mirror of
https://github.com/got-feedBack/feedBack.git
synced 2026-07-22 04:41:23 +00:00
32ed564006
The GP→arrangement-XML writers persisted their output with
`Path.write_text(xml_str)` and no explicit encoding. On Windows that uses
the cp1252 default, so a non-ASCII metadata character — e.g. the © in an
album name like "Chrysalis©1982" — was written as the lone byte 0xA9.
The XML is read back as UTF-8 (expat's default), where 0xA9 is an invalid
start byte, so `parse_arrangement` died with:
xml.etree.ElementTree.ParseError: not well-formed (invalid token): line 10, column 22
and the whole Guitar Pro import failed (HTTP 500). All three arrangement
XML writes (gp2rs.py, gp2rs_gpx.py ×2) now pin encoding="utf-8".
CI runs on Linux (UTF-8 default) so the bug was invisible there; the new
test pins the locale-independent contract at the source level plus a
round-trip of a © album name.
Claude-Session: https://claude.ai/code/session_01EBQCHCNA81E9tHmSDHSe2Q
Signed-off-by: ChrisBeWithYou <christian.a.cowan@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
54 lines
2.0 KiB
Python
54 lines
2.0 KiB
Python
"""Regression: the GP→arrangement-XML writers must pin UTF-8.
|
|
|
|
A bare ``Path.write_text(xml_str)`` uses the platform's *default* text
|
|
encoding. On Windows that is cp1252, which encodes a non-ASCII metadata
|
|
character — e.g. the © in an album name like "Chrysalis©1982" — as the lone
|
|
byte 0xA9. The XML is then read back as UTF-8 (expat's default), where 0xA9
|
|
is an invalid start byte, so parsing dies with
|
|
|
|
not well-formed (invalid token): line N, column 22
|
|
|
|
CI runs on Linux (UTF-8 default), so the bug is invisible there and a plain
|
|
functional test would pass on the old code too. These assertions instead pin
|
|
the locale-independent contract directly.
|
|
"""
|
|
|
|
import inspect
|
|
import re
|
|
import xml.etree.ElementTree as ET
|
|
|
|
import gp2rs
|
|
import gp2rs_gpx
|
|
|
|
|
|
def test_arrangement_xml_writes_specify_utf8():
|
|
# Every write of the arrangement XML string must pass encoding="utf-8"
|
|
# so non-ASCII metadata survives regardless of the host locale.
|
|
for mod in (gp2rs, gp2rs_gpx):
|
|
src = inspect.getsource(mod)
|
|
bare = re.findall(r"\.write_text\(\s*xml_str\s*\)", src)
|
|
assert not bare, (
|
|
f"{mod.__name__}: XML write must pass encoding=\"utf-8\" — a bare "
|
|
f"write_text() uses the platform default (cp1252 on Windows) and "
|
|
f"mangles non-ASCII metadata into invalid UTF-8"
|
|
)
|
|
assert 'write_text(xml_str, encoding="utf-8")' in src, (
|
|
f"{mod.__name__}: expected a UTF-8-pinned arrangement XML write"
|
|
)
|
|
|
|
|
|
def test_utf8_write_round_trips_non_ascii_album():
|
|
# The behavioural end of the contract: a © album name written as UTF-8
|
|
# parses cleanly and reads back intact (the cp1252 write does not).
|
|
from pathlib import Path
|
|
import tempfile
|
|
|
|
xml_str = (
|
|
'<?xml version="1.0"?>\n<song>\n'
|
|
" <albumName>Chrysalis©1982</albumName>\n</song>\n"
|
|
)
|
|
path = Path(tempfile.mkdtemp()) / "arr.xml"
|
|
path.write_text(xml_str, encoding="utf-8")
|
|
root = ET.parse(path).getroot()
|
|
assert root.findtext("albumName") == "Chrysalis©1982"
|