PARSING WORKS OML FUCK YEAH

transcental · transcental · commit c7ea55bca685 · 2024-12-01T01:08:54.000Z
diff --git a/events/views/create_event.py b/events/views/create_event.py
@@ -3,8 +3,9 @@
 from datetime import datetime, timezone
 
 from utils.env import env
-from utils.utils import rich_text_to_md, md_to_mrkdwn
+from utils.utils import rich_text_to_md, rich_text_to_mrkdwn
 from views.app_home import get_home
+import json
 
 
 def handle_create_event_view(ack: Callable, body: dict[str, Any], client: WebClient):
@@ -52,7 +53,8 @@ def handle_create_event_view(ack: Callable, body: dict[str, Any], client: WebCli
     user_id = body.get("user", {}).get("id", "")
     host_mention = f"for <@{host_id}>" if host_id != user_id else ""
     host_str = f"<@{user_id}> {host_mention}"
-    mrkdwn = md_to_mrkdwn(md)
+    rich_text = json.loads(event["fields"]["Raw Description"])
+    mrkdwn = rich_text_to_mrkdwn(rich_text)
     client.chat_postMessage(
         channel=env.slack_approval_channel,
         text=f"New event request by <@{body['user']['id']}>!\nTitle: {title[0]}\nDescription: {mrkdwn}\nStart Time: {start_time[0]}\nEnd Time: {end_time[0]}",
diff --git a/events/views/edit_event.py b/events/views/edit_event.py
@@ -3,7 +3,7 @@
 from datetime import datetime, timezone
 
 from utils.env import env
-from utils.utils import rich_text_to_md, md_to_mrkdwn
+from utils.utils import rich_text_to_md, rich_text_to_mrkdwn
 from views.app_home import get_home
 
 import json
@@ -66,7 +66,8 @@ def handle_edit_event_view(ack: Callable, body: dict[str, Any], client: WebClien
     user_id = body.get("user", {}).get("id", "")
     host_mention = f"for <@{host_id}>" if host_id != user_id else ""
     host_str = f"<@{user_id}> {host_mention}"
-    mrkdwn = md_to_mrkdwn(md)
+    rich_text = json.loads(raw_description_string)
+    mrkdwn = rich_text_to_mrkdwn(rich_text)
     client.chat_postMessage(
         channel=env.slack_approval_channel,
         text=f"New event request by <@{body['user']['id']}>!\nTitle: {title[0]}\nDescription: {mrkdwn}\nStart Time: {start_time[0]}\nEnd Time: {end_time[0]}",
diff --git a/utils/utils.py b/utils/utils.py
@@ -1,11 +1,13 @@
 from .env import env
+from slack_sdk import WebClient
+from urllib.parse import quote
 
 import re
+import mistune
 
-from slack_sdk import WebClient
 
 client = WebClient(token=env.slack_bot_token)
-
+ZWSP = '\u200B'
 
 def user_in_safehouse(user_id: str):
     sad_members = client.conversations_members(channel=env.slack_sad_channel)["members"]
@@ -18,17 +20,36 @@ def parse_elements(elements):
         if element["type"] == "text":
             text = element["text"]
             if "style" in element:
-                if element["style"].get("bold"):
+                styles = element["style"]
+                if styles.get("bold") and styles.get("italic"):
+                    text = f"**_{text}_**"
+                elif styles.get("bold"):
                     text = f"**{text}**"
-                if element["style"].get("italic"):
-                    text = f"*{text}*"
-                if element["style"].get("strike"):
+                elif styles.get("italic"):
+                    text = f"_{text}_"
+                if styles.get("strike"):
                     text = f"~~{text}~~"
-                if element["style"].get("code"):
+                if styles.get("code"):
                     text = f"`{text}`"
             markdown += text
         elif element["type"] == "link":
             markdown += f"[{element['text']}]({element['url']})"
+        elif element["type"] == "user":
+            markdown += f"<@{element['user_id']}>"
+        elif element["type"] == "emoji":
+            markdown += f":{element['name']}:"
+        elif element["type"] == "channel":
+            markdown += f"<#{element['channel_id']}>"
+        elif element["type"] == "subteam":
+            markdown += f"<!subteam^{element['subteam_id']}|{element['name']}>"
+        elif element["type"] == "date":
+            markdown += f"<!date^{element['timestamp']}^{element['format']}|{element['fallback']}>"
+        elif element["type"] == "url":
+            markdown += f"<{element['url']}>"
+        elif element["type"] == "line_break":
+            markdown += "\n"
+        elif element["type"] == "usergroup":
+            markdown += f"<!subteam^{element['usergroup_id']}>"
     return markdown
 
 
@@ -59,26 +80,65 @@ def rich_text_to_md(input_data, indent_level=0, in_quote=False):
     return markdown
 
