diff options
Diffstat (limited to 'setuptools/package_index.py')
| -rw-r--r-- | setuptools/package_index.py | 76 |
1 files changed, 41 insertions, 35 deletions
diff --git a/setuptools/package_index.py b/setuptools/package_index.py index 3979b131..123e9582 100644 --- a/setuptools/package_index.py +++ b/setuptools/package_index.py @@ -320,7 +320,8 @@ class PackageIndex(Environment): else: self.opener = urllib.request.urlopen - def process_url(self, url, retrieve=False): + # FIXME: 'PackageIndex.process_url' is too complex (14) + def process_url(self, url, retrieve=False): # noqa: C901 """Evaluate a URL as a possible download, and maybe retrieve it""" if url in self.scanned_urls and not retrieve: return @@ -428,49 +429,53 @@ class PackageIndex(Environment): dist.precedence = SOURCE_DIST self.add(dist) + def _scan(self, link): + # Process a URL to see if it's for a package page + NO_MATCH_SENTINEL = None, None + if not link.startswith(self.index_url): + return NO_MATCH_SENTINEL + + parts = list(map( + urllib.parse.unquote, link[len(self.index_url):].split('/') + )) + if len(parts) != 2 or '#' in parts[1]: + return NO_MATCH_SENTINEL + + # it's a package page, sanitize and index it + pkg = safe_name(parts[0]) + ver = safe_version(parts[1]) + self.package_pages.setdefault(pkg.lower(), {})[link] = True + return to_filename(pkg), to_filename(ver) + def process_index(self, url, page): """Process the contents of a PyPI page""" - def scan(link): - # Process a URL to see if it's for a package page - if link.startswith(self.index_url): - parts = list(map( - urllib.parse.unquote, link[len(self.index_url):].split('/') - )) - if len(parts) == 2 and '#' not in parts[1]: - # it's a package page, sanitize and index it - pkg = safe_name(parts[0]) - ver = safe_version(parts[1]) - self.package_pages.setdefault(pkg.lower(), {})[link] = True - return to_filename(pkg), to_filename(ver) - return None, None - # process an index page into the package-page index for match in HREF.finditer(page): try: - scan(urllib.parse.urljoin(url, htmldecode(match.group(1)))) + self._scan(urllib.parse.urljoin(url, htmldecode(match.group(1)))) except ValueError: pass - pkg, ver = scan(url) # ensure this page is in the page index - if pkg: - # process individual package page - for new_url in find_external_links(url, page): - # Process the found URL - base, frag = egg_info_for_url(new_url) - if base.endswith('.py') and not frag: - if ver: - new_url += '#egg=%s-%s' % (pkg, ver) - else: - self.need_version_info(url) - self.scan_url(new_url) - - return PYPI_MD5.sub( - lambda m: '<a href="%s#md5=%s">%s</a>' % m.group(1, 3, 2), page - ) - else: + pkg, ver = self._scan(url) # ensure this page is in the page index + if not pkg: return "" # no sense double-scanning non-package pages + # process individual package page + for new_url in find_external_links(url, page): + # Process the found URL + base, frag = egg_info_for_url(new_url) + if base.endswith('.py') and not frag: + if ver: + new_url += '#egg=%s-%s' % (pkg, ver) + else: + self.need_version_info(url) + self.scan_url(new_url) + + return PYPI_MD5.sub( + lambda m: '<a href="%s#md5=%s">%s</a>' % m.group(1, 3, 2), page + ) + def need_version_info(self, url): self.scan_all( "Page at %s links to .py file(s) without version info; an index " @@ -591,7 +596,7 @@ class PackageIndex(Environment): spec = parse_requirement_arg(spec) return getattr(self.fetch_distribution(spec, tmpdir), 'location', None) - def fetch_distribution( + def fetch_distribution( # noqa: C901 # is too complex (14) # FIXME self, requirement, tmpdir, force_scan=False, source=False, develop_ok=False, local_index=None): """Obtain a distribution suitable for fulfilling `requirement` @@ -762,7 +767,8 @@ class PackageIndex(Environment): def reporthook(self, url, filename, blocknum, blksize, size): pass # no-op - def open_url(self, url, warning=None): + # FIXME: + def open_url(self, url, warning=None): # noqa: C901 # is too complex (12) if url.startswith('file:'): return local_open(url) try: |