File size: 2,658 Bytes
3943768 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 |
import sys
def test_extract_xml_tags():
xml_input = """
<doc>
<name>Zulu is hot..pdf</name>
<page>1</page>
<text>
Zulu is hot.
</text>
</doc>
"""
from openai_server.backend_utils import extract_xml_tags
name_page_dict = extract_xml_tags(xml_input)
assert name_page_dict == {'name': 'Zulu is hot..pdf', 'page': '1'}
from openai_server.backend_utils import generate_unique_filename
filename, clean_name, page = generate_unique_filename(name_page_dict)
assert (filename, clean_name, page) == ('Zulu_is_hot__page_1.txt', 'Zulu_is_hot_', '1')
def test_deduplicate_filenames():
original_filenames = [
"Zulu_is_hot__page_1.txt",
"Zulu_is_hot__page_1.txt",
"Zulu_is_hot__page_2.txt",
"Another_document_page_1.txt",
"Zulu_is_hot__page_1.txt"
]
expected = [
"Zulu_is_hot__page_1_chunk_0.txt",
"Zulu_is_hot__page_1_chunk_1.txt",
"Zulu_is_hot__page_2.txt",
"Another_document_page_1.txt",
"Zulu_is_hot__page_1_chunk_2.txt"
]
from openai_server.backend_utils import deduplicate_filenames
result = deduplicate_filenames(original_filenames)
assert result == expected, f"Expected: {expected}, but got: {result}"
def test_generate_unique_filename_multiple_returns():
meta_datas = [
"<name>Zulu is hot..pdf</name>\n<page>1</page>",
"<name>Missing page.pdf</name>",
"<page>5</page>",
"No XML tags here",
""
]
from openai_server.backend_utils import generate_unique_filename
from openai_server.backend_utils import extract_xml_tags
results = [generate_unique_filename(extract_xml_tags(x)) for x in meta_datas]
file_names, cleaned_names, pages = zip(*results)
print("File names:", file_names)
print("Cleaned names:", cleaned_names)
print("Pages:", pages)
# Assertions to verify the results
assert len(file_names) == len(meta_datas)
assert len(cleaned_names) == len(meta_datas)
assert len(pages) == len(meta_datas)
assert file_names[0] == "Zulu_is_hot__page_1.txt"
assert cleaned_names[0] == "Zulu_is_hot_"
assert pages[0] == "1"
assert file_names[1].endswith("_page_0.txt")
assert cleaned_names[1] == "Missing_page"
assert pages[1] == "0"
assert pages[2] == "5"
assert file_names[3] == 'unknown_page_0.txt'
assert file_names[4] == 'unknown_page_0.txt'
def test_exif():
import pyexiv2
img_file_one = 'tests/image_exif.jpg'
with pyexiv2.Image(img_file_one) as img:
metadata = img.read_exif()
assert metadata is not None and metadata != {}
print(metadata, file=sys.stderr)
|