Mercurial > p > roundup > code
view roundup/support.py @ 5096:e74c3611b138
- issue2550636, issue2550909: Added support for Whoosh indexer.
Also adds new config.ini setting called indexer to select
indexer. See ``doc/upgrading.txt`` for details. Initial patch
done by David Wolever. Patch modified (see ticket or below for
changes), docs updated and committed.
I have an outstanding issue with test/test_indexer.py. I have to
comment out all imports and tests for indexers I don't have (i.e.
mysql, postgres) otherwise no tests run.
With that change made, dbm, sqlite (rdbms), xapian and whoosh indexes
are all passing the indexer tests.
Changes summary:
1) support native back ends dbm and rdbms. (original patch only fell
through to dbm)
2) Developed whoosh stopfilter to not index stopwords or words outside
the the maxlength and minlength limits defined in index_common.py.
Required to pass the extremewords test_indexer test. Also I
removed a call to .lower on the input text as the tokenizer I chose
automatically does the lowercase.
3) Added support for max/min length to find. This was needed to pass
extremewords test.
4) Added back a call to save_index in add_text. This allowed all but
two tests to pass.
5) Fixed a call to:
results = searcher.search(query.Term("identifier", identifier))
which had an extra parameter that is an error under current whoosh.
6) Set limit=None in search call for find() otherwise it only return
10 items. This allowed it to pass manyresults test
Also due to changes in the roundup code removed the call in
indexer_whoosh to
from roundup.anypy.sets_ import set
since we use the python builtin set.
| author | John Rouillard <rouilj@ieee.org> |
|---|---|
| date | Sat, 25 Jun 2016 20:10:03 -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 :
