mailmap support

Cargo.toml

@@ -142,6 +142,7 @@ members = [
     "git-worktree",
     "git-revision",
     "git-packetline",
+    "git-mailmap",
     "git-submodule",
     "git-transport",
     "git-protocol",

Makefile

@@ -90,6 +90,8 @@ check: ## Build all code in suitable configurations
                   && cargo check --features verbose-object-parsing-errors
 	cd git-index && cargo check --features serde1
 	cd git-revision && cargo check --features serde1
+	cd git-attributes && cargo check --features serde1
+	cd git-mailmap && cargo check --features serde1
 	cd git-worktree && cargo check --features serde1
 	cd git-actor && cargo check --features serde1
 	cd git-pack && cargo check --features serde1 \

README.md

@@ -108,6 +108,7 @@ Follow linked crate name for detailed status. Please note that all crates follow
   * [git-attributes](https://github.com/Byron/gitoxide/blob/main/crate-status.md#git-attributes)
   * [git-quote](https://github.com/Byron/gitoxide/blob/main/crate-status.md#git-quote)
 * **idea**
+  * [git-mailmap](https://github.com/Byron/gitoxide/blob/main/crate-status.md#git-mailmap)
   * [git-pathspec](https://github.com/Byron/gitoxide/blob/main/crate-status.md#git-pathspec)
   * [git-subomdule](https://github.com/Byron/gitoxide/blob/main/crate-status.md#git-submodule)
   * [git-tui](https://github.com/Byron/gitoxide/blob/main/crate-status.md#git-tui)

crate-status.md

@@ -220,6 +220,11 @@ Check out the [performance discussion][git-traverse-performance] as well.
 * **ansi-c**
   * [x] quote
   * [ ] unquote
+  * 
+### git-mailmap
+
+* [ ] parsing
+* [ ] lookup and mapping of author names
 
 ### git-pathspec
 

git-actor/src/lib.rs

@@ -11,13 +11,14 @@ use bstr::{BStr, BString};
 
 ///
 pub mod signature;
+mod time;
 
 const SPACE: &[u8; 1] = b" ";
 
 /// A mutable signature is created by an actor at a certain time.
 ///
 /// Note that this is not a cryptographical signature.
-#[derive(PartialEq, Eq, Debug, Hash, Ord, PartialOrd, Clone)]
+#[derive(Default, PartialEq, Eq, Debug, Hash, Ord, PartialOrd, Clone)]
 #[cfg_attr(feature = "serde1", derive(serde::Serialize, serde::Deserialize))]
 pub struct Signature {
     /// The actors name.
@@ -63,5 +64,3 @@ pub struct Time {
     /// the sign of `offset`, used to encode `-0000` which would otherwise loose sign information.
     pub sign: Sign,
 }
-
-mod time;

git-actor/src/signature/mod.rs

@@ -22,26 +22,12 @@ mod _ref {
 }
 
 mod convert {
-    use crate::{Sign, Signature, SignatureRef, Time};
-
-    impl Default for Signature {
-        fn default() -> Self {
-            Signature::empty()
-        }
-    }
+    use crate::{Signature, SignatureRef};
 
     impl Signature {
         /// An empty signature, similar to 'null'.
         pub fn empty() -> Self {
-            Signature {
-                name: Default::default(),
-                email: Default::default(),
-                time: Time {
-                    seconds_since_unix_epoch: 0,
-                    offset_in_seconds: 0,
-                    sign: Sign::Plus,
-                },
-            }
+            Signature::default()
         }
 
         /// Borrow this instance as immutable

git-actor/src/time.rs

@@ -12,6 +12,16 @@ impl From<i32> for Sign {
     }
 }
 
+impl Default for Time {
+    fn default() -> Self {
+        Time {
+            seconds_since_unix_epoch: 0,
+            offset_in_seconds: 0,
+            sign: Sign::Plus,
+        }
+    }
+}
+
 impl Time {
     /// Serialize this instance to `out` in a format suitable for use in header fields of serialized git commits or tags.
     pub fn write_to(&self, mut out: impl io::Write) -> io::Result<()> {

git-attributes/src/ignore.rs

@@ -2,6 +2,7 @@ pub mod pattern {
     use bitflags::bitflags;
 
     bitflags! {
+        #[cfg_attr(feature = "serde1", derive(serde::Serialize, serde::Deserialize))]
         pub struct Mode: u32 {
             /// The pattern does not contain a sub-directory and - it doesn't contain slashes after removing the trailing one.
             const NO_SUB_DIR = 1 << 0;

git-attributes/src/lib.rs

@@ -1,4 +1,5 @@
-#![forbid(unsafe_code, rust_2018_idioms)]
+#![forbid(unsafe_code)]
+#![deny(rust_2018_idioms)]
 
 use bstr::BStr;
 
