File: moin2asc.py

package info (click to toggle)
debian-reference 2.128
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 31,588 kB
  • sloc: python: 586; makefile: 572; sh: 526; sed: 80
file content (220 lines) | stat: -rwxr-xr-x 7,177 bytes parent folder | download | duplicates (4)
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
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
#!/usr/bin/env python3
# vim: set sts=4 expandtab:
"""
moin2ascii - convert a moinmoin text file to an AsciiDoc

Copyright (C) 2009 Osamu Aoki, GPL
"""

import sys, os, re

VERSION = '1.0.1'

def process_text(line):
#    line = re.sub(r"\\",'@bslash@',line)
    line = re.sub(r"\\",r'\\',line)
    line = re.sub(r"\~",r'\~',line)
    line = re.sub(r"\^",r'\^',line)
    line = re.sub(r"\*",r'\*',line)
    line = re.sub(r'{{{',r'`',line)
    line = re.sub(r'}}}',r'`',line)
    line = re.sub(r"'''",r'**',line)
    line = re.sub(r"''",r'__',line)
    line = re.sub(r"'",r"\'",line)
#    line = re.sub(r"\&",r'&',line)
#    line = re.sub(r"\<",r'&gt;',line)
#    line = re.sub(r"\>",r'&lt;',line)
    line = re.sub(r'\[\[([^|]+)\|([^]]+)\]\]',r'\1[\2]',line)
    line = re.sub(r'\[\[([^|]+)\\]\]',r'\1[\1]',line)
    return line

def process_indent(line):
    if re.match(r'^=',line):
        line = re.sub(r'^=(.*) =+',r'==\1',line)
    elif line[0:2] == ' *':
        line = "-" + line[2:]
    elif line[0:3] == '  *':
        line = "--" + line[3:]
    elif re.match(r'^ +[0-9]\.',line):
        line = line[1:]
    elif line[0:3] == '/!\\':
        line = "WARNING:" + line[3:]
    elif line[0:3] == r'<!>':
        line = "CAUTION:" + line[3:]
    elif line[0:3] == r'{i}':
        line = "TIP:" + line[3:]
    elif line[0:3] == r'(!)':
        line = "NOTE:" + line[3:]
    line =  process_text(line)
    if line[0:2] == '--':
        line = " *" + line[2:]
    return line

def process_table(line):
    line = re.sub(r'\|\| *([^ ].*[^ ]) *\|\|',r'\1',line)
    items = re.split(r' *\|\| *',line,8)
    i = 0
    for item in items:
        items[i] = process_text(item)
        i = i + 1
    return items

if __name__ == '__main__':

    m2a_mode = 'NORMAL'
    m2a_table_mode = 0
    m2a_table_popcon = 0

    for line in sys.stdin.readlines():
        line=line[0:-1]
        if line == r"{{{#!plain":
            line = "{{{"
        if m2a_mode != 'SCREEN':
            if line[0:2] == '##':
                print("//" + line[2:])
            elif line[0:2] == '||':
                if m2a_mode == 'NORMAL':
                    table_items = [[]]
                    table_rows = 0
                    table_cols = 0
                    table_cols_width = [0]
                    table_item =  process_table(line)
                    table_title = table_item[0]
                    if len(table_item) != 1:
                        table_pkg = table_item[1] # '', '1', '2'
                    else:
                        table_pkg =0
                    print("\n." + table_title)
                    print('[grid="all"]')
                    m2a_mode = 'TABLE_HEAD'
                elif m2a_mode == 'TABLE_HEAD':
                    line = re.sub("'''",'',line)
                    table_items =  [process_table(line)]
                    i = 0
                    m2a_mode = 'TABLE_BODY'
                elif m2a_mode == 'TABLE_BODY':
                    table_item =  process_table(line)
                    if table_pkg == "1":
                        table_item[1] = "@@@popcon1@@@"
                        table_item[2] = "@@@psize1@@@"
                    if table_pkg == "2":
                        table_item[2] = "@@@popcon2@@@"
                        table_item[3] = "@@@psize2@@@"
                    table_items = table_items + [table_item]
                    m2a_mode = 'TABLE_BODY'
            else:
                if m2a_mode == 'TABLE_BODY':
                    # now time to print table
                    table_rows = len(table_items)
                    # find table_cols_width
                    table_cols_width = [0,0,0,0,0,0,0,0,0]
                    for table_item in table_items:
                        i = 0
                        for item in table_item:
                            table_cols_width[i] = max(table_cols_width[i], len(item))
                            i = i + 1
                    # print ruler
                    ruler1 = ""
                    ruler2 = ""
                    i = 0
                    for item in table_cols_width:
                        if item != 0:
                            ruler1 = ruler1 + "`" + ( "-" * item )
                            ruler2 = ruler2 + "-" + ( "-" * item )
                    print(ruler1)
                    # print table_items
                    j = 0
                    for table_item in table_items:
                        i = 0
                        for item in table_item:
                            print(item + " " * (table_cols_width[i] - len(item)), end=' ')
                            i = i + 1
                        print("")
                        j = j + 1
                        if j == 1:
                            print(ruler2)
                    print(ruler2)

                    m2a_mode = 'NORMAL'

                # so this is normal text
                if re.match("^{{{$", line):
                    print('')
                    print('--------------------')
                    m2a_mode = 'SCREEN'
                elif re.match("^ +{{{$", line):
                    print(' +\n--------------------')
                    m2a_mode = 'SCREEN'
                else:
                    if re.match("^ +\*", line):
                        if m2a_mode != 'BULLET':
                            print("")
                            m2a_mode = 'BULLET'
                    else:
                            m2a_mode = 'NORMAL'
                    print(process_indent(line))
        else:
            if re.match("^}}}$", line):
                print('--------------------')
                m2a_mode = 'NORMAL'
            else:
                print(line)
                m2a_mode = 'SCREEN'

""" 
Design: Convert text depending on mode:

MODE = NORMAL
-------------

This is default mode.
This can be base text including buletted/numerated list items.

Processing:
+ Ajust header leads: "s/^=/==/"
+ Adjust buletted/numerated list items.
+ /!\ for "WARNING"
+ <!> for "CAUTION"
+ {i} for "TIP"
+ (!) for "NOTE"
+ content text adjustments and processing

MODE = TABLE
------------

This is table section.
It starts at a line matching "^||"
It ends at a line matching "^[^|][^|]"

Processing:
+ The first line is translated to "TITLE of TABLE".
+ .. If first line contains 2,3,4th argument, they are processed (popcon/size).
     Insert: @@@popcon@@@, @@@size@@@
+ The second line is translated to "HEADER".
+ content text adjustments and processing

MODE = SCREEN
-------------

This is screen section.
It starts at a line matching "^{{{" or "^ {{{"
It ends at a line matching "^}}}"

Processing:
+ verbatim copy as screen ....
+ In case of "^ {{{", continuation of indented list item.

process_line()
------------------
Content text adjustments and processing inclises folowing
+ format converting
 * URL: [[http://...|...]]          --> http://...[...]
 * URL: [[http://...]]              --> http://...
 * The verbatim text are {{{....}}} --> +++....++++
 * ''' for strong *
 * ''  for italics _
 * @{@...@}@ to new style (predefined)
+ reporting to stderr
 * normal text with funny strings
 * @{@...@}@ unprocessed
"""