public static int UnescapeChar(string s, ref int i)
{
UString s2 = new UString(s, i);
EscapeC _ = 0;
int result = UnescapeChar(ref s2, ref _);
i = s2.InternalStart;
return(result);
}
/// <summary>Escapes characters in a string using C style.</summary>
/// <param name="flags">Specifies which characters should be escaped.</param>
/// <param name="quoteType">Specifies a character that should always be
/// escaped (typically one of <c>' " `</c>)</param>
public static string EscapeCStyle(UString s, EscapeC flags, char quoteType)
{
StringBuilder s2 = new StringBuilder(s.Length+1);
bool usedEscapes = false, fail;
for (;;) {
int c = s.PopFirst(out fail);
if (fail) break;
usedEscapes |= EscapeCStyle(c, s2, flags, quoteType);
}
if (!usedEscapes && s.InternalString.Length == s.Length)
return s.InternalString;
return s2.ToString();
}
static void EscapeU(char c, StringBuilder @out, EscapeC flags)
{
if (c <= 255 && (flags & EscapeC.BackslashX) != 0)
{
@out.Append(@"\x");
}
else
{
@out.Append(@"\u");
@out.Append(HexDigitChar((c >> 12) & 0xF));
@out.Append(HexDigitChar((c >> 8) & 0xF));
}
@out.Append(HexDigitChar((c >> 4) & 0xF));
@out.Append(HexDigitChar(c & 0xF));
}
public static string EscapeCStyle(UString s, EscapeC flags, char quoteType)
{
StringBuilder s2 = new StringBuilder(s.Length + 1);
bool any = false;
for (int i = 0; i < s.Length; i++)
{
char c = s[i];
any |= EscapeCStyle(c, s2, flags, quoteType);
}
if (!any && s.InternalString.Length == s.Length)
{
return(s.InternalString);
}
return(s2.ToString());
}
/// <summary>Unescapes a string that uses C-style escape sequences, e.g.
/// "\\\n\\\r" becomes "\n\r".</summary>
/// <param name="encountered">Returns information about whether escape
/// sequences were encountered, and which categories.</param>
/// <param name="removeUnnecessaryBackslashes">Causes the backslash before
/// an unrecognized escape sequence to be removed, e.g. "\z" => "z".</param>
/// <remarks>See <see cref="UnescapeChar(ref UString, ref EscapeC)"/> for details.</remarks>
public static StringBuilder UnescapeCStyle(UString s, out EscapeC encountered, bool removeUnnecessaryBackslashes = false)
{
encountered = 0;
StringBuilder @out = new StringBuilder(s.Length);
while (s.Length > 0) {
EscapeC encounteredHere = 0;
int c = UnescapeChar(ref s, ref encounteredHere);
encountered |= encounteredHere;
if (removeUnnecessaryBackslashes && (encounteredHere & EscapeC.Unrecognized) != 0) {
Debug.Assert(c == '\\');
continue;
}
@out.AppendCodePoint(c);
}
return @out;
}
/// <summary>Unescapes a string that uses C-style escape sequences, e.g. "\n\r" becomes @"\n\r".</summary>
/// <param name="encountered">Returns information about whether escape
/// sequences were encountered, and which categories.</param>
/// <param name="removeUnnecessaryBackslashes">Causes the backslash before
/// an unrecognized escape sequence to be removed, e.g. "\z" => "z".</param>
public static string UnescapeCStyle(string s, int index, int length, out EscapeC encountered, bool removeUnnecessaryBackslashes = false)
{
encountered = 0;
StringBuilder s2 = new StringBuilder(length);
for (int i = index; i < index + length;)
{
int oldi = i;
char c = UnescapeChar(s, ref i, ref encountered);
if (removeUnnecessaryBackslashes && c == '\\' && i == oldi + 1)
{
continue;
}
s2.Append(c);
}
return(s2.ToString());
}
static void EscapeU(int c, StringBuilder @out, EscapeC flags)
{
if (c <= 255 && (flags & EscapeC.BackslashX) != 0)
@out.Append(@"\x");
else {
@out.Append(@"\u");
if (c > 0xFFFF || (flags & EscapeC.HasLongEscape) != 0) {
Debug.Assert(c <= 0x10FFFF);
@out.Append(HexDigitChar((c >> 20) & 0xF));
@out.Append(HexDigitChar((c >> 16) & 0xF));
}
@out.Append(HexDigitChar((c >> 12) & 0xF));
@out.Append(HexDigitChar((c >> 8) & 0xF));
}
@out.Append(HexDigitChar((c >> 4) & 0xF));
@out.Append(HexDigitChar(c & 0xF));
}
/// <summary>Unescapes a string that uses C-style escape sequences, e.g.
