gmakstutis/cognee
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Change document test ground truth values for new chunk_by_word

Browse source
This commit is contained in:
Leon Luithlen 2024-11-14 14:20:18 +01:00
parent eaf9167fa1
commit a52d3ac6ba
4 changed files with 18 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
cognee/tests/integration/documents/AudioDocument_test.py
View file

@ -4,9 +4,9 @@ from unittest.mock import patch
from cognee.modules.data.processing.document_types.AudioDocument import AudioDocument from cognee.modules.data.processing.document_types.AudioDocument import AudioDocument
GROUND_TRUTH = [ GROUND_TRUTH = [
{"word_count": 60, "len_text": 318, "cut_type": "sentence_end"}, {"word_count": 57, "len_text": 353, "cut_type": "sentence_end"},
{"word_count": 64, "len_text": 358, "cut_type": "sentence_end"}, {"word_count": 58, "len_text": 358, "cut_type": "sentence_end"},
{"word_count": 56, "len_text": 255, "cut_type": "sentence_cut"}, {"word_count": 41, "len_text": 220, "cut_type": "sentence_cut"},
] ]
TEST_TEXT = """ TEST_TEXT = """

2
cognee/tests/integration/documents/ImageDocument_test.py
View file

@ -5,7 +5,7 @@ from cognee.modules.data.processing.document_types.ImageDocument import ImageDoc
GROUND_TRUTH = [ GROUND_TRUTH = [
{"word_count": 51, "len_text": 298, "cut_type": "sentence_end"}, {"word_count": 51, "len_text": 298, "cut_type": "sentence_end"},
{"word_count": 63, "len_text": 369, "cut_type": "sentence_end"}, {"word_count": 62, "len_text": 369, "cut_type": "sentence_end"},
{"word_count": 44, "len_text": 294, "cut_type": "sentence_end"}, {"word_count": 44, "len_text": 294, "cut_type": "sentence_end"},
] ]

8
cognee/tests/integration/documents/TextDocument_test.py
View file

@ -7,12 +7,12 @@ from cognee.modules.data.processing.document_types.TextDocument import TextDocum
GROUND_TRUTH = { GROUND_TRUTH = {
"code.txt": [ "code.txt": [
{"word_count": 253, "len_text": 953, "cut_type": "paragraph_end"}, {"word_count": 205, "len_text": 1024, "cut_type": "sentence_cut"},
{"word_count": 157, "len_text": 905, "cut_type": "paragraph_end"}, {"word_count": 104, "len_text": 833, "cut_type": "sentence_cut"},
], ],
"Natural_language_processing.txt": [ "Natural_language_processing.txt": [
{"word_count": 115, "len_text": 839, "cut_type": "paragraph_end"}, {"word_count": 128, "len_text": 984, "cut_type": "paragraph_end"},
{"word_count": 15, "len_text": 146, "cut_type": "paragraph_end"}, {"word_count": 1, "len_text": 1, "cut_type": "sentence_cut"},
], ],
} }

20
cognee/tests/unit/processing/chunks/chunk_by_paragraph_test.py
View file

@ -3,34 +3,34 @@ from cognee.tasks.chunks import chunk_by_paragraph
GROUND_TRUTH = { GROUND_TRUTH = {
"whole_text": [ "whole_text": [
{ {
"text": "This is example text. It contains multiple sentences.\n", "text": "This is example text. It contains multiple sentences.",
"word_count": 9, "word_count": 8,
"cut_type": "paragraph_end", "cut_type": "paragraph_end",
}, },
{ {
"text": "This is a second paragraph. First two paragraphs are whole.\n", "text": "\nThis is a second paragraph. First two paragraphs are whole.",
"word_count": 11, "word_count": 10,
"cut_type": "paragraph_end", "cut_type": "paragraph_end",
}, },
{ {
"text": "Third paragraph is a bit longer and is finished with a dot.", "text": "\nThird paragraph is a bit longer and is finished with a dot.",
"word_count": 12, "word_count": 12,
"cut_type": "sentence_end", "cut_type": "sentence_end",
}, },
], ],
"cut_text": [ "cut_text": [
{ {
"text": "This is example text. It contains multiple sentences.\n", "text": "This is example text. It contains multiple sentences.",
"word_count": 9, "word_count": 8,
"cut_type": "paragraph_end", "cut_type": "paragraph_end",
}, },
{ {
"text": "This is a second paragraph. First two paragraphs are whole.\n", "text": "\nThis is a second paragraph. First two paragraphs are whole.",
"word_count": 11, "word_count": 10,
"cut_type": "paragraph_end", "cut_type": "paragraph_end",
}, },
{ {
"text": "Third paragraph is cut and is missing the dot at the end", "text": "\nThird paragraph is cut and is missing the dot at the end",
"word_count": 12, "word_count": 12,
"cut_type": "word", "cut_type": "word",
}, },