Remove lxml HTML parser as it was messing up emoji offset handling

mautrix_telegram/formatter/from_matrix/__init__.py

@@ -76,7 +76,6 @@ def matrix_to_telegram(html: str) -> ParsedMessage:
         if should_bridge_plaintext_highlights:
             html = plain_mention_regex.sub(plain_mention_to_html, html)
 
-        html = add_surrogates(html)
         text, entities = parse_html(add_surrogates(html))
         text = remove_surrogates(text.strip())
         text, entities = cut_long_message(text, entities)

mautrix_telegram/formatter/from_matrix/html_reader.py

@@ -1,4 +1,58 @@
-try:
+# -*- coding: future_fstrings -*-
-    from .html_reader_lxml import HTMLNode, read_html
+# mautrix-telegram - A Matrix-Telegram puppeting bridge
-except ImportError:
+# Copyright (C) 2018 Tulir Asokan
-    from .html_reader_htmlparser import HTMLNode, read_html
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <https://www.gnu.org/licenses/>.
+from typing import Dict, List, Tuple
+
+from html.parser import HTMLParser
+
+
+class HTMLNode(list):
+    def __init__(self, tag: str, attrs: List[Tuple[str, str]]):
+        super().__init__()
+        self.tag = tag  # type: str
+        self.text = ""  # type: str
+        self.tail = ""  # type: str
+        self.attrib = dict(attrs)  # type: Dict[str, str]
+
+
+class NodeifyingParser(HTMLParser):
+    def __init__(self):
+        super().__init__()
+        self.stack = [HTMLNode("html", [])]  # type: List[HTMLNode]
+
+    def handle_starttag(self, tag, attrs):
+        node = HTMLNode(tag, attrs)
+        self.stack[-1].append(node)
+        self.stack.append(node)
+
+    def handle_endtag(self, tag):
+        if tag == self.stack[-1].tag:
+            self.stack.pop()
+
+    def handle_data(self, data):
+        if len(self.stack[-1]) > 0:
+            self.stack[-1][-1].tail += data
+        else:
+            self.stack[-1].text += data
+
+    def error(self, message):
+        pass
+
+
+def read_html(data: str) -> HTMLNode:
+    parser = NodeifyingParser()
+    parser.feed(data)
+    return parser.stack[0]

mautrix_telegram/formatter/from_matrix/html_reader_htmlparser.py

@@ -1,58 +0,0 @@
-# -*- coding: future_fstrings -*-
-# mautrix-telegram - A Matrix-Telegram puppeting bridge
-# Copyright (C) 2018 Tulir Asokan
-#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-#
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-from typing import Dict, List, Tuple
-
-from html.parser import HTMLParser
-
-
-class HTMLNode(list):
-    def __init__(self, tag: str, attrs: List[Tuple[str, str]]):
-        super().__init__()
-        self.tag = tag  # type: str
-        self.text = ""  # type: str
-        self.tail = ""  # type: str
-        self.attrib = dict(attrs)  # type: Dict[str, str]
-
-
-class NodeifyingParser(HTMLParser):
-    def __init__(self):
-        super().__init__()
-        self.stack = [HTMLNode("html", [])]  # type: List[HTMLNode]
-
-    def handle_starttag(self, tag, attrs):
-        node = HTMLNode(tag, attrs)
-        self.stack[-1].append(node)
-        self.stack.append(node)
-
-    def handle_endtag(self, tag):
-        if tag == self.stack[-1].tag:
-            self.stack.pop()
-
-    def handle_data(self, data):
-        if len(self.stack[-1]) > 0:
-            self.stack[-1][-1].tail += data
-        else:
-            self.stack[-1].text += data
-
-    def error(self, message):
-        pass
-
-
-def read_html(data: str) -> HTMLNode:
-    parser = NodeifyingParser()
-    parser.feed(data)
-    return parser.stack[0]

mautrix_telegram/formatter/from_matrix/html_reader_lxml.py

@@ -1,23 +0,0 @@
-# -*- coding: future_fstrings -*-
-# mautrix-telegram - A Matrix-Telegram puppeting bridge
-# Copyright (C) 2018 Tulir Asokan
-#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-#
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-from lxml import html
-
-HTMLNode = html.HtmlElement
-
-
-def read_html(data: str) -> HTMLNode:
-    return html.fromstring(data)