From 4f5c94891a9b398711c68ee5834806fcc81f2a37 Mon Sep 17 00:00:00 2001
From: Jordan Santell <jsantell@users.noreply.github.com>
Date: Fri, 10 Feb 2017 16:03:35 -0800
Subject: [PATCH] Add octal, hexadecimal, and arbitrary base integers to the
 EDN parser. Fixes #277. r=rnewman (#286)

---
 edn/src/edn.rustpeg | 22 +++++++++++++++++++++-
 edn/tests/tests.rs  | 30 ++++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+), 1 deletion(-)

diff --git a/edn/src/edn.rustpeg b/edn/src/edn.rustpeg
index 71e95d09..7363f05a 100644
--- a/edn/src/edn.rustpeg
+++ b/edn/src/edn.rustpeg
@@ -44,6 +44,10 @@ pub boolean -> Value =
     "false" { Value::Boolean(false) }
 
 digit = [0-9]
+alphanumeric = [0-9a-zA-Z]
+octaldigit = [0-7]
+validbase = [3][0-6] / [12][0-9] / [2-9]
+hex = [0-9a-fA-F]
 sign = "-" / "+"
 
 pub bigint -> Value =
@@ -51,6 +55,22 @@ pub bigint -> Value =
         Value::BigInteger(b.parse::<BigInt>().unwrap())
     }
 
+pub octalinteger -> Value =
+    "0" i:$( octaldigit+ ) {
+        Value::Integer(i64::from_str_radix(i, 8).unwrap())
+    }
+
+pub hexinteger -> Value =
+    "0x" i:$( hex+ ) {
+        Value::Integer(i64::from_str_radix(i, 16).unwrap())
+    }
+
+pub basedinteger -> Value =
+    // Only allow values 2-36
+    b:$( validbase ) "r" i:$( alphanumeric+ ) {
+        Value::Integer(i64::from_str_radix(i, b.parse::<u32>().unwrap()).unwrap())
+    }
+
 pub integer -> Value =
     i:$( sign? digit+ ) {
         Value::Integer(i.parse::<i64>().unwrap())
@@ -134,7 +154,7 @@ pub map -> Value =
 // It's important that float comes before integer or the parser assumes that
 // floats are integers and fails to parse
 pub value -> Value =
-    __ v:(nil / nan / infinity / boolean / float / bigint / integer / text / keyword / symbol / list / vector / map / set) __ {
+    __ v:(nil / nan / infinity / boolean / float / octalinteger / hexinteger / basedinteger / bigint / integer / text / keyword / symbol / list / vector / map / set) __ {
         v
     }
 
diff --git a/edn/tests/tests.rs b/edn/tests/tests.rs
index 04b4ac72..3c5f3693 100644
--- a/edn/tests/tests.rs
+++ b/edn/tests/tests.rs
@@ -101,6 +101,33 @@ fn test_integer() {
     assert!(integer("nil").is_err());
 }
 
+#[test]
+fn test_hexinteger() {
+    assert_eq!(hexinteger("0xabc111").unwrap(), Integer(11256081));
+    assert_eq!(hexinteger("0xABCDEF").unwrap(), Integer(11259375));
+    assert_eq!(hexinteger("0xabcdef").unwrap(), Integer(11259375));
+
+    assert!(hexinteger("nil").is_err());
+    assert!(hexinteger("0xZZZ").is_err());
+}
+
+#[test]
+fn test_basedinteger() {
+    assert_eq!(basedinteger("2r111").unwrap(), Integer(7));
+    assert_eq!(basedinteger("36r1z").unwrap(), Integer(71));
+    assert_eq!(basedinteger("36r1Z").unwrap(), Integer(71));
+    assert_eq!(basedinteger("12r11").unwrap(), Integer(13));
+    assert_eq!(basedinteger("24r10").unwrap(), Integer(24));
+
+    assert!(basedinteger("nil").is_err());
+}
+
+#[test]
+fn test_octalinteger() {
+    assert_eq!(octalinteger("011").unwrap(), Integer(9));
+    assert_eq!(octalinteger("00107").unwrap(), Integer(71));
+}
+
 #[test]
 fn test_bigint() {
     let max_i64 = i64::max_value().to_bigint().unwrap();
@@ -186,6 +213,9 @@ fn test_value() {
     assert_eq!(value("[1]").unwrap(), Vector(vec![Integer(1)]));
     assert_eq!(value("111.222").unwrap(), Float(OrderedFloat(111.222f64)));
     assert_eq!(value("85070591730234615847396907784232501249N").unwrap(), BigInteger(bigger));
+    assert_eq!(value("0xabc111").unwrap(), Integer(11256081));
+    assert_eq!(value("2r111").unwrap(), Integer(7));
+    assert_eq!(value("011").unwrap(), Integer(9));
 }
 
 #[test]