contrib/synthrepo: walk a repo's directory structure during analysis

Augments the analyze command to additionally walk the repo's current
directory structure (or of any directory tree), counting how many files
appear in which paths. This data is saved in the repo model to be used
by synthesize, for creating an initial commit with many files.

This change is aimed at developing, testing and measuring scaling
improvements when importing/converting a large repository to mercurial.

contrib/synthrepo.py

@@ -23,6 +23,7 Properties that are analyzed and synthes
 - Probability of a commit being a merge
 - Probability of a newly added file being added to a new directory
 - Interarrival time, and time zone, of commits
+- Number of files in each directory
 
 A few obvious properties that are not currently handled realistically:
 
@@ -81,21 +82,25 def parsegitdiff(lines):
         yield filename, mar, lineadd, lineremove, binary
 
 @command('analyze',
-         [('o', 'output', [], _('write output to given file'), _('FILE')),
+         [('o', 'output', '', _('write output to given file'), _('FILE')),
           ('r', 'rev', [], _('analyze specified revisions'), _('REV'))],
-         _('hg analyze'))
+         _('hg analyze'), optionalrepo=True)
 def analyze(ui, repo, *revs, **opts):
     '''create a simple model of a repository to use for later synthesis
 
     This command examines every changeset in the given range (or all
     of history if none are specified) and creates a simple statistical
-    model of the history of the repository.
+    model of the history of the repository. It also measures the directory
+    structure of the repository as checked out.
 
     The model is written out to a JSON file, and can be used by
     :hg:`synthesize` to create or augment a repository with synthetic
     commits that have a structure that is statistically similar to the
     analyzed repository.
     '''
+    root = repo.root
+    if not root.endswith(os.path.sep):
+        root += os.path.sep
 
     revs = list(revs)
     revs.extend(opts['rev'])
@@ -104,15 +109,24 def analyze(ui, repo, *revs, **opts):
 
     output = opts['output']
     if not output:
-        output = os.path.basename(repo.root) + '.json'
+        output = os.path.basename(root) + '.json'
 
     if output == '-':
         fp = sys.stdout
     else:
         fp = open(output, 'w')
 
-    revs = scmutil.revrange(repo, revs)
-    revs.sort()
+    # Always obtain file counts of each directory in the given root directory.
+    def onerror(e):
+        ui.warn(_('error walking directory structure: %s\n') % e)
+
+    dirs = {}
+    rootprefixlen = len(root)
+    for dirpath, dirnames, filenames in os.walk(root, onerror=onerror):
+        dirpathfromroot = dirpath[rootprefixlen:]
+        dirs[dirpathfromroot] = len(filenames)
+        if '.hg' in dirnames:
+            dirnames.remove('.hg')
 
     lineschanged = zerodict()
     children = zerodict()
@@ -128,6 +142,11 def analyze(ui, repo, *revs, **opts):
     dirsadded = zerodict()
     tzoffset = zerodict()
 
+    # If a mercurial repo is available, also model the commit history.
+    if repo:
+        revs = scmutil.revrange(repo, revs)
+        revs.sort()
+
     progress = ui.progress
     _analyzing = _('analyzing')
     _changesets = _('changesets')
@@ -150,16 +169,18 def analyze(ui, repo, *revs, **opts):
         else:
             lastctx = repo[rev - 1]
         if lastctx.rev() != nullrev:
-            interarrival[roundto(ctx.date()[0] - lastctx.date()[0], 300)] += 1
+                timedelta = ctx.date()[0] - lastctx.date()[0]
+                interarrival[roundto(timedelta, 300)] += 1
         diff = sum((d.splitlines() for d in ctx.diff(pctx, git=True)), [])
         fileadds, diradds, fileremoves, filechanges = 0, 0, 0, 0
-        for filename, mar, lineadd, lineremove, binary in parsegitdiff(diff):
-            if binary:
+            for filename, mar, lineadd, lineremove, isbin in parsegitdiff(diff):
+                if isbin:
                 continue
             added = sum(lineadd.itervalues(), 0)
             if mar == 'm':
                 if added and lineremove:
-                    lineschanged[roundto(added, 5), roundto(lineremove, 5)] += 1
+                        lineschanged[roundto(added, 5),
+                                     roundto(lineremove, 5)] += 1
                     filechanges += 1
             elif mar == 'a':
                 fileadds += 1
@@ -189,6 +210,7 def analyze(ui, repo, *revs, **opts):
         return sorted(d.iteritems(), key=lambda x: x[1], reverse=True)
 
     json.dump({'revs': len(revs),
+               'initdirs': pronk(dirs),
                'lineschanged': pronk(lineschanged),
                'children': pronk(invchildren),
                'fileschanged': pronk(fileschanged),