util/generate-hugo-content.py: re-work vocabularies

Read vocabularies from the data/controlled-vocabularies directory
instead of exporting them from the schema itself. Also, I use the
name vocabulary.txt for all of them on the site since they are in
each field's directory already.
This commit is contained in:
Alan Orth 2021-12-13 15:03:20 +02:00
parent 96bc2b5f79
commit c5eca3cc12
Signed by: alanorth
GPG Key ID: 0FB860CC9C45B1B9

View File

@ -9,6 +9,7 @@ import os
import re import re
import sys import sys
from shutil import rmtree from shutil import rmtree
from shutil import copyfile
import pandas as pd import pandas as pd
@ -78,9 +79,13 @@ def parseSchema(schema_df):
if row["element controlled values or terms"]: if row["element controlled values or terms"]:
controlled_vocab = True controlled_vocab = True
exportVocabulary( controlled_vocabulary_src=f"data/controlled-vocabularies/{element_name_safe}.txt"
row["element controlled values or terms"], element_name_safe controlled_vocabulary_dst=f"site/content/terms/{element_name_safe}/vocabulary.txt"
)
copyfile(controlled_vocabulary_src, controlled_vocabulary_dst)
if args.debug:
print(f"Copied controlled vocabulary: {element_name_safe}")
else: else:
controlled_vocab = False controlled_vocab = False
@ -118,7 +123,7 @@ def parseSchema(schema_df):
indexLines.append(f"comment: '{comment}'\n") indexLines.append(f"comment: '{comment}'\n")
indexLines.append(f"required: {required}\n") indexLines.append(f"required: {required}\n")
if controlled_vocab: if controlled_vocab:
indexLines.append(f"vocabulary: '{element_name_safe}.txt'\n") indexLines.append(f"vocabulary: 'vocabulary.txt'\n")
if module: if module:
indexLines.append(f"module: '{module}'\n") indexLines.append(f"module: '{module}'\n")
if cluster: if cluster:
@ -132,24 +137,6 @@ def parseSchema(schema_df):
f.writelines(indexLines) f.writelines(indexLines)
def exportVocabulary(vocabulary: str, element_name_safe: str):
# Create an empty list where we'll add all the values (we don't need to do
# it this way, but using a list allows us to de-duplicate the values).
controlledVocabularyLines = []
for value in vocabulary.split("||"):
if value not in controlledVocabularyLines:
controlledVocabularyLines.append(value)
with open(
f"site/content/terms/{element_name_safe}/{element_name_safe}.txt", "w"
) as f:
for value in controlledVocabularyLines:
f.write(f"{value}\n")
if args.debug:
print(f"Exported controlled vocabulary: {element_name_safe}")
parser = argparse.ArgumentParser( parser = argparse.ArgumentParser(
description="Parse an ISEAL schema Excel file to produce documentation about metadata requirements." description="Parse an ISEAL schema Excel file to produce documentation about metadata requirements."
) )