commit 7be3084244cf8ad5c924f07a25a87afd4fc04e47
author Dylan DPC <99973273+Dylan-DPC@users.noreply.github.com> Fri Apr 08 11:48:22 2022 +0200
committer GitHub <noreply@github.com> Fri Apr 08 11:48:22 2022 +0200
tree be39d79c329ba0e976433f2a93a9ffd80bb25866
parent d5232c6b93db1d5a95b14838cc2094a000e67b3e
parent 05a467e4ce0000dd5372cbca74c18c001382341a

Rollup merge of #95634 - dtolnay:mailmap, r=Mark-Simulacrum

Mailmap update

I noticed there are a lot of contributors who appear multiple times in https://thanks.rust-lang.org/rust/all-time/, which makes their "rank" on that page inaccurate. For example Nick Cameron currently appears at rank 21 with 2010 contributions and at rank 27 with 1287 contributions, because some of those are from nrc⁠```@ncameron.org``` and some from ncameron⁠```@mozilla.com.``` In reality Nick's rank would be 11 if counted correctly, which is a large difference.

Solving this in a totally automated way is tricky because it involves figuring out whether Nick is 1 person with multiple emails, or is 2 people sharing the same name.

This PR addresses a subset of the cases: only where a person has committed under multiple names using the same email. This is still not something that can be totally automated (e.g. by modifying https://github.com/rust-lang/thanks to dedup by email instead of name+email) because:

- Some emails are not necessarily unique to one contributor, such as `ubuntu@localhost`.

- It involves some judgement and mindfulness in picking the "canonical name" among the names used with a particular email. This is the name that will appear on thanks.rust-lang.org. Humans change their names sometimes and can be sensitive or picky about the use of names that are no longer preferred.

For the purpose of this PR, I've tried to stick to the following heuristics which should be unobjectionable:

- If one of the names is currently set as the display name on the contributor's GitHub profile, prefer that name.

- If one of the names is used exclusively over the others in chronologically newer pull requests, prefer the newest name.

- If one of the names has whitespace and the other doesn't (i.e. is username-like), such as `Foo Bar` vs `FooBar` or `foobar` or `foo-bar123`, but otherwise closely resemble one another, then prefer the human-like name.

- If none of the above suffice in determining a canonical name and the contributor has some other name set on their GitHub profile, use the name from the GitHub profile.

- If no name on their GitHub profile but the profile links to their personal website which unambiguously identifies their preferred name, then use that name.

I'm also thinking about how to handle cases like Nick's, but that will be a project for a different PR. Basically I'd like to be able to find cases of the same person making commits that differ in name *and* email by looking at all the commits present in pull requests opened by the same GitHub user.

