Smart scan of new notebooks

#1606

OneMore/Commands/Tagging/HashtagDialog.cs

@@ -50,6 +50,7 @@ public HashtagDialog()
 					"checkAllLink",
 					"uncheckAllLink",
 					"scanButton",
+					"scanLink",
 					"scheduleButton",
 					"indexButton=word_Index",
 					"moveButton=word_Move",
@@ -79,7 +80,11 @@ public HashtagDialog()
 			experimental = new SettingsProvider()
 				.GetCollection("GeneralSheet").Get<bool>("experimental");
 
+			scanLink.Left = lastScanLabel.Left;
+			scanLink.Visible = false;
+
 			ShowScanTimes();
+			CheckForNewNotebooks();
 
 			ShowOfflineNotebooks = new SettingsProvider()
 				.GetCollection(SettingsKey)
@@ -98,6 +103,30 @@ public HashtagDialog()
 		public bool ShowOfflineNotebooks { get; private set; }
 
 
+		private void CheckForNewNotebooks()
+		{
+			Task.Run(async () =>
+			{
+				await using var one = new OneNote();
+				var books = await one.GetNotebooks();
+				var ns = books.GetNamespaceOfPrefix(OneNote.Prefix);
+
+				var bookIDs = books.Elements(ns + "Notebook")
+					.Where(e => e.Attribute("isRecycleBin") is null)
+					.Select(e => e.Attribute("ID").Value);
+
+				var provider = new HashtagProvider();
+				var known = provider.ReadKnownNotebooks();
+
+				if (bookIDs.Any(e => !known.Contains(e)))
+				{
+					lastScanLabel.Visible = false;
+					scanLink.Visible = true;
+				}
+			});
+		}
+
+
 		private void ShowScanTimes()
 		{
 			var scan = new HashtagProvider().ReadScanTime();
@@ -291,6 +320,12 @@ private void DoScheduleScan(object sender, EventArgs e)
 		}
 
 
+		private void ScanDiscovered(object sender, LinkLabelLinkClickedEventArgs e)
+		{
+			DoScheduleScan(sender, e);
+		}
+
+
 		private void Control_Checked(object sender, EventArgs e)
 		{
 			var control = sender as HashtagContextControl;

OneMore/Commands/Tagging/HashtagNotebook.cs

@@ -35,5 +35,11 @@ internal class HashtagNotebook
 	/// <summary>
 	/// A collection of HashtagNotebooks
 	/// </summary>
-	internal class HashtagNotebooks : List<HashtagNotebook> { }
+	internal class HashtagNotebooks : List<HashtagNotebook>
+	{
+		public bool Contains(string notebookID)
+		{
+			return Find(e => e.NotebookID == notebookID) is not null;
+		}
+	}
 }

OneMore/Commands/Tagging/HashtagScanner.cs

@@ -33,6 +33,7 @@ public class Statistics
 		}
 
 		public const int DefaultThrottle = 40;
+		private const int MaxPagesThreshold = 100;
 
 		private readonly string lastTime;
 		private readonly HashtagPageSannerFactory factory;
@@ -171,24 +172,51 @@ public async Task Scan()
 
 					var known = knownNotebooks.Find(n => n.NotebookID == notebookID);
 
-					// Filter on two levels...
+					// Filter on three levels...
 					//
 					// knownNotebooks
 					//   If knownNotebooks is empty, then we assume that this is the first scan
-					//   and will allow all; otherwise we only scan known notebooks to avoid
-					//   pulling in large data from newly added notebooks - user must schedule
-					//   a scan to pull in those new notebooks explicitly.
+					//   and will allow all; otherwise only scan known notebooks, also include
+					//   newly added notebooks that are below the size threshold to avoid causing
+					//   OneNote to behave sluggishly - user must schedule a scan to pull in those
+					//   new notebooks explicitly.
 					//
 					// notebookFilters
 					//   If notebookFilters is empty then allow any notebook that has passed the
 					//   knownNotebook test; otherwise, the user has explicitly requested a scan
-					//   of notebooks specified in the notebookFilters list.
+					//   of notebooks specified in the notebookFilters list or the notebook is
+					//   within the size threshold.
 					//
+					// size
+					//   If there are known notebooks, yet this notebook is not one of them, and
+					//   not filtered, then check the size of the new notebook; if below the set
+					//   threshold then scanit, otherwise user must schedule explicitly.
+					//
+
+					// known is empty so accept any and all
+					var accepted = knownNotebooks.Count == 0;
+					if (!accepted)
+					{
+						if (notebookFilters is null)
+						{
+							// known notebook so accept it
+							accepted = known is not null;
+							if (!accepted)
+							{
+								// notebook size is within threshold?
+								// this may load the notebook twice, but small cost
+								var populated = await one.GetNotebook(notebookID, OneNote.Scope.Pages);
+								accepted = populated.Descendants(ns + "Page")
+									.Count(e => e.Attribute("isInRecycleBin") is null) < MaxPagesThreshold;
+							}
+						}
+						else
+						{
+							accepted = notebookFilters.Contains(notebookID);
+						}
+					}
 
