mirror of
https://github.com/jmcnamara/libxlsxwriter
synced 2025-03-28 21:13:14 +00:00
test: update python test runner
This commit is contained in:
John McNamara
parent
545939dfd3
commit
61a3ceaf9a
@ -6,29 +6,26 @@
|
||||
# Copyright 2014-2025, John McNamara, jmcnamara@cpan.org.
|
||||
#
|
||||
|
||||
import re
|
||||
import sys
|
||||
import os.path
|
||||
from zipfile import ZipFile
|
||||
from zipfile import BadZipfile
|
||||
from zipfile import LargeZipFile
|
||||
import re
|
||||
from zipfile import BadZipFile, LargeZipFile, ZipFile
|
||||
|
||||
|
||||
def _xml_to_list(xml_str):
|
||||
# Convert test generated XML strings into lists for comparison testing.
|
||||
|
||||
# Split the XML string at tag boundaries.
|
||||
parser = re.compile(r'>\s*<')
|
||||
parser = re.compile(r">\s*<")
|
||||
elements = parser.split(xml_str.strip())
|
||||
|
||||
elements = [s.replace("\r", "") for s in elements]
|
||||
|
||||
# Add back the removed brackets.
|
||||
for index, element in enumerate(elements):
|
||||
if not element[0] == '<':
|
||||
elements[index] = '<' + elements[index]
|
||||
if not element[-1] == '>':
|
||||
elements[index] = elements[index] + '>'
|
||||
if not element[0] == "<":
|
||||
elements[index] = "<" + elements[index]
|
||||
if not element[-1] == ">":
|
||||
elements[index] = elements[index] + ">"
|
||||
|
||||
return elements
|
||||
|
||||
@ -43,7 +40,7 @@ def _vml_to_list(vml_str):
|
||||
vml_str = vml_str.replace("\r", "")
|
||||
|
||||
vml = vml_str.split("\n")
|
||||
vml_str = ''
|
||||
vml_str = ""
|
||||
|
||||
for line in vml:
|
||||
# Skip blank lines.
|
||||
@ -61,11 +58,11 @@ def _vml_to_list(vml_str):
|
||||
line += " "
|
||||
|
||||
# Add newline after element end.
|
||||
if re.search('>$', line):
|
||||
if re.search(">$", line):
|
||||
line += "\n"
|
||||
|
||||
# Split multiple elements.
|
||||
line = line.replace('><', ">\n<")
|
||||
line = line.replace("><", ">\n<")
|
||||
|
||||
# Put all of Anchor on one line.
|
||||
if line == "<x:Anchor>\n":
|
||||
@ -109,28 +106,28 @@ def _compare_xlsx_files(got_file, exp_file, ignore_files, ignore_elements):
|
||||
# XML file into an list of XML elements.
|
||||
try:
|
||||
# Open the XlsxWriter as a zip file for testing.
|
||||
got_zip = ZipFile(got_file, 'r')
|
||||
got_zip = ZipFile(got_file, "r")
|
||||
except IOError:
|
||||
# For Python 2.5+ compatibility.
|
||||
e = sys.exc_info()[1]
|
||||
error = "XlsxWriter file error: " + str(e)
|
||||
return error, ''
|
||||
return error, ""
|
||||
except (BadZipfile, LargeZipFile):
|
||||
e = sys.exc_info()[1]
|
||||
error = "XlsxWriter zipfile error, '" + exp_file + "': " + str(e)
|
||||
return error, ''
|
||||
return error, ""
|
||||
|
||||
try:
|
||||
# Open the Excel as a zip file for testing.
|
||||
exp_zip = ZipFile(exp_file, 'r')
|
||||
exp_zip = ZipFile(exp_file, "r")
|
||||
except IOError:
|
||||
e = sys.exc_info()[1]
|
||||
error = "Excel file error: " + str(e)
|
||||
return error, ''
|
||||
return error, ""
|
||||
except (BadZipfile, LargeZipFile):
|
||||
e = sys.exc_info()[1]
|
||||
error = "Excel zipfile error, '" + exp_file + "': " + str(e)
|
||||
return error, ''
|
||||
return error, ""
