auto merge of #15257 : erickt/rust/hashmap, r=alexcrichton

While `HashMap::new` and `HashMap::with_capacity` were being initialized with a random `SipHasher`, it turns out that `HashMap::from_iter` was just using the default instance of `SipHasher`, which wasn't randomized. This closes that bug, and also inlines some important methods.

src/libstd/collections/hashmap.rs

@@ -16,15 +16,13 @@
 use default::Default;
 use fmt::Show;
 use fmt;
-use hash::{Hash, Hasher, sip};
+use hash::{Hash, Hasher, RandomSipHasher};
 use iter::{Iterator, FilterMap, Chain, Repeat, Zip, Extendable};
 use iter::{range, range_inclusive, FromIterator};
 use iter;
 use mem::replace;
 use num;
 use option::{Some, None, Option};
-use rand::Rng;
-use rand;
 use result::{Ok, Err};
 
 mod table {
@@ -733,7 +731,7 @@ fn reserve(&mut self, new_capacity: uint) {
 /// }
 /// ```
 #[deriving(Clone)]
-pub struct HashMap<K, V, H = sip::SipHasher> {
+pub struct HashMap<K, V, H = RandomSipHasher> {
     // All hashes are keyed on these values, to prevent hash collision attacks.
     hasher: H,
 
@@ -1033,18 +1031,17 @@ fn pop(&mut self, k: &K) -> Option<V> {
 
 }
 
-impl<K: Hash + Eq, V> HashMap<K, V, sip::SipHasher> {
+impl<K: Hash + Eq, V> HashMap<K, V, RandomSipHasher> {
     /// Create an empty HashMap.
-    pub fn new() -> HashMap<K, V, sip::SipHasher> {
+    #[inline]
+    pub fn new() -> HashMap<K, V, RandomSipHasher> {
         HashMap::with_capacity(INITIAL_CAPACITY)
     }
 
     /// Creates an empty hash map with the given initial capacity.
-    pub fn with_capacity(capacity: uint) -> HashMap<K, V, sip::SipHasher> {
-        let mut r = rand::task_rng();
-        let r0 = r.gen();
-        let r1 = r.gen();
-        let hasher = sip::SipHasher::new_with_keys(r0, r1);
+    #[inline]
+    pub fn with_capacity(capacity: uint) -> HashMap<K, V, RandomSipHasher> {
+        let hasher = RandomSipHasher::new();
         HashMap::with_capacity_and_hasher(capacity, hasher)
     }
 }
@@ -1053,6 +1050,7 @@ impl<K: Eq + Hash<S>, V, S, H: Hasher<S>> HashMap<K, V, H> {
     /// Creates an empty hashmap which will use the given hasher to hash keys.
     ///
     /// The creates map has the default initial capacity.
+    #[inline]
     pub fn with_hasher(hasher: H) -> HashMap<K, V, H> {
         HashMap::with_capacity_and_hasher(INITIAL_CAPACITY, hasher)
     }
@@ -1064,6 +1062,7 @@ pub fn with_hasher(hasher: H) -> HashMap<K, V, H> {
     /// is designed to allow HashMaps to be resistant to attacks that
     /// cause many collisions and very poor performance. Setting it
     /// manually using this function can expose a DoS attack vector.
+    #[inline]
     pub fn with_capacity_and_hasher(capacity: uint, hasher: H) -> HashMap<K, V, H> {
         let cap = num::next_power_of_two(max(INITIAL_CAPACITY, capacity));
         HashMap {
@@ -1489,7 +1488,7 @@ fn extend<T: Iterator<(K, V)>>(&mut self, mut iter: T) {
 /// HashMap where the value is (). As with the `HashMap` type, a `HashSet`
 /// requires that the elements implement the `Eq` and `Hash` traits.
 #[deriving(Clone)]
-pub struct HashSet<T, H = sip::SipHasher> {
+pub struct HashSet<T, H = RandomSipHasher> {
     map: HashMap<T, (), H>
 }
 
@@ -1529,15 +1528,17 @@ fn insert(&mut self, value: T) -> bool { self.map.insert(value, ()) }
     fn remove(&mut self, value: &T) -> bool { self.map.remove(value) }
 }
 
-impl<T: Hash + Eq> HashSet<T, sip::SipHasher> {
+impl<T: Hash + Eq> HashSet<T, RandomSipHasher> {
     /// Create an empty HashSet
-    pub fn new() -> HashSet<T, sip::SipHasher> {
+    #[inline]
+    pub fn new() -> HashSet<T, RandomSipHasher> {
         HashSet::with_capacity(INITIAL_CAPACITY)
     }
 
