diff options
author | Yi Kong <yikong@google.com> | 2021-02-13 04:04:00 +0800 |
---|---|---|
committer | Yi Kong <yikong@google.com> | 2021-02-13 04:04:00 +0800 |
commit | f19c3f2587f29a0177eb1dddefc23c46504bf786 (patch) | |
tree | 3c5d21eb4c4844980d4364b035e0836f38f66022 | |
parent | 0f414e4d198c3d1323c06ac54ded935b783061e1 (diff) | |
download | zip-f19c3f2587f29a0177eb1dddefc23c46504bf786.tar.gz |
Import zip-0.5.9
Change-Id: Iac411645f074c4d7b7c3b02a56648d4869dce289
42 files changed, 4512 insertions, 0 deletions
diff --git a/.cargo_vcs_info.json b/.cargo_vcs_info.json new file mode 100644 index 0000000..054c2ae --- /dev/null +++ b/.cargo_vcs_info.json @@ -0,0 +1,5 @@ +{ + "git": { + "sha1": "229fe94bdfa35ed20d16e7548441c0009060a8cd" + } +} diff --git a/.github/dependabot.yml b/.github/dependabot.yml new file mode 100644 index 0000000..5cde165 --- /dev/null +++ b/.github/dependabot.yml @@ -0,0 +1,7 @@ +version: 2 +updates: +- package-ecosystem: cargo + directory: "/" + schedule: + interval: daily + open-pull-requests-limit: 10 diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml new file mode 100644 index 0000000..1e7b395 --- /dev/null +++ b/.github/workflows/ci.yaml @@ -0,0 +1,57 @@ +name: CI + +on: + pull_request: + push: + branches: + - master + +env: + RUSTFLAGS: -Dwarnings + +jobs: + build_and_test: + name: Build and test + runs-on: ${{ matrix.os }} + strategy: + matrix: + os: [ubuntu-latest, macOS-latest, windows-latest] + rust: [stable, 1.34.0] + + steps: + - uses: actions/checkout@master + + - name: Install ${{ matrix.rust }} + uses: actions-rs/toolchain@v1 + with: + toolchain: ${{ matrix.rust }} + override: true + + - name: check + uses: actions-rs/cargo@v1 + with: + command: check + args: --all --bins --examples + + - name: tests + uses: actions-rs/cargo@v1 + with: + command: test + args: --all + + check_fmt_and_docs: + name: Checking fmt and docs + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@master + - uses: actions-rs/toolchain@v1 + with: + toolchain: nightly + components: rustfmt, clippy + override: true + + - name: fmt + run: cargo fmt --all -- --check + + - name: Docs + run: cargo doc
\ No newline at end of file diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..f976c0b --- /dev/null +++ b/.gitignore @@ -0,0 +1,4 @@ +Cargo.lock +target + +\.idea/ diff --git a/Android.bp b/Android.bp new file mode 100644 index 0000000..1098a45 --- /dev/null +++ b/Android.bp @@ -0,0 +1,25 @@ +// This file is generated by cargo2android.py --run --device --dependencies --features=. + +rust_library { + name: "libzip", + host_supported: true, + crate_name: "zip", + srcs: ["src/lib.rs"], + edition: "2018", + rustlibs: [ + "libbyteorder", + "libcrc32fast", + "libthiserror", + ], +} + +// dependent_library ["feature_list"] +// byteorder-1.4.2 "default,std" +// cfg-if-1.0.0 +// crc32fast-1.2.1 "default,std" +// proc-macro2-1.0.24 "default,proc-macro" +// quote-1.0.8 "default,proc-macro" +// syn-1.0.60 "clone-impls,default,derive,parsing,printing,proc-macro,quote" +// thiserror-1.0.23 +// thiserror-impl-1.0.23 +// unicode-xid-0.2.1 "default" diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md new file mode 100644 index 0000000..845634e --- /dev/null +++ b/CODE_OF_CONDUCT.md @@ -0,0 +1,77 @@ + +# Contributor Covenant Code of Conduct + +## Our Pledge + +In the interest of fostering an open and welcoming environment, we as +contributors and maintainers pledge to make participation in our project and +our community a harassment-free experience for everyone, regardless of age, body +size, disability, ethnicity, sex characteristics, gender identity and expression, +level of experience, education, socio-economic status, nationality, personal +appearance, race, religion, or sexual identity and orientation. + +## Our Standards + +Examples of behavior that contributes to creating a positive environment +include: + +* Using welcoming and inclusive language +* Being respectful of differing viewpoints and experiences +* Gracefully accepting constructive criticism +* Focusing on what is best for the community +* Showing empathy towards other community members + +Examples of unacceptable behavior by participants include: + +* The use of sexualized language or imagery and unwelcome sexual attention or + advances +* Trolling, insulting/derogatory comments, and personal or political attacks +* Public or private harassment +* Publishing others' private information, such as a physical or electronic + address, without explicit permission +* Other conduct which could reasonably be considered inappropriate in a + professional setting + +## Our Responsibilities + +Project maintainers are responsible for clarifying the standards of acceptable +behavior and are expected to take appropriate and fair corrective action in +response to any instances of unacceptable behavior. + +Project maintainers have the right and responsibility to remove, edit, or +reject comments, commits, code, wiki edits, issues, and other contributions +that are not aligned to this Code of Conduct, or to ban temporarily or +permanently any contributor for other behaviors that they deem inappropriate, +threatening, offensive, or harmful. + +## Scope + +This Code of Conduct applies within all project spaces, and it also applies when +an individual is representing the project or its community in public spaces. +Examples of representing a project or community include using an official +project e-mail address, posting via an official social media account, or acting +as an appointed representative at an online or offline event. Representation of +a project may be further defined and clarified by project maintainers. + +## Enforcement + +Instances of abusive, harassing, or otherwise unacceptable behavior may be +reported by contacting the project team at ryan.levick@gmail.com. All +complaints will be reviewed and investigated and will result in a response that +is deemed necessary and appropriate to the circumstances. The project team is +obligated to maintain confidentiality with regard to the reporter of an incident. +Further details of specific enforcement policies may be posted separately. + +Project maintainers who do not follow or enforce the Code of Conduct in good +faith may face temporary or permanent repercussions as determined by other +members of the project's leadership. + +## Attribution + +This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4, +available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html + +[homepage]: https://www.contributor-covenant.org + +For answers to common questions about this code of conduct, see +https://www.contributor-covenant.org/faq diff --git a/Cargo.toml b/Cargo.toml new file mode 100644 index 0000000..fef317a --- /dev/null +++ b/Cargo.toml @@ -0,0 +1,61 @@ +# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO +# +# When uploading crates to the registry Cargo will automatically +# "normalize" Cargo.toml files for maximal compatibility +# with all versions of Cargo and also rewrite `path` dependencies +# to registry (e.g., crates.io) dependencies +# +# If you believe there's an error in this file please file an +# issue against the rust-lang/cargo repository. If you're +# editing this file be aware that the upstream Cargo.toml +# will likely look very different (and much more reasonable) + +[package] +edition = "2018" +name = "zip" +version = "0.5.9" +authors = ["Mathijs van de Nes <git@mathijs.vd-nes.nl>"] +description = "Library to support the reading and writing of zip files.\n" +documentation = "http://mvdnes.github.io/rust-docs/zip-rs/zip/index.html" +keywords = ["zip", "archive"] +license = "MIT" +repository = "https://github.com/mvdnes/zip-rs.git" + +[[bench]] +name = "read_entry" +harness = false +[dependencies.byteorder] +version = "1.3" + +[dependencies.bzip2] +version = "0.3" +optional = true + +[dependencies.crc32fast] +version = "1.0" + +[dependencies.flate2] +version = ">=1.0.0, <=1.0.14" +optional = true +default-features = false + +[dependencies.thiserror] +version = "1.0" + +[dependencies.time] +version = "0.1" +optional = true +[dev-dependencies.bencher] +version = "0.1" + +[dev-dependencies.rand] +version = "0.7" + +[dev-dependencies.walkdir] +version = "2" + +[features] +default = ["bzip2", "deflate", "time"] +deflate = ["flate2/rust_backend"] +deflate-miniz = ["flate2/default"] +deflate-zlib = ["flate2/zlib"] diff --git a/Cargo.toml.orig b/Cargo.toml.orig new file mode 100644 index 0000000..f063a92 --- /dev/null +++ b/Cargo.toml.orig @@ -0,0 +1,36 @@ +[package] +name = "zip" +version = "0.5.9" +authors = ["Mathijs van de Nes <git@mathijs.vd-nes.nl>"] +license = "MIT" +repository = "https://github.com/mvdnes/zip-rs.git" +documentation = "http://mvdnes.github.io/rust-docs/zip-rs/zip/index.html" +keywords = ["zip", "archive"] +description = """ +Library to support the reading and writing of zip files. +""" +edition = "2018" + +[dependencies] +# FIXME(#170): flate2 1.0.15 has an MSRV of 1.36.0, breaking ours. We'll update when we know if this will be addressed +flate2 = { version = ">=1.0.0, <=1.0.14", default-features = false, optional = true } +time = { version = "0.1", optional = true } +byteorder = "1.3" +bzip2 = { version = "0.3", optional = true } +crc32fast = "1.0" +thiserror = "1.0" + +[dev-dependencies] +bencher = "0.1" +rand = "0.7" +walkdir = "2" + +[features] +deflate = ["flate2/rust_backend"] +deflate-miniz = ["flate2/default"] +deflate-zlib = ["flate2/zlib"] +default = ["bzip2", "deflate", "time"] + +[[bench]] +name = "read_entry" +harness = false @@ -0,0 +1,21 @@ +The MIT License (MIT) + +Copyright (c) 2014 Mathijs van de Nes + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE.
\ No newline at end of file diff --git a/METADATA b/METADATA new file mode 100644 index 0000000..3679dc8 --- /dev/null +++ b/METADATA @@ -0,0 +1,19 @@ +name: "zip" +description: "Library to support the reading and writing of zip files." +third_party { + url { + type: HOMEPAGE + value: "https://crates.io/crates/zip" + } + url { + type: ARCHIVE + value: "https://static.crates.io/crates/zip/zip-0.5.9.crate" + } + version: "0.5.9" + license_type: NOTICE + last_upgrade_date { + year: 2021 + month: 2 + day: 6 + } +} diff --git a/MODULE_LICENSE_MIT b/MODULE_LICENSE_MIT new file mode 100644 index 0000000..e69de29 --- /dev/null +++ b/MODULE_LICENSE_MIT @@ -0,0 +1 @@ +include platform/prebuilts/rust:/OWNERS diff --git a/README.md b/README.md new file mode 100644 index 0000000..c386363 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +zip-rs +====== + +[![Build Status](https://img.shields.io/github/workflow/status/zip-rs/zip/CI)](https://github.com/zip-rs/zip/actions?query=branch%3Amaster+workflow%3ACI) +[![Crates.io version](https://img.shields.io/crates/v/zip.svg)](https://crates.io/crates/zip) + +[Documentation](http://mvdnes.github.io/rust-docs/zip-rs/zip/index.html) + + +Info +---- + +A zip library for rust which supports reading and writing of simple ZIP files. + +Supported compression formats: + +* stored (i.e. none) +* deflate +* bzip2 + +Currently unsupported zip extensions: + +* Encryption +* Multi-disk + +Usage +----- + +With all default features: + +```toml +[dependencies] +zip = "0.5" +``` + +Without the default features: + +```toml +[dependencies] +zip = { version = "0.5", default-features = false } +``` + +The features available are: + +* `deflate`: Enables the deflate compression algorithm, which is the default for zipfiles +* `bzip2`: Enables the BZip2 compression algorithm. +* `time`: Enables features using the [time](https://github.com/rust-lang-deprecated/time) crate. + +All of these are enabled by default. + +MSRV +---- + +Our current Minimum Supported Rust Version is **1.34.0**. When adding features, +we will follow these guidelines: + +- We will always support the latest four minor Rust versions. This gives you a 6 + month window to upgrade your compiler. +- Any change to the MSRV will be accompanied with a **minor** version bump + - While the crate is pre-1.0, this will be a change to the PATCH version. + +Examples +-------- + +See the [examples directory](examples) for: + * How to write a file to a zip. + * How to write a directory of files to a zip (using [walkdir](https://github.com/BurntSushi/walkdir)). + * How to extract a zip file. + * How to extract a single file from a zip. + * How to read a zip from the standard input. diff --git a/benches/read_entry.rs b/benches/read_entry.rs new file mode 100644 index 0000000..25c0b94 --- /dev/null +++ b/benches/read_entry.rs @@ -0,0 +1,43 @@ +use bencher::{benchmark_group, benchmark_main}; + +use std::io::{Cursor, Read, Write}; + +use bencher::Bencher; +use rand::Rng; +use zip::{ZipArchive, ZipWriter}; + +fn generate_random_archive(size: usize) -> Vec<u8> { + 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); diff --git a/examples/extract.rs b/examples/extract.rs new file mode 100644 index 0000000..05c5a4a --- /dev/null +++ b/examples/extract.rs @@ -0,0 +1,63 @@ +use std::fs; +use std::io; + +fn main() { + std::process::exit(real_main()); +} + +fn real_main() -> i32 { + let args: Vec<_> = std::env::args().collect(); + if args.len() < 2 { + println!("Usage: {} <filename>", args[0]); + return 1; + } + let fname = std::path::Path::new(&*args[1]); + let file = fs::File::open(&fname).unwrap(); + + let mut archive = zip::ZipArchive::new(file).unwrap(); + + for i in 0..archive.len() { + let mut file = archive.by_index(i).unwrap(); + let outpath = match file.enclosed_name() { + Some(path) => path.to_owned(), + None => continue, + }; + + { + let comment = file.comment(); + if !comment.is_empty() { + println!("File {} comment: {}", i, comment); + } + } + + if (&*file.name()).ends_with('/') { + println!("File {} extracted to \"{}\"", i, outpath.display()); + fs::create_dir_all(&outpath).unwrap(); + } else { + println!( + "File {} extracted to \"{}\" ({} bytes)", + i, + outpath.display(), + file.size() + ); + if let Some(p) = outpath.parent() { + if !p.exists() { + fs::create_dir_all(&p).unwrap(); + } + } + let mut outfile = fs::File::create(&outpath).unwrap(); + io::copy(&mut file, &mut outfile).unwrap(); + } + + // Get and Set permissions + #[cfg(unix)] + { + use std::os::unix::fs::PermissionsExt; + + if let Some(mode) = file.unix_mode() { + fs::set_permissions(&outpath, fs::Permissions::from_mode(mode)).unwrap(); + } + } + } + return 0; +} diff --git a/examples/extract_lorem.rs b/examples/extract_lorem.rs new file mode 100644 index 0000000..89e33ef --- /dev/null +++ b/examples/extract_lorem.rs @@ -0,0 +1,31 @@ +use std::io::prelude::*; + +fn main() { + std::process::exit(real_main()); +} + +fn real_main() -> i32 { + let args: Vec<_> = std::env::args().collect(); + if args.len() < 2 { + println!("Usage: {} <filename>", args[0]); + return 1; + } + let fname = std::path::Path::new(&*args[1]); + let zipfile = std::fs::File::open(&fname).unwrap(); + + let mut archive = zip::ZipArchive::new(zipfile).unwrap(); + + let mut file = match archive.by_name("test/lorem_ipsum.txt") { + Ok(file) => file, + Err(..) => { + println!("File test/lorem_ipsum.txt not found"); + return 2; + } + }; + + let mut contents = String::new(); + file.read_to_string(&mut contents).unwrap(); + println!("{}", contents); + + return 0; +} diff --git a/examples/file_info.rs b/examples/file_info.rs new file mode 100644 index 0000000..315b5c3 --- /dev/null +++ b/examples/file_info.rs @@ -0,0 +1,53 @@ +use std::fs; +use std::io::BufReader; + +fn main() { + std::process::exit(real_main()); +} + +fn real_main() -> i32 { + let args: Vec<_> = std::env::args().collect(); + if args.len() < 2 { + println!("Usage: {} <filename>", args[0]); + return 1; + } + let fname = std::path::Path::new(&*args[1]); + let file = fs::File::open(&fname).unwrap(); + let reader = BufReader::new(file); + + let mut archive = zip::ZipArchive::new(reader).unwrap(); + + for i in 0..archive.len() { + let file = archive.by_index(i).unwrap(); + let outpath = match file.enclosed_name() { + Some(path) => path, + None => { + println!("Entry {} has a suspicious path", file.name()); + continue; + } + }; + + { + let comment = file.comment(); + if !comment.is_empty() { + println!("Entry {} comment: {}", i, comment); + } + } + + if (&*file.name()).ends_with('/') { + println!( + "Entry {} is a directory with name \"{}\"", + i, + outpath.display() + ); + } else { + println!( + "Entry {} is a file with name \"{}\" ({} bytes)", + i, + outpath.display(), + file.size() + ); + } + } + return 0; +} diff --git a/examples/stdin_info.rs b/examples/stdin_info.rs new file mode 100644 index 0000000..606944c --- /dev/null +++ b/examples/stdin_info.rs @@ -0,0 +1,34 @@ +use std::io::{self, Read}; + +fn main() { + std::process::exit(real_main()); +} + +fn real_main() -> i32 { + let stdin = io::stdin(); + let mut stdin_handle = stdin.lock(); + let mut buf = [0u8; 16]; + + loop { + match zip::read::read_zipfile_from_stream(&mut stdin_handle) { + Ok(Some(mut file)) => { + println!( + "{}: {} bytes ({} bytes packed)", + file.name(), + file.size(), + file.compressed_size() + ); + match file.read(&mut buf) { + Ok(n) => println!("The first {} bytes are: {:?}", n, &buf[0..n]), + Err(e) => println!("Could not read the file: {:?}", e), + }; + } + Ok(None) => break, + Err(e) => { + println!("Error encountered while reading zip: {:?