From mboxrd@z Thu Jan 1 00:00:00 1970 From: Thomas Petazzoni Date: Thu, 15 Feb 2018 23:03:41 +0100 Subject: [Buildroot] [PATCH next 1/5] support/scripts/pkg-stats-new: rewrite in Python In-Reply-To: <20180215220345.8532-1-thomas.petazzoni@bootlin.com> References: <20180215220345.8532-1-thomas.petazzoni@bootlin.com> Message-ID: <20180215220345.8532-2-thomas.petazzoni@bootlin.com> List-Id: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: buildroot@busybox.net This commit adds a new version of the pkg-stats script, rewritten in Python. It is for now implemented in a separate file called, pkg-stats-new, in order to make the diff easily readable. A future commit will rename it to pkg-stats. Compared to the existing shell-based pkg-stats script, the functionality and output is basically the same. The main difference is that the output no longer goes to stdout, but to the file passed as argument using the -o option. This allows stdout to be used for more debugging related information. The way the script works is that a first function get_pkglist() creates a dict associating package names with an instance of a Package() object, containing basic information about the package. Then a number of other functions (add_infra_info, add_pkg_make_info, add_hash_info, add_patch_count, add_check_package_warnings) will calculate additional information about packages, and fill in fields in the Package objects. calculate_stats() then calculates global statistics (how packages have license information, how packages have a hash file, etc.). Finally, dump_html() produces the HTML output, using a number of sub-functions. Signed-off-by: Thomas Petazzoni --- support/scripts/pkg-stats-new | 424 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 424 insertions(+) create mode 100755 support/scripts/pkg-stats-new diff --git a/support/scripts/pkg-stats-new b/support/scripts/pkg-stats-new new file mode 100755 index 0000000000..a5e056a948 --- /dev/null +++ b/support/scripts/pkg-stats-new @@ -0,0 +1,424 @@ +#!/usr/bin/env python + +import argparse +import fnmatch +import os +from collections import defaultdict +import re +import subprocess +import sys + +class Package: + def __init__(self, name): + self.name = name + self.path = None + self.infras = None + self.has_license = False + self.has_license_files = False + self.has_hash = False + self.patch_count = 0 + self.warnings = 0 + def __str__(self): + return "%s (path='%s', license='%s', license_files='%s', hash='%s', patches=%d)" % \ + (self.name, self.path, self.has_license, self.has_license_files, self.has_hash, self.patch_count) + +# +# Builds the list of Buildroot packages, returning a dict, where the +# key is the package name, and the value is an instance of the Package +# object. Only the .name and .path fields of the Package object are +# initialized. +# +# npackages: limit to N packages +# package_list: limit to those packages in this list +# +def get_pkglist(): + WALK_USEFUL_SUBDIRS = ["boot", "linux", "package", "toolchain"] + WALK_EXCLUDES = [ "boot/common.mk", + "linux/linux-ext-.*.mk", + "package/freescale-imx/freescale-imx.mk", + "package/gcc/gcc.mk", + "package/gstreamer/gstreamer.mk", + "package/gstreamer1/gstreamer1.mk", + "package/gtk2-themes/gtk2-themes.mk", + "package/matchbox/matchbox.mk", + "package/opengl/opengl.mk", + "package/qt5/qt5.mk", + "package/x11r7/x11r7.mk", + "package/doc-asciidoc.mk", + "package/pkg-.