pyrofork: Add support for custom emoji in markdown unparser

Signed-off-by: wulan17 <wulan17@nusantararom.org>

pyrogram/methods/chats/get_forum_topics.py

@@ -32,7 +32,10 @@ class GetForumTopics:
     async def get_forum_topics(
         self: "pyrogram.Client",
         chat_id: Union[int, str],
-        limit: int = 0
+        limit: int = 0,
+        offset_date: int = 0,
+        offset_id: int = 0,
+        offset_topic: int = 0
     ) -> Optional[AsyncGenerator["types.ForumTopic", None]]:
         """Get one or more topic from a chat.
 
@@ -46,6 +49,15 @@ class GetForumTopics:
             limit (``int``, *optional*):
                 Limits the number of topics to be retrieved.
 
+            offset_date (``int``, *optional*):
+                Date of the last message of the last found topic.
+
+            offset_id (``int``, *optional*):
+                ID of the last message of the last found topic.
+
+            offset_topic (``int``, *optional*):
+                ID of the last found topic.
+
         Returns:
             ``Generator``: On success, a generator yielding :obj:`~pyrogram.types.ForumTopic` objects is returned.
 
@@ -62,7 +74,7 @@ class GetForumTopics:
 
         peer = await self.resolve_peer(chat_id)
 
-        rpc = raw.functions.channels.GetForumTopics(channel=peer, offset_date=0, offset_id=0, offset_topic=0, limit=limit)
+        rpc = raw.functions.channels.GetForumTopics(channel=peer, offset_date=offset_date, offset_id=offset_id, offset_topic=offset_topic, limit=limit)
 
         r = await self.invoke(rpc, sleep_threshold=-1)
 

pyrogram/parser/markdown.py

@@ -182,78 +182,84 @@ class Markdown:
 
     @staticmethod
     def unparse(text: str, entities: list):
+        """
+        Performs the reverse operation to .parse(), effectively returning
+        markdown-like syntax given a normal text and its MessageEntity's.
+
+        :param text: the text to be reconverted into markdown.
+        :param entities: list of MessageEntity's applied to the text.
+        :return: a markdown-like text representing the combination of both inputs.
+        """
+        delimiters = {
+            MessageEntityType.BOLD: BOLD_DELIM,
+            MessageEntityType.ITALIC: ITALIC_DELIM,
+            MessageEntityType.UNDERLINE: UNDERLINE_DELIM,
+            MessageEntityType.STRIKETHROUGH: STRIKE_DELIM,
+            MessageEntityType.CODE: CODE_DELIM,
+            MessageEntityType.PRE: PRE_DELIM,
+            MessageEntityType.BLOCKQUOTE: BLOCKQUOTE_DELIM,
+            MessageEntityType.EXPANDABLE_BLOCKQUOTE: BLOCKQUOTE_EXPANDABLE_DELIM,
+            MessageEntityType.SPOILER: SPOILER_DELIM
+        }
+
         text = utils.add_surrogates(text)
 
