# HG changeset patch
# User casties
# Date 1383151383 -3600
# Node ID 9a23640f7f49dac1f0c124d334923241fc113672
# Parent 1eabc75b9180eeccf00315fcaf3f962e98b3757f
added getAllProjectsAndTagsAsCSV.
diff -r 1eabc75b9180 -r 9a23640f7f49 MPIWGThesaurus.py
--- a/MPIWGThesaurus.py Wed Oct 30 10:18:08 2013 +0100
+++ b/MPIWGThesaurus.py Wed Oct 30 17:43:03 2013 +0100
@@ -17,6 +17,7 @@
from AccessControl import ClassSecurityInfo
#import os
+import re
import os.path
import logging
import time
@@ -27,7 +28,7 @@
import urllib2
import urllib
-
+from SrvTxtUtils import utf8ify
class projectHolder:
projectHolder=""
@@ -318,17 +319,52 @@
retarray.append(project.projectName)
retarray.append(project.persons)
-
-
for tagType in self.tags.keys():
tags = project.tags.get(tagType,[''])
retarray.append(";".join(tags))
-
ret+="\t".join(retarray)+"\n"
return ret
+
+ def getAllProjectsAndTagsAsCSV(self,archived=1,RESPONSE=None):
+ """alle projekte auch die nicht getaggten"""
+ retList=[]
+ headers=['projectId','sortingNumber','projectName','scholars','startedAt','completedAt','lastChangeThesaurusAt','lastChangeProjectAt','projectCreatedAt','persons','objects']
+ headers.extend(list(self.tags.keys()))
+ retList.append("\t".join(headers))
+
+ projectTags = self.getProjectsAndTags()
+ projects = self.getMPIWGRoot().getProjectFolder().getProjectsAsList(archived=archived)
+ for proj in projects:
+ p_name = proj.getLabel()
+ retProj=[]
+ #if (not proj.isArchivedProject() and archived==1) or (proj.isArchivedProject() and archived==2):
+ retProj.append(utf8ify(proj.getId()))
+ retProj.append(utf8ify(proj.getContent('xdata_05')))
+ retProj.append(utf8ify(p_name))
+ retProj.append(utf8ify(proj.getContent('xdata_01')))
+ retProj.append(utf8ify(proj.getStartedAt()))
+ retProj.append(utf8ify(proj.getCompletedAt()))
+ changeDate=self.lastChangeInThesaurus.get(proj.getId(),'')
+ n = re.sub("[:\- ]","",str(changeDate))
+ retProj.append(n)
+ retProj.append(utf8ify(getattr(proj,'creationTime','20050101000000')))
+ retProj.append("")#TODO: project created at
+ retProj.append(";".join([person[1] for person in self.getPersonsFromProject(proj.getId())]))
+ #retProj.append(";".join([person[1] for person in self.thesaurus.getHistoricalPlacesFromProject(proj.getId())]))
+ retProj.append(";".join([person[1] for person in self.getObjectsFromProject(proj.getId())]))
+ retProj+=self.getTags(proj.getId(),projectTags)
+ retList.append("\t".join(retProj))
+
+ if RESPONSE:
+ RESPONSE.setHeader('Content-Disposition','attachment; filename="ProjectsAndTags.tsv"')
+ RESPONSE.setHeader('Content-Type', "application/octet-stream")
+
+ return "\n".join(retList);
+
+
def getLogpath(self):
return getattr(self,"logpath",self.logpathDefault)
@@ -803,7 +839,7 @@
retarray=[]
for tagType in self.tags.keys():
tags = project.tags.get(tagType,[''])
- retarray.append(self.utf8ify(";".join(tags)))
+ retarray.append(utf8ify(";".join(tags)))
return retarray
@@ -1529,8 +1565,6 @@
if tags is None:
logging.debug("can't find Tags")
return []
-
-
tagsStored=tags.get(tagType,None)
if tagsStored is None:
@@ -1552,7 +1586,8 @@
return ret
def getProjectDetails(self,projectId):
- project=getattr(self.projects,projectId,None)
+ pf = self.getMPIWGRoot().getProjectFolder()
+ project=pf.get(projectId,None)
if project is None:
logging.debug("no project!! " +projectId)
return None
@@ -1652,7 +1687,6 @@
return
opener2 = urllib2.build_opener()
-
personIDencoded=urllib.quote(personURI,safe="")
graphEncoded=urllib.quote(self.additionalNamesGraphURL,safe="")
@@ -1667,8 +1701,6 @@
logging.error(e.code)
logging.error(e.read())
return
-
-
return
@@ -1676,12 +1708,6 @@
def storeChange(self,typeString,projectID,value):
from time import gmtime,strftime
-
-
-
-
-
-
fl = open(self.getLogpath(),"a")
person = self.REQUEST.AUTHENTICATED_USER.getId()
date = strftime("%Y-%m-%d %H:%M:%S", gmtime())
diff -r 1eabc75b9180 -r 9a23640f7f49 SrvTxtUtils.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/SrvTxtUtils.py Wed Oct 30 17:43:03 2013 +0100
@@ -0,0 +1,284 @@
+"""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 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 = "1.12.0"
+
+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
+
+
diff -r 1eabc75b9180 -r 9a23640f7f49 zpt/manageMPIWGThesaurus.zpt
--- a/zpt/manageMPIWGThesaurus.zpt Wed Oct 30 10:18:08 2013 +0100
+++ b/zpt/manageMPIWGThesaurus.zpt Wed Oct 30 17:43:03 2013 +0100
@@ -10,7 +10,7 @@
Overview
Uebersicht ueber alle vergebenenen Tags (TAB-getrennte Liste)
-
+Uebersicht ueber alle Projekte mit deren Tags (TAB-getrennte Liste)