[git-llvm] Make push work on CRLF files with svn:eol-style=native

Summary:
`git apply` on Windows doesn't work for files that SVN checks out as
CRLF. There is no way to force SVN to check everything out with Unix
line endings on Windows. Files with svn:eol-style=native will always
come out with CRLF, breaking `git apply`, which wants Unix line endings.
My workaround is to list all files with this property set in the change,
and run `dos2unix` on them. SVN doesn't commit a massive line ending
change because the svn:eol-style property indicates that these are text
files.

Tested on r301245.

Reviewers: zturner, jlebar

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D32452

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@301262 91177308-0d34-0410-b5e6-96231b3b80d8

utils/git-svn/git-llvm

@@ -51,6 +51,7 @@ GIT_TO_SVN_DIR.update({'clang': 'cfe/trunk'})
 
 VERBOSE = False
 QUIET = False
+dev_null_fd = None
 
 
 def eprint(*args, **kwargs):
@@ -82,19 +83,33 @@ def first_dirname(d):
         d = head
 
 
-def shell(cmd, strip=True, cwd=None, stdin=None, die_on_failure=True):
+def get_dev_null():
+    """Lazily create a /dev/null fd for use in shell()"""
+    global dev_null_fd
+    if dev_null_fd is None:
+        dev_null_fd = open(os.devnull, 'w')
+    return dev_null_fd
+
+
+def shell(cmd, strip=True, cwd=None, stdin=None, die_on_failure=True,
+          ignore_errors=False):
     log_verbose('Running: %s' % ' '.join(cmd))
 
+    err_pipe = subprocess.PIPE
+    if ignore_errors:
+        # Silence errors if requested.
+        err_pipe = get_dev_null()
+
     start = time.time()
-    p = subprocess.Popen(cmd, cwd=cwd, stdout=subprocess.PIPE,
-                         stderr=subprocess.PIPE, stdin=subprocess.PIPE)
+    p = subprocess.Popen(cmd, cwd=cwd, stdout=subprocess.PIPE, stderr=err_pipe,
+                         stdin=subprocess.PIPE)
     stdout, stderr = p.communicate(input=stdin)
     elapsed = time.time() - start
 
     log_verbose('Command took %0.1fs' % elapsed)
 
-    if p.returncode == 0:
-        if stderr:
+    if p.returncode == 0 or ignore_errors:
+        if stderr and not ignore_errors:
             eprint('`%s` printed to stderr:' % ' '.join(cmd))
             eprint(stderr.rstrip())
         if strip:
@@ -115,7 +130,8 @@ def git(*cmd, **kwargs):
 
 def svn(cwd, *cmd, **kwargs):
     # TODO: Better way to do default arg when we have *cmd?
-    return shell(['svn'] + list(cmd), cwd=cwd, stdin=kwargs.get('stdin', None))
+    return shell(['svn'] + list(cmd), cwd=cwd, stdin=kwargs.get('stdin', None),
+                 ignore_errors=kwargs.get('ignore_errors', None))
 
 
 def get_default_rev_range():
@@ -173,6 +189,41 @@ def svn_init(svn_root):
         die("Can't initialize svn staging dir (%s)" % svn_root)
 
 
+def fix_eol_style_native(rev, sr, svn_sr_path):
+    """Fix line endings before applying patches with Unix endings
+
+    SVN on Windows will check out files with CRLF for files with the
+    svn:eol-style property set to "native". This breaks `git apply`, which
+    typically works with Unix-line ending patches. Work around the problem here
+    by doing a dos2unix up front for files with svn:eol-style set to "native".
+    SVN will not commit a mass line ending re-doing because it detects the line
+    ending format for files with this property.
+    """
+    files = git('diff-tree', '--no-commit-id', '--name-only', '-r', rev, '--',
+                sr).split('\n')
+    files = [f.split('/', 1)[1] for f in files]
+    # Use ignore_errors because 'svn propget' prints errors if the file doesn't
+    # have the named property. There doesn't seem to be a way to suppress that.
+    eol_props = svn(svn_sr_path, 'propget', 'svn:eol-style', *files,
+                    ignore_errors=True).split('\n')
+    crlf_files = []
+    for eol_prop in eol_props:
+        if not eol_prop:
+            continue
+        prop_parts = eol_prop.rsplit(' - ', 1)
+        if len(prop_parts) != 2:
+            eprint("unable to parse svn propget line:")
+            eprint(eol_prop)
+            continue
+        (f, eol_style) = prop_parts
+        if eol_style == 'native':
+            crlf_files.append(f)
+    # Reformat all files with native SVN line endings to Unix format. SVN knows
+    # files with native line endings are text files. It will commit just the
+    # diff, and not a mass line ending change.
+    shell(['dos2unix', '-q'] + crlf_files, cwd=svn_sr_path)
+
+
 def svn_push_one_rev(svn_repo, rev, dry_run):
     files = git('diff-tree', '--no-commit-id', '--name-only', '-r',
                 rev).split('\n')
@@ -186,8 +237,10 @@ def svn_push_one_rev(svn_repo, rev, dry_run):
             (rev, status))
 
     for sr in subrepos:
-        diff = git('show', '--binary', rev, '--', sr, strip=False)
         svn_sr_path = os.path.join(svn_repo, GIT_TO_SVN_DIR[sr])
+        if os.name == 'nt':
+            fix_eol_style_native(rev, sr, svn_sr_path)
+        diff = git('show', '--binary', rev, '--', sr, strip=False)
         # git is the only thing that can handle its own patches...
         log_verbose('Apply patch: %s' % diff)
         try: