beenull/ladybird
1
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2024-11-22 15:40:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

test_pdf.py: Output tweaks

Browse source 
* Count files that are password-protected
* Use `pdf --json` to groups by missing feature and then by file
  instead of by file first, feature second
* Count files that render with issues
* Print number of files without issues last
* Always print all crash stacks
This commit is contained in:
Nico Weber 2023-11-09 22:02:54 +01:00 committed by Andreas Kling
parent ed7549c64f
commit 8f4966fc5c
Notes: sideshowbarker 2024-07-17 05:02:42 +09:00 
Author: https://github.com/nico
Commit: https://github.com/SerenityOS/serenity/commit/8f4966fc5c
Pull-request: https://github.com/SerenityOS/serenity/pull/21862
1 changed files with 55 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

65
Meta/test_pdf.py
View file

@ -14,7 +14,9 @@ One of those zip files in unzipped makes for a good input folder.
import argparse
import collections
import dataclasses
import glob
import json
import multiprocessing
import os
import random
@ -26,6 +28,14 @@ Result = collections.namedtuple(
'Result', ['filename', 'returncode', 'stdout', 'stderr'])
@dataclasses.dataclass
class Issues:
filenames: [str]
filename_to_issues: {str: [int]}
num_pages: int
count: int
def elide_aslr(s):
return re.sub(rb'\b0x[0-9a-f]+\b', b'0xc3ns0r3d', s)
@ -36,7 +46,7 @@ def elide_parser_offset(s):
def test_pdf(filename):
pdf_path = os.path.join(os.path.dirname(__file__), '../Build/lagom/bin/pdf')
r = subprocess.run([pdf_path, '--debugging-stats', filename],
r = subprocess.run([pdf_path, '--debugging-stats', '--json', filename],
capture_output=True)
return Result(filename, r.returncode, r.stdout,
elide_parser_offset(elide_aslr(r.stderr)))
@ -60,15 +70,29 @@ def main():
results = multiprocessing.Pool().map(test_pdf, files)
num_files_without_issues = 0
num_files_with_password = 0
num_files_with_issues = 0
failed_files = []
num_crashes = 0
stack_to_files = {}
issues = {}
for r in results:
print(r.filename)
print(r.stdout.decode('utf-8'))
if r.returncode == 0:
if b'no issues found' in r.stdout:
if b'PDF requires password' in r.stderr:
num_files_with_password += 1
continue
j = json.loads(r.stdout.decode('utf-8'))
if not j['issues']:
num_files_without_issues += 1
else:
num_files_with_issues += 1
for diag in j['issues']:
issue = issues.setdefault(diag, Issues([], {}, 0, 0))
issue.filenames.append(r.filename)
issue.filename_to_issues[r.filename] = j['issues'][diag]
issue.num_pages += len(j['issues'][diag])
issue.count += sum(a * b for (a, b) in j['issues'][diag])
continue
if r.returncode == 1:
failed_files.append(r.filename)
@ -76,10 +100,26 @@ def main():
num_crashes += 1
stack_to_files.setdefault(r.stderr, []).append(r.filename)
print('Top 5 crashiest stacks')
percent = 100 * num_files_with_issues / len(results)
print(f'{len(issues)} distinct issues, in {num_files_with_issues} files ({percent}%):')
issue_keys = list(issues.keys())
issue_keys.sort(reverse=True, key=lambda x: len(issues[x].filenames))
for issue_key in issue_keys:
issue = issues[issue_key]
print(issue_key, end='')
print(f', in {len(issue.filenames)} files, on {issue.num_pages} pages, {issue.count} times')
filenames = sorted(issue.filenames, reverse=True, key=lambda x: len(issue.filename_to_issues[x]))
for filename in filenames:
page_counts = issue.filename_to_issues[filename]
page_counts = ' '.join([f'{page} ({count}x)' if count > 1 else f'{page}' for (page, count) in page_counts])
print(f' {filename} {page_counts}')
print()
print()
print('Stacks:')
keys = list(stack_to_files.keys())
keys.sort(key=lambda x: len(stack_to_files[x]), reverse=True)
for stack in reversed(keys[:5]):
for stack in reversed(keys):
files = stack_to_files[stack]
print(stack.decode('utf-8', 'backslashreplace'), end='')
print(f'In {len(files)} files:')
@ -87,10 +127,6 @@ def main():
print(f' {file}')
print()
percent = 100 * num_files_without_issues / len(results)
print(f'{num_files_without_issues} files without issues ({percent:.1f}%)')
print()
percent = 100 * num_crashes / len(results)
print(f'{num_crashes} crashes ({percent:.1f}%)')
print(f'{len(keys)} distinct crash stacks')
@ -100,6 +136,15 @@ def main():
print(f'{len(failed_files)} failed to open ({percent:.1f}%)')
for f in failed_files:
print(f' {f}')
print()
percent = 100 * num_files_with_password / len(results)
print(f'{num_files_with_password} files with password ({percent:.1f}%)')
print()
percent = 100 * num_files_without_issues / len(results)
print(f'{num_files_without_issues} files without issues ({percent:.1f}%)')
print()
if __name__ == '__main__':