normalize parser struct for all file types (#321)

This commit is contained in:
Timothy Carambat 2023-11-01 16:44:02 -07:00 committed by GitHub
parent 1c5d55c425
commit 5441717294
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 3 additions and 5 deletions

View File

@ -61,7 +61,7 @@ def as_odt(**kwargs):
'id': guid(),
'url': "file://"+os.path.abspath(f"{parent_dir}/processed/{filename}{ext}"),
'title': f"{filename}{ext}",
'author': 'Unknown', # TODO: Find a better author
'docAuthor': 'Unknown', # TODO: Find a better author
'description': 'Unknown', # TODO: Find a better bescription
'docSource': 'ODT Text file uploaded by the user.',
'chunkSource': f"{filename}{ext}",

View File

@ -110,11 +110,8 @@ def as_mbox(**kwargs):
"docAuthor": message["From"],
"description": f"email from {message['From']} to {message['To']}",
"docSource": "mbox file uploaded by the user.",
"chunkSource": subject,
"published": file_creation_time(fullpath),
"sender": message["From"],
"recipient": message["To"],
"subject": subject,
"date_sent": date_sent,
"wordCount": len(content),
"pageContent": content,
"token_count_estimate": len(tokenize(content)),

View File

@ -23,6 +23,7 @@ def as_text(**kwargs):
'title': f"{filename}{ext}",
'docAuthor': 'Unknown', # TODO: Find a better author
'description': 'Unknown', # TODO: Find a better description
'docSource': 'a text file uploaded by the user.',
'chunkSource': f"{filename}{ext}",
'published': file_creation_time(fullpath),
'wordCount': len(content),