Skip to content

Commit a4e87a4

Browse files
subrata-mssubrata-ms
committed
fixing test error
1 parent 1ca9f73 commit a4e87a4

File tree

1 file changed

+72
-32
lines changed

1 file changed

+72
-32
lines changed

‎tests/test_002_types.py‎

Lines changed: 72 additions & 32 deletions
Original file line numberDiff line numberDiff line change
@@ -826,11 +826,15 @@ def test_utf8_2byte_sequence_complete_coverage():
826826
for test_bytes, binary, desc in invalid_continuation:
827827
try:
828828
result = test_bytes.decode("utf-8", errors="replace")
829-
print(f" {test_bytes.hex()}: {binary} ({desc}) -> {repr(result)}")
829+
try:
830+
print(f" {test_bytes.hex()}: {binary} ({desc}) -> {repr(result)}")
831+
except UnicodeEncodeError:
832+
print(f" {test_bytes.hex()}: {binary} ({desc}) -> <decoded>")
830833
# Check that invalid sequences are handled (may produce replacement chars or split)
831834
assert len(result) > 0, f"Should produce some output for {desc}"
832835
except Exception as e:
833-
print(f" {test_bytes.hex()}: {binary} ({desc}) -> Exception: {e}")
836+
# Print without the exception message to avoid encoding errors
837+
print(f" {test_bytes.hex()}: {binary} ({desc}) -> Exception occurred")
834838
# Any error handling is acceptable for invalid sequences
835839

836840
print(" ✓ All invalid continuation bytes handled\n")
@@ -873,14 +877,17 @@ def test_utf8_2byte_sequence_complete_coverage():
873877
for test_bytes, codepoint, desc in overlong_2byte:
874878
try:
875879
result = test_bytes.decode("utf-8", errors="replace")
876-
print(
877-
f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> {repr(result)}"
878-
)
880+
try:
881+
print(
882+
f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> {repr(result)}"
883+
)
884+
except UnicodeEncodeError:
885+
print(f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> <decoded>")
879886
# Check that overlong sequences are handled (behavior may vary by platform)
880887
assert len(result) > 0, f"Should produce some output for overlong U+{codepoint:04X}"
881888
except Exception as e:
882889
print(
883-
f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> Exception: {e}"
890+
f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> Exception occurred"
884891
)
885892

886893
print(" ✓ All overlong 2-byte encodings handled\n")
@@ -965,11 +972,14 @@ def test_utf8_3byte_sequence_complete_coverage():
965972
for test_bytes, desc in invalid_second_byte:
966973
try:
967974
result = test_bytes.decode("utf-8", errors="replace")
968-
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
975+
try:
976+
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
977+
except UnicodeEncodeError:
978+
print(f" {test_bytes.hex()}: {desc} -> <decoded>")
969979
# Check that invalid sequences are handled (may produce replacement chars or split)
970980
assert len(result) > 0, f"Should produce some output for {desc}"
971981
except Exception as e:
972-
print(f" {test_bytes.hex()}: {desc} -> Exception: {e}")
982+
print(f" {test_bytes.hex()}: {desc} -> Exception occurred")
973983

974984
# Third byte invalid (second byte must be valid to isolate third byte error)
975985
invalid_third_byte = [
@@ -983,11 +993,14 @@ def test_utf8_3byte_sequence_complete_coverage():
983993
for test_bytes, desc in invalid_third_byte:
984994
try:
985995
result = test_bytes.decode("utf-8", errors="replace")
986-
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
996+
try:
997+
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
998+
except UnicodeEncodeError:
999+
print(f" {test_bytes.hex()}: {desc} -> <decoded>")
9871000
# Check that invalid sequences are handled (may produce replacement chars or split)
9881001
assert len(result) > 0, f"Should produce some output for {desc}"
9891002
except Exception as e:
990-
print(f" {test_bytes.hex()}: {desc} -> Exception: {e}")
1003+
print(f" {test_bytes.hex()}: {desc} -> Exception occurred")
9911004

