From 2b42b0219bbd0f5d2103a876b1217456d7f39d35 Mon Sep 17 00:00:00 2001 From: Sam Rijs Date: Wed, 7 Nov 2018 18:35:32 +1100 Subject: [PATCH 1/2] add read_entry benchmark --- Cargo.toml | 6 ++++++ benches/read_entry.rs | 46 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 52 insertions(+) create mode 100644 benches/read_entry.rs diff --git a/Cargo.toml b/Cargo.toml index 1346f2c5..95bc1471 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -19,8 +19,14 @@ bzip2 = { version = "0.3", optional = true } libflate = { version = "0.1.16", optional = true } [dev-dependencies] +bencher = "0.1" +rand = "0.4" walkdir = "1.0" [features] deflate = ["libflate"] default = ["bzip2", "deflate"] + +[[bench]] +name = "read_entry" +harness = false diff --git a/benches/read_entry.rs b/benches/read_entry.rs new file mode 100644 index 00000000..104e97c1 --- /dev/null +++ b/benches/read_entry.rs @@ -0,0 +1,46 @@ +#[macro_use] +extern crate bencher; +extern crate rand; +extern crate zip; + +use std::io::{Cursor, Read, Write}; + +use bencher::Bencher; +use rand::Rng; +use zip::{ZipArchive, ZipWriter}; + +fn generate_random_archive(size: usize) -> Vec { + let data = Vec::new(); + let mut writer = ZipWriter::new(Cursor::new(data)); + let options = zip::write::FileOptions::default() + .compression_method(zip::CompressionMethod::Stored); + + writer.start_file("random.dat", options).unwrap(); + let mut bytes = vec![0u8; size]; + rand::thread_rng().fill_bytes(&mut bytes); + writer.write_all(&bytes).unwrap(); + + writer.finish().unwrap().into_inner() +} + +fn read_entry(bench: &mut Bencher) { + let size = 1024 * 1024; + let bytes = generate_random_archive(size); + let mut archive = ZipArchive::new(Cursor::new(bytes.as_slice())).unwrap(); + + bench.iter(|| { + let mut file = archive.by_name("random.dat").unwrap(); + let mut buf = [0u8; 1024]; + loop { + let n = file.read(&mut buf).unwrap(); + if n == 0 { + break; + } + } + }); + + bench.bytes = size as u64; +} + +benchmark_group!(benches, read_entry); +benchmark_main!(benches); From 8ae6d81ab955e0951058380d01c42938fd4a74a0 Mon Sep 17 00:00:00 2001 From: Sam Rijs Date: Wed, 7 Nov 2018 18:35:57 +1100 Subject: [PATCH 2/2] use crc32fast crate for checksumming --- Cargo.toml | 1 + src/crc32.rs | 86 +++------------------------------------------------- src/lib.rs | 1 + src/write.rs | 10 +++--- 4 files changed, 12 insertions(+), 86 deletions(-) diff --git a/Cargo.toml b/Cargo.toml index 95bc1471..53b3736c 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -17,6 +17,7 @@ podio = "0.1" msdos_time = "0.1" bzip2 = { version = "0.3", optional = true } libflate = { version = "0.1.16", optional = true } +crc32fast = "1.0" [dev-dependencies] bencher = "0.1" diff --git a/src/crc32.rs b/src/crc32.rs index 35e6b2c5..d84af9a1 100644 --- a/src/crc32.rs +++ b/src/crc32.rs @@ -3,70 +3,13 @@ use std::io; use std::io::prelude::*; -const CRC32_TABLE : [u32; 256] = [ - 0x00000000, 0x77073096, 0xee0e612c, 0x990951ba, 0x076dc419, 0x706af48f, - 0xe963a535, 0x9e6495a3, 0x0edb8832, 0x79dcb8a4, 0xe0d5e91e, 0x97d2d988, - 0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, 