denisa/bussines_case_automation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix Excel corruption issue when modifying XML content

Browse Source
This commit is contained in:
denisacirstea
2025-09-12 14:02:53 +03:00
parent 4e18caa8f7
commit 3bb09839ae
1 changed files with 44 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
update_excel.py
View File

@@ -248,7 +248,7 @@ def update_excel_with_direct_xml(excel_path, store_name):
# Create a temporary file for modification
temp_dir = os.path.dirname(os.path.abspath(excel_path))
temp_file = os.path.join(temp_dir, "_temp_for_xml_edit.xlsx")
temp_file = os.path.join(temp_dir, f"_temp_{os.path.basename(excel_path)}")
# Make a copy of the original file
import shutil
@@ -257,46 +257,50 @@ def update_excel_with_direct_xml(excel_path, store_name):
# Count of replacements
total_replacements = 0
# Process the Excel file
with ZipFile(temp_file, 'r') as zip_in:
with ZipFile(excel_path, 'w', ZIP_DEFLATED) as zip_out:
# Process each file in the zip
for item in zip_in.infolist():
content = zip_in.read(item.filename)
# Only modify XML files that might contain formulas or text
if item.filename.endswith('.xml'):
# Skip sheet8.xml which is the Variables sheet (based on common Excel structure)
if 'sheet8.xml' in item.filename:
print(f"Skipping Variables sheet: {item.filename}")
else:
# Convert to string for text replacement
try:
text_content = content.decode('utf-8')
# Check if this file contains our placeholder
if '{store_name}' in text_content:
# Count occurrences before replacement
occurrences = text_content.count('{store_name}')
total_replacements += occurrences
# Replace all instances of {store_name} with the actual store name
modified_content = text_content.replace('{store_name}', store_name)
# Convert back to bytes
content = modified_content.encode('utf-8')
print(f"Replaced {occurrences} instances of '{{store_name}}' in {item.filename}")
except UnicodeDecodeError:
# Not a text file, leave as is
pass
# Write the file (original or modified) to the new zip
zip_out.writestr(item, content)
# Process the Excel file - use a safer approach
# First read all files from the zip
files_data = {}
with ZipFile(excel_path, 'r') as zip_ref:
for item in zip_ref.infolist():
files_data[item.filename] = (zip_ref.read(item.filename), item)
# Clean up the temporary file
if os.path.exists(temp_file):
os.remove(temp_file)
# Modify the content
for filename, (content, item) in files_data.items():
# Only modify XML files that might contain formulas or text
if filename.endswith('.xml') or filename.endswith('.rels'):
# Skip sheet8.xml which is the Variables sheet (based on common Excel structure)
if 'sheet8.xml' in filename:
print(f"Skipping Variables sheet: {filename}")
continue
# Convert to string for text replacement
try:
text_content = content.decode('utf-8')
# Check if this file contains our placeholder
if '{store_name}' in text_content:
# Count occurrences before replacement
occurrences = text_content.count('{store_name}')
total_replacements += occurrences
# Replace all instances of {store_name} with the actual store name
modified_content = text_content.replace('{store_name}', store_name)
# Convert back to bytes
files_data[filename] = (modified_content.encode('utf-8'), item)
print(f"Replaced {occurrences} instances of '{{store_name}}' in {filename}")
except UnicodeDecodeError:
# Not a text file, leave as is
pass
# Write the modified zip file
with ZipFile(temp_file, 'w', ZIP_DEFLATED) as zip_out:
for filename, (content, item) in files_data.items():
zip_out.writestr(filename, content)
# Replace the original file with the modified one
shutil.move(temp_file, excel_path)
print(f"Total replacements: {total_replacements}")
return True