Add extensions package

2024-11-16 04:35:24 +00:00 · 2017-12-05 12:42:57 +01:00 · 2017-12-05 12:42:57 +01:00 · 4ed7110048
commit 4ed7110048
parent fc5fc6e85b
2 changed files with 139 additions and 0 deletions
--- a/pyrogram/extensions/init.py
+++ b/pyrogram/extensions/init.py
@ -0,0 +1,19 @@
+# Pyrogram - Telegram MTProto API Client Library for Python
+# Copyright (C) 2017 Dan Tès <https://github.com/delivrance>
+#
+# This file is part of Pyrogram.
+#
+# Pyrogram is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Lesser General Public License as published
+# by the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Pyrogram 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 Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with Pyrogram.  If not, see <http://www.gnu.org/licenses/>.
+
+from .markdown import Markdown
--- a/pyrogram/extensions/markdown.py
+++ b/pyrogram/extensions/markdown.py
@ -0,0 +1,120 @@
+# Pyrogram - Telegram MTProto API Client Library for Python
+# Copyright (C) 2017 Dan Tès <https://github.com/delivrance>
+#
+# This file is part of Pyrogram.
+#
+# Pyrogram is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Lesser General Public License as published
+# by the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Pyrogram 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 Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public License
+# along with Pyrogram.  If not, see <http://www.gnu.org/licenses/>.
+
+import re
+from struct import unpack
+
+from pyrogram.api.types import (
+    MessageEntityBold as Bold,
+    MessageEntityItalic as Italic,
+    MessageEntityCode as Code,
+    MessageEntityTextUrl as Url,
+    MessageEntityPre as Pre,
+)
+
+
+class Markdown:
+    INLINE_DELIMITERS = {
+        "**": Bold,
+        "__": Italic,
+        "`": Code
+    }
+
+    # SMP = Supplementary Multilingual Plane: https://en.wikipedia.org/wiki/Plane_(Unicode)#Overview
+    SMP_RE = re.compile(r"[\U00010000-\U0010FFFF]")
+
+    # ``` python
+    # for i in range(10):
+    #     print(i)
+    # ```
+    PRE_RE = r"(?P<pre>```(?P<lang>.*)\n(?P<code>(.|\n)*)\n```)"
+
+    # [url](github.com)
+    URL_RE = r"(?P<url>(\[(?P<text>.+?)\]\((?P<path>.+?)\)))"
+
+    # **bold**
+    # __italic__
+    # `code`
+    INLINE_RE = r"(?P<inline>(?P<start_delimiter>{d})(?P<body>.+?)(?P<end_delimiter>{d}))".format(
+        d="|".join(
+            ["".join(i) for i in [
+                ["\{}".format(j) for j in i]
+                for i in sorted(  # Sort delimiters by length
+                    INLINE_DELIMITERS.keys(),
+                    key=lambda k: len(k),  # Or: key=len
+                    reverse=True
+                )
+            ]]
+        )
+    )
+
+    MARKDOWN_RE = re.compile("|".join([PRE_RE, URL_RE, INLINE_RE]))
+
+    @classmethod
+    def add_surrogates(cls, text):
+        # Replace each SMP code point with a surrogate pair
+        return cls.SMP_RE.sub(
+            lambda match:  # Split SMP in two surrogates
+            "".join(chr(i) for i in unpack("<HH", match.group().encode("utf-16le")))
+            , text
+        )
+
+    @staticmethod
+    def remove_surrogates(text):
+        # Replace each surrogate pair with a SMP code point
+        return text.encode("utf-16", "surrogatepass").decode("utf-16")
+
+    @classmethod
+    def parse(cls, text):
+        entities = []
+        text = cls.add_surrogates(text)
+        offset = 0
+
+        for match in cls.MARKDOWN_RE.finditer(text):
+            start = match.start() - offset
+
+            if match.group("pre"):
+                pattern = match.group("pre")
+                lang = match.group("lang")
+                replace = match.group("code")
+                entity = Pre(start, len(replace), lang.strip())
+                offset += len(lang) + 8
+            elif match.group("url"):
+                pattern = match.group("url")
+                replace = match.group("text")
+                path = match.group("path")
+                entity = Url(start, len(replace), path)
+                offset += len(path) + 4
+            elif match.group("inline"):
+                pattern = match.group("inline")
+                replace = match.group("body")
+                start_delimiter = match.group("start_delimiter")
+                end_delimiter = match.group("end_delimiter")
+
+                if start_delimiter != end_delimiter:
+                    continue
+
+                entity = cls.INLINE_DELIMITERS[start_delimiter](start, len(replace))
+                offset += len(start_delimiter) * 2
+            else:
+                continue
+
+            entities.append(entity)
+            text = text.replace(pattern, replace)
+
+        return cls.remove_surrogates(text), entities