/// <summary>
/// Parse a string field
/// </summary>
static bool ParseString(Action <object> add, TextVisiter input, FormatSpecifier spec)
{
// Skip any whitespace
input.MovePastWhitespace();
// Parse string characters
var start = input.Position;
while (!input.EndOfText && !char.IsWhiteSpace(input.Peek()))
{
input.MoveAhead();
}
// Don't exceed field width
if (spec.Width > 0)
{
var count = input.Position - start;
if (spec.Width < count)
{
input.MoveAhead(spec.Width - count);
}
}
// Extract token
if (input.Position > start)
{
if (!spec.NoResult)
{
add(input.Extract(start, input.Position));
}
return(true);
}
return(false);
}
/// <summary>
/// Parse an octal field
/// </summary>
static bool ParseOctal(Action <object> add, TextVisiter input, FormatSpecifier spec)
{
// Skip any whitespace
input.MovePastWhitespace();
// Parse digits
var start = input.Position;
while (IsValidDigit(input.Peek(), 8))
{
input.MoveAhead();
}
// Don't exceed field width
if (spec.Width > 0)
{
var count = input.Position - start;
if (spec.Width < count)
{
input.MoveAhead(spec.Width - count);
}
}
// Extract token
if (input.Position > start)
{
if (!spec.NoResult)
{
add(Unsigned(input.Extract(start, input.Position), spec.Modifier, 8));
}
return(true);
}
return(false);
}
/// <summary>
/// Parse integer field
/// </summary>
static bool ParseDecimal(Action <object> add, TextVisiter input, FormatSpecifier spec)
{
// Skip any whitespace
input.MovePastWhitespace();
// Parse leading sign
var radix = 10;
var start = input.Position;
if (input.Peek() == '+' || input.Peek() == '-')
{
input.MoveAhead();
}
else if (input.Peek() == '0')
{
if (char.ToLower(input.Peek(1)) == 'x')
{
radix = 16; input.MoveAhead(2);
}
else
{
radix = 8; input.MoveAhead();
}
}
// Parse digits
while (IsValidDigit(input.Peek(), radix))
{
input.MoveAhead();
}
// Don't exceed field width
if (spec.Width > 0)
{
var count = input.Position - start;
if (spec.Width < count)
{
input.MoveAhead(spec.Width - count);
}
}
// Extract token
if (input.Position > start)
{
if (!spec.NoResult)
{
add(spec.Type == Types.Decimal
? Signed(input.Extract(start, input.Position), spec.Modifier, radix)
: Unsigned(input.Extract(start, input.Position), spec.Modifier, radix));
}
return(true);
}
return(false);
}
/// <summary>
/// Parses the input string according to the rules in the
/// format string. Similar to the standard C library's
/// sscanf() function. Parsed fields are placed in the
/// class' Results member.
/// </summary>
/// <param name="input">String to parse</param>
/// <param name="format">Specifies rules for parsing input</param>
public static int Parse(string input, string format, out IList <object> values)
{
var inp = new TextVisiter(input);
var fmt = new TextVisiter(format);
var results = new List <object>();
var spec = new FormatSpecifier();
var count = 0;
// Process input string as indicated in format string
while (!fmt.EndOfText && !inp.EndOfText)
{
if (ParseFormatSpecifier(fmt, spec))
{
// Found a format specifier
var parser = _typeParsers.First(tp => tp.Type == spec.Type);
if (parser.Parser(results.Add, inp, spec))
{
count++;
}
else
{
break;
}
}
else if (char.IsWhiteSpace(fmt.Peek()))
{
// Whitespace
inp.MovePastWhitespace();
fmt.MoveAhead();
}
else if (fmt.Peek() == inp.Peek())
{
// Matching character
inp.MoveAhead();
fmt.MoveAhead();
}
else
{
break; // Break at mismatch
}
}
// Return number of fields successfully parsed
values = results;
return(count);
}
/// <summary>
/// Parse a scan-set field
/// </summary>
static bool ParseScanSet(Action <object> add, TextVisiter input, FormatSpecifier spec)
{
// Parse characters
var start = input.Position;
if (!spec.ScanSetExclude)
{
while (spec.ScanSet.Contains(input.Peek()))
{
input.MoveAhead();
}
}
else
{
while (!input.EndOfText && !spec.ScanSet.Contains(input.Peek()))
{
input.MoveAhead();
}
}
// Don't exceed field width
if (spec.Width > 0)
{
var count = input.Position - start;
if (spec.Width < count)
{
input.MoveAhead(spec.Width - count);
}
}
// Extract token
if (input.Position > start)
{
if (!spec.NoResult)
{
add(input.Extract(start, input.Position));
}
return(true);
}
return(false);
}
/// <summary>
/// Parse a character field
/// </summary>
static bool ParseCharacter(Action <object> add, TextVisiter input, FormatSpecifier spec)
{
// Parse character(s)
var start = input.Position;
var count = (spec.Width > 1) ? spec.Width : 1;
while (!input.EndOfText && count-- > 0)
{
input.MoveAhead();
}
// Extract token
if (count <= 0 && input.Position > start)
{
if (!spec.NoResult)
{
var token = input.Extract(start, input.Position);
add(token.Length > 1 ? token.ToCharArray() : token[0]);
}
return(true);
}
return(false);
}
/// <summary>
/// Parse a floating-point field
/// </summary>
static bool ParseFloat(Action <object> add, TextVisiter input, FormatSpecifier spec)
{
// Skip any whitespace
input.MovePastWhitespace();
// Parse leading sign
var start = input.Position;
if (input.Peek() == '+' || input.Peek() == '-')
{
input.MoveAhead();
}
// Parse digits
var hasPoint = false;
while (char.IsDigit(input.Peek()) || input.Peek() == '.')
