Mercurial > p > roundup > code
view roundup/support.py @ 5108:67fad01d2009
issue2550653: xapian search, stemming is not working
This is a partial fix for the issue. It does make stemming work
(so searching for silent will also return docs with silently in
them). However to do this we need to lowercase the text so the
porter stemmer will work. This means capitalization is not
preserved.
Tests in test/test_indexer for xapian backend all pass.
David Wolever (wolever) did the work.
| author | John Rouillard <rouilj@ieee.org> |
|---|---|
| date | Mon, 27 Jun 2016 22:10:45 -0400 |
| parents | ac0c117cd24c |
| children | 64b05e24dbd8 |
line wrap: on
line source
"""Implements various support classes and functions used in a number of places in Roundup code. """ __docformat__ = 'restructuredtext' import os, time, sys, re class TruthDict: '''Returns True for valid keys, False for others. ''' def __init__(self, keys): if keys: self.keys = {} for col in keys: self.keys[col] = 1 else: self.__getitem__ = lambda name: 1 def __getitem__(self, name): return self.keys.has_key(name) def ensureParentsExist(dest): if not os.path.exists(os.path.dirname(dest)): os.makedirs(os.path.dirname(dest)) class PrioList: '''Manages a sorted list. Currently only implements method 'append' and iteration from a full list interface. Implementation: We manage a "sorted" status and sort on demand. Appending to the list will require re-sorting before use. >>> p = PrioList() >>> for i in 5,7,1,-1: ... p.append(i) ... >>> for k in p: ... print k ... -1 1 5 7 ''' def __init__(self): self.list = [] self.sorted = True def append(self, item): self.list.append(item) self.sorted = False def __iter__(self): if not self.sorted: self.list.sort() self.sorted = True return iter(self.list) class Progress: '''Progress display for console applications. See __main__ block at end of file for sample usage. ''' def __init__(self, info, sequence): self.info = info self.sequence = iter(sequence) self.total = len(sequence) self.start = self.now = time.time() self.num = 0 self.stepsize = self.total / 100 or 1 self.steptimes = [] self.display() def __iter__(self): return self def next(self): self.num += 1 if self.num > self.total: print self.info, 'done', ' '*(75-len(self.info)-6) sys.stdout.flush() return self.sequence.next() if self.num % self.stepsize: return self.sequence.next() self.display() return self.sequence.next() def display(self): # figure how long we've spent - guess how long to go now = time.time() steptime = now - self.now self.steptimes.insert(0, steptime) if len(self.steptimes) > 5: self.steptimes.pop() steptime = sum(self.steptimes) / len(self.steptimes) self.now = now eta = steptime * ((self.total - self.num)/self.stepsize) # tell it like it is (or might be) if now - self.start > 3: M = eta / 60 H = M / 60 M = M % 60 S = eta % 60 if self.total: s = '%s %2d%% (ETA %02d:%02d:%02d)'%(self.info, self.num * 100. / self.total, H, M, S) else: s = '%s 0%% (ETA %02d:%02d:%02d)'%(self.info, H, M, S) elif self.total: s = '%s %2d%%'%(self.info, self.num * 100. / self.total) else: s = '%s %d done'%(self.info, self.num) sys.stdout.write(s + ' '*(75-len(s)) + '\r') sys.stdout.flush() # vim: set et sts=4 sw=4 :