*.mk", + "package/nvidia-tegra23/nvidia-tegra23.mk", + "toolchain/toolchain-external/pkg-toolchain-external.mk", + "toolchain/toolchain-external/toolchain-external.mk", + "toolchain/toolchain.mk", + "toolchain/helpers.mk", + "toolchain/toolchain-wrapper.mk" ] + packages = dict() + for root, dirs, files in os.walk("."): + rootdir = root.split("/") + if len(rootdir) < 2: + continue + if rootdir[1] not in WALK_USEFUL_SUBDIRS: + continue + for f in files: + if not f.endswith(".mk"): + continue + # Strip ending ".mk" + pkgname = f[:-3] + pkgpath = os.path.join(root, f) + skip = False + for exclude in WALK_EXCLUDES: + # pkgpath[2:] strips the initial './' + if re.match(exclude, pkgpath[2:]): + skip = True + continue + if skip: + continue + p = Package(pkgname) + p.path = pkgpath + packages[pkgname] = p + return packages + +INFRA_RE = re.compile("\$\(eval \$\(([a-z-]*)-package\)\)") + +def get_pkg_infra_info(pkgpath): + infras = list() + with open(pkgpath, 'r') as f: + lines = f.readlines() + for l in lines: + match = INFRA_RE.match(l) + if not match: + continue + infra = match.group(1) + if infra.startswith("host-"): + infras.append(("host", infra[5:])) + else: + infras.append(("target", infra)) + return infras + +# Fills in the .infras field of all Package objects +def add_infra_info(packages): + for name, pkg in packages.iteritems(): + pkg.infras = get_pkg_infra_info(pkg.path) + +def pkgname_to_pkgvar(pkgname): + return pkgname.upper().replace("-", "_") + +# Fills in the .has_license and .has_license_files fields of all +# Package objects +def add_pkg_make_info(packages): + licenses = list() + license_files = list() + + # Licenses + o = subprocess.check_output(["make", "-s", "printvars", "VARS=%_LICENSE"]) + for l in o.splitlines(): + # Get variable name and value + pkgvar, value = l.split("=") + + # If present, strip HOST_ from variable name + if pkgvar.startswith("HOST_"): + pkgvar = pkgvar[5:] + + # Strip _LICENSE + pkgvar = pkgvar[:-8] + + # If value is "unknown", no license details available + if value == "unknown": + continue + licenses.append(pkgvar) + + # License files + o = subprocess.check_output(["make", "-s", "printvars", "VARS=%_LICENSE_FILES"]) + for l in o.splitlines(): + # Get variable name and value + pkgvar, value = l.split("=") + + # If present, strip HOST_ from variable name + if pkgvar.startswith("HOST_"): + pkgvar = pkgvar[5:] + + if pkgvar.endswith("_MANIFEST_LICENSE_FILES"): + continue + + # Strip _LICENSE_FILES + pkgvar = pkgvar[:-14] + + license_files.append(pkgvar) + + for name, pkg in packages.iteritems(): + var = pkgname_to_pkgvar(name) + if var in licenses: + pkg.has_license = True + if var in license_files: + pkg.has_license_files = True + +# Fills in the .has_hash field of all Package objects +def add_hash_info(packages): + for name, pkg in packages.iteritems(): + hashpath = pkg.path.replace(".mk", ".hash") + pkg.has_hash = os.path.exists(hashpath) + +# Fills in the .patch_count field of all Package objects +def add_patch_count(packages): + for name, pkg in packages.iteritems(): + pkgdir = os.path.dirname(pkg.path) + pkg.patch_count = len(fnmatch.filter(os.listdir(pkgdir), '*.patch')) + +def get_check_package_warnings(pkgdir): + cmd = ["./utils/check-package"] + for root, dirs, files in os.walk(pkgdir): + for f in files: + if f.endswith(".mk") or f.endswith(".hash") or f == "Config.in" or f == "Config.in.host": + cmd.append(f) + o = subprocess.check_output(cmd, stderr=subprocess.STDOUT) + lines = o.splitlines() + for line in lines: + m = re.match("^([0-9]*) warnings generated", line) + if m: + return int(m.group(1)) + return None + +# Fills in the .warnings field of all Package objects +def add_check_package_warnings(packages): + for name, pkg in packages.iteritems(): + pkg.warnings = get_check_package_warnings(os.path.dirname(pkg.path)) + + +def calculate_stats(packages): + stats = defaultdict(int) + for name, pkg in packages.iteritems(): + # If packages have multiple infra, take the first one. For the + # vast majority of packages, the target and host infra are the + # same. There are very few packages that use a different infra + # for the host and target variants. + if len(pkg.infras) > 0: + infra = pkg.infras[0][1] + stats["infra-%s" % infra] += 1 + else: + stats["infra-unknown"] += 1 + if pkg.has_license: + stats["license"] += 1 + else: + stats["no-license"] += 1 + if pkg.has_license_files: + stats["license-files"] += 1 + else: + stats["no-license-files"] += 1 + if pkg.has_hash: + stats["hash"] += 1 + else: + stats["no-hash"] += 1 + stats["patches"] += pkg.patch_count + return stats + +html_header = """ + + + +Statistics of Buildroot packages + + +Results