 
-def md_to_mrkdwn(md):
-    # Convert bold and italic text (bold first to avoid conflicts)
-    md = re.sub(r"\*\*\*(.*?)\*\*\*", r"***\1***", md)  # Bold and italic
-    md = re.sub(r"\*\*(.*?)\*\*", r"*\1*", md)  # Bold
-    md = re.sub(r"\b\*(.*?)\*\b", r"_\1_", md)  # Italic
-    # Convert strikethrough text
-    md = re.sub(r"~~(.*?)~~", r"~\1~", md)
-    # Convert inline code
-    md = re.sub(r"`(.*?)`", r"`\1`", md)
-    # Convert links
-    md = re.sub(r"\[(.*?)\]\((.*?)\)", r"<\2|\1>", md)
-    # Convert blockquotes
-    md = re.sub(r"^> (.*)", r"> \1", md, flags=re.MULTILINE)
-    # Convert code blocks
-    md = re.sub(r"```(.*?)```", r"```\1```", md, flags=re.DOTALL)
-    # Convert unordered lists
-    md = re.sub(r"^\s*-\s+(.*)", r"• \1", md, flags=re.MULTILINE)
-    # Convert ordered lists
-    md = re.sub(r"^\s*\d+\.\s+(.*)", r"1. \1", md, flags=re.MULTILINE)
-    # Handle nested lists
-    md = re.sub(r"(\n\s*)•", r"\1  •", md)
-    md = re.sub(r"(\n\s*)1\.", r"\1  1.", md)
-    return md
+def parse_elements_to_mrkdwn(elements):
+    mrkdwn = ""
+    for element in elements:
+        if element["type"] == "text":
+            text = element["text"]
+            if "style" in element:
+                styles = element["style"]
+                words = re.split(r'(\s+)', text)  # Split by whitespace but keep the whitespace
+                formatted_words = []
+                for word in words:
+                    if word.strip():  # Only apply formatting to non-whitespace words
+                        if styles.get("bold") and styles.get("italic"):
+                            word = f"*_{word.strip()}_*"
+                        elif styles.get("bold"):
+                            word = f"*{word.strip()}*"
+                        elif styles.get("italic"):
+                            word = f"_{word.strip()}_"
+                        if styles.get("strike"):
+                            word = f"~{word.strip()}~"
+                        if styles.get("code"):
+                            word = f"`{word.strip()}`"
+                    formatted_words.append(word)
+                text = "".join(formatted_words)  # Join without adding extra spaces
+            mrkdwn += text
+        elif element["type"] == "link":
+            mrkdwn += f"<{element['url']}|{element['text']}>"
+        elif element["type"] == "user":
+            mrkdwn += f"<@{element['user_id']}>"
+        elif element["type"] == "emoji":
+            mrkdwn += f":{element['name']}:"
+        elif element["type"] == "channel":
+            mrkdwn += f"<#{element['channel_id']}>"
+        elif element["type"] == "subteam":
+            mrkdwn += f"<!subteam^{element['subteam_id']}|{element['name']}>"
+        elif element["type"] == "date":
+            mrkdwn += f"<!date^{element['timestamp']}^{element['format']}|{element['fallback']}>"
+        elif element["type"] == "url":
+            mrkdwn += f"<{element['url']}>"
+        elif element["type"] == "line_break":
+            mrkdwn += "\n"
+        elif element["type"] == "usergroup":
+            mrkdwn += f"<!subteam^{element['usergroup_id']}>"
+    return mrkdwn
+
+def rich_text_to_mrkdwn(data):
+    mrkdwn = ""
+    for block in data:
+        if isinstance(block, dict) and block["type"] == "rich_text_section":
+            mrkdwn += parse_elements_to_mrkdwn(block["elements"]) + "\n"
+        elif isinstance(block, dict) and block["type"] == "rich_text_quote":
+            mrkdwn += "> " + parse_elements_to_mrkdwn(block["elements"]) + "\n"
+            # Handle nested lists within quotes
+            mrkdwn += rich_text_to_mrkdwn(block["elements"])
+        elif isinstance(block, dict) and block["type"] == "rich_text_preformatted":
+            mrkdwn += "```\n" + parse_elements_to_mrkdwn(block["elements"]) + "\n```\n"
+        elif isinstance(block, dict) and block["type"] == "rich_text_list":
+            for item in block["elements"]:
+                mrkdwn += f"- {parse_elements_to_mrkdwn(item['elements'])}\n"
+                # Recursively parse nested lists
+                if "elements" in item:
+                    mrkdwn += rich_text_to_mrkdwn(item["elements"])
+    return mrkdwn
diff --git a/views/app_home.py b/views/app_home.py
@@ -2,7 +2,8 @@
 from slack_sdk import WebClient
 
 from utils.env import env
-from utils.utils import user_in_safehouse, md_to_mrkdwn
+from utils.utils import user_in_safehouse, rich_text_to_mrkdwn
+import json
 
 
 def get_home(user_id: str, client: WebClient):
@@ -47,7 +48,8 @@ def get_home(user_id: str, client: WebClient):
             "Ends at %I:%M %p"
         )
         formatted_time = f"<!date^{int(datetime.fromisoformat(event['fields']['End Time']).timestamp())}^Ends at {{time}}|{fallback_time}>"
-        mrkdwn = md_to_mrkdwn(event["fields"]["Description"])
+        rich_text = json.loads(event["fields"]["Raw Description"])
+        mrkdwn = rich_text_to_mrkdwn(rich_text['elements'])
         current_events_blocks.append(
             {
                 "type": "section",
@@ -117,7 +119,8 @@ def get_home(user_id: str, client: WebClient):
             "%A, %B %d at %I:%M %p"
         )
         formatted_time = f"<!date^{int(datetime.fromisoformat(event['fields']['Start Time']).timestamp())}^{{date_long_pretty}} at {{time}}|{fallback_time}>"
-        mrkdwn = md_to_mrkdwn(event["fields"]["Description"])
+        rich_text = json.loads(event["fields"]["Raw Description"])
+        mrkdwn = rich_text_to_mrkdwn(rich_text['elements'])
         upcoming_events_blocks.append(
             {
                 "type": "section",
