luciano/markitdown
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

resolving conflict after adding the new lines from merged code

Browse source
This commit is contained in:
Aviral Bhardwaj 2024-12-17 18:48:23 +05:30
parent fb7beff170
commit 1a6064a752
1 changed files with 28 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

28
tests/test_markitdown.py
View file

@ -51,6 +51,17 @@ DOCX_TEST_STRINGS = [
"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation", "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation",
] ]
DOCX_COMMENT_TEST_STRINGS = [
"314b0a30-5b04-470b-b9f7-eed2c2bec74a",
"49e168b7-d2ae-407f-a055-2167576f39a1",
"## d666f1f7-46cb-42bd-9a39-9a39cf2a509f",
"# Abstract",
"# Introduction",
"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation",
"This is a test comment. 12df-321a",
"Yet another comment in the doc. 55yiyi-asd09",
]
DOC_TEST_STRINGS = [ DOC_TEST_STRINGS = [
"314b0a30-5b04-470b-b9f7-eed2c2bec74a", "314b0a30-5b04-470b-b9f7-eed2c2bec74a",
"49e168b7-d2ae-407f-a055-2167576f39a1", "49e168b7-d2ae-407f-a055-2167576f39a1",
@ -138,6 +149,23 @@ def test_markitdown_local() -> None:
for test_string in DOCX_TEST_STRINGS: for test_string in DOCX_TEST_STRINGS:
text_content = result.text_content.replace("\\", "") text_content = result.text_content.replace("\\", "")
assert test_string in text_content assert test_string in text_content
# Test DOCX processing, with comments
result = markitdown.convert(
os.path.join(TEST_FILES_DIR, "test_with_comment.docx"),
style_map="comment-reference => ",
)
for test_string in DOCX_COMMENT_TEST_STRINGS:
text_content = result.text_content.replace("\\", "")
assert test_string in text_content
# Test DOCX processing, with comments and setting style_map on init
markitdown_with_style_map = MarkItDown(style_map="comment-reference => ")
result = markitdown_with_style_map.convert(
os.path.join(TEST_FILES_DIR, "test_with_comment.docx")
)
for test_string in DOCX_COMMENT_TEST_STRINGS:
text_content = result.text_content.replace("\\", "")
assert test_string in text_content
# Test DOC processing # Test DOC processing
result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.doc")) result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.doc"))