exist\n")
+
+ def format_doc_ids(self, docs):
+ """method to format doc_ids for list items"""
+ for _key, val in docs.items():
+ if isinstance(val, list):
+ for doc_obj in val:
+ doc_name = doc_obj["filename"].removesuffix(".pdf").removesuffix(".txt").replace("_", "")
+ self.doc_ids.update({doc_obj["id"]: doc_name})
+
+ def get_info(self, doc_id):
+ """ interface to make read from doc_ids"""
if doc_id in self.doc_ids.keys():
return self.doc_ids[doc_id]
else: