Add languages to "pre" tags (HTML and Markdown) pyrogram#1118

Princic-1837592 · delivrance · web-flow · commit 9ade92c85525 · 2022-10-15T18:19:38.000+02:00
* added `language` to entities when unparsing (both markdown and html)

* added `language` to entities also when parsing (html only)

* Update html.py

* Update markdown.py

* Update markdown.py

* Update markdown.py

Co-authored-by: Dan &lt;14043624+delivrance@users.noreply.github.com&gt;
diff --git a/pyrogram/parser/html.py b/pyrogram/parser/html.py
@@ -61,7 +61,7 @@ def handle_starttag(self, tag, attrs):
             entity = raw.types.MessageEntityCode
         elif tag == "pre":
             entity = raw.types.MessageEntityPre
-            extra["language"] = ""
+            extra["language"] = attrs.get("language", "")
         elif tag == "spoiler":
             entity = raw.types.MessageEntitySpoiler
         elif tag == "a":
@@ -172,9 +172,13 @@ def unparse(text: str, entities: list):
                 name = entity_type.name[0].lower()
                 start_tag = f"<{name}>"
                 end_tag = f"</{name}>"
+            elif entity_type == MessageEntityType.PRE:
+                name = entity_type.name.lower()
+                language = getattr(entity, "language", "") or ""
+                start_tag = f'<{name} language="{language}">' if language else f"<{name}>"
+                end_tag = f"</{name}>"
             elif entity_type in (
                 MessageEntityType.CODE,
-                MessageEntityType.PRE,
                 MessageEntityType.BLOCKQUOTE,
                 MessageEntityType.SPOILER,
             ):
diff --git a/pyrogram/parser/markdown.py b/pyrogram/parser/markdown.py
@@ -105,6 +105,12 @@ async def parse(self, text: str, strict: bool = False):
                 delims.remove(delim)
                 tag = CLOSING_TAG.format(tag)
 
+            if delim == PRE_DELIM and delim in delims:
+                delim_and_language = text[text.find(PRE_DELIM):].split("\n")[0]
+                language = delim_and_language[len(PRE_DELIM):]
+                text = utils.replace_once(text, delim_and_language, f'<pre language="{language}">', start)
+                continue
+
             text = utils.replace_once(text, delim, tag, start)
 
         return await self.html.parse(text)
@@ -130,7 +136,11 @@ def unparse(text: str, entities: list):
                 start_tag = end_tag = STRIKE_DELIM
             elif entity_type == MessageEntityType.CODE:
                 start_tag = end_tag = CODE_DELIM
-            elif entity_type in (MessageEntityType.PRE, MessageEntityType.BLOCKQUOTE):
+            elif entity_type == MessageEntityType.PRE:
+                language = getattr(entity, "language", "") or ""
+                start_tag = f"{PRE_DELIM}{language}\n"
+                end_tag = f"\n{PRE_DELIM}"
+            elif entity_type == MessageEntityType.BLOCKQUOTE:
                 start_tag = end_tag = PRE_DELIM
             elif entity_type == MessageEntityType.SPOILER:
                 start_tag = end_tag = SPOILER_DELIM
