public Dictionary <string, List <Tuple <string /* pageId */, string /* pageName */> > > GetDuplicatesGroups()
{
if (pageInfos == null)
{
return(null);
}
else
{
Dictionary <string, List <Tuple <string, string> > > duplicatesGroups = new Dictionary <string, List <Tuple <string, string> > >();
foreach (KeyValuePair <string, OneNotePageInfo> elem in pageInfos)
{
string pageId = elem.Key;
OneNotePageInfo pageInfo = elem.Value;
string hashValueForInnerText = pageInfo.HashValueForInnerText;
if (hashValueForInnerText != null)
{
if (duplicatesGroups.ContainsKey(hashValueForInnerText) == false)
{
duplicatesGroups.Add(hashValueForInnerText, new List <Tuple <string, string> >());
}
duplicatesGroups[hashValueForInnerText].Add(Tuple.Create(pageId, pageInfo.PageTitle));
}
}
return(duplicatesGroups);
}
}
private bool TryGetOneNotePageInfos(System.Xml.XmlDocument xmlDocument, out Dictionary <string /*PageId*/, OneNotePageInfo> pageInfos)
{
pageInfos = new Dictionary <string, OneNotePageInfo>();
if (xmlDocument != null)
{
System.Xml.XmlNodeList pageNodeList = xmlDocument.GetElementsByTagName("one:Page");
foreach (System.Xml.XmlNode pageNode in pageNodeList)
{
try
{
string pageUniqueId = pageNode.Attributes["ID"].Value;
string parentNodeName = pageNode.ParentNode.Name;
if (parentNodeName == "one:Section")
{
bool isDeletedPages = CheckIfDeleted(pageNode);
// To avoid the situation that it is going to delete the pages that shouldn't be deleted and to keep the pages in the 'trash' folder.
if (isDeletedPages == false)
{
if (pageInfos.ContainsKey(pageUniqueId) == false)
{
// 'ID', 'path' and 'name' attributes are always existing.
string sectionId = pageNode.ParentNode.Attributes["ID"].Value;
string sectionPath = pageNode.ParentNode.Attributes["path"].Value;
string sectionName = pageNode.ParentNode.Attributes["name"].Value;
OneNotePageInfo pageInfo = new OneNotePageInfo();
pageInfo.ParentSectionId = sectionId;
pageInfo.ParentSectionFilePath = sectionPath;
pageInfo.ParentSectionName = sectionName;
pageInfo.PageName = pageNode.Attributes["name"].Value;
pageInfos.Add(pageUniqueId, pageInfo);
}
}
}
}
catch (System.Exception exception)
{
etc.LoggerHelper.LogWarn("Ignore the exception: {0}", exception.ToString());
}
}
return(true);
}
else
{
etc.LoggerHelper.LogWarn("xmlDocument is null");
return(false);
}
}
private bool TryGetOneNotePageInfos(System.Xml.XmlDocument xmlDocument, out Dictionary<string /*PageId*/, OneNotePageInfo> pageInfos)
{
pageInfos = new Dictionary<string, OneNotePageInfo>();
if (xmlDocument != null)
{
System.Xml.XmlNodeList pageNodeList = xmlDocument.GetElementsByTagName("one:Page");
foreach (System.Xml.XmlNode pageNode in pageNodeList)
{
try
{
string pageUniqueId = pageNode.Attributes["ID"].Value;
string parentNodeName = pageNode.ParentNode.Name;
if (parentNodeName == "one:Section")
{
bool isDeletedPages = CheckIfDeleted(pageNode);
// To avoid the situation that it is going to delete the pages that shouldn't be deleted and to keep the pages in the 'trash' folder.
if (isDeletedPages == false)
{
if (pageInfos.ContainsKey(pageUniqueId) == false)
{
// 'ID', 'path' and 'name' attributes are always existing.
