pyobjc-framework-searchkit

import os import tempfile import shutil from Foundation import NSURL from SearchKit import SKIndex, SKDocument, SKSearch, SKSearchGroup, kSKSearchOptionFindSimilar, kSKSearchOptionNone # Create a temporary directory for the index temp_dir = tempfile.mkdtemp() index_path = os.path.join(temp_dir, "MySearchIndex") print(f"Creating SearchKit index at: {index_path}") # 1. Create an SKIndex # Convert Python path to NSURL index_url = NSURL.fileURLWithPath_(index_path) # Create a new index (kSKIndexTypeInverted or kSKIndexTypeVector) # For simplicity, using kSKIndexTypeInverted here index = SKIndex.alloc().initForURL_create_dictionary_( index_url, True, None # No special options dictionary ) if not index: print("Failed to create SearchKit index.") shutil.rmtree(temp_dir) exit() # 2. Add documents to the index doc_id_counter = 0 def add_document(content, filename): global doc_id_counter doc_id_counter += 1 doc_name = f"doc_{doc_id_counter}" # Create an SKDocument from content string document = SKDocument.alloc().initWithURL_mimeType_textEncoding_( NSURL.fileURLWithPath_(filename), # URL identifies the document, can be dummy None, # MIME type, can be None None # Text encoding, can be None ) if document: index.addDocumentWithText_url_properties_(document, content, None, None) print(f"Added '{filename}' to index.") else: print(f"Failed to create SKDocument for {filename}") add_document("The quick brown fox jumps over the lazy dog.", "file1.txt") add_document("Lazy dogs often sleep deeply.", "file2.txt") add_document("A quick jump is good exercise.", "file3.txt") index.flush() index.close() # 3. Perform a search search_index = SKIndex.alloc().initForURL_create_dictionary_(index_url, False, None) if not search_index: print("Failed to open SearchKit index for searching.") shutil.rmtree(temp_dir) exit() search_query = "quick dog" print(f"\nSearching for: '{search_query}'") search = SKSearch.alloc().initWithIndex_( search_index ) if search: search_options = kSKSearchOptionNone search_group = SKSearchGroup.alloc().init() # You can specify the maximum number of results results = search.findMatchesForQuery_maxCount_( search_query, 10 # Max 10 results ) if results: for i, doc_ref in enumerate(results.objectAtIndex_(0)): score = results.objectAtIndex_(1)[i] # Get original document URL (which we used as a dummy path) doc_url = search_index.documentPropertiesForDocumentRef_(doc_ref).objectForKey_("kSKDocumentURL").path() print(f" Match: {doc_url} (Score: {score:.2f})") else: print(" No matches found.") else: print("Failed to create SKSearch object.") search_index.close() # 4. Clean up shutil.rmtree(temp_dir) print(f"\nCleaned up temporary index directory: {temp_dir}")