also store a complete copy of the document
This commit is contained in:
		
							
								
								
									
										11
									
								
								addindex
									
									
									
									
									
								
							
							
						
						
									
										11
									
								
								addindex
									
									
									
									
									
								
							| @@ -60,10 +60,13 @@ def process_pdf(path): | ||||
| 		result.append(data) | ||||
| 		count += 1 | ||||
| 	 | ||||
| 	#everything = pagedata() | ||||
| 	#everything.page = 0 | ||||
| 	#everything.content = content.replace("\f", "") | ||||
| 	#result.append(everything) | ||||
| 	#TODO: current hack, so we can fts search several words over the whole document | ||||
| 	#this of course uses more space, but in the end that's not a big problem | ||||
| 	#Nevertheless, this remains a hack | ||||
| 	everything = pagedata() | ||||
| 	everything.page = 0 | ||||
| 	everything.content = content.replace("\f", "") | ||||
| 	result.append(everything) | ||||
| 	return result | ||||
| 	 | ||||
| def process_odt(path): | ||||
|   | ||||
		Reference in New Issue
	
	Block a user