0x90bf1d91, 0x1db71064, 0x6ab020f2, - 0xf3b97148, 0x84be41de, 0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7, - 0x136c9856, 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec, 0x14015c4f, 0x63066cd9, - 0xfa0f3d63, 0x8d080df5, 0x3b6e20c8, 0x4c69105e, 0xd56041e4, 0xa2677172, - 0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b, 0x35b5a8fa, 0x42b2986c, - 0xdbbbc9d6, 0xacbcf940, 0x32d86ce3, 0x45df5c75, 0xdcd60dcf, 0xabd13d59, - 0x26d930ac, 0x51de003a, 0xc8d75180, 0xbfd06116, 0x21b4f4b5, 0x56b3c423, - 0xcfba9599, 0xb8bda50f, 0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924, - 0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d, 0x76dc4190, 0x01db7106, - 0x98d220bc, 0xefd5102a, 0x71b18589, 0x06b6b51f, 0x9fbfe4a5, 0xe8b8d433, - 0x7807c9a2, 0x0f00f934, 0x9609a88e, 0xe10e9818, 0x7f6a0dbb, 0x086d3d2d, - 0x91646c97, 0xe6635c01, 0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e, - 0x6c0695ed, 0x1b01a57b, 0x8208f4c1, 0xf50fc457, 0x65b0d9c6, 0x12b7e950, - 0x8bbeb8ea, 0xfcb9887c, 0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, 0xfbd44c65, - 0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2, 0x4adfa541, 0x3dd895d7, - 0xa4d1c46d, 0xd3d6f4fb, 0x4369e96a, 0x346ed9fc, 0xad678846, 0xda60b8d0, - 0x44042d73, 0x33031de5, 0xaa0a4c5f, 0xdd0d7cc9, 0x5005713c, 0x270241aa, - 0xbe0b1010, 0xc90c2086, 0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f, - 0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4, 0x59b33d17, 0x2eb40d81, - 0xb7bd5c3b, 0xc0ba6cad, 0xedb88320, 0x9abfb3b6, 0x03b6e20c, 0x74b1d29a, - 0xead54739, 0x9dd277af, 0x04db2615, 0x73dc1683, 0xe3630b12, 0x94643b84, - 0x0d6d6a3e, 0x7a6a5aa8, 0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1, - 0xf00f9344, 0x8708a3d2, 0x1e01f268, 0x6906c2fe, 0xf762575d, 0x806567cb, - 0x196c3671, 0x6e6b06e7, 0xfed41b76, 0x89d32be0, 0x10da7a5a, 0x67dd4acc, - 0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5, 0xd6d6a3e8, 0xa1d1937e, - 0x38d8c2c4, 0x4fdff252, 0xd1bb67f1, 0xa6bc5767, 0x3fb506dd, 0x48b2364b, - 0xd80d2bda, 0xaf0a1b4c, 0x36034af6, 0x41047a60, 0xdf60efc3, 0xa867df55, - 0x316e8eef, 0x4669be79, 0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236, - 0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f, 0xc5ba3bbe, 0xb2bd0b28, - 0x2bb45a92, 0x5cb36a04, 0xc2d7ffa7, 0xb5d0cf31, 0x2cd99e8b, 0x5bdeae1d, - 0x9b64c2b0, 0xec63f226, 0x756aa39c, 0x026d930a, 0x9c0906a9, 0xeb0e363f, - 0x72076785, 0x05005713, 0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38, - 0x92d28e9b, 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21, 0x86d3d2d4, 0xf1d4e242, - 0x68ddb3f8, 0x1fda836e, 0x81be16cd, 0xf6b9265b, 0x6fb077e1, 0x18b74777, - 0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c, 0x8f659eff, 0xf862ae69, - 0x616bffd3, 0x166ccf45, 0xa00ae278, 0xd70dd2ee, 0x4e048354, 0x3903b3c2, - 0xa7672661, 0xd06016f7, 0x4969474d, 0x3e6e77db, 0xaed16a4a, 0xd9d65adc, - 0x40df0b66, 0x37d83bf0, 0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9, - 0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6, 0xbad03605, 0xcdd70693, - 0x54de5729, 0x23d967bf, 0xb3667a2e, 0xc4614ab8, 0x5d681b02, 