scanner: multibyte rune literals now support unicode, hex, and octal escape codes (#13140)

.editorconfig

@@ -16,6 +16,11 @@ indent_size = 2
 
 [*.md]
 trim_trailing_whitespace = false
+# lines that are too long will trigger an error in cmd/tools/vcheck-md.v
+# run v check-md [folder/file] to test markdown files
+# the longest normal line is specified with this constant:
+# `too_long_line_length_other     = 100`
+max_line_length = 100
 
 [*.{txt,out}]
 insert_final_newline = false

doc/docs.md

@@ -476,16 +476,33 @@ d := b + x     // d is of type `f64` - automatic promotion of `x`'s value
 
 ### Strings
 
-```v
+```v nofmt
 name := 'Bob'
-println(name.len)
+assert name.len == 3       // will print 3
-println(name[0]) // indexing gives a byte B
+assert name[0] == byte(66) // indexing gives a byte, byte(66) == `B`
-println(name[1..3]) // slicing gives a string 'ob'
+assert name[1..3] == 'ob'  // slicing gives a string 'ob'
+
+// escape codes
 windows_newline := '\r\n'      // escape special characters like in C
 assert windows_newline.len == 2
+
+// arbitrary bytes can be directly specified using `\x##` notation where `#` is
+// a hex digit aardvark_str := '\x61ardvark' assert aardvark_str == 'aardvark'
+assert '\xc0'[0] == byte(0xc0)
+
+// or using octal escape `\###` notation where `#` is an octal digit
+aardvark_str2 := '\141ardvark'
+assert aardvark_str2 == 'aardvark'
+
+// Unicode can be specified directly as `\u####` where # is a hex digit
+// and will be converted internally to its UTF-8 representation
+star_str := '\u2605' // ★
+assert star_str == '★'
+assert star_str == '\xe2\x98\x85' // UTF-8 can be specified this way too.
 ```
 
-In V, a string is a read-only array of bytes. String data is encoded using UTF-8:
+In V, a string is a read-only array of bytes. All Unicode characters are encoded using UTF-8:
+
 ```v
 s := 'hello 🌎' // emoji takes 4 bytes
 assert s.len == 10
@@ -503,11 +520,12 @@ String values are immutable. You cannot mutate elements:
 mut s := 'hello 🌎'
 s[0] = `H` // not allowed
 ```
+
 > error: cannot assign to `s[i]` since V strings are immutable
 
-Note that indexing a string will produce a `byte`, not a `rune` nor another `string`.
+Note that indexing a string will produce a `byte`, not a `rune` nor another `string`. Indexes
-Indexes correspond to bytes in the string, not Unicode code points. If you want to
+correspond to _bytes_ in the string, not Unicode code points. If you want to convert the `byte` to a
-convert the `byte` to a `string`, use the `ascii_str()` method:
+`string`, use the `.ascii_str()` method on the `byte`:
 
 ```v
 country := 'Netherlands'
@@ -515,20 +533,13 @@ println(country[0]) // Output: 78
 println(country[0].ascii_str()) // Output: N
 ```
 
-Character literals have type `rune`. To denote them, use `
+Both single and double quotes can be used to denote strings. For consistency, `vfmt` converts double
+quotes to single quotes unless the string contains a single quote character.
+
+For raw strings, prepend `r`. Escape handling is not done for raw strings:
 