}", e); + return 1; + } + } + } + return 0; +} diff --git a/examples/write_dir.rs b/examples/write_dir.rs new file mode 100644 index 0000000..793bd6b --- /dev/null +++ b/examples/write_dir.rs @@ -0,0 +1,120 @@ +use std::io::prelude::*; +use std::io::{Seek, Write}; +use std::iter::Iterator; +use zip::result::ZipError; +use zip::write::FileOptions; + +use std::fs::File; +use std::path::Path; +use walkdir::{DirEntry, WalkDir}; + +fn main() { + std::process::exit(real_main()); +} + +const METHOD_STORED: Option<zip::CompressionMethod> = Some(zip::CompressionMethod::Stored); + +#[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" +))] +const METHOD_DEFLATED: Option<zip::CompressionMethod> = Some(zip::CompressionMethod::Deflated); +#[cfg(not(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" +)))] +const METHOD_DEFLATED: Option<zip::CompressionMethod> = None; + +#[cfg(feature = "bzip2")] +const METHOD_BZIP2: Option<zip::CompressionMethod> = Some(zip::CompressionMethod::Bzip2); +#[cfg(not(feature = "bzip2"))] +const METHOD_BZIP2: Option<zip::CompressionMethod> = None; + +fn real_main() -> i32 { + let args: Vec<_> = std::env::args().collect(); + if args.len() < 3 { + println!( + "Usage: {} <source_directory> <destination_zipfile>", + args[0] + ); + return 1; + } + + let src_dir = &*args[1]; + let dst_file = &*args[2]; + for &method in [METHOD_STORED, METHOD_DEFLATED, METHOD_BZIP2].iter() { + if method.is_none() { + continue; + } + match doit(src_dir, dst_file, method.unwrap()) { + Ok(_) => println!("done: {} written to {}", src_dir, dst_file), + Err(e) => println!("Error: {:?}", e), + } + } + + return 0; +} + +fn zip_dir<T>( + it: &mut dyn Iterator<Item = DirEntry>, + prefix: &str, + writer: T, + method: zip::CompressionMethod, +) -> zip::result::ZipResult<()> +where + T: Write + Seek, +{ + let mut zip = zip::ZipWriter::new(writer); + let options = FileOptions::default() + .compression_method(method) + .unix_permissions(0o755); + + let mut buffer = Vec::new(); + for entry in it { + let path = entry.path(); + let name = path.strip_prefix(Path::new(prefix)).unwrap(); + + // Write file or directory explicitly + // Some unzip tools unzip files with directory paths correctly, some do not! + if path.is_file() { + println!("adding file {:?} as {:?} ...", path, name); + #[allow(deprecated)] + zip.start_file_from_path(name, options)?; + let mut f = File::open(path)?; + + f.read_to_end(&mut buffer)?; + zip.write_all(&*buffer)?; + buffer.clear(); + } else if name.as_os_str().len() != 0 { + // Only if not root! Avoids path spec / warning + // and mapname conversion failed error on unzip + println!("adding dir {:?} as {:?} ...", path, name); + #[allow(deprecated)] + zip.add_directory_from_path(name, options)?; + } + } + zip.finish()?; + Result::Ok(()) +} + +fn doit( + src_dir: &str, + dst_file: &str, + method: zip::CompressionMethod, +) -> zip::result::ZipResult<()> { + if !Path::new(src_dir).is_dir() { + return Err(ZipError::FileNotFound); + } + + let path = Path::new(dst_file); + let file = File::create(&path).unwrap(); + + let walkdir = WalkDir::new(src_dir.to_string()); + let it = walkdir.into_iter(); + + zip_dir(&mut it.filter_map(|e| e.ok()), src_dir, file, method)?; + + Ok(()) +} diff --git a/examples/write_sample.rs b/examples/write_sample.rs new file mode 100644 index 0000000..4ef5ce3 --- /dev/null +++ b/examples/write_sample.rs @@ -0,0 +1,71 @@ +use std::io::prelude::*; +use zip::write::FileOptions; + +fn main() { + std::process::exit(real_main()); +} + +fn real_main() -> i32 { + let args: Vec<_> = std::env::args().collect(); + if args.len() < 2 { + println!("Usage: {} <filename>", args[0]); + return 1; + } + + let filename = &*args[1]; + match doit(filename) { + Ok(_) => println!("File written to {}", filename), + Err(e) => println!("Error: {:?}", e), + } + + return 0; +} + +fn doit(filename: &str) -> zip::result::ZipResult<()> { + let path = std::path::Path::new(filename); + let file = std::fs::File::create(&path).unwrap(); + + let mut zip = zip::ZipWriter::new(file); + + zip.add_directory("test/", Default::default())?; + + let options = FileOptions::default() + .compression_method(zip::CompressionMethod::Stored) + .unix_permissions(0o755); + zip.start_file("test/☃.txt", options)?; + zip.write_all(b"Hello, World!\n")?; + + zip.start_file("test/lorem_ipsum.txt", Default::default())?; + zip.write_all(LOREM_IPSUM)?; + + zip.finish()?; + Ok(()) +} + +const LOREM_IPSUM : &'static [u8] = b"Lorem ipsum dolor sit amet, consectetur adipiscing elit. In tellus elit, tristique vitae mattis egestas, ultricies vitae risus. Quisque sit amet quam ut urna aliquet +molestie. Proin blandit ornare dui, a tempor nisl accumsan in. Praesent a consequat felis. Morbi metus diam, auctor in auctor vel, feugiat id odio. Curabitur ex ex, +dictum quis auctor quis, suscipit id lorem. Aliquam vestibulum dolor nec enim vehicula, porta tristique augue tincidunt. Vivamus ut gravida est. Sed pellentesque, dolor +vitae tristique consectetur, neque lectus pulvinar dui, sed feugiat purus diam id lectus. Class aptent taciti sociosqu ad litora torquent per conubia nostra, per +inceptos himenaeos. Maecenas feugiat velit in ex ultrices scelerisque id id neque. + +Phasellus sed nisi in augue sodales pulvinar ut et leo. Pellentesque eget leo vitae massa bibendum sollicitudin. Curabitur erat lectus, congue quis auctor sed, aliquet +bibendum est. Ut porta ultricies turpis at maximus. Cras non lobortis justo. Duis rutrum magna sed velit facilisis, et sagittis metus laoreet. Pellentesque quam ligula, +dapibus vitae mauris quis, dapibus cursus leo. Sed sit amet condimentum eros. Nulla vestibulum enim sit amet lorem pharetra, eu fringilla nisl posuere. Sed tristique non +nibh at viverra. Vivamus sed accumsan lacus, nec pretium eros. Mauris elementum arcu eu risus fermentum, tempor ullamcorper neque aliquam. Sed tempor in erat eu +suscipit. In euismod in libero in facilisis. Donec sagittis, odio et fermentum dignissim, risus justo pretium nibh, eget vestibulum lectus metus vel lacus. + +Quisque feugiat, magna ac feugiat ullamcorper, augue justo consequat felis, ut fermentum arcu lorem vitae ligula. Quisque iaculis tempor maximus. In quis eros ac tellus +aliquam placerat quis id tellus. Donec non gravida nulla. Morbi faucibus neque sed faucibus aliquam. Sed accumsan mattis nunc, non interdum justo. Cras vitae facilisis +leo. Fusce sollicitudin ultrices sagittis. Maecenas eget massa id lorem dignissim ultrices non et ligula. Pellentesque aliquam mi ac neque tempus ornare. Morbi non enim +vulputate quam ullamcorper finibus id non neque. Quisque malesuada commodo lorem, ut ornare velit iaculis rhoncus. Mauris vel maximus ex. + +Morbi eleifend blandit diam, non vulputate ante iaculis in. Donec pellentesque augue id enim suscipit, eget suscipit lacus commodo. Ut vel ex vitae elit imperdiet +vulputate. Nunc eu mattis orci, ut pretium sem. Nam vitae purus mollis ante tempus malesuada a at magna. Integer mattis lectus non luctus lobortis. In a cursus quam, +eget faucibus sem. + +Donec vitae condimentum nisi, non efficitur massa. Praesent sed mi in massa sollicitudin iaculis. Pellentesque a libero ultrices, sodales lacus eu, ornare dui. In +laoreet est nec dolor aliquam consectetur. Integer iaculis felis venenatis libero pulvinar, ut pretium odio interdum. Donec in nisi eu dolor varius vestibulum eget vel +nunc. Morbi a venenatis quam, in vehicula justo. Nam risus dui, auctor eu accumsan at, sagittis ac lectus. Mauris iaculis dignissim interdum. Cras cursus dapibus auctor. +Donec sagittis massa vitae tortor viverra vehicula. Mauris fringilla nunc eu lorem ultrices placerat. Maecenas posuere porta quam at semper. Praesent eu bibendum eros. +Nunc congue sollicitudin ante, sollicitudin lacinia magna cursus vitae. +"; diff --git a/script/doc-upload.cfg b/script/doc-upload.cfg new file mode 100644 index 0000000..cd512ba --- /dev/null +++ b/script/doc-upload.cfg @@ -0,0 +1,3 @@ +PROJECT_NAME=zip-rs +DOCS_REPO=mvdnes/rust-docs.git +DOC_RUST_VERSION=stable diff --git a/src/compression.rs b/src/compression.rs new file mode 100644 index 0000000..5fdde07 --- /dev/null +++ b/src/compression.rs @@ -0,0 +1,180 @@ +//! Possible ZIP compression methods. + +use std::fmt; + +#[allow(deprecated)] +/// Identifies the storage format used to compress a file within a ZIP archive. +/// +/// Each file's compression method is stored alongside it, allowing the +/// contents to be read without context. +/// +/// When creating ZIP files, you may choose the method to use with +/// [`zip::write::FileOptions::compression_method`] +#[derive(Copy, Clone, PartialEq, Eq, Debug)] +pub enum CompressionMethod { + /// Store the file as is + Stored, + /// Compress the file using Deflate + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + Deflated, + /// Compress the file using BZIP2 + #[cfg(feature = "bzip2")] + Bzip2, + /// Unsupported compression method + #[deprecated(since = "0.5.7", note = "use the constants instead")] + Unsupported(u16), +} +#[allow(deprecated, missing_docs)] +/// All compression methods defined for the ZIP format +impl CompressionMethod { + pub const STORE: Self = CompressionMethod::Stored; + pub const SHRINK: Self = CompressionMethod::Unsupported(1); + pub const REDUCE_1: Self = CompressionMethod::Unsupported(2); + pub const REDUCE_2: Self = CompressionMethod::Unsupported(3); + pub const REDUCE_3: Self = CompressionMethod::Unsupported(4); + pub const REDUCE_4: Self = CompressionMethod::Unsupported(5); + pub const IMPLODE: Self = CompressionMethod::Unsupported(6); + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + pub const DEFLATE: Self = CompressionMethod::Deflated; + #[cfg(not(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + )))] + pub const DEFLATE: Self = CompressionMethod::Unsupported(8); + pub const DEFLATE64: Self = CompressionMethod::Unsupported(9); + pub const PKWARE_IMPLODE: Self = CompressionMethod::Unsupported(10); + #[cfg(feature = "bzip2")] + pub const BZIP2: Self = CompressionMethod::Bzip2; + #[cfg(not(feature = "bzip2"))] + pub const BZIP2: Self = CompressionMethod::Unsupported(12); + pub const LZMA: Self = CompressionMethod::Unsupported(14); + pub const IBM_ZOS_CMPSC: Self = CompressionMethod::Unsupported(16); + pub const IBM_TERSE: Self = CompressionMethod::Unsupported(18); + pub const ZSTD_DEPRECATED: Self = CompressionMethod::Unsupported(20); + pub const ZSTD: Self = CompressionMethod::Unsupported(93); + pub const MP3: Self = CompressionMethod::Unsupported(94); + pub const XZ: Self = CompressionMethod::Unsupported(95); + pub const JPEG: Self = CompressionMethod::Unsupported(96); + pub const WAVPACK: Self = CompressionMethod::Unsupported(97); + pub const PPMD: Self = CompressionMethod::Unsupported(98); +} +impl CompressionMethod { + /// Converts an u16 to its corresponding CompressionMethod + #[deprecated( + since = "0.5.7", + note = "use a constant to construct a compression method" + )] + pub fn from_u16(val: u16) -> CompressionMethod { + #[allow(deprecated)] + match val { + 0 => CompressionMethod::Stored, + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + 8 => CompressionMethod::Deflated, + #[cfg(feature = "bzip2")] + 12 => CompressionMethod::Bzip2, + + v => CompressionMethod::Unsupported(v), + } + } + + /// Converts a CompressionMethod to a u16 + #[deprecated( + since = "0.5.7", + note = "to match on other compression methods, use a constant" + )] + pub fn to_u16(self) -> u16 { + #[allow(deprecated)] + match self { + CompressionMethod::Stored => 0, + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + CompressionMethod::Deflated => 8, + #[cfg(feature = "bzip2")] + CompressionMethod::Bzip2 => 12, + CompressionMethod::Unsupported(v) => v, + } + } +} + +impl fmt::Display for CompressionMethod { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + // Just duplicate what the Debug format looks like, i.e, the enum key: + write!(f, "{:?}", self) + } +} + +#[cfg(test)] +mod test { + use super::CompressionMethod; + + #[test] + fn from_eq_to() { + for v in 0..(::std::u16::MAX as u32 + 1) { + #[allow(deprecated)] + let from = CompressionMethod::from_u16(v as u16); + #[allow(deprecated)] + let to = from.to_u16() as u32; + assert_eq!(v, to); + } + } + + fn methods() -> Vec<CompressionMethod> { + let mut methods = Vec::new(); + methods.push(CompressionMethod::Stored); + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + methods.push(CompressionMethod::Deflated); + #[cfg(feature = "bzip2")] + methods.push(CompressionMethod::Bzip2); + methods + } + + #[test] + fn to_eq_from() { + fn check_match(method: CompressionMethod) { + #[allow(deprecated)] + let to = method.to_u16(); + #[allow(deprecated)] + let from = CompressionMethod::from_u16(to); + #[allow(deprecated)] + let back = from.to_u16(); + assert_eq!(to, back); + } + + for method in methods() { + check_match(method); + } + } + + #[test] + fn to_display_fmt() { + fn check_match(method: CompressionMethod) { + let debug_str = format!("{:?}", method); + let display_str = format!("{}", method); + assert_eq!(debug_str, display_str); + } + + for method in methods() { + check_match(method); + } + } +} diff --git a/src/cp437.rs b/src/cp437.rs new file mode 100644 index 0000000..f994814 --- /dev/null +++ b/src/cp437.rs @@ -0,0 +1,203 @@ +//! Convert a string in IBM codepage 437 to UTF-8 + +/// Trait to convert IBM codepage 437 to the target type +pub trait FromCp437 { + /// Target type + type Target; + + /// Function that does the conversion from cp437. + /// Gennerally allocations will be avoided if all data falls into the ASCII range. + fn from_cp437(self) -> Self::Target; +} + +impl<'a> FromCp437 for &'a [u8] { + type Target = ::std::borrow::Cow<'a, str>; + + fn from_cp437(self) -> Self::Target { + if self.iter().all(|c| *c < 0x80) { + ::std::str::from_utf8(self).unwrap().into() + } else { + self.iter().map(|c| to_char(*c)).collect::<String>().into() + } + } +} + +impl FromCp437 for Vec<u8> { + type Target = String; + + fn from_cp437(self) -> Self::Target { + if self.iter().all(|c| *c < 0x80) { + String::from_utf8(self).unwrap() + } else { + self.into_iter().map(to_char).collect() + } + } +} + +fn to_char(input: u8) -> char { + let output = match input { + 0x00..=0x7f => input as u32, + 0x80 => 0x00c7, + 0x81 => 0x00fc, + 0x82 => 0x00e9, + 0x83 => 0x00e2, + 0x84 => 0x00e4, + 0x85 => 0x00e0, + 0x86 => 0x00e5, + 0x87 => 0x00e7, + 0x88 => 0x00ea, + 0x89 => 0x00eb, + 0x8a => 0x00e8, + 0x8b => 0x00ef, + 0x8c => 0x00ee, + 0x8d => 0x00ec, + 0x8e => 0x00c4, + 0x8f => 0x00c5, + 0x90 => 0x00c9, + 0x91 => 0x00e6, + 0x92 => 0x00c6, + 0x93 => 0x00f4, + 0x94 => 0x00f6, + 0x95 => 0x00f2, + 0x96 => 0x00fb, + 0x97 => 0x00f9, + 0x98 => 0x00ff, + 0x99 => 0x00d6, + 0x9a => 0x00dc, + 0x9b => 0x00a2, + 0x9c => 0x00a3, + 0x9d => 0x00a5, + 0x9e => 0x20a7, + 0x9f => 0x0192, + 0xa0 => 0x00e1, + 0xa1 => 0x00ed, + 0xa2 => 0x00f3, + 0xa3 => 0x00fa, + 0xa4 => 0x00f1, + 0xa5 => 0x00d1, + 0xa6 => 0x00aa, + 0xa7 => 0x00ba, + 0xa8 => 0x00bf, + 0xa9 => 0x2310, + 0xaa => 0x00ac, + 0xab => 0x00bd, + 0xac => 0x00bc, + 0xad => 0x00a1, + 0xae => 0x00ab, + 0xaf => 0x00bb, + 0xb0 => 0x2591, + 0xb1 => 0x2592, + 0xb2 => 0x2593, + 0xb3 => 0x2502, + 0xb4 => 0x2524, + 0xb5 => 0x2561, + 0xb6 => 0x2562, + 0xb7 => 0x2556, + 0xb8 => 0x2555, + 0xb9 => 0x2563, + 0xba => 0x2551, + 0xbb => 0x2557, + 0xbc => 0x255d, + 0xbd => 0x255c, + 0xbe => 0x255b, + 0xbf => 0x2510, + 0xc0 => 0x2514, + 0xc1 => 0x2534, + 0xc2 => 0x252c, + 0xc3 => 0x251c, + 0xc4 => 0x2500, + 0xc5 => 0x253c, + 0xc6 => 0x255e, + 0xc7 => 0x255f, + 0xc8 => 0x255a, + 0xc9 => 0x2554, + 0xca => 0x2569, + 0xcb => 0x2566, + 0xcc => 0x2560, + 0xcd => 0x2550, + 0xce => 0x256c, + 0xcf => 0x2567, + 0xd0 => 0x2568, + 0xd1 => 0x2564, + 0xd2 => 0x2565, + 0xd3 => 0x2559, + 0xd4 => 0x2558, + 0xd5 => 0x2552, + 0xd6 => 0x2553, + 0xd7 => 0x256b, + 0xd8 => 0x256a, + 0xd9 => 0x2518, + 0xda => 0x250c, + 0xdb => 0x2588, + 0xdc => 0x2584, + 0xdd => 0x258c, + 0xde => 0x2590, + 0xdf => 0x2580, + 0xe0 => 0x03b1, + 0xe1 => 0x00df, + 0xe2 => 0x0393, + 0xe3 => 0x03c0, + 0xe4 => 0x03a3, + 0xe5 => 0x03c3, + 0xe6 => 0x00b5, + 0xe7 => 0x03c4, + 0xe8 => 0x03a6, + 0xe9 => 0x0398, + 0xea => 0x03a9, + 0xeb => 0x03b4, + 0xec => 0x221e, + 0xed => 0x03c6, + 0xee => 0x03b5, + 0xef => 0x2229, + 0xf0 => 0x2261, + 0xf1 => 0x00b1, + 0xf2 => 0x2265, + 0xf3 => 0x2264, + 0xf4 => 0x2320, + 0xf5 => 0x2321, + 0xf6 => 0x00f7, + 0xf7 => 0x2248, + 0xf8 => 0x00b0, + 0xf9 => 0x2219, + 0xfa => 0x00b7, + 0xfb => 0x221a, + 0xfc => 0x207f, + 0xfd => 0x00b2, + 0xfe => 0x25a0, + 0xff => 0x00a0, + }; + ::std::char::from_u32(output).unwrap() +} + +#[cfg(test)] +mod test { + #[test] + fn to_char_valid() { + for i in 0x00_u32..0x100 { + super::to_char(i as u8); + } + } + + #[test] + fn ascii() { + for i in 0x00..0x80 { + assert_eq!(super::to_char(i), i as char); + } + } + + #[test] + fn example_slice() { + use super::FromCp437; + let data = b"Cura\x87ao"; + assert!(::std::str::from_utf8(data).is_err()); + assert_eq!(data.from_cp437(), "Curaçao"); + } + + #[test] + fn example_vec() { + use super::FromCp437; + let data = vec![0xCC, 0xCD, 0xCD, 0xB9]; + assert!(String::from_utf8(data.clone()).is_err()); + assert_eq!