diff options
Diffstat (limited to 'scripts/contrib/patchreview.py')
-rwxr-xr-x | scripts/contrib/patchreview.py | 88 |
1 files changed, 77 insertions, 11 deletions
diff --git a/scripts/contrib/patchreview.py b/scripts/contrib/patchreview.py index a4d5ba6867..bceae06561 100755 --- a/scripts/contrib/patchreview.py +++ b/scripts/contrib/patchreview.py @@ -1,10 +1,25 @@ #! /usr/bin/env python3 +# +# Copyright OpenEmbedded Contributors +# +# SPDX-License-Identifier: GPL-2.0-only +# + +import argparse +import collections +import json +import os +import os.path +import pathlib +import re +import subprocess # TODO # - option to just list all broken files # - test suite # - validate signed-off-by +status_values = ("accepted", "pending", "inappropriate", "backport", "submitted", "denied", "inactive-upstream") class Result: # Whether the patch has an Upstream-Status or not @@ -29,27 +44,25 @@ def blame_patch(patch): From a patch filename, return a list of "commit summary (author name <author email>)" strings representing the history. """ - import subprocess return subprocess.check_output(("git", "log", "--follow", "--find-renames", "--diff-filter=A", "--format=%s (%aN <%aE>)", "--", patch)).decode("utf-8").splitlines() def patchreview(patches): - import re # General pattern: start of line, optional whitespace, tag with optional # hyphen or spaces, maybe a colon, some whitespace, then the value, all case # insensitive. sob_re = re.compile(r"^[\t ]*(Signed[-_ ]off[-_ ]by:?)[\t ]*(.+)", re.IGNORECASE | re.MULTILINE) - status_re = re.compile(r"^[\t ]*(Upstream[-_ ]Status:?)[\t ]*(\w*)", re.IGNORECASE | re.MULTILINE) - status_values = ("accepted", "pending", "inappropriate", "backport", "submitted", "denied") + status_re = re.compile(r"^[\t ]*(Upstream[-_ ]Status:?)[\t ]*([\w-]*)", re.IGNORECASE | re.MULTILINE) cve_tag_re = re.compile(r"^[\t ]*(CVE:)[\t ]*(.*)", re.IGNORECASE | re.MULTILINE) cve_re = re.compile(r"cve-[0-9]{4}-[0-9]{4,6}", re.IGNORECASE) results = {} for patch in patches: + result = Result() results[patch] = result @@ -122,6 +135,8 @@ def analyse(results, want_blame=False, verbose=True): missing_status += 1 if r.malformed_upstream_status or r.unknown_upstream_status: malformed_status += 1 + # Count patches with no status as pending + pending_patches +=1 if r.missing_cve: missing_cve += 1 if r.upstream_status == "pending": @@ -132,7 +147,6 @@ def analyse(results, want_blame=False, verbose=True): need_blame = True if verbose: print("Missing Signed-off-by tag (%s)" % patch) - if r.malformed_sob: need_blame = True if verbose: @@ -185,27 +199,79 @@ Patches in Pending state: %s""" % (total_patches, def histogram(results): from toolz import recipes, dicttoolz import math + counts = recipes.countby(lambda r: r.upstream_status, results.values()) bars = dicttoolz.valmap(lambda v: "#" * int(math.ceil(float(v) / len(results) * 100)), counts) for k in bars: print("%-20s %s (%d)" % (k.capitalize() if k else "No status", bars[k], counts[k])) +def find_layers(candidate): + # candidate can either be the path to a layer directly (eg meta-intel), or a + # repository that contains other layers (meta-arm). We can determine what by + # looking for a conf/layer.conf file. If that file exists then it's a layer, + # otherwise its a repository of layers and we can assume they're called + # meta-*. + + if (candidate / "conf" / "layer.conf").exists(): + return [candidate.absolute()] + else: + return [d.absolute() for d in candidate.iterdir() if d.is_dir() and (d.name == "meta" or d.name.startswith("meta-"))] + +# TODO these don't actually handle dynamic-layers/ + +def gather_patches(layers): + patches = [] + for directory in layers: + filenames = subprocess.check_output(("git", "-C", directory, "ls-files", "recipes-*/**/*.patch", "recipes-*/**/*.diff"), universal_newlines=True).split() + patches += [os.path.join(directory, f) for f in filenames] + return patches + +def count_recipes(layers): + count = 0 + for directory in layers: + output = subprocess.check_output(["git", "-C", directory, "ls-files", "recipes-*/**/*.bb"], universal_newlines=True) + count += len(output.splitlines()) + return count if __name__ == "__main__": - import argparse, subprocess, os - args = argparse.ArgumentParser(description="Patch Review Tool") args.add_argument("-b", "--blame", action="store_true", help="show blame for malformed patches") args.add_argument("-v", "--verbose", action="store_true", help="show per-patch results") args.add_argument("-g", "--histogram", action="store_true", help="show patch histogram") - args.add_argument("directory", nargs="?", help="directory to scan") + args.add_argument("-j", "--json", help="update JSON") + args.add_argument("directory", type=pathlib.Path, metavar="DIRECTORY", help="directory to scan (layer, or repository of layers)") args = args.parse_args() - if args.directory: - os.chdir(args.directory) - patches = subprocess.check_output(("git", "ls-files", "recipes-*/**/*.patch", "recipes-*/**/*.diff")).decode("utf-8").split() + layers = find_layers(args.directory) + print(f"Found layers {' '.join((d.name for d in layers))}") + patches = gather_patches(layers) results = patchreview(patches) analyse(results, want_blame=args.blame, verbose=args.verbose) + + if args.json: + if os.path.isfile(args.json): + data = json.load(open(args.json)) + else: + data = [] + + row = collections.Counter() + row["total"] = len(results) + row["date"] = subprocess.check_output(["git", "-C", args.directory, "show", "-s", "--pretty=format:%cd", "--date=format:%s"], universal_newlines=True).strip() + row["commit"] = subprocess.check_output(["git", "-C", args.directory, "rev-parse", "HEAD"], universal_newlines=True).strip() + row['commit_count'] = subprocess.check_output(["git", "-C", args.directory, "rev-list", "--count", "HEAD"], universal_newlines=True).strip() + row['recipe_count'] = count_recipes(layers) + + for r in results.values(): + if r.upstream_status in status_values: + row[r.upstream_status] += 1 + if r.malformed_upstream_status or r.missing_upstream_status: + row['malformed-upstream-status'] += 1 + if r.malformed_sob or r.missing_sob: + row['malformed-sob'] += 1 + + data.append(row) + json.dump(data, open(args.json, "w"), sort_keys=True, indent="\t") + if args.histogram: print() histogram(results) |