/// <summary>
/// Escape string with backslash sequences (e.g. \r\n -> \\r\\n)
/// </summary>
/// <param name="s">String to escape</param>
/// <param name="stringEscapeOptions">String escape options</param>
/// <param name="charEscapeOptions">Char escape options</param>
/// <param name="addQuotes">Add quotes after escaping</param>
/// <returns>String with escape sequences for string</returns>
/// <exception cref="ArgumentNullException"></exception>
/// <exception cref="ArgumentException"></exception>
public static string Escape(string s, StringEscapeOptions stringEscapeOptions = null, CharEscapeOptions charEscapeOptions = null, bool addQuotes = false)
{
if (s == null)
{
throw new ArgumentNullException(nameof(s));
}
if (stringEscapeOptions == null)
{
stringEscapeOptions = new StringEscapeOptions();
}
if (charEscapeOptions == null)
{
charEscapeOptions = new CharEscapeOptions();
}
switch (charEscapeOptions.EscapeLanguage)
{
case CharEscapeLanguage.CSharp:
return(EscapeCSharp(s, stringEscapeOptions, charEscapeOptions, addQuotes));
case CharEscapeLanguage.FSharp:
return(EscapeFSharp(s, stringEscapeOptions, charEscapeOptions, addQuotes));
case CharEscapeLanguage.PowerShell:
return(EscapePowerShell(s, stringEscapeOptions, charEscapeOptions, addQuotes));
default:
throw new ArgumentException(string.Format("{0} is not a valid {1}.", charEscapeOptions.EscapeLanguage, nameof(charEscapeOptions.EscapeLanguage)), nameof(charEscapeOptions));
}
}
/// <summary>
/// Escape char with backslash sequence (e.g. \n -> \\n)
/// </summary>
/// <param name="c">Char to escape</param>
/// <param name="escapeOptions">Escape options</param>
/// <param name="addQuotes">Add quotes after escaping</param>
/// <returns>String with escape sequence for char</returns>
/// <exception cref="ArgumentException"></exception>
public static string Escape(char c, CharEscapeOptions escapeOptions = null, bool addQuotes = false)
{
if (escapeOptions == null)
{
escapeOptions = new CharEscapeOptions();
}
switch (escapeOptions.EscapeLanguage)
{
case CharEscapeLanguage.CSharp:
return(EscapeCSharp(c, escapeOptions, addQuotes));
case CharEscapeLanguage.FSharp:
return(EscapeFSharp(c, escapeOptions, addQuotes));
case CharEscapeLanguage.PowerShell:
throw new ArgumentException(string.Format("{0} does not have a char type.", escapeOptions.EscapeLanguage), nameof(escapeOptions));
default:
throw new ArgumentException(string.Format("{0} is not a valid {1}.", escapeOptions.EscapeLanguage, nameof(escapeOptions.EscapeLanguage)), nameof(escapeOptions));
}
}
/// <summary>
/// Escape char with backslash sequence (e.g. \n -> \\n)
/// </summary>
/// <param name="c">Char to escape</param>
/// <param name="escapeOptions">Escape options</param>
/// <param name="addQuotes">Add quotes after escaping</param>
/// <returns>String with escape sequence for char</returns>
/// <exception cref="ArgumentException"></exception>
internal static string EscapeCSharp(char c, CharEscapeOptions escapeOptions, bool addQuotes = false)
{
if (escapeOptions.UseShortEscape)
{
switch (c)
{
case '\'':
return("\\\'");
case '\"':
return("\\\"");
case '\\':
return("\\\\");
case '\0':
return("\\0");
case '\a':
return("\\a");
case '\b':
return("\\b");
case '\f':
return("\\f");
case '\n':
return("\\n");
case '\r':
return("\\r");
case '\t':
return("\\t");
case '\v':
return("\\v");
}
}
string xu;
string hex;
switch (escapeOptions.EscapeLetter)
{
case CharEscapeLetter.LowerCaseX1:
xu = "x";
hex = escapeOptions.UseLowerCaseHex ? "x1" : "X1";
break;
case CharEscapeLetter.LowerCaseX2:
xu = "x";
hex = escapeOptions.UseLowerCaseHex ? "x2" : "X2";
break;
case CharEscapeLetter.LowerCaseX3:
xu = "x";
hex = escapeOptions.UseLowerCaseHex ? "x3" : "X3";
break;
case CharEscapeLetter.LowerCaseX4:
xu = "x";
hex = escapeOptions.UseLowerCaseHex ? "x4" : "X4";
break;
case CharEscapeLetter.LowerCaseU4:
xu = "u";
hex = escapeOptions.UseLowerCaseHex ? "x4" : "X4";
break;
case CharEscapeLetter.UpperCaseU8:
xu = "U";
hex = escapeOptions.UseLowerCaseHex ? "x8" : "X8";
break;
default:
throw new ArgumentException(string.Format("{0} is not a valid {1} for {2}.", escapeOptions.EscapeLetter, nameof(escapeOptions.EscapeLetter), escapeOptions.EscapeLanguage), nameof(escapeOptions));
}
string escaped = "\\" + xu + ((int)c).ToString(hex);
if (addQuotes)
{
escaped = "\'" + escaped + "\'";
}
return(escaped);
}
/// <summary>
/// Escape surrogate pair with `u{HHHHH}
/// </summary>
/// <param name="highSurrogate">High surrogate</param>
/// <param name="lowSurrogate">Low surrogate</param>
/// <param name="escapeOptions">Char escape options</param>
/// <returns>String with escape sequence for surrogate pair</returns>
/// <exception cref="ArgumentOutOfRangeException"></exception>
/// <exception cref="ArgumentException"></exception>
internal static string EscapeSurrogatePairPowerShell(char highSurrogate, char lowSurrogate, CharEscapeOptions escapeOptions)
{
int codePoint = char.ConvertToUtf32(highSurrogate, lowSurrogate);
string hex;
switch (escapeOptions.SurrogatePairEscapeLetter)
{
// 1/2/3/4 will output as 5 so we can just fall through
case CharEscapeLetter.LowerCaseU1:
case CharEscapeLetter.LowerCaseU2:
case CharEscapeLetter.LowerCaseU3:
case CharEscapeLetter.LowerCaseU4:
case CharEscapeLetter.LowerCaseU5:
hex = escapeOptions.UseLowerCaseHex ? "x5" : "X5";
break;
case CharEscapeLetter.LowerCaseU6:
hex = escapeOptions.UseLowerCaseHex ? "x6" : "X6";
break;
default:
throw new ArgumentException(string.Format("{0} is not a valid {1} for {2}.", escapeOptions.SurrogatePairEscapeLetter, nameof(escapeOptions.SurrogatePairEscapeLetter), escapeOptions.EscapeLanguage), nameof(escapeOptions));
}
return("`u{" + codePoint.ToString(hex) + "}");
}
/// <summary>
/// Escape surrogate pair with \\UHHHHHHHH
/// </summary>
/// <param name="highSurrogate">High surrogate</param>
/// <param name="lowSurrogate">Low surrogate</param>
/// <param name="escapeOptions">Char escape options</param>
/// <returns>String with escape sequence for surrogate pair</returns>
/// <exception cref="ArgumentOutOfRangeException"></exception>
/// <exception cref="ArgumentException"></exception>
internal static string EscapeSurrogatePairFSharp(char highSurrogate, char lowSurrogate, CharEscapeOptions escapeOptions)
{
int codePoint = char.ConvertToUtf32(highSurrogate, lowSurrogate);
string hex;
switch (escapeOptions.SurrogatePairEscapeLetter)
{
case CharEscapeLetter.UpperCaseU8:
hex = escapeOptions.UseLowerCaseHex ? "x8" : "X8";
break;
default:
throw new ArgumentException(string.Format("{0} is not a valid {1} for {2}.", escapeOptions.SurrogatePairEscapeLetter, nameof(escapeOptions.SurrogatePairEscapeLetter), escapeOptions.EscapeLanguage), nameof(escapeOptions));
}
return("\\U" + codePoint.ToString(hex));
}
/// <summary>
/// Escape char with backslash sequence (e.g. \n -> `n)
/// </summary>
/// <param name="c">Char to escape</param>
/// <param name="escapeOptions">Escape options</param>
/// <returns>String with escape sequence for char</returns>
/// <exception cref="ArgumentException"></exception>
internal static string EscapePowerShell(char c, CharEscapeOptions escapeOptions)
{
if (escapeOptions.UseShortEscape)
{
// escaping single quotes here doesn't make any sense
// within double-quoted strings `' is the same as '
// within single-quoted strings `' doesn't work, you have to double ' to ''
switch (c)
{
case '\0':
return("`0");
case '\a':
return("`a");
case '\b':
return("`b");
case '\x1B': // escape
