Self-Hosted
/
changedetection.io
mirror of https://github.com/dgtlmoon/changedetection.io.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

feature: Support XPath2.0 to 3.1 (#1774)

Browse Source
pull/1748/merge
Constantin Hong 1 year ago committed by GitHub
parent 5229094e44
commit 26931e0167
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
10 changed files with 541 additions and 21 deletions
Show Stats Download Patch File Download Diff File

4
README.md
Unescape View File

@ -268,3 +268,7 @@ I offer commercial support, this software is depended on by network security, ae
[license-shield]: https://img.shields.io/github/license/dgtlmoon/changedetection.io.svg?style=for-the-badge [license-shield]: https://img.shields.io/github/license/dgtlmoon/changedetection.io.svg?style=for-the-badge
[release-link]: https://github.com/dgtlmoon/changedetection.io/releases [release-link]: https://github.com/dgtlmoon/changedetection.io/releases
[docker-link]: https://hub.docker.com/r/dgtlmoon/changedetection.io [docker-link]: https://hub.docker.com/r/dgtlmoon/changedetection.io
## Third-party licenses
changedetectionio.html_tools.elementpath_tostring: Copyright (c), 2018-2021, SISSA (Scuola Internazionale Superiore di Studi Avanzati), Licensed under [MIT license](https://github.com/sissaschool/elementpath/blob/master/LICENSE)

5
changedetectionio/blueprint/tags/templates/edit-tag.html
Unescape View File

@ -69,11 +69,12 @@ xpath://body/div/span[contains(@class, 'example-class')]",
{% endif %} {% endif %}
</ul> </ul>
</li> </li>
<li>XPath - Limit text to this XPath rule, simply start with a forward-slash, <li>XPath - Limit text to this XPath rule, simply start with a forward-slash. To specify XPath to be used explicitly or the XPath rule starts with an XPath function: Prefix with <code>xpath:</code>
<ul> <ul>
<li>Example: <code>//*[contains(@class, 'sametext')]</code> or <code>xpath://*[contains(@class, 'sametext')]</code>, <a <li>Example: <code>//*[contains(@class, 'sametext')]</code> or <code>xpath:count(//*[contains(@class, 'sametext')])</code>, <a
href="http://xpather.com/" target="new">test your XPath here</a></li> href="http://xpather.com/" target="new">test your XPath here</a></li>
<li>Example: Get all titles from an RSS feed <code>//title/text()</code></li> <li>Example: Get all titles from an RSS feed <code>//title/text()</code></li>
<li>To use XPath1.0: Prefix with <code>xpath1:</code></li>
</ul> </ul>
</li> </li>
</ul> </ul>

21
changedetectionio/forms.py
Unescape View File

@ -328,11 +328,30 @@ class ValidateCSSJSONXPATHInput(object):
return return
# Does it look like XPath? # Does it look like XPath?
if line.strip()[0] == '/': if line.strip()[0] == '/' or line.strip().startswith('xpath:'):
if not self.allow_xpath: if not self.allow_xpath:
raise ValidationError("XPath not permitted in this field!") raise ValidationError("XPath not permitted in this field!")
from lxml import etree, html from lxml import etree, html
import elementpath
# xpath 2.0-3.1
from elementpath.xpath3 import XPath3Parser
tree = html.fromstring("<html></html>") tree = html.fromstring("<html></html>")
line = line.replace('xpath:', '')
try:
elementpath.select(tree, line.strip(), parser=XPath3Parser)
except elementpath.ElementPathError as e:
message = field.gettext('\'%s\' is not a valid XPath expression. (%s)')
raise ValidationError(message % (line, str(e)))
except:
raise ValidationError("A system-error occurred when validating your XPath expression")
if line.strip().startswith('xpath1:'):
if not self.allow_xpath:
raise ValidationError("XPath not permitted in this field!")
from lxml import etree, html
tree = html.fromstring("<html></html>")
line = line.replace('xpath1:', '')
try: try:
tree.xpath(line.strip()) tree.xpath(line.strip())

79
changedetectionio/html_tools.py
Unescape View File

@ -69,10 +69,89 @@ def element_removal(selectors: List[str], html_content):
selector = ",".join(selectors) selector = ",".join(selectors)
return subtractive_css_selector(selector, html_content) return subtractive_css_selector(selector, html_content)
def elementpath_tostring(obj):
"""
change elementpath.select results to string type
# The MIT License (MIT), Copyright (c), 2018-2021, SISSA (Scuola Internazionale Superiore di Studi Avanzati)
# https://github.com/sissaschool/elementpath/blob/dfcc2fd3d6011b16e02bf30459a7924f547b47d0/elementpath/xpath_tokens.py#L1038
"""
import elementpath
from decimal import Decimal
import math
if obj is None:
return ''
# https://elementpath.readthedocs.io/en/latest/xpath_api.html#elementpath.select
elif isinstance(obj, elementpath.XPathNode):
return obj.string_value
elif isinstance(obj, bool):
return 'true' if obj else 'false'
elif isinstance(obj, Decimal):
value = format(obj, 'f')
if '.' in value:
return value.rstrip('0').rstrip('.')
return value
elif isinstance(obj, float):
if math.isnan(obj):
return 'NaN'
elif math.isinf(obj):
return str(obj).upper()
value = str(obj)
if '.' in value:
value = value.rstrip('0').rstrip('.')
if '+' in value:
value = value.replace('+', '')
if 'e' in value:
return value.upper()
return value
return str(obj)
# Return str Utf-8 of matched rules # Return str Utf-8 of matched rules
def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False, is_rss=False): def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False, is_rss=False):
from lxml import etree, html from lxml import etree, html
import elementpath
# xpath 2.0-3.1
from elementpath.xpath3 import XPath3Parser
parser = etree.HTMLParser()
if is_rss:
# So that we can keep CDATA for cdata_in_document_to_text() to process
parser = etree.XMLParser(strip_cdata=False)
tree = html.fromstring(bytes(html_content, encoding='utf-8'), parser=parser)
html_block = ""
r = elementpath.select(tree, xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'}, parser=XPath3Parser)
#@note: //title/text() wont work where <title>CDATA..
if type(r) != list:
r = [r]
for element in r:
# When there's more than 1 match, then add the suffix to separate each line
# And where the matched result doesn't include something that will cause Inscriptis to add a newline
# (This way each 'match' reliably has a new-line in the diff)
# Divs are converted to 4 whitespaces by inscriptis
if append_pretty_line_formatting and len(html_block) and (not hasattr( element, 'tag' ) or not element.tag in (['br', 'hr', 'div', 'p'])):
html_block += TEXT_FILTER_LIST_LINE_SUFFIX
if type(element) == str:
html_block += element
elif issubclass(type(element), etree._Element) or issubclass(type(element), etree._ElementTree):
html_block += etree.tostring(element, pretty_print=True).decode('utf-8')
else:
html_block += elementpath_tostring(element)
return html_block
# Return str Utf-8 of matched rules
# 'xpath1:'
def xpath1_filter(xpath_filter, html_content, append_pretty_line_formatting=False, is_rss=False):
from lxml import etree, html
parser = None parser = None
if is_rss: if is_rss:

5
changedetectionio/processors/text_json_diff.py
Unescape View File

@ -173,6 +173,11 @@ class perform_site_check(difference_detection_processor):
html_content=self.fetcher.content, html_content=self.fetcher.content,
append_pretty_line_formatting=not watch.is_source_type_url, append_pretty_line_formatting=not watch.is_source_type_url,
is_rss=is_rss) is_rss=is_rss)
elif filter_rule.startswith('xpath1:'):
html_content += html_tools.xpath1_filter(xpath_filter=filter_rule.replace('xpath1:', ''),
html_content=fetcher.content,
append_pretty_line_formatting=not is_source,
is_rss=is_rss)
else: else:
# CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
html_content += html_tools.include_filters(include_filters=filter_rule, html_content += html_tools.include_filters(include_filters=filter_rule,

10
changedetectionio/store.py
Unescape View File

@ -848,3 +848,13 @@ class ChangeDetectionStore:
self.data['watching'][uuid]['date_created'] = i self.data['watching'][uuid]['date_created'] = i
i+=1 i+=1
return return
# #1774 - protect xpath1 against migration
def update_14(self):
for awatch in self.__data["watching"]:
if self.__data["watching"][awatch]['include_filters']:
for num, selector in enumerate(self.__data["watching"][awatch]['include_filters']):
if selector.startswith('/'):
self.__data["watching"][awatch]['include_filters'][num] = 'xpath1:' + selector
if selector.startswith('xpath:'):
self.__data["watching"][awatch]['include_filters'][num] = selector.replace('xpath:', 'xpath1:', 1)

