Merge pull request #302 from qwhelan/hash_uniqueness

Add utility function to enforce hash prefix uniqueness

asv/results.py

@@ -50,11 +50,12 @@ def iter_results_for_machine_and_hash(results, machine_name, commit):
     Iterate over all of the result files with a given hash for a
     particular machine.
     """
+    full_commit = get_result_hash_from_prefix(results, machine_name, commit)
+
     for (root, filename) in iter_results_paths(
             os.path.join(results, machine_name)):
         results_commit = filename.split('-')[0]
-        cmp_len = min(len(commit), len(results_commit))
-        if results_commit[:cmp_len] == commit[:cmp_len]:
+        if results_commit == full_commit:
             yield Results.load(os.path.join(root, filename))
 
 
@@ -80,6 +81,34 @@ def get_existing_hashes(results):
     return hashes
 
 
+def get_result_hash_from_prefix(results, machine_name, commit_prefix):
+    """
+    Get the 8-char result commit identifier from a potentially shorter
+    prefix. Only considers the set of commits that have had
+    results computed.
+
+    Returns None if there are no matches. Raises a UserError
+    if the prefix is non-unique.
+    """
+    commits = set([])
+
+    for (root, filename) in iter_results_paths(os.path.join(results,
+                                                            machine_name)):
+        results_commit = filename.split('-')[0]
+        cmp_len = min(len(commit_prefix), len(results_commit))
+        if results_commit[:cmp_len] == commit_prefix[:cmp_len]:
+            commits.add(results_commit)
+
+    if len(commits) > 1:
+        commit_list_str = ', '.join(sorted(commits))
+        raise util.UserError('Git hash prefix could represent one of ' +
+                             'multiple commits: {0}'.format(commit_list_str))
+    elif len(commits) == 1:
+        return list(commits)[0]
+    else:
+        return None
+
+
 def find_latest_result_hash(machine, root, hashes=None):
     """
     Find the latest result for the given machine.

test/test_results.py

@@ -4,11 +4,13 @@
 from __future__ import (absolute_import, division, print_function,
                         unicode_literals)
 
+import os
 from os.path import join
 
 import six
 
-from asv import results
+from asv import results, util
+import pytest
 
 
 def test_results(tmpdir):
@@ -35,3 +37,25 @@ def test_results(tmpdir):
         assert r2._results == r._results
         assert r2.date == r.date
         assert r2.commit_hash == r.commit_hash
+
+
+def test_get_result_hash_from_prefix(tmpdir):
+    results_dir = tmpdir.mkdir('results')
+    machine_dir = results_dir.mkdir('machine')
+
+    for f in ['e5b6cdbc', 'e5bfoo12']:
+        open(join(str(machine_dir), '{0}-py2.7-Cython-numpy1.8.json'.format(f)), 'a').close()
+
+    # check unique, valid case
+    full_commit = results.get_result_hash_from_prefix(str(results_dir), 'machine', 'e5b6')
+    assert full_commit == 'e5b6cdbc'
+
+    # check invalid hash case
+    bad_commit = results.get_result_hash_from_prefix(str(results_dir), 'machine', 'foobar')
+    assert bad_commit is None
+
+    # check non-unique case
+    with pytest.raises(util.UserError) as excinfo:
+        results.get_result_hash_from_prefix(str(results_dir), 'machine', 'e')
+
+    assert 'one of multiple commits' in str(excinfo.value)