I am trying to parse a large CSV (5MB) file using some code I found here:
http://www.macresearch.org/cocoa-scientists-part-xxvi-parsing-csv-data
but I am getting what I think is an out of memory error part way through, the
error is:
DataImport(1324,0xa09f3500) malloc: *** mmap(size=16777216) failed (error
code=12)
*** error: can't allocate region
I'm fairly certain I do not have a memory leak it is just that the NSString is
very large. Is there anyway to increase the memory allocated or clean up the
code to reduce its memory usage?
Thanks
Greg
Here is the code:
#import <Cocoa/Cocoa.h>
#import <Foundation/Foundation.h>
@interface NSString (ParsingExtensions)
-(NSArray *)csvRows;
@end
---------
#import "NSStringCategory.h"
@implementation NSString (ParsingExtensions)
-(NSArray *)csvRows
{
NSMutableArray *rows = [NSMutableArray array];
// Get newline character set
NSMutableCharacterSet *newlineCharacterSet = (id)[NSMutableCharacterSet
whitespaceAndNewlineCharacterSet];
[newlineCharacterSet formIntersectionWithCharacterSet:[[NSCharacterSet
whitespaceCharacterSet] invertedSet]];
// Characters that are important to the parser
NSMutableCharacterSet *importantCharactersSet = (id)[NSMutableCharacterSet
characterSetWithCharactersInString:@",\""];
[importantCharactersSet formUnionWithCharacterSet:newlineCharacterSet];
// Create scanner, and scan string
NSScanner *scanner = [NSScanner scannerWithString:self];
[scanner setCharactersToBeSkipped:nil];
while ( ![scanner isAtEnd] ) {
BOOL insideQuotes = NO;
BOOL finishedRow = NO;
NSMutableArray *columns = [NSMutableArray arrayWithCapacity:12];
NSMutableString *currentColumn = [NSMutableString string];
while ( !finishedRow ) {
NSString *tempString;
if ( [scanner scanUpToCharactersFromSet:importantCharactersSet
intoString:&tempString] ) {
[currentColumn appendString:tempString];
}
if ( [scanner isAtEnd] ) {
if ( ![currentColumn isEqualToString:@""] ) [columns
addObject:currentColumn];
finishedRow = YES;
}
else if ( [scanner scanCharactersFromSet:newlineCharacterSet
intoString:&tempString] ) {
if ( insideQuotes ) {
// Add line break to column text
[currentColumn appendString:tempString];
}
else {
// End of row
if ( ![currentColumn isEqualToString:@""] ) [columns
addObject:currentColumn];
finishedRow = YES;
}
}
else if ( [scanner scanString:@"\"" intoString:NULL] ) {
if ( insideQuotes && [scanner scanString:@"\"" intoString:NULL]
) {
// Replace double quotes with a single quote in the column
string.
[currentColumn appendString:@"\""];
}
else {
// Start or end of a quoted string.
insideQuotes = !insideQuotes;
}
}
else if ( [scanner scanString:@"," intoString:NULL] ) {
if ( insideQuotes ) {
[currentColumn appendString:@","];
}
else {
// This is a column separating comma
[columns addObject:currentColumn];
currentColumn = [NSMutableString string];
[scanner scanCharactersFromSet:[NSCharacterSet
whitespaceCharacterSet] intoString:NULL];
}
}
}
if ( [columns count] > 0 ) [rows addObject:columns];
}
return rows;
}
@end
_______________________________________________
Cocoa-dev mailing list ([email protected])
Please do not post admin requests or moderator comments to the list.
Contact the moderators at cocoa-dev-admins(at)lists.apple.com
Help/Unsubscribe/Update your Subscription:
http://lists.apple.com/mailman/options/cocoa-dev/archive%40mail-archive.com
This email sent to [email protected]