5
changedetectionio/templates/edit.html
Unescape View File

@ -290,11 +290,12 @@ xpath://body/div/span[contains(@class, 'example-class')]",
{% endif %} {% endif %}
</ul> </ul>
</li> </li>
<li>XPath - Limit text to this XPath rule, simply start with a forward-slash, <li>XPath - Limit text to this XPath rule, simply start with a forward-slash. To specify XPath to be used explicitly or the XPath rule starts with an XPath function: Prefix with <code>xpath:</code>
<ul> <ul>
<li>Example: <code>//*[contains(@class, 'sametext')]</code> or <code>xpath://*[contains(@class, 'sametext')]</code>, <a <li>Example: <code>//*[contains(@class, 'sametext')]</code> or <code>xpath:count(//*[contains(@class, 'sametext')])</code>, <a
href="http://xpather.com/" target="new">test your XPath here</a></li> href="http://xpather.com/" target="new">test your XPath here</a></li>
<li>Example: Get all titles from an RSS feed <code>//title/text()</code></li> <li>Example: Get all titles from an RSS feed <code>//title/text()</code></li>
<li>To use XPath1.0: Prefix with <code>xpath1:</code></li>
</ul> </ul>
</li> </li>
</ul> </ul>

223
changedetectionio/tests/test_xpath_selector.py
Unescape View File

@ -6,9 +6,11 @@ from .util import live_server_setup, wait_for_all_checks
from ..html_tools import * from ..html_tools import *
def test_setup(live_server): def test_setup(live_server):
live_server_setup(live_server) live_server_setup(live_server)
def set_original_response(): def set_original_response():
test_return_data = """<html> test_return_data = """<html>
<body> <body>
@ -26,6 +28,7 @@ def set_original_response():
f.write(test_return_data) f.write(test_return_data)
return None return None
def set_modified_response(): def set_modified_response():
test_return_data = """<html> test_return_data = """<html>
<body> <body>
@ -44,11 +47,12 @@ def set_modified_response():
return None return None
# Handle utf-8 charset replies https://github.com/dgtlmoon/changedetection.io/pull/613 # Handle utf-8 charset replies https://github.com/dgtlmoon/changedetection.io/pull/613
def test_check_xpath_filter_utf8(client, live_server): def test_check_xpath_filter_utf8(client, live_server):
filter='//item/*[self::description]' filter = '//item/*[self::description]'
d='''<?xml version="1.0" encoding="UTF-8"?> d = '''<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0"> <rss xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
<channel> <channel>
<title>rpilocator.com</title> <title>rpilocator.com</title>
@ -102,9 +106,9 @@ def test_check_xpath_filter_utf8(client, live_server):
# Handle utf-8 charset replies https://github.com/dgtlmoon/changedetection.io/pull/613 # Handle utf-8 charset replies https://github.com/dgtlmoon/changedetection.io/pull/613
def test_check_xpath_text_function_utf8(client, live_server): def test_check_xpath_text_function_utf8(client, live_server):
filter='//item/title/text()' filter = '//item/title/text()'
d='''<?xml version="1.0" encoding="UTF-8"?> d = '''<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0"> <rss xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
<channel> <channel>
<title>rpilocator.com</title> <title>rpilocator.com</title>
@ -163,15 +167,12 @@ def test_check_xpath_text_function_utf8(client, live_server):
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True) res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data assert b'Deleted' in res.data
def test_check_markup_xpath_filter_restriction(client, live_server):
def test_check_markup_xpath_filter_restriction(client, live_server):
xpath_filter = "//*[contains(@class, 'sametext')]" xpath_filter = "//*[contains(@class, 'sametext')]"
set_original_response() set_original_response()
# Give the endpoint time to spin up
time.sleep(1)
# Add our URL to the import page # Add our URL to the import page
test_url = url_for('test_endpoint', _external=True) test_url = url_for('test_endpoint', _external=True)
res = client.post( res = client.post(
@ -214,7 +215,6 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
def test_xpath_validation(client, live_server): def test_xpath_validation(client, live_server):
# Add our URL to the import page # Add our URL to the import page
test_url = url_for('test_endpoint', _external=True) test_url = url_for('test_endpoint', _external=True)
res = client.post( res = client.post(
@ -235,6 +235,48 @@ def test_xpath_validation(client, live_server):
assert b'Deleted' in res.data assert b'Deleted' in res.data
def test_xpath23_prefix_validation(client, live_server):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
res = client.post(
url_for("edit_page", uuid="first"),
data={"include_filters": "xpath:/something horrible", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"is not a valid XPath expression" in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_xpath1_validation(client, live_server):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
res = client.post(
url_for("edit_page", uuid="first"),
data={"include_filters": "xpath1:/something horrible", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"is not a valid XPath expression" in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# actually only really used by the distll.io importer, but could be handy too # actually only really used by the distll.io importer, but could be handy too
