Skip to content

bpo-40624: Add support for the XPath != operator in xml.etree #22147

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Nov 9, 2020
Merged

bpo-40624: Add support for the XPath != operator in xml.etree #22147

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9029602
bpo-40624: Add support for the XPath != operator in xml.etree
ammaraskar Sep 8, 2020
0fcd589
Apply suggestions from code review
ammaraskar Sep 8, 2020
db2cefa
Minor readability improvement by increasing the indentation.
scoder Sep 22, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 18 additions & 0 deletions Doc/library/xml.etree.elementtree.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -449,6 +449,12 @@ Supported XPath syntax
| | has the given value. The value cannot contain |
| | quotes. |
+-----------------------+------------------------------------------------------+
| ``[@attrib!='value']``| Selects all elements for which the given attribute |
| | does not have the given value. The value cannot |
| | contain quotes. |
| | |
| | .. versionadded:: 3.10 |
+-----------------------+------------------------------------------------------+
| ``[tag]`` | Selects all elements that have a child named |
| | ``tag``. Only immediate children are supported. |
+-----------------------+------------------------------------------------------+
Expand All @@ -457,10 +463,22 @@ Supported XPath syntax
| | |
| | .. versionadded:: 3.7 |
+-----------------------+------------------------------------------------------+
| ``[.!='text']`` | Selects all elements whose complete text content, |
| | including descendants, does not equal the given |
| | ``text``. |
| | |
| | .. versionadded:: 3.10 |
+-----------------------+------------------------------------------------------+
| ``[tag='text']`` | Selects all elements that have a child named |
| | ``tag`` whose complete text content, including |
| | descendants, equals the given ``text``. |
+-----------------------+------------------------------------------------------+
| ``[tag!='text']`` | Selects all elements that have a child named |
| | ``tag`` whose complete text content, including |
| | descendants, does not equal the given ``text``. |
| | |
| | .. versionadded:: 3.10 |
+-----------------------+------------------------------------------------------+
| ``[position]`` | Selects all elements that are located at the given |
| | position. The position can be either an integer |
| | (1 is the first position), the expression ``last()`` |
Expand Down
35 changes: 35 additions & 0 deletions Lib/test/test_xml_etree.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2852,8 +2852,12 @@ def test_findall(self):
['tag'] * 3)
self.assertEqual(summarize_list(e.findall('.//tag[@class="a"]')),
['tag'])
self.assertEqual(summarize_list(e.findall('.//tag[@class!="a"]')),
['tag'] * 2)
self.assertEqual(summarize_list(e.findall('.//tag[@class="b"]')),
['tag'] * 2)
self.assertEqual(summarize_list(e.findall('.//tag[@class!="b"]')),
['tag'])
self.assertEqual(summarize_list(e.findall('.//tag[@id]')),
['tag'])
self.assertEqual(summarize_list(e.findall('.//section[tag]')),
Expand All @@ -2875,6 +2879,19 @@ def test_findall(self):
self.assertEqual(summarize_list(e.findall(".//section[ tag = 'subtext' ]")),
['section'])

# Negations of above tests. They match nothing because the sole section
# tag has subtext.
self.assertEqual(summarize_list(e.findall(".//section[tag!='subtext']")),
[])
self.assertEqual(summarize_list(e.findall(".//section[tag !='subtext']")),
[])
self.assertEqual(summarize_list(e.findall(".//section[tag!= 'subtext']")),
[])
self.assertEqual(summarize_list(e.findall(".//section[tag != 'subtext']")),
[])
self.assertEqual(summarize_list(e.findall(".//section[ tag != 'subtext' ]")),
[])

self.assertEqual(summarize_list(e.findall(".//tag[.='subtext']")),
['tag'])
self.assertEqual(summarize_list(e.findall(".//tag[. ='subtext']")),
Expand All @@ -2890,6 +2907,24 @@ def test_findall(self):
self.assertEqual(summarize_list(e.findall(".//tag[.= ' subtext']")),
[])

# Negations of above tests.
# Matches everything but the tag containing subtext
self.assertEqual(summarize_list(e.findall(".//tag[.!='subtext']")),
['tag'] * 3)
self.assertEqual(summarize_list(e.findall(".//tag[. !='subtext']")),
['tag'] * 3)
self.assertEqual(summarize_list(e.findall('.//tag[.!= "subtext"]')),
['tag'] * 3)
self.assertEqual(summarize_list(e.findall('.//tag[ . != "subtext" ]')),
['tag'] * 3)
self.assertEqual(summarize_list(e.findall(".//tag[. != 'subtext']")),
['tag'] * 3)
# Matches all tags.
self.assertEqual(summarize_list(e.findall(".//tag[. != 'subtext ']")),
['tag'] * 4)
self.assertEqual(summarize_list(e.findall(".//tag[.!= ' subtext']")),
['tag'] * 4)

# duplicate section => 2x tag matches
e[1] = e[2]
self.assertEqual(summarize_list(e.findall(".//section[tag = 'subtext']")),
Expand Down
31 changes: 24 additions & 7 deletions Lib/xml/etree/ElementPath.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,8 +65,9 @@
r"//?|"
r"\.\.|"
r"\(\)|"
r"!=|"
r"[/.*:\[\]\(\)@=])|"
r"((?:\{[^}]+\})?[^/\[\]\(\)@=\s]+)|"
r"((?:\{[^}]+\})?[^/\[\]\(\)@!=\s]+)|"
r"\s+"
)

Expand Down Expand Up @@ -253,15 +254,19 @@ def select(context, result):
if elem.get(key) is not None:
yield elem
return select
if signature == "@-='":
# [@attribute='value']
if signature == "@-='" or signature == "@-!='":
# [@attribute='value'] or [@attribute!='value']
key = predicate[1]
value = predicate[-1]
def select(context, result):
for elem in result:
if elem.get(key) == value:
yield elem
return select
def select_negated(context, result):
for elem in result:
if (attr_value := elem.get(key)) is not None and attr_value != value:
yield elem
return select_negated if '!=' in signature else select
if signature == "-" and not re.match(r"\-?\d+$", predicate[0]):
# [tag]
tag = predicate[0]
Expand All @@ -270,8 +275,10 @@ def select(context, result):
if elem.find(tag) is not None:
yield elem
return select
if signature == ".='" or (signature == "-='" and not re.match(r"\-?\d+$", predicate[0])):
# [.='value'] or [tag='value']
if signature == ".='" or signature == ".!='" or (
(signature == "-='" or signature == "-!='")
and not re.match(r"\-?\d+$", predicate[0])):
# [.='value'] or [tag='value'] or [.!='value'] or [tag!='value']
tag = predicate[0]
value = predicate[-1]
if tag:
Expand All @@ -281,12 +288,22 @@ def select(context, result):
if "".join(e.itertext()) == value:
yield elem
break
def select_negated(context, result):
for elem in result:
for e in elem.iterfind(tag):
if "".join(e.itertext()) != value:
yield elem
break
else:
def select(context, result):
for elem in result:
if "".join(elem.itertext()) == value:
yield elem
return select
def select_negated(context, result):
for elem in result:
if "".join(elem.itertext()) != value:
yield elem
return select_negated if '!=' in signature else select
if signature == "-" or signature == "-()" or signature == "-()-":
# [index] or [last()] or [last()-index]
if signature == "-":
Expand Down
1 change: 1 addition & 0 deletions Misc/NEWS.d/next/Library/2020-09-08-03-19-04.bpo-40624.0-gYfx.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Added support for the XPath ``!=`` operator in xml.etree