#! /usr/bin/env python -- # -*- python -*- # $What$ '''Structured Text Manipulation Parse a structured text string into a form that can be used with structured formats, like html. Structured text is text that uses indentation and simple symbology to indicate the structure of a document. A structured string consists of a sequence of paragraphs separated by one or more blank lines. Each paragraph has a level which is defined as the minimum indentation of the paragraph. A paragraph is a sub-paragraph of another paragraph if the other paragraph is the last preceedeing paragraph that has a lower level. Special symbology is used to indicate special constructs: - A paragraph that begins with a '-', '*', or 'o' is treated as an unordered list (bullet) element. - A paragraph that begins with a sequence of digits followed by a white-space character is treated as an ordered list element. - A paragraph that begins with a sequence of sequences, where each sequence is a sequence of digits or a sequence of letters followed by a period, is treated as an ordered list element. - A paragraph with a first line that contains some text, followed by some white-space and '--' is treated as a descriptive list element. The leading text is treated as the element title. - Sub-paragraphs of a paragraph that ends in the word 'example' or the word 'examples' is treated as example code and is output as is. - Text enclosed single quotes (with white-space to the left of the first quote and whitespace or puctuation to the right of the second quote) is treated as example code. - Text surrounded by '*' characters (with white-space to the left of the first '*' and whitespace or puctuation to the right of the second '*') is emphasized. - Text surrounded by '**' characters (with white-space to the left of the first '**' and whitespace or puctuation to the right of the second '**') is emphasized. $Id: StructuredText.py,v 1.1 1996/08/26 20:31:46 omfadmin Exp $''' # Copyright # # Copyright 1996 Digital Creations, L.C., 910 Princess Anne # Street, Suite 300, Fredericksburg, Virginia 22401 U.S.A. All # rights reserved. Copyright in this software is owned by DCLC, # unless otherwise indicated. Permission to use, copy and # distribute this software is hereby granted, provided that the # above copyright notice appear in all copies and that both that # copyright notice and this permission notice appear. Note that # any product, process or technology described in this software # may be the subject of other Intellectual Property rights # reserved by Digital Creations, L.C. and are not licensed # hereunder. # # Trademarks # # Digital Creations & DCLC, are trademarks of Digital Creations, L.C.. # All other trademarks are owned by their respective companies. # # No Warranty # # The software is provided "as is" without warranty of any kind, # either express or implied, including, but not limited to, the # implied warranties of merchantability, fitness for a particular # purpose, or non-infringement. This software could include # technical inaccuracies or typographical errors. Changes are # periodically made to the software; these changes will be # incorporated in new editions of the software. DCLC may make # improvements and/or changes in this software at any time # without notice. # # Limitation Of Liability # # In no event will DCLC be liable for direct, indirect, special, # incidental, economic, cover, or consequential damages arising # out of the use of or inability to use this software even if # advised of the possibility of such damages. Some states do not # allow the exclusion or limitation of implied warranties or # limitation of liability for incidental or consequential # damages, so the above limitation or exclusion may not apply to # you. # # # If you have questions regarding this software, # contact: # # Jim Fulton, jim@digicool.com # # (540) 371-6909 # # $Log: /Gendoc/StructuredText.py $ # # 1 98-04-01 13:15 Daniel # Revision 1.1 1996/08/26 20:31:46 omfadmin # Initial revision # # # import regex, regsub indent_tab =regex.compile('\(\n\|^\)\( *\)\t') indent_space=regex.compile('\n\( *\)') paragraph_divider=regex.compile('\(\n *\)+\n') def untabify(aString): '''\ Convert indentation tabs to spaces. ''' result='' rest=aString while 1: start=indent_tab.search(rest) if start >= 0: lnl=len(indent_tab.group(1)) indent=len(indent_tab.group(2)) result=result+rest[:start] rest="\n%s%s" % (' ' * ((indent/8+1)*8), rest[start+indent+1+lnl:]) else: return result+rest def indent_level(aString): '''\ Find the minimum indentation for a string, not counting blank lines. ''' start=0 text='\n'+aString indent=l=len(text) while 1: start=indent_space.search(text,start) if start >= 0: i=len(indent_space.group(1)) start=start+i+1 if start < l and text[start] != '\n': # Skip blank lines if not i: return (0,aString) if i < indent: indent = i else: return (indent,aString) def paragraphs(list,start): l=len(list) level=list[start][0] i=start+1 while i < l and list[i][0] > level: i=i+1 return i-1-start def structure(list): if not list: return [] i=0 l=len(list) r=[] while i < l: sublen=paragraphs(list,i) i=i+1 r.append((list[i-1][1],structure(list[i:i+sublen]))) i=i+sublen return r bullet=regex.compile('[ \t\n]*[o*-][ \t\n]+\([^\0]*\)') example=regex.compile('[ \t\n]examples?:[ \t\n]*$') dl=regex.compile('\([^\n]+\)[ \t]+--[ \t\n]+\([^\0]*\)') nl=regex.compile('\n') ol=regex.compile('[ \t]*\(\([0-9]+\|[a-zA-Z]+\)\.\)+[ \t\n]+\([^\0]*\|$\)') olp=regex.compile('[ \t]*([0-9]+)[ \t\n]+\([^\0]*\|$\)') em=regex.compile("[ \t\n]\*\([^ \t][^\n*]*[^ \t]\)\*\([ \t\n,.:;!?]\)") code=regex.compile("[ \t\n(]'\([^ \t']\([^\n']*[^ \t']\)?\)'\([) \t\n,.:;!?]\)") strong=regex.compile("[ \t\n]\*\*\([^ \t][^\n*]*[^ \t]\)\*\*\([ \t\n,.:;!?]\)") extra_dl=regex.compile("\n
") extra_ul=regex.compile("\n