lexers: Add BIND DNS Zone lexer

Closes #623 Signed-off-by: Mubashshir <ahmubashshir@gmail.com>
alecthomas · Jun 27, 2022 · 5ce1d5d · 5ce1d5d
1 parent f941d46
commit 5ce1d5d
Show file tree

Hide file tree

Showing 4 changed files with 176 additions and 0 deletions.
diff --git a/lexers/dns.go b/lexers/dns.go
@@ -0,0 +1,17 @@
+package lexers
+
+import (
+	"regexp"
+)
+
+// TODO(moorereason): can this be factored away?
+var zoneAnalyserRe = regexp.MustCompile(`(?m)^@\s+IN\s+SOA\s+`)
+
+func init() { // nolint: gochecknoinits
+	Get("dns").SetAnalyser(func(text string) float32 {
+		if zoneAnalyserRe.FindString(text) != "" {
+			return 1.0
+		}
+		return 0.0
+	})
+}
diff --git a/lexers/embedded/dns.xml b/lexers/embedded/dns.xml
@@ -0,0 +1,42 @@
+<?xml version="1.0"?>
+<lexer>
+  <config>
+    <name>dns</name>
+    <alias>zone</alias>
+    <alias>bind</alias>
+  </config>
+  <rules>
+    <state name="root">
+      <rule pattern="\b(IN|A|AAAA|AFSDB|APL|CAA|CDNSKEY|CDS|CERT|CNAME|DHCID|DLV|DNAME|DNSKEY|DS|HIP|IPSECKEY|KEY|KX|LOC|MX|NAPTR|NS|NSEC|NSEC3|NSEC3PARAM|PTR|RRSIG|RP|SIG|SOA|SRV|SSHFP|TA|TKEY|TLSA|TSIG|TXT)\b">
+        <token type="Keyword"/>
+      </rule>
+      <rule pattern=";.*(\S|$)">
+        <token type="Comment"/>
+      </rule>
+      <rule pattern="\b((([0-9A-Fa-f]{1,4}:){7}([0-9A-Fa-f]{1,4}|:))|(([0-9A-Fa-f]{1,4}:){6}(:[0-9A-Fa-f]{1,4}|((25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){5}(((:[0-9A-Fa-f]{1,4}){1,2})|:((25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){4}(((:[0-9A-Fa-f]{1,4}){1,3})|((:[0-9A-Fa-f]{1,4})?:((25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){3}(((:[0-9A-Fa-f]{1,4}){1,4})|((:[0-9A-Fa-f]{1,4}){0,2}:((25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){2}(((:[0-9A-Fa-f]{1,4}){1,5})|((:[0-9A-Fa-f]{1,4}){0,3}:((25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){1}(((:[0-9A-Fa-f]{1,4}){1,6})|((:[0-9A-Fa-f]{1,4}){0,4}:((25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)){3}))|:))|(:(((:[0-9A-Fa-f]{1,4}){1,7})|((:[0-9A-Fa-f]{1,4}){0,5}:((25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)){3}))|:)))\b">
+        <token type="LiteralNumberIntegerLong"/>
+      </rule>
+      <rule pattern="\b((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\b">
+        <token type="LiteralNumberInteger"/>
+      </rule>
+      <rule pattern="\b\d+[dhwm]?">
+        <token type="LiteralStringChar"/>
+      </rule>
+      <rule pattern="\b([[:alnum:].-])+\.($|\s)">
+        <token type="NameProperty"/>
+      </rule>
+      <rule pattern="^(@|[[:alnum:]-]+)">
+        <token type="NameClass"/>
+      </rule>
+      <rule pattern="^\$(TTL|GENERATE|INCLUDE|ORIGIN)">
+        <token type="NameAttribute"/>
+      </rule>
+      <rule pattern="\(|\)">
+        <token type="Punctuation"/>
+      </rule>
+      <rule pattern="[\r\n\s\t]+">
+        <token type="TextWhitespace"/>
+      </rule>
+    </state>
+  </rules>
+</lexer>
diff --git a/lexers/testdata/dns.actual b/lexers/testdata/dns.actual
@@ -0,0 +1,19 @@
+; /etc/bind/zones/example.org
+$TTL 3h;
+@	IN	SOA	ns.example.org. example.org. (
+	1 ; serial
+	3h; refresh timeout
+	1h; retry timeout
+	1w; expire timeout
+	1h; negative caching TTL
+)
+@	IN	NS		ns.example.org.  ; name server
+@	IN	MX	10	example.org.     ; mail exchange server
+
+ns	IN	A		1.2.3.4
+@	IN	A		1.2.3.4
+
+ns	IN	AAAA	ef::1
+@	IN	AAAA	ef::1
+
+www	IN	CNAME	example.org.
diff --git a/lexers/testdata/dns.expected b/lexers/testdata/dns.expected
@@ -0,0 +1,98 @@
+[
+  {"type":"Comment","value":"; /etc/bind/zones/example.org"},
+  {"type":"TextWhitespace","value":"\n"},
+  {"type":"NameAttribute","value":"$TTL"},