|
||||
|
||||
# Get the filenames from the zip files.
|
||||
got_files = sorted(got_zip.namelist())
|
||||
@ -146,57 +143,58 @@ def _compare_xlsx_files(got_file, exp_file, ignore_files, ignore_elements):
|
||||
|
||||
# Compare each file in the XLSX containers.
|
||||
for filename in exp_files:
|
||||
|
||||
got_xml_str = got_zip.read(filename)
|
||||
exp_xml_str = exp_zip.read(filename)
|
||||
|
||||
# Compare binary files with string comparison based on extension.
|
||||
extension = os.path.splitext(filename)[1]
|
||||
if extension in ('.png', '.jpeg', '.gif','.bmp', '.bin'):
|
||||
if extension in (".png", ".jpeg", ".gif", ".bmp", ".wmf", ".emf", ".bin"):
|
||||
if got_xml_str != exp_xml_str:
|
||||
return 'got: %s' % filename, 'exp: %s' % filename
|
||||
return f"got: {filename}", f"exp: {filename}"
|
||||
continue
|
||||
|
||||
if sys.version_info >= (3, 0, 0):
|
||||
got_xml_str = got_xml_str.decode('utf-8')
|
||||
exp_xml_str = exp_xml_str.decode('utf-8')
|
||||
got_xml_str = got_xml_str.decode("utf-8")
|
||||
exp_xml_str = exp_xml_str.decode("utf-8")
|
||||
|
||||
# Check for errant xml tags in the generated file.
|
||||
if "<<" in got_xml_str:
|
||||
return f"Double start tag in XlsxWriter file {filename}", ""
|
||||
|
||||
# Remove dates and user specific data from the core.xml data.
|
||||
if filename == 'docProps/core.xml':
|
||||
exp_xml_str = re.sub(r' ?John', '', exp_xml_str)
|
||||
exp_xml_str = re.sub(r'\d\d\d\d-\d\d-\d\dT\d\d\:\d\d:\d\dZ',
|
||||
'', exp_xml_str)
|
||||
got_xml_str = re.sub(r'\d\d\d\d-\d\d-\d\dT\d\d\:\d\d:\d\dZ',
|
||||
'', got_xml_str)
|
||||
if filename == "docProps/core.xml":
|
||||
exp_xml_str = re.sub(r" ?John", "", exp_xml_str)
|
||||
exp_xml_str = re.sub(
|
||||
r"\d\d\d\d-\d\d-\d\dT\d\d\:\d\d:\d\dZ", "", exp_xml_str
|
||||
)
|
||||
got_xml_str = re.sub(
|
||||
r"\d\d\d\d-\d\d-\d\dT\d\d\:\d\d:\d\dZ", "", got_xml_str
|
||||
)
|
||||
|
||||
# Remove workbookView dimensions which are almost always different
|
||||
# and calcPr which can have different Excel version ids.
|
||||
if filename == 'xl/workbook.xml':
|
||||
exp_xml_str = re.sub(r'<workbookView[^>]*>',
|
||||
'<workbookView/>', exp_xml_str)
|
||||
got_xml_str = re.sub(r'<workbookView[^>]*>',
|
||||
'<workbookView/>', got_xml_str)
|
||||
exp_xml_str = re.sub(r'<calcPr[^>]*>',
|
||||
'<calcPr/>', exp_xml_str)
|
||||
got_xml_str = re.sub(r'<calcPr[^>]*>',
|
||||
'<calcPr/>', got_xml_str)
|
||||
if filename == "xl/workbook.xml":
|
||||
exp_xml_str = re.sub(r"<workbookView[^>]*>", "<workbookView/>", exp_xml_str)
|
||||
got_xml_str = re.sub(r"<workbookView[^>]*>", "<workbookView/>", got_xml_str)
|
||||
exp_xml_str = re.sub(r"<calcPr[^>]*>", "<calcPr/>", exp_xml_str)
|
||||
got_xml_str = re.sub(r"<calcPr[^>]*>", "<calcPr/>", got_xml_str)
