Merge pull request #694 from willkg/minor-fixes

Convert tags, skip_tags, recognized_tags to sets; fix doctests; f-strings

Author: willkg

bleach/html5lib_shim.py

@@ -81,127 +81,129 @@
 
 #: List of valid HTML tags, from WHATWG HTML Living Standard as of 2018-10-17
 #: https://html.spec.whatwg.org/multipage/indices.html#elements-3
-HTML_TAGS = [
-    "a",
-    "abbr",
-    "address",
-    "area",
-    "article",
-    "aside",
-    "audio",
-    "b",
-    "base",
-    "bdi",
-    "bdo",
-    "blockquote",
-    "body",
-    "br",
-    "button",
-    "canvas",
-    "caption",
-    "cite",
-    "code",
-    "col",
-    "colgroup",
-    "data",
-    "datalist",
-    "dd",
-    "del",
-    "details",
-    "dfn",
-    "dialog",
-    "div",
-    "dl",
-    "dt",
-    "em",
-    "embed",
-    "fieldset",
-    "figcaption",
-    "figure",
-    "footer",
-    "form",
-    "h1",
-    "h2",
-    "h3",
-    "h4",
-    "h5",
-    "h6",
-    "head",
-    "header",
-    "hgroup",
-    "hr",
-    "html",
-    "i",
-    "iframe",
-    "img",
-    "input",
-    "ins",
-    "kbd",
-    "keygen",
-    "label",
-    "legend",
-    "li",
-    "link",
-    "map",
-    "mark",
-    "menu",
-    "meta",
-    "meter",
-    "nav",
-    "noscript",
-    "object",
-    "ol",
-    "optgroup",
-    "option",
-    "output",
-    "p",
-    "param",
-    "picture",
-    "pre",
-    "progress",
-    "q",
-    "rp",
-    "rt",
-    "ruby",
-    "s",
-    "samp",
-    "script",
-    "section",
-    "select",
-    "slot",
-    "small",
-    "source",
-    "span",
-    "strong",
-    "style",
-    "sub",
-    "summary",
-    "sup",
-    "table",
-    "tbody",
-    "td",
-    "template",
-    "textarea",
-    "tfoot",
-    "th",
-    "thead",
-    "time",
-    "title",
-    "tr",
-    "track",
-    "u",
-    "ul",
-    "var",
-    "video",
-    "wbr",
-]
+HTML_TAGS = frozenset(
+    (
+        "a",
+        "abbr",
+        "address",
+        "area",
+        "article",
+        "aside",
+        "audio",
+        "b",
+        "base",
+        "bdi",
+        "bdo",
+        "blockquote",
+        "body",
+        "br",
+        "button",
+        "canvas",
+        "caption",
+        "cite",
+        "code",
+        "col",
+        "colgroup",
+        "data",
+        "datalist",
+        "dd",
+        "del",
+        "details",
+        "dfn",
+        "dialog",
+        "div",
+        "dl",
+        "dt",
+        "em",
+        "embed",
+        "fieldset",
+        "figcaption",
+        "figure",
+        "footer",
+        "form",
+        "h1",
+        "h2",
+        "h3",
+        "h4",
+        "h5",
+        "h6",
+        "head",
+        "header",
+        "hgroup",
+        "hr",
+        "html",
+        "i",
+        "iframe",
+        "img",
+        "input",
+        "ins",
+        "kbd",
+        "keygen",
+        "label",
+        "legend",
+        "li",
+        "link",
+        "map",
+        "mark",
+        "menu",
+        "meta",
+        "meter",
+        "nav",
+        "noscript",
+        "object",
+        "ol",
+        "optgroup",
+        "option",
+        "output",
+        "p",
+        "param",
+        "picture",
+        "pre",
+        "progress",
+        "q",
+        "rp",
+        "rt",
+        "ruby",
+        "s",
+        "samp",
+        "script",
+        "section",
+        "select",
+        "slot",
+        "small",
+        "source",
+        "span",
+        "strong",
+        "style",
+        "sub",
+        "summary",
+        "sup",
+        "table",
+        "tbody",
+        "td",
+        "template",
+        "textarea",
+        "tfoot",
+        "th",
+        "thead",
+        "time",
+        "title",
+        "tr",
+        "track",
+        "u",
+        "ul",
+        "var",
+        "video",
+        "wbr",
+    )
+)
 
 
 #: List of block level HTML tags, as per https://github.com/mozilla/bleach/issues/369
 #: from mozilla on 2019.07.11
 #: https://developer.mozilla.org/en-US/docs/Web/HTML/Block-level_elements#Elements
 HTML_TAGS_BLOCK_LEVEL = frozenset(
-    [
+    (
         "address",
         "article",
         "aside",
@@ -235,7 +237,7 @@
         "section",
         "table",
         "ul",
-    ]
+    )
 )
 
 
@@ -476,15 +478,17 @@ class BleachHTMLParser(HTMLParser):
 
     def __init__(self, tags, strip, consume_entities, **kwargs):
         """
-        :arg tags: list of allowed tags--everything else is either stripped or
+        :arg tags: set of allowed tags--everything else is either stripped or
             escaped; if None, then this doesn't look at tags at all
         :arg strip: whether to strip disallowed tags (True) or escape them (False);
             if tags=None, then this doesn't have any effect
         :arg consume_entities: whether to consume entities (default behavior) or
             leave them as is when tokenizing (BleachHTMLTokenizer-added behavior)
 
         """
-        self.tags = [tag.lower() for tag in tags] if tags is not None else None
+        self.tags = (
+            frozenset((tag.lower() for tag in tags)) if tags is not None else None
+        )
         self.strip = strip
         self.consume_entities = consume_entities
         super().__init__(**kwargs)
@@ -694,7 +698,7 @@ def escape_base_amp(self, stoken):
                 # Only leave entities in that are not ambiguous. If they're
                 # ambiguous, then we escape the ampersand.
                 if entity is not None and convert_entity(entity) is not None:
-                    yield "&" + entity + ";"
+                    yield f"&{entity};"
 
                     # Length of the entity plus 2--one for & at the beginning
                     # and one for ; at the end

bleach/linkifier.py

@@ -120,17 +120,18 @@ def __init__(
         :arg list callbacks: list of callbacks to run when adjusting tag attributes;
             defaults to ``bleach.linkifier.DEFAULT_CALLBACKS``
 
-        :arg list skip_tags: list of tags that you don't want to linkify the
-            contents of; for example, you could set this to ``['pre']`` to skip
-            linkifying contents of ``pre`` tags
+        :arg set skip_tags: set of tags that you don't want to linkify the
+            contents of; for example, you could set this to ``{'pre'}`` to skip
+            linkifying contents of ``pre`` tags; ``None`` means you don't
+            want linkify to skip any tags
 
         :arg bool parse_email: whether or not to linkify email addresses
 
         :arg url_re: url matching regex
 
         :arg email_re: email matching regex
 
-        :arg list recognized_tags: the list of tags that linkify knows about;
+        :arg set recognized_tags: the set of tags that linkify knows about;
             everything else gets escaped
 
         :returns: linkified text as unicode
@@ -145,7 +146,7 @@ def __init__(
         # Create a parser/tokenizer that allows all HTML tags and escapes
         # anything not in that list.
         self.parser = html5lib_shim.BleachHTMLParser(
-            tags=recognized_tags,
+            tags=frozenset(recognized_tags),
             strip=False,
             consume_entities=False,
             namespaceHTMLElements=False,
@@ -221,8 +222,8 @@ def __init__(
         :arg list callbacks: list of callbacks to run when adjusting tag attributes;
             defaults to ``bleach.linkifier.DEFAULT_CALLBACKS``
 
-        :arg list skip_tags: list of tags that you don't want to linkify the
-            contents of; for example, you could set this to ``['pre']`` to skip
+        :arg set skip_tags: set of tags that you don't want to linkify the
+            contents of; for example, you could set this to ``{'pre'}`` to skip
             linkifying contents of ``pre`` tags
 
         :arg bool parse_email: whether or not to linkify email addresses
@@ -235,7 +236,7 @@ def __init__(
         super().__init__(source)
 
         self.callbacks = callbacks or []
-        self.skip_tags = skip_tags or []
+        self.skip_tags = skip_tags or {}
         self.parse_email = parse_email
 
         self.url_re = url_re