Merge pull request #6 from kbkpbot/master

byte is deprecated, use u8 instead

README.md

@@ -19,38 +19,39 @@ It is written in V, hence the name.
 [Hexadecimal color](https://developer.mozilla.org/en-US/docs/Web/CSS/color) parser:
 
 ```v
-import strconv
+module main
+
 import vom { is_hex_digit, tag, take_while_m_n, tuple }
 
 struct Color {
-	red   byte
-	green byte
-	blue  byte
+        red   u8
+        green u8
+        blue  u8
 }
 
-fn from_hex(input string) ?byte {
-	return byte(strconv.parse_uint(input, 16, 8) ?)
+fn from_hex(input string) u8 {
+        return '0x${input}'.u8()
 }
 
-fn hex_primary(input string) ?(string, string) {
-	parser := take_while_m_n(2, 2, is_hex_digit)
-	return parser(input)
+fn hex_primary(input string) !(string, string, int) {
+        parser := take_while_m_n(2, 2, is_hex_digit)
+        return parser(input)
 }
 
-fn hex_color(input string) ?(string, Color) {
-	discard := tag('#')
-	hex_part, _ := discard(input) ?
-	parser := tuple([hex_primary, hex_primary, hex_primary])
-	rest, output := parser(hex_part) ?
-	red, green, blue := from_hex(output[0]) ?, from_hex(output[1]) ?, from_hex(output[2]) ?
-	return rest, Color{red, green, blue}
+fn hex_color(input string) !(string, Color) {
+        discard := tag('#')
+        hex_part, _, _ := discard(input)!
+        parser := tuple([hex_primary, hex_primary, hex_primary])
+        rest, output, _ := parser(hex_part)!
+        red, green, blue := from_hex(output[0]), from_hex(output[1]), from_hex(output[2])
+        return rest, Color{red, green, blue}
 }
 
 fn main() {
-	_, color := hex_color('#2F14DF') ?
-	assert color == Color{47, 20, 223}
+        _, color := hex_color('#2F14DF')!
+        assert color == Color{47, 20, 223}
+        println(color)
 }
-
 ```
 
 ## When will it reach 1.0?

bytes.v

@@ -86,7 +86,7 @@ pub fn take(n int) Fn {
 }
 
 // Returns the longest input slice (if any) till a predicate `condition` is met.
-pub fn take_till(condition fn (byte) bool) Fn {
+pub fn take_till(condition fn (u8) bool) Fn {
 	return fn [condition] (input string) !(string, string, int) {
 		for i, c in input.bytes() {
 			if condition(c) {
@@ -98,7 +98,7 @@ pub fn take_till(condition fn (byte) bool) Fn {
 }
 
 // Returns the longest (at least 1) input slice till a predicate `condition` is met.
-pub fn take_till1(condition fn (byte) bool) Fn {
+pub fn take_till1(condition fn (u8) bool) Fn {
 	return fn [condition] (input string) !(string, string, int) {
 		for i, c in input.bytes() {
 			if condition(c) && i > 0 {
@@ -134,7 +134,7 @@ pub fn take_until1(pattern string) Fn {
 }
 
 // Returns the longest input slice (if any) that matches the predicate `condition`.
-pub fn take_while(condition fn (byte) bool) Fn {
+pub fn take_while(condition fn (u8) bool) Fn {
 	return fn [condition] (input string) !(string, string, int) {
 		for i, c in input.bytes() {
 			if !condition(c) {
@@ -146,7 +146,7 @@ pub fn take_while(condition fn (byte) bool) Fn {
 }
 
 // Returns the longest (at least 1) input slice that matches the predicate `condition`.
-pub fn take_while1(condition fn (byte) bool) Fn {
+pub fn take_while1(condition fn (u8) bool) Fn {
 	return fn [condition] (input string) !(string, string, int) {
 		for i, c in input.bytes() {
 			if !condition(c) {
@@ -161,7 +161,7 @@ pub fn take_while1(condition fn (byte) bool) Fn {
 }
 
