| 1 | """Utility methods for handling XML, reading HTTP, etc""" |
|---|
| 2 | |
|---|
| 3 | from App.ImageFile import ImageFile |
|---|
| 4 | from App.Common import rfc1123_date |
|---|
| 5 | |
|---|
| 6 | import sys |
|---|
| 7 | import os |
|---|
| 8 | import stat |
|---|
| 9 | import urllib |
|---|
| 10 | import logging |
|---|
| 11 | import time |
|---|
| 12 | import re |
|---|
| 13 | import string |
|---|
| 14 | import datetime |
|---|
| 15 | try: |
|---|
| 16 | import httplib2 |
|---|
| 17 | httplib = 'httplib2' |
|---|
| 18 | except: |
|---|
| 19 | logging.warn("Unable to import httplib2! Falling back to urllib2!") |
|---|
| 20 | import urllib2 |
|---|
| 21 | httplib = 'urllib2' |
|---|
| 22 | |
|---|
| 23 | import xml.etree.ElementTree as ET |
|---|
| 24 | |
|---|
| 25 | srvTxtUtilsVersion = "1.12.1" |
|---|
| 26 | |
|---|
| 27 | map_months = {'en': [u"", |
|---|
| 28 | u"January", |
|---|
| 29 | u"February", |
|---|
| 30 | u"March", |
|---|
| 31 | u"April", |
|---|
| 32 | u"May", |
|---|
| 33 | u"June", |
|---|
| 34 | u"July", |
|---|
| 35 | u"August", |
|---|
| 36 | u"September", |
|---|
| 37 | u"October", |
|---|
| 38 | u"November", |
|---|
| 39 | u"December"], |
|---|
| 40 | 'de': [u"", |
|---|
| 41 | u"Januar", |
|---|
| 42 | u"Februar", |
|---|
| 43 | u"M\u00e4rz", |
|---|
| 44 | u"April", |
|---|
| 45 | u"Mai", |
|---|
| 46 | u"Juni", |
|---|
| 47 | u"Juli", |
|---|
| 48 | u"August", |
|---|
| 49 | u"September", |
|---|
| 50 | u"Oktober", |
|---|
| 51 | u"November", |
|---|
| 52 | u"Dezember"]} |
|---|
| 53 | |
|---|
| 54 | def getInt(number, default=0): |
|---|
| 55 | """returns always an int (0 in case of problems)""" |
|---|
| 56 | try: |
|---|
| 57 | return int(number) |
|---|
| 58 | except: |
|---|
| 59 | return int(default) |
|---|
| 60 | |
|---|
| 61 | def getAt(array, idx, default=None): |
|---|
| 62 | """returns element idx from array or default (in case of problems)""" |
|---|
| 63 | try: |
|---|
| 64 | return array[idx] |
|---|
| 65 | except: |
|---|
| 66 | return default |
|---|
| 67 | |
|---|
| 68 | def unicodify(s): |
|---|
| 69 | """decode str (utf-8 or latin-1 representation) into unicode object""" |
|---|
| 70 | if not s: |
|---|
| 71 | return u"" |
|---|
| 72 | if isinstance(s, str): |
|---|
| 73 | try: |
|---|
| 74 | return s.decode('utf-8') |
|---|
| 75 | except: |
|---|
| 76 | return s.decode('latin-1') |
|---|
| 77 | else: |
|---|
| 78 | return s |
|---|
| 79 | |
|---|
| 80 | def utf8ify(s): |
|---|
| 81 | """encode unicode object or string into byte string in utf-8 representation. |
|---|
| 82 | assumes string objects to be utf-8""" |
|---|
| 83 | if not s: |
|---|
| 84 | return "" |
|---|
| 85 | if isinstance(s, str): |
|---|
| 86 | return s |
|---|
| 87 | else: |
|---|
| 88 | return s.encode('utf-8') |
|---|
| 89 | |
|---|
| 90 | def getText(node, recursive=0): |
|---|
| 91 | """returns all text content of a (etree) node and its subnodes""" |
|---|
| 92 | if node is None: |
|---|
| 93 | return '' |
|---|
| 94 | |
|---|
| 95 | # ElementTree: |
|---|
| 96 | text = node.text or '' |
|---|
| 97 | for e in node: |
|---|
| 98 | if recursive: |
|---|
| 99 | text += getText(e) |
|---|
| 100 | else: |
|---|
| 101 | text += e.text or '' |
|---|
| 102 | if e.tail: |
|---|
| 103 | text += e.tail |
|---|
| 104 | |
|---|
| 105 | # 4Suite: |
|---|
| 106 | #nodelist=node.childNodes |
|---|
| 107 | #text = "" |
|---|
| 108 | #for n in nodelist: |
|---|
| 109 | # if n.nodeType == node.TEXT_NODE: |
|---|
| 110 | # text = text + n.data |
|---|
| 111 | |
|---|
| 112 | return text |
|---|
| 113 | |
|---|
| 114 | |
|---|
| 115 | def serialize(node): |
|---|
| 116 | """returns a string containing an XML snippet of (etree) node""" |
|---|
| 117 | s = ET.tostring(node, 'UTF-8') |
|---|
| 118 | # snip off XML declaration |
