[StGit PATCH v2 4/4] Handle refresh of changed files with non-ASCII names

["Karl Hasselström" <kha@treskal.com>]

Without -z, git diff-files was quoting them for us.

Signed-off-by: Karl Hasselström <kha@treskal.com>

---

 stgit/git.py                   |   43 +++++++++++++++++++++-------------------
 t/t3200-non-ascii-filenames.sh |    2 +-
 2 files changed, 24 insertions(+), 21 deletions(-)


diff --git a/stgit/git.py b/stgit/git.py
index 8c637d5..8e6bdf4 100644
--- a/stgit/git.py
+++ b/stgit/git.py
@@ -191,6 +191,19 @@ def ls_files(files, tree = 'HEAD', full_name = True):
         raise GitException, \
             'Some of the given paths are either missing or not known to GIT'
 
+def parse_git_ls(output):
+    t = None
+    for line in output.split('\0'):
+        if not line:
+            # There's a zero byte at the end of the output, which
+            # gives us an empty string as the last "line".
+            continue
+        if t == None:
+            mode_a, mode_b, sha1_a, sha1_b, t = line.split(' ')
+        else:
+            yield (t, line)
+            t = None
+
 def tree_status(files = None, tree_id = 'HEAD', unknown = False,
                   noexclude = True, verbose = False, diff_flags = []):
     """Get the status of all changed files, or of a selected set of
@@ -242,21 +255,12 @@ def tree_status(files = None, tree_id = 'HEAD', unknown = False,
         args = diff_flags + [tree_id]
         if files_left:
             args += ['--'] + files_left
-        t = None
-        for line in GRun('diff-index', '-z', *args).raw_output().split('\0'):
-            if not line:
-                # There's a zero byte at the end of the output, which
-                # gives us an empty string as the last "line".
-                continue
-            if t == None:
-                mode_a, mode_b, sha1_a, sha1_b, t = line.split(' ')
-            else:
-                # the condition is needed in case files is emtpy and
-                # diff-index lists those already reported
-                if not line in reported_files:
-                    cache_files.append((t, line))
-                    reported_files.add(line)
-                t = None
+        for t, fn in parse_git_ls(GRun('diff-index', '-z', *args).raw_output()):
+            # the condition is needed in case files is emtpy and
+            # diff-index lists those already reported
+            if not fn in reported_files:
+                cache_files.append((t, fn))
+                reported_files.add(fn)
         files_left = [f for f in files if f not in reported_files]
 
     # files in the index but changed on (or removed from) disk. Only
@@ -267,13 +271,12 @@ def tree_status(files = None, tree_id = 'HEAD', unknown = False,
         args = list(diff_flags)
         if files_left:
             args += ['--'] + files_left
-        for line in GRun('diff-files', *args).output_lines():
-            fs = tuple(line.rstrip().split(' ',4)[-1].split('\t',1))
+        for t, fn in parse_git_ls(GRun('diff-files', '-z', *args).raw_output()):
             # the condition is needed in case files is empty and
             # diff-files lists those already reported
-            if fs[1] not in reported_files:
-                cache_files.append(fs)
-                reported_files.add(fs[1])
+            if not fn in reported_files:
+                cache_files.append((t, fn))
+                reported_files.add(fn)
 
     if verbose:
         out.done()
diff --git a/t/t3200-non-ascii-filenames.sh b/t/t3200-non-ascii-filenames.sh
index 3146b8d..1aa78ed 100755
--- a/t/t3200-non-ascii-filenames.sh
+++ b/t/t3200-non-ascii-filenames.sh
@@ -40,7 +40,7 @@ test_expect_success 'Setup' '
 cat > expected.txt <<EOF
 M skärgårdsö.txt
 EOF
-test_expect_failure 'Status of modified non-ASCII file' '
+test_expect_success 'Status of modified non-ASCII file' '
     stg status > output.txt &&
     diff -u expected.txt output.txt
 '