Code review fixes

docs/DocGenerator/DocGenerator.py

@@ -23,6 +23,7 @@
 VERSION = "0.1"
 CONFIG_PATH = "config.yaml"
 
+
 class DocGenerator:
  """
  brief: Main class of DocGenerator tool.
@@ -53,7 +54,8 @@ def is_valid_folder(self, path):
 
  def is_valid_file(self, file):
  """
- brief: Checks if a file name should be ignored because it's in the ignore list or doesn´t match with the regexes.
+ brief: Checks if a file name should be ignored because it's in the ignore list
+ or doesn´t match with the regexes.
  args:
  - "file (str): File name to be controlled"
  returns: "boolean: False if the file should be ignored. True otherwise."
@@ -84,7 +86,7 @@ def get_group_doc_path(self, group):
  returns: "string: The name of the documentation group file"
  """
  base_path = os.path.join(self.conf.documentation_path, os.path.basename(self.scan_path))
- doc_path = os.path.join(base_path,group['name']+".group")
+ doc_path = os.path.join(base_path, group['name']+".group")
  return doc_path
 
  def get_test_doc_path(self, path):
@@ -154,8 +156,6 @@ def create_test(self, path, group_id):
  logging.warning(f"Content for {path} is empty, ignoring it")
  return None
 
-
-
  def parse_folder(self, path, group_id):
  """
  brief: Search in a specific folder to parse possible group files and each test file.
@@ -173,15 +173,15 @@ def parse_folder(self, path, group_id):
  (root, folders, files) = next(os.walk(path))
  for file in files:
  if self.is_group_file(file):
- new_group = self.create_group(os.path.join(root,file), group_id)
+ new_group = self.create_group(os.path.join(root, file), group_id)
  if new_group:
  group_id = new_group
  break
  for file in files:
  if self.is_valid_file(file):
- self.create_test(os.path.join(root,file), group_id)
+ self.create_test(os.path.join(root, file), group_id)
  for folder in folders:
- self.parse_folder(os.path.join(root,folder), group_id)
+ self.parse_folder(os.path.join(root, folder), group_id)
 
  def run(self):
  """
@@ -194,8 +194,9 @@ def run(self):
  logging.debug(f"Going to parse files on '{path}'")
  self.parse_folder(path, self.__id_counter)
 
+
 def start_logging(folder, debug_level=logging.INFO):
- LOG_PATH = os.path.join(folder, os.path.splitext(os.path.basename(__file__))[0]+".log" )
+ LOG_PATH = os.path.join(folder, os.path.splitext(os.path.basename(__file__))[0]+".log")
  if not os.path.exists(folder):
  os.makedirs(folder)
  logging.basicConfig(filename=LOG_PATH, level=debug_level)
@@ -224,10 +225,10 @@ def start_logging(folder, debug_level=logging.INFO):
  sanity = Sanity(Config(CONFIG_PATH))
  sanity.run()
  elif args.index_name:
- indexData=IndexData(args.index_name, Config(CONFIG_PATH))
+ indexData = IndexData(args.index_name, Config(CONFIG_PATH))
  indexData.run()
  elif args.launch_app:
- indexData=IndexData(args.launch_app, Config(CONFIG_PATH))
+ indexData = IndexData(args.launch_app, Config(CONFIG_PATH))
  indexData.run()
  os.chdir("Search-UI")
  os.system("ELASTICSEARCH_HOST=http://localhost:9200 npm start")

docs/DocGenerator/lib/IndexData.py

@@ -1,5 +1,5 @@
 """
-brief: Wazuh DocGenerator config parser.
+brief: Wazuh DocGenerator data indexer.
 copyright: Copyright (C) 2015-2021, Wazuh Inc.
 date: August 04, 2021
 license: This program is free software; you can redistribute it
@@ -11,18 +11,18 @@
 import re
 import json
 import requests
+import logging
 from elasticsearch import Elasticsearch, helpers
 
+
 class IndexData:
  """
  brief: Class that indexes the data from JSON files into ElasticSearch.
  """
  def __init__(self, index, config):
- self.conf = config
- self.path = self.conf.documentation_path
+ self.path = config.documentation_path
  self.index = index
- self.regex = ".*json"
- self.files = self.get_files()
+ self.regex = re.compile(".*json")
  self.es = Elasticsearch()
  self.output = []
 
@@ -35,47 +35,46 @@ def test_connection(self):
  if res.status_code == 200:
  return True
  except Exception as e:
- print(e)
+ logging.exception(f"Connection error:\n{e}")
  return False
 
  def get_files(self):
  """
  brief: Recursively finds all the files that match with the regex provided.
  """
  doc_files = []
- r = re.compile(self.regex)
  for (root, *_, files) in os.walk(self.path):
  for file in files:
- if r.match(file):
- doc_files.append(os.path.join(root,file))
+ if self.regex.match(file):
+ doc_files.append(os.path.join(root, file))
  return doc_files
 
- def read_files_content(self):
+ def read_files_content(self, files):
  """
- brief: It Opens every file found in the path and appends the content into a list.
+ brief: Opens every file found in the path and appends the content into a list.
  """
- for file in self.files:
+ for file in files:
  with open(os.path.join(self.path, file)) as f:
  lines = json.load(f)
  self.output.append(lines)
 
  def remove_index(self):
  """
- brief: It Deletes an index.
+ brief: Deletes an index.
  """
- delete=self.es.indices.delete(index=self.index, ignore=[400, 404])
- print(f'Delete index {self.index}\n {delete}\n')
+ delete = self.es.indices.delete(index=self.index, ignore=[400, 404])
+ logging.debug(f'Delete index {self.index}\n {delete}\n')
 
  def run(self):
  """
- brief: This calls all the methods of the Class. Finally, it uses the index name and the documents
- to make a request to the BULK API.
+ brief: Collects all the documentation files and makes a request to the BULK API to index the new data.
  """
  self.test_connection()
- self.read_files_content()
+ files = self.get_files()
+ self.read_files_content(files)
  if self.test_connection():
  self.remove_index()
- print("Indexing data...\n")
+ logging.debug("Indexing data...\n")
  helpers.bulk(self.es, self.output, index=self.index)
- out=json.dumps(self.es.cluster.health(wait_for_status='yellow', request_timeout=1), indent=4)
- print(out)
+ out = json.dumps(self.es.cluster.health(wait_for_status='yellow', request_timeout=1), indent=4)
+ logging.debug(out)