/// "\\\n\\\r" becomes "\n\r".</summary>
/// <param name="encountered">Returns information about whether escape
/// sequences were encountered, and which categories.</param>
/// <param name="removeUnnecessaryBackslashes">Causes the backslash before
/// an unrecognized escape sequence to be removed, e.g. "\z" => "z".</param>
/// <remarks>See <see cref="UnescapeChar(ref UString, ref EscapeC)"/> for details.</remarks>
public static StringBuilder UnescapeCStyle(UString s, out EscapeC encountered, bool removeUnnecessaryBackslashes = false)
{
encountered = 0;
StringBuilder @out = new StringBuilder(s.Length);
while (s.Length > 0)
{
EscapeC encounteredHere = 0;
int c = UnescapeChar(ref s, ref encounteredHere);
encountered |= encounteredHere;
if (removeUnnecessaryBackslashes && (encounteredHere & EscapeC.Unrecognized) != 0)
{
Debug.Assert(c == '\\');
continue;
}
@out.AppendCodePoint(c);
}
return(@out);
}
/// <summary>Escapes characters in a string using C style.</summary>
/// <param name="flags">Specifies which characters should be escaped.</param>
/// <param name="quoteType">Specifies a character that should always be
/// escaped (typically one of <c>' " `</c>)</param>
public static string EscapeCStyle(UString s, EscapeC flags, char quoteType)
{
StringBuilder s2 = new StringBuilder(s.Length + 1);
bool usedEscapes = false, fail;
for (;;)
{
int c = s.PopFirst(out fail);
if (fail)
{
break;
}
usedEscapes |= EscapeCStyle(c, s2, flags, quoteType);
}
if (!usedEscapes && s.InternalString.Length == s.Length)
{
return(s.InternalString);
}
return(s2.ToString());
}
static void EscapeU(int c, StringBuilder @out, EscapeC flags)
{
if (c <= 255 && (flags & EscapeC.BackslashX) != 0)
{
@out.Append(@"\x");
}
else
{
@out.Append(@"\u");
if (c > 0xFFFF || (flags & EscapeC.HasLongEscape) != 0)
{
Debug.Assert(c <= 0x10FFFF);
@out.Append(HexDigitChar((c >> 20) & 0xF));
@out.Append(HexDigitChar((c >> 16) & 0xF));
}
@out.Append(HexDigitChar((c >> 12) & 0xF));
@out.Append(HexDigitChar((c >> 8) & 0xF));
}
@out.Append(HexDigitChar((c >> 4) & 0xF));
@out.Append(HexDigitChar(c & 0xF));
}
/// <summary>Writes a character <c>c</c> to a StringBuilder, either as a normal
/// character or as a C-style escape sequence.</summary>
/// <param name="flags">Specifies which characters should be escaped.</param>
/// <param name="quoteType">Specifies a character that should always be
/// escaped (typically one of <c>' " `</c>)</param>
/// <returns>true if an escape sequence was emitted, false if not.</returns>
/// <remarks><see cref="EscapeC.HasLongEscape"/> can be used to force a 6-digit
/// unicode escape; this may be needed if the next character after this one
/// is a digit.</remarks>
public static bool EscapeCStyle(int c, StringBuilder @out, EscapeC flags = EscapeC.Default, char quoteType = '\0')
{
for (;;)
{
if (c >= 128)
{
if ((flags & EscapeC.NonAscii) != 0)
{
EscapeU(c, @out, flags);
}
else if (c >= 0xDC00)
{
if ((flags & EscapeC.UnicodeNonCharacters) != 0 && (
c >= 0xFDD0 && c <= 0xFDEF || // 0xFDD0...0xFDEF
(c & 0xFFFE) == 0xFFFE) || // 0xFFFE, 0xFFFF, 0x1FFFE, 0x1FFFF, etc.
(c & 0xFC00) == 0xDC00) // 0xDC00...0xDCFF
{
EscapeU(c, @out, flags);
}
else if ((flags & EscapeC.UnicodePrivateUse) != 0 && (
c >= 0xE000 && c <= 0xF8FF ||
c >= 0xF0000 && c <= 0xFFFFD ||
c >= 0x100000 && c <= 0x10FFFD))
{
EscapeU(c, @out, flags);
}
else
{
break;
}
}
else
{
break;
}
}
else if (c < 32)
{
if (c == '\n')
{
@out.Append(@"\n");
}
else if (c == '\r')
{
@out.Append(@"\r");
}
else if (c == '\0')
{
@out.Append(@"\0");
}
else
{
if ((flags & EscapeC.ABFV) != 0)
{
if (c == '\a') // 7 (alert)
{
@out.Append(@"\a");
return(true);
}
if (c == '\b') // 8 (backspace)
{
@out.Append(@"\b");
return(true);
}
if (c == '\f') // 12 (form feed)
{
@out.Append(@"\f");
return(true);
}
if (c == '\v') // 11 (vertical tab)
{
@out.Append(@"\v");
return(true);
}
}
if ((flags & EscapeC.Control) != 0)
{
if (c == '\t')
{
@out.Append(@"\t");
}
else
{
EscapeU(c, @out, flags);
}
}
else
{
@out.Append(c);
}
}
}
else if (c == '\"' && (flags & EscapeC.DoubleQuotes) != 0)
{
@out.Append("\\\"");
}
else if (c == '\'' && (flags & EscapeC.SingleQuotes) != 0)
{
@out.Append("\\'");
}
else if (c == '\\')
{
@out.Append(@"\\");
}
else
{
break;
}
return(true);
}
if (c == quoteType)
{
@out.Append('\\');
@out.Append((char)c);
return(true);
}
else
{
@out.AppendCodePoint(c);
}
return(false);
}
/// <summary>Escapes characters in a string using C style, e.g. the string
/// <c>"Foo\"\n"</c> maps to <c>"Foo\\\"\\\n"</c> by default.</summary>
public static string EscapeCStyle(UString s, EscapeC flags = EscapeC.Default)
{
return(EscapeCStyle(s, flags, '\0'));
}
/// <summary>Parses a normal or triple-quoted string whose starting quotes
/// have been stripped out. If triple-quote parsing was requested, stops
/// parsing at three quote marks; otherwise, stops parsing at a single
/// end-quote or newline.</summary>
/// <returns>true if parsing stopped at one or three quote marks, or false
/// if parsing stopped at the end of the input string or at a newline (in
/// a string that is not triple-quoted).</returns>
/// <remarks>This method recognizes LES and EC#-style string syntax.</remarks>
public static bool UnescapeString(ref UString sourceText, char quoteType, bool isTripleQuoted, Action <int, string> onError, StringBuilder sb, UString indentation = default(UString), bool allowExtraIndent = false)
{
Debug.Assert(quoteType == '"' || quoteType == '\'' || quoteType == '`');
bool fail;
for (; ;)
{
if (sourceText.IsEmpty)
{
return(false);
}
int i0 = sourceText.InternalStart;
if (!isTripleQuoted)
{
EscapeC category = 0;
int c = ParseHelpers.UnescapeChar(ref sourceText, ref category);
if ((c == quoteType || c == '\n') && sourceText.InternalStart == i0 + 1)
{
return(c == quoteType); // end of string
}
if ((category & EscapeC.Unrecognized) != 0)
{
// This backslash was ignored by UnescapeChar
onError(i0, @"Unrecognized escape sequence '\{0}' in string".Localized(PrintHelpers.EscapeCStyle(sourceText[0, ' '].ToString(), EscapeC.Control)));
}
