Merge pull request #2777 from tirkarthi/fix-xml

cElementTree has been deprecated since Python 3.3 and removed in Python 3.9

gensim/corpora/wikicorpus.py

@@ -25,8 +25,12 @@
 import re
 import signal
 from pickle import PicklingError
-from xml.etree.cElementTree import \
-    iterparse  # LXML isn't faster, so let's go with the built-in solution
+# LXML isn't faster, so let's go with the built-in solution
+try:
+    from xml.etree.cElementTree import iterparse
+except ImportError:
+    from xml.etree.ElementTree import iterparse
+
 
 from gensim import utils
 # cannot import whole gensim.corpora, because that imports wikicorpus...

gensim/scripts/segment_wiki.py

@@ -61,7 +61,10 @@
 import multiprocessing
 import re
 import sys
-from xml.etree import cElementTree
+try:
+    from xml.etree import cElementTree as ET
+except ImportError:
+    from xml.etree import ElementTree as ET
 from functools import partial
 
 from gensim.corpora.wikicorpus import IGNORED_NAMESPACES, WikiCorpus, filter_wiki, find_interlinks, get_namespace, utils
@@ -183,7 +186,7 @@ def extract_page_xmls(f):
         XML strings for page tags.
 
     """
-    elems = (elem for _, elem in cElementTree.iterparse(f, events=("end",)))
+    elems = (elem for _, elem in ET.iterparse(f, events=("end",)))
 
     elem = next(elems)
     namespace = get_namespace(elem.tag)
@@ -192,7 +195,7 @@ def extract_page_xmls(f):
 
     for elem in elems:
         if elem.tag == page_tag:
-            yield cElementTree.tostring(elem)
+            yield ET.tostring(elem)
             # Prune the element tree, as per
             # http://www.ibm.com/developerworks/xml/library/x-hiperfparse/
             # except that we don't need to prune backlinks from the parent
@@ -221,7 +224,7 @@ def segment(page_xml, include_interlinks=False):
         (Optionally) [(interlink_article, interlink_text), ...]).
 
     """
-    elem = cElementTree.fromstring(page_xml)
+    elem = ET.fromstring(page_xml)
     filter_namespaces = ('0',)
     namespace = get_namespace(elem.tag)
     ns_mapping = {"ns": namespace}