{
if (input.Peek() == '.')
{
if (hasPoint)
{
break;
}
hasPoint = true;
}
input.MoveAhead();
}
// Parse exponential notation
if (char.ToLower(input.Peek()) == 'e')
{
input.MoveAhead();
if (input.Peek() == '+' || input.Peek() == '-')
{
input.MoveAhead();
}
while (char.IsDigit(input.Peek()))
{
input.MoveAhead();
}
}
// Don't exceed field width
if (spec.Width > 0)
{
var count = input.Position - start;
if (spec.Width < count)
{
input.MoveAhead(spec.Width - count);
}
}
// Because we parse the exponential notation before we apply any field-width constraint, it becomes awkward to verify
// we have a valid floating point token. To prevent an exception, we use TryParse() here instead of Parse().
// Extract token
if (input.Position > start && double.TryParse(input.Extract(start, input.Position), out var result))
{
if (!spec.NoResult)
{
add(spec.Modifier == Modifiers.Long || spec.Modifier == Modifiers.LongLong ? result : result);
}
return(true);
}
return(false);
}
/// <summary>
/// Attempts to parse a field format specifier from the format string.
/// </summary>
static bool ParseFormatSpecifier(TextVisiter format, FormatSpecifier spec)
{
// Return if not a field format specifier
if (format.Peek() != '%')
{
return(false);
}
format.MoveAhead();
// Return if "%%" (treat as '%' literal)
if (format.Peek() == '%')
{
return(false);
}
// Test for asterisk, which indicates result is not stored
if (format.Peek() == '*')
{
spec.NoResult = true; format.MoveAhead();
}
else
{
spec.NoResult = false;
}
// Parse width
var start = format.Position;
while (char.IsDigit(format.Peek()))
{
format.MoveAhead();
}
if (format.Position > start)
{
spec.Width = int.Parse(format.Extract(start, format.Position));
}
else
{
spec.Width = 0;
}
// Parse modifier
if (format.Peek() == 'h')
{
format.MoveAhead();
if (format.Peek() == 'h')
{
format.MoveAhead(); spec.Modifier = Modifiers.ShortShort;
}
else
{
spec.Modifier = Modifiers.Short;
}
}
else if (char.ToLower(format.Peek()) == 'l')
{
format.MoveAhead();
if (format.Peek() == 'l')
{
format.MoveAhead(); spec.Modifier = Modifiers.LongLong;
}
else
{
spec.Modifier = Modifiers.Long;
}
}
else
{
spec.Modifier = Modifiers.None;
}
// Parse type
switch (format.Peek())
{
case 'c': spec.Type = Types.Character; break;
case 'd':
case 'i': spec.Type = Types.Decimal; break;
case 'a':
case 'A':
case 'e':
case 'E':
case 'f':
case 'F':
case 'g':
case 'G': spec.Type = Types.Float; break;
case 'o': spec.Type = Types.Octal; break;
case 's': spec.Type = Types.String; break;
case 'u': spec.Type = Types.Unsigned; break;
case 'x':
case 'X': spec.Type = Types.Hexadecimal; break;
case '[':
spec.Type = Types.ScanSet;
format.MoveAhead();
// Parse scan set characters
if (format.Peek() == '^')
{
spec.ScanSetExclude = true; format.MoveAhead();
}
else
{
spec.ScanSetExclude = false;
}
start = format.Position;
// Treat immediate ']' as literal
if (format.Peek() == ']')
{
format.MoveAhead();
}
format.MoveTo(']');
if (format.EndOfText)
{
throw new Exception("Type specifier expected character : ']'");
}
spec.ScanSet = format.Extract(start, format.Position);
break;
default: throw new Exception($"Unknown format type specified : '{format.Peek()}'");
}
format.MoveAhead();
return(true);
}
