mirror of
https://github.com/khoaliber/khoj.git
synced 2026-03-06 05:39:12 +00:00
a627f56a64
This was earlier used when the index was plaintext jsonl file. Now that documents are indexed in a DB this func is not required. Simplify org,md,pdf,plaintext to entries tests by removing the entry to jsonl conversion step
145 lines
4.2 KiB
Python
145 lines
4.2 KiB
Python
import json
|
|
import os
|
|
from pathlib import Path
|
|
|
|
from khoj.processor.content.markdown.markdown_to_entries import MarkdownToEntries
|
|
from khoj.utils.fs_syncer import get_markdown_files
|
|
from khoj.utils.rawconfig import TextContentConfig
|
|
|
|
|
|
def test_markdown_file_with_no_headings_to_jsonl(tmp_path):
|
|
"Convert files with no heading to jsonl."
|
|
# Arrange
|
|
entry = f"""
|
|
- Bullet point 1
|
|
- Bullet point 2
|
|
"""
|
|
data = {
|
|
f"{tmp_path}": entry,
|
|
}
|
|
expected_heading = f"# {tmp_path.stem}"
|
|
|
|
# Act
|
|
# Extract Entries from specified Markdown files
|
|
entries = MarkdownToEntries.extract_markdown_entries(markdown_files=data)
|
|
|
|
# Assert
|
|
assert len(entries) == 1
|
|
# Ensure raw entry with no headings do not get heading prefix prepended
|
|
assert not entries[0].raw.startswith("#")
|
|
# Ensure compiled entry has filename prepended as top level heading
|
|
assert entries[0].compiled.startswith(expected_heading)
|
|
# Ensure compiled entry also includes the file name
|
|
assert str(tmp_path) in entries[0].compiled
|
|
|
|
|
|
def test_single_markdown_entry_to_jsonl(tmp_path):
|
|
"Convert markdown entry from single file to jsonl."
|
|
# Arrange
|
|
entry = f"""### Heading
|
|
\t\r
|
|
Body Line 1
|
|
"""
|
|
data = {
|
|
f"{tmp_path}": entry,
|
|
}
|
|
|
|
# Act
|
|
# Extract Entries from specified Markdown files
|
|
entries = MarkdownToEntries.extract_markdown_entries(markdown_files=data)
|
|
|
|
# Assert
|
|
assert len(entries) == 1
|
|
|
|
|
|
def test_multiple_markdown_entries_to_jsonl(tmp_path):
|
|
"Convert multiple markdown entries from single file to jsonl."
|
|
# Arrange
|
|
entry = f"""
|
|
### Heading 1
|
|
\t\r
|
|
Heading 1 Body Line 1
|
|
### Heading 2
|
|
\t\r
|
|
Heading 2 Body Line 2
|
|
"""
|
|
data = {
|
|
f"{tmp_path}": entry,
|
|
}
|
|
|
|
# Act
|
|
# Extract Entries from specified Markdown files
|
|
entries = MarkdownToEntries.extract_markdown_entries(markdown_files=data)
|
|
|
|
# Assert
|
|
assert len(entries) == 2
|
|
# Ensure entry compiled strings include the markdown files they originate from
|
|
assert all([tmp_path.stem in entry.compiled for entry in entries])
|
|
|
|
|
|
def test_get_markdown_files(tmp_path):
|
|
"Ensure Markdown files specified via input-filter, input-files extracted"
|
|
# Arrange
|
|
# Include via input-filter globs
|
|
group1_file1 = create_file(tmp_path, filename="group1-file1.md")
|
|
group1_file2 = create_file(tmp_path, filename="group1-file2.md")
|
|
group2_file1 = create_file(tmp_path, filename="group2-file1.markdown")
|
|
group2_file2 = create_file(tmp_path, filename="group2-file2.markdown")
|
|
# Include via input-file field
|
|
file1 = create_file(tmp_path, filename="notes.md")
|
|
# Not included by any filter
|
|
create_file(tmp_path, filename="not-included-markdown.md")
|
|
create_file(tmp_path, filename="not-included-text.txt")
|
|
|
|
expected_files = set(
|
|
[os.path.join(tmp_path, file.name) for file in [group1_file1, group1_file2, group2_file1, group2_file2, file1]]
|
|
)
|
|
|
|
# Setup input-files, input-filters
|
|
input_files = [tmp_path / "notes.md"]
|
|
input_filter = [tmp_path / "group1*.md", tmp_path / "group2*.markdown"]
|
|
|
|
markdown_config = TextContentConfig(
|
|
input_files=input_files,
|
|
input_filter=[str(filter) for filter in input_filter],
|
|
compressed_jsonl=tmp_path / "test.jsonl",
|
|
embeddings_file=tmp_path / "test_embeddings.jsonl",
|
|
)
|
|
|
|
# Act
|
|
extracted_org_files = get_markdown_files(markdown_config)
|
|
|
|
# Assert
|
|
assert len(extracted_org_files) == 5
|
|
assert set(extracted_org_files.keys()) == expected_files
|
|
|
|
|
|
def test_extract_entries_with_different_level_headings(tmp_path):
|
|
"Extract markdown entries with different level headings."
|
|
# Arrange
|
|
entry = f"""
|
|
# Heading 1
|
|
## Heading 2
|
|
"""
|
|
data = {
|
|
f"{tmp_path}": entry,
|
|
}
|
|
|
|
# Act
|
|
# Extract Entries from specified Markdown files
|
|
entries = MarkdownToEntries.extract_markdown_entries(markdown_files=data)
|
|
|
|
# Assert
|
|
assert len(entries) == 2
|
|
assert entries[0].raw == "# Heading 1"
|
|
assert entries[1].raw == "## Heading 2"
|
|
|
|
|
|
# Helper Functions
|
|
def create_file(tmp_path: Path, entry=None, filename="test.md"):
|
|
markdown_file = tmp_path / filename
|
|
markdown_file.touch()
|
|
if entry:
|
|
markdown_file.write_text(entry)
|
|
return markdown_file
|