def test_check_with_prefix_include_filters(client, live_server): def test_check_with_prefix_include_filters(client, live_server):
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True) res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
@ -254,7 +296,8 @@ def test_check_with_prefix_include_filters(client, live_server):
res = client.post( res = client.post(
url_for("edit_page", uuid="first"), url_for("edit_page", uuid="first"),
data={"include_filters": "xpath://*[contains(@class, 'sametext')]", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"}, data={"include_filters": "xpath://*[contains(@class, 'sametext')]", "url": test_url, "tags": "", "headers": "",
'fetch_backend': "html_requests"},
follow_redirects=True follow_redirects=True
) )
@ -266,13 +309,15 @@ def test_check_with_prefix_include_filters(client, live_server):
follow_redirects=True follow_redirects=True
) )
assert b"Some text thats the same" in res.data #in selector assert b"Some text thats the same" in res.data # in selector
assert b"Some text that will change" not in res.data #not in selector assert b"Some text that will change" not in res.data # not in selector
client.get(url_for("form_delete", uuid="all"), follow_redirects=True) client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
def test_various_rules(client, live_server): def test_various_rules(client, live_server):
# Just check these don't error # Just check these don't error
#live_server_setup(live_server) # live_server_setup(live_server)
with open("test-datastore/endpoint-content.txt", "w") as f: with open("test-datastore/endpoint-content.txt", "w") as f:
f.write("""<html> f.write("""<html>
<body> <body>
@ -289,6 +334,7 @@ def test_various_rules(client, live_server):
</body> </body>
</html> </html>
""") """)
test_url = url_for('test_endpoint', _external=True) test_url = url_for('test_endpoint', _external=True)
res = client.post( res = client.post(
url_for("import_page"), url_for("import_page"),
@ -298,7 +344,6 @@ def test_various_rules(client, live_server):
assert b"1 Imported" in res.data assert b"1 Imported" in res.data
wait_for_all_checks(client) wait_for_all_checks(client)
for r in ['//div', '//a', 'xpath://div', 'xpath://a']: for r in ['//div', '//a', 'xpath://div', 'xpath://a']:
res = client.post( res = client.post(
url_for("edit_page", uuid="first"), url_for("edit_page", uuid="first"),
@ -313,3 +358,153 @@ def test_various_rules(client, live_server):
assert b"Updated watch." in res.data assert b"Updated watch." in res.data
res = client.get(url_for("index")) res = client.get(url_for("index"))
assert b'fetch-error' not in res.data, f"Should not see errors after '{r} filter" assert b'fetch-error' not in res.data, f"Should not see errors after '{r} filter"
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_xpath_20(client, live_server):
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
set_original_response()
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("edit_page", uuid="first"),
data={"include_filters": "//*[contains(@class, 'sametext')]|//*[contains(@class, 'changetext')]",
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
wait_for_all_checks(client)
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
assert b"Some text thats the same" in res.data # in selector
assert b"Some text that will change" in res.data # in selector
client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
def test_xpath_20_function_count(client, live_server):
set_original_response()
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
res = client.post(
url_for("edit_page", uuid="first"),
data={"include_filters": "xpath:count(//div) * 123456789987654321",
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
wait_for_all_checks(client)
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
assert b"246913579975308642" in res.data # in selector
client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
def test_xpath_20_function_count2(client, live_server):
set_original_response()
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
res = client.post(
url_for("edit_page", uuid="first"),
data={"include_filters": "/html/body/count(div) * 123456789987654321",
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
wait_for_all_checks(client)
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
assert b"246913579975308642" in res.data # in selector
client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
def test_xpath_20_function_string_join_matches(client, live_server):
set_original_response()
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
res = client.post(
url_for("edit_page", uuid="first"),
data={
"include_filters": "xpath:string-join(//*[contains(@class, 'sametext')]|//*[matches(@class, 'changetext')], 'specialconjunction')",
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
wait_for_all_checks(client)
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
assert b"Some text thats the samespecialconjunctionSome text that will change" in res.data # in selector
client.get(url_for("form_delete", uuid="all"), follow_redirects=True)