else if ((category & EscapeC.HasInvalid6DigitEscape) != 0)
{
onError(i0, @"Invalid 6-digit \u code treated as 5 digits".Localized());
}
sb.AppendCodePoint(c);
if ((category & EscapeC.BackslashX) != 0 && c >= 0x80)
{
DetectUtf8(sb);
}
else if (c.IsInRange(0xDC00, 0xDFFF))
{
RecodeSurrogate(sb);
}
}
else
{
// Inside triple-quoted string
int c;
if (sourceText[2, '\0'] == '/')
{
// Detect escape sequence
c = ParseHelpers.UnescapeChar(ref sourceText);
if (sourceText.InternalStart > i0 + 1)
{
G.Verify(sourceText.PopFirst(out fail) == '/');
}
}
else
{
c = sourceText.PopFirst(out fail);
if (fail)
{
return(false);
}
if (c == quoteType)
{
if (sourceText[0, '\0'] == quoteType &&
sourceText[1, '\0'] == quoteType)
{
sourceText = sourceText.Substring(2);
// end of string
return(true);
}
}
if (c == '\r' || c == '\n')
{
// To ensure platform independency of source code, CR and
// CR-LF become LF.
if (c == '\r')
{
c = '\n';
var copy = sourceText.Clone();
if (sourceText.PopFirst(out fail) != '\n')
{
sourceText = copy;
}
}
// Inside a triple-quoted string, the indentation following a newline
// is ignored, as long as it matches the indentation of the first line.
UString src = sourceText, ind = indentation;
int sp;
while ((sp = src.PopFirst(out fail)) == ind.PopFirst(out fail) && !fail)
{
sourceText = src;
}
if (allowExtraIndent && fail)
{
// Allow an additional one tab or three spaces when initial indent matches
if (sp == '\t')
{
sourceText = src;
}
else if (sp == ' ')
{
sourceText = src;
if (src.PopFirst(out fail) == ' ')
{
sourceText = src;
}
if (src.PopFirst(out fail) == ' ')
{
sourceText = src;
}
}
}
}
}
sb.AppendCodePoint(c);
}
}
}
public static char UnescapeChar(string s, ref int i)
{
EscapeC _ = 0;
return(UnescapeChar(s, ref i, ref _));
}
/// <summary>Unescapes a single character of a string. Returns the
/// first character if it is not a backslash, or <c>\</c> if it is a
/// backslash but no escape sequence could be discerned.</summary>
/// <param name="s">Slice of a string to be unescaped. When using a
/// <c>ref UString</c> overload of this method, <c>s</c> will be shorter upon
/// returning from this method, as the parsed character(s) are clipped
/// from the beginning (<c>s.InternalStart</c> is incremented by one
/// normally and more than one in case of an escape sequence.)</param>
/// <param name="encountered">Bits of this parameter are set according
/// to which escape sequence is encountered, if any.</param>
/// <remarks>
/// This function also decodes (non-escaped) surrogate pairs.
/// <para/>
/// Code points with 5 or 6 digits such as \u1F4A9 are supported.
/// \x escapes must be two digits and set the EscapeC.BackslashX flag.
/// \u escapes must be 4 to 6 digits. If a \u escape has more than 4
/// digits, the EscapeC.HasLongEscapes flag is set. Invalid 6-digit
/// escapes like \u123456 are "made valid" by being treated as 5 digits
/// (the largest valid escape is <c>\u10FFFF</c>.)
