From 0a8690993d572a50b95dd4f1c1903ed00ddb9c2b Mon Sep 17 00:00:00 2001
From: Charlie Stanton <charlie@shtanton.xyz>
Date: Wed, 21 Sep 2022 21:05:34 +0100
Subject: Initial commit

Parses and executes substitute expressions (subexes)

So far subex has the following operations:
- Concatenation of a and b with ab
- Or with |
- Repeat maximally with *
- Repeat minimally with -
- Copy a specific character 'a'
- Copy any character '.'
- Store text matching a regex into slot 's': `$s(regex)`
- Output text in "" including loading from slots with '$'

Regexes support all the same operations as subexes minus storing and outputting

This first implementation gives very little thought to efficiency

Example:

./main 'according to all known laws of aviation' '$1(.-)$m(( .* )| ).*"$m$1"'

This swaps the first and last words of the input string
---
 main/lex.go | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100644 main/lex.go

(limited to 'main/lex.go')

diff --git a/main/lex.go b/main/lex.go
new file mode 100644
index 0000000..c08f402
--- /dev/null
+++ b/main/lex.go
@@ -0,0 +1,34 @@
+package main
+
+import (
+	"unicode/utf8"
+)
+
+const eof rune = -1
+type RuneReader struct {
+	input string
+	pos, width int
+}
+func (l *RuneReader) next() rune {
+	if l.pos >= len(l.input) {
+		l.width = 0
+		return eof
+	}
+	var r rune
+	r, l.width = utf8.DecodeRuneInString(l.input[l.pos:])
+	l.pos += l.width
+	return r
+}
+func (l *RuneReader) accept(chars string) bool {
+	r := l.next()
+	for _, char := range chars {
+		if char == r {
+			return true
+		}
+	}
+	l.rewind()
+	return false
+}
+func (l *RuneReader) rewind() {
+	l.pos -= l.width
+}
-- 
cgit v1.2.3