 ```v
-rocket := `🚀`
+s := r'hello\nworld' // the `\n` will be preserved as two characters
-assert 'aloha!'[0] == `a`
-```
-
-Both single and double quotes can be used to denote strings. For consistency,
-`vfmt` converts double quotes to single quotes unless the string contains a single quote character.
-
-For raw strings, prepend `r`. Raw strings are not escaped:
-
-```v
-s := r'hello\nworld'
 println(s) // "hello\nworld"
 ```
 
@@ -537,41 +548,79 @@ Strings can be easily converted to integers:
 ```v
 s := '42'
 n := s.int() // 42
+
+// all int literals are supported
+assert '0xc3'.int() == 195
+assert '0o10'.int() == 8
+assert '0b1111_0000_1010'.int() == 3850
+assert '-0b1111_0000_1010'.int() == -3850
 ```
 
-### Runes
+For more advanced `string` processing and conversions, refer to the
-A `rune` represents a unicode character and is an alias for `u32`. Runes can be created like this:
+[vlib/strconv](https://modules.vlang.io/strconv.html) module.
-```v
-x := `🚀`
-```
-
-A string can be converted to runes by the `.runes()` method.
-```v
-hello := 'Hello World 👋'
-hello_runes := hello.runes() // [`H`, `e`, `l`, `l`, `o`, ` `, `W`, `o`, `r`, `l`, `d`, ` `, `👋`]
-```
 
 ### String interpolation
 
-Basic interpolation syntax is pretty simple - use `$` before a variable name.
+Basic interpolation syntax is pretty simple - use `$` before a variable name. The variable will be
-The variable will be converted to a string and embedded into the literal:
+converted to a string and embedded into the literal:
+
 ```v
 name := 'Bob'
 println('Hello, $name!') // Hello, Bob!
 ```
-It also works with fields: `'age = $user.age'`.
-If you need more complex expressions, use `${}`: `'can register = ${user.age > 13}'`.
 
-Format specifiers similar to those in C's `printf()` are also supported.
+It also works with fields: `'age = $user.age'`. If you need more complex expressions, use `${}`:
-`f`, `g`, `x`, etc. are optional and specify the output format.
+`'can register = ${user.age > 13}'`.
-The compiler takes care of the storage size, so there is no `hd` or `llu`.
+
+Format specifiers similar to those in C's `printf()` are also supported. `f`, `g`, `x`, `o`, `b`,
+etc. are optional and specify the output format. The compiler takes care of the storage size, so
+there is no `hd` or `llu`.
+
+To use a format specifier, follow this pattern:
+
+`${varname:[flags][width][.precision][type]}`
+
+- flags: may be zero or more of the following: `-` to left-align output within the field, `0` to use
+  `0` as the padding character instead of the default `space` character. (Note: V does not currently
+  support the use of `'` or `#` as format flags, and V supports but doesn't need `+` to right-align
+  since that's the default.)
+- width: may be an integer value describing the minimum width of total field to output.
+- precision: an integer value preceeded by a `.` will guarantee that many digits after the decimal
+  point, if the input variable is a float. Ignored if variable is an integer.
+- type: `f` and `F` specify the input is a float and should be rendered as such, `e` and `E` specify
+  the input is a float and should be rendered as an exponent (partially broken), `g` and `G` specify
+  the input is a float--the renderer will use floating point notation for small values and exponent
+  notation for large values, `d` specifies the input is an integer and should be rendered in base-10
+  digits, `x` and `X` require an integer and will render it as hexadecimal digits, `o` requires an
+  integer and will render it as octal digits, `b` requires an integer and will render it as binary
+  digits, `s` requires a string (almost never used).
+
+Note: when a numeric type can render alphabetic characters, such as hex strings or special values
+like `infinity`, the lowercase version of the type forces lowercase alphabetics and the uppercase
+version forces uppercase alphabetics.
+
+Also note: in most cases, it's best to leave the format type empty. Floats will be rendered by
+default as `g`, integers will be rendered by default as `d`, and `s` is almost always redundant.
+There are only three cases where specifying a type is recommended:
+
+- format strings are parsed at compile time, so specifing a type can help detect errors then
+- format strings default to using lowercase letters for hex digits and the `e` in exponents. Use a
+  uppercase type to force the use of uppercase hex digits and an uppercase `E` in exponents.
+- format strings are the most convenient way to get hex, binary or octal strings from an integer.
+
+See
+[Format Placeholder Specification](https://en.wikipedia.org/wiki/Printf_format_string#Format_placeholder_specification)
+for more information.
 
 ```v
 x := 123.4567
-println('x = ${x:4.2f}')
+println('[${x:.2}]') // round to two decimal places => [123.46]
-println('[${x:10}]') // pad with spaces on the left => [   123.457]
+println('[${x:10}]') // right-align with spaces on the left => [   123.457]
-println('[${int(x):-10}]') // pad with spaces on the right => [123       ]
+println('[${int(x):-10}]') // left-align with spaces on the right => [123       ]
 println('[${int(x):010}]') // pad with zeros on the left => [0000000123]
+println('[${int(x):b}]') // output as binary => [1111011]
+println('[${int(x):o}]') // output as octal => [173]
+println('[${int(x):X}]') // output as uppercase hex => [7B]
 ```
 
 ### String operators
@@ -585,13 +634,14 @@ s += 'world' // `+=` is used to append to a string
 println(s) // "hello world"
 ```
 
-All operators in V must have values of the same type on both sides.
+All operators in V must have values of the same type on both sides. You cannot concatenate an
-You cannot concatenate an integer to a string:
+integer to a string:
 
 ```v failcompile
 age := 10
 println('age = ' + age) // not allowed
 ```
+
 > error: infix expr: cannot use `int` (right expression) as `string`
 
