Added TAG_SEPARATORS option to supply a regex of characters to use when splitting tags

archivebox/config.py

@@ -79,6 +79,7 @@ CONFIG_SCHEMA: Dict[str, ConfigDefaultDict] = {
         'URL_BLACKLIST':            {'type': str,   'default': r'\.(css|js|otf|ttf|woff|woff2|gstatic\.com|googleapis\.com/css)(\?.*)?$'},  # to avoid downloading code assets as their own pages
         'URL_WHITELIST':            {'type': str,   'default': None},
         'ENFORCE_ATOMIC_WRITES':    {'type': bool,  'default': True},
+        'TAG_SEPARATORS':           {'type': str,   'default': '[,]'},
     },
 
     'SERVER_CONFIG': {

archivebox/config_stubs.py

@@ -98,6 +98,7 @@ class ConfigDict(BaseConfig, total=False):
     WGET_ARGS: List[str]
     CURL_ARGS: List[str]
     GIT_ARGS: List[str]
+    TAG_SEPARATORS: str
 
 
 ConfigDefaultValueGetter = Callable[[ConfigDict], ConfigValue]

archivebox/index/sql.py

@@ -1,5 +1,7 @@
 __package__ = 'archivebox.index'
 
+import re
+
 from io import StringIO
 from pathlib import Path
 from typing import List, Tuple, Iterator
@@ -8,7 +10,10 @@ from django.db import transaction
 
 from .schema import Link
 from ..util import enforce_types, parse_date
-from ..config import OUTPUT_DIR
+from ..config import (
+    OUTPUT_DIR,
+    TAG_SEPARATORS,
+)
 
 
 ### Main Links Index
@@ -35,7 +40,7 @@ def write_link_to_sql_index(link: Link):
     info = {k: v for k, v in link._asdict().items() if k in Snapshot.keys}
 
     tag_list = list(dict.fromkeys(
-        tag.strip() for tag in (link.tags or '').split(',')
+        tag.strip() for tag in re.split(TAG_SEPARATORS, link.tags or '')
     ))
     info.pop('tags')
 
@@ -107,7 +112,7 @@ def write_sql_link_details(link: Link, out_dir: Path=OUTPUT_DIR) -> None:
     snap.title = link.title
 
     tag_list = list(dict.fromkeys(
-        tag.strip() for tag in (link.tags or '').split(',')
+        tag.strip() for tag in re.split(TAG_SEPARATORS, link.tags or '')
     ))
 
     snap.save()