Skip to content

Simplify getting Encoding in TranscriptionOption.FlushContentToDisk #13910

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
rjmholt merged 10 commits into from
Dec 9, 2020
Merged

Simplify getting Encoding in TranscriptionOption.FlushContentToDisk #13910

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
4f8f6c1
Remove Encoding property in TranscriptionOption
Gimly Oct 27, 2020
ca6123d
Simplify Utils.GetEncoding to use StreamReader
Gimly Oct 27, 2020
a5849ea
Catch a more specific exception
Gimly Oct 27, 2020
4390247
Further cleanup and fix PR comment
Gimly Oct 28, 2020
3185744
Implement PR suggestions
Gimly Oct 28, 2020
6c42ba2
There is no need to initialize the variable
Gimly Oct 28, 2020
64c1407
Factor get path encoding
Gimly Nov 10, 2020
6c6bbf4
Moved local function to start of method and PascalCase
Gimly Nov 11, 2020
6c48338
Make GetPathEncoding static and use inline using
Gimly Nov 13, 2020
fe64bf9
Add back missing parameter to GetPathEncoding Path
Gimly Nov 13, 2020
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
85 changes: 0 additions & 85 deletions src/System.Management.Automation/engine/Utils.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1391,96 +1391,11 @@ internal static bool Succeeded(int hresult)
return hresult >= 0;
}

// Attempt to determine the existing encoding
internal static Encoding GetEncoding(string path)
{
if (!File.Exists(path))
{
return ClrFacade.GetDefaultEncoding();
}

byte[] initialBytes = new byte[100];
int bytesRead = 0;

try
{
using (FileStream stream = System.IO.File.OpenRead(path))
{
using (BinaryReader reader = new BinaryReader(stream))
{
bytesRead = reader.Read(initialBytes, 0, 100);
}
}
}
catch (IOException)
{
return ClrFacade.GetDefaultEncoding();
}

// Test for four-byte preambles
string preamble = null;
Encoding foundEncoding = ClrFacade.GetDefaultEncoding();

if (bytesRead > 3)
{
preamble = string.Join("-", initialBytes[0], initialBytes[1], initialBytes[2], initialBytes[3]);

if (encodingMap.TryGetValue(preamble, out foundEncoding))
{
return foundEncoding;
}
}

// Test for three-byte preambles
if (bytesRead > 2)
{
preamble = string.Join("-", initialBytes[0], initialBytes[1], initialBytes[2]);
if (encodingMap.TryGetValue(preamble, out foundEncoding))
{
return foundEncoding;
}
}

// Test for two-byte preambles
if (bytesRead > 1)
{
preamble = string.Join("-", initialBytes[0], initialBytes[1]);
if (encodingMap.TryGetValue(preamble, out foundEncoding))
{
return foundEncoding;
}
}

// Check for binary
string initialBytesAsAscii = System.Text.Encoding.ASCII.GetString(initialBytes, 0, bytesRead);
if (initialBytesAsAscii.IndexOfAny(nonPrintableCharacters) >= 0)
{
return Encoding.Unicode;
}

return utf8NoBom;
}

// BigEndianUTF32 encoding is possible, but requires creation
internal static readonly Encoding BigEndianUTF32Encoding = new UTF32Encoding(bigEndian: true, byteOrderMark: true);
// [System.Text.Encoding]::GetEncodings() | Where-Object { $_.GetEncoding().GetPreamble() } |
// Add-Member ScriptProperty Preamble { $this.GetEncoding().GetPreamble() -join "-" } -PassThru |
// Format-Table -Auto
internal static readonly Dictionary<string, Encoding> encodingMap =
new Dictionary<string, Encoding>()
{
{ "255-254", Encoding.Unicode },
{ "254-255", Encoding.BigEndianUnicode },
{ "255-254-0-0", Encoding.UTF32 },
{ "0-0-254-255", BigEndianUTF32Encoding },
{ "239-187-191", Encoding.UTF8 },
};

internal static readonly char[] nonPrintableCharacters = {
(char) 0, (char) 1, (char) 2, (char) 3, (char) 4, (char) 5, (char) 6, (char) 7, (char) 8,
(char) 11, (char) 12, (char) 14, (char) 15, (char) 16, (char) 17, (char) 18, (char) 19, (char) 20,
(char) 21, (char) 22, (char) 23, (char) 24, (char) 25, (char) 26, (char) 28, (char) 29, (char) 30,
(char) 31, (char) 127, (char) 129, (char) 141, (char) 143, (char) 144, (char) 157 };

internal static readonly UTF8Encoding utf8NoBom =
new UTF8Encoding(encoderShouldEmitUTF8Identifier: false);
Expand Down
37 changes: 12 additions & 25 deletions src/System.Management.Automation/engine/hostifaces/MshHostUserInterface.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1068,22 +1068,7 @@ internal TranscriptionOption()
/// <summary>
/// The path that this transcript is being logged to.
/// </summary>
internal string Path
{
get
{
return _path;
}

set
{
_path = value;
// Get the encoding from the file, or default (UTF8-NoBom)
Encoding = Utils.GetEncoding(value);
}
}

private string _path;
internal string Path { get; set; }

/// <summary>
/// Any output to log for this transcript.
Expand All @@ -1101,19 +1086,20 @@ internal string Path
/// </summary>
internal bool IncludeInvocationHeader { get; set; }

/// <summary>
/// The encoding of this transcript, so that appending to it
/// can be done correctly.
/// </summary>
internal Encoding Encoding { get; private set; }

/// <summary>
/// Logs buffered content to disk. We use this instead of File.AppendAllLines
/// so that we don't need to pay seek penalties all the time, and so that we
/// don't need append permission to our own files.
/// </summary>
internal void FlushContentToDisk()
{
static Encoding GetPathEncoding(string path)
{
using StreamReader reader = new StreamReader(path, Utils.utf8NoBom, detectEncodingFromByteOrderMarks: true);
_ = reader.Read();
return reader.CurrentEncoding;
}

lock (OutputBeingLogged)
{
if (!_disposed)
Expand All @@ -1122,11 +1108,13 @@ internal void FlushContentToDisk()
{
try
{
var currentEncoding = GetPathEncoding(this.Path);

// Try to first open the file with permissions that will allow us to read from it
// later.
_contentWriter = new StreamWriter(
new FileStream(this.Path, FileMode.OpenOrCreate, FileAccess.ReadWrite, FileShare.Read),
this.Encoding);
currentEncoding);
_contentWriter.BaseStream.Seek(0, SeekOrigin.End);
}
catch (IOException)
Expand All @@ -1135,7 +1123,7 @@ internal void FlushContentToDisk()
// file permissions.
_contentWriter = new StreamWriter(
new FileStream(this.Path, FileMode.Append, FileAccess.Write, FileShare.Read),
this.Encoding);
Utils.utf8NoBom);
}

_contentWriter.AutoFlush = true;
Expand Down Expand Up @@ -1332,4 +1320,3 @@ internal static int DetermineChoicePicked(string response, Collection<ChoiceDesc
}
}
}