# HG changeset patch
# User Patrick Mezard <pmezard@gmail.com>
# Date 1297624252 -3600
# Node ID 4bbc6bf947f56a92e95a04a27b94a9f72d5482d7
# Parent  607f43a0f09c1e0c9bda3025ab94cde84b97bae8
replay: fetch full revision at most once per run (issue252)

Before this change, hgsubversion was fetching full revisions from the first
revision the project was created to the first revision containing converted
data. Unfortunately, some projects exhibits such spans longer than 500
revisions, during which hgsubversion was uselessly scanning the whole tree. The
fix is not technically perfect, we could record somewhere that while no data
was converted we scanned the project already, instead of scanning once at every
hgsubversion run until a revision is converted. But it should be good enough
unless someone runs hgsubversion once for every target revision.

One repository exhibiting this behaviour:

  svn://svn.zankasoftware.com/zanka

diff --git a/hgsubversion/replay.py b/hgsubversion/replay.py
--- a/hgsubversion/replay.py
+++ b/hgsubversion/replay.py
@@ -52,14 +52,15 @@ def updateexternals(ui, meta, current):
             else:
                 current.delete(path)
 
-def convert_rev(ui, meta, svn, r, tbdelta):
+def convert_rev(ui, meta, svn, r, tbdelta, firstrun):
 
     editor = meta.editor
     editor.current.clear()
     editor.current.rev = r
 
-    if meta.revmap.oldest <= 0:
-        # no prior revisions are known, so fetch the entire revision contents
+    if firstrun and meta.revmap.oldest <= 0:
+        # We know nothing about this project, so fetch everything before
+        # trying to apply deltas.
         ui.debug('replay: fetching full revision\n')
         svn.get_revision(r.revnum, editor)
     else:
diff --git a/hgsubversion/stupid.py b/hgsubversion/stupid.py
--- a/hgsubversion/stupid.py
+++ b/hgsubversion/stupid.py
@@ -536,7 +536,7 @@ def branches_in_paths(meta, tbdelta, pat
             branches[branchname] = branchpath
     return branches
 
-def convert_rev(ui, meta, svn, r, tbdelta):
+def convert_rev(ui, meta, svn, r, tbdelta, firstrun):
     # this server fails at replay
 
     branches = branches_in_paths(meta, tbdelta, r.paths, r.revnum,
diff --git a/hgsubversion/wrappers.py b/hgsubversion/wrappers.py
--- a/hgsubversion/wrappers.py
+++ b/hgsubversion/wrappers.py
@@ -294,6 +294,7 @@ def pull(repo, source, heads=[], force=F
     try:
         try:
             # start converting revisions
+            firstrun = True
             for r in svn.revisions(start=start, stop=stopat_rev):
                 if (r.author is None and
                     r.message == 'This is an empty revision for padding.'):
@@ -320,7 +321,8 @@ def pull(repo, source, heads=[], force=F
                         util.progress(ui, 'pull', r.revnum - start, total=total)
 
                         meta.save_tbdelta(tbdelta)
-                        close = pullfuns[have_replay](ui, meta, svn, r, tbdelta)
+                        close = pullfuns[have_replay](ui, meta, svn, r, tbdelta,
+                                                      firstrun)
                         meta.committags(r, close)
                         for branch, parent in close.iteritems():
                             if parent in (None, node.nullid):
@@ -329,6 +331,7 @@ def pull(repo, source, heads=[], force=F
 
                         meta.save()
                         converted = True
+                        firstrun = False
 
                     except svnwrap.SubversionRepoCanNotReplay, e: #pragma: no cover
                         ui.status('%s\n' % e.message)