version 1.1.2.3, 2008/08/26 14:00:41
|
version 1.1.2.6, 2008/08/28 18:20:09
|
Line 1
|
Line 1
|
from types import * |
from types import * |
|
import logging |
definedFields=['WEB_title','xdata_01','xdata_02','xdata_03','xdata_04','xdata_05','xdata_06','xdata_07','xdata_08','xdata_09','xdata_10','xdata_11','xdata_12','xdata_13','WEB_project_header','WEB_project_description','WEB_related_pub'] |
definedFields=['WEB_title','xdata_01','xdata_02','xdata_03','xdata_04','xdata_05','xdata_06','xdata_07','xdata_08','xdata_09','xdata_10','xdata_11','xdata_12','xdata_13','WEB_project_header','WEB_project_description','WEB_related_pub'] |
|
|
checkFields = ['xdata_01'] |
checkFields = ['xdata_01'] |
Line 23 def sortStopWordsF(self,xo,yo):
|
Line 23 def sortStopWordsF(self,xo,yo):
|
if not hasattr(self,'_v_stopWords'): |
if not hasattr(self,'_v_stopWords'): |
self._v_stopWords=self.stopwords_en.data.split("\n") |
self._v_stopWords=self.stopwords_en.data.split("\n") |
|
|
x=str(xo[1]) |
x=unicodify(xo[1]) |
y=str(yo[1]) |
y=unicodify(yo[1]) |
|
|
strx=x.split(" ") |
strx=x.split(" ") |
stry=y.split(" ") |
stry=y.split(" ") |
Line 77 def sortI(x,y):
|
Line 77 def sortI(x,y):
|
|
|
def unicodify(str): |
def unicodify(str): |
"""decode str (utf-8 or latin-1 representation) into unicode object""" |
"""decode str (utf-8 or latin-1 representation) into unicode object""" |
logging.error("unicodify: %s"%str) |
#logging.error("unicodify: %s"%str) |
if not str: |
if not str: |
return "" |
return "" |
if type(str) is StringType: |
if type(str) is StringType: |
Line 97 def utf8ify(str):
|
Line 97 def utf8ify(str):
|
else: |
else: |
return str.encode('utf-8') |
return str.encode('utf-8') |
|
|
|
|
|
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.""" |
|
l1 = int((l - len(ellipsis)) / 2) |
|
return "%s%s%s"%(s[:l1],ellipsis,s[-l1:]) |