andoc/selection.py at master · defa/andoc · GitHub

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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
import re, string
from urlparse import urlsplit

NEXT_TXT_SELECTION = 'next.doc.%s.text.selection'
TXT_SELECTIONS = 'doc:%s:text.selections'
TXT_SELECTION_START = 'doc:%s:text.selection:%s:start'
TXT_SELECTION_END = 'doc:%s:text.selection:%s:end'
TXT_SELECTION_REF = 'doc:%s:text.selection:%s:ref'

NEXT_HTML_SELECTION = 'next.doc.%s.html.selection'
HTML_SELECTIONS = 'doc:%s:html.selections'
HTML_SELECTION_NODE = 'doc:%s:html.selection:%s:node'
HTML_SELECTION_START = 'doc:%s:html.selection:%s:start'
HTML_SELECTION_END = 'doc:%s:html.selection:%s:end'
HTML_SELECTION_REF = 'doc:%s:html.selection:%s:ref'

NAMESPACE = { 'http://www.w3.org/1999/xhtml/#h1':  'h1',
              'http://www.w3.org/1999/xhtml/#h2':  'h2',
              'http://www.w3.org/1999/xhtml/#h3':  'h3',
              'http://www.w3.org/1999/xhtml/#h4':  'h4',
              'http://www.w3.org/1999/xhtml/#p':   'p',
              'http://www.w3.org/1999/xhtml/#ul':  'ul',
              'http://www.w3.org/1999/xhtml/#div': 'div',
              'http://www.w3.org/1999/xhtml/#li':  'li',
              'http://www.w3.org/1999/xhtml/#span':'span' }

MATCH_NODE = r'^(%s)\.s([0-9]+)e([0-9]+)$' % string.join(NAMESPACE.values(), '|')

class TextSelection(object):
    def __init__(self, docid = None, start = None, end = None, ref = None):
        self.docid = int(docid)
        self.start = start
        self.end = end
        self.ref = ref


    def _valid(self):
        # TODO
        return True

    def save(self, redis):
        if self._valid():
            selection_id = redis.incr(NEXT_TXT_SELECTION % self.docid)
            pipe = redis.pipeline()
            pipe.set(TXT_SELECTION_START % \
                (self.docid, selection_id), self.start)
            pipe.set(TXT_SELECTION_END % \
                (self.docid, selection_id), self.end)
            pipe.set(TXT_SELECTION_REF % \
                (self.docid, selection_id), self.ref)
            pipe.lpush(TXT_SELECTIONS % \
                self.docid, selection_id)
            result = pipe.execute()
            print result
            return selection_id
        else:
            return False

    def from_url(self, url):
        scheme, host, path, query, param = urlsplit(url)
        p = re.compile(MATCH_NODE)
        m = re.search(p, param)
        if m is not None:
            self.rel = m.group(1)
            self.start = int(m.group(2))
            self.end = int(m.group(3))


class HtmlSelection(object):
    def __init__(self, docid = None, node = None,
        start = None, end = None, ref = None):
        self.docid = docid
        self.node = node
        self.start = start
        self.end = end
        self.ref = ref

    def _valid(self):
        #TODO
        return True

    def save(self, redis):
        if self._valid():
            selection_id = redis.incr(NEXT_HTML_SELECTION % self.docid)
            pipe = redis.pipeline()
            pipe.set(HTML_SELECTION_NODE % \
                (self.docid, selection_id), self.node)
            pipe.set(HTML_SELECTION_START % \
                (self.docid, selection_id), self.start)
            pipe.set(HTML_SELECTION_END % \
                (self.docid, selection_id), self.end)
            pipe.set(HTML_SELECTION_REF % \
                (self.docid, selection_id), self.ref)
            pipe.lpush(HTML_SELECTIONS % \
                self.docid, selection_id)
            result = pipe.execute()
            print result
            return selection_id
        else:
            return False
        return True

class TextSelections():
    def __init__(self, redis):
        self._redis = redis
        pass

    def from_document_id(self, docid):
        result = []
        selections = self._redis.lrange(TXT_SELECTIONS % docid, 0, -1)
        if len(selections) == 0:
            return result
        pipe = self._redis.pipeline()
        for selection_id in selections:
            pipe.get(TXT_SELECTION_START % (docid, selection_id))
            pipe.get(TXT_SELECTION_END % (docid, selection_id))
            pipe.get(TXT_SELECTION_REF % (docid, selection_id))
            start,end,ref = pipe.execute()
            t = TextSelection(docid, int(start), int(end), ref)
            result.append(t)
        return result

class HtmlSelections():
    def __init__(self, redis):
        self._redis = redis
        pass

    def from_document_id(self, docid):
        result = []
        selections = self._redis.lrange(HTML_SELECTIONS % docid, 0, -1)
        if len(selections) == 0:
            return result
        pipe = self._redis.pipeline()
        for selection_id in selections:
            pipe.get(HTML_SELECTION_NODE % (docid, selection_id))
            pipe.get(HTML_SELECTION_START % (docid, selection_id))
            pipe.get(HTML_SELECTION_END % (docid, selection_id))
            pipe.get(HTML_SELECTION_REF % (docid, selection_id))
            node,start,end,ref = pipe.execute()
            t = HtmlSelection(docid, node, int(start), int(end), ref)
            result.append(t)
        return result