src_prepare/euscan-ng
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

euscan: fix #435118 and #435120

Browse Source 
Signed-off-by: Corentin Chary <corentin.chary@gmail.com>
This commit is contained in:
Corentin Chary 2012-09-15 23:20:30 +02:00
parent 89f3192937
commit 9afb31fc65
4 changed files with 23 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
bin/euscan
View File

@ -287,9 +287,9 @@ def main():
from os.path import basename # To get the short name from os.path import basename # To get the short name
output.error( output.eerror(
"The short ebuild name '%s' is ambiguous. Please specify" % "The short ebuild name '%s' is ambiguous. Please specify" %
basename(pkgs[0]), basename(pkgs[0]) +
"one of the above fully-qualified ebuild names instead." "one of the above fully-qualified ebuild names instead."
) )
exit_helper(1) exit_helper(1)

11
pym/euscan/__init__.py
View File

@ -77,11 +77,12 @@ ROBOTS_TXT_BLACKLIST_DOMAINS = [
'(.*)sourceforge(.*)', '(.*)sourceforge(.*)',
'(.*)github.com', '(.*)github.com',
'(.*)berlios(.*)', '(.*)berlios(.*)',
'(.*)qt.nokia.com(.*)', '(.*)qt\.nokia\.com(.*)',
'(.*)chromium.org(.*)', '(.*)chromium\.org(.*)',
'(.*)nodejs.org(.*)', '(.*)nodejs\.org(.*)',
'(.*)download.mono-project.com(.*)', '(.*)download\.mono-project\.com(.*)',
'(.*)fedorahosted.org(.*)', '(.*)fedorahosted\.org(.*)',
'(.*)download\.tuxfamily\.org(.*)',
] ]
from out import EuscanOutput from out import EuscanOutput

1
pym/euscan/handlers/generic.py
View File

@ -70,6 +70,7 @@ def scan_html(data, url, pattern):
match.group(0)) match.group(0))
) )
return results return results

27
pym/euscan/helpers.py
View File

@ -373,27 +373,28 @@ def tryurl(fileurl, template):
def regex_from_template(template): def regex_from_template(template):
# Escape # Escape
template = re.escape(template) regexp = re.escape(template)
# Unescape specific stuff # Unescape specific stuff
template = template.replace('\$\{', '${') regexp = regexp.replace('\$\{', '${')
template = template.replace('\}', '}') regexp = regexp.replace('\}', '}')
template = template.replace('}\.$', '}.$') regexp = regexp.replace('}\.$', '}.$')
# Replace ${\d+} # Replace ${\d+}
#template = template.replace('${0}', r'([\d]+?)') #regexp = regexp.replace('${0}', r'([\d]+?)')
template = re.sub(r'(\$\{\d+\}(\.?))+', r'([\w\.]+?)', template) regexp = re.sub(r'(\$\{\d+\}(\.?))+', r'([\w\.]+?)', regexp)
#template = re.sub(r'(\$\{\d+\}\.?)+', r'([\w]+?)', template) #regexp = re.sub(r'(\$\{\d+\}\.?)+', r'([\w]+?)', regexp)
#template = re.sub(r'(\$\{\d+\}\.+)+', '(.+?)\.', template) #regexp = re.sub(r'(\$\{\d+\}\.+)+', '(.+?)\.', regexp)
#template = re.sub(r'(\$\{\d+\})+', '(.+?)', template) #regexp = re.sub(r'(\$\{\d+\})+', '(.+?)', regexp)
# Full version # Full version
template = template.replace('${PV}', _v) regexp = regexp.replace('${PV}', _v)
# End # End
template = template + r'/?$' regexp = regexp + r'/?$'
return template
return regexp
def basedir_from_template(template): def basedir_from_template(template):
@ -417,7 +418,7 @@ def generate_scan_paths(url):
path = prefix + ":/" path = prefix + ":/"
for chunk in chunks: for chunk in chunks:
if '${' in chunk: if '${' in chunk:
steps.append((path, regex_from_template(chunk))) steps.append((path, '^(?:|.*/)' + regex_from_template(chunk)))
path = "" path = ""
else: else:
path += "/" path += "/"