+  {"type":"TextWhitespace","value":" "},
+  {"type":"LiteralStringChar","value":"3h"},
+  {"type":"Comment","value":";"},
+  {"type":"TextWhitespace","value":"\n"},
+  {"type":"NameClass","value":"@"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"IN"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"SOA"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"NameProperty","value":"ns.example.org. example.org. "},
+  {"type":"Punctuation","value":"("},
+  {"type":"TextWhitespace","value":"\n\t"},
+  {"type":"LiteralStringChar","value":"1"},
+  {"type":"TextWhitespace","value":" "},
+  {"type":"Comment","value":"; serial"},
+  {"type":"TextWhitespace","value":"\n\t"},
+  {"type":"LiteralStringChar","value":"3h"},
+  {"type":"Comment","value":"; refresh timeout"},
+  {"type":"TextWhitespace","value":"\n\t"},
+  {"type":"LiteralStringChar","value":"1h"},
+  {"type":"Comment","value":"; retry timeout"},
+  {"type":"TextWhitespace","value":"\n\t"},
+  {"type":"LiteralStringChar","value":"1w"},
+  {"type":"Comment","value":"; expire timeout"},
+  {"type":"TextWhitespace","value":"\n\t"},
+  {"type":"LiteralStringChar","value":"1h"},
+  {"type":"Comment","value":"; negative caching TTL"},
+  {"type":"TextWhitespace","value":"\n"},
+  {"type":"Punctuation","value":")"},
+  {"type":"TextWhitespace","value":"\n"},
+  {"type":"NameClass","value":"@"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"IN"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"NS"},
+  {"type":"TextWhitespace","value":"\t\t"},
+  {"type":"NameProperty","value":"ns.example.org. "},
+  {"type":"TextWhitespace","value":" "},
+  {"type":"Comment","value":"; name server"},
+  {"type":"TextWhitespace","value":"\n"},
+  {"type":"NameClass","value":"@"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"IN"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"MX"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"LiteralStringChar","value":"10"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"NameProperty","value":"example.org. "},
+  {"type":"TextWhitespace","value":"    "},
+  {"type":"Comment","value":"; mail exchange server"},
+  {"type":"TextWhitespace","value":"\n\n"},
+  {"type":"NameClass","value":"ns"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"IN"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"A"},
+  {"type":"TextWhitespace","value":"\t\t"},
+  {"type":"LiteralNumberInteger","value":"1.2.3.4"},
+  {"type":"TextWhitespace","value":"\n"},
+  {"type":"NameClass","value":"@"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"IN"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"A"},
+  {"type":"TextWhitespace","value":"\t\t"},
+  {"type":"LiteralNumberInteger","value":"1.2.3.4"},
+  {"type":"TextWhitespace","value":"\n\n"},
+  {"type":"NameClass","value":"ns"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"IN"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"AAAA"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"LiteralNumberIntegerLong","value":"ef::1"},
+  {"type":"TextWhitespace","value":"\n"},
+  {"type":"NameClass","value":"@"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"IN"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"AAAA"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"LiteralNumberIntegerLong","value":"ef::1"},
+  {"type":"TextWhitespace","value":"\n\n"},
+  {"type":"NameClass","value":"www"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"IN"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"Keyword","value":"CNAME"},
+  {"type":"TextWhitespace","value":"\t"},
+  {"type":"NameProperty","value":"example.org."},
+  {"type":"TextWhitespace","value":"\n"}
+]