/// <para/>
/// Supported escapes: <c>\u \x \\ \n \r \0 \' \" \` \t \a \b \f \v</c>
/// </remarks>
/// <example>
/// EscapeC e = 0;
/// UString str = @"\nfoo";
/// char c = UnescapeChar(ref str, ref e);
/// Contract.Assert(str == "foo");
/// Contract.Assert(e == EscapeC.HasEscapes);
/// </example>
public static int UnescapeChar(ref UString s, ref EscapeC encountered)
{
bool fail;
int c = s.PopFirst(out fail);
if (c != '\\' || s.Length <= 0)
return c;
encountered |= EscapeC.HasEscapes;
int code; // hex code after \u or \x
UString slice, original = s;
switch (s.PopFirst(out fail)) {
case 'u':
slice = s.Left(6);
if (TryParseHex(ref slice, out code) >= 4) {
if (code <= 0x10FFFF) {
s = s.Substring(slice.InternalStart - s.InternalStart);
} else {
Debug.Assert(slice.Length == 0);
// It appears to be 6 digits but only the first 5 can
// be treated as part of the escape sequence.
s = s.Substring(5);
code >>= 4;
encountered |= EscapeC.HasInvalid6DigitEscape;
}
if (slice.InternalStart > s.InternalStart + 4)
encountered |= EscapeC.HasLongEscape;
if (code < 32)
encountered |= EscapeC.Control;
else if (code > 127)
encountered |= EscapeC.NonAscii;
return code;
} else
break;
case 'x':
slice = s.Left(2);
if (TryParseHex(slice, out code)) {
encountered |= EscapeC.BackslashX;
if (code < 32)
encountered |= EscapeC.Control;
else if (code > 127)
encountered |= EscapeC.NonAscii;
s = s.Substring(2);
return code;
} else
break;
case '\\':
return '\\';
case 'n':
return '\n';
case 'r':
return '\r';
case '0':
return '\0';
case '\"':
encountered |= EscapeC.DoubleQuotes;
return '\"';
case '\'':
encountered |= EscapeC.SingleQuotes;
return '\'';
case '`':
encountered |= EscapeC.Quotes;
return '`';
case 't':
encountered |= EscapeC.Control;
return '\t';
case 'a':
encountered |= EscapeC.ABFV;
return '\a';
case 'b':
encountered |= EscapeC.ABFV;
return '\b';
case 'f':
encountered |= EscapeC.ABFV;
return '\f';
case 'v':
encountered |= EscapeC.ABFV;
return '\v';
}
encountered |= EscapeC.Unrecognized;
s = original;
return c;
}
public static int UnescapeChar(ref UString s)
{
EscapeC _ = 0;
return(UnescapeChar(ref s, ref _));
}
/// <summary>Unescapes a single character of a string. Returns the
/// first character if it is not a backslash, or <c>\</c> if it is a
/// backslash but no escape sequence could be discerned.</summary>
/// <param name="s">Slice of a string to be unescaped. When using a
/// <c>ref UString</c> overload of this method, <c>s</c> will be shorter upon
/// returning from this method, as the parsed character(s) are clipped
/// from the beginning (<c>s.InternalStart</c> is incremented by one
/// normally and more than one in case of an escape sequence.)</param>
/// <param name="encountered">Bits of this parameter are set according
/// to which escape sequence is encountered, if any.</param>
/// <remarks>
/// This function also decodes (non-escaped) surrogate pairs.
/// <para/>
/// Code points with 5 or 6 digits such as \u1F4A9 are supported.
/// \x escapes must be two digits and set the EscapeC.BackslashX flag.
/// \u escapes must be 4 to 6 digits. If a \u escape has more than 4
/// digits, the EscapeC.HasLongEscapes flag is set. Invalid 6-digit
/// escapes like \u123456 are "made valid" by being treated as 5 digits
/// (the largest valid escape is <c>\u10FFFF</c>.)