|
||||
|
||||
# Remove printer specific settings from Worksheet pageSetup elements.
|
||||
if re.match(r'xl/worksheets/sheet\d.xml', filename):
|
||||
exp_xml_str = re.sub(r'horizontalDpi="200" ', '', exp_xml_str)
|
||||
exp_xml_str = re.sub(r'verticalDpi="200" ', '', exp_xml_str)
|
||||
exp_xml_str = re.sub(r'(<pageSetup[^>]*) r:id="rId1"',
|
||||
r'\1', exp_xml_str)
|
||||
if re.match(r"xl/worksheets/sheet\d.xml", filename):
|
||||
exp_xml_str = re.sub(r'horizontalDpi="200" ', "", exp_xml_str)
|
||||
exp_xml_str = re.sub(r'verticalDpi="200" ', "", exp_xml_str)
|
||||
exp_xml_str = re.sub(r'(<pageSetup[^>]*) r:id="rId1"', r"\1", exp_xml_str)
|
||||
|
||||
# Remove Chart pageMargin dimensions which are almost always different.
|
||||
if re.match(r'xl/charts/chart\d.xml', filename):
|
||||
exp_xml_str = re.sub(r'<c:pageMargins[^>]*>',
|
||||
'<c:pageMargins/>', exp_xml_str)
|
||||
got_xml_str = re.sub(r'<c:pageMargins[^>]*>',
|
||||
'<c:pageMargins/>', got_xml_str)
|
||||
if re.match(r"xl/charts/chart\d.xml", filename):
|
||||
exp_xml_str = re.sub(
|
||||
r"<c:pageMargins[^>]*>", "<c:pageMargins/>", exp_xml_str
|
||||
)
|
||||
got_xml_str = re.sub(
|
||||
r"<c:pageMargins[^>]*>", "<c:pageMargins/>", got_xml_str
|
||||
)
|
||||
|
||||
# Convert the XML string to lists for comparison.
|
||||
if re.search('.vml$', filename):
|
||||
if re.search(".vml$", filename):
|
||||
got_xml = _xml_to_list(got_xml_str)
|
||||
exp_xml = _vml_to_list(exp_xml_str)
|
||||
else:
|
||||
@ -212,10 +210,14 @@ def _compare_xlsx_files(got_file, exp_file, ignore_files, ignore_elements):
|
||||
got_xml = [tag for tag in got_xml if not re.match(pattern, tag)]
|
||||
|
||||
# Reorder the XML elements in the XLSX relationship files.
|
||||
if filename == '[Content_Types].xml' or re.search('.rels$', filename):
|
||||
if filename == "[Content_Types].xml" or re.search(".rels$", filename):
|
||||
got_xml = _sort_rel_file_data(got_xml)
|
||||
exp_xml = _sort_rel_file_data(exp_xml)
|
||||
|
||||
# Indent the XML elements to make the visual comparison of failures easier.
|
||||
got_xml = _indent_elements(got_xml)
|
||||
exp_xml = _indent_elements(exp_xml)
|
||||
|
||||
# Compared the XML elements in each file.
|
||||
if got_xml != exp_xml:
|
||||
got_xml.insert(0, filename)
|
||||
@ -223,4 +225,42 @@ def _compare_xlsx_files(got_file, exp_file, ignore_files, ignore_elements):
|
||||
return got_xml, exp_xml
|
||||
|
||||
# If we got here the files are the same.
|
||||
return 'Ok', 'Ok'
|
||||
return "Ok", "Ok"
|
||||
|
||||
|
||||
def compare_xlsx_files(file1, file2, ignore_files=None, ignore_elements=None):
|
||||
"""
|
||||
External wrapper function to allow simplified equality testing of two Excel
|
||||
files. Note, this function doesn't test equivalence, only equality.
|
||||
|
||||
"""
|
||||
if ignore_files is None:
|
||||
ignore_files = []
|
||||
|
||||
if ignore_elements is None:
|
||||
ignore_elements = []
|
||||
|
||||
got, exp = _compare_xlsx_files(file1, file2, ignore_files, ignore_elements)
|
||||
|
||||
return got == exp
|
||||
|
||||
|
||||
# Indent XML elements to make the visual comparison of failures easier.
|
||||
def _indent_elements(xml_elements):
|
||||
indent_level = 0
|
||||
indented_elements = []
|
||||
|
||||
for element in xml_elements:
|
||||
if element.startswith("</"):
|
||||
indent_level -= 1
|
||||
|
||||
indented_elements.append(" " * indent_level + element)
|
||||
|
||||
if (
|
||||
not element.startswith("</")
|
||||
and "</" not in element
|
||||
and not element.endswith("/>")
|
||||
):
|
||||
indent_level += 1
|
||||
|
||||
return indented_elements
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user