How to change a generator ?

MRAB google at mrabarnett.plus.com
Wed Dec 24 12:03:58 EST 2008


Barak, Ron wrote:
> Hi,
>  
> I have a generator whose aim is to returns consecutive lines from a file 
> (the listing below is a simplified version).
> However, as it is written now, the generator method changes the text 
> file pointer to end of file after first invocation.
> Namely, the file pointer changes from 0 to 6623 on line 24.
>  
It might be that the generator method of self.input_file is reading the 
file a chunk at a time for efficiency even though it's yielding a line 
at a time.

> Can you suggest how the generator could be changed, so it will allow me 
> to get the current location in the file after each yield ?
>  
> Thanks,
> Ron.
>  
> $ cat -n generator.py          # listing without line numbers is below
>      1  #!/usr/bin/env python
>      2
>      3  import gzip
>      4  from Debug import _line as line
>      5
>      6  class LogStream():
>      7     
>      8      def __init__(self, filename):
>      9          self.filename = filename
>     10          self.input_file = self.open_file(filename)
>     11
>     12      def open_file(self, in_file):
>     13          try:
>     14              f = gzip.GzipFile(in_file, "r")
>     15              f.readline()
>     16          except IOError:
>     17              f = open(in_file, "r")
>     18              f.readline()
>     19          f.seek(0)
>     20          return(f)
>     21
>     22      def line_generator(self):
>     23          print line()+". 
> self.input_file.tell()==",self.input_file.tell()
>     24          for line_ in self.input_file:
>     25              print line()+". 
> self.input_file.tell()==",self.input_file.tell()
>     26              yield line_.strip()
>     27
>     28
>     29  if __name__ == "__main__":
>     30
>     31      filename = "sac.log.50lines"
>     32      log_stream = LogStream(filename)
>     33      log_stream.input_file.seek(0)
>     34      line_generator = log_stream.line_generator()
>     35      line_ = line_generator.next()
>  
> $ python generator.py
> 23. self.input_file.tell()== 0
> 25. self.input_file.tell()== 6623
>  
> $ wc -c sac.log.50lines
> 6623 sac.log.50lines
> $ cat generator.py    
> #!/usr/bin/env python
>  
> import gzip
> from Debug import _line as line
>  
> class LogStream():
>    
>     def __init__(self, filename):
>         self.filename = filename
>         self.input_file = self.open_file(filename)
>  
>     def open_file(self, in_file):
>         try:
>             f = gzip.GzipFile(in_file, "r")
>             f.readline()
>         except IOError:
>             f = open(in_file, "r")
>             f.readline()
>         f.seek(0)
>         return(f)
>  
>     def line_generator(self):
>         print line()+". self.input_file.tell()==",self.input_file.tell()
>         for line_ in self.input_file:
>             print line()+". self.input_file.tell()==",self.input_file.tell()
>             yield line_.strip()
>  
> 
> if __name__ == "__main__":
>  
>     filename = "sac.log.50lines"
>     log_stream = LogStream(filename)
>     log_stream.input_file.seek(0)
>     line_generator = log_stream.line_generator()
>     line_ = line_generator.next()
>  



More information about the Python-list mailing list