/// <para/>
/// Supported escapes: <c>\u \x \\ \n \r \0 \' \" \` \t \a \b \f \v</c>
/// </remarks>
/// <example>
/// EscapeC e = 0;
/// UString str = @"\nfoo";
/// char c = UnescapeChar(ref str, ref e);
/// Contract.Assert(str == "foo");
/// Contract.Assert(e == EscapeC.HasEscapes);
/// </example>
public static int UnescapeChar(ref UString s, ref EscapeC encountered)
{
bool fail;
int c = s.PopFirst(out fail);
if (c != '\\' || s.Length <= 0)
{
return(c);
}
encountered |= EscapeC.HasEscapes;
int code; // hex code after \u or \x or \U
int len; // length of hex code after \u or \x or \U
UString slice, original = s;
int type = s.PopFirst(out fail);
switch (type)
{
case 'x':
encountered |= EscapeC.BackslashX;
goto case 'u';
case 'u':
len = type == 'u' ? 4 : 2;
slice = s.Left(len);
if (TryParseHex(ref slice, out code) == len)
{
s = s.Substring(slice.InternalStart - s.InternalStart);
if (code < 32)
{
encountered |= EscapeC.Control;
}
else if (code > 127)
{
encountered |= EscapeC.NonAscii;
}
return(code);
}
else
{
break;
}
case 'U':
encountered |= EscapeC.HasLongEscape;
slice = s.Left(6);
len = TryParseHex(ref slice, out code);
if (len > 0)
{
if (code <= 0x10FFFF)
{
s = s.Substring(len);
}
else
{
Debug.Assert(slice.Length == 0);
// It appears to be 6 digits but only the first 5 can
// be treated as part of the escape sequence.
encountered |= EscapeC.HasInvalid6DigitEscape;
s = s.Substring(5);
code >>= 4;
}
if (code < 32)
{
encountered |= EscapeC.Control;
}
else if (code > 127)
{
encountered |= EscapeC.NonAscii;
}
return(code);
}
else
{
break;
}
case '\\':
return('\\');
case 'n':
return('\n');
case 'r':
return('\r');
case '0':
return('\0');
case '\"':
encountered |= EscapeC.DoubleQuotes;
return('\"');
case '\'':
encountered |= EscapeC.SingleQuotes;
return('\'');
case '`':
encountered |= EscapeC.Quotes;
return('`');
case 't':
encountered |= EscapeC.Control;
return('\t');
case 'a':
encountered |= EscapeC.ABFV;
return('\a');
case 'b':
encountered |= EscapeC.ABFV;
return('\b');
case 'f':
encountered |= EscapeC.ABFV;
return('\f');
case 'v':
encountered |= EscapeC.ABFV;
return('\v');
}
encountered |= EscapeC.Unrecognized;
s = original;
return(c);
}
/// <summary>Unescapes a single character of a string. Returns the
/// character at 'index' if it is not a backslash, or if it is a
/// backslash but no escape sequence could be discerned.</summary>
/// <param name="i">Current index within the string, incremented
/// by one normally and more than one in case of an escape sequence.</param>
/// <param name="encountered">Bits of this parameter are set according
/// to which escape sequence is encountered, if any.</param>
/// <exception cref="IndexOutOfRangeException">The index was invalid.</exception>
/// <example>
/// int i = 3;
/// EscapeC e = 0;
/// char c = UnescapeChar(@"foo\n", ref i, ref e);
/// Contract.Assert(c == '\n' && e == EscapeC.HasEscapes);
/// </example>
public static char UnescapeChar(string s, ref int i, ref EscapeC encountered)
{
char c = s[i++];
if (c != '\\')
{
return(c);
}
encountered |= EscapeC.HasEscapes;