|---|
| 119 | if s.startswith('<?xml'): |
|---|
| 120 | i = s.find('?>') |
|---|
| 121 | return s[i+3:] |
|---|
| 122 | |
|---|
| 123 | return s |
|---|
| 124 | |
|---|
| 125 | |
|---|
| 126 | def getMonthName(mon, lang): |
|---|
| 127 | """returns the name of the month mon in the language lang""" |
|---|
| 128 | return map_months[lang][mon] |
|---|
| 129 | |
|---|
| 130 | |
|---|
| 131 | def getDateString(date=None, lang='en', withYear=True, monthNames=True, abbrev=False): |
|---|
| 132 | """Return formatted date string.""" |
|---|
| 133 | if date is None: |
|---|
| 134 | return None |
|---|
| 135 | |
|---|
| 136 | ds = None |
|---|
| 137 | if callable(date.day): |
|---|
| 138 | # callable members |
|---|
| 139 | day = date.day() |
|---|
| 140 | month = date.month() |
|---|
| 141 | year = date.year() |
|---|
| 142 | else: |
|---|
| 143 | # data members |
|---|
| 144 | day = date.day |
|---|
| 145 | month = date.month |
|---|
| 146 | year = date.year |
|---|
| 147 | |
|---|
| 148 | if lang.lower() == 'en': |
|---|
| 149 | ds = "%s %s"%(getMonthName(month, lang), day) |
|---|
| 150 | if withYear: |
|---|
| 151 | ds += ", %s"%year |
|---|
| 152 | |
|---|
| 153 | elif lang.lower() == 'de': |
|---|
| 154 | ds = "%s. %s"%(day, getMonthName(month, lang)) |
|---|
| 155 | if withYear: |
|---|
| 156 | ds += " %s"%year |
|---|
| 157 | |
|---|
| 158 | elif lang.lower() == 'iso': |
|---|
| 159 | ds = date.isoformat() |
|---|
| 160 | |
|---|
| 161 | return ds |
|---|
| 162 | |
|---|
| 163 | |
|---|
| 164 | def getDate(date): |
|---|
| 165 | """return date object from date or datetime date.""" |
|---|
| 166 | if isinstance(date, datetime.datetime): |
|---|
| 167 | # strip time |
|---|
| 168 | return date.date() |
|---|
| 169 | |
|---|
| 170 | return date |
|---|
| 171 | |
|---|
| 172 | |
|---|
| 173 | def getDatetime(date): |
|---|
| 174 | """return datetime object from date or datetime date.""" |
|---|
| 175 | if isinstance(date, datetime.date): |
|---|
| 176 | # add time 0:00 |
|---|
| 177 | return datetime.datetime.combine(date, datetime.time()) |
|---|
| 178 | |
|---|
| 179 | return date |
|---|
| 180 | |
|---|
| 181 | |
|---|
| 182 | def getHttpData(url, data=None, num_tries=3, timeout=10, username=None, password=None, cache=None, insecure=False, noExceptions=False): |
|---|
| 183 | """returns result from url+data HTTP request""" |
|---|
| 184 | # we do GET (by appending data to url) |
|---|
| 185 | if isinstance(data, str) or isinstance(data, unicode): |
|---|
| 186 | # if data is string then append |
|---|
| 187 | url = "%s?%s"%(url,data) |
|---|
| 188 | elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple): |
|---|
| 189 | # urlencode |
|---|
| 190 | url = "%s?%s"%(url,urllib.urlencode(data)) |
|---|
| 191 | |
|---|
| 192 | errmsg = None |
|---|
| 193 | if httplib == 'httplib2': |
|---|
| 194 | # use httplib2 |
|---|
| 195 | for cnt in range(num_tries): |
|---|
| 196 | try: |
|---|
| 197 | logging.debug("getHttp(lib2)Data(#%s %ss) url=%s"%(cnt+1,timeout,url)) |
|---|
| 198 | h = httplib2.Http(cache=cache, timeout=float(timeout), disable_ssl_certificate_validation=insecure) |
|---|
| 199 | if username: |
|---|
| 200 | h.add_credentials(username, password) |
|---|
| 201 | |
|---|
| 202 | resp, data = h.request(url) |
|---|
| 203 | return data |
|---|
| 204 | |
|---|
| 205 | except httplib2.HttpLib2Error, e: |
|---|
| 206 | logging.error("getHttp(lib2)Data: HTTP error(%s): %s"%(e.code,e)) |
|---|
| 207 | errmsg = str(e) |
|---|
| 208 | # stop trying |
|---|
| 209 | break |
|---|
| 210 | |
|---|
| 211 | else: |
|---|
| 212 | # use urllib2 |
|---|
| 213 | response = None |
|---|
| 214 | for cnt in range(num_tries): |
|---|
| 215 | try: |
|---|
| 216 | logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url)) |
|---|
