update gitignore for intermediate/resultant content

6 files changed, 45 insertions, 14 deletions

diff --git a/.gitignore b/.gitignore
index 3a10075..6f54c02 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,8 @@
-cvs-repo
-output
-final
+/cvs-repo
+/output
+/final
+/git
+/export-stream-raw
+/export-stream-rewritten
+/userinfo.xml
+/gentoo_mailmap.py
diff --git a/README b/README
index c56f068..1fe1420 100644
--- a/README
+++ b/README
@@ -7,6 +7,8 @@ that said, it needs to conform to thus:
 $(pwd)/cvs-repo/CVSROOT
 $(pwd)/cvs-repo/gentoo-x86/*
 
+From there, get yourself a userinfo.xml, and place it into $(pwd).
+
 From there, ./script.sh is your main point of entry; it'll process that,
 going parallel, using $(pwd)/output for temp space- it's suggested that
 be tmpfs (much like cvs-repo).
diff --git a/config b/config
index 60cd351..58d398b 100644
--- a/config
+++ b/config
@@ -481,17 +481,12 @@ ctx.retain_conflicting_attic_files = False
 # with "u" as a prefix) or 8-bit strings in the utf-8 encoding.
 # Please substitute your own project's usernames here to use with the
 # author_transforms option of GitOutputOption below.
-author_transforms={
-    'jrandom' : ('J. Random', 'jrandom@example.com'),
-    'mhagger' : ('Michael Haggerty', 'mhagger@alum.mit.edu'),
-    'brane' : (u'Branko Čibej', 'brane@xbc.nu'),
-    'ringstrom' : ('Tobias Ringström', 'tobias@ringstrom.mine.nu'),
-    'dionisos' : (u'Erik Hülsmann', 'e.huelsmann@gmx.net'),
-
-    # This one will be used for commits for which CVS doesn't record
-    # the original author, as explained above.
-    'cvs2svn' : ('cvs2svn', 'admin@example.com'),
-    }
+
+import gentoo_mailmap
+author_transforms = gentoo_mailmap.mailmap.copy()
+# This one will be used for commits for which CVS doesn't record
+# the original author, as explained above.
+author_transforms['cvs2svn'] = ('cvs2svn', 'admin@gentoo.org')
 
 # This is the main option that causes cvs2svn to output to a
 # "fastimport"-format dumpfile rather than to Subversion:
diff --git a/create-mailmap.py b/create-mailmap.py
new file mode 100755
index 0000000..085d84f
--- /dev/null
+++ b/create-mailmap.py
@@ -0,0 +1,26 @@
+#!/usr/bin/python
+from xml.etree import ElementTree as etree
+
+def main(source):
+  root = etree.parse(source).getroot()
+  for user in root.findall('user'):
+    fullname = user.findall('realname')[0].get('fullname')
+    # Compute email ourselves...
+    username = user.get('username')
+    assert username
+    email = '%s@gentoo.org' % username
+    yield username, (fullname, email)
+    # Handle aliases...
+    for alias in user.findall('alias'):
+      yield alias.text, (fullname, email)
+
+
+if __name__ == '__main__':
+  import sys
+  if len(sys.argv) != 2:
+    sys.stderr.write("path to userinfo.xml required\n")
+    sys.exit(1)
+  
+  mailmap = dict(main(open(sys.argv[1], 'rb')))
+  sys.stdout.write("mailmap=%r\n" % (mailmap,))
+  sys.exit(0)
diff --git a/process_directory.sh b/process_directory.sh
index c9ff6e6..14ef28c 100755
--- a/process_directory.sh
+++ b/process_directory.sh
@@ -9,8 +9,10 @@ f() {
   ln -s "${root}/gentoo-x86/$1" "${output}/cvs-repo/gentoo-x86/$1"
   #ln -s "${root}/gentoo-x86/Attic" "${output}/cvs-repo/gentoo-x86/Attic"
   ln -s "$(pwd)/config" "${output}/config"
+  ln -s "$(pwd)/gentoo_mailmap.py" "${output}/gentoo_mailmap.py"
   # Note- this must be canonical path, else it screws up our $Header rewriting.
   cd "$(readlink -f "${output}" )"
+  export PYTHONPATH="${output}${PYTHONPATH:+:${PYTHONPATH}}"
   time cvs2git --options config -vv
   cd git
   git init --bare
diff --git a/script.sh b/script.sh
index e5a4e35..7104262 100755
--- a/script.sh
+++ b/script.sh
@@ -5,6 +5,7 @@ proc_count=$(grep -c MHz /proc/cpuinfo)
 
 rm -rf git/* git/.git final/*
 mkdir git -p
+./create-mailmap.py userinfo.xml > gentoo_mailmap.py || { echo "failed to create mailmap."; exit 1; }
 # Prioritize the larger categories first; they typically will have
 # the most revs, thus start them first.
 time { \