"""Utility methods for handling XML, reading HTTP, etc""" from App.ImageFile import ImageFile from App.Common import rfc1123_date import sys import os import stat import urllib import logging import time import re import string import datetime try: import httplib2 httplib = 'httplib2' except: logging.warn("Unable to import httplib2! Falling back to urllib2!") import urllib2 httplib = 'urllib2' import xml.etree.ElementTree as ET srvTxtUtilsVersion = "1.12.1" map_months = {'en': [u"", u"January", u"February", u"March", u"April", u"May", u"June", u"July", u"August", u"September", u"October", u"November", u"December"], 'de': [u"", u"Januar", u"Februar", u"M\u00e4rz", u"April", u"Mai", u"Juni", u"Juli", u"August", u"September", u"Oktober", u"November", u"Dezember"]} def getInt(number, default=0): """returns always an int (0 in case of problems)""" try: return int(number) except: return int(default) def getAt(array, idx, default=None): """returns element idx from array or default (in case of problems)""" try: return array[idx] except: return default def unicodify(s): """decode str (utf-8 or latin-1 representation) into unicode object""" if not s: return u"" if isinstance(s, str): try: return s.decode('utf-8') except: return s.decode('latin-1') else: return s def utf8ify(s): """encode unicode object or string into byte string in utf-8 representation. assumes string objects to be utf-8""" if not s: return "" if isinstance(s, str): return s else: return s.encode('utf-8') def getText(node, recursive=0): """returns all text content of a (etree) node and its subnodes""" if node is None: return '' # ElementTree: text = node.text or '' for e in node: if recursive: text += getText(e) else: text += e.text or '' if e.tail: text += e.tail # 4Suite: #nodelist=node.childNodes #text = "" #for n in nodelist: # if n.nodeType == node.TEXT_NODE: # text = text + n.data return text def serialize(node): """returns a string containing an XML snippet of (etree) node""" s = ET.tostring(node, 'UTF-8') # snip off XML declaration if s.startswith('') return s[i+3:] return s def getMonthName(mon, lang): """returns the name of the month mon in the language lang""" return map_months[lang][mon] def getDateString(date=None, lang='en', withYear=True, monthNames=True, abbrev=False): """Return formatted date string.""" if date is None: return None ds = None if callable(date.day): # callable members day = date.day() month = date.month() year = date.year() else: # data members day = date.day month = date.month year = date.year if lang.lower() == 'en': ds = "%s %s"%(getMonthName(month, lang), day) if withYear: ds += ", %s"%year elif lang.lower() == 'de': ds = "%s. %s"%(day, getMonthName(month, lang)) if withYear: ds += " %s"%year elif lang.lower() == 'iso': ds = date.isoformat() return ds def getDate(date): """return date object from date or datetime date.""" if isinstance(date, datetime.datetime): # strip time return date.date() return date def getDatetime(date): """return datetime object from date or datetime date.""" if isinstance(date, datetime.date): # add time 0:00 return datetime.datetime.combine(date, datetime.time()) return date def getHttpData(url, data=None, num_tries=3, timeout=10, username=None, password=None, cache=None, insecure=False, noExceptions=False): """returns result from url+data HTTP request""" # we do GET (by appending data to url) if isinstance(data, str) or isinstance(data, unicode): # if data is string then append url = "%s?%s"%(url,data) elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple): # urlencode url = "%s?%s"%(url,urllib.urlencode(data)) errmsg = None if httplib == 'httplib2': # use httplib2 for cnt in range(num_tries): try: logging.debug("getHttp(lib2)Data(#%s %ss) url=%s"%(cnt+1,timeout,url)) h = httplib2.Http(cache=cache, timeout=float(timeout), disable_ssl_certificate_validation=insecure) if username: h.add_credentials(username, password) resp, data = h.request(url) return data except httplib2.HttpLib2Error, e: logging.error("getHttp(lib2)Data: HTTP error(%s): %s"%(e.code,e)) errmsg = str(e) # stop trying break else: # use urllib2 response = None for cnt in range(num_tries): try: logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url)) if sys.version_info < (2, 6): # set timeout on socket -- ugly :-( import socket socket.setdefaulttimeout(float(timeout)) response = urllib2.urlopen(url) else: # timeout as parameter response = urllib2.urlopen(url,timeout=float(timeout)) # check result? data = response.read() response.close() return data except urllib2.HTTPError, e: logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e)) errmsg = str(e) # stop trying break except urllib2.URLError, e: logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e)) errmsg = str(e) # stop trying #break if noExceptions: return None raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) #return None def refreshingImageFileIndexHtml(self, REQUEST, RESPONSE): """index_html method for App.ImageFile that updates the file info for each request.""" stat_info = os.stat(self.path) self.size = stat_info[stat.ST_SIZE] self.lmt = float(stat_info[stat.ST_MTIME]) or time.time() self.lmh = rfc1123_date(self.lmt) # call original method return ImageFile.index_html(self, REQUEST, RESPONSE) def shortenString(s, l, ellipsis='...'): """returns a string of length l (or l-1) by omitting characters in the middle of s, replacing with ellipsis.""" if len(s) <= l: return s l1 = int((l - len(ellipsis)) / 2) return "%s%s%s"%(s[:l1],ellipsis,s[-l1:]) def sqlName(s, lc=True, more=''): """returns restricted ASCII-only version of string""" if s is None: return "" if not isinstance(s, basestring): # make string object s = str(s) # remove ' s = s.replace("'","") # all else -> "_" s = re.sub('[^A-Za-z0-9_'+more+']','_',s) if lc: return s.lower() return s def getBrowserType(self): """(legacy) check the browsers request to find out the browser type""" bt = {} ua = self.REQUEST.get_header("HTTP_USER_AGENT") bt['ua'] = ua bt['isIE'] = False bt['isN4'] = False if string.find(ua, 'MSIE') > -1: bt['isIE'] = True else: bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) try: nav = ua[string.find(ua, '('):] ie = string.split(nav, "; ")[1] if string.find(ie, "MSIE") > -1: bt['versIE'] = string.split(ie, " ")[1] except: pass bt['isMac'] = string.find(ua, 'Macintosh') > -1 bt['isWin'] = string.find(ua, 'Windows') > -1 bt['isIEWin'] = bt['isIE'] and bt['isWin'] bt['isIEMac'] = bt['isIE'] and bt['isMac'] bt['staticHTML'] = False return bt