-					if (knownNotebooks.Count == 0 ||
-						(notebookFilters is null
-							? known is not null
-							: notebookFilters.Contains(notebookID)))
+					if (accepted)
 					{
 						//logger.Verbose($"scanning notebook {notebookID} \"{name}\"");
 
@@ -233,7 +261,8 @@ public async Task Scan()
 			int totalPages = 0;
 			var ns = one.GetNamespace(parent);
 
-			var sectionRefs = parent.Elements(ns + "Section")
+			// Descendants allows diving into SectionGroups
+			var sectionRefs = parent.Descendants(ns + "Section")
 				.Where(e =>
 					e.Attribute("isRecycleBin") is null &&
 					e.Attribute("isInRecycleBin") is null &&

OneMore/Commands/Tagging/HashtagService.cs

@@ -123,7 +123,6 @@ protected virtual async Task StartupLoop()
 			{
 				try
 				{
-					logger.Debug("StartupLoop() Scan()");
 					await Scan();
 
 					errors = 0;

OneMore/Properties/Resources.ar-SA.resx

@@ -1331,6 +1331,10 @@
     <value>إفحص الآن</value>
     <comment>menu button</comment>
   </data>
+  <data name="HashtagDialog_scanLink.Text" xml:space="preserve">
+    <value>تم اكتشاف دفاتر ملاحظات جديدة. انقر هنا للمسح الضوئي.</value>
+    <comment>link label</comment>
+  </data>
   <data name="HashtagDialog_scheduleButton.Text" xml:space="preserve">
     <value>جدولة المسح</value>
     <comment>menu item</comment>

OneMore/Properties/Resources.de-DE.resx

@@ -1329,6 +1329,10 @@ Die Suche nach Hashtags ist erst möglich, wenn dies abgeschlossen ist.</value>
     <value>Scanne jetzt</value>
     <comment>menu button</comment>
   </data>
+  <data name="HashtagDialog_scanLink.Text" xml:space="preserve">
+    <value>Neue Notizbücher entdeckt. Klicken Sie hier, um zu scannen.</value>
+    <comment>link label</comment>
+  </data>
   <data name="HashtagDialog_scheduleButton.Text" xml:space="preserve">
     <value>Planen Sie den Scan</value>
     <comment>menu item</comment>

OneMore/Properties/Resources.es-ES.resx

@@ -1331,6 +1331,10 @@ La búsqueda de hashtags no estará disponible hasta que se complete.</value>
     <value>Escanear ahora</value>
     <comment>menu button</comment>
   </data>
+  <data name="HashtagDialog_scanLink.Text" xml:space="preserve">
+    <value>Nuevos cuadernos descubiertos. Haga clic aquí para escanear.</value>
+    <comment>link label</comment>
+  </data>
   <data name="HashtagDialog_scheduleButton.Text" xml:space="preserve">
     <value>Programar escaneo</value>
     <comment>menu item</comment>

OneMore/Properties/Resources.fr-FR.resx

@@ -1331,6 +1331,10 @@ La recherche de hashtags n'est pas disponible tant qu'elle n'est pas terminée.<
     <value>Scanne maintenant</value>
     <comment>menu button</comment>
   </data>
+  <data name="HashtagDialog_scanLink.Text" xml:space="preserve">
+    <value>Nouveaux cahiers découverts. Cliquez ici pour numériser.</value>
+    <comment>link label</comment>
+  </data>
   <data name="HashtagDialog_scheduleButton.Text" xml:space="preserve">
     <value>Planifier une analyse</value>
     <comment>menu item</comment>

