File: split_enums.py

package info (click to toggle)
chromium 120.0.6099.224-1~deb11u1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 6,112,112 kB
  • sloc: cpp: 32,907,025; ansic: 8,148,123; javascript: 3,679,536; python: 2,031,248; asm: 959,718; java: 804,675; xml: 617,256; sh: 111,417; objc: 100,835; perl: 88,443; cs: 53,032; makefile: 29,579; fortran: 24,137; php: 21,162; tcl: 21,147; sql: 20,809; ruby: 17,735; pascal: 12,864; yacc: 8,045; lisp: 3,388; lex: 1,323; ada: 727; awk: 329; jsp: 267; csh: 117; exp: 43; sed: 37
file content (179 lines) | stat: -rwxr-xr-x 5,954 bytes parent folder | download
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
#!/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.
"""
Extracts enums.xml to separate files.

Usage:
  tools/metrics/histograms/split_enums.py <dir_name>

Where <dir_name> is a subdirectory of tools/metrics/histograms/metadata/ where
a new enums.xml file should be populated from enums referenced by the
histograms.xml in that directory.
"""

import io
import logging
import os
import sys
from xml.dom import minidom

sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'common'))

import extract_histograms
import histogram_configuration_model
import histogram_paths
import merge_xml
import path_util

ENUMS_XML_TEMPLATE = """<!--
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.
-->

<!--

This file describes the enumerations referenced by entries in histograms.xml for
this directory. Some enums may instead be listed in the central enums.xml file
at src/tools/metrics/histograms/enums.xml when multiple files use them.

For best practices on writing enumerations descriptions, see
https://chromium.googlesource.com/chromium/src.git/+/HEAD/tools/metrics/histograms/README.md#Enum-Histograms

Please follow the instructions in the OWNERS file in this directory to find a
reviewer. If no OWNERS file exists, please consider signing up at
go/reviewing-metrics (Googlers only), as all subdirectories are expected to
have an OWNERS file. As a last resort you can send the CL to
chromium-metrics-reviews@google.com.
-->

<histogram-configuration>

<!-- Enum types -->

<enums>


</enums>

</histogram-configuration>
"""


def _get_enums_from_files(files):
  """Finds the names of all referenced enums from the specified XML files."""
  merged = merge_xml.MergeFiles(files)
  histograms, _ = extract_histograms.ExtractHistogramsFromDom(merged)
  enums_used_in_file = set()
  for histogram_name, data in histograms.items():
    # Skip non-enum histograms.
    if 'enum' not in data:
      continue
    enum_name = data['enum']['name']
    enums_used_in_file.add(enum_name)
  return enums_used_in_file


def _extract_enum_nodes_by_names(enum_names):
  """Returns the <enum> nodes corresponding to the specified names."""
  with io.open(histogram_paths.ENUMS_XML, 'r', encoding='utf-8') as f:
    document = minidom.parse(f)

  enum_nodes = []
  for enum_node in document.getElementsByTagName('enum'):
    if enum_node.attributes['name'].value in enum_names:
      enum_nodes.append(enum_node)

  for node in enum_nodes:
    node.parentNode.removeChild(node)

  xml_with_nodes_removed = histogram_configuration_model.PrettifyTree(document)
  return enum_nodes, xml_with_nodes_removed


def _read_enums_xml_or_blank_template(path):
  """Reads the enums XML file as minidom or a blank template if not found."""
  if not os.path.isfile(path):
    print(f'No existing file at {path}, creating it.')
    return minidom.parseString(ENUMS_XML_TEMPLATE)
  with io.open(path, 'r', encoding='utf-8') as f:
    print(f'Oppening existing file {path}...')
    return minidom.parse(f)


def _move_enums_to_file(enum_nodes, enums_file):
  """Adds enum nodes to `enums_file` and returns the updated XML."""
  document = _read_enums_xml_or_blank_template(enums_file)
  enums_node = document.getElementsByTagName('enums')[0]
  for node in enum_nodes:
    enums_node.appendChild(document.importNode(node, True))
  return histogram_configuration_model.PrettifyTree(document)


def _split_enums(dir_name):
  """Splits out an enums.xml file in the specified directory."""
  histograms_file = path_util.GetInputFile(
      f'tools/metrics/histograms/metadata/{dir_name}/histograms.xml')
  if not os.path.isfile(histograms_file):
    print(f'File {histograms_file} not found! Exiting.')
    return

  enums_file = path_util.GetInputFile(
      f'tools/metrics/histograms/metadata/{dir_name}/enums.xml')

  print(f'Reading XML files...')

  # Get the enums referenced by the given histograms.xml file.
  relevant_files = [histograms_file, histogram_paths.ENUMS_XML]
  if os.path.isfile(enums_file):
    relevant_files.append(enums_file)
  enum_names = _get_enums_from_files(relevant_files)

  # Only move enums that aren't referenced by other files.
  all_enum_names = _get_enums_from_files(
      [f for f in histogram_paths.ALL_XMLS if f != histograms_file])
  candidate_enum_names = enum_names - all_enum_names
  print(f'Found {len(candidate_enum_names)} candidate enums.')

  enum_nodes, updated_full_xml = _extract_enum_nodes_by_names(
      candidate_enum_names)
  # There may be fewer, when some of the enums are not in the common enums.xml
  # file (for example, they may be in the target file already).
  assert len(enum_nodes) <= len(candidate_enum_names)
  print(f'Of these, {len(enum_nodes)} are in the common enums.xml file.')

  new_enums_xml = _move_enums_to_file(enum_nodes, enums_file)

  enums_file_did_not_exist = not os.path.isfile(enums_file)
  print(f'Writing updated file: {enums_file}')
  with open(enums_file, 'w') as f:
    f.write(new_enums_xml)
  print(f'Writing updated file: {histogram_paths.ENUMS_XML}')
  with open(histogram_paths.ENUMS_XML, 'w') as f:
    f.write(updated_full_xml)

  print('')
  print(f'Moved {len(enum_nodes)} to {enums_file}.')
  print('')

  if enums_file_did_not_exist:
    print('Please run `git add` on the new enums.xml file:')
    print(f'  git add {enums_file}')
    print('')
    print('IMPORTANT: You must also manually add the new file to:')
    print('  tools/metrics/histograms/histograms_index.txt')
    print('  components/metrics/generate_expired_histograms_array.gni')


def main():
  logging.basicConfig(format='%(levelname)s: %(message)s', level=logging.INFO)
  if len(sys.argv) != 2:
    print('Usage split_enums.py <dir_name>')
    return
  _split_enums(sys.argv[1])


if __name__ == '__main__':
  main()