(&data.from_cp437(), "╠══╣"); + } +} diff --git a/src/crc32.rs b/src/crc32.rs new file mode 100644 index 0000000..b351aa0 --- /dev/null +++ b/src/crc32.rs @@ -0,0 +1,93 @@ +//! Helper module to compute a CRC32 checksum + +use std::io; +use std::io::prelude::*; + +use crc32fast::Hasher; + +/// Reader that validates the CRC32 when it reaches the EOF. +pub struct Crc32Reader<R> { + inner: R, + hasher: Hasher, + check: u32, +} + +impl<R> Crc32Reader<R> { + /// Get a new Crc32Reader which check the inner reader against checksum. + pub fn new(inner: R, checksum: u32) -> Crc32Reader<R> { + Crc32Reader { + inner, + hasher: Hasher::new(), + check: checksum, + } + } + + fn check_matches(&self) -> bool { + self.check == self.hasher.clone().finalize() + } + + pub fn into_inner(self) -> R { + self.inner + } +} + +impl<R: Read> Read for Crc32Reader<R> { + fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> { + let count = match self.inner.read(buf) { + Ok(0) if !buf.is_empty() && !self.check_matches() => { + return Err(io::Error::new(io::ErrorKind::Other, "Invalid checksum")) + } + Ok(n) => n, + Err(e) => return Err(e), + }; + self.hasher.update(&buf[0..count]); + Ok(count) + } +} + +#[cfg(test)] +mod test { + use super::*; + use std::io::Read; + + #[test] + fn test_empty_reader() { + let data: &[u8] = b""; + let mut buf = [0; 1]; + + let mut reader = Crc32Reader::new(data, 0); + assert_eq!(reader.read(&mut buf).unwrap(), 0); + + let mut reader = Crc32Reader::new(data, 1); + assert!(reader + .read(&mut buf) + .unwrap_err() + .to_string() + .contains("Invalid checksum")); + } + + #[test] + fn test_byte_by_byte() { + let data: &[u8] = b"1234"; + let mut buf = [0; 1]; + + let mut reader = Crc32Reader::new(data, 0x9be3e0a3); + assert_eq!(reader.read(&mut buf).unwrap(), 1); + assert_eq!(reader.read(&mut buf).unwrap(), 1); + assert_eq!(reader.read(&mut buf).unwrap(), 1); + assert_eq!(reader.read(&mut buf).unwrap(), 1); + assert_eq!(reader.read(&mut buf).unwrap(), 0); + // Can keep reading 0 bytes after the end + assert_eq!(reader.read(&mut buf).unwrap(), 0); + } + + #[test] + fn test_zero_read() { + let data: &[u8] = b"1234"; + let mut buf = [0; 5]; + + let mut reader = Crc32Reader::new(data, 0x9be3e0a3); + assert_eq!(reader.read(&mut buf[..0]).unwrap(), 0); + assert_eq!(reader.read(&mut buf).unwrap(), 4); + } +} diff --git a/src/lib.rs b/src/lib.rs new file mode 100644 index 0000000..3b39ab4 --- /dev/null +++ b/src/lib.rs @@ -0,0 +1,21 @@ +//! An ergonomic API for reading and writing ZIP files. +//! +//! The current implementation is based on [PKWARE's APPNOTE.TXT v6.3.9](https://pkware.cachefly.net/webdocs/casestudies/APPNOTE.TXT) +// TODO(#184): Decide on the crate's bias: Do we prioritise permissiveness/correctness/speed/ergonomics? + +#![warn(missing_docs)] + +pub use crate::compression::CompressionMethod; +pub use crate::read::ZipArchive; +pub use crate::types::DateTime; +pub use crate::write::ZipWriter; + +mod compression; +mod cp437; +mod crc32; +pub mod read; +pub mod result; +mod spec; +mod types; +pub mod write; +mod zipcrypto; diff --git a/src/read.rs b/src/read.rs new file mode 100644 index 0000000..3aac00f --- /dev/null +++ b/src/read.rs @@ -0,0 +1,1078 @@ +//! Types for reading ZIP archives + +use crate::compression::CompressionMethod; +use crate::crc32::Crc32Reader; +use crate::result::{InvalidPassword, ZipError, ZipResult}; +use crate::spec; +use crate::zipcrypto::ZipCryptoReader; +use crate::zipcrypto::ZipCryptoReaderValid; +use std::borrow::Cow; +use std::collections::HashMap; +use std::io::{self, prelude::*}; +use std::path::{Component, Path}; + +use crate::cp437::FromCp437; +use crate::types::{DateTime, System, ZipFileData}; +use byteorder::{LittleEndian, ReadBytesExt}; + +#[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" +))] +use flate2::read::DeflateDecoder; + +#[cfg(feature = "bzip2")] +use bzip2::read::BzDecoder; + +mod ffi { + pub const S_IFDIR: u32 = 0o0040000; + pub const S_IFREG: u32 = 0o0100000; +} + +/// ZIP archive reader +/// +/// ```no_run +/// use std::io::prelude::*; +/// fn list_zip_contents(reader: impl Read + Seek) -> zip::result::ZipResult<()> { +/// let mut zip = zip::ZipArchive::new(reader)?; +/// +/// for i in 0..zip.len() { +/// let mut file = zip.by_index(i)?; +/// println!("Filename: {}", file.name()); +/// std::io::copy(&mut file, &mut std::io::stdout()); +/// } +/// +/// Ok(()) +/// } +/// ``` +#[derive(Clone, Debug)] +pub struct ZipArchive<R: Read + io::Seek> { + reader: R, + files: Vec<ZipFileData>, + names_map: HashMap<String, usize>, + offset: u64, + comment: Vec<u8>, +} + +enum CryptoReader<'a> { + Plaintext(io::Take<&'a mut dyn Read>), + ZipCrypto(ZipCryptoReaderValid<io::Take<&'a mut dyn Read>>), +} + +impl<'a> Read for CryptoReader<'a> { + fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> { + match self { + CryptoReader::Plaintext(r) => r.read(buf), + CryptoReader::ZipCrypto(r) => r.read(buf), + } + } +} + +impl<'a> CryptoReader<'a> { + /// Consumes this decoder, returning the underlying reader. + pub fn into_inner(self) -> io::Take<&'a mut dyn Read> { + match self { + CryptoReader::Plaintext(r) => r, + CryptoReader::ZipCrypto(r) => r.into_inner(), + } + } +} + +enum ZipFileReader<'a> { + NoReader, + Raw(io::Take<&'a mut dyn io::Read>), + Stored(Crc32Reader<CryptoReader<'a>>), + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + Deflated(Crc32Reader<flate2::read::DeflateDecoder<CryptoReader<'a>>>), + #[cfg(feature = "bzip2")] + Bzip2(Crc32Reader<BzDecoder<CryptoReader<'a>>>), +} + +impl<'a> Read for ZipFileReader<'a> { + fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> { + match self { + ZipFileReader::NoReader => panic!("ZipFileReader was in an invalid state"), + ZipFileReader::Raw(r) => r.read(buf), + ZipFileReader::Stored(r) => r.read(buf), + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + ZipFileReader::Deflated(r) => r.read(buf), + #[cfg(feature = "bzip2")] + ZipFileReader::Bzip2(r) => r.read(buf), + } + } +} + +impl<'a> ZipFileReader<'a> { + /// Consumes this decoder, returning the underlying reader. + pub fn into_inner(self) -> io::Take<&'a mut dyn Read> { + match self { + ZipFileReader::NoReader => panic!("ZipFileReader was in an invalid state"), + ZipFileReader::Raw(r) => r, + ZipFileReader::Stored(r) => r.into_inner().into_inner(), + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + ZipFileReader::Deflated(r) => r.into_inner().into_inner().into_inner(), + #[cfg(feature = "bzip2")] + ZipFileReader::Bzip2(r) => r.into_inner().into_inner().into_inner(), + } + } +} + +/// A struct for reading a zip file +pub struct ZipFile<'a> { + data: Cow<'a, ZipFileData>, + crypto_reader: Option<CryptoReader<'a>>, + reader: ZipFileReader<'a>, +} + +fn find_content<'a>( + data: &mut ZipFileData, + reader: &'a mut (impl Read + Seek), +) -> ZipResult<io::Take<&'a mut dyn Read>> { + // Parse local header + reader.seek(io::SeekFrom::Start(data.header_start))?; + let signature = reader.read_u32::<LittleEndian>()?; + if signature != spec::LOCAL_FILE_HEADER_SIGNATURE { + return Err(ZipError::InvalidArchive("Invalid local file header")); + } + + reader.seek(io::SeekFrom::Current(22))?; + let file_name_length = reader.read_u16::<LittleEndian>()? as u64; + let extra_field_length = reader.read_u16::<LittleEndian>()? as u64; + let magic_and_header = 4 + 22 + 2 + 2; + data.data_start = data.header_start + magic_and_header + file_name_length + extra_field_length; + + reader.seek(io::SeekFrom::Start(data.data_start))?; + Ok((reader as &mut dyn Read).take(data.compressed_size)) +} + +fn make_crypto_reader<'a>( + compression_method: crate::compression::CompressionMethod, + crc32: u32, + reader: io::Take<&'a mut dyn io::Read>, + password: Option<&[u8]>, +) -> ZipResult<Result<CryptoReader<'a>, InvalidPassword>> { + #[allow(deprecated)] + { + if let CompressionMethod::Unsupported(_) = compression_method { + return unsupported_zip_error("Compression method not supported"); + } + } + + let reader = match password { + None => CryptoReader::Plaintext(reader), + Some(password) => match ZipCryptoReader::new(reader, password).validate(crc32)? { + None => return Ok(Err(InvalidPassword)), + Some(r) => CryptoReader::ZipCrypto(r), + }, + }; + Ok(Ok(reader)) +} + +fn make_reader<'a>( + compression_method: CompressionMethod, + crc32: u32, + reader: CryptoReader<'a>, +) -> ZipFileReader<'a> { + match compression_method { + CompressionMethod::Stored => ZipFileReader::Stored(Crc32Reader::new(reader, crc32)), + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + CompressionMethod::Deflated => { + let deflate_reader = DeflateDecoder::new(reader); + ZipFileReader::Deflated(Crc32Reader::new(deflate_reader, crc32)) + } + #[cfg(feature = "bzip2")] + CompressionMethod::Bzip2 => { + let bzip2_reader = BzDecoder::new(reader); + ZipFileReader::Bzip2(Crc32Reader::new(bzip2_reader, crc32)) + } + _ => panic!("Compression method not supported"), + } +} + +impl<R: Read + io::Seek> ZipArchive<R> { + /// Get the directory start offset and number of files. This is done in a + /// separate function to ease the control flow design. + fn get_directory_counts( + reader: &mut R, + footer: &spec::CentralDirectoryEnd, + cde_start_pos: u64, + ) -> ZipResult<(u64, u64, usize)> { + // See if there's a ZIP64 footer. The ZIP64 locator if present will + // have its signature 20 bytes in front of the standard footer. The + // standard footer, in turn, is 22+N bytes large, where N is the + // comment length. Therefore: + let zip64locator = if reader + .seek(io::SeekFrom::End( + -(20 + 22 + footer.zip_file_comment.len() as i64), + )) + .is_ok() + { + match spec::Zip64CentralDirectoryEndLocator::parse(reader) { + Ok(loc) => Some(loc), + Err(ZipError::InvalidArchive(_)) => { + // No ZIP64 header; that's actually fine. We're done here. + None + } + Err(e) => { + // Yikes, a real problem + return Err(e); + } + } + } else { + // Empty Zip files will have nothing else so this error might be fine. If + // not, we'll find out soon. + None + }; + + match zip64locator { + None => { + // Some zip files have data prepended to them, resulting in the + // offsets all being too small. Get the amount of error by comparing + // the actual file position we found the CDE at with the offset + // recorded in the CDE. + let archive_offset = cde_start_pos + .checked_sub(footer.central_directory_size as u64) + .and_then(|x| x.checked_sub(footer.central_directory_offset as u64)) + .ok_or(ZipError::InvalidArchive( + "Invalid central directory size or offset", + ))?; + + let directory_start = footer.central_directory_offset as u64 + archive_offset; + let number_of_files = footer.number_of_files_on_this_disk as usize; + Ok((archive_offset, directory_start, number_of_files)) + } + Some(locator64) => { + // If we got here, this is indeed a ZIP64 file. + + if footer.disk_number as u32 != locator64.disk_with_central_directory { + return unsupported_zip_error( + "Support for multi-disk files is not implemented", + ); + } + + // We need to reassess `archive_offset`. We know where the ZIP64 + // central-directory-end structure *should* be, but unfortunately we + // don't know how to precisely relate that location to our current + // actual offset in the file, since there may be junk at its + // beginning. Therefore we need to perform another search, as in + // read::CentralDirectoryEnd::find_and_parse, except now we search + // forward. + + let search_upper_bound = cde_start_pos + .checked_sub(60) // minimum size of Zip64CentralDirectoryEnd + Zip64CentralDirectoryEndLocator + .ok_or(ZipError::InvalidArchive( + "File cannot contain ZIP64 central directory end", + ))?; + let (footer, archive_offset) = spec::Zip64CentralDirectoryEnd::find_and_parse( + reader, + locator64.end_of_central_directory_offset, + search_upper_bound, + )?; + + if footer.disk_number != footer.disk_with_central_directory { + return unsupported_zip_error( + "Support for multi-disk files is not implemented", + ); + } + + let directory_start = footer + .central_directory_offset + .checked_add(archive_offset) + .ok_or_else(|| { + ZipError::InvalidArchive("Invalid central directory size or offset") + })?; + + Ok(( + archive_offset, + directory_start, + footer.number_of_files as usize, + )) + } + } + } + + /// Read a ZIP archive, collecting the files it contains + /// + /// This uses the central directory record of the ZIP file, and ignores local file headers + pub fn new(mut reader: R) -> ZipResult<ZipArchive<R>> { + let (footer, cde_start_pos) = spec::CentralDirectoryEnd::find_and_parse(&mut reader)?; + + if footer.disk_number != footer.disk_with_central_directory { + return unsupported_zip_error("Support for multi-disk files is not implemented"); + } + + let (archive_offset, directory_start, number_of_files) = + Self::get_directory_counts(&mut reader, &footer, cde_start_pos)?; + + let mut files = Vec::new(); + let mut names_map = HashMap::new(); + + if let Err(_) = reader.seek(io::SeekFrom::Start(directory_start)) { + return Err(ZipError::InvalidArchive( + "Could not seek to start of central directory", + )); + } + + for _ in 0..number_of_files { + let file = central_header_to_zip_file(&mut reader, archive_offset)?; + names_map.insert(file.file_name.clone(), files.len()); + files.push(file); + } + + Ok(ZipArchive { + reader, + files, + names_map, + offset: archive_offset, + comment: footer.zip_file_comment, + }) + } + /// Extract a Zip archive into a directory, overwriting files if they + /// already exist. Paths are sanitized with [`ZipFile::enclosed_name`]. + /// + /// Extraction is not atomic; If an error is encountered, some of the files + /// may be left on disk. + pub fn extract<P: AsRef<Path>>(&mut self, directory: P) -> ZipResult<()> { + use std::fs; + + for i in 0..self.len() { + let mut file = self.by_index(i)?; + let filepath = file + .enclosed_name() + .ok_or(ZipError::InvalidArchive("Invalid file path"))?; + + let outpath = directory.as_ref().join(filepath); + + if file.name().ends_with('/') { + fs::create_dir_all(&outpath)?; + } else { + if let Some(p) = outpath.parent() { + if !p.exists() { + fs::create_dir_all(&p)?; + } + } + let mut outfile = fs::File::create(&outpath)?; + io::copy(&mut file, &mut outfile)?; + } + // Get and Set permissions + #[cfg(unix)] + { + use std::os::unix::fs::PermissionsExt; + if let Some(mode) = file.unix_mode() { + fs::set_permissions(&outpath, fs::Permissions::from_mode(mode))?; + } + } + } + Ok(()) + } + + /// Number of files contained in this zip. + pub fn len(&self) -> usize { + self.files.len() + } + + /// Whether this zip archive contains no files + pub fn is_empty(&self) -> bool { + self.len() == 0 + } + + /// Get the offset from the beginning of the underlying reader that this zip begins at, in bytes. + /// + /// Normally this value is zero, but if the zip has arbitrary data prepended to it, then this value will be the size + /// of that prepended data. + pub fn offset(&self) -> u64 { + self.offset + } + + /// Get the comment of the zip archive. + pub fn comment(&self) -> &[u8] { + &self.comment + } + + /// Returns an iterator over all the file and directory names in this archive. + pub fn file_names(&self) -> impl Iterator<Item = &str> { + self.names_map.keys().map(|s| s.as_str()) + } + + /// Search for a file entry by name, decrypt with given password + pub fn by_name_decrypt<'a>( + &'a mut self, + name: &str, + password: &[u8], + ) -> ZipResult<Result<ZipFile<'a>, InvalidPassword>> { + self.by_name_with_optional_password(name, Some(password)) + } + + /// Search for a file entry by name + pub fn by_name<'a>(&'a mut self, name: &str) -> ZipResult<ZipFile<'a>> { + Ok(self.by_name_with_optional_password(name, None)?.unwrap()) + } + + fn by_name_with_optional_password<'a>( + &'a mut self, + name: &str, + password: Option<&[u8]>, + ) -> ZipResult<Result<ZipFile<'a>, InvalidPassword>> { + let index = match self.names_map.get(name) { + Some(index) => *index, + None => { + return Err(ZipError::FileNotFound); + } + }; + self.by_index_with_optional_password(index, password) + } + + /// Get a contained file by index, decrypt with given password + pub fn by_index_decrypt<'a>( + &'a mut self, + file_number: usize, + password: &[u8], + ) -> ZipResult<Result<ZipFile<'a>, InvalidPassword>> { + self.by_index_with_optional_password(file_number, Some(password)) + } + + /// Get a contained file by index + pub fn by_index<'a>(&'a mut self, file_number: usize) -> ZipResult<ZipFile<'a>> { + Ok(self + .by_index_with_optional_password(file_number, None)? + .unwrap()) + } + + /// Get a contained file by index without decompressing it + pub fn by_index_raw<'a>(&'a mut self, file_number: usize) -> ZipResult<ZipFile<'a>> { + let reader = &mut self.reader; + self.files + .get_mut(file_number) + .ok_or(ZipError::FileNotFound) + .and_then(move |data| { + Ok(ZipFile { + crypto_reader: None, + reader: ZipFileReader::Raw(find_content(data, reader)?), + data: Cow::Borrowed(data), + }) + }) + } + + fn by_index_with_optional_password<'a>( + &'a mut self, + file_number: usize, + mut password: Option<&[u8]>, + ) -> ZipResult<Result<ZipFile<'a>, InvalidPassword>> { + if file_number >= self.files.len() { + return Err(ZipError::FileNotFound); + } + let data = &mut self.files[file_number]; + + match (password, data.encrypted) { + (None, true) => { + return Err(ZipError::UnsupportedArchive( + "Password required to decrypt file", + )) + } + (Some(_), false) => password = None, //Password supplied, but none needed! Discard. + _ => {} + } + let limit_reader = find_content(data, &mut self.reader)?; + + match make_crypto_reader(data.compression_method, data.crc32, limit_reader, password) { + Ok(Ok(crypto_reader)) => Ok(Ok(ZipFile { + crypto_reader: Some(crypto_reader), + reader: ZipFileReader::NoReader, + data: Cow::Borrowed(data), + })), + Err(e) => Err(e), + Ok(Err(e)) => Ok(Err(e)), + } + } + + /// Unwrap