File: indexdictd.py

package info (click to toggle)
serpento 0.3.6
  • links: PTS
  • area: main
  • in suites: woody
  • size: 292 kB
  • ctags: 381
  • sloc: python: 1,644; ansic: 666; perl: 157; sh: 116; makefile: 72
file content (53 lines) | stat: -rwxr-xr-x 1,264 bytes parent folder | download | duplicates (3)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
#!/usr/bin/python
# make .index file from raw dictd dictionary file
# (containing %h and %d tags)
# to be used with FileDbDict
# .index is written to stdout 
# and is not sorted. Sorting it can speed up
# serpento startup a bit

import sys, string
from utils import decb64

def writeindex(header, start, ln):
    for i in header:
        r = "%s\t%s\t%s\n" % (i, decb64(start), decb64(ln))
        sys.stdout.write(r)

db = sys.argv[1]

f = open(db, 'r')
header = []
entrystart = 0
while 1:
    while 1: # skip all %h in this cycle, go to first %d
        l = f.readline()
        if not l:
            break
        sl = string.lstrip(l)
        if sl[:2]=='%d':
            break
        if sl[:2]=='%h':
            header.append(string.strip(l[2:]))
    if not l:
        break
    while 1:
        tp = f.tell()
        l = f.readline()
        if not l:
            end = f.tell()
            break
        sl = string.lstrip(l)
        if sl[:2]=='%h': #next entry has started
            nextheader = [string.strip(sl[2:])]
            newstart = tp
            end = tp-1
            break
    ln = end-entrystart
    if header:
        writeindex(header, entrystart, ln)
    entrystart = newstart
    header = nextheader
    if not l:
        break