qurator-spk/modstool
1
0
Fork 0
mirror of https://github.com/qurator-spk/modstool.git synced 2025-08-29 03:19:52 +02:00
Code Issues Releases Wiki Activity

🎨 Reformat with Black

Browse source
This commit is contained in:
Mike Gerber 2025-08-21 15:55:55 +02:00
parent 664900635d
commit 48d7bb3dc4
2 changed files with 19 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

3
src/mods4pandas/lib.py
View file

@ -457,7 +457,6 @@ def convert_db_to_parquet(con, table, index_col, output_file):
def sqlite3_column_exists(con, table, col): def sqlite3_column_exists(con, table, col):
"""Check if column col exists in table.""" """Check if column col exists in table."""
cur = con.execute( cur = con.execute(
"SELECT 1 FROM pragma_table_info(?) WHERE name = ? LIMIT 1", "SELECT 1 FROM pragma_table_info(?) WHERE name = ? LIMIT 1", (table, col)
(table, col)
) )
return cur.fetchone() is not None return cur.fetchone() is not None

28
src/mods4pandas/mods4pandas.py
View file

@ -162,6 +162,7 @@ def mods_to_dict(mods, raise_errors=True):
.descend(raise_errors) .descend(raise_errors)
) )
elif tag == "{http://www.loc.gov/mods/v3}recordIdentifier": elif tag == "{http://www.loc.gov/mods/v3}recordIdentifier":
def no_uuid(record_identifier): def no_uuid(record_identifier):
return record_identifier.attrib.get("type") != "uuid" return record_identifier.attrib.get("type") != "uuid"
@ -169,10 +170,11 @@ def mods_to_dict(mods, raise_errors=True):
# however, in mods:relatedItems, there may be source="dnb-ppns", # however, in mods:relatedItems, there may be source="dnb-ppns",
# which we need to distinguish by using a separate field name. # which we need to distinguish by using a separate field name.
for field_name, source in \ for field_name, source in (
("recordIdentifier", "gbv-ppn"), \ ("recordIdentifier", "gbv-ppn"),
("recordIdentifier-dnb-ppn", "dnb-ppn"), \ ("recordIdentifier-dnb-ppn", "dnb-ppn"),
("recordIdentifier-zdb", "zdb"): ("recordIdentifier-zdb", "zdb"),
):
try: try:
value[field_name] = ( value[field_name] = (
TagGroup(tag, group) TagGroup(tag, group)
@ -525,7 +527,9 @@ def validate_mets_files(ctx, param, mets_files):
@click.command() @click.command()
@click.argument("mets_files", type=click.Path(exists=True), nargs=-1, callback=validate_mets_files) @click.argument(
"mets_files", type=click.Path(exists=True), nargs=-1, callback=validate_mets_files
)
@click.option( @click.option(
"--output", "--output",
"-o", "-o",
@ -539,9 +543,13 @@ def validate_mets_files(ctx, param, mets_files):
"--output-page-info", type=click.Path(), help="Output page info Parquet file" "--output-page-info", type=click.Path(), help="Output page info Parquet file"
) )
@click.option( @click.option(
"--mets-files-list", type=click.Path(), help="Read list of METS files from this file" "--mets-files-list",
type=click.Path(),
help="Read list of METS files from this file",
) )
def process_command(mets_files: list[str], output_file: str, output_page_info: str, mets_files_list: str): def process_command(
mets_files: list[str], output_file: str, output_page_info: str, mets_files_list: str
):
""" """
A tool to convert the MODS metadata in METS_FILES to a pandas DataFrame. A tool to convert the MODS metadata in METS_FILES to a pandas DataFrame.
@ -558,9 +566,9 @@ def process_command(mets_files: list[str], output_file: str, output_page_info: s
process(mets_files, output_file, output_page_info, mets_files_list) process(mets_files, output_file, output_page_info, mets_files_list)
def process(
mets_files: list[str], output_file: str, output_page_info: str, mets_files_list: str
def process(mets_files: list[str], output_file: str, output_page_info: str, mets_files_list: str): ):
mets_files_real: list[str] = [] mets_files_real: list[str] = []
if mets_files_list: if mets_files_list: