Add new strict option in the emoji extension (#2488)

* Add new strict option in the emoji extension

* Add emoji test for strict mode and twemoji not pointing to latest ver.

* Remove unnecessary function

Author: facelessuser

docs/src/markdown/about/changelog.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 10.12
+
+-   **NEW**: Emoji: Add a new `strict` option that will raise an exception if an emoji is used whose name has changed,
+    removed, or never existed.
+-   **FIX**: Emoji: Emoji links should be generated such that they point to the new CDN version.
+
 ## 10.11.2
 
 -   **FIX**: SuperFences: Fix a regression where certain patterns could cause a hang.

docs/src/markdown/extensions/emoji.md

@@ -500,17 +500,22 @@ Option                      | Type       | Default              | Description
 --------------------------- | ---------- | -------------------- | -----------
 `emoji_index`               | function   | `emojione` index     | A function that returns the index to use when parsing `:short_name:` syntax. See [Default Emoji Indexes](#default-emoji-indexes) to see the provided indexes.
 `emoji_generator`           | function   | `to_png` generator   | A function that takes the emoji info and constructs the desired emoji output. See [Default Emoji Generators](#default-emoji-generators) to see the provided generators.
-`title`                     | string     | `#!py3thon 'short'`   | Specifies the title format that is fed into the emoji generator function.  Can either be `long` which is the long description of the emoji, `short` which is the short name (`:short:`), or `none` which will simply pass `None`.
-`alt`                       | string     | `#!py3thon 'unicode'` | Specifies the format for the alt value that is passed to the emoji generator function. If `alt` is set to `short`, the short name will be passed to the generator.  If `alt` is set to `unicode` the Unicode characters are passed to the generator.  Lastly, if `alt` is set to `html_entity`, the Unicode characters are passed encoded as HTML entities.
-`remove_variation_selector` | bool       | `#!py3thon False`     | Specifies whether variation selectors should be removed from Unicode alt. Currently, only `fe0f` is removed as it is the only one presently found in the current emoji sets.
-`options`                   | dictionary | `#!py3thon {}`        | Options that are specific to emoji generator functions.  Supported parameters can vary from function to function.
+`title`                     | string     | `#!python 'short'`   | Specifies the title format that is fed into the emoji generator function.  Can either be `long` which is the long description of the emoji, `short` which is the short name (`:short:`), or `none` which will simply pass `None`.
+`alt`                       | string     | `#!python 'unicode'` | Specifies the format for the alt value that is passed to the emoji generator function. If `alt` is set to `short`, the short name will be passed to the generator.  If `alt` is set to `unicode` the Unicode characters are passed to the generator.  Lastly, if `alt` is set to `html_entity`, the Unicode characters are passed encoded as HTML entities.
+`remove_variation_selector` | bool       | `#!python False`     | Specifies whether variation selectors should be removed from Unicode alt. Currently, only `fe0f` is removed as it is the only one presently found in the current emoji sets.
+`options`                   | dictionary | `#!python {}`        | Options that are specific to emoji generator functions.  Supported parameters can vary from function to function.
+`strict`                    | bool       | `#!python False`     | Raise an exception if an emoji is used whose name is not found in the database.
 
 /// new | New 7.1
 `options` is now shared between index and generator functions opposed to being passed to the generator function
 only. The generator and/or index function should decide which of the arguments are relevant for its usage and parse
 accordingly.
 ///
 
+/// new | New 10.12
+Added `strict` mode.
+///
+
 /// tip | Legacy GitHubEmoji Emulation
 The Emoji extension was actually created to replace the now retired GitHubEmoji extension. Emoji was written to be
 much more flexible.  If you have a desire to configure the output to be like the legacy GitHubEmoji extension, you

pymdownx/__meta__.py

@@ -185,5 +185,5 @@ def parse_version(ver, pre=False):
     return Version(major, minor, micro, release, pre, post, dev)
 
 
-__version_info__ = Version(10, 11, 2, "final")
+__version_info__ = Version(10, 12, 0, "final")
 __version__ = __version_info__._get_canonical()

pymdownx/emoji.py

@@ -24,6 +24,7 @@
 """
 from markdown import Extension
 from markdown.inlinepatterns import InlineProcessor
+from markdown.postprocessors import Postprocessor
 from markdown import util as md_util
 import xml.etree.ElementTree as etree
 import inspect
@@ -35,8 +36,8 @@
 UNICODE_VARIATION_SELECTOR_16 = 'fe0f'
 EMOJIONE_SVG_CDN = 'https://cdnjs.cloudflare.com/ajax/libs/emojione/2.2.7/assets/svg/'
 EMOJIONE_PNG_CDN = 'https://cdnjs.cloudflare.com/ajax/libs/emojione/2.2.7/assets/png/'
-TWEMOJI_SVG_CDN = 'https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.0.3/assets/svg/'
-TWEMOJI_PNG_CDN = 'https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.0.3/assets/72x72/'
+TWEMOJI_SVG_CDN = 'https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/svg/'
+TWEMOJI_PNG_CDN = 'https://cdn.jsdelivr.net/gh/jdecked/twemoji@15.1.0/assets/72x72/'
 GITHUB_UNICODE_CDN = 'https://github.githubassets.com/images/icons/emoji/unicode/'
 GITHUB_CDN = 'https://github.githubassets.com/images/icons/emoji/'
 NO_TITLE = 'none'
@@ -52,6 +53,13 @@
 Please update your custom index accordingly.
 """
 
+MSG_BAD_EMOJI = """
+Emoji Extension (strict mode): The following emoji were detected and either had
+their name change, were removed, or have never existed.
+
+{}
+"""
+
 
 def add_attributes(options, attributes):
     """Add additional attributes from options."""
@@ -226,7 +234,7 @@ def to_alt(index, shortname, alias, uc, alt, title, category, options, md):
 class EmojiPattern(InlineProcessor):
     """Return element of type `tag` with a text attribute of group(2) of an `InlineProcessor`."""
 
-    def __init__(self, pattern, config, md):
+    def __init__(self, pattern, config, strict_mode, md):
         """Initialize."""
 
         InlineProcessor.__init__(self, pattern, md)
@@ -240,6 +248,8 @@ def __init__(self, pattern, config, md):
         self.remove_var_sel = config['remove_variation_selector']
         self.title = title if title in VALID_TITLE else NO_TITLE
         self.generator = config['emoji_generator']
+        self.strict = config['strict']
+        self.strict_cache = strict_mode
 
     def _set_index(self, index):
         """Set the index."""
@@ -336,10 +346,30 @@ def handleMatch(self, m, data):
                 self.options,
                 self.md
             )
+        elif self.strict:
+            self.strict_cache.add(shortname)
 
         return el, m.start(0), m.end(0)
 
 
+class EmojiAlertPostprocessor(Postprocessor):
+    """Post processor to strip out unwanted content."""
+
+    def __init__(self, strict_cache, md):
+        """Initialize."""
+
+        self.strict_cache = strict_cache
+
+    def run(self, text):
+        """Strip out ids and classes for a simplified HTML output."""
+
+        if len(self.strict_cache):
+            raise RuntimeError(
+                MSG_BAD_EMOJI.format('\n'.join([f'- {x}' for x in sorted(self.strict_cache)]))
+            )
+        return text
+
+
 class EmojiExtension(Extension):
     """Add emoji extension to Markdown class."""
 
@@ -371,21 +401,35 @@ def __init__(self, *args, **kwargs):
                 False,
                 "Remove variation selector 16 from unicode. - Default: False"
             ],
+            'strict': [
+                False,
+                "When enabled, if an emoji with a missing name is detected, an exception will be raised."
+            ],
             'options': [
                 {},
                 "Emoji options see documentation for options for github and emojione."
             ]
         }
         super().__init__(*args, **kwargs)
 
+    def reset(self):
+        """Reset."""
+
+        self.strict_cache.clear()
+
     def extendMarkdown(self, md):
         """Add support for emoji."""
 
+        md.registerExtension(self)
+
         config = self.getConfigs()
 
         util.escape_chars(md, [':'])
 
-        md.inlinePatterns.register(EmojiPattern(RE_EMOJI, config, md), "emoji", 75)
+        self.strict_cache = set()
+        md.inlinePatterns.register(EmojiPattern(RE_EMOJI, config, self.strict_cache, md), "emoji", 75)
+        if config['strict']:
+            md.postprocessors.register(EmojiAlertPostprocessor(self.strict_cache, md), "emoji-alert", 50)
 
 
 ###################