if (i < s.Length)
{
int code;
UString slice;
switch (s[i++])
{
case 'u':
slice = s.Slice(i, 4);
if (TryParseHex(slice, out code))
{
encountered |= code < 32 ? EscapeC.Control
: EscapeC.NonAscii;
i += slice.Length;
return((char)code);
}
else
{
break;
}
case 'x':
slice = s.Slice(i, 2);
if (TryParseHex(slice, out code))
{
encountered |= code < 32 ? EscapeC.BackslashX | EscapeC.Control
: EscapeC.BackslashX | EscapeC.NonAscii;
i += slice.Length;
return((char)code);
}
else
{
break;
}
case '\\':
return('\\');
case 'n':
return('\n');
case 'r':
return('\r');
case '0':
return('\0');
case '\"':
encountered |= EscapeC.DoubleQuotes;
return('\"');
case '\'':
encountered |= EscapeC.SingleQuotes;
return('\'');
case '`':
encountered |= EscapeC.Quotes;
return('`');
case 't':
encountered |= EscapeC.Control;
return('\t');
case 'a':
encountered |= EscapeC.ABFV;
return('\a');
case 'b':
encountered |= EscapeC.ABFV;
return('\b');
case 'f':
encountered |= EscapeC.ABFV;
return('\f');
case 'v':
encountered |= EscapeC.ABFV;
return('\v');
default:
encountered |= EscapeC.Unrecognized;
i--;
break;
}
}
return(c);
}
public static bool EscapeCStyle(char c, StringBuilder @out, EscapeC flags = EscapeC.Default, char quoteType = '\0')
{
do
{
if (c >= 128)
{
if ((flags & EscapeC.NonAscii) != 0)
{
EscapeU(c, @out, flags);
}
else
{
break;
}
}
else if (c < 32)
{
if (c == '\n')
{
@out.Append(@"\n");
}
else if (c == '\r')
{
@out.Append(@"\r");
}
else if (c == '\0')
{
@out.Append(@"\0");
}
else
{
if ((flags & EscapeC.ABFV) != 0)
{
if (c == '\a') // 7 (alert)
{
@out.Append(@"\a");
return(true);
}
if (c == '\b') // 8 (backspace)
{
@out.Append(@"\b");
return(true);
}
if (c == '\f') // 12 (form feed)
{
@out.Append(@"\f");
return(true);
}
if (c == '\v') // 11 (vertical tab)
{
@out.Append(@"\v");
return(true);
}
}
if ((flags & EscapeC.Control) != 0)
{
if (c == '\t')
{
@out.Append(@"\t");
}
else
{
EscapeU(c, @out, flags);
}
}
else
{
@out.Append(c);
}
}
}
else if (c == '\"' && (flags & EscapeC.DoubleQuotes) != 0)
{
@out.Append("\\\"");
}
else if (c == '\'' && (flags & EscapeC.SingleQuotes) != 0)
{
@out.Append("\\'");
}
else if (c == '\\')
{
@out.Append(@"\\");
}
else
{
break;
}
return(true);
} while (false);
if (c == quoteType)
{
@out.Append('\\');
@out.Append(c);
return(true);
}
else
{
@out.Append(c);
return(false);
}
}
public static bool EscapeCStyle(char c, StringBuilder @out, EscapeC flags = EscapeC.Default, char quoteType = '\0')
{
if (c > 255 && (flags & (EscapeC.Unicode | EscapeC.NonAscii)) != 0)
{
@out.AppendFormat((IFormatProvider)null, @"\u{0:x0000}", (int)c);
}
else if (c == '\"' && (flags & EscapeC.DoubleQuotes) != 0)
{
@out.Append("\\\"");
}
else if (c == '\'' && (flags & EscapeC.SingleQuotes) != 0)
{
@out.Append("\\'");
}
else if (c == quoteType)
{
@out.Append('\\');
@out.Append(c);
}
else if (c < 32)
{
if (c == '\n')
{
@out.Append(@"\n");
}
else if (c == '\r')
{
@out.Append(@"\r");
}
else if (c == '\0')
{
@out.Append(@"\0");
}
else
{
if ((flags & EscapeC.ABFV) != 0)
{
if (c == '\a') // 7 (alert)
{
@out.Append(@"\a");
return(true);
}
