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
|
"""
conv_text.py - convert Doc to/from text
$Id: conv_text.py,v 1.4 1998/09/09 11:55:30 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_text.py,v 1.4 1998/09/09 11:55:30 rob Exp $'
import sys, os, string, formatter, re
from PDA.Palm.App import Doc
import DocWriter
class TextParser:
def __init__(self, w, options):
self.writer = w
self.options = options
self.do_markup = 0
self.tag_regex = ''
self.case_fold_tags = 0
self.tag_prefix = None
def __call__(self, fd):
self.fd = fd
w = self.writer
self.verbatim = w.has_option('verbatim')
if self.do_markup: self.do_markup = not w.has_option('no-tags')
if self.do_markup:
if self.tag_prefix:
rx_markup = re.compile(self.tag_regex %
re.escape(w.get_option('tag-prefix',
self.tag_prefix)))
else:
rx_markup = re.compile(self.tag_regex)
self.formatter = formatter.AbstractFormatter(w)
self.in_para = 0
while 1:
l = self.fd.readline()
if not l: break
if self.do_markup:
m = rx_markup.match(string.rstrip(l))
if m:
tag, arg = m.group('tag','arg')
if self.case_fold_tags: tag = string.lower(tag)
meth = 'tag_' + tag
if hasattr(self, meth):
apply(getattr(self, meth), (arg,))
continue
elif hasattr(self, 'tag'):
if not self.tag(tag, arg):
continue
if self.verbatim:
self.formatter.add_literal_data(l)
else:
if not string.strip(l):
if self.in_para:
in_para = 0
self.formatter.end_paragraph(1)
else:
self.in_para = 1
self.formatter.add_flowing_data(l)
class TextWithTagsParser(TextParser):
def __init__(self, *a, **kw):
apply(TextParser.__init__, (self,)+a, kw)
self.do_markup = 1
self.tag_regex = "^%s\s*(?P<tag>[a-zA-Z0-9/_]+)(?:\s*(?P<arg>.*)\s*)?"
self.case_fold_tags = 0
self.tag_prefix = '.'
def tag_TITLE(self, arg):
if not self.writer.has_title(): self.writer.set_title(arg)
def tag_BOOKMARK(self, arg):
self.writer.set_bookmark(arg)
tag_BM = tag_BOOKMARK
def tag_H1(self, arg):
self.formatter.end_paragraph(1)
self.writer.send_heading(arg, 1)
def tag_H2(self, arg):
self.formatter.end_paragraph(1)
self.writer.send_heading(arg, 2)
def tag_H3(self, arg):
self.formatter.end_paragraph(1)
self.writer.send_heading(arg, 3)
def tag_H4(self, arg):
self.formatter.end_paragraph(1)
self.writer.send_heading(arg, 4)
def tag_H5(self, arg):
self.formatter.end_paragraph(1)
self.writer.send_heading(arg, 5)
def tag_H6(self, arg):
self.formatter.end_paragraph(1)
self.writer.send_heading(arg, 6)
def tag_PRE(self, arg):
self.verbatim = 1
def tag(self, tag, arg):
if tag == '/PRE': self.verbatim = 0
else:
return 1
def tag_HR(self, arg):
self.writer.send_hor_rule()
parsers = {
'none': TextParser,
'default': TextWithTagsParser,
}
# The input-type option is not yet supported
def text_to_doc(fd, w, title=None, options=None, default_title='Untitled'):
p = parsers.get(w.get_option('input-type','default'),
TextParser)(w, options)
p(fd)
if not w.has_title():
w.set_title(default_title)
def doc_to_text(docname, fd, dlp=None):
if dlp:
doc = Doc.openDocRemote(dlp, docname, 'r')
else:
doc = Doc.openDoc(docname, 'r')
while 1:
l = doc.readline()
if not l: break
fd.write(l)
doc.close()
# really need to flesh this out :)
def totext_main(argv):
for fn in argv[1:]:
doc_to_text(fn, sys.stdout)
def todoc_main(argv):
from cmdproc import CmdLine
c = CmdLine('text',
[('verbatim', 'direct conversion; do not process text'),
('no-tags', 'do not process embedded tags'),
('tag-prefix', 'string that marks embedded tags')])
c.process_options(argv)
c.process_files(text_to_doc)
|
