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
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
|
# -*- mode: python; coding: utf-8; -*-
import sys
import string
from io import StringIO
import xml.sax
import xml.parsers.expat
from .paragraph import Paragraph, attr
class StopParsing(Exception):
pass
class ContentHandler:
def __init__(self):
## self.elem_stack = []
self.is_desc = False
self.cur_data = []
self.is_title = False
self.is_body = False
self.is_epigraph = False
self.is_cite = False
self.cur_title = []
self.attrs = []
self.cur_attr = []
self.lang = None
self.content = []
self.cur_id = None
self.prev_paragraph_is_empty = True
def add_empty_line(self):
if not self.prev_paragraph_is_empty:
self.content.append(Paragraph('empty-line', '',
byte_index=_parser.CurrentByteIndex))
self.prev_paragraph_is_empty = True
def startElement(self, name, attrs):
if name == 'description':
self.is_desc = True
elif name == 'body':
self.is_body = True
elif name == 'epigraph':
self.is_epigraph = True
elif name == 'cite':
self.is_cite = True
elif name == 'title':
self.is_title = True
self.cur_title = []
elif name == 'stanza':
self.add_empty_line()
elif name == 'image':
for atr in list(attrs.keys()):
if atr.endswith('href'):
self.add_empty_line()
self.cur_data = '[' + attrs[atr][1:] + ']'
break
elif name == 'binary':
raise StopParsing
elif name in ('strong', 'emphasis', 'style'):
self.cur_attr = [sum(map(len, self.cur_data)), attr[name]]
elif name == 'a':
href = None
for atr in list(attrs.keys()):
if atr.endswith('href'):
href = attrs[atr]
break
self.cur_attr = [sum(map(len, self.cur_data)), (attr.a, href)]
elif name == 'subtitle':
self.add_empty_line()
if 'id' in attrs:
self.cur_id = attrs['id']
def endElement(self, name):
if name == 'empty-line':
self.add_empty_line()
elif self.is_body and name != 'body':
data = ''.join(self.cur_data)
if name in ['strong', 'emphasis', 'a', 'style']:
if not self.cur_attr:
##print 'FB2 PARSER ERROR: nested styles?'
return
self.cur_attr.insert(1, len(data))
self.attrs.append(self.cur_attr)
self.cur_attr = []
return
if data and data.strip():
if self.is_title:
self.add_empty_line()
self.content.append(
Paragraph(
'title', data,
attrs=self.attrs,
lang=self.lang,
id=self.cur_id,
byte_index=_parser.CurrentByteIndex,
)
)
elif self.is_epigraph and name == 'p':
self.content.append(
Paragraph(
'epigraph', data,
attrs=self.attrs,
lang=self.lang,
id=self.cur_id,
byte_index=_parser.CurrentByteIndex
)
)
elif self.is_cite and name == 'p':
self.content.append(
Paragraph(
'cite', data,
attrs=self.attrs,
lang=self.lang,
id=self.cur_id,
byte_index=_parser.CurrentByteIndex
)
)
else:
self.content.append(
Paragraph(
name, data,
attrs=self.attrs,
lang=self.lang,
id=self.cur_id,
byte_index=_parser.CurrentByteIndex
)
)
self.prev_paragraph_is_empty = False
self.attrs = []
self.id = None
if name == 'description':
self.is_desc = False
elif name == 'body':
self.is_body = False
elif name == 'epigraph':
self.is_epigraph = False
self.add_empty_line()
elif name == 'cite':
self.is_cite = False
elif name == 'title':
self.is_title = False
self.add_empty_line()
elif name in ('subtitle', 'image', 'poem'):
self.add_empty_line()
elif name == 'lang':
self.lang = ''.join(self.cur_data).strip()
#del self.elem_stack[-1]
self.cur_data = []
self.links = {}
def characters(self, data):
#data = data.strip()
#data = data.replace('\n', ' ')
self.cur_data.append(data)
##----------------------------------------------------------------------
def fb2parse(data):
if not data.startswith(b'<?xml'):
print('Warning: file is not an XML file. Skipped.')
return None
global _parser
# remove invalid chars
data = data.replace(b'\07', b'')
data = data.replace(b'\032', b'')
content_handler = ContentHandler()
_parser = xml.parsers.expat.ParserCreate()
_parser.StartElementHandler = content_handler.startElement
_parser.EndElementHandler = content_handler.endElement
_parser.CharacterDataHandler = content_handler.characters
try:
_parser.Parse(data)
except StopParsing:
pass
return content_handler.content
##----------------------------------------------------------------------
if __name__ == '__main__':
fn = sys.argv[1]
#from main import create_content
#c = create_content(fn, 80)
c = fb2parse(file(fn).read())
#for s, t in c:
# print t, s
|
