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
|
"""Coverage data for Coverage."""
import os
from coverage.backward import pickle, sorted # pylint: disable=W0622
class CoverageData(object):
"""Manages collected coverage data, including file storage.
The data file format is a pickled dict, with these keys:
* collector: a string identifying the collecting software
* lines: a dict mapping filenames to sorted lists of line numbers
executed:
{ 'file1': [17,23,45], 'file2': [1,2,3], ... }
* arcs: a dict mapping filenames to sorted lists of line number pairs:
{ 'file1': [(17,23), (17,25), (25,26)], ... }
"""
def __init__(self, basename=None, collector=None):
"""Create a CoverageData.
`basename` is the name of the file to use for storing data.
`collector` is a string describing the coverage measurement software.
"""
self.collector = collector or 'unknown'
self.use_file = True
# Construct the filename that will be used for data file storage, if we
# ever do any file storage.
self.filename = basename or ".coverage"
self.filename = os.path.abspath(self.filename)
# A map from canonical Python source file name to a dictionary in
# which there's an entry for each line number that has been
# executed:
#
# {
# 'filename1.py': { 12: None, 47: None, ... },
# ...
# }
#
self.lines = {}
# A map from canonical Python source file name to a dictionary with an
# entry for each pair of line numbers forming an arc:
#
# {
# 'filename1.py': { (12,14): None, (47,48): None, ... },
# ...
# }
#
self.arcs = {}
self.os = os
self.sorted = sorted
self.pickle = pickle
def usefile(self, use_file=True):
"""Set whether or not to use a disk file for data."""
self.use_file = use_file
def read(self):
"""Read coverage data from the coverage data file (if it exists)."""
if self.use_file:
self.lines, self.arcs = self._read_file(self.filename)
else:
self.lines, self.arcs = {}, {}
def write(self, suffix=None):
"""Write the collected coverage data to a file.
`suffix` is a suffix to append to the base file name. This can be used
for multiple or parallel execution, so that many coverage data files
can exist simultaneously. A dot will be used to join the base name and
the suffix.
"""
if self.use_file:
filename = self.filename
if suffix:
filename += "." + suffix
self.write_file(filename)
def erase(self):
"""Erase the data, both in this object, and from its file storage."""
if self.use_file:
if self.filename and os.path.exists(self.filename):
os.remove(self.filename)
self.lines = {}
self.arcs = {}
def line_data(self):
"""Return the map from filenames to lists of line numbers executed."""
return dict(
[(f, self.sorted(lmap.keys())) for f, lmap in self.lines.items()]
)
def arc_data(self):
"""Return the map from filenames to lists of line number pairs."""
return dict(
[(f, self.sorted(amap.keys())) for f, amap in self.arcs.items()]
)
def write_file(self, filename):
"""Write the coverage data to `filename`."""
# Create the file data.
data = {}
data['lines'] = self.line_data()
arcs = self.arc_data()
if arcs:
data['arcs'] = arcs
if self.collector:
data['collector'] = self.collector
# Write the pickle to the file.
fdata = open(filename, 'wb')
try:
self.pickle.dump(data, fdata, 2)
finally:
fdata.close()
def read_file(self, filename):
"""Read the coverage data from `filename`."""
self.lines, self.arcs = self._read_file(filename)
def raw_data(self, filename):
"""Return the raw pickled data from `filename`."""
fdata = open(filename, 'rb')
try:
data = pickle.load(fdata)
finally:
fdata.close()
return data
def _read_file(self, filename):
"""Return the stored coverage data from the given file.
Returns two values, suitable for assigning to `self.lines` and
`self.arcs`.
"""
lines = {}
arcs = {}
try:
data = self.raw_data(filename)
if isinstance(data, dict):
# Unpack the 'lines' item.
lines = dict([
(f, dict.fromkeys(linenos, None))
for f, linenos in data.get('lines', {}).items()
])
# Unpack the 'arcs' item.
arcs = dict([
(f, dict.fromkeys(arcpairs, None))
for f, arcpairs in data.get('arcs', {}).items()
])
except Exception:
pass
return lines, arcs
def combine_parallel_data(self):
"""Combine a number of data files together.
Treat `self.filename` as a file prefix, and combine the data from all
of the data files starting with that prefix plus a dot.
"""
data_dir, local = os.path.split(self.filename)
localdot = local + '.'
for f in os.listdir(data_dir or '.'):
if f.startswith(localdot):
full_path = os.path.join(data_dir, f)
new_lines, new_arcs = self._read_file(full_path)
for filename, file_data in new_lines.items():
self.lines.setdefault(filename, {}).update(file_data)
for filename, file_data in new_arcs.items():
self.arcs.setdefault(filename, {}).update(file_data)
if f != local:
os.remove(full_path)
def add_line_data(self, line_data):
"""Add executed line data.
`line_data` is { filename: { lineno: None, ... }, ...}
"""
for filename, linenos in line_data.items():
self.lines.setdefault(filename, {}).update(linenos)
def add_arc_data(self, arc_data):
"""Add measured arc data.
`arc_data` is { filename: { (l1,l2): None, ... }, ...}
"""
for filename, arcs in arc_data.items():
self.arcs.setdefault(filename, {}).update(arcs)
def touch_file(self, filename):
"""Ensure that `filename` appears in the data, empty if needed."""
self.lines.setdefault(filename, {})
def measured_files(self):
"""A list of all files that had been measured."""
return list(self.lines.keys())
def executed_lines(self, filename):
"""A map containing all the line numbers executed in `filename`.
If `filename` hasn't been collected at all (because it wasn't executed)
then return an empty map.
"""
return self.lines.get(filename) or {}
def executed_arcs(self, filename):
"""A map containing all the arcs executed in `filename`."""
return self.arcs.get(filename) or {}
def add_to_hash(self, filename, hasher):
"""Contribute `filename`'s data to the Md5Hash `hasher`."""
hasher.update(self.executed_lines(filename))
hasher.update(self.executed_arcs(filename))
def summary(self, fullpath=False):
"""Return a dict summarizing the coverage data.
Keys are based on the filenames, and values are the number of executed
lines. If `fullpath` is true, then the keys are the full pathnames of
the files, otherwise they are the basenames of the files.
"""
summ = {}
if fullpath:
filename_fn = lambda f: f
else:
filename_fn = self.os.path.basename
for filename, lines in self.lines.items():
summ[filename_fn(filename)] = len(lines)
return summ
def has_arcs(self):
"""Does this data have arcs?"""
return bool(self.arcs)
if __name__ == '__main__':
# Ad-hoc: show the raw data in a data file.
import pprint, sys
covdata = CoverageData()
if sys.argv[1:]:
fname = sys.argv[1]
else:
fname = covdata.filename
pprint.pprint(covdata.raw_data(fname))
|