return("`e"); // this is supported in PowerShell v7, but not Windows PowerShell v5
case '\f':
return("`f");
case '\n':
return("`n");
case '\r':
return("`r");
case '\t':
return("`t");
case '\v':
return("`v");
case '`':
return("``");
case '\"':
return("`\""); // technically you can use either `" or "" within double-quoted strings
case '$':
return("`$"); // dollar sign interpolates variables, something we can't support, so escape it
}
}
string hex;
switch (escapeOptions.EscapeLetter)
{
case CharEscapeLetter.LowerCaseU1:
hex = escapeOptions.UseLowerCaseHex ? "x1" : "X1";
break;
case CharEscapeLetter.LowerCaseU2:
hex = escapeOptions.UseLowerCaseHex ? "x2" : "X2";
break;
case CharEscapeLetter.LowerCaseU3:
hex = escapeOptions.UseLowerCaseHex ? "x3" : "X3";
break;
case CharEscapeLetter.LowerCaseU4:
hex = escapeOptions.UseLowerCaseHex ? "x4" : "X4";
break;
case CharEscapeLetter.LowerCaseU5:
hex = escapeOptions.UseLowerCaseHex ? "x5" : "X5";
break;
case CharEscapeLetter.LowerCaseU6:
hex = escapeOptions.UseLowerCaseHex ? "x6" : "X6";
break;
default:
throw new ArgumentException(string.Format("{0} is not a valid {1} for {2}.", escapeOptions.EscapeLetter, nameof(escapeOptions.EscapeLetter), escapeOptions.EscapeLanguage), nameof(escapeOptions));
}
return("`u{" + ((int)c).ToString(hex) + "}"); // this is supported in PowerShell v7, but not Windows PowerShell v5
}
/// <summary>
/// Escape char with backslash sequence (e.g. \n -> \\n)
/// </summary>
/// <param name="c">Char to escape</param>
/// <param name="escapeOptions">Escape options</param>
/// <param name="addQuotes">Add quotes after escaping</param>
/// <returns>String with escape sequence for char</returns>
/// <exception cref="ArgumentException"></exception>
internal static string EscapeFSharp(char c, CharEscapeOptions escapeOptions, bool addQuotes = false)
{
if (escapeOptions.UseShortEscape)
{
// FSharp doesn't define \0, the closest is \000
switch (c)
{
case '\a':
return("\\a");
case '\b':
return("\\b");
case '\f':
return("\\f");
case '\n':
return("\\n");
case '\r':
return("\\r");
case '\t':
return("\\t");
case '\v':
return("\\v");
case '\\':
return("\\\\");
case '\'':
return("\\\'");
case '\"':
return("\\\"");
}
}
string xu = null;
string hex = null;
switch (escapeOptions.EscapeLetter)
{
case CharEscapeLetter.None3:
if (c <= 255)
{
xu = "";
hex = "D3";
}
break;
case CharEscapeLetter.LowerCaseX2:
if (c <= 0xFF)
{
xu = "x";
hex = escapeOptions.UseLowerCaseHex ? "x2" : "X2";
}
break;
case CharEscapeLetter.LowerCaseU4:
xu = "u";
hex = escapeOptions.UseLowerCaseHex ? "x4" : "X4";
break;
case CharEscapeLetter.UpperCaseU8:
xu = "U";
hex = escapeOptions.UseLowerCaseHex ? "x8" : "X8";
break;
default:
throw new ArgumentException(string.Format("{0} is not a valid {1} for {2}.", escapeOptions.EscapeLetter, nameof(escapeOptions.EscapeLetter), escapeOptions.EscapeLanguage), nameof(escapeOptions));
}
if (xu == null || hex == null)
{
switch (escapeOptions.EscapeLetterFallback)
{
case CharEscapeLetter.LowerCaseU4:
xu = "u";
hex = escapeOptions.UseLowerCaseHex ? "x4" : "X4";
break;
case CharEscapeLetter.UpperCaseU8:
xu = "U";
hex = escapeOptions.UseLowerCaseHex ? "x8" : "X8";
break;
default:
throw new ArgumentException(string.Format("{0} is not a valid {1} for {2}.", escapeOptions.EscapeLetterFallback, nameof(escapeOptions.EscapeLetterFallback), escapeOptions.EscapeLanguage), nameof(escapeOptions));
}
}
string escaped = "\\" + xu + ((int)c).ToString(hex);
if (addQuotes)
{
escaped = "\'" + escaped + "\'";
}
return(escaped);
}
/// <summary>
/// Escape string with backslash sequences (e.g. \r\n -> \\r\\n)
/// </summary>
/// <param name="s">String to escape</param>
/// <param name="stringEscapeOptions">String escape options</param>
/// <param name="charEscapeOptions"></param>
