Lokasi ngalangkungan proxy:   [ UP ]  
[Ngawartoskeun bug]   [Panyetelan cookie]                
Skip to content

Pull request to bug on parser to emails 8bit/utf-8/flowed #24

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
reinaldocoelho merged 2 commits into from
Apr 12, 2017
Merged

Pull request to bug on parser to emails 8bit/utf-8/flowed #24

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dfea1c5
Add fail unit test to e-mail 8bit utf8 flowed with crushed chars.
reinaldocoelho Apr 12, 2017
1a40492
Adding bugfix to parse 8Bit Utf-8 Flowed messages.
reinaldocoelho Apr 12, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 32 additions & 21 deletions Class Library/ActiveUp.Net.Common/Parser.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,48 +117,56 @@ private static ContentType GetContentType(string input)
/// <returns></returns>
private static ContentDisposition GetContentDisposition(string input)
{
ContentDisposition field = new ContentDisposition();
//TODO: include TAB detection in Regex
field.Disposition = Regex.Match(input.Replace("\t", ""), @"(?<=: ?)\S+?(?=([;\s]|\Z))").Value;
var field = new ContentDisposition
{
//TODO: include TAB detection in Regex
Disposition = Regex.Match(input.Replace("\t", ""), @"(?<=: ?)\S+?(?=([;\s]|\Z))").Value
};
//TODO: include TAB detection in Regex
Match parammatch = Regex.Match(input.Replace("\t", ""), @"(?<=;[ \t]?)[^;]*=[^;]*(?=(;|\Z))");
for (; parammatch.Success; parammatch = parammatch.NextMatch()) field.Parameters.Add(FormatFieldName(parammatch.Value.Substring(0, parammatch.Value.IndexOf('='))), parammatch.Value.Substring(parammatch.Value.IndexOf('=') + 1).Replace("\"", "").Trim('\r', '\n'));
return field;
}

[Obsolete("We are migrating ASCII default char structure to UTF8, please, use GetUtf8ByteCountOfPart() as a default.")]
private static int GetASCIIByteCountOfPart(string part)
{
return Encoding.ASCII.GetByteCount(part);
}

private static int GetUtf8ByteCountOfPart(string part)
{
return Encoding.UTF8.GetByteCount(part);
}

/// <summary>
/// Parses the sub parts.
/// </summary>
/// <param name="part">The part.</param>
private static void ParseSubParts(ref MimePart part, Message message)
{
string boundary = part.ContentType.Parameters["boundary"];
string parentPartAsciiBody = ToUtf8(part.BinaryContent);
string parentPartUtf8Body = ToUtf8(part.BinaryContent);
byte[] parentPartBinary = part.BinaryContent;

Logger.AddEntry(typeof(Parser), "boundary : " + boundary);
string[] arrpart = Regex.Split(parentPartAsciiBody, @"\r?\n?" + Regex.Escape("--" + boundary));
string[] arrpart = Regex.Split(parentPartUtf8Body, @"\r?\n?" + Regex.Escape("--" + boundary));

foreach (var strpart in arrpart)
{
if (string.IsNullOrWhiteSpace(strpart))
continue;

int bounaryByteLen = GetASCIIByteCountOfPart(parentPartAsciiBody.Substring(0, parentPartAsciiBody.IndexOf(strpart)));
int binaryPartLen = bounaryByteLen + GetASCIIByteCountOfPart(strpart);
parentPartAsciiBody = null;
int bounaryByteLen = GetUtf8ByteCountOfPart(parentPartUtf8Body.Substring(0, parentPartUtf8Body.IndexOf(strpart)));
int binaryPartLen = bounaryByteLen + GetUtf8ByteCountOfPart(strpart);
parentPartUtf8Body = null;

//complete Part (incl. boundary)
byte[] binaryPart = new byte[binaryPartLen];
Array.Copy(parentPartBinary, binaryPart, binaryPart.Length);

//Body only (without Boundary)
byte[] binaryBody = new byte[GetASCIIByteCountOfPart(strpart)];
byte[] binaryBody = new byte[GetUtf8ByteCountOfPart(strpart)];
Array.Copy(binaryPart, bounaryByteLen, binaryBody, 0, binaryBody.Length);

//Remove Subpart from ParentPart
Expand All @@ -171,7 +179,7 @@ private static void ParseSubParts(ref MimePart part, Message message)
GC.WaitForPendingFinalizers();

parentPartBinary = tmp;
parentPartAsciiBody = ToUtf8(parentPartBinary);
parentPartUtf8Body = ToUtf8(parentPartBinary);
tmp = null;

if (!strpart.StartsWith("--") && !string.IsNullOrEmpty(strpart))
Expand Down Expand Up @@ -497,7 +505,7 @@ private static void ParseBody(byte[] binaryData, MimePart part, int bodyStart)
{
if (bodyStart < part.OriginalContent.Length)
{
string body = part.OriginalContent.Substring(bodyStart);
var body = part.OriginalContent.Substring(bodyStart);
part.BinaryContent = GetBinaryPart(binaryData, body);
}
}
Expand All @@ -506,23 +514,26 @@ private static void ParseBody(byte[] binaryData, MimePart part, int bodyStart)
/// Parses the MIME part.
/// </summary>
/// <param name="binaryData">The data.</param>
/// <param name="message">Message object to update</param>
/// <returns></returns>
public static MimePart ParseMimePart(byte[] binaryData, Message message)
{
MimePart part = new MimePart();
part.ParentMessage = message;
part.OriginalContent = ToUtf8(binaryData); //ASCII content for header parsing
var part = new MimePart
{
ParentMessage = message,
OriginalContent = ToUtf8(binaryData) //UTF8 content for header parsing
};

try
{
// Separate header and body.
int headerEnd = Regex.Match(part.OriginalContent, @".(?=\r?\n\r?\n)").Index + 1;
int bodyStart = Regex.Match(part.OriginalContent, @"(?<=\r?\n\r?\n).").Index;
var headerEnd = Regex.Match(part.OriginalContent, @".(?=\r?\n\r?\n)").Index + 1;
var bodyStart = Regex.Match(part.OriginalContent, @"(?<=\r?\n\r?\n).").Index;

//TODO: remove this workaround
if (bodyStart == 0)
{
int indexBody = part.OriginalContent.IndexOf("\r\n\r\n");
var indexBody = part.OriginalContent.IndexOf("\r\n\r\n");
if (indexBody > 0)
bodyStart = indexBody;
}
Expand All @@ -533,12 +544,12 @@ public static MimePart ParseMimePart(byte[] binaryData, Message message)

// Build the part tree.
// This is a container part.
if (part.ContentType.Type.ToLower().Equals("multipart"))
if (part.ContentType.Type.ToLower().Trim().Equals("multipart"))
{
ParseSubParts(ref part, message);
}
// This is a nested message.
else if (part.ContentType.Type.ToLower().Equals("message"))
else if (part.ContentType.Type.ToLower().Trim().Equals("message"))
{
// TODO: Create an interpreter to this.
}
Expand All @@ -560,9 +571,9 @@ public static MimePart ParseMimePart(byte[] binaryData, Message message)
}


private static byte[] GetBinaryPart(byte[] srcData, string asciiPart)
private static byte[] GetBinaryPart(byte[] srcData, string utf8Part)
{
byte[] result = new byte[GetASCIIByteCountOfPart(asciiPart)];
var result = new byte[GetUtf8ByteCountOfPart(utf8Part)];
Array.Copy(srcData, (srcData.Length - result.Length), result, 0, result.Length);

return result;
Expand Down
3 changes: 3 additions & 0 deletions Class Library/ActiveUp.Net.Tests/ActiveUp.Net.Tests.csproj
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,6 +102,9 @@
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</Content>
<None Include="packages.config" />
<None Include="resource\content-transfer-encode-8bit-utf8-flowed.eml">
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
</None>
<None Include="resource\confirm_read_parse_problem.eml">
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
</None>
Expand Down
15 changes: 14 additions & 1 deletion Class Library/ActiveUp.Net.Tests/Common/ParserTests.cs
View file
Open in desktop

Large diffs are not rendered by default.

Loading