9921005
# Both bytes invalid
9931006
both_invalid = [
@@ -1000,11 +1013,14 @@ def test_utf8_3byte_sequence_complete_coverage():
10001013
for test_bytes, desc in both_invalid:
10011014
try:
10021015
result = test_bytes.decode("utf-8", errors="replace")
1003-
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
1016+
try:
1017+
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
1018+
except UnicodeEncodeError:
1019+
print(f" {test_bytes.hex()}: {desc} -> <decoded>")
10041020
# Check that invalid sequences are handled (may produce replacement chars or split)
10051021
assert len(result) > 0, f"Should produce some output for {desc}"
10061022
except Exception as e:
1007-
print(f" {test_bytes.hex()}: {desc} -> Exception: {e}")
1023+
print(f" {test_bytes.hex()}: {desc} -> Exception occurred")
10081024

10091025
print(" ✓ All invalid continuation bytes handled\n")
10101026

@@ -1052,11 +1068,14 @@ def test_utf8_3byte_sequence_complete_coverage():
10521068
for test_bytes, codepoint, desc in surrogate_encodings:
10531069
try:
10541070
result = test_bytes.decode("utf-8", errors="replace")
1055-
print(f" {test_bytes.hex()}: {desc} (0x{codepoint:04X}) -> {repr(result)}")
1071+
try:
1072+
print(f" {test_bytes.hex()}: {desc} (0x{codepoint:04X}) -> {repr(result)}")
1073+
except UnicodeEncodeError:
1074+
print(f" {test_bytes.hex()}: {desc} (0x{codepoint:04X}) -> <decoded>")
10561075
# Check that surrogate sequences are handled (behavior may vary by platform)
10571076
assert len(result) > 0, f"Should produce some output for surrogate U+{codepoint:04X}"
10581077
except Exception as e:
1059-
print(f" {test_bytes.hex()}: {desc} (0x{codepoint:04X}) -> Exception: {e}")
1078+
print(f" {test_bytes.hex()}: {desc} (0x{codepoint:04X}) -> Exception occurred")
10601079
except ValueError:
10611080
# Python may not allow creating surrogate characters directly
10621081
pass
@@ -1077,14 +1096,17 @@ def test_utf8_3byte_sequence_complete_coverage():
10771096
for test_bytes, codepoint, desc in overlong_3byte:
10781097
try:
10791098
result = test_bytes.decode("utf-8", errors="replace")
1080-
print(
1081-
f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> {repr(result)}"
1082-
)
1099+
try:
1100+
print(
1101+
f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> {repr(result)}"
1102+
)
1103+
except UnicodeEncodeError:
1104+
print(f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> <decoded>")
10831105
# Check that overlong sequences are handled (behavior may vary by platform)
10841106
assert len(result) > 0, f"Should produce some output for overlong U+{codepoint:04X}"
10851107
except Exception as e:
10861108
print(
1087-
f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> Exception: {e}"
1109+
f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> Exception occurred"
10881110
)
10891111

10901112
print(" ✓ All overlong 3-byte encodings handled\n")
@@ -1190,11 +1212,14 @@ def test_utf8_4byte_sequence_complete_coverage():
11901212
for test_bytes, desc in invalid_byte1:
11911213
try:
11921214
result = test_bytes.decode("utf-8", errors="replace")
1193-
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
1215+
try:
1216+
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
1217+
except UnicodeEncodeError:
1218+
print(f" {test_bytes.hex()}: {desc} -> <decoded>")
11941219
# Check that invalid sequences are handled (may produce replacement chars or split)
11951220
assert len(result) > 0, f"Should produce some output for {desc}"
11961221
except Exception as e:
1197-
print(f" {test_bytes.hex()}: {desc} -> Exception: {e}")
1222+
print(f" {test_bytes.hex()}: {desc} -> Exception occurred")
11981223

11991224
# Third byte invalid (byte 2)
12001225
invalid_byte2 = [
@@ -1208,11 +1233,14 @@ def test_utf8_4byte_sequence_complete_coverage():
12081233
for test_bytes, desc in invalid_byte2:
12091234
try:
12101235
result = test_bytes.decode("utf-8", errors="replace")
1211-
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
1236+
try:
1237+
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
1238+
except UnicodeEncodeError:
1239+
print(f" {test_bytes.hex()}: {desc} -> <decoded>")
12121240
# Check that invalid sequences are handled (may produce replacement chars or split)
12131241
assert len(result) > 0, f"Should produce some output for {desc}"
12141242
except Exception as e:
1215-
print(f" {test_bytes.hex()}: {desc} -> Exception: {e}")
1243+
print(f" {test_bytes.hex()}: {desc} -> Exception occurred")
12161244

