#6: code reorganization, added binaries for index and search

Cargo.toml

@@ -12,14 +12,19 @@ version = "0.0.1"
 
 [dependencies]
 bincode = "2.0.0-rc.3"
+clickrs = "0.1.5"
 fixedbitset = "0.5.7"
 nom = "7.1.3"
 petgraph = "0.6.5"
 
+[lib]
+name = "ringo"
+path = "src/lib.rs"
+
 [[bin]]
 name = "ringo-index"
-path = "src/ringo/ringo/index/main.rs"
+path = "src/bin/ringo_index.rs"
 
 [[bin]]
 name = "ringo-search"
-path = "src/ringo/ringo/search/main.rs"
+path = "src/bin/ringo_search.rs"

src/bin/ringo_index.rs

@@ -0,0 +1,8 @@
+extern crate ringo;
+
+use ringo::db::index::index_file;
+
+fn main() {
+    let args: Vec<String> = std::env::args().collect();
+    index_file(&args[1]);
+}

src/bin/ringo_search.rs

@@ -0,0 +1,11 @@
+extern crate ringo;
+
+use ringo::db::search::similarity_search;
+
+fn main() {
+    let args: Vec<String> = std::env::args().collect();
+    let results = similarity_search(&args[1], &args[2], args[3].parse().unwrap(), args[4].parse().unwrap());
+    for result in results {
+        println!("{:?} {:?}", result.line, result.similarity);
+    }
+}

src/db.rs

@@ -0,0 +1,4 @@
+pub mod index_item;
+pub mod index;
+pub mod search;
+pub mod fingerprint;

src/ringo/fingerprint/fingerprint.rs → src/db/fingerprint.rs

@@ -32,7 +32,7 @@ impl<'de> bincode::BorrowDecode<'de> for Fingerprint {
 
 #[cfg(test)]
 mod tests {
-    use crate::ringo::fingerprint::fingerprint::{Fingerprint, FINGERPRINT_SIZE};
+    use crate::db::fingerprint::{Fingerprint, FINGERPRINT_SIZE};
     use fixedbitset::FixedBitSet;
 
     #[test]

src/ringo/ringo/index/index.rs → src/db/index.rs

@@ -1,16 +1,17 @@
-use crate::ringo::fingerprint::fingerprint::FINGERPRINT_SIZE;
-use crate::ringo::molecule::smiles::reader::molecule::parse_molecule;
-use crate::ringo::ringo::index::index_item::IndexItem;
+
 use bincode::encode_into_slice;
 use std::fs::File;
 use std::io::{BufRead, BufWriter, Write};
+use crate::db::index_item::IndexItem;
+use crate::db::fingerprint::FINGERPRINT_SIZE;
+use crate::molecule::smiles::reader::molecule::parse_molecule;
 
 #[cfg(windows)]
 const LINE_ENDING_LENGTH: usize = 2;
 #[cfg(not(windows))]
 const LINE_ENDING_LENGTH: usize = 1;
 
-pub(crate) fn index(smiles_file: &str) {
+pub fn index_file(smiles_file: &str) {
     // open file for reading
     let fi = File::open(smiles_file).expect("Could not open file");
 
@@ -35,12 +36,13 @@ pub(crate) fn index(smiles_file: &str) {
     }
 }
 
+
 #[cfg(test)]
 mod test {
-    use crate::ringo::ringo::index::index::index;
+    use crate::db::index::index_file;
 
     #[test]
     fn test_index() {
-        index("molecules.smi");
+        index_file("molecules.smi");
     }
 }

src/ringo/ringo/index/index_item.rs → src/db/index_item.rs

@@ -1,4 +1,4 @@
-use crate::ringo::fingerprint::fingerprint::Fingerprint;
+use crate::db::fingerprint::Fingerprint;
 use bincode::{Decode, Encode};
 
 #[derive(Debug, Encode, Decode)]
@@ -9,11 +9,11 @@ pub struct IndexItem {
 
 #[cfg(test)]
 mod tests {
-    use crate::ringo::fingerprint::fingerprint::Fingerprint;
-    use crate::ringo::ringo::index::index_item::IndexItem;
     use bincode::config::standard;
     use bincode::{decode_from_slice, encode_to_vec};
     use fixedbitset::FixedBitSet;
+    use crate::db::fingerprint::Fingerprint;
+    use crate::db::index_item::IndexItem;
 
     #[test]
     fn test_index_item_encode_decode() {

src/ringo/ringo/search/search.rs → src/db/search.rs

@@ -1,6 +1,6 @@
-use crate::ringo::math::similarity::tanimoto::tanimoto_bitset;
-use crate::ringo::molecule::smiles::reader::molecule::parse_molecule;
-use crate::ringo::ringo::index::index_item::IndexItem;
+use crate::math::similarity::tanimoto::tanimoto_bitset;
+use crate::molecule::smiles::reader::molecule::parse_molecule;
+use crate::db::index_item::IndexItem;
 use std::fs::File;
 use std::io::{BufRead, BufReader, Read, Seek};
 