and return the inner reader object + /// + /// The position of the reader is undefined. + pub fn into_inner(self) -> R { + self.reader + } +} + +fn unsupported_zip_error<T>(detail: &'static str) -> ZipResult<T> { + Err(ZipError::UnsupportedArchive(detail)) +} + +fn central_header_to_zip_file<R: Read + io::Seek>( + reader: &mut R, + archive_offset: u64, +) -> ZipResult<ZipFileData> { + let central_header_start = reader.seek(io::SeekFrom::Current(0))?; + // Parse central header + let signature = reader.read_u32::<LittleEndian>()?; + if signature != spec::CENTRAL_DIRECTORY_HEADER_SIGNATURE { + return Err(ZipError::InvalidArchive("Invalid Central Directory header")); + } + + let version_made_by = reader.read_u16::<LittleEndian>()?; + let _version_to_extract = reader.read_u16::<LittleEndian>()?; + let flags = reader.read_u16::<LittleEndian>()?; + let encrypted = flags & 1 == 1; + let is_utf8 = flags & (1 << 11) != 0; + let compression_method = reader.read_u16::<LittleEndian>()?; + let last_mod_time = reader.read_u16::<LittleEndian>()?; + let last_mod_date = reader.read_u16::<LittleEndian>()?; + let crc32 = reader.read_u32::<LittleEndian>()?; + let compressed_size = reader.read_u32::<LittleEndian>()?; + let uncompressed_size = reader.read_u32::<LittleEndian>()?; + let file_name_length = reader.read_u16::<LittleEndian>()? as usize; + let extra_field_length = reader.read_u16::<LittleEndian>()? as usize; + let file_comment_length = reader.read_u16::<LittleEndian>()? as usize; + let _disk_number = reader.read_u16::<LittleEndian>()?; + let _internal_file_attributes = reader.read_u16::<LittleEndian>()?; + let external_file_attributes = reader.read_u32::<LittleEndian>()?; + let offset = reader.read_u32::<LittleEndian>()? as u64; + let mut file_name_raw = vec![0; file_name_length]; + reader.read_exact(&mut file_name_raw)?; + let mut extra_field = vec![0; extra_field_length]; + reader.read_exact(&mut extra_field)?; + let mut file_comment_raw = vec![0; file_comment_length]; + reader.read_exact(&mut file_comment_raw)?; + + let file_name = match is_utf8 { + true => String::from_utf8_lossy(&*file_name_raw).into_owned(), + false => file_name_raw.clone().from_cp437(), + }; + let file_comment = match is_utf8 { + true => String::from_utf8_lossy(&*file_comment_raw).into_owned(), + false => file_comment_raw.from_cp437(), + }; + + // Construct the result + let mut result = ZipFileData { + system: System::from_u8((version_made_by >> 8) as u8), + version_made_by: version_made_by as u8, + encrypted, + compression_method: { + #[allow(deprecated)] + CompressionMethod::from_u16(compression_method) + }, + last_modified_time: DateTime::from_msdos(last_mod_date, last_mod_time), + crc32, + compressed_size: compressed_size as u64, + uncompressed_size: uncompressed_size as u64, + file_name, + file_name_raw, + file_comment, + header_start: offset, + central_header_start, + data_start: 0, + external_attributes: external_file_attributes, + }; + + match parse_extra_field(&mut result, &*extra_field) { + Ok(..) | Err(ZipError::Io(..)) => {} + Err(e) => return Err(e), + } + + // Account for shifted zip offsets. + result.header_start += archive_offset; + + Ok(result) +} + +fn parse_extra_field(file: &mut ZipFileData, data: &[u8]) -> ZipResult<()> { + let mut reader = io::Cursor::new(data); + + while (reader.position() as usize) < data.len() { + let kind = reader.read_u16::<LittleEndian>()?; + let len = reader.read_u16::<LittleEndian>()?; + let mut len_left = len as i64; + // Zip64 extended information extra field + if kind == 0x0001 { + if file.uncompressed_size == 0xFFFFFFFF { + file.uncompressed_size = reader.read_u64::<LittleEndian>()?; + len_left -= 8; + } + if file.compressed_size == 0xFFFFFFFF { + file.compressed_size = reader.read_u64::<LittleEndian>()?; + len_left -= 8; + } + if file.header_start == 0xFFFFFFFF { + file.header_start = reader.read_u64::<LittleEndian>()?; + len_left -= 8; + } + // Unparsed fields: + // u32: disk start number + } + + // We could also check for < 0 to check for errors + if len_left > 0 { + reader.seek(io::SeekFrom::Current(len_left))?; + } + } + Ok(()) +} + +/// Methods for retrieving information on zip files +impl<'a> ZipFile<'a> { + fn get_reader(&mut self) -> &mut ZipFileReader<'a> { + if let ZipFileReader::NoReader = self.reader { + let data = &self.data; + let crypto_reader = self.crypto_reader.take().expect("Invalid reader state"); + self.reader = make_reader(data.compression_method, data.crc32, crypto_reader) + } + &mut self.reader + } + + pub(crate) fn get_raw_reader(&mut self) -> &mut dyn Read { + if let ZipFileReader::NoReader = self.reader { + let crypto_reader = self.crypto_reader.take().expect("Invalid reader state"); + self.reader = ZipFileReader::Raw(crypto_reader.into_inner()) + } + &mut self.reader + } + + /// Get the version of the file + pub fn version_made_by(&self) -> (u8, u8) { + ( + self.data.version_made_by / 10, + self.data.version_made_by % 10, + ) + } + + /// Get the name of the file + /// + /// # Warnings + /// + /// It is dangerous to use this name directly when extracting an archive. + /// It may contain an absolute path (`/etc/shadow`), or break out of the + /// current directory (`../runtime`). Carelessly writing to these paths + /// allows an attacker to craft a ZIP archive that will overwrite critical + /// files. + /// + /// You can use the [`ZipFile::enclosed_name`] method to validate the name + /// as a safe path. + pub fn name(&self) -> &str { + &self.data.file_name + } + + /// Get the name of the file, in the raw (internal) byte representation. + /// + /// The encoding of this data is currently undefined. + pub fn name_raw(&self) -> &[u8] { + &self.data.file_name_raw + } + + /// Get the name of the file in a sanitized form. It truncates the name to the first NULL byte, + /// removes a leading '/' and removes '..' parts. + #[deprecated( + since = "0.5.7", + note = "by stripping `..`s from the path, the meaning of paths can change. + `mangled_name` can be used if this behaviour is desirable" + )] + pub fn sanitized_name(&self) -> ::std::path::PathBuf { + self.mangled_name() + } + + /// Rewrite the path, ignoring any path components with special meaning. + /// + /// - Absolute paths are made relative + /// - [`ParentDir`]s are ignored + /// - Truncates the filename at a NULL byte + /// + /// This is appropriate if you need to be able to extract *something* from + /// any archive, but will easily misrepresent trivial paths like + /// `foo/../bar` as `foo/bar` (instead of `bar`). Because of this, + /// [`ZipFile::enclosed_name`] is the better option in most scenarios. + /// + /// [`ParentDir`]: `Component::ParentDir` + pub fn mangled_name(&self) -> ::std::path::PathBuf { + self.data.file_name_sanitized() + } + + /// Ensure the file path is safe to use as a [`Path`]. + /// + /// - It can't contain NULL bytes + /// - It can't resolve to a path outside the current directory + /// > `foo/../bar` is fine, `foo/../../bar` is not. + /// - It can't be an absolute path + /// + /// This will read well-formed ZIP files correctly, and is resistant + /// to path-based exploits. It is recommended over + /// [`ZipFile::mangled_name`]. + pub fn enclosed_name(&self) -> Option<&Path> { + if self.data.file_name.contains('\0') { + return None; + } + let path = Path::new(&self.data.file_name); + let mut depth = 0usize; + for component in path.components() { + match component { + Component::Prefix(_) | Component::RootDir => return None, + Component::ParentDir => depth = depth.checked_sub(1)?, + Component::Normal(_) => depth += 1, + Component::CurDir => (), + } + } + Some(path) + } + + /// Get the comment of the file + pub fn comment(&self) -> &str { + &self.data.file_comment + } + + /// Get the compression method used to store the file + pub fn compression(&self) -> CompressionMethod { + self.data.compression_method + } + + /// Get the size of the file in the archive + pub fn compressed_size(&self) -> u64 { + self.data.compressed_size + } + + /// Get the size of the file when uncompressed + pub fn size(&self) -> u64 { + self.data.uncompressed_size + } + + /// Get the time the file was last modified + pub fn last_modified(&self) -> DateTime { + self.data.last_modified_time + } + /// Returns whether the file is actually a directory + pub fn is_dir(&self) -> bool { + self.name() + .chars() + .rev() + .next() + .map_or(false, |c| c == '/' || c == '\\') + } + + /// Returns whether the file is a regular file + pub fn is_file(&self) -> bool { + !self.is_dir() + } + + /// Get unix mode for the file + pub fn unix_mode(&self) -> Option<u32> { + if self.data.external_attributes == 0 { + return None; + } + + match self.data.system { + System::Unix => Some(self.data.external_attributes >> 16), + System::Dos => { + // Interpret MSDOS directory bit + let mut mode = if 0x10 == (self.data.external_attributes & 0x10) { + ffi::S_IFDIR | 0o0775 + } else { + ffi::S_IFREG | 0o0664 + }; + if 0x01 == (self.data.external_attributes & 0x01) { + // Read-only bit; strip write permissions + mode &= 0o0555; + } + Some(mode) + } + _ => None, + } + } + + /// Get the CRC32 hash of the original file + pub fn crc32(&self) -> u32 { + self.data.crc32 + } + + /// Get the starting offset of the data of the compressed file + pub fn data_start(&self) -> u64 { + self.data.data_start + } + + /// Get the starting offset of the zip header for this file + pub fn header_start(&self) -> u64 { + self.data.header_start + } + /// Get the starting offset of the zip header in the central directory for this file + pub fn central_header_start(&self) -> u64 { + self.data.central_header_start + } +} + +impl<'a> Read for ZipFile<'a> { + fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> { + self.get_reader().read(buf) + } +} + +impl<'a> Drop for ZipFile<'a> { + fn drop(&mut self) { + // self.data is Owned, this reader is constructed by a streaming reader. + // In this case, we want to exhaust the reader so that the next file is accessible. + if let Cow::Owned(_) = self.data { + let mut buffer = [0; 1 << 16]; + + // Get the inner `Take` reader so all decryption, decompression and CRC calculation is skipped. + let mut reader: std::io::Take<&mut dyn std::io::Read> = match &mut self.reader { + ZipFileReader::NoReader => { + let innerreader = ::std::mem::replace(&mut self.crypto_reader, None); + innerreader.expect("Invalid reader state").into_inner() + } + reader => { + let innerreader = ::std::mem::replace(reader, ZipFileReader::NoReader); + innerreader.into_inner() + } + }; + + loop { + match reader.read(&mut buffer) { + Ok(0) => break, + Ok(_) => (), + Err(e) => panic!( + "Could not consume all of the output of the current ZipFile: {:?}", + e + ), + } + } + } + } +} + +/// Read ZipFile structures from a non-seekable reader. +/// +/// This is an alternative method to read a zip file. If possible, use the ZipArchive functions +/// as some information will be missing when reading this manner. +/// +/// Reads a file header from the start of the stream. Will return `Ok(Some(..))` if a file is +/// present at the start of the stream. Returns `Ok(None)` if the start of the central directory +/// is encountered. No more files should be read after this. +/// +/// The Drop implementation of ZipFile ensures that the reader will be correctly positioned after +/// the structure is done. +/// +/// Missing fields are: +/// * `comment`: set to an empty string +/// * `data_start`: set to 0 +/// * `external_attributes`: `unix_mode()`: will return None +pub fn read_zipfile_from_stream<'a, R: io::Read>( + reader: &'a mut R, +) -> ZipResult<Option<ZipFile<'_>>> { + let signature = reader.read_u32::<LittleEndian>()?; + + match signature { + spec::LOCAL_FILE_HEADER_SIGNATURE => (), + spec::CENTRAL_DIRECTORY_HEADER_SIGNATURE => return Ok(None), + _ => return Err(ZipError::InvalidArchive("Invalid local file header")), + } + + let version_made_by = reader.read_u16::<LittleEndian>()?; + let flags = reader.read_u16::<LittleEndian>()?; + let encrypted = flags & 1 == 1; + let is_utf8 = flags & (1 << 11) != 0; + let using_data_descriptor = flags & (1 << 3) != 0; + #[allow(deprecated)] + let compression_method = CompressionMethod::from_u16(reader.read_u16::<LittleEndian>()?); + let last_mod_time = reader.read_u16::<LittleEndian>()?; + let last_mod_date = reader.read_u16::<LittleEndian>()?; + let crc32 = reader.read_u32::<LittleEndian>()?; + let compressed_size = reader.read_u32::<LittleEndian>()?; + let uncompressed_size = reader.read_u32::<LittleEndian>()?; + let file_name_length = reader.read_u16::<LittleEndian>()? as usize; + let extra_field_length = reader.read_u16::<LittleEndian>()? as usize; + + let mut file_name_raw = vec![0; file_name_length]; + reader.read_exact(&mut file_name_raw)?; + let mut extra_field = vec![0; extra_field_length]; + reader.read_exact(&mut extra_field)?; + + let file_name = match is_utf8 { + true => String::from_utf8_lossy(&*file_name_raw).into_owned(), + false => file_name_raw.clone().from_cp437(), + }; + + let mut result = ZipFileData { + system: System::from_u8((version_made_by >> 8) as u8), + version_made_by: version_made_by as u8, + encrypted, + compression_method, + last_modified_time: DateTime::from_msdos(last_mod_date, last_mod_time), + crc32, + compressed_size: compressed_size as u64, + uncompressed_size: uncompressed_size as u64, + file_name, + file_name_raw, + file_comment: String::new(), // file comment is only available in the central directory + // header_start and data start are not available, but also don't matter, since seeking is + // not available. + header_start: 0, + data_start: 0, + central_header_start: 0, + // The external_attributes field is only available in the central directory. + // We set this to zero, which should be valid as the docs state 'If input came + // from standard input, this field is set to zero.' + external_attributes: 0, + }; + + match parse_extra_field(&mut result, &extra_field) { + Ok(..) | Err(ZipError::Io(..)) => {} + Err(e) => return Err(e), + } + + if encrypted { + return unsupported_zip_error("Encrypted files are not supported"); + } + if using_data_descriptor { + return unsupported_zip_error("The file length is not available in the local header"); + } + + let limit_reader = (reader as &'a mut dyn io::Read).take(result.compressed_size as u64); + + let result_crc32 = result.crc32; + let result_compression_method = result.compression_method; + let crypto_reader = + make_crypto_reader(result_compression_method, result_crc32, limit_reader, None)?.unwrap(); + + Ok(Some(ZipFile { + data: Cow::Owned(result), + crypto_reader: None, + reader: make_reader(result_compression_method, result_crc32, crypto_reader), + })) +} + +#[cfg(test)] +mod test { + #[test] + fn invalid_offset() { + use super::ZipArchive; + use std::io; + + let mut v = Vec::new(); + v.extend_from_slice(include_bytes!("../tests/data/invalid_offset.zip")); + let reader = ZipArchive::new(io::Cursor::new(v)); + assert!(reader.is_err()); + } + + #[test] + fn invalid_offset2() { + use super::ZipArchive; + use std::io; + + let mut v = Vec::new(); + v.extend_from_slice(include_bytes!("../tests/data/invalid_offset2.zip")); + let reader = ZipArchive::new(io::Cursor::new(v)); + assert!(reader.is_err()); + } + + #[test] + fn zip64_with_leading_junk() { + use super::ZipArchive; + use std::io; + + let mut v = Vec::new(); + v.extend_from_slice(include_bytes!("../tests/data/zip64_demo.zip")); + let reader = ZipArchive::new(io::Cursor::new(v)).unwrap(); + assert!(reader.len() == 1); + } + + #[test] + fn zip_contents() { + use super::ZipArchive; + use std::io; + + let mut v = Vec::new(); + v.extend_from_slice(include_bytes!("../tests/data/mimetype.zip")); + let mut reader = ZipArchive::new(io::Cursor::new(v)).unwrap(); + assert!(reader.comment() == b""); + assert_eq!(reader.by_index(0).unwrap().central_header_start(), 77); + } + + #[test] + fn zip_read_streaming() { + use super::read_zipfile_from_stream; + use std::io; + + let mut v = Vec::new(); + v.extend_from_slice(include_bytes!("../tests/data/mimetype.zip")); + let mut reader = io::Cursor::new(v); + loop { + match read_zipfile_from_stream(&mut reader).unwrap() { + None => break, + _ => (), + } + } + } + + #[test] + fn zip_clone() { + use super::ZipArchive; + use std::io::{self, Read}; + + let mut v = Vec::new(); + v.extend_from_slice(include_bytes!("../tests/data/mimetype.zip")); + let mut reader1 = ZipArchive::new(io::Cursor::new(v)).unwrap(); + let mut reader2 = reader1.clone(); + + let mut file1 = reader1.by_index(0).unwrap(); + let mut file2 = reader2.by_index(0).unwrap(); + + let t = file1.last_modified(); + assert_eq!( + ( + t.year(), + t.month(), + t.day(), + t.hour(), + t.minute(), + t.second() + ), + (1980, 1, 1, 0, 0, 0) + ); + + let mut buf1 = [0; 5]; + let mut buf2 = [0; 5]; + let mut buf3 = [0; 5]; + let mut buf4 = [0; 5]; + + file1.read(&mut buf1).unwrap(); + file2.read(&mut buf2).unwrap(); + file1.read(&mut buf3).unwrap(); + file2.read(&mut buf4).unwrap(); + + assert_eq!(buf1, buf2); + assert_eq!(buf3, buf4); + assert!(buf1 != buf3); + } + + #[test] + fn file_and_dir_predicates() { + use super::ZipArchive; + use std::io; + + let mut v = Vec::new(); + v.extend_from_slice(include_bytes!("../tests/data/files_and_dirs.zip")); + let mut zip = ZipArchive::new(io::Cursor::new(v)).unwrap(); + + for i in 0..zip.len() { + let zip_file = zip.by_index(i).unwrap(); + let full_name = zip_file.enclosed_name().unwrap(); + let file_name = full_name.file_name().unwrap().to_str().unwrap(); + assert!