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
|
#!/usr/bin/env python3
# Copyright 2023 The Chromium Authors
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
"""Scans components/autofill/core/browser/field_types.h for FieldTypes
and updates histograms that are calculated from this enum.
"""
import optparse
import os
import re
import sys
sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'common'))
import path_util
import update_histogram_enum
FIELD_TYPES_PATH = 'components/autofill/core/browser/field_types.h'
FIELD_PREDICTION_GROUPS_PATH = \
'components/autofill/core/browser/metrics/autofill_metrics.cc'
def ReadEnum(filename, first_line, last_line_exclusive):
"""Extracts an enum from a file.
Args:
filename: name of file to read.
first_line: prefix of a line where extracting values starts. Leading
whitespaces are ignored.
last_line_exclusive: prefix of a line before which extraction stops.
This means that the line matching this parameter is not considered
a valid enum entry that is returned. Leading whitespaces are ignored.
Returns:
Dictionary from enum ids (integers) to names (strings).
"""
# Read the enum FieldType as a list of lines.
before_enum = True
content = []
with open(path_util.GetInputFile(filename)) as f:
for line in f.readlines():
stripped_line = line.strip()
# Search for beginning of enum.
if before_enum:
if stripped_line.startswith(first_line):
before_enum = False
continue
# Terminate at end of enum.
if stripped_line.startswith(last_line_exclusive):
break
content.append(stripped_line)
ENUM_REGEX = re.compile(
r"""^\s*?(\w+)\s+= # capture the enum name
\s+(\d+)(?:,.*)?$ # capture the id
""", re.VERBOSE)
enums = {}
for line in content:
enum_match = ENUM_REGEX.search(line)
if enum_match:
enum_name = enum_match.group(1)
enum_id = int(enum_match.group(2))
enums[enum_id] = enum_name
return enums
def ReadFieldTypes(filename):
return ReadEnum(filename, 'enum FieldType {', 'MAX_VALID_FIELD_TYPE =')
def ReadFieldPredictionGroups(filename):
result = ReadEnum(filename, 'enum FieldTypeGroupForMetrics {',
'NUM_FIELD_TYPE_GROUPS_FOR_METRICS')
# Strip the GROUP_ prefix because it only adds clutter.
return {k: v.replace('GROUP_', '') for k, v in result.items()}
def GenerateAutofilledFieldUserEditingStatusByFieldType(server_field_types):
result = {}
for enum_id, enum_name in server_field_types.items():
result[16 * enum_id + 0] = f'{enum_name}: edited'
result[16 * enum_id + 1] = f'{enum_name}: accepted'
return result
def GenerateAutofillFieldPredictionQualityByFieldType():
groups = ReadFieldPredictionGroups(FIELD_PREDICTION_GROUPS_PATH)
result = {}
for enum_id, enum_name in groups.items():
result[256 * enum_id + 0] = f'{enum_name}: True Positive'
result[256 * enum_id + 1] = f'{enum_name}: True Negative (Ambiguous)'
result[256 * enum_id + 2] = f'{enum_name}: True Negative (Unknown)'
result[256 * enum_id + 3] = f'{enum_name}: True Negative (Empty)'
result[256 * enum_id + 4] = f'{enum_name}: False Positive (Mismatch)'
result[256 * enum_id + 5] = f'{enum_name}: False Positive (Ambiguous)'
result[256 * enum_id + 6] = f'{enum_name}: False Positive (Unknown)'
result[256 * enum_id + 7] = f'{enum_name}: False Positive (Empty)'
result[256 * enum_id + 8] = f'{enum_name}: False Negative (Mismatch)'
result[256 * enum_id + 9] = f'{enum_name}: False Negative (Unknown)'
return result
def GenerateAutofillDataUtilizationByFieldType(field_types):
result = {}
for enum_id, enum_name in field_types.items():
result[64 * enum_id +
0] = f'{enum_name}: Not autofilled or autofilled value edited'
result[64 * enum_id + 1] = f'{enum_name}: Autofilled value accepted'
return result
def GenerateFillingAcceptanceByFieldType(server_field_types):
result = {}
for enum_id, enum_name in server_field_types.items():
result[4 * enum_id + 0] = f'{enum_name}: Ignored'
result[4 * enum_id + 1] = f'{enum_name}: Accepted'
return result
if __name__ == '__main__':
server_field_types = ReadFieldTypes(FIELD_TYPES_PATH)
update_histogram_enum.UpdateHistogramFromDict(
'tools/metrics/histograms/metadata/autofill/enums.xml',
'AutofillFieldType', server_field_types, FIELD_TYPES_PATH,
os.path.basename(__file__))
update_histogram_enum.UpdateHistogramFromDict(
'tools/metrics/histograms/metadata/autofill/enums.xml',
'AutofilledFieldUserEditingStatusByFieldType',
GenerateAutofilledFieldUserEditingStatusByFieldType(server_field_types),
FIELD_TYPES_PATH, os.path.basename(__file__))
update_histogram_enum.UpdateHistogramFromDict(
'tools/metrics/histograms/metadata/autofill/enums.xml',
'AutofillFieldPredictionQualityByFieldType',
GenerateAutofillFieldPredictionQualityByFieldType(),
FIELD_PREDICTION_GROUPS_PATH, os.path.basename(__file__))
update_histogram_enum.UpdateHistogramFromDict(
'tools/metrics/histograms/metadata/autofill/enums.xml',
'AutofillDataUtilizationByFieldType',
GenerateAutofillDataUtilizationByFieldType(server_field_types),
FIELD_TYPES_PATH, os.path.basename(__file__))
update_histogram_enum.UpdateHistogramFromDict(
'tools/metrics/histograms/metadata/autofill/enums.xml',
'FillingAcceptanceByFieldType',
GenerateFillingAcceptanceByFieldType(server_field_types),
FIELD_TYPES_PATH, os.path.basename(__file__))
update_histogram_enum.UpdateHistogramFromDict(
'tools/metrics/histograms/metadata/autofill/histograms.xml',
'AutofillFieldType',
server_field_types,
FIELD_TYPES_PATH,
os.path.basename(__file__),
update_comment=False)
|
