first commit

tests/test_caption_parser.py

@@ -0,0 +1,102 @@
+from caption_parser import parse_caption
+from conftest import EXAMPLE_CAPTION
+
+
+def test_supplied_example():
+    p = parse_caption(EXAMPLE_CAPTION)
+    assert p.indexes == ["001", "002"]
+    assert p.title == "Class 01 Aman sir.mp4"
+    assert p.topic == "Misc• Grammar Practice"
+    assert p.batch == "English ( SSC MAINS )"
+    assert p.extracted_by == "@PUTINxINDIA"
+    assert p.missing == []
+    assert p.warnings == []
+    assert p.raw == EXAMPLE_CAPTION
+
+
+def test_index_is_never_used_as_title():
+    p = parse_caption("Index: 007\nIndex: 008\nTopic: Nouns")
+    assert p.indexes == ["007", "008"]
+    assert p.title is None
+    assert "title" in p.missing
+
+
+def test_multiple_index_order_preserved():
+    p = parse_caption("Index: 3\nTitle: A\nIndex: 1\nTopic: T\nIndex: 2")
+    assert p.indexes == ["3", "1", "2"]
+
+
+def test_fields_in_any_order_and_whitespace_variants():
+    caption = "  topic :   Error Detection  \n\n\nTITLE:Class 02.mp4\r\n  batch:   X  \nExtracted by :@someone\n"
+    p = parse_caption(caption)
+    assert p.topic == "Error Detection"
+    assert p.title == "Class 02.mp4"
+    assert p.batch == "X"
+    assert p.extracted_by == "@someone"
+
+
+def test_decorations_and_fullwidth_colon():
+    p = parse_caption("🎬 Title： Class 05.mp4\n📚 Topic: Reading Comprehension\n• Batch - ignored\n**Batch:** B1")
+    assert p.title == "Class 05.mp4"
+    assert p.topic == "Reading Comprehension"
+    assert p.batch == "** B1"  # value text is preserved verbatim apart from trimming
+
+
+def test_missing_title_and_topic():
+    p = parse_caption("Index: 001\nBatch: English")
+    assert p.missing == ["title", "topic"]
+    assert "Title field is missing" in p.warnings
+    assert "Topic field is missing" in p.warnings
+
+
+def test_empty_and_none_caption():
+    for value in (None, "", "   \n  "):
+        p = parse_caption(value)
+        assert p.missing == ["title", "topic"]
+        assert "caption is empty" in p.warnings
+
+
+def test_empty_field_values_are_reported():
+    p = parse_caption("Title:\nTopic:   \nIndex:")
+    assert p.title is None and p.topic is None
+    assert "Title field is empty" in p.warnings
+    assert "empty Index field ignored" in p.warnings
+
+
+def test_unicode_preserved():
+    p = parse_caption("Title: कक्षा 01 — व्याकरण (भाग १).mp4\nTopic: हिंदी • व्याकरण\nBatch: Ünïcödé ( 2024 )")
+    assert p.title == "कक्षा 01 — व्याकरण (भाग १).mp4"
+    assert p.topic == "हिंदी • व्याकरण"
+    assert p.batch == "Ünïcödé ( 2024 )"
+
+
+def test_next_field_is_not_swallowed():
+    p = parse_caption("Title: Class 01\nTopic: Grammar\nBatch: SSC")
+    assert p.title == "Class 01"
+    assert p.topic == "Grammar"
+
+
+def test_flattened_single_line_caption():
+    p = parse_caption("Index: 001 Title: Class 01 Aman sir.mp4 Topic: Misc• Grammar Practice | Batch: English ( SSC MAINS )")
+    assert p.indexes == ["001"]
+    assert p.title == "Class 01 Aman sir.mp4"
+    assert p.topic == "Misc• Grammar Practice"
+    assert p.batch == "English ( SSC MAINS )"
+
+
+def test_duplicate_field_keeps_first_and_warns():
+    p = parse_caption("Title: First.mp4\nTitle: Second.mp4\nTopic: T")
+    assert p.title == "First.mp4"
+    assert any("duplicate Title" in w for w in p.warnings)
+
+
+def test_unknown_fields_and_free_text_kept_in_extra_or_ignored():
+    p = parse_caption("Join: @channel\nSome free text line\nTitle: A.mp4\nTopic: T\nSubtitle: not a title")
+    assert p.title == "A.mp4"
+    assert p.extra["Join"] == "@channel"
+    assert p.extra["Subtitle"] == "not a title"
+
+
+def test_label_must_be_whole_word():
+    p = parse_caption("Topics: wrong\nTopic: right")
+    assert p.topic == "right"