support/scripts/pkg-stats: add latest upstream version information

This commit adds fetching the latest upstream version of each package
from release-monitoring.org.

The fetching process first tries to use the package mappings of the
"Buildroot" distribution [1]. This mapping mechanism allows to tell
release-monitoring.org what is the name of a package in a given
distribution/build-system. For example, the package xutil_util-macros
in Buildroot is named xorg-util-macros on release-monitoring.org. This
mapping can be seen in the section "Mappings" of
https://release-monitoring.org/project/15037/.

If there is no mapping, then it does a regular search, and within the
search results, looks for a package whose name matches the Buildroot
name.

Even though fetching from release-monitoring.org is a bit slow, using
multiprocessing.Pool has proven to not be reliable, with some requests
ending up with an exception. So we keep a serialized approach, but
with a single HTTPSConnectionPool() for all queries. Long term, we
hope to be able to use a database dump of release-monitoring.org
instead.

From an output point of view, the latest version column:

 - Is green when the version in Buildroot matches the latest upstream
   version

 - Is orange when the latest upstream version is unknown because the
   package was not found on release-monitoring.org

 - Is red when the version in Buildroot doesn't match the latest
   upstream version. Note that we are not doing anything smart here:
   we are just testing if the strings are equal or not.

 - The cell contains the link to the project on release-monitoring.org
   if found.

 - The cell indicates if the match was done using a distro mapping, or
   through a regular search.

[1] https://release-monitoring.org/distro/Buildroot/

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Tested-by: Matthew Weber <matthew.weber@rockwellcollins.com>
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
This commit is contained in:
Thomas Petazzoni 2019-02-05 16:19:59 +01:00
parent 4b530daf42
commit 2c74d0aabb