( + (file_name.starts_with("dir") && zip_file.is_dir()) + || (file_name.starts_with("file") && zip_file.is_file()) + ); + } + } +} diff --git a/src/result.rs b/src/result.rs new file mode 100644 index 0000000..e8b7d05 --- /dev/null +++ b/src/result.rs @@ -0,0 +1,39 @@ +//! Error types that can be emitted from this library + +use std::io; + +use thiserror::Error; + +/// Generic result type with ZipError as its error variant +pub type ZipResult<T> = Result<T, ZipError>; + +/// The given password is wrong +#[derive(Error, Debug)] +#[error("invalid password for file in archive")] +pub struct InvalidPassword; + +/// Error type for Zip +#[derive(Debug, Error)] +pub enum ZipError { + /// An Error caused by I/O + #[error(transparent)] + Io(#[from] io::Error), + + /// This file is probably not a zip archive + #[error("invalid Zip archive")] + InvalidArchive(&'static str), + + /// This archive is not supported + #[error("unsupported Zip archive")] + UnsupportedArchive(&'static str), + + /// The requested file could not be found in the archive + #[error("specified file not found in archive")] + FileNotFound, +} + +impl From<ZipError> for io::Error { + fn from(err: ZipError) -> io::Error { + io::Error::new(io::ErrorKind::Other, err) + } +} diff --git a/src/spec.rs b/src/spec.rs new file mode 100644 index 0000000..91966b6 --- /dev/null +++ b/src/spec.rs @@ -0,0 +1,182 @@ +use crate::result::{ZipError, ZipResult}; +use byteorder::{LittleEndian, ReadBytesExt, WriteBytesExt}; +use std::io; +use std::io::prelude::*; + +pub const LOCAL_FILE_HEADER_SIGNATURE: u32 = 0x04034b50; +pub const CENTRAL_DIRECTORY_HEADER_SIGNATURE: u32 = 0x02014b50; +const CENTRAL_DIRECTORY_END_SIGNATURE: u32 = 0x06054b50; +pub const ZIP64_CENTRAL_DIRECTORY_END_SIGNATURE: u32 = 0x06064b50; +const ZIP64_CENTRAL_DIRECTORY_END_LOCATOR_SIGNATURE: u32 = 0x07064b50; + +pub struct CentralDirectoryEnd { + pub disk_number: u16, + pub disk_with_central_directory: u16, + pub number_of_files_on_this_disk: u16, + pub number_of_files: u16, + pub central_directory_size: u32, + pub central_directory_offset: u32, + pub zip_file_comment: Vec<u8>, +} + +impl CentralDirectoryEnd { + pub fn parse<T: Read>(reader: &mut T) -> ZipResult<CentralDirectoryEnd> { + let magic = reader.read_u32::<LittleEndian>()?; + if magic != CENTRAL_DIRECTORY_END_SIGNATURE { + return Err(ZipError::InvalidArchive("Invalid digital signature header")); + } + let disk_number = reader.read_u16::<LittleEndian>()?; + let disk_with_central_directory = reader.read_u16::<LittleEndian>()?; + let number_of_files_on_this_disk = reader.read_u16::<LittleEndian>()?; + let number_of_files = reader.read_u16::<LittleEndian>()?; + let central_directory_size = reader.read_u32::<LittleEndian>()?; + let central_directory_offset = reader.read_u32::<LittleEndian>()?; + let zip_file_comment_length = reader.read_u16::<LittleEndian>()? as usize; + let mut zip_file_comment = vec![0; zip_file_comment_length]; + reader.read_exact(&mut zip_file_comment)?; + + Ok(CentralDirectoryEnd { + disk_number, + disk_with_central_directory, + number_of_files_on_this_disk, + number_of_files, + central_directory_size, + central_directory_offset, + zip_file_comment, + }) + } + + pub fn find_and_parse<T: Read + io::Seek>( + reader: &mut T, + ) -> ZipResult<(CentralDirectoryEnd, u64)> { + const HEADER_SIZE: u64 = 22; + const BYTES_BETWEEN_MAGIC_AND_COMMENT_SIZE: u64 = HEADER_SIZE - 6; + let file_length = reader.seek(io::SeekFrom::End(0))?; + + let search_upper_bound = file_length.saturating_sub(HEADER_SIZE + ::std::u16::MAX as u64); + + if file_length < HEADER_SIZE { + return Err(ZipError::InvalidArchive("Invalid zip header")); + } + + let mut pos = file_length - HEADER_SIZE; + while pos >= search_upper_bound { + reader.seek(io::SeekFrom::Start(pos as u64))?; + if reader.read_u32::<LittleEndian>()? == CENTRAL_DIRECTORY_END_SIGNATURE { + reader.seek(io::SeekFrom::Current( + BYTES_BETWEEN_MAGIC_AND_COMMENT_SIZE as i64, + ))?; + let cde_start_pos = reader.seek(io::SeekFrom::Start(pos as u64))?; + return CentralDirectoryEnd::parse(reader).map(|cde| (cde, cde_start_pos)); + } + pos = match pos.checked_sub(1) { + Some(p) => p, + None => break, + }; + } + Err(ZipError::InvalidArchive( + "Could not find central directory end", + )) + } + + pub fn write<T: Write>(&self, writer: &mut T) -> ZipResult<()> { + writer.write_u32::<LittleEndian>(CENTRAL_DIRECTORY_END_SIGNATURE)?; + writer.write_u16::<LittleEndian>(self.disk_number)?; + writer.write_u16::<LittleEndian>(self.disk_with_central_directory)?; + writer.write_u16::<LittleEndian>(self.number_of_files_on_this_disk)?; + writer.write_u16::<LittleEndian>(self.number_of_files)?; + writer.write_u32::<LittleEndian>(self.central_directory_size)?; + writer.write_u32::<LittleEndian>(self.central_directory_offset)?; + writer.write_u16::<LittleEndian>(self.zip_file_comment.len() as u16)?; + writer.write_all(&self.zip_file_comment)?; + Ok(()) + } +} + +pub struct Zip64CentralDirectoryEndLocator { + pub disk_with_central_directory: u32, + pub end_of_central_directory_offset: u64, + pub number_of_disks: u32, +} + +impl Zip64CentralDirectoryEndLocator { + pub fn parse<T: Read>(reader: &mut T) -> ZipResult<Zip64CentralDirectoryEndLocator> { + let magic = reader.read_u32::<LittleEndian>()?; + if magic != ZIP64_CENTRAL_DIRECTORY_END_LOCATOR_SIGNATURE { + return Err(ZipError::InvalidArchive( + "Invalid zip64 locator digital signature header", + )); + } + let disk_with_central_directory = reader.read_u32::<LittleEndian>()?; + let end_of_central_directory_offset = reader.read_u64::<LittleEndian>()?; + let number_of_disks = reader.read_u32::<LittleEndian>()?; + + Ok(Zip64CentralDirectoryEndLocator { + disk_with_central_directory, + end_of_central_directory_offset, + number_of_disks, + }) + } +} + +pub struct Zip64CentralDirectoryEnd { + pub version_made_by: u16, + pub version_needed_to_extract: u16, + pub disk_number: u32, + pub disk_with_central_directory: u32, + pub number_of_files_on_this_disk: u64, + pub number_of_files: u64, + pub central_directory_size: u64, + pub central_directory_offset: u64, + //pub extensible_data_sector: Vec<u8>, <-- We don't do anything with this at the moment. +} + +impl Zip64CentralDirectoryEnd { + pub fn find_and_parse<T: Read + io::Seek>( + reader: &mut T, + nominal_offset: u64, + search_upper_bound: u64, + ) -> ZipResult<(Zip64CentralDirectoryEnd, u64)> { + let mut pos = nominal_offset; + + while pos <= search_upper_bound { + reader.seek(io::SeekFrom::Start(pos))?; + + if reader.read_u32::<LittleEndian>()? == ZIP64_CENTRAL_DIRECTORY_END_SIGNATURE { + let archive_offset = pos - nominal_offset; + + let _record_size = reader.read_u64::<LittleEndian>()?; + // We would use this value if we did anything with the "zip64 extensible data sector". + + let version_made_by = reader.read_u16::<LittleEndian>()?; + let version_needed_to_extract = reader.read_u16::<LittleEndian>()?; + let disk_number = reader.read_u32::<LittleEndian>()?; + let disk_with_central_directory = reader.read_u32::<LittleEndian>()?; + let number_of_files_on_this_disk = reader.read_u64::<LittleEndian>()?; + let number_of_files = reader.read_u64::<LittleEndian>()?; + let central_directory_size = reader.read_u64::<LittleEndian>()?; + let central_directory_offset = reader.read_u64::<LittleEndian>()?; + + return Ok(( + Zip64CentralDirectoryEnd { + version_made_by, + version_needed_to_extract, + disk_number, + disk_with_central_directory, + number_of_files_on_this_disk, + number_of_files, + central_directory_size, + central_directory_offset, + }, + archive_offset, + )); + } + + pos += 1; + } + + Err(ZipError::InvalidArchive( + "Could not find ZIP64 central directory end", + )) + } +} diff --git a/src/types.rs b/src/types.rs new file mode 100644 index 0000000..f468402 --- /dev/null +++ b/src/types.rs @@ -0,0 +1,474 @@ +//! Types that specify what is contained in a ZIP. + +#[derive(Clone, Copy, Debug, PartialEq)] +pub enum System { + Dos = 0, + Unix = 3, + Unknown, +} + +impl System { + pub fn from_u8(system: u8) -> System { + use self::System::*; + + match system { + 0 => Dos, + 3 => Unix, + _ => Unknown, + } + } +} + +/// A DateTime field to be used for storing timestamps in a zip file +/// +/// This structure does bounds checking to ensure the date is able to be stored in a zip file. +/// +/// When constructed manually from a date and time, it will also check if the input is sensible +/// (e.g. months are from [1, 12]), but when read from a zip some parts may be out of their normal +/// bounds (e.g. month 0, or hour 31). +/// +/// # Warning +/// +/// Some utilities use alternative timestamps to improve the accuracy of their +/// ZIPs, but we don't parse them yet. [We're working on this](https://github.com/mvdnes/zip-rs/issues/156#issuecomment-652981904), +/// however this API shouldn't be considered complete. +#[derive(Debug, Clone, Copy)] +pub struct DateTime { + year: u16, + month: u8, + day: u8, + hour: u8, + minute: u8, + second: u8, +} + +impl ::std::default::Default for DateTime { + /// Constructs an 'default' datetime of 1980-01-01 00:00:00 + fn default() -> DateTime { + DateTime { + year: 1980, + month: 1, + day: 1, + hour: 0, + minute: 0, + second: 0, + } + } +} + +impl DateTime { + /// Converts an msdos (u16, u16) pair to a DateTime object + pub fn from_msdos(datepart: u16, timepart: u16) -> DateTime { + let seconds = (timepart & 0b0000000000011111) << 1; + let minutes = (timepart & 0b0000011111100000) >> 5; + let hours = (timepart & 0b1111100000000000) >> 11; + let days = (datepart & 0b0000000000011111) >> 0; + let months = (datepart & 0b0000000111100000) >> 5; + let years = (datepart & 0b1111111000000000) >> 9; + + DateTime { + year: (years + 1980) as u16, + month: months as u8, + day: days as u8, + hour: hours as u8, + minute: minutes as u8, + second: seconds as u8, + } + } + + /// Constructs a DateTime from a specific date and time + /// + /// The bounds are: + /// * year: [1980, 2107] + /// * month: [1, 12] + /// * day: [1, 31] + /// * hour: [0, 23] + /// * minute: [0, 59] + /// * second: [0, 60] + pub fn from_date_and_time( + year: u16, + month: u8, + day: u8, + hour: u8, + minute: u8, + second: u8, + ) -> Result<DateTime, ()> { + if year >= 1980 + && year <= 2107 + && month >= 1 + && month <= 12 + && day >= 1 + && day <= 31 + && hour <= 23 + && minute <= 59 + && second <= 60 + { + Ok(DateTime { + year, + month, + day, + hour, + minute, + second, + }) + } else { + Err(()) + } + } + + #[cfg(feature = "time")] + /// Converts a ::time::Tm object to a DateTime + /// + /// Returns `Err` when this object is out of bounds + pub fn from_time(tm: ::time::Tm) -> Result<DateTime, ()> { + if tm.tm_year >= 80 + && tm.tm_year <= 207 + && tm.tm_mon >= 0 + && tm.tm_mon <= 11 + && tm.tm_mday >= 1 + && tm.tm_mday <= 31 + && tm.tm_hour >= 0 + && tm.tm_hour <= 23 + && tm.tm_min >= 0 + && tm.tm_min <= 59 + && tm.tm_sec >= 0 + && tm.tm_sec <= 60 + { + Ok(DateTime { + year: (tm.tm_year + 1900) as u16, + month: (tm.tm_mon + 1) as u8, + day: tm.tm_mday as u8, + hour: tm.tm_hour as u8, + minute: tm.tm_min as u8, + second: tm.tm_sec as u8, + }) + } else { + Err(()) + } + } + + /// Gets the time portion of this datetime in the msdos representation + pub fn timepart(&self) -> u16 { + ((self.second as u16) >> 1) | ((self.minute as u16) << 5) | ((self.hour as u16) << 11) + } + + /// Gets the date portion of this datetime in the msdos representation + pub fn datepart(&self) -> u16 { + (self.day as u16) | ((self.month as u16) << 5) | ((self.year - 1980) << 9) + } + + #[cfg(feature = "time")] + /// Converts the datetime to a Tm structure + /// + /// The fields `tm_wday`, `tm_yday`, `tm_utcoff` and `tm_nsec` are set to their defaults. + pub fn to_time(&self) -> ::time::Tm { + ::time::Tm { + tm_sec: self.second as i32, + tm_min: self.minute as i32, + tm_hour: self.hour as i32, + tm_mday: self.day as i32, + tm_mon: self.month as i32 - 1, + tm_year: self.year as i32 - 1900, + tm_isdst: -1, + ..::time::empty_tm() + } + } + + /// Get the year. There is no epoch, i.e. 2018 will be returned as 2018. + pub fn year(&self) -> u16 { + self.year + } + + /// Get the month, where 1 = january and 12 = december + pub fn month(&self) -> u8 { + self.month + } + + /// Get the day + pub fn day(&self) -> u8 { + self.day + } + + /// Get the hour + pub fn hour(&self) -> u8 { + self.hour + } + + /// Get the minute + pub fn minute(&self) -> u8 { + self.minute + } + + /// Get the second + pub fn second(&self) -> u8 { + self.second + } +} + +pub const DEFAULT_VERSION: u8 = 46; + +/// Structure representing a ZIP file. +#[derive(Debug, Clone)] +pub struct ZipFileData { + /// Compatibility of the file attribute information + pub system: System, + /// Specification version + pub version_made_by: u8, + /// True if the file is encrypted. + pub encrypted: bool, + /// Compression method used to store the file + pub compression_method: crate::compression::CompressionMethod, + /// Last modified time. This will only have a 2 second precision. + pub last_modified_time: DateTime, + /// CRC32 checksum + pub crc32: u32, + /// Size of the file in the ZIP + pub compressed_size: u64, + /// Size of the file when extracted + pub uncompressed_size: u64, + /// Name of the file + pub file_name: String, + /// Raw file name. To be used when file_name was incorrectly decoded. + pub file_name_raw: Vec<u8>, + /// File comment + pub file_comment: String, + /// Specifies where the local header of the file starts + pub header_start: u64, + /// Specifies where the central header of the file starts + /// + /// Note that when this is not known, it is set to 0 + pub central_header_start: u64, + /// Specifies where the compressed data of the file starts + pub data_start: u64, + /// External file attributes + pub external_attributes: u32, +} + +impl ZipFileData { + pub fn file_name_sanitized(&self) -> ::std::path::PathBuf { + let no_null_filename = match self.file_name.find('\0') { + Some(index) => &self.file_name[0..index], + None => &self.file_name, + } + .to_string(); + + // zip files can contain both / and \ as separators regardless of the OS + // and as we want to return a sanitized PathBuf that only supports the + // OS separator let's convert incompatible separators to compatible ones + let separator = ::std::path::MAIN_SEPARATOR; + let opposite_separator = match separator { + '/' => '\\', + _ => '/', + }; + let filename = + no_null_filename.replace(&opposite_separator.to_string(), &separator.to_string()); + + ::std::path::Path::new(&filename) + .components() + .filter(|component| match *component { + ::std::path::Component::Normal(..) => true, + _ => false, + }) + .fold(::std::path::PathBuf::new(), |mut path, ref cur| { + path.push(cur.as_os_str()); + path + }) + } + + pub fn version_needed(&self) -> u16 { + match self.compression_method { + #[cfg(feature = "bzip2")] + crate::compression::CompressionMethod::Bzip2 => 46, + _ => 20, + } + } +} + +#[cfg(test)] +mod test { + #[test] + fn system() { + use super::System; + assert_eq!(System::Dos as u16, 0u16); + assert_eq!(System::Unix as u16, 3u16); + assert_eq!(System::from_u8(0), System::Dos); + assert_eq!(System::from_u8(3), System::Unix); + } + + #[test] + fn sanitize() { + use super::*; + let file_name = "/path/../../../../etc/./passwd\0/etc/shadow".to_string(); + let data = ZipFileData { + system: System::Dos, + version_made_by: 0, + encrypted: false, + compression_method: crate::compression::CompressionMethod::Stored, + last_modified_time: DateTime::default(), + crc32: 0, + compressed_size: 0, + uncompressed_size: 0, + file_name: file_name.clone(), + file_name_raw: file_name.into_bytes(), + file_comment: String::new(), + header_start: 0, + data_start: 0, + central_header_start: 0, + external_attributes: 0, + }; + assert_eq!( + data.file_name_sanitized(), + ::std::path::PathBuf::from("path/etc/passwd") + ); + } + + #[test] + fn datetime_default() { + use super::DateTime; + let dt = DateTime::default(); + assert_eq!(dt.timepart(), 0); + assert_eq!(dt.datepart(), 0b0000000_0001_00001); + } + + #[test] + fn datetime_max() { + use super::DateTime; + let dt = DateTime::from_date_and_time(2107, 12, 31, 23, 59, 60).unwrap(); + assert_eq!(dt.timepart(), 0b10111_111011_11110); + assert_eq!(dt.datepart(), 0b1111111_1100_11111); + } + + #[test] + fn datetime_bounds() { + use super::DateTime; + + assert!(DateTime::from_date_and_time(2000, 1, 1, 23, 59, 60).is_ok()); + assert!(DateTime::from_date_and_time(2000, 1, 1, 24, 0, 0).is_err()); + assert!(DateTime::from_date_and_time(2000, 1, 1, 0, 60, 0).is_err()); + assert!(DateTime::from_date_and_time(2000, 1, 1, 0, 0, 61).is_err()); + + assert!(DateTime::from_date_and_time(2107, 12, 31, 0, 0, 0).is_ok()); + assert!(DateTime::from_date_and_time(1980, 1, 1, 0, 0, 0).is_ok()); + assert!(DateTime::from_date_and_time(1979, 1, 1, 0, 0, 0).is_err()); + assert!(DateTime::from_date_and_time(1980, 0, 1, 0, 0, 0).is_err()); + assert!(DateTime::from_date_and_time(1980, 1, 0, 0, 0, 0).is_err()); + assert!(DateTime::from_date_and_time(2108, 12, 31, 0, 0, 0).is_err()); + assert!(DateTime::from_date_and_time(2107, 13, 31, 0, 0, 0).is_err()); + assert!(DateTime::from_date_and_time(2107, 12, 32, 0, 0, 0).is_err()); + } + + #[cfg(feature = "time")] + #[test] + fn datetime_from_time_bounds() { + use super::DateTime; + + // 1979-12-31 23:59:59 + assert!