203
changedetectionio/tests/test_xpath_selector_unit.py
Unescape View File

@ -0,0 +1,203 @@
import sys
import os
import pytest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import html_tools
# test generation guide.
# 1. Do not include encoding in the xml declaration if the test object is a str type.
# 2. Always paraphrase test.
hotels = """
<hotel>
<branch location="California">
<staff>
<given_name>Christopher</given_name>
<surname>Anderson</surname>
<age>25</age>
</staff>
<staff>
<given_name>Christopher</given_name>
<surname>Carter</surname>
<age>30</age>
</staff>
</branch>
<branch location="Las Vegas">
<staff>
<given_name>Lisa</given_name>
<surname>Walker</surname>
<age>60</age>
</staff>
<staff>
<given_name>Jessica</given_name>
<surname>Walker</surname>
<age>32</age>
</staff>
<staff>
<given_name>Jennifer</given_name>
<surname>Roberts</surname>
<age>50</age>
</staff>
</branch>
</hotel>"""
@pytest.mark.parametrize("html_content", [hotels])
@pytest.mark.parametrize("xpath, answer", [('(//staff/given_name, //staff/age)', '25'),
("xs:date('2023-10-10')", '2023-10-10'),
("if (/hotel/branch[@location = 'California']/staff[1]/age = 25) then 'is 25' else 'is not 25'", 'is 25'),
("if (//hotel/branch[@location = 'California']/staff[1]/age = 25) then 'is 25' else 'is not 25'", 'is 25'),
("if (count(/hotel/branch/staff) = 5) then true() else false()", 'true'),
("if (count(//hotel/branch/staff) = 5) then true() else false()", 'true'),
("for $i in /hotel/branch/staff return if ($i/age >= 40) then upper-case($i/surname) else lower-case($i/surname)", 'anderson'),
("given_name = 'Christopher' and age = 40", 'false'),
("//given_name = 'Christopher' and //age = 40", 'false'),
#("(staff/given_name, staff/age)", 'Lisa'),
("(//staff/given_name, //staff/age)", 'Lisa'),
#("hotel/branch[@location = 'California']/staff/age union hotel/branch[@location = 'Las Vegas']/staff/age", ''),
("(//hotel/branch[@location = 'California']/staff/age union //hotel/branch[@location = 'Las Vegas']/staff/age)", '60'),
("(200 to 210)", "205"),
("(//hotel/branch[@location = 'California']/staff/age union //hotel/branch[@location = 'Las Vegas']/staff/age)", "50"),
("(1, 9, 9, 5)", "5"),
("(3, (), (14, 15), 92, 653)", "653"),
("for $i in /hotel/branch/staff return $i/given_name", "Christopher"),
("for $i in //hotel/branch/staff return $i/given_name", "Christopher"),
("distinct-values(for $i in /hotel/branch/staff return $i/given_name)", "Jessica"),
("distinct-values(for $i in //hotel/branch/staff return $i/given_name)", "Jessica"),
("for $i in (7 to 15) return $i*10", "130"),
("some $i in /hotel/branch/staff satisfies $i/age < 20", "false"),
("some $i in //hotel/branch/staff satisfies $i/age < 20", "false"),
("every $i in /hotel/branch/staff satisfies $i/age > 20", "true"),
("every $i in //hotel/branch/staff satisfies $i/age > 20 ", "true"),
("let $x := branch[@location = 'California'], $y := branch[@location = 'Las Vegas'] return (avg($x/staff/age), avg($y/staff/age))", "27.5"),
("let $x := //branch[@location = 'California'], $y := //branch[@location = 'Las Vegas'] return (avg($x/staff/age), avg($y/staff/age))", "27.5"),
("let $nu := 1, $de := 1000 return 'probability = ' || $nu div $de * 100 || '%'", "0.1%"),
("let $nu := 2, $probability := function ($argument) { 'probability = ' || $nu div $argument * 100 || '%'}, $de := 5 return $probability($de)", "40%"),
("'XPATH2.0-3.1 dissemination' instance of xs:string ", "true"),