@@ -11,6 +12,7 @@ pub enum State<'a> {
     Unset,
     /// The attribute is set to the given value, which followed the `=` sign.
     /// Note that values can be empty.
+    #[cfg_attr(feature = "serde1", serde(borrow))]
     Value(&'a BStr),
     /// The attribute isn't mentioned with a given path or is explicitly set to `Unspecified` using the `!` sign.
     Unspecified,

git-attributes/src/parse/ignore.rs

@@ -49,6 +49,9 @@ pub(crate) fn parse_line(mut line: &[u8]) -> Option<(BString, ignore::pattern::M
             line = &line[1..];
         }
     }
+    if line.iter().all(|b| b.is_ascii_whitespace()) {
+        return None;
+    }
     let mut line = truncate_non_escaped_trailing_spaces(line);
     if line.last() == Some(&b'/') {
         mode |= ignore::pattern::Mode::MUST_BE_DIR;

git-attributes/tests/parse/attribute.rs

@@ -1,7 +1,7 @@
 use bstr::{BStr, ByteSlice};
 use git_attributes::ignore::pattern::Mode;
 use git_attributes::{parse, State};
-use git_testtools::fixture_path;
+use git_testtools::fixture_bytes;
 
 #[test]
 fn byte_order_marks_are_no_patterns() {
@@ -14,9 +14,9 @@ fn byte_order_marks_are_no_patterns() {
 
 #[test]
 fn line_numbers_are_counted_correctly() {
-    let ignore = std::fs::read(fixture_path("attributes/various.txt")).unwrap();
+    let input = fixture_bytes("attributes/various.txt");
     assert_eq!(
-        try_lines(&String::from_utf8(ignore).unwrap()).unwrap(),
+        try_lines(&String::from_utf8(input).unwrap()).unwrap(),
         vec![
             (pattern(r"*.[oa]", Mode::NO_SUB_DIR), vec![set("c")], 2),
             (
@@ -44,13 +44,14 @@ fn line_endings_can_be_windows_or_unix() {
 }
 
 #[test]
-fn comment_lines_are_ignored() {
+fn comment_lines_are_ignored_as_well_as_empty_ones() {
     assert!(git_attributes::parse(b"# hello world").next().is_none());
     assert!(git_attributes::parse(b"# \"hello world\"").next().is_none());
     assert!(
         git_attributes::parse(b" \t\r# \"hello world\"").next().is_none(),
         "also behind leading whitespace"
     );
+    assert!(git_attributes::parse(b"\n\r\n\t\t   \n").next().is_none());
 }
 
 #[test]
@@ -266,10 +267,7 @@ fn try_line(input: &str) -> Result<ExpandedAttribute, parse::Error> {
 }
 
 fn line(input: &str) -> ExpandedAttribute {
-    let mut lines = git_attributes::parse(input.as_bytes());
-    let res = expand(lines.next().expect("single line")).unwrap();
-    assert!(lines.next().is_none(), "expected only one line");
-    res
+    try_line(input).unwrap()
 }
 
 fn try_lines(input: &str) -> Result<Vec<ExpandedAttribute>, parse::Error> {

git-attributes/tests/parse/ignore.rs

@@ -1,5 +1,5 @@
 use git_attributes::ignore::pattern::Mode;
-use git_testtools::fixture_path;
+use git_testtools::fixture_bytes;
 
 #[test]
 fn byte_order_marks_are_no_patterns() {
@@ -11,8 +11,8 @@ fn byte_order_marks_are_no_patterns() {
 
