sg101: custom_search/fields.py annotate

Word wrap Yahoo Group postings.

rev	line source
bgneal@943	1 """Custom Haystack SearchFields."""
bgneal@943	2
bgneal@943	3 import haystack.fields
bgneal@943	4
bgneal@943	5
bgneal@943	6 class MaxTermSizeCharField(haystack.fields.CharField):
bgneal@943	7 """A CharField that discards large terms when preparing the search index.
bgneal@943	8
bgneal@943	9 Some backends (e.g. Xapian) throw errors when terms are bigger than some
bgneal@943	10 limit. This field omits the terms over a limit when preparing the data for
bgneal@943	11 the search index.
bgneal@943	12
bgneal@943	13 The keyword argument max_term_size sets the maximum size of a whitespace
bgneal@943	14 delimited word/term. Terms over this size are not indexed. The default value
bgneal@943	15 is 64.
bgneal@943	16 """
bgneal@943	17 DEFAULT_MAX_TERM_SIZE = 64
bgneal@943	18
bgneal@943	19 def __init__(self, args, *kwargs):
bgneal@943	20 self.max_term_size = kwargs.pop('max_term_size', self.DEFAULT_MAX_TERM_SIZE)
bgneal@943	21 super(MaxTermSizeCharField, self).__init__(args, *kwargs)
bgneal@943	22
bgneal@943	23 def prepare(self, obj):
bgneal@943	24 text = super(MaxTermSizeCharField, self).prepare(obj)
bgneal@943	25 if text is None or self.max_term_size is None:
bgneal@943	26 return text
bgneal@943	27
bgneal@943	28 terms = (term for term in text.split() if len(term) <= self.max_term_size)
bgneal@943	29 return u' '.join(terms)

Mercurial > public > sg101