@@ -43,7 +43,6 @@ pub fn similarity_search(
 
         // calculate similarity
         let similarity = tanimoto_bitset(&index_item.fingerprint.0, &query_fp.0);
-
         // print similarity if it is greater than min_similarity
         if similarity >= min_similarity {
             let position = index_item.position;
@@ -68,14 +67,18 @@ pub fn similarity_search(
     results
 }
 
+fn main() {
+    println!("db-search");
+}
+
 #[cfg(test)]
 mod test {
-    use crate::ringo::ringo::index::index::index;
-    use crate::ringo::ringo::search::search::similarity_search;
+    use crate::db::index::index_file;
+    use crate::db::search::similarity_search;
 
     #[test]
     fn test_similarity_search() {
-        index("molecles.smi");
+        index_file("molecles.smi");
         let results = similarity_search("molecules.smi", "CC(C)CC1=CC=C(C=C1)C(C)C(=O)O", 0.7, 100);
         assert_eq!(results.len(), 1);
         assert!(results[0].line.starts_with("CC(C)CC1=CC=C(C=C1)C(C)C(=O)O"));

src/lib.rs

@@ -1,2 +1,3 @@
-mod bin;
-pub mod ringo;
+pub mod db;
+mod math;
+mod molecule;

src/ringo/math/similarity/tanimoto.rs → src/math/similarity/tanimoto.rs

@@ -9,7 +9,7 @@ pub fn tanimoto_bitset(a: &FixedBitSet, b: &FixedBitSet) -> f32 {
 
 #[cfg(test)]
 mod tests {
-    use crate::ringo::math::similarity::tanimoto::tanimoto_bitset;
+    use crate::math::similarity::tanimoto::tanimoto_bitset;
     use fixedbitset::FixedBitSet;
 
     #[test]

src/molecule.rs

@@ -0,0 +1,2 @@
+mod model;
+pub mod smiles;

src/ringo/molecule/model/atom.rs → src/molecule/model/atom.rs

@@ -1,4 +1,4 @@
-use crate::ringo::molecule::model::element::Element;
+use crate::molecule::model::element::Element;
 
 #[derive(Hash, Eq, PartialEq, Debug)]
 pub struct Atom {

src/ringo/molecule/model/molecule.rs → src/molecule/model/molecule.rs

@@ -1,8 +1,8 @@
-use crate::ringo::fingerprint::fingerprint::{Fingerprint, FINGERPRINT_SIZE};
-use crate::ringo::math::similarity::tanimoto::tanimoto_bitset;
-use crate::ringo::molecule::model::atom::Atom;
-use crate::ringo::molecule::model::bond::Bond;
-use crate::ringo::molecule::smiles::reader::molecule::parse_molecule;
+use crate::db::fingerprint::{Fingerprint, FINGERPRINT_SIZE};
+use crate::math::similarity::tanimoto::tanimoto_bitset;
+use crate::molecule::model::atom::Atom;
+use crate::molecule::model::bond::Bond;
+use crate::molecule::smiles::reader::molecule::parse_molecule;
 use fixedbitset::FixedBitSet;
 use petgraph::stable_graph::{EdgeIndex, NodeIndex, StableGraph};
 use petgraph::visit::EdgeRef;

src/molecule/smiles.rs

@@ -0,0 +1 @@
+pub mod reader;

src/ringo/molecule/smiles/reader.rs → src/molecule/smiles/reader.rs

@@ -4,4 +4,4 @@ mod charge;
 mod element;
 mod hydrogens;
 mod isotope;
-pub(crate) mod molecule;
+pub mod molecule;

src/ringo/molecule/smiles/reader/atom.rs → src/molecule/smiles/reader/atom.rs

@@ -1,13 +1,13 @@
-use crate::ringo::molecule::model::atom::Atom;
-use crate::ringo::molecule::model::element::Element;
-use crate::ringo::molecule::smiles::reader::charge::parse_charge;
-use crate::ringo::molecule::smiles::reader::element::parse_element;
-use crate::ringo::molecule::smiles::reader::hydrogens::parse_hydrogens;
-use crate::ringo::molecule::smiles::reader::isotope::parse_isotope;
+use crate::molecule::model::atom::Atom;
+use crate::molecule::model::element::Element;
+use crate::molecule::smiles::reader::charge::parse_charge;
+use crate::molecule::smiles::reader::element::parse_element;
+use crate::molecule::smiles::reader::hydrogens::parse_hydrogens;
+use crate::molecule::smiles::reader::isotope::parse_isotope;
 use nom::combinator::opt;
 use nom::IResult;
 
-pub(crate) fn parse_atom(input: &str) -> IResult<&str, Atom> {
+pub fn parse_atom(input: &str) -> IResult<&str, Atom> {
     let mut isotope: Option<u8> = None;
     let mut charge: Option<i8> = None;
     let mut hs: Option<u8> = None;
@@ -47,7 +47,7 @@ pub(crate) fn parse_atom(input: &str) -> IResult<&str, Atom> {
 