+ +

+""" + +html_footer = """ + + + + +""" + +def infra_str(infra_list): + if not infra_list: + return "Unknown" + elif len(infra_list) == 1: + return "%s
%s" % (infra_list[0][1], infra_list[0][0]) + elif infra_list[0][1] == infra_list[1][1]: + return "%s
%s + %s" % \ + (infra_list[0][1], infra_list[0][0], infra_list[1][0]) + else: + return "%s (%s)
%s (%s)" % \ + (infra_list[0][1], infra_list[0][0], + infra_list[1][1], infra_list[1][0]) + +def boolean_str(b): + if b: + return "Yes" + else: + return "No" + +def dump_html_pkg(f, pkg): + f.write(" ") + f.write(" %s" % pkg.path[2:]) + + # Patch count + td_class = ["centered"] + if pkg.patch_count == 0: + td_class.append("nopatches") + elif pkg.patch_count < 5: + td_class.append("somepatches") + else: + td_class.append("lotsofpatches") + f.write(" %s" % + (" ".join(td_class), str(pkg.patch_count))) + + # Infrastructure + infra = infra_str(pkg.infras) + td_class = ["centered"] + if infra == "Unknown": + td_class.append("wrong") + else: + td_class.append("correct") + f.write(" %s" % \ + (" ".join(td_class), infra_str(pkg.infras))) + + # License + td_class = ["centered"] + if pkg.has_license: + td_class.append("correct") + else: + td_class.append("wrong") + f.write(" %s" % \ + (" ".join(td_class), boolean_str(pkg.has_license))) + + # License files + td_class = ["centered"] + if pkg.has_license_files: + td_class.append("correct") + else: + td_class.append("wrong") + f.write(" %s" % \ + (" ".join(td_class), boolean_str(pkg.has_license_files))) + + # Hash + td_class = ["centered"] + if pkg.has_hash: + td_class.append("correct") + else: + td_class.append("wrong") + f.write(" %s" % \ + (" ".join(td_class), boolean_str(pkg.has_hash))) + + # Warnings + td_class = ["centered"] + if pkg.warnings == 0: + td_class.append("correct") + else: + td_class.append("wrong") + f.write(" %d" % \ + (" ".join(td_class), pkg.warnings)) + + f.write(" ") + +def dump_html_all_pkgs(f, packages): + f.write(""" + + + + + + + + + +""") + for name, pkg in sorted(packages.iteritems()): + dump_html_pkg(f, pkg) + f.write("
PackagePatch countInfrastructureLicenseLicense filesHash fileWarnings
") + +def dump_html_stats(f, stats): + f.write("") + infras = [ infra[6:] for infra in stats.keys() if infra.startswith("infra-") ] + for infra in infras: + f.write("" % \ + (infra, stats["infra-%s" % infra])) + f.write("" % + stats["license"]) + f.write("" % + stats["no-license"]) + f.write("" % + stats["license-files"]) + f.write("" % + stats["no-license-files"]) + f.write("" % + stats["hash"]) + f.write("" % + stats["no-hash"]) + f.write("" % + stats["patches"]) + f.write("
Packages using the %s infrastructure%s
Packages having license information%s
Packages not having license information%s
Packages having license files information%s
Packages not having license files information%s
Packages having a hash file%s
Packages not having a hash file%s
Total number of patches%s
") + +def dump_html(packages, stats, output): + with open(output, 'w') as f: + f.write(html_header) + dump_html_all_pkgs(f, packages) + dump_html_stats(f, stats) + f.write(html_footer) + +def parse_args(): + parser = argparse.ArgumentParser() + parser.add_argument('-o', dest='output', action='store', required=True, + help='HTML output file') + return parser.parse_args() + +def __main__(): + args = parse_args() + print "Build package list ..." + packages = get_pkglist() + print "Get package infra ..." + add_infra_info(packages) + print "Get make info ..." + add_pkg_make_info(packages) + print "Get hash info ..." + add_hash_info(packages) + print "Get patch count ..." + add_patch_count(packages) + print "Get package warnings ..." + add_check_package_warnings(packages) + print "Calculate stats" + stats = calculate_stats(packages) + print "Write HTML" + dump_html(packages, stats, args.output) + +__main__() -- 2.14.3