X-Git-Url: https://git.saurik.com/wxWidgets.git/blobdiff_plain/c12bc4de5887421242de7f619b3c5e265bf631ac..edb89f7e356761b4fbdaebb8b5ebd5c7a7643da7:/wxPython/samples/stxview/StructuredText/StructuredText.py diff --git a/wxPython/samples/stxview/StructuredText/StructuredText.py b/wxPython/samples/stxview/StructuredText/StructuredText.py index a1b3fd03ad..2408f2331c 100644 --- a/wxPython/samples/stxview/StructuredText/StructuredText.py +++ b/wxPython/samples/stxview/StructuredText/StructuredText.py @@ -1,4 +1,3 @@ -#! /usr/bin/env python -- # -*- python -*- ############################################################################## # # Zope Public License (ZPL) Version 1.0 @@ -83,751 +82,67 @@ # attributions are listed in the accompanying credits file. # ############################################################################## -'''Structured Text Manipulation -Parse a structured text string into a form that can be used with -structured formats, like html. +""" Alias module for StructuredTextClassic compatibility which makes +use of StructuredTextNG """ -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 -preceding paragraph that has a lower level. +import HTMLClass, DocumentClass, ClassicDocumentClass +from ST import Basic -Special symbology is used to indicate special constructs: +import re, string,sys +from STletters import letters -- A single-line paragraph whose immediately succeeding paragraphs are lower - level is treated as a header. +Document = ClassicDocumentClass.DocumentClass() +HTMLNG = HTMLClass.HTMLClass() -- A paragraph that begins with a '-', '*', or 'o' is treated as an - unordered list (bullet) element. +def HTML(aStructuredString, level=0): + st = Basic(aStructuredString) + doc = Document(st) + return HTMLNG(doc) -- A paragraph that begins with a sequence of digits followed by a - white-space character is treated as an ordered list element. +def StructuredText(aStructuredString, level=0): + return HTML(aStructuredString,level) -- 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', or '::' 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 made strong. - -- Text surrounded by '_' underscore characters (with whitespace to the left - and whitespace or punctuation to the right) is made underlined. - -- Text encloded by double quotes followed by a colon, a URL, and concluded - by punctuation plus white space, *or* just white space, is treated as a - hyper link. For example: - - "Zope":http://www.zope.org/ is ... - - Is interpreted as 'Zope is ....' - Note: This works for relative as well as absolute URLs. - -- Text enclosed by double quotes followed by a comma, one or more spaces, - an absolute URL and concluded by punctuation plus white space, or just - white space, is treated as a hyper link. For example: - - "mail me", mailto:amos@digicool.com. - - Is interpreted as 'mail me.' - -- Text enclosed in brackets which consists only of letters, digits, - underscores and dashes is treated as hyper links within the document. - For example: - - As demonstrated by Smith [12] this technique is quite effective. - - Is interpreted as '... by Smith [12] this ...'. Together - with the next rule this allows easy coding of references or end notes. - -- Text enclosed in brackets which is preceded by the start of a line, two - periods and a space is treated as a named link. For example: - - .. [12] "Effective Techniques" Smith, Joe ... - - Is interpreted as '[12] "Effective Techniques" ...'. - Together with the previous rule this allows easy coding of references or - end notes. - - -- A paragraph that has blocks of text enclosed in '||' is treated as a - table. The text blocks correspond to table cells and table rows are - denoted by newlines. By default the cells are center aligned. A cell - can span more than one column by preceding a block of text with an - equivalent number of cell separators '||'. Newlines and '|' cannot - be a part of the cell text. For example: - - |||| **Ingredients** || - || *Name* || *Amount* || - ||Spam||10|| - ||Eggs||3|| - - is interpreted as:: - - - - - - - - - - - - - - - - - -

