merge from trunk

3 files changed, 121 insertions, 14 deletions

diff --git a/cloudinit/sources/DataSourceAzure.py b/cloudinit/sources/DataSourceAzure.py
index 97f151d6..c7331da5 100644
--- a/cloudinit/sources/DataSourceAzure.py
+++ b/cloudinit/sources/DataSourceAzure.py
@@ -34,6 +34,7 @@ DEFAULT_METADATA = {"instance-id": "iid-AZURE-NODE"}
 AGENT_START = ['service', 'walinuxagent', 'start']
 BOUNCE_COMMAND = ['sh', '-xc',
     "i=$interface; x=0; ifdown $i || x=$?; ifup $i || x=$?; exit $x"]
+DATA_DIR_CLEAN_LIST = ['SharedConfig.xml']
 
 BUILTIN_DS_CONFIG = {
     'agent_command': AGENT_START,
@@ -101,7 +102,7 @@ class DataSourceAzureNet(sources.DataSource):
             except BrokenAzureDataSource as exc:
                 raise exc
             except util.MountFailedError:
-                LOG.warn("%s was not mountable" % cdev)
+                LOG.warn("%s was not mountable", cdev)
                 continue
 
             (md, self.userdata_raw, cfg, files) = ret
@@ -128,10 +129,26 @@ class DataSourceAzureNet(sources.DataSource):
         user_ds_cfg = util.get_cfg_by_path(self.cfg, DS_CFG_PATH, {})
         self.ds_cfg = util.mergemanydict([user_ds_cfg, self.ds_cfg])
         mycfg = self.ds_cfg
+        ddir = mycfg['data_dir']
+
+        if found != ddir:
+            cached_ovfenv = util.load_file(
+                os.path.join(ddir, 'ovf-env.xml'), quiet=True)
+            if cached_ovfenv != files['ovf-env.xml']:
+                # source was not walinux-agent's datadir, so we have to clean
+                # up so 'wait_for_files' doesn't return early due to stale data
+                cleaned = []
+                for f in [os.path.join(ddir, f) for f in DATA_DIR_CLEAN_LIST]:
+                    if os.path.exists(f):
+                        util.del_file(f)
+                        cleaned.append(f)
+                if cleaned:
+                    LOG.info("removed stale file(s) in '%s': %s",
+                             ddir, str(cleaned))
 
         # walinux agent writes files world readable, but expects
         # the directory to be protected.
-        write_files(mycfg['data_dir'], files, dirmode=0700)
+        write_files(ddir, files, dirmode=0700)
 
         # handle the hostname 'publishing'
         try:
@@ -139,7 +156,7 @@ class DataSourceAzureNet(sources.DataSource):
                                 self.metadata.get('local-hostname'),
                                 mycfg['hostname_bounce'])
         except Exception as e:
-            LOG.warn("Failed publishing hostname: %s" % e)
+            LOG.warn("Failed publishing hostname: %s", e)
             util.logexc(LOG, "handling set_hostname failed")
 
         try:
@@ -149,13 +166,13 @@ class DataSourceAzureNet(sources.DataSource):
             util.logexc(LOG, "agent command '%s' failed.",
                         mycfg['agent_command'])
 
-        shcfgxml = os.path.join(mycfg['data_dir'], "SharedConfig.xml")
+        shcfgxml = os.path.join(ddir, "SharedConfig.xml")
         wait_for = [shcfgxml]
 
         fp_files = []
         for pk in self.cfg.get('_pubkeys', []):
             bname = str(pk['fingerprint'] + ".crt")
-            fp_files += [os.path.join(mycfg['data_dir'], bname)]
+            fp_files += [os.path.join(ddir, bname)]
 
         missing = util.log_time(logfunc=LOG.debug, msg="waiting for files",
                                 func=wait_for_files,
@@ -169,7 +186,7 @@ class DataSourceAzureNet(sources.DataSource):
             try:
                 self.metadata['instance-id'] = iid_from_shared_config(shcfgxml)
             except ValueError as e:
-                LOG.warn("failed to get instance id in %s: %s" % (shcfgxml, e))
+                LOG.warn("failed to get instance id in %s: %s", shcfgxml, e)
 
         pubkeys = pubkeys_from_crt_files(fp_files)
 
@@ -250,7 +267,7 @@ def pubkeys_from_crt_files(flist):
             errors.append(fname)
 
     if errors:
-        LOG.warn("failed to convert the crt files to pubkey: %s" % errors)
+        LOG.warn("failed to convert the crt files to pubkey: %s", errors)
 
     return pubkeys
 
@@ -281,7 +298,7 @@ def write_files(datadir, files, dirmode=None):
 def invoke_agent(cmd):
     # this is a function itself to simplify patching it for test
     if cmd:
-        LOG.debug("invoking agent: %s" % cmd)
+        LOG.debug("invoking agent: %s", cmd)
         util.subp(cmd, shell=(not isinstance(cmd, list)))
     else:
         LOG.debug("not invoking agent")
@@ -328,7 +345,7 @@ def load_azure_ovf_pubkeys(sshnode):
             continue
         cur = {'fingerprint': "", 'path': ""}
         for child in pk_node.childNodes:
-            if (child.nodeType == text_node or not child.localName):
+            if child.nodeType == text_node or not child.localName:
                 continue
 
             name = child.localName.lower()
@@ -414,7 +431,7 @@ def read_azure_ovf(contents):
 