 We have to either convert `age` to a `string`:
@@ -608,6 +658,62 @@ age := 12
 println('age = $age')
 ```
 
+### Runes
+
+A `rune` represents a single Unicode character and is an alias for `u32`. To denote them, use `
+(backticks) :
+
+```v
+rocket := `🚀`
+```
+
+A `rune` can be converted to a UTF-8 string by using the `.str()` method.
+
+```v
+rocket := `🚀`
+assert rocket.str() == '🚀'
+```
+
+A `rune` can be converted to UTF-8 bytes by using the `.bytes()` method.
+
+```v
+rocket := `🚀`
+assert rocket.bytes() == [byte(0xf0), 0x9f, 0x9a, 0x80]
+```
+
+Hex, Unicode, and Octal escape sequences also work in a `rune` literal:
+
+```v
+assert `\x61` == `a`
+assert `\141` == `a`
+assert `\u0061` == `a`
+
+// multibyte literals work too
+assert `\u2605` == `★`
+assert `\u2605`.bytes() == [byte(0xe2), 0x98, 0x85]
+assert `\xe2\x98\x85`.bytes() == [byte(0xe2), 0x98, 0x85]
+assert `\342\230\205`.bytes() == [byte(0xe2), 0x98, 0x85]
+```
+
+Note that `rune` literals use the same escape syntax as strings, but they can only hold one unicode
+character. Therefore, if your code does not specify a single Unicode character, you will receive an
+error at compile time.
+
+Also remember that strings are indexed as bytes, not runes, so beware:
+
+```v
+rocket_string := '🚀'
+assert rocket_string[0] != `🚀`
+assert 'aloha!'[0] == `a`
+```
+
+A string can be converted to runes by the `.runes()` method.
+
+```v
+hello := 'Hello World 👋'
+hello_runes := hello.runes() // [`H`, `e`, `l`, `l`, `o`, ` `, `W`, `o`, `r`, `l`, `d`, ` `, `👋`]
+```
+
 ### Numbers
 
 ```v

vlib/v/scanner/scanner.v

@@ -1307,6 +1307,28 @@ fn decode_h_escapes(s string, start int, escapes_pos []int) string {
 	return ss.join('')
 }
 
+// handle single-byte inline octal escapes like '\###'
+fn decode_o_escapes(s string, start int, escapes_pos []int) string {
+	if escapes_pos.len == 0 {
+		return s
+	}
+	mut ss := []string{cap: escapes_pos.len}
+	ss << s[..escapes_pos.first() - start] // everything before the first escape code position
+	for i, pos in escapes_pos {
+		idx := pos - start
+		end_idx := idx + 4 // "\XXX".len == 4
+		// notice this function doesn't do any decoding... it just replaces '\141' with the byte 0o141
+		ss << [byte(strconv.parse_uint(s[idx + 1..end_idx], 8, 8) or { 0 })].bytestr()
+		if i + 1 < escapes_pos.len {
+			ss << s[end_idx..escapes_pos[i + 1] - start]
+		} else {
+			ss << s[end_idx..]
+		}
+	}
+	return ss.join('')
+}
+
+// decode the flagged unicode escape sequences into their utf-8 bytes
 fn decode_u_escapes(s string, start int, escapes_pos []int) string {
 	if escapes_pos.len == 0 {
 		return s
@@ -1348,9 +1370,10 @@ fn trim_slash_line_break(s string) string {
 /// possibilities:
 ///   single chars like `a`, `b` => 'a', 'b'
 ///   escaped single chars like `\\`, `\``, `\n` => '\\', '`', '\n'
-///   escaped hex bytes like `\x01`, `\x61` => '\x01', 'a'
+///   escaped single hex bytes like `\x01`, `\x61` => '\x01', 'a'
-///   escaped multibyte runes like `\xe29885` => (★)
 ///   escaped unicode literals like `\u2605`
+///   escaped utf8 runes in hex like `\xe2\x98\x85` => (★)
+///   escaped utf8 runes in octal like `\342\230\205` => (★)
 fn (mut s Scanner) ident_char() string {
 	lspos := token.Position{
 		line_nr: s.line_nr
@@ -1365,6 +1388,7 @@ fn (mut s Scanner) ident_char() string {
 	// set flags for advanced escapes first
 	escaped_hex := s.expect('\\x', start + 1)
 	escaped_unicode := s.expect('\\u', start + 1)
+	escaped_octal := !escaped_hex && !escaped_unicode && s.expect('\\', start + 1)
 
