Resolve HEAD in ksurl to actual hash

When the image build configuration specifies kickstart URL as a HEAD of
a git repo, pungi now figures out what the actual hash of that commit is
and uses that hash instead. This might make logs clearer and should
prevent potential problems if someone pushes to that repo during
composing.

Documentation is updated to mention this.

Signed-off-by: Lubomír Sedlář <lsedlar@redhat.com>

doc/configuration.rst

@@ -480,7 +480,8 @@ Image Build Settings
 
 .. note::
     Config can contain anything what is accepted by
-    koji image-build --config configfile.ini
+    ``koji image-build --config configfile.ini``
+
     Repo is currently the only option which is being automatically transformed
     into a string.
 
@@ -488,6 +489,10 @@ Image Build Settings
     The 'format' attr is [('image_type', 'image_suffix'), ...].
     productmd should ideally contain all of image types and suffixes.
 
+    If ``ksurl`` ends with ``#HEAD``, Pungi will figure out the SHA1 hash of
+    current HEAD and use that instead.
+
+
 Example
 -------
 ::
@@ -501,6 +506,7 @@ Example
                     'target': 'koji-target-name',
                     'ksversion': 'F23', # value from pykickstart
                     'version': '23',
+                    # correct SHA1 hash will be put into the URL below automatically
                     'ksurl': 'https://git.fedorahosted.org/git/spin-kickstarts.git?somedirectoryifany#HEAD',
                     'kickstart': "fedora-docker-base.ks",
                     'repo': ["http://someextrarepos.org/repo", "ftp://rekcod.oi/repo].

pungi/phases/image_build.py

@@ -4,7 +4,7 @@
 import os
 import time
 
-from pungi.util import get_arch_variant_data
+from pungi.util import get_arch_variant_data, resolve_git_url
 from pungi.phases.base import PhaseBase
 from pungi.linker import Linker
 from pungi.paths import translate_path
@@ -34,6 +34,9 @@ class ImageBuildPhase(PhaseBase):
             for variant in self.compose.get_variants(arch=arch):
                 image_build_data = get_arch_variant_data(self.compose.conf, self.name, arch, variant)
                 for image_conf in image_build_data:
+                    # Replace possible ambiguous ref name with explicit hash.
+                    if 'ksurl' in image_conf:
+                        image_conf['ksurl'] = resolve_git_url(image_conf['ksurl'])
                     image_conf["arches"] = arch # passed to get_image_build_cmd as dict
                     image_conf["variant"] = variant # ^
                     image_conf["install_tree"] = translate_path(self.compose, self.compose.paths.compose.os_tree(arch, variant)) # ^

pungi/util.py

@@ -23,6 +23,7 @@ import hashlib
 import errno
 import pipes
 import re
+import urlparse
 
 from kobo.shortcuts import run
 from productmd.common import get_major_version
@@ -214,6 +215,32 @@ def get_arch_variant_data(conf, var_name, arch, variant):
     return result
 
 
+def resolve_git_url(url):
+    """Given a url to a Git repo specifying HEAD as a ref, replace that
+    specifier with actual SHA1 of the commit.
+
+    Otherwise, the original URL will be returned.
+
+    Raises RuntimeError if there was an error. Most likely cause is failure to
+    run git command.
+    """
+    r = urlparse.urlsplit(url)
+    if r.fragment != 'HEAD':
+        return url
+
+    baseurl = urlparse.urlunsplit((r.scheme, r.netloc, r.path, '', ''))
+    _, output = run(['git', 'ls-remote', baseurl, r.fragment])
+
+    lines = [line for line in output.split('\n') if line]
+    if len(lines) != 1:
+        # This should never happen. HEAD can not match multiple commits in a
+        # single repo, and there can not be a repo without a HEAD.
+        raise RuntimeError('Failed to resolve %s', url)
+
+    fragment = lines[0].split()[0]
+    return urlparse.urlunsplit((r.scheme, r.netloc, r.path, r.query, fragment))
+
+
 # fomat: {arch|*: [data]}
 def get_arch_data(conf, var_name, arch):
     result = []

tests/test_util.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+
+import mock
+import os
+import sys
+import unittest
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
+
+from pungi import util
+
+
+class TestGitRefResolver(unittest.TestCase):
+
+    @mock.patch('pungi.util.run')
+    def test_successful_resolve(self, run):
+        run.return_value = (0, 'CAFEBABE\tHEAD\n')
+
+        url = util.resolve_git_url('https://git.example.com/repo.git?somedir#HEAD')
+
+        self.assertEqual(url, 'https://git.example.com/repo.git?somedir#CAFEBABE')
+        run.assert_called_once_with(['git', 'ls-remote', 'https://git.example.com/repo.git', 'HEAD'])
+
+    @mock.patch('pungi.util.run')
+    def test_resolve_missing_spec(self, run):
+        url = util.resolve_git_url('https://git.example.com/repo.git')
+
+        self.assertEqual(url, 'https://git.example.com/repo.git')
+        self.assertEqual(run.mock_calls, [])
+
+    @mock.patch('pungi.util.run')
+    def test_resolve_non_head_spec(self, run):
+        url = util.resolve_git_url('https://git.example.com/repo.git#some-tag')
+
+        self.assertEqual(url, 'https://git.example.com/repo.git#some-tag')
+        self.assertEqual(run.mock_calls, [])
+
+    @mock.patch('pungi.util.run')
+    def test_resolve_ambiguous(self, run):
+        run.return_value = (0, 'CAFEBABE\tF11\nDEADBEEF\tF10\n')
+
+        with self.assertRaises(RuntimeError):
+            util.resolve_git_url('https://git.example.com/repo.git?somedir#HEAD')
+
+        run.assert_called_once_with(['git', 'ls-remote', 'https://git.example.com/repo.git', 'HEAD'])
+
+
+if __name__ == "__main__":
+    unittest.main()