     /// Create an empty HashSet with space for at least `n` elements in
     /// the hash table.
-    pub fn with_capacity(capacity: uint) -> HashSet<T, sip::SipHasher> {
+    #[inline]
+    pub fn with_capacity(capacity: uint) -> HashSet<T, RandomSipHasher> {
         HashSet { map: HashMap::with_capacity(capacity) }
     }
 }
@@ -1547,6 +1548,7 @@ impl<T: Eq + Hash<S>, S, H: Hasher<S>> HashSet<T, H> {
     /// keys.
     ///
     /// The hash set is also created with the default initial capacity.
+    #[inline]
     pub fn with_hasher(hasher: H) -> HashSet<T, H> {
         HashSet::with_capacity_and_hasher(INITIAL_CAPACITY, hasher)
     }
@@ -1558,6 +1560,7 @@ pub fn with_hasher(hasher: H) -> HashSet<T, H> {
     /// is designed to allow `HashSet`s to be resistant to attacks that
     /// cause many collisions and very poor performance. Setting it
     /// manually using this function can expose a DoS attack vector.
+    #[inline]
     pub fn with_capacity_and_hasher(capacity: uint, hasher: H) -> HashSet<T, H> {
         HashSet { map: HashMap::with_capacity_and_hasher(capacity, hasher) }
     }

src/libstd/hash.rs

@@ -0,0 +1,102 @@
+// Copyright 2014 The Rust Project Developers. See the COPYRIGHT
+// file at the top-level directory of this distribution and at
+// http://rust-lang.org/COPYRIGHT.
+//
+// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
+// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
+// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
+// option. This file may not be copied, modified, or distributed
+// except according to those terms.
+
+/*!
+ * Generic hashing support.
+ *
+ * This module provides a generic way to compute the hash of a value. The
+ * simplest way to make a type hashable is to use `#[deriving(Hash)]`:
+ *
+ * # Example
+ *
+ * ```rust
+ * use std::hash;
+ * use std::hash::Hash;
+ *
+ * #[deriving(Hash)]
+ * struct Person {
+ *     id: uint,
+ *     name: String,
+ *     phone: u64,
+ * }
+ *
+ * let person1 = Person { id: 5, name: "Janet".to_string(), phone: 555_666_7777 };
+ * let person2 = Person { id: 5, name: "Bob".to_string(), phone: 555_666_7777 };
+ *
+ * assert!(hash::hash(&person1) != hash::hash(&person2));
+ * ```
+ *
+ * If you need more control over how a value is hashed, you need to implement
+ * the trait `Hash`:
+ *
+ * ```rust
+ * use std::hash;
+ * use std::hash::Hash;
+ * use std::hash::sip::SipState;
+ *
+ * struct Person {
+ *     id: uint,
+ *     name: String,
+ *     phone: u64,
+ * }
+ *
+ * impl Hash for Person {
+ *     fn hash(&self, state: &mut SipState) {
+ *         self.id.hash(state);
+ *         self.phone.hash(state);
+ *     }
+ * }
+ *
+ * let person1 = Person { id: 5, name: "Janet".to_string(), phone: 555_666_7777 };
+ * let person2 = Person { id: 5, name: "Bob".to_string(), phone: 555_666_7777 };
+ *
+ * assert!(hash::hash(&person1) == hash::hash(&person2));
+ * ```
+ */
+
+pub use core_collections::hash::{Hash, Hasher, Writer, hash, sip};
+
+use default::Default;
+use rand::Rng;
+use rand;
+
+/// `RandomSipHasher` computes the SipHash algorithm from a stream of bytes
+/// initialized with random keys.
+#[deriving(Clone)]
+pub struct RandomSipHasher {
+    hasher: sip::SipHasher,
+}
+
+impl RandomSipHasher {
+    /// Construct a new `RandomSipHasher` that is initialized with random keys.
+    #[inline]
+    pub fn new() -> RandomSipHasher {
+        let mut r = rand::task_rng();
+        let r0 = r.gen();
+        let r1 = r.gen();
+        RandomSipHasher {
+            hasher: sip::SipHasher::new_with_keys(r0, r1),
+        }
+    }
+}
+
+impl Hasher<sip::SipState> for RandomSipHasher {
+    #[inline]
+    fn hash<T: Hash<sip::SipState>>(&self, value: &T) -> u64 {
+        self.hasher.hash(value)
+    }
+}
+
+impl Default for RandomSipHasher {
+    #[inline]
+    fn default() -> RandomSipHasher {
+        RandomSipHasher::new()
+    }
+}

src/libstd/lib.rs

@@ -167,7 +167,6 @@
 pub use alloc::owned;
 pub use alloc::rc;
 
-pub use core_collections::hash;
 pub use core_collections::slice;
 pub use core_collections::str;
 pub use core_collections::string;
@@ -237,6 +236,7 @@ fn start(argc: int, argv: *const *const u8) -> int {
 /* Common data structures */
 
 pub mod collections;
+pub mod hash;
 
 /* Tasks and communication */