87 lines
3.0 KiB
Go
87 lines
3.0 KiB
Go
package parser
|
|
|
|
import "git.makaay.nl/mauricem/go-parsekit"
|
|
|
|
var (
|
|
// There are four ways to express strings: basic, multi-line basic,
|
|
// literal, and multi-line literal. All strings must contain only valid
|
|
// UTF-8 characters. * Multi-line basic strings are surrounded by three
|
|
// quotation marks on each side. * Basic strings are surrounded by
|
|
// quotation marks.
|
|
doubleQuote3 = c.String(`"""`)
|
|
|
|
// Any Unicode character may be used except those that must be escaped:
|
|
// quotation mark, backslash, and the control characters (U+0000 to
|
|
// U+001F, U+007F).
|
|
charThatMustBeEscaped = c.AnyOf(c.RuneRange('\u0000', '\u001F'), c.Rune('\u007F'))
|
|
|
|
// For convenience, some popular characters have a compact escape sequence.
|
|
//
|
|
// \b - backspace (U+0008)
|
|
// \t - tab (U+0009)
|
|
// \n - linefeed (U+000A)
|
|
// \f - form feed (U+000C)
|
|
// \r - carriage return (U+000D)
|
|
// \" - quote (U+0022)
|
|
// \\ - backslash (U+005C)
|
|
// \uXXXX - unicode (U+XXXX)
|
|
// \UXXXXXXXX - unicode (U+XXXXXXXX)
|
|
validEscapeChar = c.AnyOf(c.Runes('b', 't', 'n', 'f', 'r'), doubleQuote, backslash)
|
|
shortEscape = c.Sequence(backslash, validEscapeChar)
|
|
hex = c.AnyOf(digit, c.RuneRange('a', 'f'), c.RuneRange('A', 'F'))
|
|
shortUtf8Escape = c.Sequence(backslash, c.Rune('u'), c.Repeat(4, hex))
|
|
longUtf8Escape = c.Sequence(backslash, c.Rune('U'), c.Repeat(8, hex))
|
|
validEscape = c.AnyOf(shortEscape, shortUtf8Escape, longUtf8Escape)
|
|
)
|
|
|
|
func startString(p *parsekit.P) {
|
|
p.Expects("a string value")
|
|
switch {
|
|
case p.On(doubleQuote3).RouteTo(startMultiLineBasicString).End():
|
|
case p.On(doubleQuote).RouteTo(startBasicString).End():
|
|
}
|
|
}
|
|
|
|
func startBasicString(p *parsekit.P) {
|
|
p.Expects("a basic string")
|
|
p.On(doubleQuote).Skip().RouteTo(parseBasicString).ThenTo(basicStringSpecifics)
|
|
}
|
|
|
|
func parseBasicString(p *parsekit.P) {
|
|
p.Expects("string contents")
|
|
switch {
|
|
case p.On(charThatMustBeEscaped).End():
|
|
p.EmitError("invalid character in basic string: %q (must be escaped)", p.LastMatch)
|
|
case p.On(validEscape).Accept().RouteRepeat().End():
|
|
case p.On(backslash).RouteReturn().End():
|
|
case p.On(doubleQuote).RouteReturn().End():
|
|
case p.On(anyRune).Accept().RouteRepeat().End():
|
|
}
|
|
}
|
|
|
|
// Specific handling of input for basic strings.
|
|
// * A double quote ends the string
|
|
// * No additional \escape sequences are allowed. What the spec say about this:
|
|
// "All other escape sequences [..] are reserved and, if used, TOML should
|
|
// produce an error.""
|
|
func basicStringSpecifics(p *parsekit.P) {
|
|
p.Expects("string contents")
|
|
switch {
|
|
case p.On(doubleQuote).Skip().End():
|
|
if err := p.EmitInterpreted(ItemString); err != nil { // TODO testcase?
|
|
p.EmitError("invalid data in string: %s", err)
|
|
} else {
|
|
p.RouteTo(startKeyValuePair)
|
|
}
|
|
case p.On(backslash).End():
|
|
p.EmitError("invalid escape sequence")
|
|
}
|
|
}
|
|
|
|
func startMultiLineBasicString(p *parsekit.P) {
|
|
p.Expects("a multi-line basic string")
|
|
if p.On(doubleQuote3).Skip().End() {
|
|
p.EmitError("not yet implemented")
|
|
}
|
|
}
|