Spaces:
Running on Zero
Running on Zero
File size: 12,426 Bytes
db06ffa | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 | import unittest
from zsgdp.chunking import build_agentic_chunks
from zsgdp.config import load_config
from zsgdp.schema import DocumentProfile, Element, FigureObject, PageProfile, ParsedDocument, QualityReport, TableObject
from zsgdp.verify import verify_chunks
class ChunkingTests(unittest.TestCase):
def test_agentic_chunking_builds_parent_child_chunks(self):
profile = DocumentProfile(
doc_id="d1",
source_path="sample.md",
file_type="markdown",
page_count=1,
extension=".md",
pages=[PageProfile(page_num=1, digital_text_chars=120, digital_text_quality=1.0)],
)
parsed = ParsedDocument(
doc_id="d1",
source_path="sample.md",
file_type="markdown",
quality_report=QualityReport(score=0.95),
)
parsed.elements.extend(
[
Element("e1", "d1", 1, "title", markdown="# Report", reading_order=1, source_parser="text"),
Element("e2", "d1", 1, "paragraph", text=" ".join(["alpha"] * 80), reading_order=2, source_parser="text"),
]
)
chunks = build_agentic_chunks(parsed, profile, load_config())
self.assertTrue(any(chunk.content_type == "parent" for chunk in chunks))
self.assertTrue(any(chunk.parent_chunk_id for chunk in chunks))
self.assertEqual(parsed.provenance["chunking"]["plan"]["target_tokens"], 512)
def test_chunk_readiness_adds_metrics(self):
profile = DocumentProfile(
doc_id="d1",
source_path="sample.md",
file_type="markdown",
page_count=1,
extension=".md",
pages=[PageProfile(page_num=1, digital_text_chars=120, digital_text_quality=1.0)],
)
parsed = ParsedDocument(
doc_id="d1",
source_path="sample.md",
file_type="markdown",
quality_report=QualityReport(score=0.95),
)
parsed.elements.append(
Element("e1", "d1", 1, "paragraph", text=" ".join(["alpha"] * 80), reading_order=1, source_parser="text")
)
parsed.chunks = build_agentic_chunks(parsed, profile, load_config())
report = verify_chunks(parsed, load_config())
self.assertEqual(report.metrics["chunk_count"], len(parsed.chunks))
self.assertIn("fixed_token_baseline", report.metrics["chunk_strategy_counts"])
self.assertIn("recursive_structure", report.metrics["chunk_strategy_counts"])
def test_fixed_token_baseline_chunks_are_emitted_with_provenance(self):
profile = DocumentProfile(
doc_id="d1",
source_path="sample.md",
file_type="markdown",
page_count=2,
extension=".md",
pages=[
PageProfile(page_num=1, digital_text_chars=120, digital_text_quality=1.0),
PageProfile(page_num=2, digital_text_chars=120, digital_text_quality=1.0),
],
)
parsed = ParsedDocument(
doc_id="d1",
source_path="sample.md",
file_type="markdown",
quality_report=QualityReport(score=0.95),
)
parsed.elements.extend(
[
Element("e1", "d1", 1, "paragraph", text=" ".join(["alpha"] * 18), reading_order=1, source_parser="text"),
Element("e2", "d1", 2, "paragraph", text=" ".join(["beta"] * 18), reading_order=1, source_parser="text"),
]
)
config = load_config(overrides={"chunking": {"target_tokens": 10, "overlap_ratio": 0.2}})
chunks = build_agentic_chunks(parsed, profile, config)
baseline_chunks = [chunk for chunk in chunks if chunk.strategy == "fixed_token_baseline"]
self.assertGreaterEqual(len(baseline_chunks), 4)
self.assertEqual(baseline_chunks[0].element_ids, ["e1"])
self.assertEqual(baseline_chunks[-1].page_end, 2)
self.assertEqual(parsed.provenance["chunking"]["fixed_token_baseline_count"], len(baseline_chunks))
def test_figure_without_caption_still_gets_visual_chunk(self):
profile = DocumentProfile(
doc_id="d1",
source_path="sample.pdf",
file_type="pdf",
page_count=1,
extension=".pdf",
pages=[PageProfile(page_num=1, digital_text_chars=20, digital_text_quality=1.0)],
)
parsed = ParsedDocument(
doc_id="d1",
source_path="sample.pdf",
file_type="pdf",
quality_report=QualityReport(score=0.90),
)
parsed.elements.append(Element("e1", "d1", 1, "paragraph", text="hello world", reading_order=1, source_parser="pymupdf"))
parsed.figures.append(
FigureObject(
figure_id="f1",
page_num=1,
image_path="/tmp/figure.png",
confidence=0.5,
source_parser="pymupdf",
)
)
parsed.chunks = build_agentic_chunks(parsed, profile, load_config())
report = verify_chunks(parsed, load_config())
self.assertTrue(any(chunk.figure_ids == ["f1"] for chunk in parsed.chunks))
self.assertEqual(report.metrics["figure_chunk_coverage"], 1.0)
def test_table_chunk_keeps_multimodal_metadata(self):
profile = DocumentProfile(
doc_id="d1",
source_path="sample.pdf",
file_type="pdf",
page_count=1,
extension=".pdf",
pages=[PageProfile(page_num=1, digital_text_chars=20, digital_text_quality=1.0)],
)
parsed = ParsedDocument(
doc_id="d1",
source_path="sample.pdf",
file_type="pdf",
quality_report=QualityReport(score=0.90),
)
parsed.elements.append(Element("e1", "d1", 1, "paragraph", text="hello world", reading_order=1, source_parser="pymupdf"))
parsed.tables.append(
TableObject(
table_id="t1",
page_nums=[1],
bbox=[(1.0, 2.0, 3.0, 4.0)],
markdown="| A | B |\n| --- | --- |\n| 1 | 2 |",
natural_language_rendering="Table with columns A, B. Rows: 1: B=2.",
confidence=0.82,
source_parser="pymupdf",
provenance={"crop_path": "/tmp/table.png", "source_parsers": ["pymupdf", "docling"]},
)
)
parsed.chunks = build_agentic_chunks(parsed, profile, load_config())
table_chunk = next(chunk for chunk in parsed.chunks if chunk.strategy == "table_object")
self.assertEqual(table_chunk.text, "Table with columns A, B. Rows: 1: B=2.")
