Revision: 4309 Author: russblau Date: 2007-09-16 16:07:09 +0000 (Sun, 16 Sep 2007)

Log Message: ----------- Further efforts to standardize access to bot data files.

Modified Paths: -------------- trunk/pywikipedia/casechecker.py trunk/pywikipedia/category.py trunk/pywikipedia/config.py trunk/pywikipedia/copyright.py trunk/pywikipedia/interwiki.py trunk/pywikipedia/welcome.py trunk/pywikipedia/wikipedia.py

Modified: trunk/pywikipedia/casechecker.py =================================================================== --- trunk/pywikipedia/casechecker.py 2007-09-16 14:51:43 UTC (rev 4308) +++ trunk/pywikipedia/casechecker.py 2007-09-16 16:07:09 UTC (rev 4309) @@ -153,8 +153,7 @@ raise ValueError(u'Suspects must be the same size')

if not os.path.isabs(self.wikilogfile): - self.wikilogfile = os.path.join(wikipedia.config.base_dir, - self.wikilogfile) + self.wikilogfile = wikipedia.datafilepath(self.wikilogfile) try: self.wikilog = codecs.open(self.wikilogfile, 'a', 'utf-8') except IOError:

Modified: trunk/pywikipedia/category.py =================================================================== --- trunk/pywikipedia/category.py 2007-09-16 14:51:43 UTC (rev 4308) +++ trunk/pywikipedia/category.py 2007-09-16 16:07:09 UTC (rev 4309) @@ -156,8 +156,7 @@ else: try: if not os.path.isabs(filename): - filename = os.path.join(wikipedia.config.base_dir, - filename) + filename = wikipedia.datafilepath(filename) f = bz2.BZ2File(filename, 'r') wikipedia.output(u'Reading dump from %s' % filename) databases = pickle.load(f) @@ -223,7 +222,7 @@ Saves the contents of the dictionaries superclassDB and catContentDB to disk. ''' if not os.path.isabs(filename): - filename = os.path.join(wikipedia.config.base_dir, filename) + filename = wikipedia.datafilepath(filename) wikipedia.output(u'Dumping to %s, please wait...' % filename) f = bz2.BZ2File(filename, 'w') databases = { @@ -679,8 +678,7 @@ self.catTitle = catTitle self.catDB = catDB if not os.path.isabs(filename): - filename = os.path.join(wikipedia.config.base_dir, - filename) + filename = wikipedia.datafilepath(filename) self.filename = filename # TODO: make maxDepth changeable with a parameter or config file entry self.maxDepth = maxDepth

Modified: trunk/pywikipedia/config.py =================================================================== --- trunk/pywikipedia/config.py 2007-09-16 14:51:43 UTC (rev 4308) +++ trunk/pywikipedia/config.py 2007-09-16 16:07:09 UTC (rev 4309) @@ -43,6 +43,7 @@ usernames = {} sysopnames = {} disambiguation_comment = {} +gdab_namespaces = {}

# Some sites will require password identication to access the HTML pages at # the site. If you have any such site, add lines to your user-config.py of

Modified: trunk/pywikipedia/copyright.py =================================================================== --- trunk/pywikipedia/copyright.py 2007-09-16 14:51:43 UTC (rev 4308) +++ trunk/pywikipedia/copyright.py 2007-09-16 16:07:09 UTC (rev 4309) @@ -86,8 +86,8 @@ # No checks if the page is a disambiguation page. skip_disambig = True

