qurator-spk/modstool
1
0
Fork 0
mirror of https://github.com/qurator-spk/modstool.git synced 2025-08-28 19:09:53 +02:00
Code Issues Releases Wiki Activity

🧹 Use stacklevel for warnings, enable ruff rules 'B'

Browse source
This commit is contained in:
Mike Gerber 2025-08-21 16:04:29 +02:00
parent 48d7bb3dc4
commit 9137cc9c4b
4 changed files with 35 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

2
pyproject.toml
View file

@ -48,7 +48,7 @@ where = ["src"]
[tool.ruff]
line-length = 120
lint.select = ["E", "F", "I"]
lint.select = ["E", "F", "I", "B"]
[tool.liccheck]

2
src/mods4pandas/alto4pandas.py
View file

@ -157,7 +157,7 @@ def walk(m):
try:
yield from walk(f.path)
except PermissionError:
warnings.warn(f"Error walking {f.path}")
warnings.warn(f"Error walking {f.path}", stacklevel=1)
else:
yield m.path

45
src/mods4pandas/lib.py
View file

@ -88,7 +88,7 @@ class TagGroup:
new_group.append(e)
else:
if warn:
warnings.warn("Filtered {} element ({})".format(self.tag, warn))
warnings.warn(f"Filtered {self.tag} element ({warn})", stacklevel=1)
return TagGroup(self.tag, new_group)
def force_singleton(self, warn=True) -> TagGroup:
@ -96,7 +96,7 @@ class TagGroup:
return self
else:
if warn:
warnings.warn("Forced single instance of {}".format(self.tag))
warnings.warn(f"Forced single instance of {self.tag}", stacklevel=1)
return TagGroup(self.tag, self.group[:1])
RE_ISO8601_DATE = r"^\d{2}(\d{2}|XX)(-\d{2}-\d{2})?$" # Note: Includes non-specific century dates like '18XX'
@ -106,31 +106,33 @@ class TagGroup:
for e in self.group:
if e.attrib.get("encoding") == "w3cdtf":
# This should be 'iso8601' according to MODS-AP 2.3.1
warnings.warn("Changed w3cdtf encoding to iso8601")
warnings.warn("Changed w3cdtf encoding to iso8601", stacklevel=1)
e.attrib["encoding"] = "iso8601"
new_group = []
for e in self.group:
if e.text is None:
warnings.warn("Empty date")
warnings.warn("Empty date", stacklevel=1)
continue
if e.attrib.get("encoding") == "iso8601" and re.match(
self.RE_ISO8601_DATE, e.text
):
new_group.append(e)
elif re.match(self.RE_ISO8601_DATE, e.text):
warnings.warn("Added iso8601 encoding to date {}".format(e.text))
warnings.warn(f"Added iso8601 encoding to date {e.text}", stacklevel=1)
e.attrib["encoding"] = "iso8601"
new_group.append(e)
elif m := re.match(self.RE_GERMAN_DATE, e.text):
warnings.warn("Converted date {} to iso8601 encoding".format(e.text))
warnings.warn(
f"Converted date {e.text} to iso8601 encoding", stacklevel=1
)
e.text = "{}-{}-{}".format(
m.group("yyyy"), m.group("mm"), m.group("dd")
)
e.attrib["encoding"] = "iso8601"
new_group.append(e)
else:
warnings.warn('Not a iso8601 date: "{}"'.format(e.text))
warnings.warn(f'Not a iso8601 date: "{e.text}"', stacklevel=1)
new_group.append(e)
self.group = new_group
@ -159,21 +161,27 @@ class TagGroup:
and e.find("mods:edition", ns).text == "[Electronic ed.]"
):
e.attrib["eventType"] = "digitization"
warnings.warn("Fixed eventType for electronic ed.")
warnings.warn(
"Fixed eventType for electronic ed.", stacklevel=1
)
continue
except AttributeError:
pass
try:
if e.find("mods:dateIssued", ns) is not None:
e.attrib["eventType"] = "publication"
warnings.warn("Fixed eventType for an issued origin")
warnings.warn(
"Fixed eventType for an issued origin", stacklevel=1
)
continue
except AttributeError:
pass
try:
if e.find("mods:dateCreated", ns) is not None:
e.attrib["eventType"] = "production"
warnings.warn("Fixed eventType for a created origin")
warnings.warn(
"Fixed eventType for a created origin", stacklevel=1
)
continue
except AttributeError:
pass
@ -184,20 +192,25 @@ class TagGroup:
# MODS-AP 2.3.1 is not clear about this, but it looks like that this should be lower case.
if e.attrib["authority"] == "ISO15924":
e.attrib["authority"] = "iso15924"
warnings.warn("Changed scriptTerm authority to lower case")
warnings.warn(
"Changed scriptTerm authority to lower case", stacklevel=1
)
return self
def fix_language_term(self) -> TagGroup:
for e in self.group:
if e.attrib["authority"] == "iso639-2":
e.attrib["authority"] = "iso639-2b"
warnings.warn("Changed languageTerm authority to iso639-2b")
warnings.warn(
"Changed languageTerm authority to iso639-2b", stacklevel=1
)
if e.attrib["authority"] == "rfc3066":
if e.text == "de":
e.attrib["authority"] = "iso639-2b"
e.text = "deu"
warnings.warn(
"Changed languageTerm authority from rfc3066 to iso639-2b"
"Changed languageTerm authority from rfc3066 to iso639-2b",
stacklevel=1,
)
return self
@ -206,7 +219,7 @@ class TagGroup:
# Default to type=text
if "type" not in e.attrib:
e.attrib["type"] = "text"
warnings.warn("Added placeTerm type='text'")
warnings.warn("Added placeTerm type='text'", stacklevel=1)
return self
def remove_attributes(self, attribs) -> TagGroup:
@ -304,7 +317,9 @@ class TagGroup:
if e.get("type") == "zdb":
e.attrib["source"] = "zdb"
del e.attrib["type"]
warnings.warn("Fixed recordIdentifier type 'zdb' to source")
warnings.warn(
"Fixed recordIdentifier type 'zdb' to source", stacklevel=1
)
return self

4
src/mods4pandas/mods4pandas.py
View file

@ -337,7 +337,9 @@ def mods_to_dict(mods, raise_errors=True):
TagGroup(tag, group).is_singleton().has_no_attributes().text()
)
elif tag == "{http://www.loc.gov/mods/v3}origininfo":
warnings.warn("Ignoring invalid tag origininfo (should be originInfo)")
warnings.warn(
"Ignoring invalid tag origininfo (should be originInfo)", stacklevel=1
)
else:
if raise_errors:
raise ValueError('Unknown tag "{}"'.format(tag))