(DateTime::from_time(::time::Tm { + tm_sec: 59, + tm_min: 59, + tm_hour: 23, + tm_mday: 31, + tm_mon: 11, // tm_mon has number range [0, 11] + tm_year: 79, // 1979 - 1900 = 79 + ..::time::empty_tm() + }) + .is_err()); + + // 1980-01-01 00:00:00 + assert!(DateTime::from_time(::time::Tm { + tm_sec: 0, + tm_min: 0, + tm_hour: 0, + tm_mday: 1, + tm_mon: 0, // tm_mon has number range [0, 11] + tm_year: 80, // 1980 - 1900 = 80 + ..::time::empty_tm() + }) + .is_ok()); + + // 2107-12-31 23:59:59 + assert!(DateTime::from_time(::time::Tm { + tm_sec: 59, + tm_min: 59, + tm_hour: 23, + tm_mday: 31, + tm_mon: 11, // tm_mon has number range [0, 11] + tm_year: 207, // 2107 - 1900 = 207 + ..::time::empty_tm() + }) + .is_ok()); + + // 2108-01-01 00:00:00 + assert!(DateTime::from_time(::time::Tm { + tm_sec: 0, + tm_min: 0, + tm_hour: 0, + tm_mday: 1, + tm_mon: 0, // tm_mon has number range [0, 11] + tm_year: 208, // 2108 - 1900 = 208 + ..::time::empty_tm() + }) + .is_err()); + } + + #[test] + fn time_conversion() { + use super::DateTime; + let dt = DateTime::from_msdos(0x4D71, 0x54CF); + assert_eq!(dt.year(), 2018); + assert_eq!(dt.month(), 11); + assert_eq!(dt.day(), 17); + assert_eq!(dt.hour(), 10); + assert_eq!(dt.minute(), 38); + assert_eq!(dt.second(), 30); + + #[cfg(feature = "time")] + assert_eq!( + format!("{}", dt.to_time().rfc3339()), + "2018-11-17T10:38:30Z" + ); + } + + #[test] + fn time_out_of_bounds() { + use super::DateTime; + let dt = DateTime::from_msdos(0xFFFF, 0xFFFF); + assert_eq!(dt.year(), 2107); + assert_eq!(dt.month(), 15); + assert_eq!(dt.day(), 31); + assert_eq!(dt.hour(), 31); + assert_eq!(dt.minute(), 63); + assert_eq!(dt.second(), 62); + + #[cfg(feature = "time")] + assert_eq!( + format!("{}", dt.to_time().rfc3339()), + "2107-15-31T31:63:62Z" + ); + + let dt = DateTime::from_msdos(0x0000, 0x0000); + assert_eq!(dt.year(), 1980); + assert_eq!(dt.month(), 0); + assert_eq!(dt.day(), 0); + assert_eq!(dt.hour(), 0); + assert_eq!(dt.minute(), 0); + assert_eq!(dt.second(), 0); + + #[cfg(feature = "time")] + assert_eq!( + format!("{}", dt.to_time().rfc3339()), + "1980-00-00T00:00:00Z" + ); + } + + #[cfg(feature = "time")] + #[test] + fn time_at_january() { + use super::DateTime; + + // 2020-01-01 00:00:00 + let clock = ::time::Timespec::new(1577836800, 0); + let tm = ::time::at_utc(clock); + assert!(DateTime::from_time(tm).is_ok()); + } +} diff --git a/src/write.rs b/src/write.rs new file mode 100644 index 0000000..bc68817 --- /dev/null +++ b/src/write.rs @@ -0,0 +1,821 @@ +//! Types for creating ZIP archives + +use crate::compression::CompressionMethod; +use crate::read::ZipFile; +use crate::result::{ZipError, ZipResult}; +use crate::spec; +use crate::types::{DateTime, System, ZipFileData, DEFAULT_VERSION}; +use byteorder::{LittleEndian, WriteBytesExt}; +use crc32fast::Hasher; +use std::default::Default; +use std::io; +use std::io::prelude::*; +use std::mem; + +#[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" +))] +use flate2::write::DeflateEncoder; + +#[cfg(feature = "bzip2")] +use bzip2::write::BzEncoder; + +enum GenericZipWriter<W: Write + io::Seek> { + Closed, + Storer(W), + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + Deflater(DeflateEncoder<W>), + #[cfg(feature = "bzip2")] + Bzip2(BzEncoder<W>), +} + +/// ZIP archive generator +/// +/// Handles the bookkeeping involved in building an archive, and provides an +/// API to edit its contents. +/// +/// ``` +/// # fn doit() -> zip::result::ZipResult<()> +/// # { +/// # use zip::ZipWriter; +/// use std::io::Write; +/// use zip::write::FileOptions; +/// +/// // We use a buffer here, though you'd normally use a `File` +/// let mut buf = [0; 65536]; +/// let mut zip = zip::ZipWriter::new(std::io::Cursor::new(&mut buf[..])); +/// +/// let options = zip::write::FileOptions::default().compression_method(zip::CompressionMethod::Stored); +/// zip.start_file("hello_world.txt", options)?; +/// zip.write(b"Hello, World!")?; +/// +/// // Apply the changes you've made. +/// // Dropping the `ZipWriter` will have the same effect, but may silently fail +/// zip.finish()?; +/// +/// # Ok(()) +/// # } +/// # doit().unwrap(); +/// ``` +pub struct ZipWriter<W: Write + io::Seek> { + inner: GenericZipWriter<W>, + files: Vec<ZipFileData>, + stats: ZipWriterStats, + writing_to_file: bool, + comment: String, + writing_raw: bool, +} + +#[derive(Default)] +struct ZipWriterStats { + hasher: Hasher, + start: u64, + bytes_written: u64, +} + +struct ZipRawValues { + crc32: u32, + compressed_size: u64, + uncompressed_size: u64, +} + +/// Metadata for a file to be written +#[derive(Copy, Clone)] +pub struct FileOptions { + compression_method: CompressionMethod, + last_modified_time: DateTime, + permissions: Option<u32>, +} + +impl FileOptions { + /// Construct a new FileOptions object + pub fn default() -> FileOptions { + FileOptions { + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + compression_method: CompressionMethod::Deflated, + #[cfg(not(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + )))] + compression_method: CompressionMethod::Stored, + #[cfg(feature = "time")] + last_modified_time: DateTime::from_time(time::now()).unwrap_or_default(), + #[cfg(not(feature = "time"))] + last_modified_time: DateTime::default(), + permissions: None, + } + } + + /// Set the compression method for the new file + /// + /// The default is `CompressionMethod::Deflated`. If the deflate compression feature is + /// disabled, `CompressionMethod::Stored` becomes the default. + /// otherwise. + pub fn compression_method(mut self, method: CompressionMethod) -> FileOptions { + self.compression_method = method; + self + } + + /// Set the last modified time + /// + /// The default is the current timestamp if the 'time' feature is enabled, and 1980-01-01 + /// otherwise + pub fn last_modified_time(mut self, mod_time: DateTime) -> FileOptions { + self.last_modified_time = mod_time; + self + } + + /// Set the permissions for the new file. + /// + /// The format is represented with unix-style permissions. + /// The default is `0o644`, which represents `rw-r--r--` for files, + /// and `0o755`, which represents `rwxr-xr-x` for directories + pub fn unix_permissions(mut self, mode: u32) -> FileOptions { + self.permissions = Some(mode & 0o777); + self + } +} + +impl Default for FileOptions { + fn default() -> Self { + Self::default() + } +} + +impl<W: Write + io::Seek> Write for ZipWriter<W> { + fn write(&mut self, buf: &[u8]) -> io::Result<usize> { + if !self.writing_to_file { + return Err(io::Error::new( + io::ErrorKind::Other, + "No file has been started", + )); + } + match self.inner.ref_mut() { + Some(ref mut w) => { + let write_result = w.write(buf); + if let Ok(count) = write_result { + self.stats.update(&buf[0..count]); + } + write_result + } + None => Err(io::Error::new( + io::ErrorKind::BrokenPipe, + "ZipWriter was already closed", + )), + } + } + + fn flush(&mut self) -> io::Result<()> { + match self.inner.ref_mut() { + Some(ref mut w) => w.flush(), + None => Err(io::Error::new( + io::ErrorKind::BrokenPipe, + "ZipWriter was already closed", + )), + } + } +} + +impl ZipWriterStats { + fn update(&mut self, buf: &[u8]) { + self.hasher.update(buf); + self.bytes_written += buf.len() as u64; + } +} + +impl<W: Write + io::Seek> ZipWriter<W> { + /// Initializes the archive. + /// + /// Before writing to this object, the [`ZipWriter::start_file`] function should be called. + pub fn new(inner: W) -> ZipWriter<W> { + ZipWriter { + inner: GenericZipWriter::Storer(inner), + files: Vec::new(), + stats: Default::default(), + writing_to_file: false, + comment: String::new(), + writing_raw: false, + } + } + + /// Set ZIP archive comment. + pub fn set_comment<S>(&mut self, comment: S) + where + S: Into<String>, + { + self.comment = comment.into(); + } + + /// Start a new file for with the requested options. + fn start_entry<S>( + &mut self, + name: S, + options: FileOptions, + raw_values: Option<ZipRawValues>, + ) -> ZipResult<()> + where + S: Into<String>, + { + self.finish_file()?; + + let is_raw = raw_values.is_some(); + let raw_values = raw_values.unwrap_or_else(|| ZipRawValues { + crc32: 0, + compressed_size: 0, + uncompressed_size: 0, + }); + + { + let writer = self.inner.get_plain(); + let header_start = writer.seek(io::SeekFrom::Current(0))?; + + let permissions = options.permissions.unwrap_or(0o100644); + let mut file = ZipFileData { + system: System::Unix, + version_made_by: DEFAULT_VERSION, + encrypted: false, + compression_method: options.compression_method, + last_modified_time: options.last_modified_time, + crc32: raw_values.crc32, + compressed_size: raw_values.compressed_size, + uncompressed_size: raw_values.uncompressed_size, + file_name: name.into(), + file_name_raw: Vec::new(), // Never used for saving + file_comment: String::new(), + header_start, + data_start: 0, + central_header_start: 0, + external_attributes: permissions << 16, + }; + write_local_file_header(writer, &file)?; + + let header_end = writer.seek(io::SeekFrom::Current(0))?; + self.stats.start = header_end; + file.data_start = header_end; + + self.stats.bytes_written = 0; + self.stats.hasher = Hasher::new(); + + self.files.push(file); + } + + self.writing_raw = is_raw; + self.inner.switch_to(if is_raw { + CompressionMethod::Stored + } else { + options.compression_method + })?; + + Ok(()) + } + + fn finish_file(&mut self) -> ZipResult<()> { + self.inner.switch_to(CompressionMethod::Stored)?; + let writer = self.inner.get_plain(); + + if !self.writing_raw { + let file = match self.files.last_mut() { + None => return Ok(()), + Some(f) => f, + }; + file.crc32 = self.stats.hasher.clone().finalize(); + file.uncompressed_size = self.stats.bytes_written; + + let file_end = writer.seek(io::SeekFrom::Current(0))?; + file.compressed_size = file_end - self.stats.start; + + update_local_file_header(writer, file)?; + writer.seek(io::SeekFrom::Start(file_end))?; + } + + self.writing_to_file = false; + self.writing_raw = false; + Ok(()) + } + + /// Create a file in the archive and start writing its' contents. + /// + /// The data should be written using the [`io::Write`] implementation on this [`ZipWriter`] + pub fn start_file<S>(&mut self, name: S, mut options: FileOptions) -> ZipResult<()> + where + S: Into<String>, + { + if options.permissions.is_none() { + options.permissions = Some(0o644); + } + *options.permissions.as_mut().unwrap() |= 0o100000; + self.start_entry(name, options, None)?; + self.writing_to_file = true; + Ok(()) + } + + /// Starts a file, taking a Path as argument. + /// + /// This function ensures that the '/' path seperator is used. It also ignores all non 'Normal' + /// Components, such as a starting '/' or '..' and '.'. + #[deprecated( + since = "0.5.7", + note = "by stripping `..`s from the path, the meaning of paths can change. Use `start_file` instead." + )] + pub fn start_file_from_path( + &mut self, + path: &std::path::Path, + options: FileOptions, + ) -> ZipResult<()> { + self.start_file(path_to_string(path), options) + } + + /// Add a new file using the already compressed data from a ZIP file being read and renames it, this + /// allows faster copies of the `ZipFile` since there is no need to decompress and compress it again. + /// Any `ZipFile` metadata is copied and not checked, for example the file CRC. + + /// ```no_run + /// use std::fs::File; + /// use std::io::{Read, Seek, Write}; + /// use zip::{ZipArchive, ZipWriter}; + /// + /// fn copy_rename<R, W>( + /// src: &mut ZipArchive<R>, + /// dst: &mut ZipWriter<W>, + /// ) -> zip::result::ZipResult<()> + /// where + /// R: Read + Seek, + /// W: Write + Seek, + /// { + /// // Retrieve file entry by name + /// let file = src.by_name("src_file.txt")?; + /// + /// // Copy and rename the previously obtained file entry to the destination zip archive + /// dst.raw_copy_file_rename(file, "new_name.txt")?; + /// + /// Ok(()) + /// } + /// ``` + pub fn raw_copy_file_rename<S>(&mut self, mut file: ZipFile, name: S) -> ZipResult<()> + where + S: Into<String>, + { + let options = FileOptions::default() + .last_modified_time(file.last_modified()) + .compression_method(file.compression()); + if let Some(perms) = file.unix_mode() { + options.unix_permissions(perms); + } + + let raw_values = ZipRawValues { + crc32: file.crc32(), + compressed_size: file.compressed_size(), + uncompressed_size: file.size(), + }; + + self.start_entry(name, options, Some(raw_values))?; + self.writing_to_file = true; + + io::copy(file.get_raw_reader(), self)?; + + Ok(()) + } + + /// Add a new file using the already compressed data from a ZIP file being read, this allows faster + /// copies of the `ZipFile` since there is no need to decompress and compress it again. Any `ZipFile` + /// metadata is copied and not checked, for example the file CRC. + /// + /// ```no_run + /// use std::fs::File; + /// use std::io::{Read, Seek, Write}; + /// use zip::{ZipArchive, ZipWriter}; + /// + /// fn copy<R, W>(src: &mut ZipArchive<R>, dst: &mut ZipWriter<W>) -> zip::result::ZipResult<()> + /// where + /// R: Read + Seek, + /// W: Write + Seek, + /// { + /// // Retrieve file entry by name + /// let file = src.by_name("src_file.txt")?; + /// + /// // Copy the previously obtained file entry to the destination zip archive + /// dst.raw_copy_file(file)?; + /// + /// Ok(()) + /// } + /// ``` + pub fn raw_copy_file(&mut self, file: ZipFile) -> ZipResult<()> { + let name = file.name().to_owned(); + self.raw_copy_file_rename(file, name) + } + + /// Add a directory entry. + /// + /// You can't write data to the file afterwards. + pub fn add_directory<S>(&mut self, name: S, mut options: FileOptions) -> ZipResult<()> + where + S: Into<String>, + { + if options.permissions.is_none() { + options.permissions = Some(0o755); + } + *options.permissions.as_mut().unwrap() |= 0o40000; + options.compression_method = CompressionMethod::Stored; + + let name_as_string = name.into(); + // Append a slash to the filename if it does not end with it. + let name_with_slash = match name_as_string.chars().last() { + Some('/') | Some('\\') => name_as_string, + _ => name_as_string + "/", + }; + + self.start_entry(name_with_slash, options, None)?; + self.writing_to_file = false; + Ok(()) + } + + /// Add a directory entry, taking a Path as argument. + /// + /// This function ensures that the '/' path seperator is used. It also ignores all non 'Normal' + /// Components, such as a starting '/' or '..' and '.'. + #[deprecated( + since = "0.5.7", + note = "by stripping `..`s from the path, the meaning of paths can change. Use `add_directory` instead." + )] + pub fn add_directory_from_path( + &mut self, + path: &std::path::Path, + options: FileOptions, + ) -> ZipResult<()> { + self.add_directory(path_to_string(path), options) + } + + /// Finish the last file and write all other zip-structures + /// + /// This will return the writer, but one should normally not append any data to the end of the file. + /// Note that the zipfile will also be finished on drop. + pub fn finish(&mut self) -> ZipResult<W> { + self.finalize()?; + let inner = mem::replace(&mut self.inner, GenericZipWriter::Closed); + Ok(inner.unwrap()) + } + + fn finalize(&mut self) -> ZipResult<()> { + self.finish_file()?; + + { + let writer = self.inner.get_plain(); + + let central_start = writer.seek(io::SeekFrom::Current(0))?; + for file in self.files.iter() { + write_central_directory_header(writer, file)?; + } + let central_size = writer.seek(io::SeekFrom::Current(0))? - central_start; + + let footer = spec::CentralDirectoryEnd { + disk_number: 0, + disk_with_central_directory: 0, + number_of_files_on_this_disk: self.files.len() as u16, + number_of_files: self.files.len() as u16, + central_directory_size: central_size as u32, + central_directory_offset: central_start as u32, + zip_file_comment: self.comment.as_bytes().to_vec(), + }; + + footer.write(writer)?; + } + + Ok(()) + } +} + +impl<W: Write + io::Seek> Drop for ZipWriter<W> { + fn drop(&mut self) { + if !self.inner.is_closed() { + if let Err(e) = self.finalize() { + let _ = write!(&mut io::stderr(), "ZipWriter drop failed: {:?}", e); + } + } + } +} + +impl<W: Write + io::Seek> GenericZipWriter<W> { + fn switch_to(&mut self, compression: CompressionMethod) -> ZipResult<()> { + match self.current_compression() { + Some(method) if method == compression => return Ok(()), + None => { + return Err(io::Error::new( + io::ErrorKind::BrokenPipe, + "ZipWriter was already closed", + ) + .into()) + } + _ => {} + } + + let bare = match mem::replace(self, GenericZipWriter::Closed) { + GenericZipWriter::Storer(w) => w, + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + GenericZipWriter::Deflater(w) => w.finish()?, + #[cfg(feature = "bzip2")] + GenericZipWriter::Bzip2(w) => w.finish()?, + GenericZipWriter::Closed => { + return Err(io::Error::new( + io::ErrorKind::BrokenPipe, + "ZipWriter was already closed", + ) + .into()) + } + }; + + *self = { + #[allow(deprecated)] + match compression { + CompressionMethod::Stored => GenericZipWriter::Storer(bare), + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + CompressionMethod::Deflated => GenericZipWriter::Deflater(DeflateEncoder::new( + bare, + flate2::Compression::default(), + )), + #[cfg(feature = "bzip2")] + CompressionMethod::Bzip2 => { + GenericZipWriter::Bzip2(BzEncoder::new(bare, bzip2::Compression::Default)) + } + CompressionMethod::Unsupported(..) => { + return Err(ZipError::UnsupportedArchive("Unsupported compression")) + } + } + }; + + Ok(()) + } + + fn ref_mut(&mut self) -> Option<&mut dyn Write> { + match *self { + GenericZipWriter::Storer(ref mut w) => Some(w as &mut dyn Write), + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + GenericZipWriter::Deflater(ref mut w) => Some(w as &mut dyn Write), + #[cfg(feature = "bzip2")] + GenericZipWriter::Bzip2(ref mut w) => Some(w as &mut dyn Write), + GenericZipWriter::Closed => None, + } + } + + fn is_closed(&self) -> bool { + match *self { + GenericZipWriter::Closed => true, + _ => false, + } + } + + fn get_plain(&mut self) -> &mut W { + match *self { + GenericZipWriter::Storer(ref mut w) => w, + _ => panic!