streamingclone: extract the scanning part from the generation part

We will reuse the scanning part for local clone, so we need it in a dedicated
function.

Differential Revision: https://phab.mercurial-scm.org/D10852

mercurial/streamclone.py

@@ -603,21 +603,19 def _test_sync_point_walk_2(repo):
     """a function for synchronisation during tests"""
 
 
-def generatev2(repo, includes, excludes, includeobsmarkers):
-    """Emit content for version 2 of a streaming clone.
+def _v2_walk(repo, includes, excludes, includeobsmarkers):
+    """emit a seris of files information useful to clone a repo
+
+    return (entries, totalfilesize)
+
+    entries is a list of tuple (vfs-key, file-path, file-type, size)
 
-    the data stream consists the following entries:
-    1) A char representing the file destination (eg: store or cache)
-    2) A varint containing the length of the filename
-    3) A varint containing the length of file data
-    4) N bytes containing the filename (the internal, store-agnostic form)
-    5) N bytes containing the file data
-
-    Returns a 3-tuple of (file count, file size, data iterator).
+    - `vfs-key`: is a key to the right vfs to write the file (see _makemap)
+    - `name`: file path of the file to copy (to be feed to the vfss)
+    - `file-type`: do this file need to be copied with the source lock ?
+    - `size`: the size of the file (or None)
     """
-
-    with repo.lock():
-
+    assert repo._currentlock(repo._lockref) is not None
         entries = []
         totalfilesize = 0
 
@@ -625,7 +623,6 def generatev2(repo, includes, excludes,
         if includes or excludes:
             matcher = narrowspec.match(repo.root, includes, excludes)
 
-        repo.ui.debug(b'scanning\n')
         for rl_type, name, ename, size in _walkstreamfiles(repo, matcher):
             if size:
                 ft = _fileappend
@@ -644,6 +641,32 def generatev2(repo, includes, excludes,
             if repo.cachevfs.exists(name):
                 totalfilesize += repo.cachevfs.lstat(name).st_size
                 entries.append((_srccache, name, _filefull, None))
+    return entries, totalfilesize
+
+
+def generatev2(repo, includes, excludes, includeobsmarkers):
+    """Emit content for version 2 of a streaming clone.
+
+    the data stream consists the following entries:
+    1) A char representing the file destination (eg: store or cache)
+    2) A varint containing the length of the filename
+    3) A varint containing the length of file data
+    4) N bytes containing the filename (the internal, store-agnostic form)
+    5) N bytes containing the file data
+
+    Returns a 3-tuple of (file count, file size, data iterator).
+    """
+
+    with repo.lock():
+
+        repo.ui.debug(b'scanning\n')
+
+        entries, totalfilesize = _v2_walk(
+            repo,
+            includes=includes,
+            excludes=excludes,
+            includeobsmarkers=includeobsmarkers,
+        )
 
         chunks = _emit2(repo, entries, totalfilesize)
         first = next(chunks)