first commit

.gitignore

@@ -0,0 +1 @@
+/target

Cargo.lock

@@ -0,0 +1,531 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+
+[[package]]
+name = "aho-corasick"
+version = "1.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b2969dcb958b36655471fc61f7e416fa76033bdd4bfed0678d8fee1e2d07a1f0"
+dependencies = [
+ "memchr",
+]
+
+[[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 = "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 = "1.0.89"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a0ba8f7aaa012f30d5b2861462f6708eccd49c3c39863fe083a308035f63d723"
+dependencies = [
+ "jobserver",
+ "libc",
+]
+
+[[package]]
+name = "cmake"
+version = "0.1.50"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a31c789563b815f77f4250caee12365734369f942439b7defd71e18a48197130"
+dependencies = [
+ "cc",
+]
+
+[[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 = "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"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9c198f91728a82281a64e1f4f9eeb25d82cb32a5de251c6bd1b5154d63a8e7bd"
+
+[[package]]
+name = "libz-sys"
+version = "1.1.15"
+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 = "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 = "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 = "pileup"
+version = "0.1.0"
+dependencies = [
+ "rust-htslib",
+]
+
+[[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 = "1.0.78"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e2422ad645d89c99f8f3e6b88a9fdeca7fabeac836b1002371c4367c8f984aae"
+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 = "0.4.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5bb987efffd3c6d0d8f5f89510bb458559eab11e4f869acb20bf845e016259cd"
+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 = "0.44.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7c7eb0f29fce64a4e22578905efef3d72389058016023279a58b282eb5c0c467"
+dependencies = [
+ "bio-types",
+ "byteorder",
+ "custom_derive",
+ "derive-new",
+ "hts-sys",
+ "ieee754",
+ "lazy_static",
+ "libc",
+ "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 = "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 = "1.0.57"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e45bcbe8ed29775f228095caf2cd67af7a4ccf756ebff23a306bf3e8b47b24b"
+dependencies = [
+ "thiserror-impl",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "1.0.57"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a953cb265bef375dae3de6663da4d3804eee9682ea80d8e2542529b73c531c81"
+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

@@ -0,0 +1,9 @@
+[package]
+name = "pileup"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+rust-htslib = "0.44.1"

src/lib.rs

@@ -0,0 +1,101 @@
+pub fn get_hts_nt_pileup(
+    bam: &mut rust_htslib::bam::IndexedReader,
+    chr: &str,
+    start: i32,
+    with_next_ins: bool,
+) -> Result<Vec<u8>> {
+    use rust_htslib::{bam, bam::Read};
+    let stop = start + 1;
+    let mut bases = Vec::new();
+    bam.fetch((chr, start, stop))?;
+    let mut bam_pileup = Vec::new();
+    for p in bam.pileup() {
+        let pileup = p.context(format!(
+            "Can't pilup bam at position {}:{}-{}",
+            chr, start, stop
+        ))?;
+        let position = pileup.pos() as i32;
+        if position == start {
+            for alignment in pileup.alignments() {
+                match alignment.indel() {
+                    bam::pileup::Indel::Ins(_len) => bam_pileup.push(b'I'),
+                    bam::pileup::Indel::Del(_len) => bam_pileup.push(b'D'),
+                    _ => {
+                        let record = alignment.record();
+                        if record.seq_len() > 0 {
+                            if let Some(b) = hts_base_at(&record, start as u32, with_next_ins)? {
+                                bases.push(b);
+                            }
+                        } else {
+                            if alignment.is_del() {
+                                bases.push(b'D');
+                            }
+                        }
+                    }
+                }
+            }
+        }
+    }
+    Ok(bases)
+}
+
+pub fn hts_base_at(
+    record: &rust_htslib::bam::record::Record,
+    at_pos: u32,
+    with_next_ins: bool,
+) -> Result<Option<u8>> {
+    use rust_htslib::bam::record::Cigar;
+
+    let cigar = record.cigar();
+    let seq = record.seq();
+    let pos = cigar.pos() as u32;
+
+    let mut read_i = 0u32;
+    let at_pos = at_pos - 1;
+    let mut ref_pos = pos;
+    if ref_pos > at_pos {
+        return Ok(None);
+    }
+
+    for (id, op) in cigar.iter().enumerate() {
+        let (add_read, add_ref) = match *op {
+            Cigar::Match(len) | Cigar::Equal(len) | Cigar::Diff(len) => (len, len),
+            Cigar::Ins(len) => (len, 0),
+            Cigar::Del(len) => (0, len),
+            Cigar::RefSkip(len) => (0, len),
+            Cigar::SoftClip(len) => (len, 0),
+            Cigar::HardClip(_) | Cigar::Pad(_) => (0, 0),
+        };
+        // If at the end of the op len and next op is Ins return I
+        if with_next_ins && ref_pos + add_read == at_pos + 1 {
+            if let Some(Cigar::Ins(_)) = cigar.get(id + 1) {
+                return Ok(Some(b'I'));
+            }
+        }
+
+        if ref_pos + add_ref > at_pos {
+            // Handle deletions directly
+            if let Cigar::Del(_) = *op {
+                return Ok(Some(b'D'));
+            } else if let Cigar::RefSkip(_) = op {
+                return Ok(None);
+            } else {
+                let diff = at_pos - ref_pos;
+                let p = read_i + diff;
+                return Ok(Some(seq[p as usize]));
+            }
+        }
+
+        read_i += add_read;
+        ref_pos += add_ref;
+    }
+    Ok(None)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn it_works() {}
+}