0x2a6f2b94, - 0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d -]; - -/// Update the checksum prev based upon the contents of buf. -pub fn update(prev: u32, buf: &[u8]) -> u32 -{ - let mut crc = !prev; - - for &byte in buf.iter() - { - crc = CRC32_TABLE[((crc as u8) ^ byte) as usize] ^ (crc >> 8); - } - - !crc -} +use crc32fast::Hasher; /// Reader that validates the CRC32 when it reaches the EOF. pub struct Crc32Reader { inner: R, - crc: u32, + hasher: Hasher, check: u32, } @@ -78,14 +21,14 @@ impl Crc32Reader Crc32Reader { inner: inner, - crc: 0, + hasher: Hasher::new(), check: checksum, } } fn check_matches(&self) -> bool { - self.check == self.crc + self.check == self.hasher.clone().finalize() } pub fn into_inner(self) -> R { @@ -103,26 +46,7 @@ impl Read for Crc32Reader Ok(n) => n, Err(e) => return Err(e), }; - self.crc = update(self.crc, &buf[0..count]); + self.hasher.update(&buf[0..count]); Ok(count) } } - -#[cfg(test)] -mod test { - #[test] - fn samples() { - assert_eq!(super::update(0, b""), 0); - - // test vectors from the iPXE project (input and output are bitwise negated) - assert_eq!(super::update(!0x12345678, b""), !0x12345678); - assert_eq!(super::update(!0xffffffff, b"hello world"), !0xf2b5ee7a); - assert_eq!(super::update(!0xffffffff, b"hello"), !0xc9ef5979); - assert_eq!(super::update(!0xc9ef5979, b" world"), !0xf2b5ee7a); - - // Some vectors found on Rosetta code - assert_eq!(super::update(0, b"\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00"), 0x190A55AD); - assert_eq!(super::update(0, b"\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF"), 0xFF6CAB0B); - assert_eq!(super::update(0, b"\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F"), 0x91267E8A); - } -} diff --git a/src/lib.rs b/src/lib.rs index f4d7738a..8d0de859 100644 --- a/src/lib.rs +++ b/src/lib.rs @@ -4,6 +4,7 @@ #[cfg(feature = "bzip2")] extern crate bzip2; +extern crate crc32fast; #[cfg(feature = "deflate")] extern crate libflate; extern crate msdos_time; diff --git a/src/write.rs b/src/write.rs index bab9a954..0f9f400d 100644 --- a/src/write.rs +++ b/src/write.rs @@ -3,7 +3,7 @@ use compression::CompressionMethod; use types::{ZipFileData, System, DEFAULT_VERSION, DateTime}; use spec; -use crc32; +use crc32fast::Hasher; use result::{ZipResult, ZipError}; use std::default::Default; use std::io; @@ -66,7 +66,7 @@ pub struct ZipWriter #[derive(Default)] struct ZipWriterStats { - crc32: u32, + hasher: Hasher, start: u64, bytes_written: u64, } @@ -162,7 +162,7 @@ impl ZipWriterStats { fn update(&mut self, buf: &[u8]) { - self.crc32 = crc32::update(self.crc32, buf); + self.hasher.update(buf); self.bytes_written += buf.len() as u64; } } @@ -219,7 +219,7 @@ impl ZipWriter file.data_start = header_end; self.stats.bytes_written = 0; - self.stats.crc32 = 0; + self.stats.hasher = Hasher::new(); self.files.push(file); } @@ -239,7 +239,7 @@ impl ZipWriter None => return Ok(()), Some(f) => f, }; - file.crc32 = self.stats.crc32; + file.crc32 = self.stats.hasher.clone().finalize(); file.uncompressed_size = self.stats.bytes_written; let file_end = writer.seek(io::SeekFrom::Current(0))?;