From 85fc3f59f537f260691dc5d0dfcd98daa5c4de7a Mon Sep 17 00:00:00 2001
From: sudo-Harshk <harshk1744@gmail.com>
Date: Mon, 1 Dec 2025 18:21:38 +0530
Subject: [PATCH] fix(stats): implement regex for sentences, lists, and tables

---
 frontend/app.js       | 12 ++++++++++++
 frontend/index.html   | 18 ++++++++++++++++++
 plugins/note_stats.py | 25 ++++++++++++++++++++++++-
 3 files changed, 54 insertions(+), 1 deletion(-)

diff --git a/frontend/app.js b/frontend/app.js
index 2aa75da..e560858 100644
--- a/frontend/app.js
+++ b/frontend/app.js
@@ -2962,6 +2962,15 @@ function noteApp() {
             // Paragraph count
             const paragraphs = content.split('\n\n').filter(p => p.trim()).length;
             
+            // Sentences: punctuation [.!?]+ followed by space or end-of-string
+            const sentences = (content.match(/[.!?]+(?:\s|$)/g) || []).length;
+            
+            // List items: lines starting with -, *, + or a number (e.g. 1., 10.), excluding tasks [-]
+            const listItems = (content.match(/^\s*(?:[-*+]|\d+\.)\s+(?!\[)/gm) || []).length;
+            
+            // Tables: separator rows containing both '|' and '---'
+            const tables = (content.match(/^(?=.*\|)(?=.*---).*$/gm) || []).length;
+            
             // Link count
             const linkMatches = content.match(/\[([^\]]+)\]\(([^\)]+)\)/g) || [];
             const links = linkMatches.length;
@@ -2990,11 +2999,14 @@ function noteApp() {
             
             this.noteStats = {
                 words,
+                sentences,
                 characters: chars,
                 total_characters: totalChars,
                 reading_time_minutes: readingTime,
                 lines,
                 paragraphs,
+                list_items: listItems,
+                tables,
                 links,
                 internal_links: internalLinks,
                 external_links: links - internalLinks,
diff --git a/frontend/index.html b/frontend/index.html
index bf35062..14cedc8 100644
--- a/frontend/index.html
+++ b/frontend/index.html
@@ -1567,6 +1567,24 @@
                                     <div class="font-semibold" style="color: var(--text-primary);" x-text="noteStats ? noteStats.lines.toLocaleString() : '0'"></div>
                                 </div>
                                 
+                                <!-- Sentences -->
+                                <div>
+                                    <div class="text-xs" style="color: var(--text-tertiary);">Sentences</div>
+                                    <div class="font-semibold" style="color: var(--text-primary);" x-text="noteStats ? noteStats.sentences.toLocaleString() : '0'"></div>
+                                </div>
+
+                                <!-- Lists -->
+                                <div>
+                                    <div class="text-xs" style="color: var(--text-tertiary);">Lists</div>
+                                    <div class="font-semibold" style="color: var(--text-primary);" x-text="noteStats ? noteStats.list_items.toLocaleString() : '0'"></div>
+                                </div>
+
+                                <!-- Tables -->
+                                <div>
+                                    <div class="text-xs" style="color: var(--text-tertiary);">Tables</div>
+                                    <div class="font-semibold" style="color: var(--text-primary);" x-text="noteStats ? noteStats.tables.toLocaleString() : '0'"></div>
+                                </div>
+                                
                                 <!-- Links -->
                                 <template x-if="noteStats && noteStats.links > 0">
                                     <div>
diff --git a/plugins/note_stats.py b/plugins/note_stats.py
index bd2fb28..d3972d0 100644
--- a/plugins/note_stats.py
+++ b/plugins/note_stats.py
@@ -40,6 +40,19 @@ class Plugin:
         
         # Paragraph count (blocks separated by blank lines)
         paragraphs = len([p for p in content.split('\n\n') if p.strip()])
+
+        # Sentence count: punctuation [.!?]+ followed by space or end-of-string
+        sentences = len(re.findall(r'[.!?]+(?:\s|$)', content))
+
+        # List items: lines starting with -, *, + or a number (e.g. 1., 10.), excluding tasks [-]
+        list_items = len(
+            re.findall(r'^\s*(?:[-*+]|\d+\.)\s+(?!\[)', content, re.MULTILINE)
+        )
+
+        # Tables: count separator rows containing both '|' and '---'
+        tables = len(
+            re.findall(r'^(?=.*\|)(?=.*---).*$', content, re.MULTILINE)
+        )
         
         # Markdown link count
         links = len(re.findall(r'\[([^\]]+)\]\(([^\)]+)\)', content))
@@ -71,11 +84,14 @@ class Plugin:
         
         return {
             'words': words,
+            'sentences': sentences,
             'characters': chars,
             'total_characters': total_chars,
             'reading_time_minutes': reading_time,
             'lines': lines,
             'paragraphs': paragraphs,
+            'list_items': list_items,
+            'tables': tables,
             'links': links,
             'internal_links': internal_links,
             'external_links': links - internal_links,
@@ -129,7 +145,14 @@ class Plugin:
         
         # Log key statistics
         print(f"📊 {note_path}:")
-        print(f"   {stats['words']:,} words | {stats['reading_time_minutes']}m read | {stats['lines']:,} lines")
+        print(
+            f"   {stats['words']:,} words | "
+            f"{stats['sentences']:,} sentences | "
+            f"{stats['reading_time_minutes']}m read | "
+            f"{stats['lines']:,} lines | "
+            f"{stats['list_items']:,} lists | "
+            f"{stats['tables']:,} tables"
+        )
         
         if stats['links'] > 0:
             print(f"   {stats['links']} links ({stats['internal_links']} internal)")