qurator-spk/modstool
1
0
Fork 0
mirror of https://github.com/qurator-spk/modstool.git synced 2025-06-09 11:49:55 +02:00
Code Issues Releases Wiki Activity

⚙ Make saving per-page information optional

Browse source
This commit is contained in:
Mike Gerber 2024-07-29 06:08:01 +02:00
parent dd4febf24d
commit 191867cdef
1 changed files with 11 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

6
src/mods4pandas/mods4pandas.py
View file

@ -373,7 +373,8 @@ def pages_to_dict(mets, raise_errors=True) -> List[Dict]:
default='mods_info_df.parquet', show_default=True) default='mods_info_df.parquet', show_default=True)
@click.option('--output-csv', type=click.Path(), help='Output CSV file') @click.option('--output-csv', type=click.Path(), help='Output CSV file')
@click.option('--output-xlsx', type=click.Path(), help='Output Excel .xlsx file') @click.option('--output-xlsx', type=click.Path(), help='Output Excel .xlsx file')
def process(mets_files: List[str], output_file: str, output_csv: str, output_xlsx: str): @click.option('--page-info', is_flag=True, show_default=True, default=False, help='Save page info')
def process(mets_files: List[str], output_file: str, output_csv: str, output_xlsx: str, page_info: bool):
""" """
A tool to convert the MODS metadata in INPUT to a pandas DataFrame. A tool to convert the MODS metadata in INPUT to a pandas DataFrame.
@ -419,9 +420,11 @@ def process(mets_files: List[str], output_file: str, output_csv: str, output_xls
d['mets_file'] = mets_file d['mets_file'] = mets_file
# METS - per-page # METS - per-page
if page_info:
page_info_doc: list[dict] = pages_to_dict(mets, raise_errors=True) page_info_doc: list[dict] = pages_to_dict(mets, raise_errors=True)
mods_info.append(d) mods_info.append(d)
if page_info:
page_info.extend(page_info_doc) page_info.extend(page_info_doc)
if caught_warnings: if caught_warnings:
@ -448,6 +451,7 @@ def process(mets_files: List[str], output_file: str, output_csv: str, output_xls
# Convert page_info # Convert page_info
# XXX hardcoded filenames + other formats # XXX hardcoded filenames + other formats
if page_info:
page_info_df = dicts_to_df(page_info, index_column=("ppn", "ID")) page_info_df = dicts_to_df(page_info, index_column=("ppn", "ID"))
# Save the DataFrame # Save the DataFrame
logger.info('Writing DataFrame to {}'.format("page_info_df.parquet")) logger.info('Writing DataFrame to {}'.format("page_info_df.parquet"))