Merge branch 'main' into ignore-does-not-exist

bookwyrm/utils/isni.py

@@ -106,7 +106,7 @@ def find_authors_by_name(name_string, description=False):
 
             if titles:
                 # some of the "titles" in ISNI are a little ...iffy
-                # '@' is used by ISNI/OCLC to index the starting point ignoring stop words
+                # @ is used by ISNI/OCLC to index the starting point ignoring stop words
                 # (e.g. "The @Government of no one")
                 title_elements = [
                     e

bookwyrm/utils/regex.py

@@ -4,7 +4,7 @@ DOMAIN = r"[\w_\-\.]+\.[a-z\-]{2,}"
 LOCALNAME = r"@?[a-zA-Z_\-\.0-9]+"
 STRICT_LOCALNAME = r"@[a-zA-Z_\-\.0-9]+"
 USERNAME = rf"{LOCALNAME}(@{DOMAIN})?"
-STRICT_USERNAME = rf"\B{STRICT_LOCALNAME}(@{DOMAIN})?\b"
+STRICT_USERNAME = rf"(\B{STRICT_LOCALNAME}(@{DOMAIN})?\b)"
 FULL_USERNAME = rf"{LOCALNAME}@{DOMAIN}\b"
 SLUG = r"/s/(?P<slug>[-_a-z0-9]*)"
 # should match (BookWyrm/1.0.0; or (BookWyrm/99.1.2;

bookwyrm/utils/sanitizer.py

@@ -0,0 +1,26 @@
+"""Clean user-provided text"""
+import bleach
+
+
+def clean(input_text):
+    """Run through "bleach" """
+    return bleach.clean(
+        input_text,
+        tags=[
+            "p",
+            "blockquote",
+            "br",
+            "b",
+            "i",
+            "strong",
+            "em",
+            "pre",
+            "a",
+            "span",
+            "ul",
+            "ol",
+            "li",
+        ],
+        attributes=["href", "rel", "src", "alt"],
+        strip=True,
+    )