Merge #8605

8605: internal: Automatically categorize the changelog entries r=matklad a=lnicola



Co-authored-by: Laurențiu Nicola <[email protected]>

3 files changed, 173 insertions, 43 deletions

diff --git a/docs/dev/README.md b/docs/dev/README.md
index b98ac4c0a..16b23adc6 100644
--- a/docs/dev/README.md
+++ b/docs/dev/README.md
@@ -208,20 +208,26 @@ Release process is handled by `release`, `dist` and `promote` xtasks, `release`
 
 Additionally, it assumes that remote for `rust-analyzer` is called `upstream` (I use `origin` to point to my fork).
 
+`release` calls the GitHub API calls to scrape pull request comments and categorize them in the changelog.
+This step uses the `curl` and `jq` applications, which need to be available in `PATH`.
+Finally, you need to obtain a GitHub personal access token and set the `GITHUB_TOKEN` environment variable.
+
 Release steps:
 
-1. Inside rust-analyzer, run `cargo xtask release`. This will:
+1. Set the `GITHUB_TOKEN` environment variable.
+2. Inside rust-analyzer, run `cargo xtask release`. This will:
    * checkout the `release` branch
    * reset it to `upstream/nightly`
    * push it to `upstream`. This triggers GitHub Actions which:
      * runs `cargo xtask dist` to package binaries and VS Code extension
      * makes a GitHub release
      * pushes VS Code extension to the marketplace
-   * create new changelog in `rust-analyzer.github.io`
-2. While the release is in progress, fill in the changelog
-3. Commit & push the changelog
-4. Tweet
-5. Inside `rust-analyzer`, run `cargo xtask promote` -- this will create a PR to rust-lang/rust updating rust-analyzer's submodule.
+   * call the GitHub API for PR details
+   * create a new changelog in `rust-analyzer.github.io`
+3. While the release is in progress, fill in the changelog
+4. Commit & push the changelog
+5. Tweet
+6. Inside `rust-analyzer`, run `cargo xtask promote` -- this will create a PR to rust-lang/rust updating rust-analyzer's submodule.
    Self-approve the PR.
 
 If the GitHub Actions release fails because of a transient problem like a timeout, you can re-run the job from the Actions console.
diff --git a/xtask/src/release.rs b/xtask/src/release.rs
index dde5d14ee..22bb50467 100644
--- a/xtask/src/release.rs
+++ b/xtask/src/release.rs
@@ -1,4 +1,4 @@
-use std::fmt::Write;
+mod changelog;
 
 use xshell::{cmd, cp, pushd, read_dir, write_file};
 
@@ -38,42 +38,7 @@ impl flags::Release {
         let tags = cmd!("git tag --list").read()?;
         let prev_tag = tags.lines().filter(|line| is_release_tag(line)).last().unwrap();
 
-        let git_log = cmd!("git log {prev_tag}..HEAD --merges --reverse").read()?;
-        let mut git_log_summary = String::new();
-        for line in git_log.lines() {
-            let line = line.trim_start();
-            if let Some(p) = line.find(':') {
-                if let Ok(pr) = line[..p].parse::<u32>() {
-                    writeln!(git_log_summary, "* pr:{}[]{}", pr, &line[p + 1..]).unwrap();
-                }
-            }
-        }
-
-        let contents = format!(
-            "\
-= Changelog #{}
-:sectanchors:
-:page-layout: post
-
-Commit: commit:{}[] +
-Release: release:{}[]
-
-== Sponsors
-
-**Become a sponsor:** On https://opencollective.com/rust-analyzer/[OpenCollective] or
-https://github.com/sponsors/rust-analyzer[GitHub Sponsors].
-
-== New Features
-
-{}
-
-== Fixes
-
-== Internal Improvements
-",
-            changelog_n, commit, today, git_log_summary
-        );
-
+        let contents = changelog::get_changelog(changelog_n, &commit, prev_tag, &today)?;
         let path = changelog_dir.join(format!("{}-changelog-{}.adoc", today, changelog_n));
         write_file(&path, &contents)?;
 