 	// walk the string to get characters up to the next backtick
 	for {
@@ -1390,65 +1414,40 @@ fn (mut s Scanner) ident_char() string {
 		return c
 	}
 	if len != 1 {
+		// the string inside the backticks is longer than one character
+		// but we might only have one rune... attempt to decode escapes
 		// if the content expresses an escape code, it will have an even number of characters
-		// e.g. \x61 or \u2605
+		// e.g. (octal) \141 (hex) \x61 or (unicode) \u2605
-		if (c.len % 2 == 0) && (escaped_hex || escaped_unicode) {
+		// we don't handle binary escape codes in rune literals
+		orig := c
+		if (c.len % 2 == 0) && (escaped_hex || escaped_unicode || escaped_octal) {
 			if escaped_unicode {
+				// there can only be one, so attempt to decode it now
 				c = decode_u_escapes(c, 0, [0])
 			} else {
-				// we have to handle hex ourselves
+				// find escape sequence start positions
-				ascii_0 := byte(0x30)
+				mut escapes_pos := []int{}
-				ascii_a := byte(0x61)
+				for i, v in c {
-				mut accumulated := []byte{}
+					if v == `\\` {
-				val := c[2..c.len].to_lower() // 0A -> 0a
+						escapes_pos << i
-				mut offset := 0
-				// take two characters at a time, parse as hex and add to bytes
-				for {
-					if offset >= val.len - 1 {
-						break
 					}
-					mut byteval := byte(0)
-					big := val[offset]
-					little := val[offset + 1]
-					if !big.is_hex_digit() {
-						accumulated.clear()
-						break
 				}
-					if !little.is_hex_digit() {
+				if escaped_hex {
-						accumulated.clear()
+					c = decode_h_escapes(c, 0, escapes_pos)
-						break
-					}
-
-					if big.is_digit() {
-						byteval |= (big - ascii_0) << 4
 				} else {
-						byteval |= (big - ascii_a + 10) << 4
+					c = decode_o_escapes(c, 0, escapes_pos)
-					}
-					if little.is_digit() {
-						byteval |= (little - ascii_0)
-					} else {
-						byteval |= (little - ascii_a + 10)
-					}
-
-					accumulated << byteval
-					offset += 2
-				}
-				if accumulated.len > 0 {
-					c = accumulated.bytestr()
 				}
 			}
 		}
 
-		// the string inside the backticks is longer than one character
-		// but we might only have one rune, say in the case
 		u := c.runes()
 		if u.len != 1 {
 			if escaped_hex || escaped_unicode {
-				s.error('invalid character literal (escape sequence did not refer to a singular rune)')
+				s.error('invalid character literal `$orig` => `$c` ($u) (escape sequence did not refer to a singular rune)')
 			} else {
 				s.add_error_detail_with_pos('use quotes for strings, backticks for characters',
 					lspos)
-				s.error('invalid character literal (more than one character)')
+				s.error('invalid character literal `$orig` => `$c` ($u) (more than one character)')
 			}
 		}
 	}

vlib/v/scanner/scanner_test.v

@@ -150,13 +150,19 @@ fn test_ref_ref_array_ref_ref_foo() {
 	assert result[6] == .name
 }
 
-fn test_escape_string() {
+fn test_escape_rune() {
-	// these assertions aren't helpful...
+	// these lines work if the v compiler is working
-	// they test the vlib built-in to the compiler,
+	// will not work until v compiler on github is updated
-	// but we want to test this module before compilation
+	// assert `\x61` == `a`
-	assert '\x61' == 'a'
+	// assert `\u0061` == `a`
-	assert '\x62' == 'b'
+
-	// assert `\x61` == `a` // will work after pull request goes through
+	// will not work until PR is accepted
+	// assert `\141` == `a`
+	// assert `\xe2\x98\x85` == `★`
+	// assert `\342\230\205` == `★`
+
+	// the following lines test the scanner module
+	// even before it is compiled into the v executable
 
 	// SINGLE CHAR ESCAPES
 	// SINGLE CHAR APOSTROPHE
@@ -187,14 +193,30 @@ fn test_escape_string() {
 	// SINGLE CHAR INCORRECT ESCAPE
 	// result = scan_tokens(r'`\x61\x61`') // should always result in an error
 
-	// SINGLE CHAR MULTI-BYTE UTF-8
+	// SINGLE CHAR MULTI-BYTE UTF-8 (hex)
-	// Compilation blocked by vlib/v/checker/check_types.v, but works in the repl
+	result = scan_tokens(r'`\xe2\x98\x85`')
-	result = scan_tokens(r'`\xe29885`')
 	assert result[0].lit == r'★'
 
+	// SINGLE CHAR MULTI-BYTE UTF-8 (octal)
+	result = scan_tokens(r'`\342\230\205`')
+	assert result[0].lit == r'★'
+}
+
+fn test_escape_string() {
+	// these lines work if the v compiler is working
+	assert '\x61' == 'a'
+	assert '\x62' == 'b'
+	assert '\u0061' == 'a'
+	assert '\141' == 'a'
+	assert '\xe2\x98\x85' == '★'
+	assert '\342\230\205' == '★'
+
+	// the following lines test the scanner module
+	// even before it is compiled into the v executable
+
 	// STRING ESCAPES =================
 	// STRING APOSTROPHE
-	result = scan_tokens(r"'\''")
+	mut result := scan_tokens(r"'\''")
 	assert result[0].kind == .string
 	assert result[0].lit == r"\'"