("'new stackoverflow question incoming' instance of xs:integer ", "false"),
("'50000' cast as xs:integer", "50000"),
("//branch[@location = 'California']/staff[1]/surname eq 'Anderson'", "true"),
("fn:false()", "false")])
def test_hotels(html_content, xpath, answer):
html_content = html_tools.xpath_filter(xpath, html_content, append_pretty_line_formatting=True)
assert type(html_content) == str
assert answer in html_content
branches_to_visit = """<?xml version="1.0" ?>
<branches_to_visit>
<manager name="Godot" room_no="501">
<branch>Area 51</branch>
<branch>A place with no name</branch>
<branch>Stalsk12</branch>
</manager>
<manager name="Freya" room_no="305">
<branch>Stalsk12</branch>
<branch>Barcelona</branch>
<branch>Paris</branch>
</manager>
</branches_to_visit>"""
@pytest.mark.parametrize("html_content", [branches_to_visit])
@pytest.mark.parametrize("xpath, answer", [
("manager[@name = 'Godot']/branch union manager[@name = 'Freya']/branch", "Area 51"),
("//manager[@name = 'Godot']/branch union //manager[@name = 'Freya']/branch", "Stalsk12"),
("manager[@name = 'Godot']/branch | manager[@name = 'Freya']/branch", "Stalsk12"),
("//manager[@name = 'Godot']/branch | //manager[@name = 'Freya']/branch", "Stalsk12"),
("manager/branch intersect manager[@name = 'Godot']/branch", "A place with no name"),
("//manager/branch intersect //manager[@name = 'Godot']/branch", "A place with no name"),
("manager[@name = 'Godot']/branch intersect manager[@name = 'Freya']/branch", ""),
("manager/branch except manager[@name = 'Godot']/branch", "Barcelona"),
("manager[@name = 'Godot']/branch[1] eq 'Area 51'", "true"),
("//manager[@name = 'Godot']/branch[1] eq 'Area 51'", "true"),
("manager[@name = 'Godot']/branch[1] eq 'Seoul'", "false"),
("//manager[@name = 'Godot']/branch[1] eq 'Seoul'", "false"),
("manager[@name = 'Godot']/branch[2] eq manager[@name = 'Freya']/branch[2]", "false"),
("//manager[@name = 'Godot']/branch[2] eq //manager[@name = 'Freya']/branch[2]", "false"),
("manager[1]/@room_no lt manager[2]/@room_no", "false"),
("//manager[1]/@room_no lt //manager[2]/@room_no", "false"),
("manager[1]/@room_no gt manager[2]/@room_no", "true"),
("//manager[1]/@room_no gt //manager[2]/@room_no", "true"),
("manager[@name = 'Godot']/branch[1] = 'Area 51'", "true"),
("//manager[@name = 'Godot']/branch[1] = 'Area 51'", "true"),
("manager[@name = 'Godot']/branch[1] = 'Seoul'", "false"),
("//manager[@name = 'Godot']/branch[1] = 'Seoul'", "false"),
("manager[@name = 'Godot']/branch = 'Area 51'", "true"),
("//manager[@name = 'Godot']/branch = 'Area 51'", "true"),
("manager[@name = 'Godot']/branch = 'Barcelona'", "false"),
("//manager[@name = 'Godot']/branch = 'Barcelona'", "false"),
("manager[1]/@room_no > manager[2]/@room_no", "true"),
("//manager[1]/@room_no > //manager[2]/@room_no", "true"),
("manager[@name = 'Godot']/branch[ . = 'Stalsk12'] is manager[1]/branch[1]", "false"),
("//manager[@name = 'Godot']/branch[ . = 'Stalsk12'] is //manager[1]/branch[1]", "false"),
("manager[@name = 'Godot']/branch[ . = 'Stalsk12'] is manager[1]/branch[3]", "true"),
("//manager[@name = 'Godot']/branch[ . = 'Stalsk12'] is //manager[1]/branch[3]", "true"),
("manager[@name = 'Godot']/branch[ . = 'Stalsk12'] << manager[1]/branch[1]", "false"),
("//manager[@name = 'Godot']/branch[ . = 'Stalsk12'] << //manager[1]/branch[1]", "false"),
("manager[@name = 'Godot']/branch[ . = 'Stalsk12'] >> manager[1]/branch[1]", "true"),
("//manager[@name = 'Godot']/branch[ . = 'Stalsk12'] >> //manager[1]/branch[1]", "true"),