("Should have switched to stored beforehand"), + } + } + + fn current_compression(&self) -> Option<CompressionMethod> { + match *self { + GenericZipWriter::Storer(..) => Some(CompressionMethod::Stored), + #[cfg(any( + feature = "deflate", + feature = "deflate-miniz", + feature = "deflate-zlib" + ))] + GenericZipWriter::Deflater(..) => Some(CompressionMethod::Deflated), + #[cfg(feature = "bzip2")] + GenericZipWriter::Bzip2(..) => Some(CompressionMethod::Bzip2), + GenericZipWriter::Closed => None, + } + } + + fn unwrap(self) -> W { + match self { + GenericZipWriter::Storer(w) => w, + _ => panic!("Should have switched to stored beforehand"), + } + } +} + +fn write_local_file_header<T: Write>(writer: &mut T, file: &ZipFileData) -> ZipResult<()> { + // local file header signature + writer.write_u32::<LittleEndian>(spec::LOCAL_FILE_HEADER_SIGNATURE)?; + // version needed to extract + writer.write_u16::<LittleEndian>(file.version_needed())?; + // general purpose bit flag + let flag = if !file.file_name.is_ascii() { + 1u16 << 11 + } else { + 0 + }; + writer.write_u16::<LittleEndian>(flag)?; + // Compression method + #[allow(deprecated)] + writer.write_u16::<LittleEndian>(file.compression_method.to_u16())?; + // last mod file time and last mod file date + writer.write_u16::<LittleEndian>(file.last_modified_time.timepart())?; + writer.write_u16::<LittleEndian>(file.last_modified_time.datepart())?; + // crc-32 + writer.write_u32::<LittleEndian>(file.crc32)?; + // compressed size + writer.write_u32::<LittleEndian>(file.compressed_size as u32)?; + // uncompressed size + writer.write_u32::<LittleEndian>(file.uncompressed_size as u32)?; + // file name length + writer.write_u16::<LittleEndian>(file.file_name.as_bytes().len() as u16)?; + // extra field length + let extra_field = build_extra_field(file)?; + writer.write_u16::<LittleEndian>(extra_field.len() as u16)?; + // file name + writer.write_all(file.file_name.as_bytes())?; + // extra field + writer.write_all(&extra_field)?; + + Ok(()) +} + +fn update_local_file_header<T: Write + io::Seek>( + writer: &mut T, + file: &ZipFileData, +) -> ZipResult<()> { + const CRC32_OFFSET: u64 = 14; + writer.seek(io::SeekFrom::Start(file.header_start + CRC32_OFFSET))?; + writer.write_u32::<LittleEndian>(file.crc32)?; + writer.write_u32::<LittleEndian>(file.compressed_size as u32)?; + writer.write_u32::<LittleEndian>(file.uncompressed_size as u32)?; + Ok(()) +} + +fn write_central_directory_header<T: Write>(writer: &mut T, file: &ZipFileData) -> ZipResult<()> { + // central file header signature + writer.write_u32::<LittleEndian>(spec::CENTRAL_DIRECTORY_HEADER_SIGNATURE)?; + // version made by + let version_made_by = (file.system as u16) << 8 | (file.version_made_by as u16); + writer.write_u16::<LittleEndian>(version_made_by)?; + // version needed to extract + writer.write_u16::<LittleEndian>(file.version_needed())?; + // general puprose bit flag + let flag = if !file.file_name.is_ascii() { + 1u16 << 11 + } else { + 0 + }; + writer.write_u16::<LittleEndian>(flag)?; + // compression method + #[allow(deprecated)] + writer.write_u16::<LittleEndian>(file.compression_method.to_u16())?; + // last mod file time + date + writer.write_u16::<LittleEndian>(file.last_modified_time.timepart())?; + writer.write_u16::<LittleEndian>(file.last_modified_time.datepart())?; + // crc-32 + writer.write_u32::<LittleEndian>(file.crc32)?; + // compressed size + writer.write_u32::<LittleEndian>(file.compressed_size as u32)?; + // uncompressed size + writer.write_u32::<LittleEndian>(file.uncompressed_size as u32)?; + // file name length + writer.write_u16::<LittleEndian>(file.file_name.as_bytes().len() as u16)?; + // extra field length + let extra_field = build_extra_field(file)?; + writer.write_u16::<LittleEndian>(extra_field.len() as u16)?; + // file comment length + writer.write_u16::<LittleEndian>(0)?; + // disk number start + writer.write_u16::<LittleEndian>(0)?; + // internal file attribytes + writer.write_u16::<LittleEndian>(0)?; + // external file attributes + writer.write_u32::<LittleEndian>(file.external_attributes)?; + // relative offset of local header + writer.write_u32::<LittleEndian>(file.header_start as u32)?; + // file name + writer.write_all(file.file_name.as_bytes())?; + // extra field + writer.write_all(&extra_field)?; + // file comment + // <none> + + Ok(()) +} + +fn build_extra_field(_file: &ZipFileData) -> ZipResult<Vec<u8>> { + let writer = Vec::new(); + // Future work + Ok(writer) +} + +fn path_to_string(path: &std::path::Path) -> String { + let mut path_str = String::new(); + for component in path.components() { + if let std::path::Component::Normal(os_str) = component { + if !path_str.is_empty() { + path_str.push('/'); + } + path_str.push_str(&*os_str.to_string_lossy()); + } + } + path_str +} + +#[cfg(test)] +mod test { + use super::{FileOptions, ZipWriter}; + use crate::compression::CompressionMethod; + use crate::types::DateTime; + use std::io; + use std::io::Write; + + #[test] + fn write_empty_zip() { + let mut writer = ZipWriter::new(io::Cursor::new(Vec::new())); + writer.set_comment("ZIP"); + let result = writer.finish().unwrap(); + assert_eq!(result.get_ref().len(), 25); + assert_eq!( + *result.get_ref(), + [80, 75, 5, 6, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 90, 73, 80] + ); + } + + #[test] + fn write_zip_dir() { + let mut writer = ZipWriter::new(io::Cursor::new(Vec::new())); + writer + .add_directory( + "test", + FileOptions::default().last_modified_time( + DateTime::from_date_and_time(2018, 8, 15, 20, 45, 6).unwrap(), + ), + ) + .unwrap(); + assert!(writer + .write(b"writing to a directory is not allowed, and will not write any data") + .is_err()); + let result = writer.finish().unwrap(); + assert_eq!(result.get_ref().len(), 108); + assert_eq!( + *result.get_ref(), + &[ + 80u8, 75, 3, 4, 20, 0, 0, 0, 0, 0, 163, 165, 15, 77, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 5, 0, 0, 0, 116, 101, 115, 116, 47, 80, 75, 1, 2, 46, 3, 20, 0, 0, 0, 0, 0, + 163, 165, 15, 77, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 237, 65, 0, 0, 0, 0, 116, 101, 115, 116, 47, 80, 75, 5, 6, 0, 0, 0, 0, 1, 0, + 1, 0, 51, 0, 0, 0, 35, 0, 0, 0, 0, 0, + ] as &[u8] + ); + } + + #[test] + fn write_mimetype_zip() { + let mut writer = ZipWriter::new(io::Cursor::new(Vec::new())); + let options = FileOptions { + compression_method: CompressionMethod::Stored, + last_modified_time: DateTime::default(), + permissions: Some(33188), + }; + writer.start_file("mimetype", options).unwrap(); + writer + .write(b"application/vnd.oasis.opendocument.text") + .unwrap(); + let result = writer.finish().unwrap(); + + assert_eq!(result.get_ref().len(), 153); + let mut v = Vec::new(); + v.extend_from_slice(include_bytes!("../tests/data/mimetype.zip")); + assert_eq!(result.get_ref(), &v); + } + + #[test] + fn path_to_string() { + let mut path = std::path::PathBuf::new(); + #[cfg(windows)] + path.push(r"C:\"); + #[cfg(unix)] + path.push("/"); + path.push("windows"); + path.push(".."); + path.push("."); + path.push("system32"); + let path_str = super::path_to_string(&path); + assert_eq!(path_str, "windows/system32"); + } +} diff --git a/src/zipcrypto.rs b/src/zipcrypto.rs new file mode 100644 index 0000000..32e8af8 --- /dev/null +++ b/src/zipcrypto.rs @@ -0,0 +1,162 @@ +//! Implementation of the ZipCrypto algorithm +//! +//! The following paper was used to implement the ZipCrypto algorithm: +//! [https://courses.cs.ut.ee/MTAT.07.022/2015_fall/uploads/Main/dmitri-report-f15-16.pdf](https://courses.cs.ut.ee/MTAT.07.022/2015_fall/uploads/Main/dmitri-report-f15-16.pdf) + +use std::num::Wrapping; + +/// A container to hold the current key state +struct ZipCryptoKeys { + key_0: Wrapping<u32>, + key_1: Wrapping<u32>, + key_2: Wrapping<u32>, +} + +impl ZipCryptoKeys { + fn new() -> ZipCryptoKeys { + ZipCryptoKeys { + key_0: Wrapping(0x12345678), + key_1: Wrapping(0x23456789), + key_2: Wrapping(0x34567890), + } + } + + fn update(&mut self, input: u8) { + self.key_0 = ZipCryptoKeys::crc32(self.key_0, input); + self.key_1 = + (self.key_1 + (self.key_0 & Wrapping(0xff))) * Wrapping(0x08088405) + Wrapping(1); + self.key_2 = ZipCryptoKeys::crc32(self.key_2, (self.key_1 >> 24).0 as u8); + } + + fn stream_byte(&mut self) -> u8 { + let temp: Wrapping<u16> = Wrapping(self.key_2.0 as u16) | Wrapping(3); + ((temp * (temp ^ Wrapping(1))) >> 8).0 as u8 + } + + fn decrypt_byte(&mut self, cipher_byte: u8) -> u8 { + let plain_byte: u8 = self.stream_byte() ^ cipher_byte; + self.update(plain_byte); + plain_byte + } + + #[allow(dead_code)] + fn encrypt_byte(&mut self, plain_byte: u8) -> u8 { + let cipher_byte: u8 = self.stream_byte() ^ plain_byte; + self.update(plain_byte); + cipher_byte + } + + fn crc32(crc: Wrapping<u32>, input: u8) -> Wrapping<u32> { + return (crc >> 8) ^ Wrapping(CRCTABLE[((crc & Wrapping(0xff)).0 as u8 ^ input) as usize]); + } +} + +/// A ZipCrypto reader with unverified password +pub struct ZipCryptoReader<R> { + file: R, + keys: ZipCryptoKeys, +} + +impl<R: std::io::Read> ZipCryptoReader<R> { + /// Note: The password is `&[u8]` and not `&str` because the + /// [zip specification](https://pkware.cachefly.net/webdocs/APPNOTE/APPNOTE-6.3.3.TXT) + /// does not specify password encoding (see function `update_keys` in the specification). + /// Therefore, if `&str` was used, the password would be UTF-8 and it + /// would be impossible to decrypt files that were encrypted with a + /// password byte sequence that is unrepresentable in UTF-8. + pub fn new(file: R, password: &[u8]) -> ZipCryptoReader<R> { + let mut result = ZipCryptoReader { + file: file, + keys: ZipCryptoKeys::new(), + }; + + // Key the cipher by updating the keys with the password. + for byte in password.iter() { + result.keys.update(*byte); + } + + result + } + + /// Read the ZipCrypto header bytes and validate the password. + pub fn validate( + mut self, + crc32_plaintext: u32, + ) -> Result<Option<ZipCryptoReaderValid<R>>, std::io::Error> { + // ZipCrypto prefixes a file with a 12 byte header + let mut header_buf = [0u8; 12]; + self.file.read_exact(&mut header_buf)?; + for byte in header_buf.iter_mut() { + *byte = self.keys.decrypt_byte(*byte); + } + + // PKZIP before 2.0 used 2 byte CRC check. + // PKZIP 2.0+ used 1 byte CRC check. It's more secure. + // We also use 1 byte CRC. + + if (crc32_plaintext >> 24) as u8 != header_buf[11] { + return Ok(None); // Wrong password + } + Ok(Some(ZipCryptoReaderValid { reader: self })) + } +} + +/// A ZipCrypto reader with verified password +pub struct ZipCryptoReaderValid<R> { + reader: ZipCryptoReader<R>, +} + +impl<R: std::io::Read> std::io::Read for ZipCryptoReaderValid<R> { + fn read(&mut self, mut buf: &mut [u8]) -> std::io::Result<usize> { + // Note: There might be potential for optimization. Inspiration can be found at: + // https://github.com/kornelski/7z/blob/master/CPP/7zip/Crypto/ZipCrypto.cpp + + let result = self.reader.file.read(&mut buf); + for byte in buf.iter_mut() { + *byte = self.reader.keys.decrypt_byte(*byte); + } + result + } +} + +impl<R: std::io::Read> ZipCryptoReaderValid<R> { + /// Consumes this decoder, returning the underlying reader. + pub fn into_inner(self) -> R { + self.reader.file + } +} + +static CRCTABLE: [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, +]; diff --git a/tests/data/comment_garbage.zip b/tests/data/comment_garbage.zip Binary files differnew file mode 100644 index 0000000..f6a289e --- /dev/null +++ b/tests/data/comment_garbage.zip diff --git a/tests/data/files_and_dirs.zip b/tests/data/files_and_dirs.zip Binary files differnew file mode 100644 index 0000000..c444078 --- /dev/null +++ b/tests/data/files_and_dirs.zip diff --git a/tests/data/invalid_offset.zip b/tests/data/invalid_offset.zip Binary files differnew file mode 100644 index 0000000..9ff2e07 --- /dev/null +++ b/tests/data/invalid_offset.zip diff --git a/tests/data/invalid_offset2.zip b/tests/data/invalid_offset2.zip Binary files differnew file mode 100644 index 0000000..944c611 --- /dev/null +++ b/tests/data/invalid_offset2.zip diff --git a/tests/data/mimetype.zip b/tests/data/mimetype.zip Binary files differnew file mode 100644 index 0000000..2d651cb --- /dev/null +++ b/tests/data/mimetype.zip diff --git a/tests/data/zip64_demo.zip b/tests/data/zip64_demo.zip Binary files differnew file mode 100644 index 0000000..f2ceee3 --- /dev/null +++ b/tests/data/zip64_demo.zip diff --git a/tests/end_to_end.rs b/tests/end_to_end.rs new file mode 100644 index 0000000..b826f54 --- /dev/null +++ b/tests/end_to_end.rs @@ -0,0 +1,108 @@ +use std::collections::HashSet; +use std::io::prelude::*; +use std::io::{Cursor, Seek}; +use std::iter::FromIterator; +use zip::write::FileOptions; +use zip::CompressionMethod; + +// This test asserts that after creating a zip file, then reading its contents back out, +// the extracted data will *always* be exactly the same as the original data. +#[test] +fn end_to_end() { + let file = &mut Cursor::new(Vec::new()); + + write_to_zip(file).expect("file written"); + + check_zip_contents(file, ENTRY_NAME); +} + +// This test asserts that after copying a `ZipFile` to a new `ZipWriter`, then reading its +// contents back out, the extracted data will *always* be exactly the same as the original data. +#[test] +fn copy() { + let src_file = &mut Cursor::new(Vec::new()); + write_to_zip(src_file).expect("file written"); + + let mut tgt_file = &mut Cursor::new(Vec::new()); + + { + let mut src_archive = zip::ZipArchive::new(src_file).unwrap(); + let mut zip = zip::ZipWriter::new(&mut tgt_file); + + { + let file = src_archive.by_name(ENTRY_NAME).expect("file found"); + zip.raw_copy_file(file).unwrap(); + } + + { + let file = src_archive.by_name(ENTRY_NAME).expect("file found"); + zip.raw_copy_file_rename(file, COPY_ENTRY_NAME).unwrap(); + } + } + + let mut tgt_archive = zip::ZipArchive::new(tgt_file).unwrap(); + + check_zip_file_contents(&mut tgt_archive, ENTRY_NAME); + check_zip_file_contents(&mut tgt_archive, COPY_ENTRY_NAME); +} + +fn write_to_zip(file: &mut Cursor<Vec<u8>>) -> zip::result::ZipResult<()> { + let mut zip = zip::ZipWriter::new(file); + + zip.add_directory("test/", Default::default())?; + + let options = FileOptions::default() + .compression_method(CompressionMethod::Stored) + .unix_permissions(0o755); + zip.start_file("test/☃.txt", options)?; + zip.write_all(b"Hello, World!\n")?; + + zip.start_file(ENTRY_NAME, Default::default())?; + zip.write_all(LOREM_IPSUM)?; + + zip.finish()?; + Ok(()) +} + +fn read_zip<R: Read + Seek>(zip_file: R) -> zip::result::ZipResult<zip::ZipArchive<R>> { + let archive = zip::ZipArchive::new(zip_file).unwrap(); + + let expected_file_names = ["test/", "test/☃.txt", ENTRY_NAME]; + let expected_file_names = HashSet::from_iter(expected_file_names.iter().map(|&v| v)); + let file_names = archive.file_names().collect::<HashSet<_>>(); + assert_eq!(file_names, expected_file_names); + + Ok(archive) +} + +fn read_zip_file<R: Read + Seek>( + archive: &mut zip::ZipArchive<R>, + name: &str, +) -> zip::result::ZipResult<String> { + let mut file = archive.by_name(name)?; + + let mut contents = String::new(); + file.read_to_string(&mut contents).unwrap(); + Ok(contents) +} + +fn check_zip_contents(zip_file: &mut Cursor<Vec<u8>>, name: &str) { + let mut archive = read_zip(zip_file).unwrap(); + check_zip_file_contents(&mut archive, name); +} + +fn check_zip_file_contents<R: Read + Seek>(archive: &mut zip::ZipArchive<R>, name: &str) { + let file_contents: String = read_zip_file(archive, name).unwrap(); + assert!