Spaces:
Running on Zero
Running on Zero
File size: 9,763 Bytes
0828c2c | 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 | """Tests for main document exclusion in document processing."""
import copy
import pytest
from src.config_loader import get_config
from src.document_processor import DocumentProcessor
@pytest.fixture(autouse=True)
def cleanup_config():
"""Ensure config is properly restored after each test in this module."""
config = get_config()
# Save original get method
original_get = config.get
# Save original config
original_config = copy.deepcopy(config._config)
yield
# Restore original get method and config
config.get = original_get
config._config = original_config
class TestMainDocumentExclusion:
"""Test that main document is excluded from vector store processing."""
def test_main_document_excluded_from_processing(self, tmp_path):
"""Test that main document file is skipped during directory processing."""
# Create test documents directory
docs_dir = tmp_path / "documents"
docs_dir.mkdir()
# Create main document
main_doc = docs_dir / "main_profile.md"
main_doc.write_text("# Main Profile\n\nThis should be excluded.")
# Create other documents
other_doc1 = docs_dir / "resume.md"
other_doc1.write_text("# Resume\n\nThis should be included.")
other_doc2 = docs_dir / "projects.md"
other_doc2.write_text("# Projects\n\nThis should also be included.")
# Create processor and mock config
processor = DocumentProcessor()
original_get = processor.config.get
def mock_get(key, default=None):
if key == "main_document.path":
return str(main_doc)
if key == "main_document.exclude_from_index":
return True
return original_get(key, default)
processor.config.get = mock_get
# Process directory
documents = processor.process_directory(docs_dir)
# Get all source files from processed documents
processed_files = {doc.metadata.get("source", "") for doc in documents}
# Main document should NOT be in processed files
assert str(main_doc) not in processed_files
# Other documents SHOULD be processed
assert any("resume.md" in source for source in processed_files)
assert any("projects.md" in source for source in processed_files)
def test_main_document_included_when_exclude_from_index_false(self, tmp_path):
"""Test main document is indexed when exclude_from_index is false."""
docs_dir = tmp_path / "documents"
docs_dir.mkdir()
main_doc = docs_dir / "main_profile.md"
main_doc.write_text("# Main Profile\n\nShould be indexed.")
processor = DocumentProcessor()
original_get = processor.config.get
def mock_get(key, default=None):
if key == "main_document.path":
return str(main_doc)
if key == "main_document.exclude_from_index":
return False
return original_get(key, default)
processor.config.get = mock_get
documents = processor.process_directory(docs_dir)
processed_files = {doc.metadata.get("source", "") for doc in documents}
assert any("main_profile.md" in source for source in processed_files)
def test_all_documents_processed_when_main_doc_disabled(self, tmp_path):
"""Test that all documents are processed when main doc feature is disabled."""
# Create test documents directory
docs_dir = tmp_path / "documents"
docs_dir.mkdir()
# Create documents including what would be the main document
main_doc = docs_dir / "main_profile.md"
main_doc.write_text("# Main Profile\n\nContent here.")
other_doc = docs_dir / "resume.md"
other_doc.write_text("# Resume\n\nContent here.")
# Create processor with main doc disabled
processor = DocumentProcessor()
original_get = processor.config.get
def mock_get(key, default=None):
if key == "main_document.path":
return "" # Empty path = disabled
return original_get(key, default)
processor.config.get = mock_get
# Process directory
documents = processor.process_directory(docs_dir)
# Get all source files
processed_files = {doc.metadata.get("source", "") for doc in documents}
# ALL documents should be processed (including main_profile.md)
assert any("main_profile.md" in source for source in processed_files)
assert any("resume.md" in source for source in processed_files)
def test_main_document_exclusion_case_insensitive_paths(self, tmp_path):
"""Test that path comparison works regardless of path format."""
docs_dir = tmp_path / "documents"
docs_dir.mkdir()
# Create main document
main_doc = docs_dir / "main_profile.md"
main_doc.write_text("# Main Profile\n\nExclude me.")
other_doc = docs_dir / "other.md"
other_doc.write_text("# Other\n\nInclude me.")
processor = DocumentProcessor()
original_get = processor.config.get
def mock_get(key, default=None):
if key == "main_document.path":
# Return path with different format but same file
return str(main_doc.resolve())
if key == "main_document.exclude_from_index":
return True
return original_get(key, default)
processor.config.get = mock_get
# Process directory
documents = processor.process_directory(docs_dir)
# Get all source files
processed_files = {doc.metadata.get("source", "") for doc in documents}
# Main document should be excluded
assert str(main_doc) not in processed_files
assert str(main_doc.resolve()) not in processed_files
# Other document should be included
assert len(documents) > 0
assert any("other.md" in source for source in processed_files)
def test_subdirectory_main_document_excluded(self, tmp_path):
"""Test that main document in subdirectory is excluded."""
docs_dir = tmp_path / "documents"
docs_dir.mkdir()
# Create subdirectory
subdir = docs_dir / "profiles"
subdir.mkdir()
# Create main document in subdirectory
main_doc = subdir / "main_profile.md"
main_doc.write_text("# Main Profile\n\nExclude me.")
# Create other document
other_doc = docs_dir / "resume.md"
other_doc.write_text("# Resume\n\nInclude me.")
processor = DocumentProcessor()
original_get = processor.config.get
def mock_get(key, default=None):
if key == "main_document.path":
return str(main_doc)
if key == "main_document.exclude_from_index":
return True
return original_get(key, default)
processor.config.get = mock_get
# Process directory (recursively)
documents = processor.process_directory(docs_dir)
# Get all source files
processed_files = {doc.metadata.get("source", "") for doc in documents}
# Main document should be excluded
assert str(main_doc) not in processed_files
# Other document should be included
assert any("resume.md" in source for source in processed_files)
def test_no_documents_after_main_doc_exclusion(self, tmp_path):
"""Test behavior when only main document exists."""
docs_dir = tmp_path / "documents"
docs_dir.mkdir()
# Create only the main document
main_doc = docs_dir / "main_profile.md"
main_doc.write_text("# Main Profile\n\nOnly document.")
processor = DocumentProcessor()
original_get = processor.config.get
def mock_get(key, default=None):
if key == "main_document.path":
return str(main_doc)
if key == "main_document.exclude_from_index":
return True
return original_get(key, default)
processor.config.get = mock_get
# Process directory
documents = processor.process_directory(docs_dir)
# Should have no documents (only main doc was excluded)
assert len(documents) == 0
def test_main_document_with_different_extension_not_confused(self, tmp_path):
"""Test that only exact main document file is excluded."""
docs_dir = tmp_path / "documents"
docs_dir.mkdir()
# Create main document (PDF)
main_doc = docs_dir / "main_profile.pdf"
main_doc.write_text("PDF content")
# Create similar named file (MD) - should NOT be excluded
similar_doc = docs_dir / "main_profile.md"
similar_doc.write_text("# Main Profile\n\nInclude me.")
processor = DocumentProcessor()
original_get = processor.config.get
def mock_get(key, default=None):
if key == "main_document.path":
return str(main_doc) # Only PDF is main doc
if key == "main_document.exclude_from_index":
return True
return original_get(key, default)
processor.config.get = mock_get
# Process directory
documents = processor.process_directory(docs_dir)
# Get all source files
processed_files = {doc.metadata.get("source", "") for doc in documents}
# MD file should be included (different extension)
assert any("main_profile.md" in source for source in processed_files)
# PDF should be excluded
# Note: PDF loading might fail with text content, but it should be skipped anyway
|