 // Returns the longest (m <= len <= n) input slice that matches the predicate `condition`.
-pub fn take_while_m_n(m int, n int, condition fn (byte) bool) Fn {
+pub fn take_while_m_n(m int, n int, condition fn (u8) bool) Fn {
 	return fn [m, n, condition] (input string) !(string, string, int) {
 		mut longest := -1
 		for i, c in input.bytes() {

bytes_test.v

@@ -100,7 +100,7 @@ fn test_take() ! {
 }
 
 fn test_take_till() ! {
-	parser := take_till(fn (b byte) bool {
+	parser := take_till(fn (b u8) bool {
 		return b == `:`
 	})
 	rest, output, len := parser('latin:123')!
@@ -110,7 +110,7 @@ fn test_take_till() ! {
 }
 
 fn test_take_till1() ! {
-	parser := take_till1(fn (b byte) bool {
+	parser := take_till1(fn (b u8) bool {
 		return b == `:`
 	})
 	rest, output, len := parser(':latin:123')!

character.v

@@ -2,38 +2,38 @@ module vom
 
 // Based on https://docs.rs/nom/7.1.3/nom/character/index.html
 
-// Tests if byte is ASCII alphabetic: A-Z, a-z.
-pub fn is_alphabetic(b byte) bool {
+// Tests if u8 is ASCII alphabetic: A-Z, a-z.
+pub fn is_alphabetic(b u8) bool {
 	return 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'.bytes().any(it == b)
 }
 
-// Tests if byte is ASCII alphanumeric: A-Z, a-z, 0-9.
-pub fn is_alphanumeric(b byte) bool {
+// Tests if u8 is ASCII alphanumeric: A-Z, a-z, 0-9.
+pub fn is_alphanumeric(b u8) bool {
 	return is_alphabetic(b) || is_digit(b)
 }
 
-// Tests if byte is ASCII digit: 0-9.
-pub fn is_digit(b byte) bool {
+// Tests if u8 is ASCII digit: 0-9.
+pub fn is_digit(b u8) bool {
 	return '0123456789'.bytes().any(it == b)
 }
 
-// Tests if byte is ASCII hex digit: 0-9, A-F, a-f.
-pub fn is_hex_digit(b byte) bool {
+// Tests if u8 is ASCII hex digit: 0-9, A-F, a-f.
+pub fn is_hex_digit(b u8) bool {
 	return is_digit(b) || 'ABCDEF'.bytes().any(it == b) || 'abcdef'.bytes().any(it == b)
 }
 
-// Tests if byte is ASCII newline: \n.
-pub fn is_newline(b byte) bool {
+// Tests if u8 is ASCII newline: \n.
+pub fn is_newline(b u8) bool {
 	return b == `\n`
 }
 
-// Tests if byte is ASCII octal digit: 0-7.
-pub fn is_oct_digit(b byte) bool {
+// Tests if u8 is ASCII octal digit: 0-7.
+pub fn is_oct_digit(b u8) bool {
 	return '01234567'.bytes().any(it == b)
 }
 
-// Tests if byte is ASCII space or tab.
-pub fn is_space(b byte) bool {
+// Tests if u8 is ASCII space or tab.
+pub fn is_space(b u8) bool {
 	return ' \t'.bytes().any(it == b)
 }
 
@@ -107,15 +107,15 @@ pub fn line_ending(input string) !(string, string, int) {
 
 // Recognizes zero or more spaces, tabs, carriage returns and line feeds.
 pub fn multispace0(input string) !(string, string, int) {
-	parser := take_while(fn (b byte) bool {
+	parser := take_while(fn (b u8) bool {
 		return ' \t\n\r'.bytes().any(it == b)
 	})
 	return parser(input)
 }
 
 // Recognizes one or more spaces, tabs, carriage returns and line feeds.
 pub fn multispace1(input string) !(string, string, int) {
-	parser := take_while1(fn (b byte) bool {
+	parser := take_while1(fn (b u8) bool {
 		return ' \t\n\r'.bytes().any(it == b)
 	})
 	return parser(input)
@@ -143,7 +143,7 @@ pub fn none_of(pattern string) Fn {
 
