#!/usr/bin/python3
# Copyright 2023 Ted Clark
#
# 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 to the Free Software Foundation, Inc.,
# 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
from sys import argv, exit, stderr
def assert_head():
if not document_head:
stderr.write('Missing document head\n')
exit(1)
def close_tags():
if state == 'QUOTE' or state == 'QUOTE2':
print('')
elif state == 'TD' or state == 'TD2':
print('')
elif state == 'TH' or state == 'TH2':
print('')
elif state == 'ULIST' or state == 'ULIST2':
print('')
def decode_string(string):
decoded_str = ''
skip = 0
for ii in range(0, len(string)):
if skip:
# Skip over HTML codes and tags
skip -= 1
continue
if string[ii] == '&':
# Replace '&' with &, but don't change HTML codes such as
# to .
codes = ('-', '✓', '&', 'ε', '>', '<',
'—', ' ', '–')
found = False
for code in codes:
if string[ii:ii + len(code)] == code:
decoded_str += code
skip = len(code) - 1
found = True
break
if found:
continue
decoded_str += '&'
elif string[ii] == '<':
# Replace '<' with <, but don't change HTML tags such as
# to <br>.
tags = ('
',
'', '',
'', '',
'', '',
'', '',
'', '',
'', '
',
'', '
',
'', '',
'', '',
'', '',
)
found = False
for tag in tags:
if string[ii:ii + len(tag)] == tag:
decoded_str += tag
skip = len(tag) - 1
found = True
break
if found:
continue
decoded_str += '<'
elif string[ii] == '>':
decoded_str += '>'
else:
decoded_str += string[ii]
return decoded_str
def get_state(line):
global document_head, in_css, in_table, paragraph_num, state
if line == '---':
close_tags()
state = 'NO_OP'
return True
elif line == '---body':
if in_css:
print('')
in_css = False
if not document_head:
print('\n')
document_head = True
state = 'NO_OP'
return True
elif line == '---br':
assert_head()
# ---br does not close tags or change state, so table rows and tables
# have to be explicitly closed.
if in_table:
print('\n')
in_table = False
state = 'NO_OP'
print('
')
return True
elif line == '---c':
close_tags()
state = 'COMMENT'
return True
elif line == '---css':
state = 'CSS'
return True
elif line == '---h1':
assert_head()
close_tags()
state = 'H1'
return True
elif line == '---h2':
assert_head()
close_tags()
state = 'H2'
return True
elif line == '---head':
state = 'HEAD'
return True
elif line == '---l':
assert_head()
close_tags()
state = 'LINK'
return True
elif line == '---pnum':
paragraph_num = 1
elif line == '---q':
assert_head()
close_tags()
state = 'QUOTE'
return True
elif line == '---raw':
assert_head()
close_tags()
state = 'RAW'
return True
elif line == '---t':
assert_head()
close_tags()
state = 'TEXT'
return True
elif line == '---td':
assert_head()
close_tags()
state = 'TD'
return True
elif line == '---th':
assert_head()
close_tags()
state = 'TH'
return True
elif line == '---ul':
assert_head()
close_tags()
state = 'ULIST'
return True
return False
def is_table_state():
if state == 'TD' or state == 'TD2' or state == 'TH' or state == 'TH2':
return True
return False
def print_css(line):
global in_css
if not in_css:
print('