Commit b586934f authored by Eli Bendersky's avatar Eli Bendersky

Issue #17741: Rename IncrementalParser and its methods.

The new names are hopefully more descriptive and consistent. If you feel you
don't agree with this change, *please* read issue 17741 first - there's a lot of
discussion in there.
parent 1221f6b6
This diff is collapsed.
......@@ -402,10 +402,9 @@ xml.etree
---------
Add an event-driven parser for non-blocking applications,
:class:`~xml.etree.ElementTree.IncrementalParser`.
(Contributed by Antoine Pitrou in :issue:`17782`.)
:class:`~xml.etree.ElementTree.XMLPullParser`.
(Contributed by Antoine Pitrou in :issue:`17741`.)
Other improvements
==================
......
......@@ -950,24 +950,24 @@ class ElementTreeTest(unittest.TestCase):
self.assertEqual(serialized, expected)
class IncrementalParserTest(unittest.TestCase):
class XMLPullParserTest(unittest.TestCase):
def _feed(self, parser, data, chunk_size=None):
if chunk_size is None:
parser.data_received(data)
parser.feed(data)
else:
for i in range(0, len(data), chunk_size):
parser.data_received(data[i:i+chunk_size])
parser.feed(data[i:i+chunk_size])
def assert_event_tags(self, parser, expected):
events = parser.events()
events = parser.read_events()
self.assertEqual([(action, elem.tag) for action, elem in events],
expected)
def test_simple_xml(self):
for chunk_size in (None, 1, 5):
with self.subTest(chunk_size=chunk_size):
parser = ET.IncrementalParser()
parser = ET.XMLPullParser()
self.assert_event_tags(parser, [])
self._feed(parser, "<!-- comment -->\n", chunk_size)
self.assert_event_tags(parser, [])
......@@ -985,14 +985,14 @@ class IncrementalParserTest(unittest.TestCase):
])
self._feed(parser, "</root>\n", chunk_size)
self.assert_event_tags(parser, [('end', 'root')])
# Receiving EOF sets the `root` attribute
# Closing sets the `root` attribute
self.assertIs(parser.root, None)
parser.eof_received()
parser.close()
self.assertEqual(parser.root.tag, 'root')
def test_data_received_while_iterating(self):
parser = ET.IncrementalParser()
it = parser.events()
def test_feed_while_iterating(self):
parser = ET.XMLPullParser()
it = parser.read_events()
self._feed(parser, "<root>\n <element key='value'>text</element>\n")
action, elem = next(it)
self.assertEqual((action, elem.tag), ('end', 'element'))
......@@ -1003,7 +1003,7 @@ class IncrementalParserTest(unittest.TestCase):
next(it)
def test_simple_xml_with_ns(self):
parser = ET.IncrementalParser()
parser = ET.XMLPullParser()
self.assert_event_tags(parser, [])
self._feed(parser, "<!-- comment -->\n")
self.assert_event_tags(parser, [])
......@@ -1021,32 +1021,32 @@ class IncrementalParserTest(unittest.TestCase):
])
self._feed(parser, "</root>\n")
self.assert_event_tags(parser, [('end', '{namespace}root')])
# Receiving EOF sets the `root` attribute
# Closing sets the `root` attribute
self.assertIs(parser.root, None)
parser.eof_received()
parser.close()
self.assertEqual(parser.root.tag, '{namespace}root')
def test_ns_events(self):
parser = ET.IncrementalParser(events=('start-ns', 'end-ns'))
parser = ET.XMLPullParser(events=('start-ns', 'end-ns'))
self._feed(parser, "<!-- comment -->\n")
self._feed(parser, "<root xmlns='namespace'>\n")
self.assertEqual(
list(parser.events()),
list(parser.read_events()),
[('start-ns', ('', 'namespace'))])
self._feed(parser, "<element key='value'>text</element")
self._feed(parser, ">\n")
self._feed(parser, "<element>text</element>tail\n")
self._feed(parser, "<empty-element/>\n")
self._feed(parser, "</root>\n")
self.assertEqual(list(parser.events()), [('end-ns', None)])
parser.eof_received()
self.assertEqual(list(parser.read_events()), [('end-ns', None)])
parser.close()
def test_events(self):
parser = ET.IncrementalParser(events=())
parser = ET.XMLPullParser(events=())
self._feed(parser, "<root/>\n")
self.assert_event_tags(parser, [])
parser = ET.IncrementalParser(events=('start', 'end'))
parser = ET.XMLPullParser(events=('start', 'end'))
self._feed(parser, "<!-- comment -->\n")
self.assert_event_tags(parser, [])
self._feed(parser, "<root>\n")
......@@ -1064,12 +1064,12 @@ class IncrementalParserTest(unittest.TestCase):
('end', '{foo}element'),
])
self._feed(parser, "</root>")
parser.eof_received()
parser.close()
self.assertIs(parser.root, None)
self.assert_event_tags(parser, [('end', 'root')])
self.assertEqual(parser.root.tag, 'root')
parser = ET.IncrementalParser(events=('start',))
