From 82338296214fc1124b3085b47400957135041cf4 Mon Sep 17 00:00:00 2001
From: Bendt <timothy.bendt@corteva.com>
Date: Fri, 19 Dec 2025 16:15:08 -0500
Subject: [PATCH] Add URL compression for mail content viewer

---
 src/mail/config.py                   |   4 ++
 src/mail/widgets/ContentContainer.py | 101 ++++++++++++++++++++++++++-
 2 files changed, 102 insertions(+), 3 deletions(-)

diff --git a/src/mail/config.py b/src/mail/config.py
index d5bcd82..da15e9c 100644
--- a/src/mail/config.py
+++ b/src/mail/config.py
@@ -82,6 +82,10 @@ class ContentDisplayConfig(BaseModel):
     # View mode: "markdown" for pretty rendering, "html" for raw/plain display
     default_view_mode: Literal["markdown", "html"] = "markdown"
 
+    # URL compression: shorten long URLs for better readability
+    compress_urls: bool = True
+    max_url_length: int = 50  # Maximum length before URL is compressed
+
 
 class LinkPanelConfig(BaseModel):
     """Configuration for the link panel."""
diff --git a/src/mail/widgets/ContentContainer.py b/src/mail/widgets/ContentContainer.py
index acb1ff6..7552f4a 100644
--- a/src/mail/widgets/ContentContainer.py
+++ b/src/mail/widgets/ContentContainer.py
@@ -6,10 +6,15 @@ from textual.widgets import Static, Markdown, Label
 from textual.reactive import reactive
 from src.services.himalaya import client as himalaya_client
 from src.mail.config import get_config
-from src.mail.screens.LinkPanel import extract_links_from_content, LinkItem
+from src.mail.screens.LinkPanel import (
+    extract_links_from_content,
+    LinkItem,
+    LinkItem as LinkItemClass,
+)
 import logging
 from datetime import datetime
-from typing import Literal, List
+from typing import Literal, List, Dict
+from urllib.parse import urlparse
 import re
 import os
 import sys
@@ -18,6 +23,88 @@ import sys
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
+def compress_urls_in_content(content: str, max_url_len: int = 50) -> str:
+    """Compress long URLs in markdown/text content for better readability.
+
+    Replaces long URLs with shortened versions using the same algorithm
+    as LinkPanel._shorten_url. Preserves markdown link syntax.
+
+    Args:
+        content: The markdown/text content to process
+        max_url_len: Maximum length for displayed URLs (default 50)
+
+    Returns:
+        Content with compressed URLs
+    """
+
+    # Pattern for markdown links: [text](url)
+    def replace_md_link(match):
+        anchor_text = match.group(1)
+        url = match.group(2)
+
+        # Don't compress if URL is already short
+        if len(url) <= max_url_len:
+            return match.group(0)
+
+        # Use LinkItem's shortening algorithm
+        short_url = LinkItemClass._shorten_url(
+            url,
+            urlparse(url).netloc.replace("www.", ""),
+            urlparse(url).path,
+            max_url_len,
+        )
+
+        # Keep original anchor text, but if it's the same as URL, use short version
+        if anchor_text == url or anchor_text.startswith("http"):
+            return f"[🔗 {short_url}]({url})"
+        else:
+            return match.group(0)  # Keep original if anchor text is meaningful
+
+    # Pattern for bare URLs (not inside markdown links)
+    def replace_bare_url(match):
+        url = match.group(0)
+
+        # Don't compress if URL is already short
+        if len(url) <= max_url_len:
+            return url
+
+        parsed = urlparse(url)
+        short_url = LinkItemClass._shorten_url(
+            url, parsed.netloc.replace("www.", ""), parsed.path, max_url_len
+        )
+
+        # Return as markdown link with icon
+        return f"[🔗 {short_url}]({url})"
+
+    # First, process markdown links
+    md_link_pattern = r"\[([^\]]+)\]\((https?://[^)]+)\)"
+    content = re.sub(md_link_pattern, replace_md_link, content)
+
+    # Then process bare URLs that aren't already in markdown links
+    # This regex matches URLs not preceded by ]( which would indicate markdown link
+    bare_url_pattern = r'(?<!\]\()https?://[^\s<>"\'\)]+[^\s<>"\'\.\,\)\]]'
+
+    # Use a more careful approach to avoid double-processing
+    # Split content, process bare URLs, rejoin
+    result = []
+    last_end = 0
+
+    for match in re.finditer(bare_url_pattern, content):
+        # Check if this URL is inside a markdown link (preceded by "](")
+        prefix_start = max(0, match.start() - 2)
+        prefix = content[prefix_start : match.start()]
+        if prefix.endswith("]("):
+            continue  # Skip URLs that are already markdown link targets
+
+        result.append(content[last_end : match.start()])
+        result.append(replace_bare_url(match))
+        last_end = match.end()
+
+    result.append(content[last_end:])
+
+    return "".join(result)
+
+
 class EnvelopeHeader(Vertical):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
@@ -192,10 +279,18 @@ class ContentContainer(ScrollableContainer):
         # Store the raw content for link extraction
         self.current_content = content
 
+        # Get URL compression settings from config
+        config = get_config()
+        compress_urls = config.content_display.compress_urls
+        max_url_len = config.content_display.max_url_length
+
         try:
             if self.current_mode == "markdown":
                 # For markdown mode, use the Markdown widget
-                self.content.update(content)
+                display_content = content
+                if compress_urls:
+                    display_content = compress_urls_in_content(content, max_url_len)
+                self.content.update(display_content)
             else:
                 # For HTML mode, use the Static widget with markup
                 # First, try to extract the body content if it's HTML