-        entities_offsets = []
+        insert_at = []
-
+        for i, entity in enumerate(entities):
-        for entity in entities:
+            s = entity.offset
-            entity_type = entity.type
+            e = entity.offset + entity.length
-            start = entity.offset
+            delimiter = delimiters.get(entity.type, None)
-            end = start + entity.length
+            if delimiter:
-
+                if entity.type != MessageEntityType.BLOCKQUOTE and entity.type != MessageEntityType.EXPANDABLE_BLOCKQUOTE:
-            if entity_type == MessageEntityType.BOLD:
+                    open_delimiter = delimiter
-                start_tag = end_tag = BOLD_DELIM
+                    close_delimiter = delimiter
-            elif entity_type == MessageEntityType.ITALIC:
+                    if entity.type == MessageEntityType.PRE:
-                start_tag = end_tag = ITALIC_DELIM
+                        close_delimiter = '\n' + delimiter
-            elif entity_type == MessageEntityType.UNDERLINE:
+                        if entity.language:
-                start_tag = end_tag = UNDERLINE_DELIM
+                            open_delimiter += entity.language + '\n'
-            elif entity_type == MessageEntityType.STRIKETHROUGH:
+                        else:
-                start_tag = end_tag = STRIKE_DELIM
+                            open_delimiter += '\n'
-            elif entity_type == MessageEntityType.CODE:
+                    insert_at.append((s, i, open_delimiter))
-                start_tag = end_tag = CODE_DELIM
+                    insert_at.append((e, -i, close_delimiter))
-            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:
-                if entity.collapsed:
-                    start_tag = BLOCKQUOTE_EXPANDABLE_DELIM + " "
                 else:
-                    start_tag = BLOCKQUOTE_DELIM + " "
+                    # Handle multiline blockquotes
-                end_tag = ""
+                    text_subset = text[s:e]
-                blockquote_text = text[start:end]
+                    lines = text_subset.splitlines()
-                lines = blockquote_text.split("\n")
+                    for line_num, line in enumerate(lines):
-                last_length = 0
+                        line_start = s + sum(len(l) + 1 for l in lines[:line_num])
-                for line in lines:
+                        if entity.collapsed:
-                    if len(line) == 0 and last_length == end:
+                            insert_at.append((line_start, i, BLOCKQUOTE_EXPANDABLE_DELIM))
-                        continue
+                        else:
-                    start_offset = start+last_length
+                            insert_at.append((line_start, i, BLOCKQUOTE_DELIM))
-                    last_length = last_length+len(line)
+                    # No closing delimiter for blockquotes
-                    end_offset = start_offset+last_length
-                    entities_offsets.append((start_tag, start_offset,))
-                    entities_offsets.append((end_tag, end_offset,))
-                    last_length = last_length+1
-                continue
-            elif entity_type == MessageEntityType.SPOILER:
-                start_tag = end_tag = SPOILER_DELIM
-            elif entity_type == MessageEntityType.TEXT_LINK:
-                url = entity.url
-                start_tag = "["
-                end_tag = f"]({url})"
-            elif entity_type == MessageEntityType.TEXT_MENTION:
-                user = entity.user
-                start_tag = "["
-                end_tag = f"](tg://user?id={user.id})"
-            elif entity_type == MessageEntityType.CUSTOM_EMOJI:
-                emoji_id = entity.custom_emoji_id
-                start_tag = "!["
-                end_tag = f"](tg://emoji?id={emoji_id})"
             else:
-                continue
+                url = None
+                is_emoji = False
+                if entity.type == MessageEntityType.TEXT_LINK:
+                    url = entity.url
+                elif entity.type == MessageEntityType.TEXT_MENTION:
+                    url = f'tg://user?id={entity.user.id}'
+                elif entity.type == MessageEntityType.CUSTOM_EMOJI:
+                    url = f"tg://emoji?id={entity.custom_emoji_id}"
+                    is_emoji = True
+                if url:
+                    if is_emoji:
+                        insert_at.append((s, i, '!['))
+                    else:
+                        insert_at.append((s, i, '['))
+                    insert_at.append((e, -i, f']({url})'))
 
-            entities_offsets.append((start_tag, start,))
+        insert_at.sort(key=lambda t: (t[0], t[1]))
-            entities_offsets.append((end_tag, end,))
+        while insert_at:
+            at, _, what = insert_at.pop()
 
-        entities_offsets = map(
+            # If we are in the middle of a surrogate nudge the position by -1.
-            lambda x: x[1],
+            # Otherwise we would end up with malformed text and fail to encode.
-            sorted(
+            # For example of bad input: "Hi \ud83d\ude1c"
-                enumerate(entities_offsets),
+            # https://en.wikipedia.org/wiki/UTF-16#U+010000_to_U+10FFFF
-                key=lambda x: (x[1][1], x[0]),
+            while utils.within_surrogate(text, at):
-                reverse=True
+                at += 1
-            )
-        )
 
-        for entity, offset in entities_offsets:
+            text = text[:at] + what + text[at:]
-            text = text[:offset] + entity + text[offset:]
 
         return utils.remove_surrogates(text)

pyrogram/parser/utils.py

@@ -40,3 +40,16 @@ def remove_surrogates(text):
 
 def replace_once(source: str, old: str, new: str, start: int):
     return source[:start] + source[start:].replace(old, new, 1)
+
+def within_surrogate(text, index, *, length=None):
+    """
+    `True` if ``index`` is within a surrogate (before and after it, not at!).
+    """
+    if length is None:
+        length = len(text)
+
+    return (
+            1 < index < len(text) and  # in bounds
+            '\ud800' <= text[index - 1] <= '\udbff' and  # previous is
+            '\ud800' <= text[index] <= '\udfff'  # current is
+    )