self.assertEqual(table_chunk.metadata["markdown"], "| A | B |\n| --- | --- |\n| 1 | 2 |")
self.assertEqual(table_chunk.metadata["bbox"], [(1.0, 2.0, 3.0, 4.0)])
self.assertEqual(table_chunk.metadata["crop_path"], "/tmp/table.png")
self.assertEqual(table_chunk.metadata["source_parsers"], ["pymupdf", "docling"])
def test_vision_guided_chunking_exports_visual_regions(self):
profile = DocumentProfile(
doc_id="d1",
source_path="sample.pdf",
file_type="pdf",
page_count=1,
extension=".pdf",
pages=[PageProfile(page_num=1, digital_text_chars=20, digital_text_quality=1.0)],
)
parsed = ParsedDocument(
doc_id="d1",
source_path="sample.pdf",
file_type="pdf",
quality_report=QualityReport(score=0.90),
)
parsed.elements.append(Element("e1", "d1", 1, "paragraph", text="hello world", reading_order=1, source_parser="pymupdf"))
parsed.tables.append(TableObject(table_id="t1", page_nums=[1], bbox=[(1.0, 2.0, 3.0, 4.0)], markdown="| A | B |\n| --- | --- |\n| 1 | 2 |"))
parsed.figures.append(FigureObject(figure_id="f1", page_num=1, bbox=(5.0, 6.0, 7.0, 8.0), source_parser="pymupdf"))
config = load_config(overrides={"chunking": {"vision_guided": True}})
parsed.chunks = build_agentic_chunks(parsed, profile, config)
visual_chunks = [chunk for chunk in parsed.chunks if chunk.content_type in {"table", "figure"}]
self.assertTrue(all(chunk.requires_visual_context for chunk in visual_chunks))
self.assertEqual(len(parsed.provenance["chunking"]["vision_regions"]), 2)
self.assertEqual(parsed.provenance["chunking"]["vision_regions"][0]["region_id"], "t1")
def test_advanced_chunking_flags_emit_strategy_chunks(self):
profile = DocumentProfile(
doc_id="d1",
source_path="sample.pdf",
file_type="pdf",
page_count=2,
extension=".pdf",
pages=[
PageProfile(page_num=1, digital_text_chars=200, digital_text_quality=1.0),
PageProfile(page_num=2, digital_text_chars=200, digital_text_quality=1.0),
],
)
parsed = ParsedDocument(
doc_id="d1",
source_path="sample.pdf",
file_type="pdf",
quality_report=QualityReport(score=0.92),
)
parsed.elements.extend(
[
Element("e1", "d1", 1, "heading", markdown="## Revenue", reading_order=1, source_parser="pymupdf"),
Element(
"e2",
"d1",
1,
"paragraph",
text="Revenue increased by 12 percent in Q1. Gross margin improved due to pricing.",
reading_order=2,
source_parser="pymupdf",
),
Element("e3", "d1", 2, "heading", markdown="## Safety", reading_order=1, source_parser="pymupdf"),
Element(
"e4",
"d1",
2,
"paragraph",
text="Safety inspections found three unresolved risks. Corrective actions are due in June.",
reading_order=2,
source_parser="pymupdf",
),
]
)
parsed.tables.append(
TableObject(
table_id="t1",
page_nums=[1],
markdown="| Metric | Value |\n| --- | --- |\n| Revenue | 12% |",
natural_language_rendering="Table t1 reports revenue growth of 12 percent.",
source_parser="pymupdf",
)
)
parsed.figures.append(
FigureObject(
figure_id="f1",
page_num=2,
caption="Risk trend chart shows open safety findings.",
source_parser="pymupdf",
)
)
config = load_config(
overrides={
"chunking": {
"contextual_retrieval": True,
"semantic_chunking": True,
"late_chunking": True,
"vision_guided": True,
"agentic_proposition_chunking": True,
}
}
)
parsed.chunks = build_agentic_chunks(parsed, profile, config)
strategies = {chunk.strategy for chunk in parsed.chunks}
self.assertIn("semantic", strategies)
self.assertIn("late", strategies)
self.assertIn("contextual_retrieval", strategies)
self.assertIn("vision_guided", strategies)
self.assertIn("agentic_proposition", strategies)
self.assertGreater(parsed.provenance["chunking"]["semantic_chunk_count"], 0)
self.assertGreater(parsed.provenance["chunking"]["late_chunk_count"], 0)
self.assertGreater(parsed.provenance["chunking"]["contextual_retrieval_chunk_count"], 0)
semantic_chunk = next(chunk for chunk in parsed.chunks if chunk.strategy == "semantic")
self.assertEqual(semantic_chunk.metadata["execution_mode"], "lexical_similarity_proxy")
contextual_chunk = next(chunk for chunk in parsed.chunks if chunk.strategy == "contextual_retrieval")
self.assertIn("source_chunk_id", contextual_chunk.metadata)
late_chunk = next(chunk for chunk in parsed.chunks if chunk.strategy == "late")
self.assertTrue(late_chunk.metadata["requires_token_level_embeddings"])
if __name__ == "__main__":
unittest.main()
|