orhan/test
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: outlook ".msg" file converter (#196)

Browse Source 
* feat: outlook .msg converter
* add test, adjust docstring
This commit is contained in:
Murat Can Kurtuluş
2025-01-04 00:34:39 +03:00
committed by GitHub
parent 4678c8a2a4
commit d248621ba4
4 changed files with 89 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
tests/test_markitdown.py
View File

@@ -63,6 +63,15 @@ DOCX_TEST_STRINGS = [
"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation",
]
MSG_TEST_STRINGS = [
"# Email Message",
"**From:** test.sender@example.com",
"**To:** test.recipient@example.com",
"**Subject:** Test Email Message",
"## Content",
"This is the body of the test email message",
]
DOCX_COMMENT_TEST_STRINGS = [
"314b0a30-5b04-470b-b9f7-eed2c2bec74a",
"49e168b7-d2ae-407f-a055-2167576f39a1",
@@ -232,6 +241,10 @@ def test_markitdown_local() -> None:
result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_mskanji.csv"))
validate_strings(result, CSV_CP932_TEST_STRINGS)
# Test MSG (Outlook email) processing
result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_outlook_msg.msg"))
validate_strings(result, MSG_TEST_STRINGS)
@pytest.mark.skipif(
skip_exiftool,