Merge pull request #829 from vsbogd/grounding-space

Grounding space implementation with a more compact representation in memory

Author: vsbogd

lib/Cargo.toml

@@ -16,6 +16,7 @@ dyn-fmt = "0.4.0"
 itertools = "0.13.0"
 unescaper = "0.1.5"
 unicode_reader = "1.0.2"
+bimap = "0.6.3"
 
 # pkg_mgmt deps
 xxhash-rust = {version="0.8.7", features=["xxh3"], optional=true }
@@ -24,6 +25,9 @@ serde_json = { version="1.0.116", optional=true }
 semver = { version="1.0", features = ["serde"], optional=true }
 git2 = { version="0.18.3", features=["vendored-libgit2"], optional=true }
 
+[dev-dependencies]
+ra_ap_profile = "0.0.261"
+
 [lib]
 name = "hyperon"
 path = "src/lib.rs"

lib/examples/load_space.rs

@@ -0,0 +1,87 @@
+use std::env;
+use std::fs::File;
+use std::io::BufReader;
+use std::time::{SystemTime, Duration};
+use ra_ap_profile::memory_usage;
+
+use hyperon::*;
+use hyperon::metta::text::*;
+use hyperon::space::grounding::*;
+
+#[inline]
+fn now() -> SystemTime {
+    SystemTime::now()
+}
+
+#[inline]
+fn since(time: SystemTime) -> Duration {
+    SystemTime::now().duration_since(time).unwrap()
+}
+
+fn main() -> Result<(), String> {
+    let args: Vec<String> = env::args().collect();
+    println!("args passed: {:?}", args);
+    let filename = match args.get(1) {
+        Some(filename) => filename,
+        None => return Err(format!("Please specify MeTTa file as a first argument")),
+    };
+    let open_error = |err| { format!("Cannot open file: {}, because of error: {}", filename, err) };
+    let file = BufReader::new(File::open(filename).map_err(open_error)?);
+
+    let mut parser = SExprParser::new(file);
+    let tokenizer = Tokenizer::new();
+    let mut space = GroundingSpace::new();
+
+    let before = memory_usage().allocated;
+    let start = now();
+    loop {
+        match parser.parse(&tokenizer)? {
+            Some(atom) => space.add(atom),
+            None => break,
+        }
+    }
+    let duration = since(start);
+    let after = memory_usage().allocated;
+    println!("loading time {:?}", duration);
+    println!("memory usage: {}", after - before);
+
+    let query = match args.get(2) {
+        Some(query) => SExprParser::new(query).parse(&tokenizer)?
+            .expect(format!("Incorrect atom: {}", query).as_str()),
+        None => expr!("no_match"),
+    };
+
+    let start = now();
+    let result = space.query(&query);
+    let duration = since(start);
+    println!("{} -> {}, time {:?}", query, result, duration);
+
+    // FILE: gaf/edges.metta
+    // QUERY: (go_gene_product (ontology_term GO:0002377) (protein A0A075B6H8))
+    //use hyperon::space::grounding::index::storage::AtomStorage;
+    //use hyperon::space::grounding::index::trie::{AllowDuplication, AtomTrie, AtomTrieNode, AtomTrieNodeContent};
+
+    //println!("Atom size {}", std::mem::size_of::<Atom>());
+    //println!("AtomTrieNode size {}", std::mem::size_of::<AtomTrieNode>());
+    //println!("AtomTrieNodeContent size {}", std::mem::size_of::<AtomTrieNodeContent<AllowDuplication>>());
+
+    //println!("atom storage count: {}", space.index.storage.count());
+    //let mut storage = AtomStorage::default();
+    //let before = memory_usage().allocated;
+    //std::mem::swap(&mut space.index.storage, &mut storage);
+    //drop(storage);
+    //let after = memory_usage().allocated;
+    //println!("atom storage mem: {}", before - after);
+
+    //println!("atom index node count: {:?}", space.index.trie.stats());
+    //let mut trie = AtomTrie::default();
+    //let before = memory_usage().allocated;
+    //std::mem::swap(&mut space.index.trie, &mut trie);
+    //drop(trie);
+    //let after = memory_usage().allocated;
+    //println!("atom index mem: {}", before - after);
+
+    //println!("{}", space.query(&query));
+
+    Ok(())
+}

