qstommyshu commented on PR #15621:
URL: https://github.com/apache/datafusion/pull/15621#issuecomment-2784515058
> > I wrote a script to migrate the test
>
> Maybe you could attach your script here? So we can use it in the future if
we have a similar task again?
Not sure if it will be helpful. I wrote this script specifically for
migrating this specific test case as it has a very unique structure. Probably
need some modification if we want to use it for other tests.
Here is the script:
```Python
import re
def process_block(block_lines, test_index):
fields = {
"sql": [],
"expected": [],
"parser_dialect": [],
"unparser_dialect": []
}
current_field = None
field_pattern =
re.compile(r'^\s*(sql|expected|parser_dialect|unparser_dialect)\s*:\s*(.*)')
for line in block_lines:
m = field_pattern.match(line)
if m:
current_field = m.group(1)
content = m.group(2)
fields[current_field].append(content)
else:
if current_field is not None:
# skip if } is found
if re.match(r'^\s*\},\s*$', line):
continue
fields[current_field].append(line.rstrip("\n"))
# concat fields into a single line
for key in fields:
combined = "\n".join(fields[key]).strip()
if combined.endswith(','):
combined = combined[:-1].rstrip()
fields[key] = combined
# keep the sql field as it is
sql_value = fields["sql"]
# process expected field
expected_lines = fields["expected"].splitlines()
expected_comments = []
expected_string_lines = []
in_string = False
for line in expected_lines:
stripped = line.strip()
if not in_string and stripped.startswith("//"):
expected_comments.append(line.rstrip())
else:
# in_string once we met a non commented line
in_string = True
expected_string_lines.append(line.rstrip())
expected_string = "\n".join(expected_string_lines).strip()
# remove extra comma
if expected_string.endswith(','):
expected_string = expected_string[:-1].rstrip()
# remove Box::new()
def process_dialect(value):
value = value.strip()
m = re.match(r'Box::new\((.*)\)', value)
if m:
return m.group(1).strip()
else:
return value
parser_dialect_value = process_dialect(fields["parser_dialect"])
unparser_dialect_value = process_dialect(fields["unparser_dialect"])
# construction new tests
new_test = []
new_test.append(f"#[test]")
new_test.append(f"fn roundtrip_statement_with_dialect_{test_index}() ->
Result<(), DataFusionError> {{")
new_test.append(f" roundtrip_statement_with_dialect_helper!(")
new_test.append(f' sql: {sql_value},')
new_test.append(f' parser_dialect: {parser_dialect_value},')
new_test.append(f' unparser_dialect: {unparser_dialect_value},')
# put back comments
for comment in expected_comments:
new_test.append(f' {comment}')
new_test.append(f' expected: @{expected_string},')
new_test.append(f" );")
new_test.append(f" Ok(())")
new_test.append(f"}}")
return "\n".join(new_test)
def transform_file(filename):
with open(filename, "r", encoding="utf-8") as f:
lines = f.readlines()
output_lines = []
in_block = False
block_lines = []
test_index = 1
for line in lines:
if not in_block:
# new block
if "TestStatementWithDialect {" in line:
in_block = True
block_lines = [line]
else:
output_lines.append(line)
else:
block_lines.append(line)
if re.match(r'^\s*\},\s*$', line):
transformed_block = process_block(block_lines, test_index)
test_index += 1
output_lines.append(transformed_block + "\n")
in_block = False
block_lines = []
# write back to the original file
with open(filename, "w", encoding="utf-8") as f:
f.write("".join(output_lines))
if __name__ == "__main__":
transform_file("macro.txt")
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
