supporting records and sequence

Cargo.lock

@@ -8,23 +8,66 @@ version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe"
 
+[[package]]
+name = "aho-corasick"
+version = "1.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b2969dcb958b36655471fc61f7e416fa76033bdd4bfed0678d8fee1e2d07a1f0"
+dependencies = [
+ "memchr",
+]
+
 [[package]]
 name = "anyhow"
 version = "1.0.81"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0952808a6c2afd1aa8947271f3a60f1a6763c7b912d210184c5149b5cf147247"
 
+[[package]]
+name = "bio-types"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9d45749b87f21808051025e9bf714d14ff4627f9d8ca967eade6946ea769aa4a"
+dependencies = [
+ "derive-new",
+ "lazy_static",
+ "regex",
+ "strum_macros",
+ "thiserror",
+]
+
 [[package]]
 name = "bytelines"
 version = "2.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "791e4e40d13e1463dee537b254225c12c46ec7328f1817c6264873bc166f615f"
 
+[[package]]
+name = "byteorder"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
+
+[[package]]
+name = "bzip2-sys"
+version = "0.1.11+1.0.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "736a955f3fa7875102d57c82b8cac37ec45224a07fd32d58f9f7a186b6cd4cdc"
+dependencies = [
+ "cc",
+ "libc",
+ "pkg-config",
+]
+
 [[package]]
 name = "cc"
 version = "1.0.90"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8cd6604a82acf3039f1144f54b8eb34e91ffba622051189e71b781822d5ee1f5"
+dependencies = [
+ "jobserver",
+ "libc",
+]
 
 [[package]]
 name = "cfg-if"
@@ -32,6 +75,15 @@ version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
+[[package]]
+name = "cmake"
+version = "0.1.50"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a31c789563b815f77f4250caee12365734369f942439b7defd71e18a48197130"
+dependencies = [
+ "cc",
+]
+
 [[package]]
 name = "crc32fast"
 version = "1.4.0"
@@ -41,6 +93,38 @@ dependencies = [
  "cfg-if",
 ]
 
+[[package]]
+name = "curl-sys"
+version = "0.4.72+curl-8.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29cbdc8314c447d11e8fd156dcdd031d9e02a7a976163e396b548c03153bc9ea"
+dependencies = [
+ "cc",
+ "libc",
+ "libz-sys",
+ "openssl-sys",
+ "pkg-config",
+ "vcpkg",
+ "windows-sys",
+]
+
+[[package]]
+name = "custom_derive"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ef8ae57c4978a2acd8b869ce6b9ca1dfe817bff704c220209fdef2c0b75a01b9"
+
+[[package]]
+name = "derive-new"
+version = "0.5.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3418329ca0ad70234b9735dc4ceed10af4df60eff9c8e7b06cb5e520d92c3535"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 1.0.109",
+]
+
 [[package]]
 name = "desc_seq_lib"
 version = "0.1.0"
@@ -48,6 +132,7 @@ dependencies = [
  "anyhow",
  "log",
  "minimap2",
+ "rust-htslib",
 ]
 
 [[package]]
@@ -73,6 +158,83 @@ dependencies = [
  "miniz_oxide",
 ]
 
+[[package]]
+name = "form_urlencoded"
+version = "1.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e13624c2627564efccf4934284bdd98cbaa14e79b0b5a141218e507b3a823456"
+dependencies = [
+ "percent-encoding",
+]
+
+[[package]]
+name = "fs-utils"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6fc7a9dc005c944c98a935e7fd626faf5bf7e5a609f94bc13e42fc4a02e52593"
+dependencies = [
+ "quick-error",
+]
+
+[[package]]
+name = "glob"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
+
+[[package]]
+name = "heck"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "95505c38b4572b2d910cecb0281560f54b440a19336cbbcb27bf6ce6adc6f5a8"
+
+[[package]]
+name = "hts-sys"
+version = "2.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "deebfb779c734d542e7f14c298597914b9b5425e4089aef482eacb5cab941915"
+dependencies = [
+ "bzip2-sys",
+ "cc",
+ "curl-sys",
+ "fs-utils",
+ "glob",
+ "libz-sys",
+ "lzma-sys",
+ "openssl-sys",
+]
+
+[[package]]
+name = "idna"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "634d9b1461af396cad843f47fdba5597a4f9e6ddd4bfb6ff5d85028c25cb12f6"
+dependencies = [
+ "unicode-bidi",
+ "unicode-normalization",
+]
+
+[[package]]
+name = "ieee754"
+version = "0.2.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9007da9cacbd3e6343da136e98b0d2df013f553d35bdec8b518f07bea768e19c"
+
+[[package]]
+name = "jobserver"
+version = "0.1.28"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ab46a6e9526ddef3ae7f787c06f0f2600639ba80ea3eade3d8e670a2230f51d6"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "lazy_static"
+version = "1.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
+
 [[package]]
 name = "libc"
 version = "0.2.153"
@@ -86,17 +248,41 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "037731f5d3aaa87a5675e895b63ddff1a87624bc29f77004ea829809654e48f6"
 dependencies = [
  "cc",
+ "cmake",
  "libc",
  "pkg-config",
  "vcpkg",
 ]
 