12171245
# Fourth byte invalid (byte 3)
12181246
invalid_byte3 = [
@@ -1226,11 +1254,14 @@ def test_utf8_4byte_sequence_complete_coverage():
12261254
for test_bytes, desc in invalid_byte3:
12271255
try:
12281256
result = test_bytes.decode("utf-8", errors="replace")
1229-
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
1257+
try:
1258+
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
1259+
except UnicodeEncodeError:
1260+
print(f" {test_bytes.hex()}: {desc} -> <decoded>")
12301261
# Check that invalid sequences are handled (may produce replacement chars or split)
12311262
assert len(result) > 0, f"Should produce some output for {desc}"
12321263
except Exception as e:
1233-
print(f" {test_bytes.hex()}: {desc} -> Exception: {e}")
1264+
print(f" {test_bytes.hex()}: {desc} -> Exception occurred")
12341265

12351266
# Multiple bytes invalid
12361267
multiple_invalid = [
@@ -1244,11 +1275,14 @@ def test_utf8_4byte_sequence_complete_coverage():
12441275
for test_bytes, desc in multiple_invalid:
12451276
try:
12461277
result = test_bytes.decode("utf-8", errors="replace")
1247-
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
1278+
try:
1279+
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
1280+
except UnicodeEncodeError:
1281+
print(f" {test_bytes.hex()}: {desc} -> <decoded>")
12481282
# Check that invalid sequences are handled (may produce replacement chars or split)
12491283
assert len(result) > 0, f"Should produce some output for {desc}"
12501284
except Exception as e:
1251-
print(f" {test_bytes.hex()}: {desc} -> Exception: {e}")
1285+
print(f" {test_bytes.hex()}: {desc} -> Exception occurred")
12521286

12531287
print(" ✓ All invalid continuation bytes handled\n")
12541288

@@ -1294,14 +1328,17 @@ def test_utf8_4byte_sequence_complete_coverage():
12941328
for test_bytes, codepoint, desc in overlong_4byte:
12951329
try:
12961330
result = test_bytes.decode("utf-8", errors="replace")
1297-
print(
1298-
f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> {repr(result)}"
1299-
)
1331+
try:
1332+
print(
1333+
f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> {repr(result)}"
1334+
)
1335+
except UnicodeEncodeError:
1336+
print(f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> <decoded>")
13001337
# Check that overlong sequences are handled (behavior may vary by platform)
13011338
assert len(result) > 0, f"Should produce some output for overlong U+{codepoint:04X}"
13021339
except Exception as e:
13031340
print(
1304-
f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> Exception: {e}"
1341+
f" {test_bytes.hex()}: Overlong encoding of U+{codepoint:04X} ({desc}) -> Exception occurred"
13051342
)
13061343

13071344
print(" ✓ All overlong 4-byte encodings handled\n")
@@ -1338,11 +1375,14 @@ def test_utf8_4byte_sequence_complete_coverage():
13381375
for test_bytes, desc in invalid_sequences:
13391376
try:
13401377
result = test_bytes.decode("utf-8", errors="replace")
1341-
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
1378+
try:
1379+
print(f" {test_bytes.hex()}: {desc} -> {repr(result)}")
1380+
except UnicodeEncodeError:
1381+
print(f" {test_bytes.hex()}: {desc} -> <decoded>")
13421382
# Check that invalid sequences are handled
13431383
assert len(result) > 0, f"Should produce some output for invalid sequence"
13441384
except Exception as e:
1345-
print(f" {test_bytes.hex()}: {desc} -> Exception: {e}")
1385+
print(f" {test_bytes.hex()}: {desc} -> Exception occurred")
13461386

13471387
print(" ✓ Invalid sequences handled\n")
13481388

0 commit comments

Comments
 (0)