mirror of
https://github.com/khoaliber/khoj.git
synced 2026-03-03 21:29:08 +00:00
Support multiple input-filters to configure content to index via khoj.yml
- Update existings code, tests to process input-filters as list instead of str - Test `text_to_jsonl' get files methods to work with combination of `input-files' and `input-filters' Resolves #84
This commit is contained in:
@@ -63,13 +63,17 @@ def markdown_to_jsonl(config: TextContentConfig, previous_entries=None):
|
||||
return entries_with_ids
|
||||
|
||||
|
||||
def get_markdown_files(markdown_files=None, markdown_file_filter=None):
|
||||
def get_markdown_files(markdown_files=None, markdown_file_filters=None):
|
||||
"Get Markdown files to process"
|
||||
absolute_markdown_files, filtered_markdown_files = set(), set()
|
||||
if markdown_files:
|
||||
absolute_markdown_files = {get_absolute_path(markdown_file) for markdown_file in markdown_files}
|
||||
if markdown_file_filter:
|
||||
filtered_markdown_files = set(glob.glob(get_absolute_path(markdown_file_filter)))
|
||||
if markdown_file_filters:
|
||||
filtered_markdown_files = {
|
||||
filtered_file
|
||||
for markdown_file_filter in markdown_file_filters
|
||||
for filtered_file in glob.glob(get_absolute_path(markdown_file_filter))
|
||||
}
|
||||
|
||||
all_markdown_files = absolute_markdown_files | filtered_markdown_files
|
||||
|
||||
|
||||
Reference in New Issue
Block a user