This is an archive of the discontinued LLVM Phabricator instance.

Differential D68986

[LNT] Python 3 support: adapt XML parsing with extra entities
ClosedPublic

Authored by thopre on Oct 15 2019, 7:14 AM.

Details

Reviewers
cmatthews
hubert.reinterpretcast
kristof.beyls
leandron
PrzemekWirkus
Summary

Test server/ui/V4Pages.py parses XML with non standard entities using
the ElementTree's XML parser. However the method it uses to declare the
non standard entities are no longer available in Python 3's ElementTree.
This commit instead modifies the DOCTYPE element in the XML directly
before passing it to ElementTree's XML parser.

Diff Detail

Revision Contents

PathSize
tests/
server/
ui/
11 lines

Diff 225029

tests/server/ui/V4Pages.py

Show All 13 Lines
# #
# RUN: lnt import %t.instance %S/Inputs/sample-failed-report1.json # RUN: lnt import %t.instance %S/Inputs/sample-failed-report1.json
# RUN: lnt import %t.instance %S/Inputs/sample-failed-report2.json # RUN: lnt import %t.instance %S/Inputs/sample-failed-report2.json
# #
# RUN: python %s %t.instance %{tidylib} # RUN: python %s %t.instance %{tidylib}
from future import standard_library from future import standard_library
standard_library.install_aliases() standard_library.install_aliases()
from builtins import chr
import logging import logging
import re import re
import sys import sys
import xml.etree.ElementTree as ET import xml.etree.ElementTree as ET
from html.entities import name2codepoint from html.entities import name2codepoint
from flask import session from flask import session
import lnt.server.db.migrate import lnt.server.db.migrate
import lnt.server.ui.app import lnt.server.ui.app
▲ Show 20 Lines • Show All 76 Lines • ▼ Show 20 Lines
def dump_html(html_string): def dump_html(html_string):
for linenr, line in enumerate(html_string.split('\n')): for linenr, line in enumerate(html_string.split('\n')):
print("%4d:%s" % (linenr + 1, line)) print("%4d:%s" % (linenr + 1, line))
def get_xml_tree(html_string): def get_xml_tree(html_string):
try: try:
parser = ET.XMLParser() entities_defs = []
parser.parser.UseForeignDTD(True) for x, i in name2codepoint.items():
parser.entity.update((x, chr(i)) for x, i in name2codepoint.items()) entities_defs.append(' <!ENTITY {x} "&#{i};">'.format(**locals()))
tree = ET.fromstring(html_string, parser=parser) docstring = "<!DOCTYPE html [\n{}\n]>".format('\n'.join(entities_defs))
html_string = html_string.replace("<!DOCTYPE html>", docstring, 1)
tree = ET.fromstring(html_string)
except: # noqa FIXME: figure out what we expect this to throw. except: # noqa FIXME: figure out what we expect this to throw.
dump_html(html_string) dump_html(html_string)
raise raise
return tree return tree
def find_table_by_thead_content(tree, table_head_contents): def find_table_by_thead_content(tree, table_head_contents):
all_tables = tree.findall(".//thead/..") all_tables = tree.findall(".//thead/..")
▲ Show 20 Lines • Show All 547 Lines • Show Last 20 Lines