From 30c90febf10981e2d5c2048f27976f9d85dd6e84 Mon Sep 17 00:00:00 2001
From: Paul O'Leary McCann <polm@dampfkraft.com>
Date: Wed, 28 Sep 2022 19:26:27 +0900
Subject: [PATCH] Attempt to handle command rewriting on Windows

This handles command rewriting on Windows to ensure the same Python
executable is re-used by using the `executable` argument to
subprocess.run. This has the advantage that it avoids any need to escape
the path of sys.executable. Still needs testing.
---
 spacy/cli/project/run.py | 24 ++++++++++++++++++++----
 spacy/util.py            |  4 ++++
 2 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/spacy/cli/project/run.py b/spacy/cli/project/run.py
index e197662c9..e1f0e3701 100644
--- a/spacy/cli/project/run.py
+++ b/spacy/cli/project/run.py
@@ -167,12 +167,28 @@ def run_commands(
     """
     for c in commands:
         command: Union[str, List[str]]
+        exe: Optional[str] = None
         if is_windows:
-            # On Windows we don't rewrite the command because there's no
-            # reliable way to split and reassemble it
             command = c
+
+            # Correct Windows splitting is hard, so this only checks for simple
+            # cases. It will work in ordinary cases, but will miss cases where
+            # the command is like:
+            #   "C:\My Programs\python.exe" script.py
+            head, _, tail = c.partition(" ")
+
+            # This doesn't rewrite the command to include sys.executable
+            # because sys.executable might include spaces, quotes, or
+            # something, and need quoting itself. Instead the exe param is used
+            # to directly specify the binary to call.
+            if head in ("python", "python3"):
+                exe = sys.executable
+            if head in ("pip", "pip3"):
+                exe = sys.executable
+                command = "python -m pip " + tail
+
             if not silent:
-                print(f"Running command: {c}")
+                print(f"Running command: {command}")
         else:
             command = shlex.split(c, posix=True)
             # Not sure if this is needed or a good idea. Motivation: users may often
@@ -190,7 +206,7 @@ def run_commands(
                 print(f"Running command: {c}")
 
         if not dry:
-            run_command(command, capture=capture)
+            run_command(command, capture=capture, exe=exe)
 
 
 def validate_subcommand(
diff --git a/spacy/util.py b/spacy/util.py
index 14b600aa1..34d470e79 100644
--- a/spacy/util.py
+++ b/spacy/util.py
@@ -941,6 +941,7 @@ def run_command(
     *,
     stdin: Optional[Any] = None,
     capture: bool = False,
+    exe: str = None,
 ) -> subprocess.CompletedProcess:
     """Run a command on the command line as a subprocess. If the subprocess
     returns a non-zero exit code, a system exit is performed.
@@ -952,6 +953,8 @@ def run_command(
         sys.exit will be called with the return code. You should use capture=False
         when you want to turn over execution to the command, and capture=True
         when you want to run the command more like a function.
+    exe (Optional[str]): Path to Python executable to use. Passed separately
+        from the command on Windows to avoid quoting issues.
     RETURNS (Optional[CompletedProcess]): The process object.
     """
 
@@ -990,6 +993,7 @@ def run_command(
             input=stdin,
             encoding="utf8",
             check=False,
+            executable=exe,
             stdout=subprocess.PIPE if capture else None,
             stderr=subprocess.STDOUT if capture else None,
         )