+[[package]]
+name = "linear-map"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bfae20f6b19ad527b550c223fddc3077a547fc70cda94b9b566575423fd303ee"
+
 [[package]]
 name = "log"
 version = "0.4.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "90ed8c1e510134f979dbc4f070f87d4313098b704861a105fe34231c70a3901c"
 
+[[package]]
+name = "lzma-sys"
+version = "0.1.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5fda04ab3764e6cde78b9974eec4f779acaba7c4e84b36eca3cf77c581b85d27"
+dependencies = [
+ "cc",
+ "libc",
+ "pkg-config",
+]
+
+[[package]]
+name = "memchr"
+version = "2.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "523dc4f511e55ab87b694dc30d0f820d60906ef06413f93d4d7a1385599cc149"
+
 [[package]]
 name = "minimap2"
 version = "0.1.16+minimap2.2.26"
@@ -130,12 +316,145 @@ dependencies = [
  "adler",
 ]
 
+[[package]]
+name = "newtype_derive"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac8cd24d9f185bb7223958d8c1ff7a961b74b1953fd05dba7cc568a63b3861ec"
+dependencies = [
+ "rustc_version",
+]
+
+[[package]]
+name = "openssl-src"
+version = "300.2.3+3.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5cff92b6f71555b61bb9315f7c64da3ca43d87531622120fea0195fc761b4843"
+dependencies = [
+ "cc",
+]
+
+[[package]]
+name = "openssl-sys"
+version = "0.9.101"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dda2b0f344e78efc2facf7d195d098df0dd72151b26ab98da807afc26c198dff"
+dependencies = [
+ "cc",
+ "libc",
+ "openssl-src",
+ "pkg-config",
+ "vcpkg",
+]
+
+[[package]]
+name = "percent-encoding"
+version = "2.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
+
 [[package]]
 name = "pkg-config"
 version = "0.3.30"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d231b230927b5e4ad203db57bbcbee2802f6bce620b1e4a9024a07d94e2907ec"
 
+[[package]]
+name = "proc-macro2"
+version = "1.0.79"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e835ff2298f5721608eb1a980ecaee1aef2c132bf95ecc026a11b7bf3c01c02e"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quick-error"
+version = "1.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a1d01941d82fa2ab50be1e79e6714289dd7cde78eba4c074bc5a4374f650dfe0"
+
+[[package]]
+name = "quote"
+version = "1.0.35"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "291ec9ab5efd934aaf503a6466c5d5251535d108ee747472c3977cc5acc868ef"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "regex"
+version = "1.10.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b62dbe01f0b06f9d8dc7d49e05a0785f153b00b2c227856282f671e0318c9b15"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "86b83b8b9847f9bf95ef68afb0b8e6cdb80f498442f5179a29fad448fcc1eaea"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c08c74e62047bb2de4ff487b251e4a92e24f48745648451635cec7d591162d9f"
+
+[[package]]
+name = "rust-htslib"
+version = "0.46.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "aec6f9ca4601beb4ae75ff8c99144dd15de5a873f6adf058da299962c760968e"
+dependencies = [
+ "bio-types",
+ "byteorder",
+ "custom_derive",
+ "derive-new",
+ "hts-sys",
+ "ieee754",
+ "lazy_static",
+ "libc",
+ "libz-sys",
+ "linear-map",
+ "newtype_derive",
+ "regex",
+ "thiserror",
+ "url",
+]
+
+[[package]]
+name = "rustc_version"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c5f5376ea5e30ce23c03eb77cbe4962b988deead10910c372b226388b594c084"
+dependencies = [
+ "semver",
+]
+
+[[package]]
+name = "rustversion"
+version = "1.0.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7ffc183a10b4478d04cbbbfc96d0873219d962dd5accaff2ffbd4ceb7df837f4"
+
+[[package]]
+name = "semver"
+version = "0.1.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d4f410fedcf71af0345d7607d246e7ad15faaadd49d240ee3b24e5dc21a820ac"
+
 [[package]]
 name = "simdutf8"
 version = "0.1.4"
@@ -148,8 +467,176 @@ version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
 
