Skip to content

Correctly handle Unicode strings #255

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
merged 9 commits into from
Jul 21, 2018
Merged

Correctly handle Unicode strings #255

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
53673f7
Split out string conversion from ZipConstants to ZipStrings
piksel Jul 20, 2018
feff09b
Switch ZipOutputStream to using ZipStrings
piksel Jul 20, 2018
27ae713
Add ZipConstants wrappers for backwards compability
piksel Jul 20, 2018
3c60807
Set IsUnicodeText based upon ZipStrings default code page
piksel Jul 20, 2018
8f547a0
Update tests
piksel Jul 20, 2018
c739673
Update string transcoding to handle DefaultCodePage not Unicode
piksel Jul 20, 2018
b818af3
Rename ZipStrings.DefaultCodePage to ZipStrings.CodePage
piksel Jul 21, 2018
48a6bd7
Add testing utility functions
piksel Jul 21, 2018
61b2cc4
Update tests for string coding
piksel Jul 21, 2018
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
165 changes: 24 additions & 141 deletions src/ICSharpCode.SharpZipLib/Zip/ZipConstants.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,7 +202,7 @@ public enum GeneralBitFlags
/// <summary>
/// This class contains constants used for Zip format files
/// </summary>
public sealed class ZipConstants
public static class ZipConstants
{
#region Versions
/// <summary>
Expand Down Expand Up @@ -421,166 +421,49 @@ public sealed class ZipConstants
public const int ENDSIG = 'P' | ('K' << 8) | (5 << 16) | (6 << 24);
#endregion

/// <remarks>
/// The original Zip specification (https://pkware.cachefly.net/webdocs/casestudies/APPNOTE.TXT) states
/// that file names should only be encoded with IBM Code Page 437 or UTF-8.
/// In practice, most zip apps use OEM or system encoding (typically cp437 on Windows).
/// Let's be good citizens and default to UTF-8 http://utf8everywhere.org/
/// </remarks>
static int defaultCodePage = Encoding.UTF8.CodePage;

/// <summary>
/// Default encoding used for string conversion. 0 gives the default system OEM code page.
/// Using the default code page isnt the full solution neccessarily
/// there are many variable factors, codepage 850 is often a good choice for
/// European users, however be careful about compatability.
/// </summary>
public static int DefaultCodePage {
get {
return defaultCodePage;
}
set {
if ((value < 0) || (value > 65535) ||
(value == 1) || (value == 2) || (value == 3) || (value == 42)) {
throw new ArgumentOutOfRangeException(nameof(value));
}

defaultCodePage = value;
}
[Obsolete("Use ZipStrings instead")]
public static int DefaultCodePage
{
get => ZipStrings.CodePage;
set => ZipStrings.CodePage = value;
}

/// <summary>
/// Convert a portion of a byte array to a string.
/// </summary>
/// <param name="data">
/// Data to convert to string
/// </param>
/// <param name="count">
/// Number of bytes to convert starting from index 0
/// </param>
/// <returns>
/// data[0]..data[count - 1] converted to a string
/// </returns>
/// <summary> Depracated wrapper for <see cref="ZipStrings.ConvertToString(byte[], int)"/></summary>
[Obsolete("Use ZipStrings.ConvertToString instead")]
public static string ConvertToString(byte[] data, int count)
{
if (data == null) {
return string.Empty;
}

return Encoding.GetEncoding(DefaultCodePage).GetString(data, 0, count);
}
=> ZipStrings.ConvertToString(data, count);

/// <summary>
/// Convert a byte array to string
/// </summary>
/// <param name="data">
/// Byte array to convert
/// </param>
/// <returns>
/// <paramref name="data">data</paramref>converted to a string
/// </returns>
/// <summary> Depracated wrapper for <see cref="ZipStrings.ConvertToString(byte[])"/></summary>
[Obsolete("Use ZipStrings.ConvertToString instead")]
public static string ConvertToString(byte[] data)
{
if (data == null) {
return string.Empty;
}
return ConvertToString(data, data.Length);
}
=> ZipStrings.ConvertToString(data);

/// <summary>
/// Convert a byte array to string
/// </summary>
/// <param name="flags">The applicable general purpose bits flags</param>
/// <param name="data">
/// Byte array to convert
/// </param>
/// <param name="count">The number of bytes to convert.</param>
/// <returns>
/// <paramref name="data">data</paramref>converted to a string
/// </returns>
/// <summary> Depracated wrapper for <see cref="ZipStrings.ConvertToStringExt(int, byte[], int)"/></summary>
[Obsolete("Use ZipStrings.ConvertToStringExt instead")]
public static string ConvertToStringExt(int flags, byte[] data, int count)
{
if (data == null) {
return string.Empty;
}

if ((flags & (int)GeneralBitFlags.UnicodeText) != 0) {
return Encoding.UTF8.GetString(data, 0, count);
} else {
return ConvertToString(data, count);
}
}
=> ZipStrings.ConvertToStringExt(flags, data, count);

/// <summary>
/// Convert a byte array to string
/// </summary>
/// <param name="data">
/// Byte array to convert
/// </param>
/// <param name="flags">The applicable general purpose bits flags</param>
/// <returns>
/// <paramref name="data">data</paramref>converted to a string
/// </returns>
/// <summary> Depracated wrapper for <see cref="ZipStrings.ConvertToStringExt(int, byte[])"/></summary>
[Obsolete("Use ZipStrings.ConvertToStringExt instead")]
public static string ConvertToStringExt(int flags, byte[] data)
{
if (data == null) {
return string.Empty;
}

if ((flags & (int)GeneralBitFlags.UnicodeText) != 0) {
return Encoding.UTF8.GetString(data, 0, data.Length);
} else {
return ConvertToString(data, data.Length);
}
}
=> ZipStrings.ConvertToStringExt(flags, data);