 #[test]
 fn line_numbers_are_counted_correctly() {
-    let ignore = std::fs::read(fixture_path("ignore/various.txt")).unwrap();
-    let actual: Vec<_> = git_attributes::parse::ignore(&ignore).collect();
+    let input = fixture_bytes("ignore/various.txt");
+    let actual: Vec<_> = git_attributes::parse::ignore(&input).collect();
     assert_eq!(
         actual,
         vec![
@@ -66,8 +66,9 @@ fn mark_ends_with_pattern_specifically() {
 }
 
 #[test]
-fn comments_are_ignored() {
+fn comments_are_ignored_as_well_as_empty_ones() {
     assert!(git_attributes::parse::ignore(b"# hello world").next().is_none());
+    assert!(git_attributes::parse::ignore(b"\n\r\n\t\t   \n").next().is_none());
 }
 
 #[test]

git-features/Cargo.toml

@@ -125,12 +125,17 @@ time = { version = "0.3.2", optional = true, default-features = false, features
 
 # path
 ## make bstr utilities available in the `path` modules, which itself is gated by the `path` feature.
-bstr = { version = "0.2.17", optional = true }
+bstr = { version = "0.2.17", optional = true, default-features = false, features = ["std"] }
 
 document-features = { version = "0.2.0", optional = true }
 
+[target.'cfg(unix)'.dependencies]
+## for fs::open_options_no_follow()
+# TODO: ideally we conditionally import it only if a plumbing crate wants to use the underlying feature. Wanted to avoid to add to feature-toggle complexity.
+libc = { version = "0.2.119" }
+
 [dev-dependencies]
-bstr = "0.2.15"
+bstr = { version = "0.2.15", default-features = false }
 
 [package.metadata.docs.rs]
 features = ["document-features"]

git-features/src/fs.rs

@@ -53,3 +53,19 @@ pub mod walkdir {
 
 #[cfg(any(feature = "walkdir", feature = "jwalk"))]
 pub use self::walkdir::{walkdir_new, walkdir_sorted_new, WalkDir};
+
+/// Prepare open options which won't follow symlinks when the file is opened.
+///
+/// Note: only effective on unix currently.
+pub fn open_options_no_follow() -> std::fs::OpenOptions {
+    let mut options = std::fs::OpenOptions::new();
+    #[cfg(unix)]
+    {
+        /// Make sure that it's impossible to follow through to the target of symlinks.
+        /// Note that this will still follow symlinks in the path, which is what we assume
+        /// has been checked separately.
+        use std::os::unix::fs::OpenOptionsExt;
+        options.custom_flags(libc::O_NOFOLLOW);
+    }
+    options
+}

git-mailmap/CHANGELOG.md

@@ -0,0 +1,29 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## 0.0.0 (2022-03-26)
+
+An empty crate without any content to reserve the name for the gitoxide project.
+
+### Commit Statistics
+
+<csr-read-only-do-not-edit/>
+
+ - 1 commit contributed to the release.
+ - 0 commits where understood as [conventional](https://www.conventionalcommits.org).
+ - 1 unique issue was worked on: [#366](https://github.com/Byron/gitoxide/issues/366)
+
+### Commit Details
+
+<csr-read-only-do-not-edit/>
+
+<details><summary>view details</summary>
+
+ * **[#366](https://github.com/Byron/gitoxide/issues/366)**
+    - empty git-mailmap crate ([`a30a5da`](https://github.com/Byron/gitoxide/commit/a30a5da60d67a4e52ba69727318edb9832b7cae2))
+</details>
+

git-mailmap/Cargo.toml

@@ -0,0 +1,26 @@
+[package]
+name = "git-mailmap"
+version = "0.0.0"
+repository = "https://github.com/Byron/gitoxide"
+license = "MIT/Apache-2.0"
+description = "A WIP crate of the gitoxide project for parsing mailmap files"
+authors = ["Sebastian Thiel <[email protected]>"]
+edition = "2018"
+
+[lib]
+doctest = false
+
+[features]
+## Data structures implement `serde::Serialize` and `serde::Deserialize`.
+serde1 = ["serde", "bstr/serde1", "git-actor/serde1"]
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+git-actor = { version = "^0.8.1", path = "../git-actor" }
+bstr = { version = "0.2.13", default-features = false, features = ["std", "unicode"]}
+quick-error = "2.0.0"
+serde = { version = "1.0.114", optional = true, default-features = false, features = ["derive"]}
+
+[dev-dependencies]
+git-testtools = { path = "../tests/tools"}