Ingredients
Name	Amount
Spam	10
Eggs	3

' - - def create(self,aPar,td=ts_regex.compile( - '[ \t\n]*||$[^\0|]*$').match_group): - '''parses a table and returns nested list representing the - table''' - self.table=[] - text=filter(None,split(aPar,'\n')) - for line in text: - row=[] - while 1: - pos=td(line,(1,)) - if not pos:return 0 - row.append(pos[1]) - if pos[0]==len(line):break - line=line[pos[0]:] - self.table.append(row) - return 1 - - def html(self): - '''Creates an HTML representation of table''' - htmltable=[] - for row in self.table: - htmlrow=[] - colspan=1 - for cell in row: - if cell=='': - colspan=colspan+1 - continue - else: - htmlrow.append(self.CELL%(colspan,cell)) - colspan=1 - htmltable.append(self.ROW%join(htmlrow,'')) - return self.TABLE%join(htmltable,'') - -optional_trailing_punctuation = '$,\|\([.:?;]$\)?' -trailing_space = '$[\0- ]$' -not_punctuation_or_whitespace = "[^-,.?:\0- ]" -table=Table() - -class StructuredText: - - """Model text as structured collection of paragraphs. - - Structure is implied by the indentation level. - - This class is intended as a base classes that do actual text - output formatting. - """ - - def __init__(self, aStructuredString, level=0, - paragraph_divider=regex.compile('$\n *$+\n'), - ): - '''Convert a structured text string into a structured text object. - - Aguments: - - aStructuredString -- The string to be parsed. - level -- The level of top level headings to be created. - ''' - - aStructuredString = gsub( - '\"$[^\"\0]+$\":' # title: <"text":> - + ('$[-:a-zA-Z0-9_,./?=@#~]+%s$' - % not_punctuation_or_whitespace) - + optional_trailing_punctuation - + trailing_space, - '\\1\\4\\5\\6', - aStructuredString) - - aStructuredString = gsub( - '\"$[^\"\0]+$\",[\0- ]+' # title: <"text", > - + ('$[a-zA-Z]*:[-:a-zA-Z0-9_,./?=@#~]*%s$' - % not_punctuation_or_whitespace) - + optional_trailing_punctuation - + trailing_space, - '\\1\\4\\5\\6', - aStructuredString) - - protoless = find(aStructuredString, '\\2\\3',s) - s=gsub(under, '\\1\\2\\3',s) - s=gsub(code, '\\1\\2\\3',s) - s=gsub(em, '\\1\\2\\3',s) - return s - -class HTML(StructuredText): - - '''\ - An HTML structured text formatter. - '''\ - - def __str__(self, - extra_dl=regex.compile("\n

"), - extra_ul=regex.compile("\n

"), - extra_ol=regex.compile("\n

"), - ): - '''\ - Return an HTML string representation of the structured text data. - - ''' - s=self._str(self.structure,self.level) - s=gsub(extra_dl,'\n',s) - s=gsub(extra_ul,'\n',s) - s=gsub(extra_ol,'\n',s) - return s - - def ul(self, before, p, after): - if p: p="

" % strip(ctag(p)) - return ('%s

%s\n%s\n

\n' - % (before,p,after)) - - def ol(self, before, p, after): - if p: p="

" % strip(ctag(p)) - return ('%s

%s\n%s\n

\n' - % (before,p,after)) - - def dl(self, before, t, d, after): - return ('%s

%s: %s
\n%s\n

\n' - % (before,ctag(t),ctag(d),after)) - - def head(self, before, t, level, d): - if level > 0 and level < 6: - return ('%s%s\n%s\n' - % (before,level,strip(ctag(t)),level,d)) - - t="

" % strip(ctag(t)) - return ('%s

%s\n: %s\n

\n' - % (before,t,d)) - - def normal(self,before,p,after): - return '%s

\n%s\n' % (before,ctag(p),after) +def html_with_references(text, level=1): + text = re.sub( + r'[\000\n]\.\. \[([0-9_%s-]+)\]' % letters, + r'\n

[\1]

\n'
-        for s in structure:
-            r="%s%s\n\n%s" % (r,html_quote(s[0]),self.pre(s[1],1))
-        if not tagged: r=r+'

