Add a Mercurial contentprovider

MyBinder could support Mercurial repositories

See https://github.com/jupyterhub/binderhub/issues/1148

Pipfile

@@ -12,6 +12,8 @@ alabaster = "*"
 Sphinx = ">=1.4,!=1.5.4"
 alabaster_jupyterhub = "*"
 sphinxcontrib-autoprogram = "*"
+mercurial = "*"
+hg-evolve = "*"
 
 [packages]
 repo2docker = {path=".", editable=true}

dev-requirements.txt

@@ -6,3 +6,5 @@ wheel
 pytest-cov
 pre-commit
 requests
+mercurial
+hg-evolve

repo2docker/contentproviders/__init__.py

@@ -4,3 +4,4 @@ from .zenodo import Zenodo
 from .figshare import Figshare
 from .dataverse import Dataverse
 from .hydroshare import Hydroshare
+from .mercurial import Mercurial

repo2docker/contentproviders/mercurial.py

@@ -0,0 +1,79 @@
+import subprocess
+
+from .base import ContentProvider, ContentProviderException
+from ..utils import execute_cmd
+
+
+hg_config = [
+    "--config",
+    "extensions.hggit=!",
+    "--config",
+    "extensions.evolve=",
+    "--config",
+    "extensions.topic=",
+]
+
+
+class Mercurial(ContentProvider):
+    """Provide contents of a remote Mercurial repository."""
+
+    def detect(self, source, ref=None, extra_args=None):
+        if "github.com/" in source or source.endswith(".git"):
+            return None
+        try:
+            subprocess.check_output(
+                ["hg", "identify", source] + hg_config, stderr=subprocess.DEVNULL,
+            )
+        except subprocess.CalledProcessError:
+            return None
+
+        return {"repo": source, "ref": ref}
+
+    def fetch(self, spec, output_dir, yield_output=False):
+        repo = spec["repo"]
+        ref = spec.get("ref", None)
+
+        # make a clone of the remote repository
+        try:
+            cmd = ["hg", "clone", repo, output_dir]
+            cmd.extend(hg_config)
+            if ref is not None:
+                # don't update so the clone will include an empty working
+                # directory, the given ref will be updated out later
+                cmd.extend(["--noupdate"])
+            for line in execute_cmd(cmd, capture=yield_output):
+                yield line
+
+        except subprocess.CalledProcessError as error:
+            msg = "Failed to clone repository from {repo}".format(repo=repo)
+            if ref is not None:
+                msg += " (ref {ref})".format(ref=ref)
+            msg += "."
+            raise ContentProviderException(msg) from error
+
+        # check out the specific ref given by the user
+        if ref is not None:
+            try:
+                for line in execute_cmd(
+                    ["hg", "update", "--clean", ref] + hg_config,
+                    cwd=output_dir,
+                    capture=yield_output,
+                ):
+                    yield line
+            except subprocess.CalledProcessError:
+                self.log.error(
+                    "Failed to update to ref %s", ref, extra=dict(phase="failed")
+                )
+                raise ValueError("Failed to update to ref {}".format(ref))
+
+        cmd = ["hg", "identify"]
+        cmd.extend(hg_config)
+        sha1 = subprocess.Popen(cmd, stdout=subprocess.PIPE, cwd=output_dir)
+        self._sha1 = sha1.stdout.read().decode().strip()
+
+    @property
+    def content_id(self):
+        """A unique ID to represent the version of the content.
+        Uses the first seven characters of the git commit ID of the repository.
+        """
+        return self._sha1[:7]

tests/unit/contentproviders/test_mercurial.py

@@ -0,0 +1,82 @@
+from pathlib import Path
+import subprocess
+from tempfile import TemporaryDirectory
+
+import pytest
+
+from repo2docker.contentproviders import Mercurial
+
+
+def _add_content_to_hg(repo_dir):
+    """Add content to file 'test' in hg repository and commit."""
+    # use append mode so this can be called multiple times
+    with open(Path(repo_dir) / "test", "a") as f:
+        f.write("Hello")
+
+    subprocess.check_call(["hg", "add", "test"], cwd=repo_dir)
+    subprocess.check_call(["hg", "commit", "-m", "Test commit"], cwd=repo_dir)
+
+
+def _get_sha1(repo_dir):
+    """Get repository's current commit SHA1."""
+    sha1 = subprocess.Popen(["hg", "identify"], stdout=subprocess.PIPE, cwd=repo_dir)
+    return sha1.stdout.read().decode().strip()
+
+
+@pytest.fixture()
+def hg_repo():
+    """
+    Make a dummy git repo in which user can perform git operations
+
+    Should be used as a contextmanager, it will delete directory when done
+    """
+    with TemporaryDirectory() as gitdir:
+        subprocess.check_call(["hg", "init"], cwd=gitdir)
+        yield gitdir
+
+
+@pytest.fixture()
+def hg_repo_with_content(hg_repo):
+    """Create a hg repository with content"""
+    _add_content_to_hg(hg_repo)
+    sha1 = _get_sha1(hg_repo)
+
+    yield hg_repo, sha1
+
+
+def test_detect_mercurial(hg_repo_with_content, repo_with_content):
+    mercurial = Mercurial()
+    assert mercurial.detect("this-is-not-a-directory") is None
+    assert mercurial.detect("https://github.com/jupyterhub/repo2docker") is None
+
+    git_repo = repo_with_content[0]
+    assert mercurial.detect(git_repo) is None
+
+    hg_repo = hg_repo_with_content[0]
+    assert mercurial.detect(hg_repo) == {"repo": hg_repo, "ref": None}
+
+
+def test_clone(hg_repo_with_content):
+    """Test simple hg clone to a target dir"""
+    upstream, sha1 = hg_repo_with_content
+
+    with TemporaryDirectory() as clone_dir:
+        spec = {"repo": upstream}
+        mercurial = Mercurial()
+        for _ in mercurial.fetch(spec, clone_dir):
+            pass
+        assert (Path(clone_dir) / "test").exists()
+
+        assert mercurial.content_id == sha1[:7]
+
+
+def test_bad_ref(hg_repo_with_content):
+    """
+    Test trying to checkout a ref that doesn't exist
+    """
+    upstream, sha1 = hg_repo_with_content
+    with TemporaryDirectory() as clone_dir:
+        spec = {"repo": upstream, "ref": "does-not-exist"}
+        with pytest.raises(ValueError):
+            for _ in Mercurial().fetch(spec, clone_dir):
+                pass