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
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
|
# standard imports
from collections import Counter
import math
import typing
# bsie imports
from bsie.extractor import base
from bsie.matcher import nodes
from bsie.utils import bsfs, ns
# exports
__all__: typing.Sequence[str] = (
'TextMetrics',
)
## code ##
log2 = lambda x: math.log(x) / math.log(2)
class TextMetrics(base.Extractor):
"""Extract text metrics (character, word, and line counts) from a document."""
CONTENT_READER = 'bsie.reader.document.Document'
_callmap: typing.Dict[bsfs.schema.Predicate, typing.Callable[[str], typing.Any]]
def __init__(self):
super().__init__(bsfs.schema.from_string(base.SCHEMA_PREAMBLE + '''
bse:num_characters rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsn:Entity ;
rdfs:range xsd:integer ;
bsfs:unique "true"^^xsd:boolean .
bse:num_paragraphs rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsn:Entity ;
rdfs:range xsd:integer ;
bsfs:unique "true"^^xsd:boolean .
bse:num_words rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsn:Entity ;
rdfs:range xsd:integer ;
bsfs:unique "true"^^xsd:boolean .
bse:vocabulary_size rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsn:Entity ;
rdfs:range xsd:integer ;
bsfs:unique "true"^^xsd:boolean .
bse:vocabulary_entropy rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsn:Entity ;
rdfs:range xsd:float ;
bsfs:unique "true"^^xsd:boolean .
'''))
self._callmap = {
self.schema.predicate(ns.bse.num_characters): self.__num_characters,
self.schema.predicate(ns.bse.num_paragraphs): self.__num_paragraphs,
self.schema.predicate(ns.bse.num_words): self.__num_words,
self.schema.predicate(ns.bse.vocabulary_size): self.__vocab_size,
self.schema.predicate(ns.bse.vocabulary_entropy): self.__entropy,
}
def extract(
self,
subject: nodes.Entity,
content: typing.Sequence[str],
principals: typing.Iterable[bsfs.schema.Predicate],
) -> typing.Iterator[typing.Tuple[nodes.Entity, bsfs.schema.Predicate, typing.Any]]:
for pred in principals:
# find callback
clbk = self._callmap.get(pred)
if clbk is None:
continue
# produce triple
yield subject, pred, clbk(content)
def __num_words(self, text: typing.Sequence[str]) -> int:
return sum([len(paragraph.split()) for paragraph in text])
def __num_characters(self, text: typing.Sequence[str]) -> int:
return sum([len(paragraph) for paragraph in text])
def __num_paragraphs(self, text: typing.Sequence[str]) -> int:
return len(text)
def __vocab_size(self, text: typing.Sequence[str]) -> int:
return sum({len(paragraph.split()) for paragraph in text})
def __entropy(self, text: typing.Sequence[str]) -> float:
words = [word for paragraph in text for word in paragraph.split() ]
word_histogram = Counter(words)
num_words = len(words)
return -sum(
word_prob / num_words * log2(word_prob / num_words)
for word_prob
in word_histogram.values()
)
## EOF ##
|