/// <summary>
/// Convert a string to a byte array
/// </summary>
/// <param name="str">
/// String to convert to an array
/// </param>
/// <returns>Converted array</returns>
/// <summary> Depracated wrapper for <see cref="ZipStrings.ConvertToArray(string)"/></summary>
[Obsolete("Use ZipStrings.ConvertToArray instead")]
public static byte[] ConvertToArray(string str)
{
if (str == null) {
return new byte[0];
}
=> ZipStrings.ConvertToArray(str);

return Encoding.GetEncoding(DefaultCodePage).GetBytes(str);
}

/// <summary>
/// Convert a string to a byte array
/// </summary>
/// <param name="flags">The applicable <see cref="GeneralBitFlags">general purpose bits flags</see></param>
/// <param name="str">
/// String to convert to an array
/// </param>
/// <returns>Converted array</returns>
/// <summary> Depracated wrapper for <see cref="ZipStrings.ConvertToArray(int, string)"/></summary>
[Obsolete("Use ZipStrings.ConvertToArray instead")]
public static byte[] ConvertToArray(int flags, string str)
{
if (str == null) {
return new byte[0];
}

if ((flags & (int)GeneralBitFlags.UnicodeText) != 0) {
return Encoding.UTF8.GetBytes(str);
} else {
return ConvertToArray(str);
}
}
=> ZipStrings.ConvertToArray(flags, str);


/// <summary>
/// Initialise default instance of <see cref="ZipConstants">ZipConstants</see>
/// </summary>
/// <remarks>
/// Private to prevent instances being created.
/// </remarks>
ZipConstants()
{
// Do nothing
}
}
}
2 changes: 2 additions & 0 deletions src/ICSharpCode.SharpZipLib/Zip/ZipEntry.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,6 +191,8 @@ internal ZipEntry(string name, int versionRequiredToExtract, int madeByInfo,
this.versionMadeBy = (ushort)madeByInfo;
this.versionToExtract = (ushort)versionRequiredToExtract;
this.method = method;

IsUnicodeText = ZipStrings.UseUnicode;
}

/// <summary>
Expand Down
7 changes: 3 additions & 4 deletions src/ICSharpCode.SharpZipLib/Zip/ZipEntryFactory.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,27 +59,26 @@ public enum TimeSetting
public ZipEntryFactory()
{
nameTransform_ = new ZipNameTransform();
isUnicodeText_ = ZipStrings.UseUnicode;
}

/// <summary>
/// Initialise a new instance of <see cref="ZipEntryFactory"/> using the specified <see cref="TimeSetting"/>
/// </summary>
/// <param name="timeSetting">The <see cref="TimeSetting">time setting</see> to use when creating <see cref="ZipEntry">Zip entries</see>.</param>
public ZipEntryFactory(TimeSetting timeSetting)
public ZipEntryFactory(TimeSetting timeSetting): this()
{
timeSetting_ = timeSetting;
nameTransform_ = new ZipNameTransform();
}

/// <summary>
/// Initialise a new instance of <see cref="ZipEntryFactory"/> using the specified <see cref="DateTime"/>
/// </summary>
/// <param name="time">The time to set all <see cref="ZipEntry.DateTime"/> values to.</param>
public ZipEntryFactory(DateTime time)
public ZipEntryFactory(DateTime time): this()
{
timeSetting_ = TimeSetting.Fixed;
FixedDateTime = time;
nameTransform_ = new ZipNameTransform();
}

#endregion
Expand Down
8 changes: 4 additions & 4 deletions src/ICSharpCode.SharpZipLib/Zip/ZipOutputStream.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,7 +98,7 @@ public bool IsFinished {
public void SetComment(string comment)
{
// TODO: Its not yet clear how to handle unicode comments here.
byte[] commentBytes = ZipConstants.ConvertToArray(comment);
byte[] commentBytes = ZipStrings.ConvertToArray(comment);
if (commentBytes.Length > 0xffff) {
throw new ArgumentOutOfRangeException(nameof(comment));
}
Expand Down Expand Up @@ -320,7 +320,7 @@ public void PutNextEntry(ZipEntry entry)
}
}

byte[] name = ZipConstants.ConvertToArray(entry.Flags, entry.Name);
byte[] name = ZipStrings.ConvertToArray(entry.Flags, entry.Name);

if (name.Length > 0xFFFF) {
throw new ZipException("Entry name too long.");
Expand Down Expand Up @@ -669,7 +669,7 @@ public override void Finish()
WriteLeInt((int)entry.Size);
}

byte[] name = ZipConstants.ConvertToArray(entry.Flags, entry.Name);
byte[] name = ZipStrings.ConvertToArray(entry.Flags, entry.Name);

if (name.Length > 0xffff) {
throw new ZipException("Name too long.");
Expand Down Expand Up @@ -705,7 +705,7 @@ public override void Finish()

byte[] entryComment =
(entry.Comment != null) ?
ZipConstants.ConvertToArray(entry.Flags, entry.Comment) :
ZipStrings.ConvertToArray(entry.Flags, entry.Comment) :
new byte[0];

if (entryComment.Length > 0xffff) {
Expand Down
Loading