File: print_stdlib_amalgamation.py

package info (click to toggle)
chromium 139.0.7258.127-1
  • links: PTS, VCS
  • area: main
  • in suites:
  • size: 6,122,068 kB
  • sloc: cpp: 35,100,771; ansic: 7,163,530; javascript: 4,103,002; python: 1,436,920; asm: 946,517; xml: 746,709; pascal: 187,653; perl: 88,691; sh: 88,436; objc: 79,953; sql: 51,488; cs: 44,583; fortran: 24,137; makefile: 22,147; tcl: 15,277; php: 13,980; yacc: 8,984; ruby: 7,485; awk: 3,720; lisp: 3,096; lex: 1,327; ada: 727; jsp: 228; sed: 36
file content (151 lines) | stat: -rwxr-xr-x 4,255 bytes parent folder | download | duplicates (6)
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
#!/usr/bin/env vpython3
# Copyright 2025 The Chromium Authors
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.

# Prints all of the Chrome tracing stdlib as an amalgamation (a single
# PerfettoSQL source which includes all transitive dependencies).
#
# All "CREATE PERFETTO" instructions are also going to be replaced with
# "CREATE OR REPLACE PERFETTO" instructions to ensure that the amalgamation
# can be used on top of existing stdlib.
#
# Usage: print_stdlib_amalgamation.py [chrome.module1 chrome.module2 ...]

from dataclasses import dataclass
from typing import Collection, Dict, List, Set
from pathlib import Path
import os
import re
import sys

CHROME_STDLIB_DIR = Path(
    os.path.dirname(__file__)) / '../../base/tracing/stdlib'


def ReadStdlib(path: Path) -> Dict[str, str]:
  """Reads all of the SQL modules in the given directory.

  Args:
    path: The path to the directory containing the SQL modules.

  Returns:
    A dictionary mapping module names to their contents.
  """
  result = {}
  for root, _, files in os.walk(path):
    for file in files:
      if not file.endswith('.sql'):
        continue
      with open(os.path.join(root, file)) as f:
        module = os.path.join(os.path.relpath(root, path),
                              file.removesuffix('.sql')).replace(
                                  os.path.sep, '.')
        result[module] = f.read()
  return result


@dataclass
class Module:
  """A class representing a parsed SQL module."""
  name: str
  includes: List[str]
  content: str


def ParseModule(name: str, content: str,
                known_stdlib_modules: Collection[str]) -> Module:
  """
  Parses a given SQL modules, resolving includes and updating
  CREATE PERFETTO ... statements to CREATE OR REPLACE.

  Args:
    name: name of the module.
    content: raw contents of the module.
    known_stdlib_modules: a list of known stdlib modules.

  Returns:
    A parsed Module object.
  """
  includes = []

  def ReplaceInclude(match):
    included_module = match.group(1)
    if included_module in known_stdlib_modules:
      includes.append(included_module)
      return ''
    return match.group(0)

  content = re.sub(r'INCLUDE PERFETTO MODULE ([\w\.]*);', ReplaceInclude,
                   content)
  content = content.replace('CREATE PERFETTO', 'CREATE OR REPLACE PERFETTO')
  # If the module doesn't end with a semicolon, add one to terminate the statement.
  if not content.strip().endswith(';'):
    content += ';'
  return Module(name, includes, content)


def ParseModules(stdlib: Dict[str, str]) -> List[Module]:
  """
  Parses the given SQL modules, resolving includes and updating
  CREATE PERFETTO ... statements to CREATE OR REPLACE.

  Args:
    stdlib: A dictionary mapping module names to their contents.

  Returns:
    A list of Module objects, each representing a parsed module.
  """
  return [
      ParseModule(name, content, stdlib.keys())
      for name, content in stdlib.items()
  ]


def SortModules(stdlib: List[Module],
                targets: List[str] | None = None) -> List[Module]:
  """
  Topologically sorts the given modules based on their includes.
  Assumes that there are no circular includes -- otherwise the behaviour is undefined.

  Args:
    stdlib: A list of Module objects.
    targets: A list of module names to sort. If None, all modules will be sorted.

  Returns:
    A list of Module objects, sorted in topological order.
  """
  modules_by_name = {m.name: m for m in stdlib}
  result = []
  visited = set()

  def AddModule(module: Module):
    if module.name in visited:
      return
    visited.add(module.name)
    for include in module.includes:
      AddModule(modules_by_name[include])
    result.append(module)

  if targets is None:
    targets = stdlib.keys()
  for target in targets:
    AddModule(modules_by_name[target])
  return result


def PrintModules(modules: List[Module]):
  for m in modules:
    print()
    print()
    print('--')
    print('--', m.name)
    print('--')
    print()
    print()
    print(m.content)


if __name__ == '__main__':
  chrome_stdlib = ReadStdlib(CHROME_STDLIB_DIR)
  PrintModules(SortModules(ParseModules(chrome_stdlib), sys.argv[1:] or None))