View File

@ -25,11 +25,19 @@ import re
import subprocess
import sys
import requests # URL checking
import json
import certifi
from urllib3 import HTTPSConnectionPool
from urllib3.exceptions import HTTPError
from multiprocessing import Pool
INFRA_RE = re.compile("\$\(eval \$\(([a-z-]*)-package\)\)")
URL_RE = re.compile("\s*https?://\S*\s*$")
RM_API_STATUS_ERROR = 1
RM_API_STATUS_FOUND_BY_DISTRO = 2
RM_API_STATUS_FOUND_BY_PATTERN = 3
RM_API_STATUS_NOT_FOUND = 4
class Package:
all_licenses = list()
@ -49,6 +57,7 @@ class Package:
self.url = None
self.url_status = None
self.url_worker = None
self.latest_version = (RM_API_STATUS_ERROR, None, None)
def pkgvar(self):
return self.name.upper().replace("-", "_")
@ -298,6 +307,73 @@ def check_package_urls(packages):
pkg.url_status = pkg.url_worker.get(timeout=3600)
def release_monitoring_get_latest_version_by_distro(pool, name):
try:
req = pool.request('GET', "/api/project/Buildroot/%s" % name)
except HTTPError:
return (RM_API_STATUS_ERROR, None, None)
if req.status != 200:
return (RM_API_STATUS_NOT_FOUND, None, None)
data = json.loads(req.data)
if 'version' in data:
return (RM_API_STATUS_FOUND_BY_DISTRO, data['version'], data['id'])
else:
return (RM_API_STATUS_FOUND_BY_DISTRO, None, data['id'])
def release_monitoring_get_latest_version_by_guess(pool, name):
try:
req = pool.request('GET', "/api/projects/?pattern=%s" % name)
except HTTPError:
return (RM_API_STATUS_ERROR, None, None)
if req.status != 200:
return (RM_API_STATUS_NOT_FOUND, None, None)
data = json.loads(req.data)
projects = data['projects']
projects.sort(key=lambda x: x['id'])
for p in projects:
if p['name'] == name and 'version' in p:
return (RM_API_STATUS_FOUND_BY_PATTERN, p['version'], p['id'])
return (RM_API_STATUS_NOT_FOUND, None, None)
def check_package_latest_version(packages):
"""
Fills in the .latest_version field of all Package objects
This field has a special format:
(status, version, id)
with:
- status: one of RM_API_STATUS_ERROR,
RM_API_STATUS_FOUND_BY_DISTRO, RM_API_STATUS_FOUND_BY_PATTERN,
RM_API_STATUS_NOT_FOUND
- version: string containing the latest version known by
release-monitoring.org for this package
- id: string containing the id of the project corresponding to this
package, as known by release-monitoring.org
"""
pool = HTTPSConnectionPool('release-monitoring.org', port=443,
cert_reqs='CERT_REQUIRED', ca_certs=certifi.where(),
timeout=30)
count = 0
for pkg in packages:
v = release_monitoring_get_latest_version_by_distro(pool, pkg.name)
if v[0] == RM_API_STATUS_NOT_FOUND:
v = release_monitoring_get_latest_version_by_guess(pool, pkg.name)
pkg.latest_version = v
print("[%d/%d] Package %s" % (count, len(packages), pkg.name))
count += 1
def calculate_stats(packages):
stats = defaultdict(int)
for pkg in packages:
@ -322,6 +398,16 @@ def calculate_stats(packages):
stats["hash"] += 1
else:
stats["no-hash"] += 1
if pkg.latest_version[0] == RM_API_STATUS_FOUND_BY_DISTRO:
stats["rmo-mapping"] += 1
else:
stats["rmo-no-mapping"] += 1
if not pkg.latest_version[1]:
stats["version-unknown"] += 1
elif pkg.latest_version[1] == pkg.current_version:
stats["version-uptodate"] += 1
else:
stats["version-not-uptodate"] += 1
stats["patches"] += pkg.patch_count
return stats
@ -354,6 +440,7 @@ td.somepatches {
td.lotsofpatches {
background: #ff9a69;
}
td.good_url {
background: #d2ffc4;
}
@ -363,6 +450,20 @@ td.missing_url {
td.invalid_url {
background: #ff9a69;
}
td.version-good {
background: #d2ffc4;
}
td.version-needs-update {
background: #ff9a69;
}
td.version-unknown {
background: #ffd870;
}
td.version-error {
background: #ccc;
}
</style>
<title>Statistics of Buildroot packages</title>
</head>
@ -465,6 +566,36 @@ def dump_html_pkg(f, pkg):
current_version = pkg.current_version
f.write(" <td class=\"centered\">%s</td>\n" % current_version)
# Latest version
if pkg.latest_version[0] == RM_API_STATUS_ERROR:
td_class.append("version-error")
if pkg.latest_version[1] is None:
td_class.append("version-unknown")
elif pkg.latest_version[1] != pkg.current_version:
td_class.append("version-needs-update")
else:
td_class.append("version-good")
if pkg.latest_version[0] == RM_API_STATUS_ERROR:
latest_version_text = "<b>Error</b>"
elif pkg.latest_version[0] == RM_API_STATUS_NOT_FOUND:
latest_version_text = "<b>Not found</b>"
else:
if pkg.latest_version[1] is None:
latest_version_text = "<b>Found, but no version</b>"
else:
latest_version_text = "<a href=\"https://release-monitoring.org/project/%s\"><b>%s</b></a>" % (pkg.latest_version[2], str(pkg.latest_version[1]))
latest_version_text += "<br/>"
if pkg.latest_version[0] == RM_API_STATUS_FOUND_BY_DISTRO:
latest_version_text += "found by <a href=\"https://release-monitoring.org/distro/Buildroot/\">distro</a>"
else:
latest_version_text += "found by guess"
f.write(" <td class=\"%s\">%s</td>\n" %
(" ".join(td_class), latest_version_text))
# Warnings
td_class = ["centered"]
if pkg.warnings == 0:
@ -502,6 +633,7 @@ def dump_html_all_pkgs(f, packages):
<td class=\"centered\">License files</td>
<td class=\"centered\">Hash file</td>
<td class=\"centered\">Current version</td>
<td class=\"centered\">Latest version</td>
<td class=\"centered\">Warnings</td>
<td class=\"centered\">Upstream URL</td>
</tr>
@ -532,6 +664,16 @@ def dump_html_stats(f, stats):
stats["no-hash"])
f.write(" <tr><td>Total number of patches</td><td>%s</td></tr>\n" %
stats["patches"])
f.write("<tr><td>Packages having a mapping on <i>release-monitoring.org</i></td><td>%s</td></tr>\n" %
stats["rmo-mapping"])
f.write("<tr><td>Packages lacking a mapping on <i>release-monitoring.org</i></td><td>%s</td></tr>\n" %
stats["rmo-no-mapping"])
f.write("<tr><td>Packages that are up-to-date</td><td>%s</td></tr>\n" %
stats["version-uptodate"])
f.write("<tr><td>Packages that are not up-to-date</td><td>%s</td></tr>\n" %
stats["version-not-uptodate"])
f.write("<tr><td>Packages with no known upstream version</td><td>%s</td></tr>\n" %
stats["version-unknown"])
f.write("</table>\n")
@ -587,6 +729,8 @@ def __main__():
pkg.set_url()
print("Checking URL status")
check_package_urls(packages)
print("Getting latest versions ...")
check_package_latest_version(packages)
print("Calculate stats")
stats = calculate_stats(packages)
print("Write HTML")