-appdir = os.path.join(wikipedia.config.base_dir, "copyright") -output_file = os.path.join(appdir, "output.txt") +appdir = "copyright" +output_file = wikipedia.datafilepath(appdir, "output.txt")

pages_for_exclusion_database = [ ('it', 'User:RevertBot/Lista_di_esclusione', 'exclusion_list.txt'), @@ -242,7 +242,7 @@

def exclusion_file_list(): for i in pages_for_exclusion_database: - path = os.path.join(appdir, i[0], i[2]) + path = wikipedia.datafilepath(appdir, i[0], i[2]) wikipedia.makepath(path) p = wikipedia.Page(wikipedia.getSite(i[0]), i[1]) yield p, path @@ -325,7 +325,7 @@ result_list.append(entry)

result_list += read_file( - os.path.join(appdir, 'exclusion_list.txt'), + wikipedia.datafilepath(appdir, 'exclusion_list.txt'), cut_comment = True, cut_newlines = True ).splitlines()

@@ -455,7 +455,7 @@ print "** " + entry

def exclusion_list_dump(): - f = open(appdir + 'exclusion_list.dump', 'w') + f = open(wikipedia.datafilepath(appdir, 'exclusion_list.dump', 'w')) f.write('\n'.join(excl_list)) f.close() print "Exclusion list dump saved." @@ -851,7 +851,7 @@ % (title.replace(" ", "_").replace(""", "%22"), id, "author") + output, - os.path.join(appdir, "ID_output.txt")) + wikipedia.datafilepath(appdir, "ID_output.txt"))

class CheckRobot: def __init__(self, generator):

Modified: trunk/pywikipedia/interwiki.py =================================================================== --- trunk/pywikipedia/interwiki.py 2007-09-16 14:51:43 UTC (rev 4308) +++ trunk/pywikipedia/interwiki.py 2007-09-16 16:07:09 UTC (rev 4309) @@ -208,7 +208,6 @@ #

import sys, copy, re -import os.path import time import codecs import socket @@ -1165,10 +1164,9 @@

def dump(self): site = wikipedia.getSite() - dumpfn = os.path.join(wikipedia.config.base_dir, - 'interwiki-dumps', - 'interwikidump-%s-%s.txt' - % (site.family.name, site.lang)) + dumpfn = wikipedia.datafilepath( + 'interwiki-dumps', + 'interwikidump-%s-%s.txt' % (site.family.name, site.lang)) f = codecs.open(dumpfn, 'w', 'utf-8') for subj in self.subjects: f.write(subj.originPage.aslink(None)+'\n') @@ -1520,10 +1518,10 @@

if optRestore or optContinue: site = wikipedia.getSite() - dumpFileName = os.path.join(wikipedia.config.base_dir, - 'interwiki-dumps', - u'interwikidump-%s-%s.txt' - % (site.family.name, site.lang)) + dumpFileName = wikipedia.datafilepath( + 'interwiki-dumps', + u'interwikidump-%s-%s.txt' + % (site.family.name, site.lang)) hintlessPageGen = pagegenerators.TextfilePageGenerator(dumpFileName) if optContinue: # We waste this generator to find out the last page's title

Modified: trunk/pywikipedia/welcome.py =================================================================== --- trunk/pywikipedia/welcome.py 2007-09-16 14:51:43 UTC (rev 4308) +++ trunk/pywikipedia/welcome.py 2007-09-16 16:07:09 UTC (rev 4309) @@ -443,11 +443,11 @@ wikipedia.output(u'Error! - No fileName!') raise FilenameNotSet("No signature filename specified.") try: - f = codecs.open(os.path.join(wikipedia.config.base_dir, fileSignName), 'r', - encoding = config.console_encoding) + f = codecs.open(wikipedia.datafilepath(fileSignName), 'r', + encoding=config.console_encoding) except: - f = codecs.open(os.path.join(wikipedia.config.base_dir, fileSignName), 'r', - encoding = 'utf-8') + f = codecs.open(wikipedia.datafilepath(fileSignName), 'r', + encoding='utf-8') signText = f.read() f.close()

@@ -623,9 +623,7 @@ welcomer = u'{{subst:Benvenuto}} %s'

welcomed_users = list() - if savedata == True and os.path.exists( - os.path.join( - wikipedia.config.base_dir, filename)): + if savedata == True and os.path.exists(wikipedia.datafilepath(filename)): f = file(filename) number_user = cPickle.load(f) yield number_user