         # we accept either UserData or CustomData.  If both are present
         # then behavior is undefined.
-        if (name == "userdata" or name == "customdata"):
+        if name == "userdata" or name == "customdata":
             if attrs.get('encoding') in (None, "base64"):
                 ud = base64.b64decode(''.join(value.split()))
             else:
diff --git a/cloudinit/sources/DataSourceCloudSigma.py b/cloudinit/sources/DataSourceCloudSigma.py
new file mode 100644
index 00000000..78acd8a4
--- /dev/null
+++ b/cloudinit/sources/DataSourceCloudSigma.py
@@ -0,0 +1,91 @@
+# vi: ts=4 expandtab
+#
+#    Copyright (C) 2014 CloudSigma
+#
+#    Author: Kiril Vladimiroff <kiril.vladimiroff@cloudsigma.com>
+#
+#    This program is free software: you can redistribute it and/or modify
+#    it under the terms of the GNU General Public License version 3, as
+#    published by the Free Software Foundation.
+#
+#    This program is distributed in the hope that it will be useful,
+#    but WITHOUT ANY WARRANTY; without even the implied warranty of
+#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#    GNU General Public License for more details.
+#
+#    You should have received a copy of the GNU General Public License
+#    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+import re
+
+from cloudinit import log as logging
+from cloudinit import sources
+from cloudinit import util
+from cloudinit.cs_utils import Cepko
+
+LOG = logging.getLogger(__name__)
+
+VALID_DSMODES = ("local", "net", "disabled")
+
+
+class DataSourceCloudSigma(sources.DataSource):
+    """
+    Uses cepko in order to gather the server context from the VM.
+
+    For more information about CloudSigma's Server Context:
+    http://cloudsigma-docs.readthedocs.org/en/latest/server_context.html
+    """
+    def __init__(self, sys_cfg, distro, paths):
+        self.dsmode = 'local'
+        self.cepko = Cepko()
+        self.ssh_public_key = ''
+        sources.DataSource.__init__(self, sys_cfg, distro, paths)
+
+    def get_data(self):
+        """
+        Metadata is the whole server context and /meta/cloud-config is used
+        as userdata.
+        """
+        try:
+            server_context = self.cepko.all().result
+            server_meta = server_context['meta']
+            self.userdata_raw = server_meta.get('cloudinit-user-data', "")
+            self.metadata = server_context
+            self.ssh_public_key = server_meta['ssh_public_key']
+
+            if server_meta.get('cloudinit-dsmode') in VALID_DSMODES:
+                self.dsmode = server_meta['cloudinit-dsmode']
+        except:
+            util.logexc(LOG, "Failed reading from the serial port")
+            return False
+        return True
+
+    def get_hostname(self, fqdn=False, resolve_ip=False):
+        """
+        Cleans up and uses the server's name if the latter is set. Otherwise
+        the first part from uuid is being used.
+        """
+        if re.match(r'^[A-Za-z0-9 -_\.]+$', self.metadata['name']):
+            return self.metadata['name'][:61]
+        else:
+            return self.metadata['uuid'].split('-')[0]
+
+    def get_public_ssh_keys(self):
+        return [self.ssh_public_key]
+
+    def get_instance_id(self):
+        return self.metadata['uuid']
+
+
+# Used to match classes to dependencies. Since this datasource uses the serial
+# port network is not really required, so it's okay to load without it, too.
+datasources = [
+    (DataSourceCloudSigma, (sources.DEP_FILESYSTEM)),
+    (DataSourceCloudSigma, (sources.DEP_FILESYSTEM, sources.DEP_NETWORK)),
+]
+
+
+def get_datasource_list(depends):
+    """
+    Return a list of data sources that match this set of dependencies
+    """
+    return sources.list_from_depends(depends, datasources)
diff --git a/cloudinit/sources/DataSourceEc2.py b/cloudinit/sources/DataSourceEc2.py
index f010e640..1b20ecf3 100644
--- a/cloudinit/sources/DataSourceEc2.py
+++ b/cloudinit/sources/DataSourceEc2.py
@@ -92,12 +92,9 @@ class DataSourceEc2(sources.DataSource):
         except Exception:
             util.logexc(LOG, "Failed to get max wait. using %s", max_wait)
 
-        if max_wait == 0:
-            return False
-
         timeout = 50
         try:
-            timeout = int(mcfg.get("timeout", timeout))
+            timeout = max(0, int(mcfg.get("timeout", timeout)))
         except Exception:
             util.logexc(LOG, "Failed to get timeout, using %s", timeout)
 
@@ -109,6 +106,8 @@ class DataSourceEc2(sources.DataSource):
             mcfg = {}
 
         (max_wait, timeout) = self._get_url_settings()
+        if max_wait <= 0:
+            return False
 
         # Remove addresses from the list that wont resolve.
         mdurls = mcfg.get("metadata_urls", DEF_MD_URLS)