| 217 | if sys.version_info < (2, 6): |
|---|
| 218 | # set timeout on socket -- ugly :-( |
|---|
| 219 | import socket |
|---|
| 220 | socket.setdefaulttimeout(float(timeout)) |
|---|
| 221 | response = urllib2.urlopen(url) |
|---|
| 222 | else: |
|---|
| 223 | # timeout as parameter |
|---|
| 224 | response = urllib2.urlopen(url,timeout=float(timeout)) |
|---|
| 225 | # check result? |
|---|
| 226 | data = response.read() |
|---|
| 227 | response.close() |
|---|
| 228 | return data |
|---|
| 229 | |
|---|
| 230 | except urllib2.HTTPError, e: |
|---|
| 231 | logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e)) |
|---|
| 232 | errmsg = str(e) |
|---|
| 233 | # stop trying |
|---|
| 234 | break |
|---|
| 235 | except urllib2.URLError, e: |
|---|
| 236 | logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e)) |
|---|
| 237 | errmsg = str(e) |
|---|
| 238 | # stop trying |
|---|
| 239 | #break |
|---|
| 240 | |
|---|
| 241 | if noExceptions: |
|---|
| 242 | return None |
|---|
| 243 | |
|---|
| 244 | raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) |
|---|
| 245 | #return None |
|---|
| 246 | |
|---|
| 247 | |
|---|
| 248 | def refreshingImageFileIndexHtml(self, REQUEST, RESPONSE): |
|---|
| 249 | """index_html method for App.ImageFile that updates the file info for each request.""" |
|---|
| 250 | stat_info = os.stat(self.path) |
|---|
| 251 | self.size = stat_info[stat.ST_SIZE] |
|---|
| 252 | self.lmt = float(stat_info[stat.ST_MTIME]) or time.time() |
|---|
| 253 | self.lmh = rfc1123_date(self.lmt) |
|---|
| 254 | # call original method |
|---|
| 255 | return ImageFile.index_html(self, REQUEST, RESPONSE) |
|---|
| 256 | |
|---|
| 257 | |
|---|
| 258 | def shortenString(s, l, ellipsis='...'): |
|---|
| 259 | """returns a string of length l (or l-1) by omitting characters in the middle of s, replacing with ellipsis.""" |
|---|
| 260 | if len(s) <= l: |
|---|
| 261 | return s |
|---|
| 262 | |
|---|
| 263 | l1 = int((l - len(ellipsis)) / 2) |
|---|
| 264 | return "%s%s%s"%(s[:l1],ellipsis,s[-l1:]) |
|---|
| 265 | |
|---|
| 266 | |
|---|
| 267 | def sqlName(s, lc=True, more=''): |
|---|
| 268 | """returns restricted ASCII-only version of string""" |
|---|
| 269 | if s is None: |
|---|
| 270 | return "" |
|---|
| 271 | |
|---|
| 272 | if not isinstance(s, basestring): |
|---|
| 273 | # make string object |
|---|
| 274 | s = str(s) |
|---|
| 275 | |
|---|
| 276 | # remove ' |
|---|
| 277 | s = s.replace("'","") |
|---|
| 278 | # all else -> "_" |
|---|
| 279 | s = re.sub('[^A-Za-z0-9_'+more+']','_',s) |
|---|
| 280 | if lc: |
|---|
| 281 | return s.lower() |
|---|
| 282 | |
|---|
| 283 | return s |
|---|
| 284 | |
|---|
| 285 | |
|---|
| 286 | def getBrowserType(self): |
|---|
| 287 | """(legacy) check the browsers request to find out the browser type""" |
|---|
| 288 | bt = {} |
|---|
| 289 | ua = self.REQUEST.get_header("HTTP_USER_AGENT") |
|---|
| 290 | bt['ua'] = ua |
|---|
| 291 | bt['isIE'] = False |
|---|
| 292 | bt['isN4'] = False |
|---|
| 293 | if string.find(ua, 'MSIE') > -1: |
|---|
| 294 | bt['isIE'] = True |
|---|
| 295 | else: |
|---|
| 296 | bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) |
|---|
| 297 | |
|---|
| 298 | try: |
|---|
| 299 | nav = ua[string.find(ua, '('):] |
|---|
| 300 | ie = string.split(nav, "; ")[1] |
|---|
| 301 | if string.find(ie, "MSIE") > -1: |
|---|
| 302 | bt['versIE'] = string.split(ie, " ")[1] |
|---|
| 303 | except: pass |
|---|
| 304 | |
|---|
| 305 | bt['isMac'] = string.find(ua, 'Macintosh') > -1 |
|---|
| 306 | bt['isWin'] = string.find(ua, 'Windows') > -1 |
|---|
| 307 | bt['isIEWin'] = bt['isIE'] and bt['isWin'] |
|---|
| 308 | bt['isIEMac'] = bt['isIE'] and bt['isMac'] |
|---|
| 309 | bt['staticHTML'] = False |
|---|
| 310 | |
|---|
| 311 | return bt |
|---|
| 312 | |
|---|
