from pathlib import Path
from textwrap import wrap

from haystack.components import converters

source = Path("sample.html")
converter = converters.HTMLToDocument(
    store_full_path=False,
)
result = converter.run(
    sources=[source],
    meta={
        "collection": "support-portal",
        "source_format": "html",
    },
)

documents = result["documents"]
document = documents[0]

print(f"documents: {len(documents)}")
print("content:")
for line in wrap(document.content, width=48):
    print(line)
print("source:", document.meta["file_path"])
print("collection:", document.meta["collection"])
print("format:", document.meta["source_format"])