def PyToHTML(inputfilename, output):
"""Convert a Python file to an HTML file"""
#~Open Files
input = open(inputfilename, 'r')
#output = open(outputfilename, 'w')
#~Make sure Token class is ready, then Parse into Tokens @N
#~Parse calls us back and returns a list of our results
Token_ClassInit()
tokens = Parse(input, Token)
#~Write out the html prefix, with title @N
#~Write out all the Tokens as html @N
#~Write out the html suffix
#~Write out the cross reference
output.write(html_prefix(inputfilename))
if Token.autosplit:
output.write(pymacro.pymax_process('@startsplit'))
for t in tokens:
output.write(t.asHTML())
output.write(html_suffix())
if Token.autosplit:
output.write(pymacro.pymax_process('@endsplit'))
if not pymacro.TestFlag('noindex'):
output.write(Token.xref.asHTML())
def main(argv):
"for command line invocation - gimme sys.argv[1:]"
if not len(argv):
print __doc__ # usage info
return
for arg in argv:
if arg[0] == '-': # command line - convert to @
s = pymacro.pymax_process('@SetFlag{'+arg[1:]+'}')
if s: # report any output
print s
else:
PyToHTML(arg, arg+".html")
def asHTML(self):
""" render this Token asHTML """
s = self.isSpecial # well, isn't that special?
if s:
if not self.preprocessed:
s = autohtml(pymacro.pymax_process(escapes4html(s)))
if 0: # doesn't work as well as hoped - dedents come too late
t = self.indentlevel + 1
if self.indentlevel:
s = '<ul>' * t + s + '</ul>' * t
return html_wrap(self.leading, self.trailing, s)
s = ""
# put out the line numbers
if (self.token or self.type==DEDENT) and self.isAfterNewLine:
s = ('<a name="%d">%4d</a> ' % (self.line, self.line))
type = self.type
token = self.token
if type > RESERVED:
type = RESERVED
wrap = gWraps.get(type,None)
# check for strings with embedded newlines
if type == STRING and string.count(token, '\n') > 1:
t = escapes4html(string.join(
string.split(token, '\n'), '\n '))
if wrap:
t = wrap % t
s = s + t + '\n'
else:
t = escapes4html(token)
if wrap:
t = wrap % t
s = s + t
return s
def __init__(self, type, token, srow, scol, erow, ecol):
#~ Pick up our token info
self.type = type
self.token= token
self.line = srow
# scol, erow, ecol, not in use
#~ Stitch up our linked list
self.next = None
self.previous = Token.previous
if Token.previous:
Token.previous.next = self
Token.previous = self
#~ Remember our level info
self.indentlevel = Token.indentlevel
self.parenlevel = Token.parenlevel
self.bracketlevel = Token.bracketlevel
self.bracelevel = Token.bracelevel
#~ Do all of the level tracking maintenance
if type == INDENT:
Token.indentlevel = Token.indentlevel + 1
elif type == DEDENT:
Token.indentlevel = Token.indentlevel - 1
elif type == OP:
if token == '(':
Token.parenlevel = Token.parenlevel + 1
elif token == ')':
Token.parenlevel = Token.parenlevel - 1
elif token == '[':
Token.bracketlevel = Token.bracketlevel + 1
elif token == ']':
Token.bracketlevel = Token.bracketlevel - 1
elif token == '{':
Token.bracelevel = Token.bracelevel + 1
elif token == '}':
Token.bracelevel = Token.bracelevel - 1
#~ Figure out if we're white space, for future reference
self.isWhite = type in (WHITE, INDENT, DEDENT, NEWLINE, NL)
#~ Worried about newline:
#~ isNewLine means we're a single literal new line character,
#~ but isAfterNewLine means previous item could have also been comment, etc.
self.isAfterNewLine = Token.afternewline
self.isNewLine = type == NL or type == NEWLINE
#~ Set up afternewline for the Next token
Token.afternewline = token and token[-1] == '\n'
#~ Looking for first string on line as possible special comment
self.isFirstString = 0
if type == STRING and Token.firstonline:
if not (self.parenlevel or self.bracketlevel or self.bracelevel):
self.isFirstString = 1
#~ For automatic formatting without explicit ~, add it in,
#~ and preserve existing formatting by adding @@N (<br>) directives
if Token.autoformat:
if Token.firstonline:
if self.isFirstString and len(token) > 2:
if token[0] == token[1]:
if token[3] <> '~':
token = token[0:3] + '~' + token[3:]
elif token[1] <> '~':
token = token[0] + '~' + token[1:]
token = string.replace(token, "\n", "@N\n")
elif type == COMMENT:
if token[1] <> '~' and token[1] <> '-':
token = '#~'+token[1:]
token = string.replace(token, "\n", "@N\n")
#~ Set up firstline for the Next token
if Token.afternewline or type == DEDENT or type == INDENT:
Token.firstonline = 1
elif type <> WHITE:
Token.firstonline = 0
#~ Special defaults
self.isSpecial = 0
self.preprocessed = 0
#~ Quick hack for division lines - beware of #- with other stuff
if type == COMMENT:
if len(token) > 1 and token[1] == '-':
self.isSpecial = "<hr>"
self.preprocessed = 1
self.token = ""
#~Look for specially marked boxes of your favorite serial
# this isn't quite as brutal as it looks
if type == COMMENT and len(token) > 2:
if token[1] == '~':
self.isSpecial = token[2:]
elif token[1] == '@': # early v late execution
self.isSpecial = pymacro.pymax_process(token[1:])
self.preprocessed = 1
self.token = ""
elif self.isFirstString and len(token) > 2:
if token[1] == '~':
self.isSpecial = token[2:-1]
elif token[0] == token[1] and token[3] == '~':
self.isSpecial = token[4:-3]
elif (token ==
'~this is a test'): # this is a test to make sure we don't grab this
pass
"""~
Worrying about the extra blank lines.
If we look backward and ignore any white space
(including INDENT/DEDENT/NEWLINE/NL etc.)
and the first thing we find is also 'special',
then tell him to forget trailing wrapping,
and tell me to forget leading wrapping.
"""
if self.isSpecial:
# drop leading space, just because
if self.isSpecial[0] == ' ':
self.isSpecial = self.isSpecial[1:]
self.leading = 1
self.trailing = 1
previous = self.previous
while previous:
if previous.isWhite:
previous.type = WHITE
previous.token = '' # clear
previous = previous.previous
else:
if previous.isSpecial:
previous.trailing = 0
self.leading = 0
break
"""~
Also look forward to get rid of extra white space/new lines following special.
Handled by looking back from newline instead.
"""
if self.isNewLine: # look back for last special
previous = self.previous
while previous:
if previous.isWhite:
previous = previous.previous
else:
if previous.isSpecial:
self.token = ''
# walk back forward looking for white
previous = previous.next
while not previous is self:
if previous.type == WHITE:
previous.token = ''
previous = previous.next
break
#~ Maintain symbol cross reference for the summary Index
if type == NAME:
Token.xref(token, srow)
#~ Trim the extra lines and white space at the end of the program
if type == ENDMARKER:
previous = self.previous
while previous:
if previous.isWhite:
previous.type = WHITE
previous.token = ''
previous = previous.previous
else:
break
def nested(s):
""" keep on expanding """
while string.find(s, '@') >= 0:
s = pymacro.pymax_process(s)
return s
