Various improvement to enhance portability:

  - Use parsable Configuration file respective ConfigParser module
  - Update documentation with sample of configuration file
  - Create entry_point for console named web_checker_utility


git-svn-id: https://svn.erp5.org/repos/public/erp5/trunk/utils/erp5.utils.web_checker/@37449 20353a03-c40f-0410-a6d1-a30d3c3de9de

erp5/util/README.webchecker.txt

 Utility able to call wget and varnishlog to extract Headers and return all failures
 according expected caching policy.
 
-This utility is configurable through a dictionnary like
-   configuration = {'url': 'http://www.example.com',
-                   'working_directory': '/home/me/tmp/crawled_content',
-                   'varnishlog_binary_path': 'varnishlog',
-                   'header_list': {'Last-Modified': True,
-                                   'Cache-Control': ('max-age=300', 'max-age=3600',),
-                                   'Vary' : ('Accept-Language, Cookie', 'Accept-Language,Cookie'),
-                                   'Expires': True,
-                                  },
-                   'email_address': 'me@example.com',
-                   'smtp_host': 'localhost',
-                   'debug_level': 'debug',
-                  }
+This utility is configurable through a configuration file like:
 
-url : website to check
-working_directory : fetched data will be downloaded
-varnishlog_binary_path :  path to varnishlog
-header_list : Key == Header id.
-              value: if equals to True, it means that header needs to be present in RESPONSE
-                     if it is a tuple, the Header value must sastify at least one of the proposed values
-email_address : email address to send result
-smtp_host : smtp host to use
-debug_level : log level of this utility (debug =>very verbose,
-                                         info=>normal,
-                                         warning=>nothing)
+[web_checker]
+url = http://www.example.com/
+working_directory = /home/me/tmp/crawled_content
+varnishlog_binary_path = varnishlog
+email_address = me@example.com
+smtp_host = localhost
+debug_level = debug
+
+[header_list]
+Last-Modified = True
+Cache-Control = max-age=300
+                max-age=3600
+Vary = Accept-Language, Cookie, Accept-Encoding
+       Accept-Language, Cookie
+       Accept-Language,Cookie,Accept-Encoding
+       Accept-Language,Cookie
+Expires = True
+
+
+with
+  url : website to check
+  working_directory : fetched data will be downloaded
+  varnishlog_binary_path :  path to varnishlog
+  header_list : Key == Header id.
+                value: if equals to True, it means that header needs to be present in RESPONSE
+                      if it is a tuple, the Header value must sastify at least one of the proposed values
+  email_address : email address to send result
+  smtp_host : smtp host to use
+  debug_level : log level of this utility (debug =>very verbose,
+                                          info=>normal,
+                                          warning=>nothing)
 
 This utility requires wget => 1.12
 And a callable varnishlog.

erp5/util/webchecker/__init__.py

@@ -378,4 +378,46 @@ class HTTPCacheCheckerTestSuite(object):
       server.quit()
       return 'Email sends to %s' % self.email_address
     else:
-      return report_message
+      return report_message
\ No newline at end of file
+
+
+from optparse import OptionParser
+import ConfigParser
+
+def web_checker_utility():
+  usage = "usage: %prog config_path"
+  parser = OptionParser(usage=usage)
+
+  (options, args) = parser.parse_args()
+
+  if len(args) != 1 :
+    print parser.print_help()
+    parser.error('incorrect number of arguments')
+  config_path = args[0]
+
+  config = ConfigParser.RawConfigParser()
+  config.read(config_path)
+  working_directory = config.get('web_checker', 'working_directory')
+  url = config.get('web_checker', 'url')
+  varnishlog_binary_path = config.get('web_checker' , 'varnishlog_binary_path')
+  header_list = {}
+  for header, configuration in config.items('header_list'):
+    if configuration in ('True', 'true', 'yes'):
+      value = True
+    else:
+      value = configuration.splitlines()
+    header_list[header] = value
+  email_address = config.get('web_checker' , 'email_address')
+  smtp_host = config.get('web_checker' , 'smtp_host')
+  debug_level = config.get('web_checker' , 'debug_level')
+  instance = HTTPCacheCheckerTestSuite(url,
+                                      working_directory,
+                                      varnishlog_binary_path,
+                                      header_list,
+                                      email_address,
+                                      smtp_host,
+                                      debug_level)
+
+  print instance.start()
+
+