[0-9_%s-]+)\]([\000- ,.:])' % letters, + r'\1[\2]\3', + text) - def _str(self,structure,level, - # Static - bullet=ts_regex.compile('[ \t\n]*[o*-][ \t\n]+$[^\0]*$' - ).match_group, - example=ts_regex.compile('[\0- ]examples?:[\0- ]*$' - ).search, - dl=ts_regex.compile('$[^\n]+$[ \t]+--[ \t\n]+$[^\0]*$' - ).match_group, - nl=ts_regex.compile('\n').search, - ol=ts_regex.compile( - '[ \t]*$\([0-9]+\|[a-zA-Z]+$[.)]\)+[ \t\n]+$[^\0]*\|$$' - ).match_group, - olp=ts_regex.compile('[ \t]*([0-9]+)[ \t\n]+$[^\0]*\|$$' - ).match_group, - ): - r='' - for s in structure: - - ts_results = bullet(s[0], (1,)) - if ts_results: - p = ts_results[1] - if s[0][-2:]=='::' and s[1]: ps=self.pre(s[1]) - else: ps=self._str(s[1],level) - r=self.ul(r,p,ps) - continue - ts_results = ol(s[0], (3,)) - if ts_results: - p = ts_results[1] - if s[0][-2:]=='::' and s[1]: ps=self.pre(s[1]) - else: ps=self._str(s[1],level) - r=self.ol(r,p,ps) - continue - ts_results = olp(s[0], (1,)) - if ts_results: - p = ts_results[1] - if s[0][-2:]=='::' and s[1]: ps=self.pre(s[1]) - else: ps=self._str(s[1],level) - r=self.ol(r,p,ps) - continue - ts_results = dl(s[0], (1,2)) - if ts_results: - t,d = ts_results[1] - r=self.dl(r,t,d,self._str(s[1],level)) - continue - if example(s[0]) >= 0 and s[1]: - # Introduce an example, using pre tags: - r=self.normal(r,s[0],self.pre(s[1])) - continue - if s[0][-2:]=='::' and s[1]: - # Introduce an example, using pre tags: - r=self.normal(r,s[0][:-1],self.pre(s[1])) - continue - if table.create(s[0]): - ## table support. - r=self.table(r,table.html(),self._str(s[1],level)) - continue - else: + text = re.sub( + r'([\000- ,])\[([^]]+)\.html\]([\000- ,.:])', + r'\1[\2]\3', + text) - if nl(s[0]) < 0 and s[1] and s[0][-1:] != ':': - # Treat as a heading - t=s[0] - r=self.head(r,t,level, - self._str(s[1],level and level+1)) - else: - r=self.normal(r,s[0],self._str(s[1],level)) - return r - + return HTML(text,level=level) def html_quote(v, character_entities=( - (regex.compile('&'), '&'), - (regex.compile("<"), '<' ), - (regex.compile(">"), '>' ), - (regex.compile('"'), '"') + (re.compile('&'), '&'), + (re.compile("<"), '<' ), + (re.compile(">"), '>' ), + (re.compile('"'), '"') )): #" text=str(v) for re,name in character_entities: - text=gsub(re,name,text) + text=re.sub(name,text) return text -def html_with_references(text, level=1): - text = gsub( - '[\0\n].. \[$[-_0-9_a-zA-Z-]+$\]', - '\n [\\1]', - text) - - text = gsub( - '$[\0- ,]$\[$[0-9_a-zA-Z-]+$\]$[\0- ,.:]$', - '\\1[\\2]\\3', - text) - - text = gsub( - '$[\0- ,]$\[$[^]]+$\.html\]$[\0- ,.:]$', - '\\1[\\2]\\3', - text) - - return HTML(text,level=level) - - -def main(): - import sys, getopt - - opts,args=getopt.getopt(sys.argv[1:],'tw') - - if args: - [infile]=args - s=open(infile,'r').read() - else: - s=sys.stdin.read() - if opts: +if __name__=='__main__': + import getopt - if filter(lambda o: o[0]=='-w', opts): - print 'Content-Type: text/html\n' + opts,args = getopt.getopt(sys.argv[1:],'',[]) - if s[:2]=='#!': - s=ts_regex.sub('^#![^\n]+','',s) + for k,v in opts: + pass - r=ts_regex.compile('$[\0-\n]*\n$') - ts_results = r.match_group(s, (1,)) - if ts_results: - s=s[len(ts_results[1]):] - s=str(html_with_references(s)) - if s[:4]=='

': - t=s[4:find(s,'

')] - s='''%s - - %s - - ''' % (t,s) - print s - else: - print html_with_references(s) -if __name__=="__main__": main() + for f in args: + print HTML(open(f).read())