<details>
<summary>script</summary>

```toml
[dependencies]
anyhow = "1.0"
git2 = "0.14"
mailmap = "0.1"
```
```rust
use anyhow::{bail, Context, Result};
use git2::{Commit, Oid, Repository};
use mailmap::{Author, Mailmap};
use std::collections::{BTreeMap as Map, BTreeSet as Set};
use std::fmt::{self, Debug};
use std::fs;
use std::path::Path;

const REPO: &str = "/git/rust";

fn main() -> Result<()> {
    let repo = Repository::open(REPO)?;
    let head_oid = repo
        .head()?
        .target()
        .context("expected head to be a direct reference")?;
    let head = repo.find_commit(head_oid)?;

    let mailmap_path = Path::new(REPO).join(".mailmap");
    let mailmap_contents = fs::read_to_string(mailmap_path)?;
    let mailmap = match Mailmap::from_string(mailmap_contents) {
        Ok(mailmap) => mailmap,
        Err(box_error) => bail!("{}", box_error),
    };

    let mut history = Set::new();
    let mut merges = Vec::new();
    let mut authors = Set::new();
    let mut emails = Map::new();
    let mut all_authors = Set::new();
    traverse_left(head, &mut history, &mut merges, &mut authors, &mailmap)?;
    while let Some((commit, i)) = merges.pop() {
        let right = commit.parents().nth(i).unwrap();
        authors.clear();
        traverse_left(right, &mut history, &mut merges, &mut authors, &mailmap)?;
        for author in &authors {
            all_authors.insert(author.clone());
            if !author.email.is_empty() {
                emails
                    .entry(author.email.clone())
                    .or_insert_with(Map::new)
                    .entry(author.name.clone())
                    .or_insert_with(Set::new);
            }
        }
        if let Some(summary) = commit.summary() {
            if let Some(pr) = parse_summary(summary)? {
                for author in &authors {
                    if !author.email.is_empty() {
                        emails
                            .get_mut(&author.email)
                            .unwrap()
                            .get_mut(&author.name)
                            .unwrap()
                            .insert(pr);
                    }
                }
            }
        }
    }

    for (email, names) in emails {
        if names.len() > 1 {
            println!("<{}>", email);
            for (name, prs) in names {
                let prs = DebugSet(prs.iter().rev());
                println!("    {} {:?}", name, prs);
            }
        }
    }

    eprintln!("{} commits", history.len());
    eprintln!("{} authors", all_authors.len());
    Ok(())
}

fn traverse_left<'repo>(
    mut commit: Commit<'repo>,
    history: &mut Set<Oid>,
    merges: &mut Vec<(Commit<'repo>, usize)>,
    authors: &mut Set<Author>,
    mailmap: &Mailmap,
) -> Result<()> {
    loop {
        let oid = commit.id();
        if !history.insert(oid) {
            return Ok(());
        }
        let author = author(mailmap, &commit);
        let is_bors = author.name == "bors" && author.email == "bors@rust-lang.org";
        if !is_bors {
            authors.insert(author);
        }
        let mut parents = commit.parents();
        let parent = match parents.next() {
            Some(parent) => parent,
            None => return Ok(()),
        };
        for i in 1..1 + parents.len() {
            merges.push((commit.clone(), i));
        }
        commit = parent;
    }
}

fn parse_summary(summary: &str) -> Result<Option<PullRequest>> {
    let mut rest = None;
    for prefix in [
        "Auto merge of #",
        "Merge pull request #",
        " Manual merge of #",
        "auto merge of #",
        "auto merge of pull req #",
        "rollup merge of #",
        "Rollup merge of #",
        "Rollup merge of  #",
        "Rollup merge of ",
        "Merge PR #",
        "Merge #",
        "Merged #",
    ] {
        if summary.starts_with(prefix) {
            rest = Some(&summary[prefix.len()..]);
            break;
        }
    }
    let rest = match rest {
        Some(rest) => rest,
        None => return Ok(None),
    };
    let end = rest.find([' ', ':']).unwrap_or(rest.len());
    let number = match rest[..end].parse::<u32>() {
        Ok(number) => number,
        Err(err) => {
            eprintln!("{}", summary);
            bail!(err);
        }
    };
    Ok(Some(PullRequest(number)))
}

fn author(mailmap: &Mailmap, commit: &Commit) -> Author {
    let signature = commit.author();
    let name = String::from_utf8_lossy(signature.name_bytes()).into_owned();
    let email = String::from_utf8_lossy(signature.email_bytes()).into_owned();
    mailmap.canonicalize(&Author { name, email })
}

#[derive(Copy, Clone, Ord, PartialOrd, Eq, PartialEq)]
struct PullRequest(u32);

impl Debug for PullRequest {
    fn fmt(&self, formatter: &mut fmt::Formatter) -> fmt::Result {
        write!(formatter, "#{}", self.0)
    }
}

struct DebugSet<T>(T);

impl<T> Debug for DebugSet<T>
where
    T: Iterator + Clone,
    T::Item: Debug,
{
    fn fmt(&self, formatter: &mut fmt::Formatter) -> fmt::Result {
        formatter.debug_set().entries(self.0.clone()).finish()
    }
}
```
</details>