From 6bfb1b3a29fa556daad7e81ab4980fb3a54c616e Mon Sep 17 00:00:00 2001
From: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Date: Tue, 1 Sep 2020 19:49:01 +0200
Subject: [PATCH] Fix sparse checkout for 'spacy project' (#6008)

* exit if cloning fails

* UX

* rewrite http link to git protocol, don't use stdin

* fixes to sparse checkout

* formatting
---
 spacy/cli/_util.py         | 29 ++++++++++++++++++-----------
 spacy/cli/project/clone.py |  5 +++--
 2 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/spacy/cli/_util.py b/spacy/cli/_util.py
index 16e257ce2..cfa126cc4 100644
--- a/spacy/cli/_util.py
+++ b/spacy/cli/_util.py
@@ -297,9 +297,7 @@ def ensure_pathy(path):
     return Pathy(path)
 
 
-def git_sparse_checkout(
-    repo: str, subpath: str, dest: Path, *, branch: Optional[str] = None
-):
+def git_sparse_checkout(repo: str, subpath: str, dest: Path, *, branch: str = "master"):
     if dest.exists():
         msg.fail("Destination of checkout must not exist", exits=1)
     if not dest.parent.exists():
@@ -323,21 +321,30 @@ def git_sparse_checkout(
         # This is the "clone, but don't download anything" part.
         cmd = (
             f"git clone {repo} {tmp_dir} --no-checkout --depth 1 "
-            "--filter=blob:none"  # <-- The key bit
+            f"--filter=blob:none "  # <-- The key bit
+            f"-b {branch}"
         )
-        if branch is not None:
-            cmd = f"{cmd} -b {branch}"
         run_command(cmd, capture=True)
         # Now we need to find the missing filenames for the subpath we want.
         # Looking for this 'rev-list' command in the git --help? Hah.
         cmd = f"git -C {tmp_dir} rev-list --objects --all --missing=print -- {subpath}"
         ret = run_command(cmd, capture=True)
-        missings = "\n".join([x[1:] for x in ret.stdout.split() if x.startswith("?")])
+        repo = _from_http_to_git(repo)
         # Now pass those missings into another bit of git internals
-        run_command(
-            f"git -C {tmp_dir} fetch-pack --stdin {repo}", capture=True, stdin=missings
-        )
+        missings = " ".join([x[1:] for x in ret.stdout.split() if x.startswith("?")])
+        cmd = f"git -C {tmp_dir} fetch-pack {repo} {missings}"
+        run_command(cmd, capture=True)
         # And finally, we can checkout our subpath
-        run_command(f"git -C {tmp_dir} checkout {branch} {subpath}")
+        cmd = f"git -C {tmp_dir} checkout {branch} {subpath}"
+        run_command(cmd)
         # We need Path(name) to make sure we also support subdirectories
         shutil.move(str(tmp_dir / Path(subpath)), str(dest))
+
+
+def _from_http_to_git(repo):
+    if repo.startswith("http://"):
+        repo = repo.replace(r"http://", r"https://")
+    if repo.startswith(r"https://"):
+        repo = repo.replace("https://", "git@").replace("/", ":", 1)
+        repo = f"{repo}.git"
+    return repo
diff --git a/spacy/cli/project/clone.py b/spacy/cli/project/clone.py
index 7f9a46a46..751c389bc 100644
--- a/spacy/cli/project/clone.py
+++ b/spacy/cli/project/clone.py
@@ -43,7 +43,7 @@ def project_clone(name: str, dest: Path, *, repo: str = about.__projects__) -> N
         git_sparse_checkout(repo, name, dest)
     except subprocess.CalledProcessError:
         err = f"Could not clone '{name}' from repo '{repo_name}'"
-        msg.fail(err)
+        msg.fail(err, exits=1)
     msg.good(f"Cloned '{name}' from {repo_name}", project_dir)
     if not (project_dir / PROJECT_FILE).exists():
         msg.warn(f"No {PROJECT_FILE} found in directory")
@@ -78,6 +78,7 @@ def check_clone(name: str, dest: Path, repo: str) -> None:
     if not dest.parent.exists():
         # We're not creating parents, parent dir should exist
         msg.fail(
-            f"Can't clone project, parent directory doesn't exist: {dest.parent}",
+            f"Can't clone project, parent directory doesn't exist: {dest.parent}. "
+            f"Create the necessary folder(s) first before continuing.",
             exits=1,
         )