OneMore/Properties/Resources.he-IL.resx

@@ -1332,6 +1332,10 @@ Total Row Font
     <value>לסרוק עכשיו</value>
     <comment>menu button</comment>
   </data>
+  <data name="HashtagDialog_scanLink.Text" xml:space="preserve">
+    <value>התגלו מחברות חדשות. לחץ כאן לסריקה.</value>
+    <comment>link label</comment>
+  </data>
   <data name="HashtagDialog_scheduleButton.Text" xml:space="preserve">
     <value>תזמון סריקה</value>
     <comment>menu item</comment>

OneMore/Properties/Resources.ja-JP.resx

@@ -1334,6 +1334,10 @@ OneNoteファイル (*.one)</value>
     <value>今すぐスキャン</value>
     <comment>menu button</comment>
   </data>
+  <data name="HashtagDialog_scanLink.Text" xml:space="preserve">
+    <value>新しいノート発見。スキャンするにはここをクリックしてください。</value>
+    <comment>link label</comment>
+  </data>
   <data name="HashtagDialog_scheduleButton.Text" xml:space="preserve">
     <value>スキャンをスケジュール</value>
     <comment>menu item</comment>

OneMore/Properties/Resources.nl-NL.resx

@@ -1332,6 +1332,10 @@ Zoeken naar hashtags is pas beschikbaar als dit is voltooid.</value>
     <value>Scan nu</value>
     <comment>menu button</comment>
   </data>
+  <data name="HashtagDialog_scanLink.Text" xml:space="preserve">
+    <value>Nieuwe notitieboekjes ontdekt. Klik hier om te scannen.</value>
+    <comment>link label</comment>
+  </data>
   <data name="HashtagDialog_scheduleButton.Text" xml:space="preserve">
     <value>Plan scannen</value>
     <comment>menu item</comment>

OneMore/Properties/Resources.pl-PL.resx

@@ -1332,6 +1332,10 @@ Wyszukiwanie hashtagów nie jest możliwe, dopóki nie zostanie zakończone.</va
     <value>Skanuj teraz</value>
     <comment>menu button</comment>
   </data>
+  <data name="HashtagDialog_scanLink.Text" xml:space="preserve">
+    <value>Odkryto nowe notesy. Kliknij tutaj, aby zeskanować.</value>
+    <comment>link label</comment>
+  </data>
   <data name="HashtagDialog_scheduleButton.Text" xml:space="preserve">
     <value>Zaplanuj skanowanie</value>
     <comment>menu item</comment>

OneMore/Properties/Resources.pt-BR.resx

@@ -1332,6 +1332,10 @@ A pesquisa de hashtags não estará disponível até que isso seja concluído.</
     <value>Escaneie agora</value>
     <comment>menu button</comment>
   </data>
+  <data name="HashtagDialog_scanLink.Text" xml:space="preserve">
+    <value>Novos cadernos descobertos. Clique aqui para digitalizar.</value>
+    <comment>link label</comment>
+  </data>
   <data name="HashtagDialog_scheduleButton.Text" xml:space="preserve">
     <value>Agendar verificação</value>
     <comment>menu item</comment>

OneMore/Properties/Resources.resx

@@ -1332,6 +1332,10 @@ Searching for hashtags is unavailable until this is completed.</value>
     <value>Scan Now</value>
     <comment>menu button</comment>
   </data>
+  <data name="HashtagDialog_scanLink.Text" xml:space="preserve">
+    <value>New notebooks discovered. Click here to scan.</value>
+    <comment>link label</comment>
+  </data>
   <data name="HashtagDialog_scheduleButton.Text" xml:space="preserve">
     <value>Schedule Scan</value>
     <comment>menu item</comment>

OneMore/Properties/Resources.zh-CN.resx

@@ -1330,6 +1330,10 @@ OneNote 文件 (*.one)</value>
     <value>现在扫描</value>
     <comment>menu button</comment>
   </data>
+  <data name="HashtagDialog_scanLink.Text" xml:space="preserve">
+    <value>发现新笔记本。点击这里扫描。</value>
+    <comment>link label</comment>
+  </data>
   <data name="HashtagDialog_scheduleButton.Text" xml:space="preserve">
     <value>安排扫描</value>
     <comment>menu item</comment>