Geek asks and answers

Numpy.memmap for an array of strings?

Can I use numpy.memmapto match a large array of strings on disk?

I know this can be done for float, etc., but this question is about strings.

I'm interested in solutions for both fixed-length strings and variable-length strings.

The solution can dictate any reasonable file format.

+3
source share
2 answers

If all lines have the same length, as suggested by the term "array", this is easily possible:

a = numpy.memmap("data", dtype="S10")

will be an example for strings of length 10.

. , -, , , O (1). . , , NumPy , . .

+2

.

, , , ...

, - , ( ) .

, - :

class IndexedText(object):
    def __init__(self, filename, mode='r'):
        if mode not in ['r', 'w', 'a']:
            raise ValueError('Only read, write, and append is supported')
        self._mainfile = open(filename, mode)
        self._idxfile = open(filename+'idx', mode)

        if mode != 'w':
            self.indicies = [int(line.strip()) for line in self._idxfile]
        else:
            self.indicies = []

    def __enter__(self):
        return self

    def __exit__(self, type, value, traceback):
        self._mainfile.close()
        self._idxfile.close()

    def __getitem__(self, idx):
        position = self.indicies[idx]
        self._mainfile.seek(position)
        # You might want to remove the automatic stripping...
        return self._mainfile.readline().rstrip('\n')

    def write(self, line):
        if not line.endswith('\n'):
            line += '\n'
        position = self._mainfile.tell()
        self.indicies.append(position)
        self._idxfile.write(str(position)+'\n')
        self._mainfile.write(line)

    def writelines(self, lines):
        for line in lines:
            self.write(line)


def main():
    with IndexedText('test.txt', 'w') as outfile:
        outfile.write('Yep')
        outfile.write('This is a somewhat longer string!')
        outfile.write('But we should be able to index this file easily')
        outfile.write('Without needing to read the entire thing in first')

    with IndexedText('test.txt', 'r') as infile:
        print infile[2]
        print infile[0]
        print infile[3]

if __name__ == '__main__':
    main()
+1

More articles:


All Articles