string sectionId = pageNode.ParentNode.Attributes["ID"].Value;
string sectionPath = pageNode.ParentNode.Attributes["path"].Value;
string sectionName = pageNode.ParentNode.Attributes["name"].Value;
OneNotePageInfo pageInfo = new OneNotePageInfo();
pageInfo.ParentSectionId = sectionId;
pageInfo.ParentSectionFilePath = sectionPath;
pageInfo.ParentSectionName = sectionName;
pageInfo.PageName = pageNode.Attributes["name"].Value;
pageInfos.Add(pageUniqueId, pageInfo);
}
}
}
}
catch (System.Exception exception)
{
etc.LoggerHelper.LogWarn("Ignore the exception: {0}", exception.ToString());
}
}
return true;
}
else
{
etc.LoggerHelper.LogWarn("xmlDocument is null");
return false;
}
}
private Tuple <bool, string> UpdatePageInfos()
{
pageInfos = new Dictionary <string, OneNotePageInfo>();
string rawXmlString = "";
if (onenoteApplication.TryGetPageHierarchyAsXML(out rawXmlString) == false)
{
return(Tuple.Create(false, "Unable to retrieve page hierarchy."));
}
etc.LoggerHelper.LogInfo("Retrieved page hierarchy: {0} bytes.", rawXmlString.Length);
System.Xml.XmlDocument hierarchyXml = new System.Xml.XmlDocument();
try
{
hierarchyXml.LoadXml(rawXmlString);
}
catch (System.Exception exception)
{
etc.LoggerHelper.LogUnexpectedException(exception);
return(Tuple.Create(false, "Unable to parse page hierarchy."));
}
System.Xml.XmlNodeList pageNodeList = hierarchyXml.GetElementsByTagName("one:Page");
foreach (System.Xml.XmlNode pageNode in pageNodeList)
{
try
{
string pageUniqueId = pageNode.Attributes["ID"].Value;
string parentNodeName = pageNode.ParentNode.Name;
if (parentNodeName == "one:Section")
{
// We must check whether the pages are deleted. Otherwise, we may end up deleting the duplicates in the trash folder.
if (IsPageDeleted(pageNode) == false)
{
if (pageInfos.ContainsKey(pageUniqueId) == false)
{
// 'ID', 'path' and 'name' attributes always exist.
string sectionId = pageNode.ParentNode.Attributes["ID"].Value;
string sectionPath = pageNode.ParentNode.Attributes["path"].Value;
string sectionName = pageNode.ParentNode.Attributes["name"].Value;
OneNotePageInfo newPageInfo = new OneNotePageInfo();
newPageInfo.ParentSectionId = sectionId;
newPageInfo.ParentSectionFilePath = sectionPath;
newPageInfo.ParentSectionName = sectionName;
newPageInfo.PageTitle = pageNode.Attributes["name"].Value;
pageInfos.Add(pageUniqueId, newPageInfo);
}
else
{
return(Tuple.Create(false, string.Format("The page id ({0}) is not unique.", pageUniqueId)));
}
}
}
}
catch (System.Exception exception)
{
etc.LoggerHelper.LogUnexpectedException(exception);
return(Tuple.Create(false, "The page hierarchy is corrupted."));
}
}
return(Tuple.Create(true, ""));
}
public Tuple <bool, string> ScanOneNotePages(IProgress <Tuple <int, int, int, string> > progress, System.Threading.CancellationToken cancellationToken)
{
Tuple <bool, string> resultUpdatePageInfos = UpdatePageInfos();
if (resultUpdatePageInfos.Item1 == false)
{
return(resultUpdatePageInfos);
}
else
{
etc.LoggerHelper.LogInfo("Found {0} pages.", pageInfos.Count);
int statCountReadSuccess = 0;
int statCountReadFailed = 0;
int statCountTotal = pageInfos.Count;
string statPageTitle = null;
progress.Report(Tuple.Create(statCountReadSuccess, statCountReadFailed, statCountTotal, statPageTitle));
foreach (KeyValuePair <string, OneNotePageInfo> elem in pageInfos)
{
if (cancellationToken.IsCancellationRequested)
{
OnCancelled.Invoke();
break;
}
string pageId = elem.Key;
OneNotePageInfo pageInfo = elem.Value;
string pageContent = "";
bool successHash = false;
pageInfo.HashValueForInnerText = null;
if (onenoteApplication.TryGetPageContent(elem.Key, out pageContent))
{
try
{
System.Xml.XmlDocument pageContentXml = new System.Xml.XmlDocument();
pageContentXml.LoadXml(pageContent);
/*
* Though the page contents are identical, it is quite common to see different 'objectID' and 'lastModified' attributes.
* This difference results in a completely different hash value, which cannot be detected by other duplicate remove software.
* By simply taking 'innerText' of the internal XML-like format, those attributes will be ignored.
* [!] The underlying assumption is that a user cannot modify the attributes directly.
*/
if (TryCalculateHashValue(pageContentXml.InnerText, out string hashValue))
{
successHash = true;
pageInfo.HashValueForInnerText = hashValue;
}
else
{
etc.LoggerHelper.LogWarn("Failed to calculate hash for the page ({0}).", pageId);
}
}
catch (System.Exception exception)
{
etc.LoggerHelper.LogUnexpectedException(exception);
}
}
statPageTitle = pageInfo.PageTitle;
if (successHash)
{
statCountReadSuccess += 1;
}
else
{
statCountReadFailed += 1;
etc.LoggerHelper.LogWarn("Failed to retrieve the content of the page ({0}).", pageId);
}
progress.Report(Tuple.Create(statCountReadSuccess, statCountReadFailed, statCountTotal, statPageTitle));
}
}
return(Tuple.Create(true, ""));
}