 // Recognizes a string of any char except '\r\n' or '\n'.
 pub fn not_line_ending(input string) !(string, string, int) {
-	parser := take_while(fn (b byte) bool {
+	parser := take_while(fn (b u8) bool {
 		return '\r\n'.bytes().all(it != b)
 	})
 	return parser(input)
@@ -176,7 +176,7 @@ pub fn one_of(pattern string) Fn {
 }
 
 // Recognizes one character and checks that it satisfies a predicate
-pub fn satisfy(condition fn (byte) bool) Fn {
+pub fn satisfy(condition fn (u8) bool) Fn {
 	return fn [condition] (input string) !(string, string, int) {
 		if input.len == 0 {
 			return error('`satisfy` failed because input is empty')

character_test.v

@@ -136,7 +136,7 @@ fn test_one_of() ! {
 }
 
 fn test_satisfy() ! {
-	parser := satisfy(fn (b byte) bool {
+	parser := satisfy(fn (b u8) bool {
 		return b == `a` || b == `b`
 	})
 	rest, output, len := parser('abc')!

examples/hexadecimal/hexadecimal.v

@@ -3,12 +3,12 @@ module main
 import vom { is_hex_digit, tag, take_while_m_n, tuple }
 
 struct Color {
-	red   byte
-	green byte
-	blue  byte
+	red   u8
+	green u8
+	blue  u8
 }
 
-fn from_hex(input string) byte {
+fn from_hex(input string) u8 {
 	return '0x${input}'.u8()
 }
 

examples/lua/lua.v

@@ -31,7 +31,7 @@ fn keyword(input string, location Location) !(string, Token) {
 }
 
 fn identifier(input string, location Location) !(string, Token) {
-	rest, output := alphanumeric1(input)!
+	rest, output, _ := alphanumeric1(input)!
 	if is_digit(output[0]) {
 		return error('${output} starts with digit')
 	} else {

regex.v

@@ -0,0 +1,85 @@
+module vom
+
+// https://www.cnblogs.com/baiyuxuan/p/15430458.html
+// 从字符串生成Regex
+
+pub struct Regex {
+	expr	string
+mut:	ind	int
+}
+
+fn (r Regex) peek() char {
+	return expr[ind]
+}
+
+fn (r Regex) next() char {
+	c := expr[ind]
+	ind ++
+	return c
+}
+
+fn (r Regex) read(c char) ! {
+	if c != next() {
+		return error('expected: ${c}')
+	}
+}
+
+fn (r Regex) end() bool {
+	return ind == expr.len
+}
+
+fn (r Regex) parse() ! {
+	ind = 0
+	return parse_expr()
+}
+
+// elem = char | (expr)
+fn (r Regex) parse_elem() ! {
+	if peek() == `(` {
+		next()
+		rr := parse_expr()
+		read(`)`)
+		return rr
+	} else if peek() == `.` {
+		next()
+		return any()
+	} else {
+		return ch(next())
+	}
+}
+
+// factor = elem* | elem+ | elem
+fn (r Regex) parse_factor() ! {
+	mut r := parse_elem()
+	if !end() && peek() == `*` {
+		r = r.zeroOrMore()
+		next()
+	} else if !end() && peek() == `+` {
+		r = r.oneOrMore()
+		next()
+	}
+	return r
+}
+
+// term = factor factor ... factor
+fn (r Regex) parse_term() ! {
+	mut r := parse_factor()
+	for !end() && peek() != ')' && peek() != '|' {
+		r = r.concat(parseFactor())
+	}
+	return r
+}
+
+// expr = term|term|...|term
+fn (r Regex) parse_expr() ! {
+	mut r := parse_term()
+
+	for !end() && peek() == '|' {
+		next()
+		r = r.or(parse_term())
+	}
+	return r
+}
+
+
+

regex_test.v

@@ -0,0 +1,10 @@
+module vom
+
+fn test_regex() ! {
+	parser := Regex{expr:'((a|b)c*)+'}
+	rest, output, len := parser('acc')
+	assert rest == ''
+	assert output == 'acc'
+	assert len == 3
+}
+