Improved using domains with dash or comma, remove for unique domain id.

Author: MartinMikita

Diff for: conf/sphinx/sphinx.conf

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 # Generate proper index and source for each DOMAIN
-# 
+#
 import sys
 from os import getenv
 
@@ -152,6 +152,12 @@ if domains is None or len(domains) < 0:
     raise Exception('Missing required environment variable DOMAINS!')
     sys.exit(1)
 
+
+def get_domain_id(domain):
+    # Remove unexpected characters: .:/-,
+    return domain.replace('.', '').replace(':', '').replace('/', '').replace('-', '').replace(',', '')
+
+
 # Split domains by comma and prepare source/index for this domain:
 # Input data /data/<domain>/search.tsv
 domains = domains.split(',')
@@ -161,7 +167,7 @@ index_config = ''
 for domain in domains:
     # continue
     domain_config = ''
-    domain_id = domain.replace('.', '').replace(':', '').replace('/', '')
+    domain_id = get_domain_id(domain)
     global_search_cols = ''
     format_args = {
         'domain': domain,

Diff for: web/websearch.py

@@ -37,6 +37,7 @@
 # Input data /data/<domain>/search.tsv
 domains = domains.split(',')
 
+
 # Return maximal number of results
 SEARCH_MAX_COUNT = 100
 SEARCH_DEFAULT_COUNT = 20
@@ -46,6 +47,10 @@
     SEARCH_DEFAULT_COUNT = int(getenv('SEARCH_DEFAULT_COUNT'))
 
 
+def get_domain_id(domain):
+    # Remove unexpected characters: .:/-,
+    return domain.replace('.', '').replace(':', '').replace('/', '').replace('-', '').replace(',', '')
+
 
 # ---------------------------------------------------------
 """
@@ -421,7 +426,7 @@ def search():
     if domain not in domains:
         data['result'] = {'error': 'Domain not allowed!'}
         return formatResponse(data, 403)
-    domain_id = domain.replace('.', '').replace(':', '').replace('/', '')
+    domain_id = get_domain_id(domain)
     data['domain'] = domain
 
     index = 'search_{}_index'.format(domain_id)
@@ -508,7 +513,7 @@ def update(domain):
         data['result'] = {'error': 'Domain not allowed!'}
         return formatResponse(data, 403)
 
-    domain_id = domain.replace('.', '').replace(':', '').replace('/', '').encode('utf-8')
+    domain_id = get_domain_id(domain).encode('utf-8')
     data['domain'] = domain.encode('utf-8')
     data['protocol'] = 'http'
     if request.args.get('https', None):