+[[package]]
+name = "strum_macros"
+version = "0.25.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "23dc1fa9ac9c169a78ba62f0b841814b7abae11bdd047b9c58f893439e309ea0"
+dependencies = [
+ "heck",
+ "proc-macro2",
+ "quote",
+ "rustversion",
+ "syn 2.0.52",
+]
+
+[[package]]
+name = "syn"
+version = "1.0.109"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72b64191b275b66ffe2469e8af2c1cfe3bafa67b529ead792a6d0160888b4237"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "syn"
+version = "2.0.52"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b699d15b36d1f02c3e7c69f8ffef53de37aefae075d8488d4ba1a7788d574a07"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "thiserror"
+version = "1.0.58"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "03468839009160513471e86a034bb2c5c0e4baae3b43f79ffc55c4a5427b3297"
+dependencies = [
+ "thiserror-impl",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "1.0.58"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c61f3ba182994efc43764a46c018c347bc492c79f024e705f46567b418f6d4f7"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.52",
+]
+
+[[package]]
+name = "tinyvec"
+version = "1.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "87cc5ceb3875bb20c2890005a4e226a4651264a5c75edb2421b52861a0a0cb50"
+dependencies = [
+ "tinyvec_macros",
+]
+
+[[package]]
+name = "tinyvec_macros"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
+
+[[package]]
+name = "unicode-bidi"
+version = "0.3.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "08f95100a766bf4f8f28f90d77e0a5461bbdb219042e7679bebe79004fed8d75"
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
+
+[[package]]
+name = "unicode-normalization"
+version = "0.1.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a56d1686db2308d901306f92a263857ef59ea39678a5458e7cb17f01415101f5"
+dependencies = [
+ "tinyvec",
+]
+
+[[package]]
+name = "url"
+version = "2.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "31e6302e3bb753d46e83516cae55ae196fc0c309407cf11ab35cc51a4c2a4633"
+dependencies = [
+ "form_urlencoded",
+ "idna",
+ "percent-encoding",
+]
+
 [[package]]
 name = "vcpkg"
 version = "0.2.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"
+
+[[package]]
+name = "windows-sys"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
+dependencies = [
+ "windows-targets",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7dd37b7e5ab9018759f893a1952c9420d060016fc19a472b4bb20d1bdd694d1b"
+dependencies = [
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bcf46cf4c365c6f2d1cc93ce535f2c8b244591df96ceee75d8e83deb70a9cac9"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "da9f259dd3bcf6990b55bffd094c4f7235817ba4ceebde8e6d11cd0c5633b675"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b474d8268f99e0995f25b9f095bc7434632601028cf86590aea5c8a5cb7801d3"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1515e9a29e5bed743cb4415a9ecf5dfca648ce85ee42e15873c3cd8610ff8e02"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5eee091590e89cc02ad514ffe3ead9eb6b660aedca2183455434b93546371a03"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "77ca79f2451b49fa9e2af39f0747fe999fcda4f5e241b2898624dca97a1f2177"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32b752e52a2da0ddfbdbcc6fceadfeede4c939ed16d13e648833a61dfb611ed8"

Cargo.toml

@@ -9,3 +9,4 @@ edition = "2021"
 minimap2 = "0.1.16+minimap2.2.26"
 anyhow = "1.0.75"
 log = "0.4.19"
+rust-htslib = "0.46.0"

src/lib.rs

@@ -1,6 +1,7 @@
 use anyhow::Result;
 use log::info;
 use minimap2::Mapping;
+use rust_htslib::bam::Record;
 use std::{
     collections::{HashMap, VecDeque},
     fmt,
@@ -10,6 +11,8 @@ use std::{
 pub struct Contig {
     pub id: String,
     pub mappings: Vec<Mapping>,
+    pub supporting_records: Vec<Record>,
+    pub sequence: String
 }
 
 #[derive(Debug, Clone)]
@@ -186,8 +189,8 @@ impl Genome {
     pub fn iter(&self) -> std::collections::hash_map::Iter<'_, String, Chromosome> {
         self.chromosomes.iter()
     }
-    pub fn add_contig(&mut self, id: String, mappings: Vec<Mapping>) -> Result<()> {
-        let mut new_contig = Contig { id, mappings };
+    pub fn add_contig(&mut self, id: String, mappings: Vec<Mapping>, supporting_records: Vec<Record>, sequence: String) -> Result<()> {
+        let mut new_contig = Contig { id, mappings, supporting_records, sequence };
         // get the category of Mapping
         let ref_res = new_contig.get_ref_pos()?;
         match ref_res.clone() {
@@ -274,11 +277,13 @@ impl Genome {
 
         Ok(())
     }
+
     pub fn stats(&self) {
         for (k, v) in self.chromosomes.iter() {
             info!("{}:{}", k, v.contigs.len());
         }
     }
+    
     pub fn chromosome(&self, chromosome: &str) -> Option<Vec<ContigsRef>> {
         if let Some(chr) = self.chromosomes.get(chromosome) {
             Some(chr.contigs.clone())
@@ -305,8 +310,8 @@ fn group_mappings(mappings: &mut Vec<Mapping>) -> Result<Vec<Vec<Mapping>>> {
     let mut alignments: Vec<Vec<Mapping>> = vec![];
     // group by overlapps > 30
     for aln in mappings.iter() {
-        let mut last = alignments.last_mut();
-        if let Some(mut l) = last {
+        let last = alignments.last_mut();
+        if let Some(l) = last {
             if l.iter()
                 .filter(|a| a.query_end - aln.query_start > 30)
                 .count()