query HEAD name, instead of assuming main/master (#386)

Summary: query HEAD name, instead of assuming main/master Test Plan: --- Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/facebook/sapling/pull/386). * __->__ #386 Pull Request resolved: #386 Fixes #375 Ran a number of affected integration tests: ``` ./run-tests.py test-git.t test-git-submodule.t test-git-submodule-rebase.t test-rust-clone.t test-doctest.py ``` Using the example from #375, cloned the repo and verified that it cloned the `trunk` branch: ``` $ lhg clone --git https://github.com/cli/cli $ cd cli $ lhg @ 179e9c256 Yesterday at 14:13 2159081+qoega remote/trunk │ Add projectsV2 support to issue create, issue edit, pr create, and pr edit (#6735) │ o 06ae07f97 Yesterday at 07:25 mislav ├─╮ Merge pull request #6880 from cli/setdefault-bare-repo │ │ o │ 351226d34 Yesterday at 07:17 mislav ├───╮ Merge pull request #6881 from cli/reviewers-json-fix │ │ │ o │ │ 241f9197e Wednesday at 21:15 rmw ├─────╮ Merge pull request #6815 from cli/intake-doc ... ``` Reviewed By: quark-zju Differential Revision: D42597162 Pulled By: bolinfest fbshipit-source-id: 2f4b3869f452b57290f2a7a69721ecdd4e444b2e
facebook · Jan 21, 2023 · c8b66c6 · c8b66c6
1 parent cea7748
commit c8b66c6
Show file tree

Hide file tree

Showing 3 changed files with 74 additions and 2 deletions.
diff --git a/eden/scm/edenscm/git.py b/eden/scm/edenscm/git.py
@@ -10,6 +10,7 @@
 import errno
 import hashlib
 import os
+import re
 import shutil
 import subprocess
 import textwrap
@@ -128,6 +129,26 @@ def clone(ui, url, destpath=None, update=True, pullnames=None):
         initgit(repo, "git", url)
         if url:
             if pullnames is None:
+                ls_remote_args = ["ls-remote", "--symref", url, "HEAD"]
+                symref_head_output = callgit(repo, ls_remote_args).decode("utf-8")
+                default_branch = parse_symref_head(symref_head_output)
+                if default_branch:
+                    pullnames = [default_branch]
+                elif not symref_head_output:
+                    # Empty string: may be empty repo?
+                    pass
+                else:
+                    ui.status_err(
+                        _("could not parse output of '%s': %s")
+                        % (
+                            " ".join(ls_remote_args),
+                            symref_head_output,
+                        )
+                    )
+
+            if pullnames is None:
+                # If `git ls-remote --symref <url> HEAD` failed to yield a name,
+                # fall back to the using the names in the config.
                 pullnames = bookmod.selectivepullbookmarknames(repo)
 
             # Make sure we pull "update". If it looks like a hash, add to
@@ -143,6 +164,7 @@ def clone(ui, url, destpath=None, update=True, pullnames=None):
                 if not nodes:
                     pullnames.append(update)
 
+            pullnames = util.dedup(pullnames)
             pull(repo, "default", names=pullnames, nodes=nodes)
     except (Exception, KeyboardInterrupt):
         repo = None
@@ -159,6 +181,55 @@ def clone(ui, url, destpath=None, update=True, pullnames=None):
     return repo
 
 
+def parse_symref_head(symref_head_output: str) -> Optional[str]:
+    r"""
+    Args:
+        symref_head_output - output of `ls-remote --symref <url> HEAD`
+
+    >>> sapling = (
+    ...     "ref: refs/heads/main\tHEAD\n"
+    ...     "f58888310501872447b1b2fa4a8789210a6c6252\tHEAD\n"
+    ... )
+    >>> parse_symref_head(sapling)
+    'main'
+    >>> pytorch = (
+    ...     "ref: refs/heads/master\tHEAD\n"
+    ...     "8b3e35ea4aa210f48a92966e3347b78dfc6e9360\tHEAD\n"
+    ... )
+    >>> parse_symref_head(pytorch)
+    'master'
+    >>> foobar = (
+    ...     "ref: refs/heads/foo/bar\tHEAD\n"
+    ...     "8b3e35ea4aa210f48a92966e3347b78dfc6e9360\tHEAD\n"
+    ... )
+    >>> parse_symref_head(foobar)
+    'foo/bar'
+    >>> tag = (
+    ...     "ref: refs/tags/foo\tHEAD\n"
+    ...     "8b3e35ea4aa210f48a92966e3347b78dfc6e9360\tHEAD\n"
+    ... )
+    >>> parse_symref_head(tag) is None
+    True
+    >>> gerrit_refs_for = (
+    ...     "ref: refs/for/master\tHEAD\n"
+    ...     "8b3e35ea4aa210f48a92966e3347b78dfc6e9360\tHEAD\n"
+    ... )
+    >>> parse_symref_head(gerrit_refs_for) is None
+    True
+    >>> parse_symref_head('') is None
+    True
+    """
+    pat = re.compile(r"^ref: ([^\t]*)\t")
+    match = pat.match(symref_head_output)
+    if match:
+        ref = match.group(1)
+        prefix = "refs/heads/"
+        if ref.startswith(prefix):
+            return ref[len(prefix) :]
+
+    return None
+
+
 def initgit(repo, gitdir, giturl=None):
     """Change a repo to be backed by a bare git repo in `gitdir`.
     This should only be called for newly created repos.

diff --git a/eden/scm/tests/test-doctest.py b/eden/scm/tests/test-doctest.py
@@ -52,6 +52,7 @@ def testmod(name, optionflags=0, testtarget=None):
 testmod("edenscm.drawdag")
 testmod("edenscm.encoding")
 testmod("edenscm.formatter")
+testmod("edenscm.git")
 testmod("edenscm.gituser")
 testmod("edenscm.hg")
 testmod("edenscm.match")

diff --git a/eden/scm/tests/test-git.t b/eden/scm/tests/test-git.t
@@ -248,10 +248,10 @@ Test clone with flags (--noupdate, --updaterev):
      remote/master             3f5848713286
   $ cd ..
 
-  $ hg clone --git "$TESTTMP/gitrepo" cloned1 --config remotenames.selectivepulldefault=foo,master
+  $ hg clone --git "$TESTTMP/gitrepo" -u foo cloned1
   From $TESTTMP/gitrepo
-   * [new ref]         57eda5013e068ac543a52ad073cec3d7750113b5 -> remote/foo
    * [new ref]         3f5848713286c67b8a71a450e98c7fa66787bde2 -> remote/master
+   * [new ref]         57eda5013e068ac543a52ad073cec3d7750113b5 -> remote/foo
   2 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg --cwd cloned1 log -r . -T '{node|short} {remotenames} {desc}\n'
   57eda5013e06 remote/foo alpha3