Modified: trunk/pywikipedia/wikipedia.py =================================================================== --- trunk/pywikipedia/wikipedia.py 2007-09-16 14:51:43 UTC (rev 4308) +++ trunk/pywikipedia/wikipedia.py 2007-09-16 16:07:09 UTC (rev 4309) @@ -2441,7 +2441,7 @@ self.setDelay(mindelay)

def logfn(self): - return os.path.join(config.base_dir, 'throttle.log') + return datafilepath('throttle.log')

def checkMultiplicity(self): self.lock.acquire() @@ -3180,7 +3180,7 @@ fam = config.family try: # search for family module in the 'families' subdirectory - sys.path.append(os.path.join(config.base_dir, 'families')) + sys.path.append(datafilepath('families')) exec "import %s_family as myfamily" % fam except ImportError: if fatal: @@ -3391,7 +3391,7 @@ else: tmp = '%s-%s-%s-login.data' % ( self.family.name, self.lang, username) - fn = os.path.join(config.base_dir, 'login-data', tmp) + fn = datafilepath('login-data', tmp) if not os.path.exists(fn): self._cookies = None self.loginStatusKnown = True @@ -4419,12 +4419,40 @@ nonGlobalArgs.append(arg) return nonGlobalArgs

+def makepath(path): + """ creates missing directories for the given path and + returns a normalized absolute version of the path. + + - if the given path already exists in the filesystem + the filesystem is not modified. + + - otherwise makepath creates directories along the given path + using the dirname() of the path. You may append + a '/' to the path if you want it to be a directory path. + + from holger@trillke.net 2002/03/18 + """ + from os import makedirs + from os.path import normpath,dirname,exists,abspath + + dpath = normpath(dirname(path)) + if not exists(dpath): makedirs(dpath) + return normpath(abspath(path)) + +def datafilepath(*filename): + """Returns an absolute path to a data file, offset from the bot's + base directory. + Argument(s) are zero or more directory names, followed by a data file + name. + """ + return os.path.join(config.base_dir, *filename) + ######################### # Interpret configuration #########################

# search for user interface module in the 'userinterfaces' subdirectory -sys.path.append(os.path.join(config.base_dir, 'userinterfaces')) +sys.path.append(datafilepath('userinterfaces')) exec "import %s_interface as uiModule" % config.userinterface ui = uiModule.UI() verbose = 0 @@ -4636,32 +4664,12 @@ result += diff[i] output(result)

-def makepath(path): - """ creates missing directories for the given path and - returns a normalized absolute version of the path. - - - if the given path already exists in the filesystem - the filesystem is not modified. - - - otherwise makepath creates directories along the given path - using the dirname() of the path. You may append - a '/' to the path if you want it to be a directory path. - - from holger@trillke.net 2002/03/18 - """ - from os import makedirs - from os.path import normpath,dirname,exists,abspath - - dpath = normpath(dirname(path)) - if not exists(dpath): makedirs(dpath) - return normpath(abspath(path)) - def setLogfileStatus(enabled, logname = None): global logfile if enabled: if not logname: logname = '%s.log' % calledModuleName() - logfn = os.path.join(config.base_dir, 'logs', logname) + logfn = datafiledpath('logs', logname) try: logfile = codecs.open(logfn, 'a', 'utf-8') except IOError: @@ -4938,7 +4946,7 @@ # Special opener in case we are using a site with authentication if config.authenticate: import urllib2, cookielib - COOKIEFILE = os.path.join(config.base_dir, 'login-data', 'cookies.lwp') + COOKIEFILE = datafilepath('login-data', 'cookies.lwp') cj = cookielib.LWPCookieJar() if os.path.isfile(COOKIEFILE): cj.load(COOKIEFILE)