add sourcehut input scheme

2 files changed, 122 insertions, 1 deletions

diff --git a/src/libfetchers/github.cc b/src/libfetchers/github.cc
index 1c539b80e..e101aa3d6 100644
--- a/src/libfetchers/github.cc
+++ b/src/libfetchers/github.cc
@@ -8,6 +8,7 @@
 
 #include <optional>
 #include <nlohmann/json.hpp>
+#include <fstream>
 
 namespace nix::fetchers {
 
@@ -17,7 +18,7 @@ struct DownloadUrl
     Headers headers;
 };
 
-// A github or gitlab host
+// A github, gitlab, or sourcehut host
 const static std::string hostRegexS = "[a-zA-Z0-9.]*"; // FIXME: check
 std::regex hostRegex(hostRegexS, std::regex::ECMAScript);
 
@@ -348,7 +349,95 @@ struct GitLabInputScheme : GitArchiveInputScheme
     }
 };
 
+struct SourceHutInputScheme : GitArchiveInputScheme
+{
+    std::string type() override { return "sourcehut"; }
+
+    std::optional<std::pair<std::string, std::string>> accessHeaderFromToken(const std::string & token) const override
+    {
+        // SourceHut supports both PAT and OAuth2. See
+        // https://man.sr.ht/meta.sr.ht/oauth.md
+        return std::pair<std::string, std::string>("Authorization", fmt("Bearer %s", token));
+        // Note: This currently serves no purpose, as this kind of authorization
+        // does not allow for downloading tarballs on sourcehut private repos.
+        // Once it is implemented, however, should work as expected.
+    }
+
+    Hash getRevFromRef(nix::ref<Store> store, const Input & input) const override
+    {
+        // TODO: In the future, when the sourcehut graphql API is implemented for mercurial
+        // and with anonymous access, this method should use it instead.
+
+        auto ref = *input.getRef();
+
+        auto host = maybeGetStrAttr(input.attrs, "host").value_or("git.sr.ht");
+        auto base_url = fmt("https://%s/%s/%s",
+            host, getStrAttr(input.attrs, "owner"), getStrAttr(input.attrs, "repo"));
+
+        Headers headers = makeHeadersWithAuthTokens(host);
+
+        std::string ref_uri;
+        if (ref == "HEAD") {
+            auto file = store->toRealPath(
+                downloadFile(store, fmt("%s/HEAD", base_url), "source", false, headers).storePath);
+            std::ifstream is(file);
+            std::string line;
+            getline(is, line);
+
+            auto ref_index = line.find("ref: ");
+            if (ref_index == std::string::npos) {
+                throw BadURL("in '%d', couldn't resolve HEAD ref '%d'", input.to_string(), ref);
+            }
+
+            ref_uri = line.substr(ref_index+5, line.length()-1);
+        } else
+            ref_uri = fmt("refs/heads/%s", ref);
+
+        auto file = store->toRealPath(
+            downloadFile(store, fmt("%s/info/refs", base_url), "source", false, headers).storePath);
+        std::ifstream is(file);
+
+        std::string line;
+        std::string id;
+        while(getline(is, line)) {
+            auto index = line.find(ref_uri);
+            if (index != std::string::npos) {
+                id = line.substr(0, index-1);
+                break;
+            }
+        }
+
+        if(id.empty())
+            throw BadURL("in '%d', couldn't find ref '%d'", input.to_string(), ref);
+
+        auto rev = Hash::parseAny(id, htSHA1);
+        debug("HEAD revision for '%s' is %s", fmt("%s/%s", base_url, ref), rev.gitRev());
+        return rev;
+    }
+
+    DownloadUrl getDownloadUrl(const Input & input) const override
+    {
+        auto host = maybeGetStrAttr(input.attrs, "host").value_or("git.sr.ht");
+        auto url = fmt("https://%s/%s/%s/archive/%s.tar.gz",
+            host, getStrAttr(input.attrs, "owner"), getStrAttr(input.attrs, "repo"),
+            input.getRev()->to_string(Base16, false));
+
+        Headers headers = makeHeadersWithAuthTokens(host);
+        return DownloadUrl { url, headers };
+    }
+
+    void clone(const Input & input, const Path & destDir) override
+    {
+        auto host = maybeGetStrAttr(input.attrs, "host").value_or("git.sr.ht");
+        Input::fromURL(fmt("git+https://%s/%s/%s",
+                host, getStrAttr(input.attrs, "owner"), getStrAttr(input.attrs, "repo")))
+            .applyOverrides(input.getRef(), input.getRev())
+            .clone(destDir);
+    }
+};
+
 static auto rGitHubInputScheme = OnStartup([] { registerInputScheme(std::make_unique<GitHubInputScheme>()); });
 static auto rGitLabInputScheme = OnStartup([] { registerInputScheme(std::make_unique<GitLabInputScheme>()); });
+static auto rSourceHutInputScheme = OnStartup([] { registerInputScheme(std::make_unique<SourceHutInputScheme>()); });
 
 }
diff --git a/src/nix/flake.md b/src/nix/flake.md
index accddd436..f539a7c28 100644
--- a/src/nix/flake.md
+++ b/src/nix/flake.md
@@ -209,6 +209,38 @@ Currently the `type` attribute can be one of the following:
   * `github:edolstra/dwarffs/unstable`
   * `github:edolstra/dwarffs/d3f2baba8f425779026c6ec04021b2e927f61e31`
 
+* `sourcehut`: Similar to `github`, is a more efficient way to fetch
+  SourceHut repositories. The following attributes are required:
+
+  * `owner`: The owner of the repository (including leading `~`).
+
+  * `repo`: The name of the repository.
+
+  Like `github`, these are downloaded as tarball archives.
+
+  The URL syntax for `sourcehut` flakes is:
+
+  `sourcehut:<owner>/<repo>(/<rev-or-ref>)?(\?<params>)?`
+
+  `<rev-or-ref>` works the same as `github`. Either a branch or tag name
+  (`ref`), or a commit hash (`rev`) can be specified.
+
+  Since SourceHut allows for self-hosting, you can specify `host` as
+  a parameter, to point to any instances other than `git.sr.ht`.
+
+  Currently, `ref` name resolution only works for Git repositories.
+  You can refer to Mercurial repositories by simply changing `host` to
+  `hg.sr.ht` (or any other Mercurial instance). With the caveat
+  that you must explicitly specify a commit hash (`rev`).
+
+  Some examples:
+
+  * `sourcehut:~misterio/nix-colors`
+  * `sourcehut:~misterio/nix-colors/main`
+  * `sourcehut:~misterio/nix-colors?host=git.example.org`
+  * `sourcehut:~misterio/nix-colors/182b4b8709b8ffe4e9774a4c5d6877bf6bb9a21c`
+  * `sourcehut:~misterio/nix-colors/21c1a380a6915d890d408e9f22203436a35bb2de?host=hg.sr.ht`
+
 * `indirect`: Indirections through the flake registry. These have the
   form