/// <param name="addQuotes">Add quotes after escaping</param>
/// <returns>String with escape sequences for string</returns>
/// <exception cref="ArgumentException"></exception>
private static string EscapeCSharp(string s, StringEscapeOptions stringEscapeOptions, CharEscapeOptions charEscapeOptions, bool addQuotes)
{
CharEscapeOptions charEscapeOptionsLowerCaseX4 = new CharEscapeOptions(
escapeLanguage: charEscapeOptions.EscapeLanguage,
escapeLetter: CharEscapeLetter.LowerCaseX4,
escapeLetterFallback: charEscapeOptions.EscapeLetterFallback,
surrogatePairEscapeLetter: charEscapeOptions.SurrogatePairEscapeLetter,
useLowerCaseHex: charEscapeOptions.UseLowerCaseHex,
useShortEscape: charEscapeOptions.UseShortEscape
);
StringBuilder sb = new StringBuilder(s.Length);
for (int i = 0; i < s.Length; i++)
{
if (stringEscapeOptions.EscapeSurrogatePairs && i + 1 < s.Length && char.IsSurrogatePair(s[i], s[i + 1]))
{
sb.Append(CharUtils.EscapeSurrogatePairCSharp(s[i], s[++i], charEscapeOptions));
}
else
{
switch (stringEscapeOptions.EscapeKind)
{
case StringEscapeKind.EscapeAll:
sb.Append(CharUtils.EscapeCSharp(s[i], charEscapeOptions));
break;
case StringEscapeKind.EscapeNonAscii:
if (s[i].IsPrintAscii() && !s[i].IsBackslash() && !s[i].IsDoubleQuote())
{
sb.Append(s[i]);
}
else
{
// pay special attention here because \x is variable length: H, HH, HHH, HHHH
// if the next char is hex then we don't want to insert it in any of the 'H' spaces
// instead we have to output the full fixed length \xHHHH so the next char doesn't become part of this \x sequence
if ((charEscapeOptions.EscapeLetter == CharEscapeLetter.LowerCaseX1 || charEscapeOptions.EscapeLetter == CharEscapeLetter.LowerCaseX2 || charEscapeOptions.EscapeLetter == CharEscapeLetter.LowerCaseX3) && i + 1 < s.Length && s[i + 1].IsHex())
{
sb.Append(CharUtils.EscapeCSharp(s[i], charEscapeOptionsLowerCaseX4));
}
else
{
sb.Append(CharUtils.EscapeCSharp(s[i], charEscapeOptions));
}
}
break;
default:
throw new ArgumentException(string.Format("{0} is not a valid {1}.", stringEscapeOptions.EscapeKind, nameof(stringEscapeOptions.EscapeKind)), nameof(stringEscapeOptions));
}
}
}
if (addQuotes)
{
sb.Insert(0, '\"');
sb.Append('\"');
}
return(sb.ToString());
}
/// <summary>
/// Escape string with backslash sequences (e.g. \r\n -> `r`n)
/// </summary>
/// <param name="s">String to escape</param>
/// <param name="stringEscapeOptions">String escape options</param>
/// <param name="charEscapeOptions">Char escape options</param>
/// <param name="addQuotes">Add quotes after escaping</param>
/// <returns>String with escape sequences for string</returns>
/// <exception cref="ArgumentException"></exception>
private static string EscapePowerShell(string s, StringEscapeOptions stringEscapeOptions, CharEscapeOptions charEscapeOptions, bool addQuotes)
{
StringBuilder sb = new StringBuilder(s.Length);
for (int i = 0; i < s.Length; i++)
{
if (stringEscapeOptions.EscapeSurrogatePairs && i + 1 < s.Length && char.IsSurrogatePair(s[i], s[i + 1]))
{
sb.Append(CharUtils.EscapeSurrogatePairPowerShell(s[i], s[++i], charEscapeOptions));
}
else
{
switch (stringEscapeOptions.EscapeKind)
{
case StringEscapeKind.EscapeAll:
sb.Append(CharUtils.EscapePowerShell(s[i], charEscapeOptions));
break;
case StringEscapeKind.EscapeNonAscii:
if (s[i].IsPrintAscii() && !s[i].IsBacktick() && !s[i].IsDoubleQuote() && !s[i].IsDollarSign())
{
sb.Append(s[i]);
}
else
{
sb.Append(CharUtils.EscapePowerShell(s[i], charEscapeOptions));
}
break;
default:
throw new ArgumentException(string.Format("{0} is not a valid {1}.", stringEscapeOptions.EscapeKind, nameof(stringEscapeOptions.EscapeKind)), nameof(stringEscapeOptions));
}
}
}
if (addQuotes)
{
sb.Insert(0, '\"');
sb.Append('\"');
}
return(sb.ToString());
}