lib/src/atom/matcher.rs

@@ -881,15 +881,6 @@ impl<'a> Iterator for BindingsIter<'a> {
     }
 }
 
-impl<'a> IntoIterator for &'a Bindings {
-    type Item = (&'a VariableAtom, Atom);
-    type IntoIter = BindingsIter<'a>;
-
-    fn into_iter(self) -> Self::IntoIter {
-        self.iter()
-    }
-}
-
 
 /// Represents a set of [Bindings] instances resulting from an operation where multiple matches are possible.
 #[derive(Clone, Debug)]
@@ -979,10 +970,15 @@ impl BindingsSet {
         BindingsSet(smallvec::smallvec![])
     }
 
-    /// Creates a new unconstrained BindingsSet
+    /// Creates a new BindingsSet with a single full match
     pub fn single() -> Self {
         BindingsSet(smallvec::smallvec![Bindings::new()])
     }
+    
+    /// Creates a new BindingsSet with `count` full matches
+    pub fn count(count: usize) -> Self {
+        BindingsSet(smallvec::SmallVec::from_elem(Bindings::new(), count))
+    }
 
     /// Returns `true` if a BindingsSet contains no Bindings Objects (fully constrained)
     ///

lib/src/atom/serial.rs

@@ -72,8 +72,11 @@ pub trait ConvertingSerializer<T>: Serializer + Default {
 /// Serialization result type
 pub type Result = std::result::Result<(), Error>;
 
+trait PrivHasher : Hasher {}
+impl PrivHasher for DefaultHasher {}
+
 // there are much speedier hashers, but not sure if it's worth the extra dependency given the other options
-impl Serializer for DefaultHasher {
+impl<H: PrivHasher> Serializer for H {
     fn serialize_bool(&mut self, v: bool) -> Result { Ok(self.write_u8(v as u8)) }
     fn serialize_i64(&mut self, v: i64) -> Result { Ok(self.write_i64(v)) }
     fn serialize_f64(&mut self, v: f64) -> Result { Ok(self.write_u64(v as u64)) }
@@ -95,3 +98,14 @@ impl Serializer for Vec<u8> {
     fn serialize_f64(&mut self, v: f64) -> Result { Ok(self.extend(v.to_le_bytes())) }
     fn serialize_str(&mut self, v: &str) -> Result { Ok(self.extend(v.bytes())) }
 }
+
+#[derive(Default)]
+pub struct NullSerializer();
+
+impl Serializer for NullSerializer {
+    fn serialize_bool(&mut self, _v: bool) -> Result { Ok(()) }
+    fn serialize_i64(&mut self, _v: i64) -> Result { Ok(()) }
+    fn serialize_f64(&mut self, _v: f64) -> Result { Ok(()) }
+    fn serialize_str(&mut self, _v: &str) -> Result { Ok(()) }
+}
+

lib/src/common/collections.rs

@@ -297,6 +297,22 @@ impl<'a, T: 'a + Display> Display for VecDisplay<'a, T> {
     }
 }
 
+/// Helper function to implement Display for all mapping like code structures.
+/// Displays iterator over pairs in a format { <key>: <value>, ... }
+pub fn write_mapping<A, B, I>(f: &mut std::fmt::Formatter, it: I) -> std::fmt::Result
+    where
+        A: Display,
+        B: Display,
+        I: Iterator<Item=(A, B)>
+{
+    write!(f, "{{").and_then(|()| {
+        it.fold((Ok(()), true), |(res, start), (a, b)| {
+            let comma = if start { "" } else { "," };
+            (res.and_then(|()| write!(f, "{} {}: {}", comma, a, b)), false)
+        }).0
+    }).and_then(|()| write!(f, " }}"))
+}
+
 
 #[cfg(test)]
 mod test {