diff --git a/xtask/src/release/changelog.rs b/xtask/src/release/changelog.rs
new file mode 100644
index 000000000..ffcae2cf7
--- /dev/null
+++ b/xtask/src/release/changelog.rs
@@ -0,0 +1,159 @@
+use std::fmt::Write;
+use std::{env, iter};
+
+use anyhow::{bail, Result};
+use xshell::cmd;
+
+pub(crate) fn get_changelog(
+    changelog_n: usize,
+    commit: &str,
+    prev_tag: &str,
+    today: &str,
+) -> Result<String> {
+    let git_log = cmd!("git log {prev_tag}..HEAD --merges --reverse").read()?;
+    let mut features = String::new();
+    let mut fixes = String::new();
+    let mut internal = String::new();
+    let mut others = String::new();
+    for line in git_log.lines() {
+        let line = line.trim_start();
+        if let Some(p) = line.find(':') {
+            let pr = &line[..p];
+            if let Ok(pr_num) = pr.parse::<u32>() {
+                let accept = "Accept: application/vnd.github.v3+json";
+                let token = match env::var("GITHUB_TOKEN") {
+                    Ok(token) => token,
+                    Err(_) => bail!("Please obtain a personal access token from https://github.com/settings/tokens and set the `GITHUB_TOKEN` environment variable."),
+                };
+                let authorization = format!("Authorization: token {}", token);
+                let pr_url = "https://api.github.com/repos/rust-analyzer/rust-analyzer/issues";
+
+                // we don't use an HTTPS client or JSON parser to keep the build times low
+                let pr_json =
+                    cmd!("curl -s -H {accept} -H {authorization} {pr_url}/{pr}").read()?;
+                let pr_title = cmd!("jq .title").stdin(&pr_json).read()?;
+                let pr_title = unescape(&pr_title[1..pr_title.len() - 1]);
+                let pr_comment = cmd!("jq .body").stdin(pr_json).read()?;
+
+                let comments_json =
+                    cmd!("curl -s -H {accept} -H {authorization} {pr_url}/{pr}/comments").read()?;
+                let pr_comments = cmd!("jq .[].body").stdin(comments_json).read()?;
+
+                let l = iter::once(pr_comment.as_str())
+                    .chain(pr_comments.lines())
+                    .rev()
+                    .find_map(|it| {
+                        let it = unescape(&it[1..it.len() - 1]);
+                        it.lines().find_map(parse_changelog_line)
+                    })
+                    .into_iter()
+                    .next()
+                    .unwrap_or_else(|| parse_title_line(&pr_title));
+                let s = match l.kind {
+                    PrKind::Feature => &mut features,
+                    PrKind::Fix => &mut fixes,
+                    PrKind::Internal => &mut internal,
+                    PrKind::Other => &mut others,
+                    PrKind::Skip => continue,
+                };
+                writeln!(s, "* pr:{}[] {}", pr_num, l.message.as_deref().unwrap_or(&pr_title))
+                    .unwrap();
+            }
+        }
+    }
+
+    let contents = format!(
+        "\
+= Changelog #{}
+:sectanchors:
+:page-layout: post
+
+Commit: commit:{}[] +
+Release: release:{}[]
+
+== Sponsors
+
+**Become a sponsor:** On https://opencollective.com/rust-analyzer/[OpenCollective] or
+https://github.com/sponsors/rust-analyzer[GitHub Sponsors].
+
+== New Features
+
+{}
+
+== Fixes
+
+{}
+
+== Internal Improvements
+
+{}
+
+== Others
+
+{}
+",
+        changelog_n, commit, today, features, fixes, internal, others
+    );
+    Ok(contents)
+}
+
+#[derive(Clone, Copy)]
+enum PrKind {
+    Feature,
+    Fix,
+    Internal,
+    Other,
+    Skip,
+}
+
+struct PrInfo {
+    message: Option<String>,
+    kind: PrKind,
+}
+
+fn unescape(s: &str) -> String {
+    s.replace(r#"\""#, "").replace(r#"\n"#, "\n").replace(r#"\r"#, "")
+}
+
+fn parse_changelog_line(s: &str) -> Option<PrInfo> {
+    let parts = s.splitn(3, ' ').collect::<Vec<_>>();
+    if parts.len() < 2 || parts[0] != "changelog" {
+        return None;
+    }
+    let message = parts.get(2).map(|it| it.to_string());
+    let kind = match parts[1].trim_end_matches(':') {
+        "feature" => PrKind::Feature,
+        "fix" => PrKind::Fix,
+        "internal" => PrKind::Internal,
+        "skip" => PrKind::Skip,
+        _ => {
+            let kind = PrKind::Other;
+            let message = format!("{} {}", parts[1], message.unwrap_or_default());
+            return Some(PrInfo { kind, message: Some(message) });
+        }
+    };
+    let res = PrInfo { kind, message };
+    Some(res)
+}
+
+fn parse_title_line(s: &str) -> PrInfo {
+    let lower = s.to_ascii_lowercase();
+    const PREFIXES: [(&str, PrKind); 5] = [
+        ("feat: ", PrKind::Feature),
+        ("feature: ", PrKind::Feature),
+        ("fix: ", PrKind::Fix),
+        ("internal: ", PrKind::Internal),
+        ("minor: ", PrKind::Skip),
+    ];
+
+    for &(prefix, kind) in &PREFIXES {
+        if lower.starts_with(prefix) {
+            let message = match &kind {
+                PrKind::Skip => None,
+                _ => Some(s[prefix.len()..].to_string()),
+            };
+            return PrInfo { kind, message };
+        }
+    }
+    PrInfo { kind: PrKind::Other, message: Some(s.to_string()) }
+}