from backend.text_coverage import (text_coverage, segment_text_layer, fallback_objects, merge_objects, recover_sheet_number) def test_coverage_full(): text = "NOTE 1\nALL LUMBER NO. 2 SOUTHERN PINE\nNOTE 2\nUSE 5/8\" PLYWOOD" objects = [{"source_text": "ALL LUMBER NO. 2 SOUTHERN PINE"}, {"source_text": "USE 5/8\" PLYWOOD"}] cov = text_coverage(text, objects) assert cov["covered_lines"] == 2 assert cov["total_lines"] == 2 assert cov["ratio"] == 1.0 def test_coverage_zero_on_empty_objects(): cov = text_coverage("LINE ALPHA CONTENT\nLINE BETA CONTENT\nLINE GAMMA CONTENT", []) assert cov["ratio"] == 0.0 and cov["total_lines"] == 3 def test_coverage_ignores_short_and_numeric_noise_lines(): text = "15\"\n19\"\nA\nB\nREAL NOTE ABOUT FRAMING HERE" cov = text_coverage(text, [{"source_text": "REAL NOTE ABOUT FRAMING HERE"}]) assert cov["total_lines"] == 1 and cov["ratio"] == 1.0 def test_segment_notes_and_rows(): text = "WOOD CONSTRUCTION\n1. \nALL SAWN LUMBER TO BE SOUTHERN PINE.\n2. \nROOF SHEATHING 5/8\" PLYWOOD." segs = segment_text_layer(text) assert any("ALL SAWN LUMBER" in s for s in segs) assert any("ROOF SHEATHING" in s for s in segs) def test_fallback_objects_verbatim_and_stamped(): objs = fallback_objects("1. \nALL SAWN LUMBER TO BE SOUTHERN PINE.", page_number=8) assert len(objs) == 1 assert objs[0]["source_text"] == "1 ALL SAWN LUMBER TO BE SOUTHERN PINE." assert objs[0]["grounding"] == "text_layer_fallback" assert objs[0]["confidence"] == "low" def test_merge_objects_keeps_vision_and_unions_text(): vision = [ {"source_text": "2X6 WD STUD @ 16\" O.C.", "object_type": "wall"}, {"source_text": None, "graphical_basis": "light fixture symbol, grid C-4", "object_type": "lighting_fixture"}, ] text = [ {"source_text": "2X6 WD STUD @ 16\" O.C.", "object_type": "wall"}, {"source_text": "ALL LUMBER NO. 2 SOUTHERN PINE", "object_type": "general_note"}, ] merged = merge_objects(vision, text) assert len(merged) == 3 assert any(o.get("graphical_basis") for o in merged) assert merged[0]["object_type"] == "wall" def test_merge_objects_dedupes_by_normalized_text(): a = [{"source_text": "RTU-1: 5 TON, 1600 CFM"}] b = [{"source_text": "rtu 1 5 ton 1600 cfm"}] assert len(merge_objects(a, b)) == 1 def test_recover_sheet_number_from_title_block(): text = ("WALL SECTIONS\n...\nSheet Information\nS301\n" "Issue Date 05.29.26\nProject Number 25177") assert recover_sheet_number(text) == "S301" def test_recover_sheet_number_none_when_absent(): assert recover_sheet_number("just some notes about lumber") is None def test_recover_prefers_discipline_pattern_over_dates(): text = "Issue Date 05.29.26\nProject Number 25177\nA102 REFLECTED CEILING PLAN" assert recover_sheet_number(text) == "A102"