mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-24 09:26:08 +00:00
7a74cdda86
* fix for processing deeply embedded list elements * fix types in mime encodings cleaner * first pass on partition_email * tests for email * test for mime encodings * changelog bump * added note about \n= * linting, linting, linting * added email docs * add partition_email to the readme * add one more test
62 lines
1.9 KiB
Python
62 lines
1.9 KiB
Python
import os
|
|
import pathlib
|
|
import pytest
|
|
|
|
from unstructured.documents.elements import NarrativeText, Title, ListItem
|
|
from unstructured.partition.email import partition_email
|
|
|
|
|
|
DIRECTORY = pathlib.Path(__file__).parent.resolve()
|
|
|
|
|
|
EXPECTED_OUTPUT = [
|
|
NarrativeText(text="This is a test email to use for unit tests."),
|
|
Title(text="Important points:"),
|
|
ListItem(text="Roses are red"),
|
|
ListItem(text="Violets are blue"),
|
|
]
|
|
|
|
|
|
def test_partition_email_from_filename():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "fake-email.eml")
|
|
elements = partition_email(filename=filename)
|
|
assert len(elements) > 0
|
|
assert elements == EXPECTED_OUTPUT
|
|
|
|
|
|
def test_partition_email_from_file():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "fake-email.eml")
|
|
with open(filename, "r") as f:
|
|
elements = partition_email(file=f)
|
|
assert len(elements) > 0
|
|
assert elements == EXPECTED_OUTPUT
|
|
|
|
|
|
def test_partition_email_from_text():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "fake-email.eml")
|
|
with open(filename, "r") as f:
|
|
text = f.read()
|
|
elements = partition_email(text=text)
|
|
assert len(elements) > 0
|
|
assert elements == EXPECTED_OUTPUT
|
|
|
|
|
|
def test_partition_email_raises_with_none_specified():
|
|
with pytest.raises(ValueError):
|
|
partition_email()
|
|
|
|
|
|
def test_partition_email_raises_with_too_many_specified():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "fake-email.eml")
|
|
with open(filename, "r") as f:
|
|
text = f.read()
|
|
|
|
with pytest.raises(ValueError):
|
|
partition_email(filename=filename, text=text)
|
|
|
|
|
|
def test_partition_email_raises_with_invalid_content_type():
|
|
filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "fake-email.eml")
|
|
with pytest.raises(ValueError):
|
|
partition_email(filename=filename, content_source="application/json")
|