 #[cfg(test)]
 mod tests {
-    use crate::ringo::molecule::smiles::reader::atom::parse_atom;
+    use crate::molecule::smiles::reader::atom::parse_atom;
 
     fn do_test_parse_atom(input: &str, atomic_number: u8, charge: i8, hs: u8, isotope: u8) {
         let (remaining_input, atom) = parse_atom(input).unwrap();

src/ringo/molecule/smiles/reader/bond.rs → src/molecule/smiles/reader/bond.rs

@@ -1,10 +1,10 @@
-use crate::ringo::molecule::model::bond::{Bond, BondOrder};
+use crate::molecule::model::bond::{Bond, BondOrder};
 use nom::branch::alt;
 use nom::bytes::complete::tag;
 use nom::combinator::map;
 use nom::IResult;
 
-pub(crate) fn parse_bond(input: &str) -> IResult<&str, Bond> {
+pub fn parse_bond(input: &str) -> IResult<&str, Bond> {
     let (input, bond_order) = alt((
         map(tag("="), |_| BondOrder::Double),
         map(tag("#"), |_| BondOrder::Triple),

src/ringo/molecule/smiles/reader/charge.rs → src/molecule/smiles/reader/charge.rs

@@ -10,7 +10,7 @@ use nom::{
 /// * single `+` or `-` sign => return 1 or -1
 /// * multiple `+` or `-` signs => return n or -n
 /// * `+` or `-` sign followed by a number => return n or -n
-pub(crate) fn parse_charge(input: &str) -> IResult<&str, i8> {
+pub fn parse_charge(input: &str) -> IResult<&str, i8> {
     let (input, sign) = alt((char('+'), char('-')))(input)?;
     let charge = match sign {
         '+' => 1,

src/ringo/molecule/smiles/reader/element.rs → src/molecule/smiles/reader/element.rs

@@ -3,7 +3,7 @@ use nom::bytes::complete::tag;
 use nom::combinator::map_res;
 use nom::IResult;
 
-pub(crate) fn parse_element(input: &str) -> IResult<&str, u8> {
+pub fn parse_element(input: &str) -> IResult<&str, u8> {
     map_res(
         alt((
             tag("Cl"),

src/ringo/molecule/smiles/reader/hydrogens.rs → src/molecule/smiles/reader/hydrogens.rs

@@ -8,7 +8,7 @@ use nom::IResult;
 /// * H - 1 hydrogen
 /// * Hn - n hydrogens
 /// Returns the number of hydrogens
-pub(crate) fn parse_hydrogens(input: &str) -> IResult<&str, u8> {
+pub fn parse_hydrogens(input: &str) -> IResult<&str, u8> {
     let single_hydrogen_parser = char('H');
     let mut hydrogen_parser = preceded(char('H'), map_res(digit1, str::parse::<u8>));
     single_hydrogen_parser(input)?;

src/ringo/molecule/smiles/reader/isotope.rs → src/molecule/smiles/reader/isotope.rs

@@ -2,7 +2,7 @@ use nom::{character::complete::digit1, combinator::map_res, IResult};
 
 /// Parses isotope value, that should be a number
 /// Returns the isotope value
-pub(crate) fn parse_isotope(input: &str) -> IResult<&str, u8> {
+pub fn parse_isotope(input: &str) -> IResult<&str, u8> {
     Ok(map_res(digit1, str::parse::<u8>)(input)?)
 }
 

src/ringo/molecule/smiles/reader/molecule.rs → src/molecule/smiles/reader/molecule.rs

@@ -1,7 +1,7 @@
-use crate::ringo::molecule::model::bond::{Bond, BondOrder};
-use crate::ringo::molecule::model::molecule::Molecule;
-use crate::ringo::molecule::smiles::reader::atom::parse_atom;
-use crate::ringo::molecule::smiles::reader::bond::parse_bond;
+use crate::molecule::model::bond::{Bond, BondOrder};
+use crate::molecule::model::molecule::Molecule;
+use crate::molecule::smiles::reader::atom::parse_atom;
+use crate::molecule::smiles::reader::bond::parse_bond;
 use nom::branch::alt;
 use nom::character::complete::{char, digit1};
 use nom::combinator::{map, map_res};
@@ -15,7 +15,7 @@ fn parse_cycle_digit(input: &str) -> IResult<&str, u8> {
     map_res(digit1, str::parse::<u8>)(input)
 }
 
-pub(crate) fn parse_molecule(input: &str) -> IResult<&str, Molecule> {
+pub fn parse_molecule(input: &str) -> IResult<&str, Molecule> {
     let mut molecule = Molecule::new();
     let mut open_cycles: HashMap<u8, NodeIndex> = HashMap::new();
     let mut stack: Vec<(NodeIndex, BondOrder)> = Vec::new();