1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
|
"""A Simple bzr plugin to generate statistics about the history."""
import re
from bzrlib import errors, tsort
from bzrlib.branch import Branch
import bzrlib.commands
from bzrlib.config import extract_email_address
from bzrlib.workingtree import WorkingTree
_fullname_re = re.compile(r'(?P<fullname>.*?)\s*<')
def extract_fullname(committer):
"""Try to get the user's name from their committer info."""
m = _fullname_re.match(committer)
if m:
return m.group('fullname')
try:
email = extract_email_address(committer)
except errors.BzrError:
return committer
else:
# We found an email address, but not a fullname
# so there is no fullname
return ''
def find_fullnames(lst):
"""Find the fullnames for a list committer names."""
counts = {}
for committer in lst:
fullname = extract_fullname(committer)
counts.setdefault(fullname, 0)
counts[fullname] += 1
return sorted(((count, name) for name,count in counts.iteritems()), reverse=True)
def collapse_by_author(committers):
"""The committers list is sorted by email, fix it up by author.
Some people commit with a similar username, but different email
address. Which makes it hard to sort out when they have multiple
entries. Email is actually more stable, though, since people
frequently forget to set their name properly.
So take the most common username for each email address, and
combine them into one new list.
"""
# Just an indirection so that multiple names can reference
# the same record information
name_to_counter = {}
# indirection back to real information
# [[full_rev_list], {email:count}, {fname:count}]
counter_to_info = {}
counter = 0
for email, revs in committers.iteritems():
fullnames = find_fullnames(rev.committer for rev in revs)
match = None
for count, fullname in fullnames:
if fullname and fullname in name_to_counter:
# We found a match
match = name_to_counter[fullname]
break
if match:
# One of the names matched, we need to collapse to records
record = counter_to_info[match]
record[0].extend(revs)
record[1][email] = len(revs)
for count, fullname in fullnames:
name_to_counter[fullname] = match
record[2].setdefault(fullname, 0)
record[2][fullname] += count
else:
# just add this one to the list
counter += 1
for count, fullname in fullnames:
if fullname:
name_to_counter[fullname] = counter
fname_map = dict((fullname, count) for count, fullname in fullnames)
counter_to_info[counter] = [revs, {email:len(revs)}, fname_map]
return sorted(((len(revs), revs, email, fname)
for revs, email, fname in counter_to_info.values()), reverse=True)
def sort_by_committer(a_repo, revids):
committers = {}
pb = bzrlib.ui.ui_factory.nested_progress_bar()
try:
pb.note('getting revisions')
revisions = a_repo.get_revisions(revids)
for count, rev in enumerate(revisions):
pb.update('checking', count, len(revids))
try:
email = extract_email_address(rev.committer)
except errors.BzrError:
email = rev.committer
committers.setdefault(email, []).append(rev)
finally:
pb.finished()
return committers
def get_info(a_repo, revision):
"""Get all of the information for a particular revision"""
pb = bzrlib.ui.ui_factory.nested_progress_bar()
a_repo.lock_read()
try:
pb.note('getting ancestry')
ancestry = a_repo.get_ancestry(revision)[1:]
committers = sort_by_committer(a_repo, ancestry)
finally:
a_repo.unlock()
pb.finished()
return collapse_by_author(committers)
def get_diff_info(a_repo, start_rev, end_rev):
"""Get only the info for new revisions between the two revisions
This lets us figure out what has actually changed between 2 revisions.
"""
pb = bzrlib.ui.ui_factory.nested_progress_bar()
committers = {}
a_repo.lock_read()
try:
pb.note('getting ancestry 1')
start_ancestry = set(a_repo.get_ancestry(start_rev))
pb.note('getting ancestry 2')
ancestry = a_repo.get_ancestry(end_rev)[1:]
ancestry = [rev for rev in ancestry if rev not in start_ancestry]
pb.note('getting revisions')
revisions = a_repo.get_revisions(ancestry)
for count, rev in enumerate(revisions):
pb.update('checking', count, len(ancestry))
try:
email = extract_email_address(rev.committer)
except errors.BzrError:
email = rev.committer
committers.setdefault(email, []).append(rev)
finally:
a_repo.unlock()
pb.finished()
info = collapse_by_author(committers)
return info
def display_info(info, to_file):
"""Write out the information"""
for count, revs, emails, fullnames in info:
# Get the most common email name
sorted_emails = sorted(((count, email)
for email,count in emails.iteritems()),
reverse=True)
sorted_fullnames = sorted(((count, fullname)
for fullname,count in fullnames.iteritems()),
reverse=True)
to_file.write('%4d %s <%s>\n'
% (count, sorted_fullnames[0][1],
sorted_emails[0][1]))
if len(sorted_fullnames) > 1:
print ' Other names:'
for count, fname in sorted_fullnames[1:]:
to_file.write(' %4d ' % (count,))
if fname == '':
to_file.write("''\n")
else:
to_file.write("%s\n" % (fname,))
if len(sorted_emails) > 1:
print ' Other email addresses:'
for count, email in sorted_emails:
to_file.write(' %4d ' % (count,))
if email == '':
to_file.write("''\n")
else:
to_file.write("%s\n" % (email,))
class cmd_statistics(bzrlib.commands.Command):
"""Generate statistics for LOCATION."""
aliases = ['stats']
takes_args = ['location?']
takes_options = ['revision']
encoding_type = 'replace'
def run(self, location='.', revision=None):
alternate_rev = None
try:
wt = WorkingTree.open_containing(location)[0]
except errors.NoWorkingTree:
a_branch = Branch.open(location)
last_rev = a_branch.last_revision()
else:
a_branch = wt.branch
last_rev = wt.last_revision()
if revision is not None:
last_rev = revision[0].in_history(a_branch).rev_id
if len(revision) > 1:
alternate_rev = revision[1].in_history(a_branch).rev_id
a_branch.lock_read()
try:
if alternate_rev:
info = get_diff_info(a_branch.repository, last_rev,
alternate_rev)
else:
info = get_info(a_branch.repository, last_rev)
finally:
a_branch.unlock()
display_info(info, self.outf)
bzrlib.commands.register_command(cmd_statistics)
class cmd_ancestor_growth(bzrlib.commands.Command):
"""Figure out the ancestor graph for LOCATION"""
takes_args = ['location?']
encoding_type = 'replace'
def run(self, location='.'):
try:
wt = WorkingTree.open_containing(location)[0]
except errors.NoWorkingTree:
a_branch = Branch.open(location)
last_rev = a_branch.last_revision()
else:
a_branch = wt.branch
last_rev = wt.last_revision()
a_branch.lock_read()
try:
graph = a_branch.repository.get_revision_graph(last_rev)
finally:
a_branch.unlock()
revno = 0
cur_parents = 0
sorted_graph = tsort.merge_sort(graph.iteritems(), last_rev)
for num, node_name, depth, isend in reversed(sorted_graph):
cur_parents += 1
if depth == 0:
revno += 1
self.outf.write('%4d, %4d\n' % (revno, cur_parents))
bzrlib.commands.register_command(cmd_ancestor_growth)
def test_suite():
from unittest import TestSuite
from bzrlib.tests import TestLoader
import test_stats
suite = TestSuite()
loader = TestLoader()
testmod_names = ['test_stats']
suite.addTest(loader.loadTestsFromModuleNames(['%s.%s' % (__name__, i) for i in testmod_names]))
return suite
|