if (c == '\b') // 8 (backspace)
{
@out.Append(@"\b");
return(true);
}
if (c == '\f') // 12 (form feed)
{
@out.Append(@"\f");
return(true);
}
if (c == '\v') // 11 (vertical tab)
{
@out.Append(@"\v");
return(true);
}
}
if ((flags & EscapeC.Control) != 0)
{
if (c == '\t')
{
@out.Append(@"\t");
}
else
{
@out.AppendFormat(null, @"\x{0:X2}", (int)c);
}
}
else
{
@out.Append(c);
}
}
}
else if (c == '\\')
{
@out.Append(@"\\");
}
else if (c > 127 && (flags & EscapeC.NonAscii) != 0)
{
@out.AppendFormat(null, @"\x{0:X2}", (int)c);
}
else
{
@out.Append(c);
return(false);
}
return(true);
}
/// <summary>Escapes characters in a string using C style, e.g. the string
/// <c>"Foo\"\n"</c> maps to <c>"Foo\\\"\\\n"</c> by default.</summary>
public static string EscapeCStyle(UString s, EscapeC flags = EscapeC.Default)
{
return EscapeCStyle(s, flags, '\0');
}
/// <summary>Writes a character <c>c</c> to a StringBuilder, either as a normal
/// character or as a C-style escape sequence.</summary>
/// <param name="flags">Specifies which characters should be escaped.</param>
/// <param name="quoteType">Specifies a character that should always be
/// escaped (typically one of <c>' " `</c>)</param>
/// <returns>true if an escape sequence was emitted, false if not.</returns>
/// <remarks><see cref="EscapeC.HasLongEscape"/> can be used to force a 6-digit
/// unicode escape; this may be needed if the next character after this one
/// is a digit.</remarks>
public static bool EscapeCStyle(int c, StringBuilder @out, EscapeC flags = EscapeC.Default, char quoteType = '\0')
{
for(;;) {
if (c >= 128) {
if ((flags & EscapeC.NonAscii) != 0) {
EscapeU(c, @out, flags);
} else if (c >= 0xDC00) {
if ((flags & EscapeC.UnicodeNonCharacters) != 0 && (
c >= 0xFDD0 && c <= 0xFDEF || // 0xFDD0...0xFDEF
(c & 0xFFFE) == 0xFFFE) || // 0xFFFE, 0xFFFF, 0x1FFFE, 0x1FFFF, etc.
(c & 0xFC00) == 0xDC00) { // 0xDC00...0xDCFF
EscapeU(c, @out, flags);
} else if ((flags & EscapeC.UnicodePrivateUse) != 0 && (
c >= 0xE000 && c <= 0xF8FF ||
c >= 0xF0000 && c <= 0xFFFFD ||
c >= 0x100000 && c <= 0x10FFFD)) {
EscapeU(c, @out, flags);
} else
break;
} else
break;
} else if (c < 32) {
if (c == '\n')
@out.Append(@"\n");
else if (c == '\r')
@out.Append(@"\r");
else if (c == '\0')
@out.Append(@"\0");
else {
if ((flags & EscapeC.ABFV) != 0) {
if (c == '\a') { // 7 (alert)
@out.Append(@"\a");
return true;
}
if (c == '\b') { // 8 (backspace)
@out.Append(@"\b");
return true;
}
if (c == '\f') { // 12 (form feed)
@out.Append(@"\f");
return true;
}
if (c == '\v') { // 11 (vertical tab)
@out.Append(@"\v");
return true;
}
}
if ((flags & EscapeC.Control) != 0) {
if (c == '\t')
@out.Append(@"\t");
else
EscapeU(c, @out, flags);
} else
@out.Append(c);
}
} else if (c == '\"' && (flags & EscapeC.DoubleQuotes) != 0) {
@out.Append("\\\"");
} else if (c == '\'' && (flags & EscapeC.SingleQuotes) != 0) {
@out.Append("\\'");
} else if (c == '\\')
@out.Append(@"\\");
else
break;
return true;
}
if (c == quoteType) {
@out.Append('\\');
@out.Append((char)c);
return true;
} else
@out.AppendCodePoint(c);
return false;
}