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
|
"""
htmldoc.py - convert HTML to/from Doc-format e-texts
$Id: conv_html.py,v 1.2 1998/09/04 08:36:46 rob Exp $
Copyright 1998 Rob Tillotson <rob@io.com>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License, version 2,
as published by the Free Software Foundation.
This program is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write the Free Software Foundation,
Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
"""
__version__ = '$Id: conv_html.py,v 1.2 1998/09/04 08:36:46 rob Exp $'
import sys, string, os
import htmllib, formatter, urllib
import DocWriter
class DocHTMLParser(htmllib.HTMLParser):
"""A HTML parser with some support for Doc-format e-texts."""
def __init__(self, *a, **kw):
apply(htmllib.HTMLParser.__init__, (self,)+a, kw)
self.writer = self.formatter.writer
self.tcol = 0
def end_title(self):
htmllib.HTMLParser.end_title(self)
if not self.writer.has_title():
self.writer.set_title(self.title)
# entities
from entitydefs import entitydefs
# headings
def start_h1(self, attr):
self.save_bgn()
def end_h1(self):
text = self.save_end()
self.formatter.end_paragraph(1)
self.writer.send_heading(text, 1)
def start_h2(self, attr):
self.save_bgn()
def end_h2(self):
text = self.save_end()
self.formatter.end_paragraph(1)
self.writer.send_heading(text, 2)
def start_h3(self, attr):
self.save_bgn()
def end_h3(self):
text = self.save_end()
self.formatter.end_paragraph(1)
self.writer.send_heading(text, 3)
def start_h4(self, attr):
self.save_bgn()
def end_h4(self):
text = self.save_end()
self.formatter.end_paragraph(1)
self.writer.send_heading(text, 4)
def start_h5(self, attr):
self.save_bgn()
def end_h5(self):
text = self.save_end()
self.formatter.end_paragraph(1)
self.writer.send_heading(text, 5)
def start_h6(self, attr):
self.save_bgn()
def end_h6(self):
text = self.save_end()
self.formatter.end_paragraph(1)
self.writer.send_heading(text, 6)
# anchors.
def anchor_bgn(self, href, name, type):
if name and not self.writer.has_option('no-anchor-bookmarks'):
if name[0] == '#': name = name[1:]
self.writer.set_bookmark(name)
if self.writer.has_option('teal-links'):
if name:
if name[0] == '#': name = name[1:]
self.writer.send_raw_tag('LABEL',{'NAME':'"%s"' % name})
if href and href[0] == '#':
self.writer.send_raw_tag('LINK',{'TEXT':'"%s"' % (chr(187)*2),
'FONT':'0',
'TAG':'"%s"' % href[1:],
'STYLE':'UNDERLINE'})
elif href and not self.writer.has_option('no-links'):
self.anchor = href
self.anchorlist.append(href)
elif href and href[0] != '#' and not self.writer.has_option('no-links'):
self.anchor = href
self.anchorlist.append(href)
# now, let's see what we can do about tables.
# the simplest thing to do is to treat each table row as a separate line;
def do_tr(self, attrs):
self.tcol = 0
self.formatter.end_paragraph(0)
def do_td(self, attrs):
if self.tcol: self.formatter.add_flowing_data(' ')
self.tcol = self.tcol+1
def start_table(self, attrs):
pass
def end_table(self):
self.formatter.end_paragraph(1)
#-- Lists, mostly cribbed from htmllib.
def start_ul(self, attrs):
type = 'disc'
for a, v in attrs:
if a == 'type': type = v
if type == 'square': label = chr(0x8d)
elif type == 'circle': label = 'o'
else: label = chr(0x95)
self.formatter.end_paragraph(not self.list_stack)
self.formatter.push_margin('ul')
self.list_stack.append(['ul', label, 0])
def do_li(self, attrs):
self.formatter.end_paragraph(0)
if self.list_stack:
[dummy, label, counter] = top = self.list_stack[-1]
top[2] = counter = counter+1
else:
label, counter = chr(0x95), 0
self.formatter.add_label_data(label, counter)
def html_to_doc(fd, w, title=None, options=None, default_title='Untitled'):
"""Convert HTML (on the specified input file) to a Doc."""
f = formatter.AbstractFormatter(w)
p = DocHTMLParser(f)
strip = not w.has_option('pass-returns')
ttbl = string.maketrans('','')
while 1:
l = fd.readline()
if not l: break
if strip: l = string.translate(l, ttbl, '\r')
p.feed(l)
# handle anchors
if p.anchorlist and not w.has_option('no-links'):
f.end_paragraph(1)
f.add_hor_rule()
w.set_bookmark('%s Links' % chr(187))
w.send_heading('Links:',3)
for x in range(0, len(p.anchorlist)):
f.add_label_data('[1] ', x+1)
f.add_flowing_data(p.anchorlist[x])
f.add_line_break()
if not w.has_title():
w.set_title(default_title)
def main(argv):
from cmdproc import CmdLine
c = CmdLine('HTML',
[('no-links', 'do not mark or footnote links'),
('no-anchor-bookmarks', 'omit bookmarks for named anchors')])
c.process_options(argv)
c.process_files(html_to_doc)
|