(file_contents.as_bytes() == LOREM_IPSUM); +} + +const LOREM_IPSUM : &'static [u8] = b"Lorem ipsum dolor sit amet, consectetur adipiscing elit. In tellus elit, tristique vitae mattis egestas, ultricies vitae risus. Quisque sit amet quam ut urna aliquet +molestie. Proin blandit ornare dui, a tempor nisl accumsan in. Praesent a consequat felis. Morbi metus diam, auctor in auctor vel, feugiat id odio. Curabitur ex ex, +dictum quis auctor quis, suscipit id lorem. Aliquam vestibulum dolor nec enim vehicula, porta tristique augue tincidunt. Vivamus ut gravida est. Sed pellentesque, dolor +vitae tristique consectetur, neque lectus pulvinar dui, sed feugiat purus diam id lectus. Class aptent taciti sociosqu ad litora torquent per conubia nostra, per +inceptos himenaeos. Maecenas feugiat velit in ex ultrices scelerisque id id neque. +"; + +const ENTRY_NAME: &str = "test/lorem_ipsum.txt"; + +const COPY_ENTRY_NAME: &str = "test/lorem_ipsum_renamed.txt"; diff --git a/tests/invalid_date.rs b/tests/invalid_date.rs new file mode 100644 index 0000000..3f24e25 --- /dev/null +++ b/tests/invalid_date.rs @@ -0,0 +1,24 @@ +use std::io::Cursor; +use zip::read::ZipArchive; + +const BUF: &[u8] = &[ + 0x50, 0x4b, 0x03, 0x04, 0x0a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x00, 0x1c, 0x00, 0x69, 0x6e, + 0x76, 0x61, 0x6c, 0x69, 0x64, 0x5f, 0x74, 0x69, 0x6d, 0x65, 0x73, 0x74, 0x61, 0x6d, 0x70, 0x2f, + 0x55, 0x54, 0x09, 0x00, 0x03, 0xf4, 0x5c, 0x88, 0x5a, 0xf4, 0x5c, 0x88, 0x5a, 0x75, 0x78, 0x0b, + 0x00, 0x01, 0x04, 0xe8, 0x03, 0x00, 0x00, 0x04, 0x0a, 0x00, 0x00, 0x00, 0x50, 0x4b, 0x01, 0x02, + 0x1e, 0x03, 0x0a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, // time part: 0 seconds, 0 minutes, 0 hours + 0x00, 0x00, // date part: day 0 (invalid), month 0 (invalid), year 0 (1980) + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x00, 0x18, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x00, 0xed, 0x41, 0x00, 0x00, 0x00, 0x00, 0x69, 0x6e, + 0x76, 0x61, 0x6c, 0x69, 0x64, 0x5f, 0x74, 0x69, 0x6d, 0x65, 0x73, 0x74, 0x61, 0x6d, 0x70, 0x2f, + 0x55, 0x54, 0x05, 0x00, 0x03, 0xf4, 0x5c, 0x88, 0x5a, 0x75, 0x78, 0x0b, 0x00, 0x01, 0x04, 0xe8, + 0x03, 0x00, 0x00, 0x04, 0x0a, 0x00, 0x00, 0x00, 0x50, 0x4b, 0x05, 0x06, 0x00, 0x00, 0x00, 0x00, + 0x01, 0x00, 0x01, 0x00, 0x58, 0x00, 0x00, 0x00, 0x4c, 0x00, 0x00, 0x00, 0x00, 0x00, +]; + +#[test] +fn invalid_date() { + let _archive = ZipArchive::new(Cursor::new(BUF)).unwrap(); +} diff --git a/tests/zip64_large.rs b/tests/zip64_large.rs new file mode 100644 index 0000000..3d10a31 --- /dev/null +++ b/tests/zip64_large.rs @@ -0,0 +1,211 @@ +// The following is a hexdump of a zip64 file containing the following files: +// zero4400: 4400 MB of zeroes +// zero100: 100 MB of zeroes +// zero4400_2: 4400 MB of zeroes +// +// 00000000 50 4b 03 04 2d 00 00 00 00 00 1b 6e 51 4d 66 82 |PK..-......nQMf.| +// 00000010 13 da ff ff ff ff ff ff ff ff 08 00 30 00 7a 65 |............0.ze| +// 00000020 72 6f 34 34 30 30 55 54 09 00 03 a5 21 c7 5b db |ro4400UT....!.[.| +// 00000030 21 c7 5b 75 78 0b 00 01 04 e8 03 00 00 04 e8 03 |!.[ux...........| +// 00000040 00 00 01 00 10 00 00 00 00 13 01 00 00 00 00 00 |................| +// 00000050 00 13 01 00 00 00 00 00 00 00 00 00 00 00 00 00 |................| +// 00000060 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 |................| +// * +// 113000050 00 00 00 00 00 00 50 4b 03 04 0a 00 00 00 00 00 |......PK........| +// 113000060 2b 6e 51 4d 98 23 28 4b 00 00 40 06 00 00 40 06 |+nQM.#(K..@...@.| +// 113000070 07 00 1c 00 7a 65 72 6f 31 30 30 55 54 09 00 03 |....zero100UT...| +// 113000080 c2 21 c7 5b c2 21 c7 5b 75 78 0b 00 01 04 e8 03 |.!.[.!.[ux......| +// 113000090 00 00 04 e8 03 00 00 00 00 00 00 00 00 00 00 00 |................| +// 1130000a0 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 |................| +// * +// 119400090 00 00 00 00 00 00 00 50 4b 03 04 2d 00 00 00 00 |.......PK..-....| +// 1194000a0 00 3b 6e 51 4d 66 82 13 da ff ff ff ff ff ff ff |.;nQMf..........| +// 1194000b0 ff 0a 00 30 00 7a 65 72 6f 34 34 30 30 5f 32 55 |...0.zero4400_2U| +// 1194000c0 54 09 00 03 e2 21 c7 5b db 21 c7 5b 75 78 0b 00 |T....!.[.!.[ux..| +// 1194000d0 01 04 e8 03 00 00 04 e8 03 00 00 01 00 10 00 00 |................| +// 1194000e0 00 00 13 01 00 00 00 00 00 00 13 01 00 00 00 00 |................| +// 1194000f0 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 |................| +// * +// 22c4000e0 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 50 |...............P| +// 22c4000f0 4b 01 02 1e 03 2d 00 00 00 00 00 1b 6e 51 4d 66 |K....-......nQMf| +// 22c400100 82 13 da ff ff ff ff ff ff ff ff 08 00 2c 00 00 |.............,..| +// 22c400110 00 00 00 00 00 00 00 a4 81 00 00 00 00 7a 65 72 |.............zer| +// 22c400120 6f 34 34 30 30 55 54 05 00 03 a5 21 c7 5b 75 78 |o4400UT....!.[ux| +// 22c400130 0b 00 01 04 e8 03 00 00 04 e8 03 00 00 01 00 10 |................| +// 22c400140 00 00 00 00 13 01 00 00 00 00 00 00 13 01 00 00 |................| +// 22c400150 00 50 4b 01 02 1e 03 0a 00 00 00 00 00 2b 6e 51 |.PK..........+nQ| +// 22c400160 4d 98 23 28 4b 00 00 40 06 00 00 40 06 07 00 24 |M.#(K..@...@...$| +// 22c400170 00 00 00 00 00 00 00 00 00 a4 81 ff ff ff ff 7a |...............z| +// 22c400180 65 72 6f 31 30 30 55 54 05 00 03 c2 21 c7 5b 75 |ero100UT....!.[u| +// 22c400190 78 0b 00 01 04 e8 03 00 00 04 e8 03 00 00 01 00 |x...............| +// 22c4001a0 08 00 56 00 00 13 01 00 00 00 50 4b 01 02 1e 03 |..V.......PK....| +// 22c4001b0 2d 00 00 00 00 00 3b 6e 51 4d 66 82 13 da ff ff |-.....;nQMf.....| +// 22c4001c0 ff ff ff ff ff ff 0a 00 34 00 00 00 00 00 00 00 |........4.......| +// 22c4001d0 00 00 a4 81 ff ff ff ff 7a 65 72 6f 34 34 30 30 |........zero4400| +// 22c4001e0 5f 32 55 54 05 00 03 e2 21 c7 5b 75 78 0b 00 01 |_2UT....!.[ux...| +// 22c4001f0 04 e8 03 00 00 04 e8 03 00 00 01 00 18 00 00 00 |................| +// 22c400200 00 13 01 00 00 00 00 00 00 13 01 00 00 00 97 00 |................| +// 22c400210 40 19 01 00 00 00 50 4b 06 06 2c 00 00 00 00 00 |@.....PK..,.....| +// 22c400220 00 00 1e 03 2d 00 00 00 00 00 00 00 00 00 03 00 |....-...........| +// 22c400230 00 00 00 00 00 00 03 00 00 00 00 00 00 00 27 01 |..............'.| +// 22c400240 00 00 00 00 00 00 ef 00 40 2c 02 00 00 00 50 4b |........@,....PK| +// 22c400250 06 07 00 00 00 00 16 02 40 2c 02 00 00 00 01 00 |........@,......| +// 22c400260 00 00 50 4b 05 06 00 00 00 00 03 00 03 00 27 01 |..PK..........'.| +// 22c400270 00 00 ff ff ff ff 00 00 |........| +// 22c400278 +use std::io::{self, Read, Seek, SeekFrom}; + +const BLOCK1_LENGTH: u64 = 0x60; +const BLOCK1: [u8; BLOCK1_LENGTH as usize] = [ + 0x50, 0x4b, 0x03, 0x04, 0x2d, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1b, 0x6e, 0x51, 0x4d, 0x66, 0x82, + 0x13, 0xda, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x08, 0x00, 0x30, 0x00, 0x7a, 0x65, + 0x72, 0x6f, 0x34, 0x34, 0x30, 0x30, 0x55, 0x54, 0x09, 0x00, 0x03, 0xa5, 0x21, 0xc7, 0x5b, 0xdb, + 0x21, 0xc7, 0x5b, 0x75, 0x78, 0x0b, 0x00, 0x01, 0x04, 0xe8, 0x03, 0x00, 0x00, 0x04, 0xe8, 0x03, + 0x00, 0x00, 0x01, 0x00, 0x10, 0x00, 0x00, 0x00, 0x00, 0x13, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x13, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +]; + +const BLOCK2_LENGTH: u64 = 0x50; +const BLOCK2: [u8; BLOCK2_LENGTH as usize] = [ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x50, 0x4b, 0x03, 0x04, 0x0a, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x2b, 0x6e, 0x51, 0x4d, 0x98, 0x23, 0x28, 0x4b, 0x00, 0x00, 0x40, 0x06, 0x00, 0x00, 0x40, 0x06, + 0x07, 0x00, 0x1c, 0x00, 0x7a, 0x65, 0x72, 0x6f, 0x31, 0x30, 0x30, 0x55, 0x54, 0x09, 0x00, 0x03, + 0xc2, 0x21, 0xc7, 0x5b, 0xc2, 0x21, 0xc7, 0x5b, 0x75, 0x78, 0x0b, 0x00, 0x01, 0x04, 0xe8, 0x03, + 0x00, 0x00, 0x04, 0xe8, 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +]; + +const BLOCK3_LENGTH: u64 = 0x60; +const BLOCK3: [u8; BLOCK3_LENGTH as usize] = [ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x50, 0x4b, 0x03, 0x04, 0x2d, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x3b, 0x6e, 0x51, 0x4d, 0x66, 0x82, 0x13, 0xda, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0x0a, 0x00, 0x30, 0x00, 0x7a, 0x65, 0x72, 0x6f, 0x34, 0x34, 0x30, 0x30, 0x5f, 0x32, 0x55, + 0x54, 0x09, 0x00, 0x03, 0xe2, 0x21, 0xc7, 0x5b, 0xdb, 0x21, 0xc7, 0x5b, 0x75, 0x78, 0x0b, 0x00, + 0x01, 0x04, 0xe8, 0x03, 0x00, 0x00, 0x04, 0xe8, 0x03, 0x00, 0x00, 0x01, 0x00, 0x10, 0x00, 0x00, + 0x00, 0x00, 0x13, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x13, 0x01, 0x00, 0x00, 0x00, 0x00, +]; + +const BLOCK4_LENGTH: u64 = 0x198; +const BLOCK4: [u8; BLOCK4_LENGTH as usize] = [ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x50, + 0x4b, 0x01, 0x02, 0x1e, 0x03, 0x2d, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1b, 0x6e, 0x51, 0x4d, 0x66, + 0x82, 0x13, 0xda, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x08, 0x00, 0x2c, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xa4, 0x81, 0x00, 0x00, 0x00, 0x00, 0x7a, 0x65, 0x72, + 0x6f, 0x34, 0x34, 0x30, 0x30, 0x55, 0x54, 0x05, 0x00, 0x03, 0xa5, 0x21, 0xc7, 0x5b, 0x75, 0x78, + 0x0b, 0x00, 0x01, 0x04, 0xe8, 0x03, 0x00, 0x00, 0x04, 0xe8, 0x03, 0x00, 0x00, 0x01, 0x00, 0x10, + 0x00, 0x00, 0x00, 0x00, 0x13, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x13, 0x01, 0x00, 0x00, + 0x00, 0x50, 0x4b, 0x01, 0x02, 0x1e, 0x03, 0x0a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x2b, 0x6e, 0x51, + 0x4d, 0x98, 0x23, 0x28, 0x4b, 0x00, 0x00, 0x40, 0x06, 0x00, 0x00, 0x40, 0x06, 0x07, 0x00, 0x24, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xa4, 0x81, 0xff, 0xff, 0xff, 0xff, 0x7a, + 0x65, 0x72, 0x6f, 0x31, 0x30, 0x30, 0x55, 0x54, 0x05, 0x00, 0x03, 0xc2, 0x21, 0xc7, 0x5b, 0x75, + 0x78, 0x0b, 0x00, 0x01, 0x04, 0xe8, 0x03, 0x00, 0x00, 0x04, 0xe8, 0x03, 0x00, 0x00, 0x01, 0x00, + 0x08, 0x00, 0x56, 0x00, 0x00, 0x13, 0x01, 0x00, 0x00, 0x00, 0x50, 0x4b, 0x01, 0x02, 0x1e, 0x03, + 0x2d, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3b, 0x6e, 0x51, 0x4d, 0x66, 0x82, 0x13, 0xda, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x0a, 0x00, 0x34, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0xa4, 0x81, 0xff, 0xff, 0xff, 0xff, 0x7a, 0x65, 0x72, 0x6f, 0x34, 0x34, 0x30, 0x30, + 0x5f, 0x32, 0x55, 0x54, 0x05, 0x00, 0x03, 0xe2, 0x21, 0xc7, 0x5b, 0x75, 0x78, 0x0b, 0x00, 0x01, + 0x04, 0xe8, 0x03, 0x00, 0x00, 0x04, 0xe8, 0x03, 0x00, 0x00, 0x01, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x13, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x13, 0x01, 0x00, 0x00, 0x00, 0x97, 0x00, + 0x40, 0x19, 0x01, 0x00, 0x00, 0x00, 0x50, 0x4b, 0x06, 0x06, 0x2c, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x1e, 0x03, 0x2d, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x27, 0x01, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xef, 0x00, 0x40, 0x2c, 0x02, 0x00, 0x00, 0x00, 0x50, 0x4b, + 0x06, 0x07, 0x00, 0x00, 0x00, 0x00, 0x16, 0x02, 0x40, 0x2c, 0x02, 0x00, 0x00, 0x00, 0x01, 0x00, + 0x00, 0x00, 0x50, 0x4b, 0x05, 0x06, 0x00, 0x00, 0x00, 0x00, 0x03, 0x00, 0x03, 0x00, 0x27, 0x01, + 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, +]; + +const BLOCK1_START: u64 = 0x000000000; +const BLOCK2_START: u64 = 0x113000050; +const BLOCK3_START: u64 = 0x119400090; +const BLOCK4_START: u64 = 0x22c4000e0; + +const BLOCK1_END: u64 = BLOCK1_START + BLOCK1_LENGTH - 1; +const BLOCK2_END: u64 = BLOCK2_START + BLOCK2_LENGTH - 1; +const BLOCK3_END: u64 = BLOCK3_START + BLOCK3_LENGTH - 1; +const BLOCK4_END: u64 = BLOCK4_START + BLOCK4_LENGTH - 1; + +const TOTAL_LENGTH: u64 = BLOCK4_START + BLOCK4_LENGTH; + +struct Zip64File { + pointer: u64, +} + +impl Zip64File { + fn new() -> Self { + Zip64File { pointer: 0 } + } +} + +impl Seek for Zip64File { + fn seek(&mut self, pos: SeekFrom) -> io::Result<u64> { + match pos { + SeekFrom::Start(offset) => { + self.pointer = offset; + } + SeekFrom::End(offset) => { + if offset > 0 || offset < -(TOTAL_LENGTH as i64) { + return Err(io::Error::new(io::ErrorKind::Other, "Invalid seek offset")); + } + self.pointer = (TOTAL_LENGTH as i64 + offset) as u64; + } + SeekFrom::Current(offset) => { + let seekpos = self.pointer as i64 + offset; + if seekpos < 0 || seekpos as u64 > TOTAL_LENGTH { + return Err(io::Error::new(io::ErrorKind::Other, "Invalid seek offset")); + } + self.pointer = seekpos as u64; + } + } + Ok(self.pointer) + } +} + +impl Read for Zip64File { + fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> { + if self.pointer >= TOTAL_LENGTH { + return Ok(0); + } + match self.pointer { + BLOCK1_START..=BLOCK1_END => { + buf[0] = BLOCK1[(self.pointer - BLOCK1_START) as usize]; + } + BLOCK2_START..=BLOCK2_END => { + buf[0] = BLOCK2[(self.pointer - BLOCK2_START) as usize]; + } + BLOCK3_START..=BLOCK3_END => { + buf[0] = BLOCK3[(self.pointer - BLOCK3_START) as usize]; + } + BLOCK4_START..=BLOCK4_END => { + buf[0] = BLOCK4[(self.pointer - BLOCK4_START) as usize]; + } + _ => { + buf[0] = 0; + } + } + self.pointer += 1; + Ok(1) + } +} + +#[test] +fn zip64_large() { + let zipfile = Zip64File::new(); + let mut archive = zip::ZipArchive::new(zipfile).unwrap(); + let mut buf = [0u8; 32]; + + for i in 0..archive.len() { + let mut file = archive.by_index(i).unwrap(); + let outpath = file.enclosed_name().unwrap(); + println!( + "Entry {} has name \"{}\" ({} bytes)", + i, + outpath.display(), + file.size() + ); + + match file.read_exact(&mut buf) { + Ok(()) => println!("The first {} bytes are: {:?}", buf.len(), buf), + Err(e) => println!("Could not read the file: {:?}", e), + }; + } +} diff --git a/tests/zip_comment_garbage.rs b/tests/zip_comment_garbage.rs new file mode 100644 index 0000000..ef4d975 --- /dev/null +++ b/tests/zip_comment_garbage.rs @@ -0,0 +1,30 @@ +// Some zip files can contain garbage after the comment. For example, python zipfile generates +// it when opening a zip in 'a' mode: +// +// >>> from zipfile import ZipFile +// >>> with ZipFile('comment_garbage.zip', 'a') as z: +// ... z.comment = b'long comment bla bla bla' +// ... +// >>> with ZipFile('comment_garbage.zip', 'a') as z: +// ... z.comment = b'short.' +// ... +// >>> +// +// Hexdump: +// +// 00000000 50 4b 05 06 00 00 00 00 00 00 00 00 00 00 00 00 |PK..............| +// 00000010 00 00 00 00 06 00 73 68 6f 72 74 2e 6f 6d 6d 65 |......short.omme| +// 00000020 6e 74 20 62 6c 61 20 62 6c 61 20 62 6c 61 |nt bla bla bla| +// 0000002e + +use std::io; +use zip::ZipArchive; + +#[test] +fn correctly_handle_zip_with_garbage_after_comment() { + let mut v = Vec::new(); + v.extend_from_slice(include_bytes!("../tests/data/comment_garbage.zip")); + let archive = ZipArchive::new(io::Cursor::new(v)).expect("couldn't open test zip file"); + + assert_eq!(archive.comment(), "short.".as_bytes()); +} diff --git a/tests/zip_crypto.rs b/tests/zip_crypto.rs new file mode 100644 index 0000000..cae6b1f --- /dev/null +++ b/tests/zip_crypto.rs @@ -0,0 +1,85 @@ +// The following is a hexdump of a zip file containing the following +// ZipCrypto encrypted file: +// test.txt: 35 bytes, contents: `abcdefghijklmnopqrstuvwxyz123456789`, password: `test` +// +// 00000000 50 4b 03 04 14 00 01 00 00 00 54 bd b5 50 2f 20 |PK........T..P/ | +// 00000010 79 55 2f 00 00 00 23 00 00 00 08 00 00 00 74 65 |yU/...#.......te| +// 00000020 73 74 2e 74 78 74 ca 2d 1d 27 19 19 63 43 77 9a |st.txt.-.'..cCw.| +// 00000030 71 76 c9 ec d1 6f d9 f5 22 67 b3 8f 52 b5 41 bc |qv...o.."g..R.A.| +// 00000040 5c 36 f2 1d 84 c3 c0 28 3b fd e1 70 c2 cc 0c 11 |\6.....(;..p....| +// 00000050 0c c5 95 2f a4 50 4b 01 02 3f 00 14 00 01 00 00 |.../.PK..?......| +// 00000060 00 54 bd b5 50 2f 20 79 55 2f 00 00 00 23 00 00 |.T..P/ yU/...#..| +// 00000070 00 08 00 24 00 00 00 00 00 00 00 20 00 00 00 00 |...$....... ....| +// 00000080 00 00 00 74 65 73 74 2e 74 78 74 0a 00 20 00 00 |...test.txt.. ..| +// 00000090 00 00 00 01 00 18 00 31 b2 3b bf b8 2f d6 01 31 |.......1.;../..1| +// 000000a0 b2 3b bf b8 2f d6 01 a8 c4 45 bd b8 2f d6 01 50 |.;../....E../..P| +// 000000b0 4b 05 06 00 00 00 00 01 00 01 00 5a 00 00 00 55 |K..........Z...U| +// 000000c0 00 00 00 00 00 |.....| +// 000000c5 + +use std::io::Cursor; +use std::io::Read; + +#[test] +fn encrypted_file() { + let zip_file_bytes = &mut Cursor::new(vec![ + 0x50, 0x4b, 0x03, 0x04, 0x14, 0x00, 0x01, 0x00, 0x00, 0x00, 0x54, 0xbd, 0xb5, 0x50, 0x2f, + 0x20, 0x79, 0x55, 0x2f, 0x00, 0x00, 0x00, 0x23, 0x00, 0x00, 0x00, 0x08, 0x00, 0x00, 0x00, + 0x74, 0x65, 0x73, 0x74, 0x2e, 0x74, 0x78, 0x74, 0xca, 0x2d, 0x1d, 0x27, 0x19, 0x19, 0x63, + 0x43, 0x77, 0x9a, 0x71, 0x76, 0xc9, 0xec, 0xd1, 0x6f, 0xd9, 0xf5, 0x22, 0x67, 0xb3, 0x8f, + 0x52, 0xb5, 0x41, 0xbc, 0x5c, 0x36, 0xf2, 0x1d, 0x84, 0xc3, 0xc0, 0x28, 0x3b, 0xfd, 0xe1, + 0x70, 0xc2, 0xcc, 0x0c, 0x11, 0x0c, 0xc5, 0x95, 0x2f, 0xa4, 0x50, 0x4b, 0x01, 0x02, 0x3f, + 0x00, 0x14, 0x00, 0x01, 0x00, 0x00, 0x00, 0x54, 0xbd, 0xb5, 0x50, 0x2f, 0x20, 0x79, 0x55, + 0x2f, 0x00, 0x00, 0x00, 0x23, 0x00, 0x00, 0x00, 0x08, 0x00, 0x24, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x20, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x74, 0x65, 0x73, 0x74, + 0x2e, 0x74, 0x78, 0x74, 0x0a, 0x00, 0x20, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x18, + 0x00, 0x31, 0xb2, 0x3b, 0xbf, 0xb8, 0x2f, 0xd6, 0x01, 0x31, 0xb2, 0x3b, 0xbf, 0xb8, 0x2f, + 0xd6, 0x01, 0xa8, 0xc4, 0x45, 0xbd, 0xb8, 0x2f, 0xd6, 0x01, 0x50, 0x4b, 0x05, 0x06, 0x00, + 0x00, 0x00, 0x00, 0x01, 0x00, 0x01, 0x00, 0x5a, 0x00, 0x00, 0x00, 0x55, 0x00, 0x00, 0x00, + 0x00, 0x00, + ]); + + let mut archive = zip::ZipArchive::new(zip_file_bytes).unwrap(); + + assert_eq!(archive.len(), 1); //Only one file inside archive: `test.txt` + + { + // No password + let file = archive.by_index(0); + match file { + Err(zip::result::ZipError::UnsupportedArchive("Password required to decrypt file")) => { + () + } + Err(_) => panic!( + "Expected PasswordRequired error when opening encrypted file without password" + ), + Ok(_) => panic!("Error: Successfully opened encrypted file without password?!"), + } + } + + { + // Wrong password + let file = archive.by_index_decrypt(0, b"wrong password"); + match file { + Ok(Err(zip::result::InvalidPassword)) => (), + Err(_) => panic!( + "Expected InvalidPassword error when opening encrypted file with wrong password" + ), + Ok(Ok(_)) => panic!("Error: Successfully opened encrypted file with wrong password?!"), + } + } + + { + // Correct password, read contents + let mut file = archive + .by_index_decrypt(0, "test".as_bytes()) + .unwrap() + .unwrap(); + let file_name = file.enclosed_name().unwrap(); + assert_eq!(file_name, std::path::PathBuf::from("test.txt")); + + let mut data = Vec::new(); + file.read_to_end(&mut data).unwrap(); + assert_eq!(data, "abcdefghijklmnopqrstuvwxyz123456789".as_bytes()); + } +} |