parser = ET.XMLPullParser(events=('start',))
self._feed(parser, "<!-- comment -->\n")
self.assert_event_tags(parser, [])
self._feed(parser, "<root>\n")
......@@ -1085,13 +1085,13 @@ class IncrementalParserTest(unittest.TestCase):
('start', '{foo}empty-element'),
])
self._feed(parser, "</root>")
parser.eof_received()
parser.close()
self.assertEqual(parser.root.tag, 'root')
def test_events_sequence(self):
# Test that events can be some sequence that's not just a tuple or list
eventset = {'end', 'start'}
parser = ET.IncrementalParser(events=eventset)
parser = ET.XMLPullParser(events=eventset)
self._feed(parser, "<foo>bar</foo>")
self.assert_event_tags(parser, [('start', 'foo'), ('end', 'foo')])
......@@ -1103,14 +1103,14 @@ class IncrementalParserTest(unittest.TestCase):
def __next__(self):
return next(self.events)
parser = ET.IncrementalParser(events=DummyIter())
parser = ET.XMLPullParser(events=DummyIter())
self._feed(parser, "<foo>bar</foo>")
self.assert_event_tags(parser, [('start', 'foo'), ('end', 'foo')])
def test_unknown_event(self):
with self.assertRaises(ValueError):
ET.IncrementalParser(events=('start', 'end', 'bogus'))
ET.XMLPullParser(events=('start', 'end', 'bogus'))
#
......@@ -2546,7 +2546,6 @@ def test_main(module=None):
ElementSlicingTest,
BasicElementTest,
ElementTreeTest,
IncrementalParserTest,
IOTest,
ParseErrorTest,
XIncludeTest,
......@@ -2555,6 +2554,7 @@ def test_main(module=None):
ElementIterTest,
TreeBuilderTest,
XMLParserTest,
XMLPullParserTest,
BugsTest,
]
......
......@@ -1210,37 +1210,39 @@ def iterparse(source, events=None, parser=None):
return _IterParseIterator(source, events, parser, close_source)
class IncrementalParser:
class XMLPullParser:
def __init__(self, events=None, *, _parser=None):
# The _parser argument is for internal use only and must not be relied
# upon in user code. It will be removed in a future release.
# See http://bugs.python.org/issue17741 for more details.
def __init__(self, events=None, parser=None):
# _elementtree.c expects a list, not a deque
self._events_queue = []
self._index = 0
self.root = self._root = None
if not parser:
parser = XMLParser(target=TreeBuilder())
self._parser = parser
self._parser = _parser or XMLParser(target=TreeBuilder())
# wire up the parser for event reporting
if events is None:
events = ("end",)
self._parser._setevents(self._events_queue, events)
def data_received(self, data):
def feed(self, data):
if self._parser is None:
raise ValueError("data_received() called after end of stream")
raise ValueError("feed() called after end of stream")
if data:
try:
self._parser.feed(data)
except SyntaxError as exc:
self._events_queue.append(exc)
def eof_received(self):
def close(self):
self._root = self._parser.close()
self._parser = None
if self._index >= len(self._events_queue):
self.root = self._root
def events(self):
def read_events(self):
events = self._events_queue
while True:
index = self._index
......@@ -1268,14 +1270,16 @@ class IncrementalParser:
class _IterParseIterator:
def __init__(self, source, events, parser, close_source=False):
self._parser = IncrementalParser(events, parser)
# Use the internal, undocumented _parser argument for now; When the
# parser argument of iterparse is removed, this can be killed.
self._parser = XMLPullParser(events=events, _parser=parser)
self._file = source
self._close_file = close_source
self.root = None
def __next__(self):
while 1:
for event in self._parser.events():
for event in self._parser.read_events():
return event
if self._parser._parser is None:
self.root = self._parser.root
......@@ -1283,11 +1287,11 @@ class _IterParseIterator:
self._file.close()
raise StopIteration
# load event buffer
data = self._file.read(16384)
data = self._file.read(16 * 1024)
if data:
self._parser.data_received(data)
self._parser.feed(data)
else:
self._parser.eof_received()
self._parser.close()
def __iter__(self):
return self
......@@ -1481,9 +1485,9 @@ class XMLParser:
pass # unknown
def _setevents(self, events_queue, events_to_report):
# Internal API for IncrementalParser
# Internal API for XMLPullParser
# events_to_report: a list of events to report during parsing (same as
# the *events* of IncrementalParser's constructor.
# the *events* of XMLPullParser's constructor.
# events_queue: a list of actual parsing events that will be populated
# by the underlying parser.
#
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment