Add messy sh lexer

Surprisingly seems to work for everything I looked at in my repos.

1 files changed, 175 insertions, 0 deletions

diff --git a/bin/sh.l b/bin/sh.l
new file mode 100644
index 00000000..77dd2518
--- /dev/null
+++ b/bin/sh.l
@@ -0,0 +1,175 @@
+/* Copyright (C) 2021  C. McEnroe <june@causal.agency>
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+%option prefix="sh"
+%option noyywrap
+
+%{
+#include <assert.h>
+#include <string.h>
+#include "hilex.h"
+
+enum { Cap = 64 };
+static int len = 1;
+static int stack[Cap];
+static int push(int val) {
+	if (len < Cap) stack[len++] = val;
+	return val;
+}
+static int pop(void) {
+	if (len > 1) len--;
+	return stack[len-1];
+}
+%}
+
+%s First
+%s Param Command Arith Backtick
+%x DQuote HereDocDel HereDoc HereDocLit
+
+word [[:alnum:]_.-]+
+param [^:=?+%#{}-]+
+reserved [!{}]|else|do|elif|for|done|fi|then|until|while|if|case|esac
+
+%%
+	static char *delimiter;
+
+[[:blank:]]+ { return Normal; }
+
+"\\". { return Escape; }
+
+<INITIAL,First,DQuote,HereDoc,Param,Command,Arith>{
+	"$"[*@#?$!0-9-] |
+	"$"[_[:alpha:][_[:alnum:]]* |
+	"${"[#]?{param}"}" {
+		return Subst;
+	}
+	"${"{param} {
+		BEGIN(push(Param));
+		return Subst;
+	}
+	"$(" {
+		BEGIN(push(Command));
+		return Subst;
+	}
+	"$((" {
+		BEGIN(push(Arith));
+		return Subst;
+	}
+	"`" {
+		BEGIN(push(Backtick));
+		return Subst;
+	}
+}
+<Param>"}" |
+<Command>")" |
+<Arith>"))" |
+<Backtick>"`" {
+	BEGIN(pop());
+	return Subst;
+}
+
+[&();|]|"&&"|";;"|"||" {
+	BEGIN(push(First));
+	return Operator;
+}
+[0-9]?([<>]"&"?|">|"|">>"|"<>") {
+	return Operator;
+}
+
+^{reserved} { return Keyword; }
+<First>{
+	[[:blank:]]+ { return Normal; }
+	{reserved} {
+		BEGIN(pop());
+		return Keyword;
+	}
+	{word} {
+		BEGIN(pop());
+		return Normal;
+	}
+}
+
+{word}/[[:blank:]]*"()" { return Ident; }
+
+[0-9]?("<<"|"<<-") {
+	BEGIN(push(HereDocDel));
+	return Operator;
+}
+<HereDocDel>{
+	[[:blank:]]+ { return Normal; }
+	{word} {
+		delimiter = strdup(yytext);
+		assert(delimiter);
+		BEGIN(pop(), push(HereDoc));
+		return Ident;
+	}
+	"'"{word}"'" {
+		delimiter = strndup(&yytext[1], strlen(yytext)-2);
+		assert(delimiter);
+		BEGIN(pop(), push(HereDocLit));
+		return Ident;
+	}
+}
+<HereDoc,HereDocLit>{
+	^"\t"*{word} {
+		if (strcmp(&yytext[strspn(yytext, "\t")], delimiter)) REJECT;
+		free(delimiter);
+		BEGIN(pop());
+		return Ident;
+	}
+}
+<HereDoc>{
+	[^$`\n]+ { return String; }
+	.|\n { return String; }
+}
+<HereDocLit>{
+	.*\n { return String; }
+}
+
+"'"[^'']*"'" { return String; }
+
+"\""/[^$`\\] {
+	BEGIN(push(DQuote));
+	yymore();
+}
+"\"" {
+	BEGIN(push(DQuote));
+	return String;
+}
+
+<DQuote>{
+	[^\\$`""]*"\"" {
+		BEGIN(pop());
+		return String;
+	}
+	"\\"[$`""\\\n] { return Escape; }
+	[^\\$`""]+|. { return String; }
+}
+
+<INITIAL,First,Command,Backtick,Arith>"#".* { return Comment; }
+
+{word} { return Normal; }
+
+.|\n { return Normal; }
+
+%{
+	(void)yyunput;
+	(void)input;
+%}
+
+%%
+
+const struct Lexer LexSh = { yylex, &yyin, &yytext };