explicitly set large_file on all files and update zip module. #30

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "echtvar"
-version = "0.1.8"
+version = "0.1.9"
 edition = "2021"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
@@ -17,17 +17,17 @@ path = "src/main.rs"
 [dependencies]
 rust-htslib = { version = "0.38.2", features = ["libdeflate", "static"] }
 #bitpacking = "0.8.4"
-stream-vbyte = {version = "0.4.0", features=["x86_ssse3", "x86_sse41"]}
-clap = {version = "~2.27.0", features=["suggestions"] }
+stream-vbyte = { version = "0.4.0", features = ["x86_ssse3", "x86_sse41"] }
+clap = { version = "~2.27.0", features = ["suggestions"] }
 c2rust-bitfields = "0.3.0"
 libc = "*"
 # TODO: try deflate-miniz, deflate-zlib, deflate
-zip = { version = "0.6", default-features = false, features=["deflate"] }
+zip = { version = "0.6.4", default-features = false, features = ["deflate"] }
 byteorder = "1"
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1.0"
 
-fasteval = { version = "0.2.4", features= ["unsafe-vars"]}
+fasteval = { version = "0.2.4", features = ["unsafe-vars"] }
 
 bincode = { version = "1.3.3" }
 json5 = "0.4.1"

src/commands/encoder_cmd.rs

@@ -8,8 +8,7 @@ use stream_vbyte::{encode::encode, x86::Sse41};
 use std::borrow::{Borrow, BorrowMut};
 use std::collections::HashMap;
 use std::fs::File;
-use std::io::Read;
-use std::io::Write;
+use std::io::{Read, Write};
 
 use byteorder::{LittleEndian, WriteBytesExt};
 use std::str;
@@ -229,6 +228,7 @@ pub fn encoder_main(vpaths: Vec<&str>, opath: &str, jpath: &str) {
 
     let options = FileOptions::default()
         .compression_method(zip::CompressionMethod::Deflated)
+        .large_file(true)
         .unix_permissions(0o755);
 
     zipf.start_file("echtvar/config.json", options)
@@ -264,7 +264,7 @@ pub fn encoder_main(vpaths: Vec<&str>, opath: &str, jpath: &str) {
             vcf.set_threads(2).ok();
         }
         eprintln!("[echtvar] adding VCF:{}", vpath);
-		let mut warn = 0;
+        let mut warn = 0;
 
         for r in vcf.records() {
             let rec = r.expect("error getting record");
@@ -394,7 +394,12 @@ pub fn encoder_main(vpaths: Vec<&str>, opath: &str, jpath: &str) {
                         .collect::<Vec<_>>()
                 );
             }
-            var32s.push(var32::encode(rec.pos() as u32, alleles[0], alleles[1], &mut warn));
+            var32s.push(var32::encode(
+                rec.pos() as u32,
+                alleles[0],
+                alleles[1],
+                &mut warn,
+            ));
 
             if alleles[0].len() + alleles[1].len() > var32::MAX_COMBINED_LEN {
                 long_vars.push(var32::LongVariant {

src/lib/fields.rs

@@ -74,6 +74,7 @@ mod tests {
              field: "AN",
              alias: "gnomad_AN",
              missing_value: -2147483648,
+             missing: -2,
              multiplier: 1, // this is useful for float fields as internally, everythign is stored as integer.
              zigzag: true, // set this to true if the field can contain negative numbers.
              ftype: "Integer", // this is discovered by echtvar and should not be set.