("manager[@name = 'Godot']/branch[ . = 'Stalsk12'] is manager[@name = 'Freya']/branch[ . = 'Stalsk12']", "false"),
("//manager[@name = 'Godot']/branch[ . = 'Stalsk12'] is //manager[@name = 'Freya']/branch[ . = 'Stalsk12']", "false"),
("manager[1]/@name || manager[2]/@name", "GodotFreya"),
("//manager[1]/@name || //manager[2]/@name", "GodotFreya"),
])
def test_branches_to_visit(html_content, xpath, answer):
html_content = html_tools.xpath_filter(xpath, html_content, append_pretty_line_formatting=True)
assert type(html_content) == str
assert answer in html_content
trips = """
<trips>
<trip reservation_number="10">
<depart>2023-10-06</depart>
<arrive>2023-10-10</arrive>
<traveler name="Christopher Anderson">
<duration>4</duration>
<price>2000.00</price>
</traveler>
</trip>
<trip reservation_number="12">
<depart>2023-10-06</depart>
<arrive>2023-10-12</arrive>
<traveler name="Frank Carter">
<duration>6</duration>
<price>3500.34</price>
</traveler>
</trip>
</trips>"""
@pytest.mark.parametrize("html_content", [trips])
@pytest.mark.parametrize("xpath, answer", [
("1 + 9 * 9 + 5 div 5", "83"),
("(1 + 9 * 9 + 5) div 6", "14.5"),
("23 idiv 3", "7"),
("23 div 3", "7.66666666"),
("for $i in ./trip return $i/traveler/duration * $i/traveler/price", "21002.04"),
("for $i in ./trip return $i/traveler/duration ", "4"),
("for $i in .//trip return $i/traveler/duration * $i/traveler/price", "21002.04"),
("sum(for $i in ./trip return $i/traveler/duration * $i/traveler/price)", "29002.04"),
("sum(for $i in .//trip return $i/traveler/duration * $i/traveler/price)", "29002.04"),
#("trip[1]/depart - trip[1]/arrive", "fail_to_get_answer"),
#("//trip[1]/depart - //trip[1]/arrive", "fail_to_get_answer"),
#("trip[1]/depart + trip[1]/arrive", "fail_to_get_answer"),
#("xs:date(trip[1]/depart) + xs:date(trip[1]/arrive)", "fail_to_get_answer"),
("(//trip[1]/arrive cast as xs:date) - (//trip[1]/depart cast as xs:date)", "P4D"),
("(//trip[1]/depart cast as xs:date) - (//trip[1]/arrive cast as xs:date)", "-P4D"),
("(//trip[1]/depart cast as xs:date) + xs:dayTimeDuration('P3D')", "2023-10-09"),
("(//trip[1]/depart cast as xs:date) - xs:dayTimeDuration('P3D')", "2023-10-03"),
("(456, 623) instance of xs:integer", "false"),
("(456, 623) instance of xs:integer*", "true"),
("/trips/trip instance of element()", "false"),
("/trips/trip instance of element()*", "true"),
("/trips/trip[1]/arrive instance of xs:date", "false"),
("date(/trips/trip[1]/arrive) instance of xs:date", "true"),
("'8' cast as xs:integer", "8"),
("'11.1E3' cast as xs:double", "11100"),
("6.5 cast as xs:integer", "6"),
#("/trips/trip[1]/arrive cast as xs:dateTime", "fail_to_get_answer"),
("/trips/trip[1]/arrive cast as xs:date", "2023-10-10"),
("('2023-10-12') cast as xs:date", "2023-10-12"),
("for $i in //trip return concat($i/depart, ' ', $i/arrive)", "2023-10-06 2023-10-10"),
])
def test_trips(html_content, xpath, answer):
html_content = html_tools.xpath_filter(xpath, html_content, append_pretty_line_formatting=True)
assert type(html_content) == str
assert answer in html_content

3
requirements.txt
Unescape View File

@ -46,6 +46,9 @@ beautifulsoup4
# XPath filtering, lxml is required by bs4 anyway, but put it here to be safe. # XPath filtering, lxml is required by bs4 anyway, but put it here to be safe.
lxml lxml
# XPath 2.0-3.1 support
elementpath
selenium~=4.14.0 selenium~=4.14.0
werkzeug~=3.0 werkzeug~=3.0

Write Preview
Loading…
Cancel
Save