Skip to content

Added Support For Big Endian UTF-32 #11947

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
adityapatwardhan merged 2 commits into from
Apr 7, 2020
Merged

Added Support For Big Endian UTF-32 #11947

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
2dea0d5
Added Support For Big Endian UTF-32
NoMoreFood Feb 25, 2020
774cb48
Added Support For Big Endian UTF-32: Review Changes
NoMoreFood Feb 25, 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
5 changes: 5 additions & 0 deletions src/Microsoft.PowerShell.Commands.Utility/commands/utility/UtilityCommon.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,11 @@ public enum TextEncodingType
/// </summary>
BigEndianUnicode,

/// <summary>
/// Big Endian UTF32 encoding.
/// </summary>
BigEndianUTF32,

/// <summary>
/// UTF8 encoding.
/// </summary>
Expand Down
5 changes: 4 additions & 1 deletion src/System.Management.Automation/utils/EncodingUtils.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@ internal static class EncodingConversion
internal const string String = "string";
internal const string Unicode = "unicode";
internal const string BigEndianUnicode = "bigendianunicode";
internal const string BigEndianUtf32 = "bigendianutf32";
internal const string Ascii = "ascii";
internal const string Utf8 = "utf8";
internal const string Utf8NoBom = "utf8NoBOM";
Expand All @@ -25,13 +26,14 @@ internal static class EncodingConversion
internal const string Default = "default";
internal const string OEM = "oem";
internal static readonly string[] TabCompletionResults = {
Ascii, BigEndianUnicode, OEM, Unicode, Utf7, Utf8, Utf8Bom, Utf8NoBom, Utf32
Ascii, BigEndianUnicode, BigEndianUtf32, OEM, Unicode, Utf7, Utf8, Utf8Bom, Utf8NoBom, Utf32
};

internal static Dictionary<string, Encoding> encodingMap = new Dictionary<string, Encoding>(StringComparer.OrdinalIgnoreCase)
{
{ Ascii, System.Text.Encoding.ASCII },
{ BigEndianUnicode, System.Text.Encoding.BigEndianUnicode },
{ BigEndianUtf32, new UTF32Encoding(bigEndian: true, byteOrderMark: true) },
{ Default, ClrFacade.GetDefaultEncoding() },
{ OEM, ClrFacade.GetOEMEncoding() },
{ Unicode, System.Text.Encoding.Unicode },
Expand Down Expand Up @@ -116,6 +118,7 @@ internal sealed class ArgumentEncodingCompletionsAttribute : ArgumentCompletions
public ArgumentEncodingCompletionsAttribute() : base(
EncodingConversion.Ascii,
EncodingConversion.BigEndianUnicode,
EncodingConversion.BigEndianUtf32,
EncodingConversion.OEM,
EncodingConversion.Unicode,
EncodingConversion.Utf7,
Expand Down
56 changes: 23 additions & 33 deletions test/powershell/Language/Parser/RedirectionOperator.Tests.ps1
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,42 +45,32 @@ Describe "Redirection operator now supports encoding changes" -Tags "CI" {
}
}

# $availableEncodings = "unknown","string","unicode","bigendianunicode","utf8","utf7", "utf32","ascii","default","oem"
$availableEncodings = (Get-Command Out-File).Parameters["Encoding"].Attributes.ValidValues

$availableEncodings =
@([System.Text.Encoding]::ASCII
[System.Text.Encoding]::BigEndianUnicode
[System.Text.UTF32Encoding]::new($true,$true)
[System.Text.Encoding]::Unicode
[System.Text.Encoding]::UTF7
[System.Text.Encoding]::UTF8
[System.Text.Encoding]::UTF32)

foreach($encoding in $availableEncodings) {
$skipTest = $false
if ($encoding -eq "default") {
# [System.Text.Encoding]::Default is exposed by 'System.Private.CoreLib.dll' at
# runtime via reflection. However,it isn't exposed in the reference contract of
# 'System.Text.Encoding', and therefore we cannot use 'Encoding.Default' in our
# code. So we need to skip this encoding in the test.
$skipTest = $true
}

# some of the encodings accepted by Out-File aren't real,
# and Out-File has its own translation, so we'll
# not do that logic here, but simply ignore those encodings
# as they eventually are translated to "real" encoding
$enc = [System.Text.Encoding]::$encoding
if ( $enc )
{
$msg = "Overriding encoding for Out-File is respected for $encoding"
$BOM = $enc.GetPreamble()
$TXT = $enc.GetBytes($asciiString)
$CR = $enc.GetBytes($asciiCR)
$expectedBytes = .{ $BOM; $TXT; $CR }
$PSDefaultParameterValues["Out-File:Encoding"] = "$encoding"
$asciiString > TESTDRIVE:/file.txt
$observedBytes = Get-Content -AsByteStream TESTDRIVE:/file.txt
# THE TEST
It $msg -Skip:$skipTest {
$observedBytes.Count | Should -Be $expectedBytes.Count
for($i = 0;$i -lt $observedBytes.Count; $i++) {
$observedBytes[$i] | Should -Be $expectedBytes[$i]
}
$encodingName = $encoding.EncodingName
$msg = "Overriding encoding for Out-File is respected for $encodingName"
$BOM = $encoding.GetPreamble()
$TXT = $encoding.GetBytes($asciiString)
$CR = $encoding.GetBytes($asciiCR)
$expectedBytes = @( $BOM; $TXT; $CR )
$PSDefaultParameterValues["Out-File:Encoding"] = $encoding
$asciiString > TESTDRIVE:/file.txt
$observedBytes = Get-Content -AsByteStream TESTDRIVE:/file.txt
# THE TEST
It $msg {
$observedBytes.Count | Should -Be $expectedBytes.Count
for($i = 0;$i -lt $observedBytes.Count; $i++) {
$observedBytes[$i] | Should -Be $expectedBytes[$i]
}

}
}
}
Expand Down
1 change: 1 addition & 0 deletions test/powershell/Modules/Microsoft.PowerShell.Management/Get-Content.Tests.ps1
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,6 +97,7 @@ Describe "Get-Content" -Tags "CI" {
@{EncodingName = 'String'},
@{EncodingName = 'Unicode'},
@{EncodingName = 'BigEndianUnicode'},
@{EncodingName = 'BigEndianUTF32'},
@{EncodingName = 'UTF8'},
@{EncodingName = 'UTF7'},
@{EncodingName = 'UTF32'},
Expand Down
7 changes: 7 additions & 0 deletions test/powershell/Modules/Microsoft.PowerShell.Utility/Format-Hex.Tests.ps1
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -432,6 +432,13 @@ public enum TestSByteEnum : sbyte {
Count = 1
ExpectedResult = "0000000000000000 00 68 00 65 00 6C 00 6C 00 6F h e l l o"
}
@{
Name = "Can process BigEndianUTF32 encoding 'fhx -InputObject 'hello' -Encoding BigEndianUTF32'"
Encoding = "BigEndianUTF32"
Count = 2
ExpectedResult = "0000000000000000 00 00 00 68 00 00 00 65 00 00 00 6C 00 00 00 6C h e l l"
ExpectedSecondResult = "0000000000000010 00 00 00 6F o"
}
@{
Name = "Can process Unicode encoding 'fhx -InputObject 'hello' -Encoding Unicode'"
Encoding = "Unicode"
Expand Down