Skip to content

Address UTF-8 Detection In Get-Content -Tail #11899

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
iSazonov merged 4 commits into from
Mar 14, 2020
Merged

Address UTF-8 Detection In Get-Content -Tail #11899

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
378cabd
Address UTF-8 Detection In Get-Content -Tail
NoMoreFood Feb 20, 2020
868a814
Add Additional Explicit Encodings For Get-Content -Tail Tests
NoMoreFood Feb 21, 2020
bfdda8e
Add Multi-Byte Unicode Tail Character Tests
NoMoreFood Feb 21, 2020
6c62890
Remove BigEndianUnicode Reference In Comment
NoMoreFood Mar 14, 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
10 changes: 4 additions & 6 deletions src/System.Management.Automation/namespaces/FileSystemContentStream.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1434,7 +1434,7 @@ private int RefillByteBuff()
int toRead = lengthLeft > BuffSize ? BuffSize : (int)lengthLeft;
_stream.Seek(-toRead, SeekOrigin.Current);

if (_currentEncoding.Equals(Encoding.UTF8))
if (_currentEncoding is UTF8Encoding)
{
// It's UTF-8, we need to detect the starting byte of a character
do
Expand All @@ -1460,14 +1460,12 @@ private int RefillByteBuff()
_byteCount += _stream.Read(_byteBuff, _byteCount, (int)(lengthLeft - _stream.Position));
_stream.Position = _currentPosition;
}
else if (_currentEncoding.Equals(Encoding.Unicode) ||
_currentEncoding.Equals(Encoding.BigEndianUnicode) ||
_currentEncoding.Equals(Encoding.UTF32) ||
_currentEncoding.Equals(Encoding.ASCII) ||
else if (_currentEncoding is UnicodeEncoding ||
_currentEncoding is UTF32Encoding ||
_currentEncoding is ASCIIEncoding ||
IsSingleByteCharacterSet())
{
// Unicode -- two bytes per character
// BigEndianUnicode -- two types per character
// UTF-32 -- four bytes per character
// ASCII -- one byte per character
// The BufferSize will be a multiple of 4, so we can just read toRead number of bytes
Expand Down
47 changes: 28 additions & 19 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 @@ -93,35 +93,44 @@ Describe "Get-Content" -Tags "CI" {
{ Get-Content -Path Variable:\PSHOME -Tail 1 -TotalCount 5 -ErrorAction Stop} | Should -Throw -ErrorId 'TailAndHeadCannotCoexist,Microsoft.PowerShell.Commands.GetContentCommand'
}

It 'Verifies -Tail with content that uses an explicit encoding' -TestCases @(
It 'Verifies -Tail with content that uses an explicit/implicit encoding' -TestCases @(
@{EncodingName = 'String'},
@{EncodingName = 'OEM'},
@{EncodingName = 'Unicode'},
@{EncodingName = 'BigEndianUnicode'},
@{EncodingName = 'UTF8'},
@{EncodingName = 'UTF8BOM'},
@{EncodingName = 'UTF8NoBOM'},
@{EncodingName = 'UTF7'},
@{EncodingName = 'UTF32'},
@{EncodingName = 'Ascii'}
){
param($EncodingName)

$content = @"
one
two
foo
bar
baz
"@
$expected = 'foo'
$tailCount = 3

$testPath = Join-Path -Path $TestDrive -ChildPath 'TailWithEncoding.txt'
$content | Set-Content -Path $testPath -Encoding $encodingName
$expected = 'foo'

$actual = Get-Content -Path $testPath -Tail $tailCount -Encoding $encodingName
$actual | Should -BeOfType string
$actual.Length | Should -Be $tailCount
$actual[0] | Should -BeExactly $expected
$contentSets =
@(@('a1','aa2','aaa3','aaaa4','aaaaa5'), # utf-8
@('€1','€€2','€€€3','€€€€4','€€€€€5'), # utf-16
@('𐍈1','𐍈𐍈2','𐍈𐍈𐍈3','𐍈𐍈𐍈𐍈4','𐍈𐍈𐍈𐍈𐍈5')) # utf-32
ForEach ($content in $contentSets)
{
$tailCount = 3
$testPath = Join-Path -Path $TestDrive -ChildPath 'TailWithEncoding.txt'
$content | Set-Content -Path $testPath -Encoding $EncodingName

# read and verify using explicit encoding
$expected = (Get-Content -Path $testPath -Encoding $EncodingName)[-$tailCount]
$actual = Get-Content -Path $testPath -Tail $tailCount -Encoding $EncodingName
$actual | Should -BeOfType string
$actual.Length | Should -Be $tailCount
$actual[0] | Should -BeExactly $expected

# read and verify using implicit encoding
$expected = (Get-Content -Path $testPath)[-$tailCount]
$actual = Get-Content -Path $testPath -Tail $tailCount
$actual | Should -BeOfType string
$actual.Length | Should -Be $tailCount
$actual[0] | Should -BeExactly $expected
}
}

It "should Get-Content with a variety of -Tail and -ReadCount: <test>" -TestCases @(
Expand Down