From fcf7892bfba842581c2b3a78d5ef0c28e974b34f Mon Sep 17 00:00:00 2001
From: Adam Fourney <adamfo@microsoft.com>
Date: Fri, 28 Feb 2025 16:05:13 -0800
Subject: [PATCH] Added unit tests for exceptions.

---
 .../markitdown/tests/test_files/random.bin    | Bin 0 -> 1024 bytes
 packages/markitdown/tests/test_markitdown.py  |  18 +++++++++++++++++-
 2 files changed, 17 insertions(+), 1 deletion(-)
 create mode 100644 packages/markitdown/tests/test_files/random.bin

diff --git a/packages/markitdown/tests/test_files/random.bin b/packages/markitdown/tests/test_files/random.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e673935e3fe247eb568b532edda79cfa6d7cfd23
GIT binary patch
literal 1024
zcmV+b1poVZqDUF|I@MPm@I2ba$0^0xsbp5=o$th>YH+h(LnR-*n?R?s5~^bsp5l$X
z7!7%l(k=#N0Jw)Mg|7LqVl#M>YgXS>F_7qT+Ta$BOcL@<=D?8&Tyzbza0M!}1$;|W
zE280En|hWp5mqOnj+8dseB-OIb=`)1NzxJ`L~!o}I7|^;+VBtH0Eryk+!aOZQtBbu
z+d)OC*Sj!C8hXD<05H0AteX&eRn;m*M-^4a)GnCF&Oy_Xtl2HYT$Q4Cl5VSs&Ep6m
zBH}pJ@5V)56TBb@{sw}78^asVLNQvD&&bza?s=)<`Aum^Nwp9aYfaNz@n1(ZtEb3T
zn1_qrM48Xdk_Sp=F9@=dlt0+n(CwH7(8{%|5AU1C`0=y}c8wJ(VA?k|Fxn_-03S<%
z$$npfgt!B__+tzm3hvzTwmBh^;BS#Xmy#m!uK{z{@z~TV;a{SJXCFB0G0>@izrxvx
zLDXFsvXHb$p}6ONcFotcO_yhBU>g^5`itQOtrNzb33~pIm^}+Nu)R^|`okXdo2=yR
zql_<o*Fvw8o6v}hl<*&Myy_ANu#N8<9J6>_p$hJ^g1zP)QpcN+Y<zGJ03}b2Y(g#s
z4ygj=NT3eYs14lu>cA2?NB5#bK&KyY*C&eZHE<BYdkA6Q={sKqLzeIww{!i=X;0=z
z?pUmX76+k)6rz*t(D3XxH-kA7tyP!7d2^GbtF+4Wow!#`Rhu{^a{U0K`EtDj1iOO-
zrEuS6r&G8Sog#dmS%ig{3@Hf_thv+AFd01ID~|?$#7L=!iixlRRp?%_qIFUKVsj$C
zwHbKNELQsm=%RDooTFOl8?`Zn+osS0%O&WLtZWdz2hGvYF;tm+Nz}8;X*NoB+$C{!
z_|j?v;<~+kaP{2(0Dk1siA*;L?N%{dVO;nBp3+|elO_@^u1ge?nFM|YWGG=XC(i<6
z{*ONI3D-I_H>FLGUm&Zeypx-Y>RQV_7eJE?j{;Fovw#+-GF2oxJtV}EyPNi0fN&@c
zy$8z^dxzdPjCj{s>*ZM6XASd9ew9-p$NFR)ABLs}(MEP|*<4wZP9tC-Dmu2BTG{ez
zM9(1*o!NO|rTs52NkHUb8t^@X;Gb=?g5W+B@PHq)d9}wi50J=^)9<FIh)c!ikU~A8
zz1EsjZ8%AMCmLPp7(m-8*GFwXuJgov3W58FJK=UF(!=D?Qy95vCiUA%x7M&3B2BJ0
zqM8l?tMI>pDfUine~u}mW@EAyzV60qXX@FPW%u??=}_W#YoyH!tqHeq^X1rTURVlV
uZ!;^~(Qhc=?1M<ings2#K8)9V6;E2-o$rP>m6xcY{dXP^%X3G4bAv$;g8TUZ

literal 0
HcmV?d00001

diff --git a/packages/markitdown/tests/test_markitdown.py b/packages/markitdown/tests/test_markitdown.py
index 55afcc3..0a3b56e 100644
--- a/packages/markitdown/tests/test_markitdown.py
+++ b/packages/markitdown/tests/test_markitdown.py
@@ -8,7 +8,7 @@ import requests
 
 from warnings import catch_warnings, resetwarnings
 
-from markitdown import MarkItDown
+from markitdown import MarkItDown, UnsupportedFormatException, FileConversionException
 
 skip_remote = (
     True if os.environ.get("GITHUB_ACTIONS") else False
@@ -272,6 +272,21 @@ def test_markitdown_local() -> None:
     assert "# Test" in result.text_content
 
 
+def test_exceptions() -> None:
+    # Check that an exception is raised when trying to convert an unsupported format
+    markitdown = MarkItDown()
+    with pytest.raises(UnsupportedFormatException):
+        markitdown.convert(os.path.join(TEST_FILES_DIR, "random.bin"))
+
+    # Check that an exception is raised when trying to convert a file that is corrupted
+    with pytest.raises(FileConversionException) as exc_info:
+        markitdown.convert(
+            os.path.join(TEST_FILES_DIR, "random.bin"), file_extension=".pptx"
+        )
+    assert len(exc_info.value.attempts) == 1
+    assert type(exc_info.value.attempts[0].converter).__name__ == "PptxConverter"
+
+
 @pytest.mark.skipif(
     skip_exiftool,
     reason="do not run if exiftool is not installed",
@@ -329,6 +344,7 @@ if __name__ == "__main__":
     """Runs this file's tests from the command line."""
     test_markitdown_remote()
     test_markitdown_local()
+    test_exceptions()
     test_markitdown_exiftool()
     # test_markitdown_llm()
     print("All tests passed!")