[Zope3-checkins] CVS: zopeproducts/bugtracker/browser/StructuredText - ClassicDocumentClass.py:1.1 ClassicStructuredText.py:1.1 DocBookClass.py:1.1 DocumentClass.py:1.1 DocumentWithImages.py:1.1 HTMLClass.py:1.1 HTMLWithImages.py:1.1 ST.py:1.1 STDOM.py:1.1 STNG.txt:1.1 STletters.py:1.1 StructuredText.py:1.1 __init__.py:1.1 ts_regex.py:1.1
Stephan Richter
srichter@cosmos.phy.tufts.edu
Thu, 24 Jul 2003 14:08:30 -0400
Update of /cvs-repository/zopeproducts/bugtracker/browser/StructuredText
In directory cvs.zope.org:/tmp/cvs-serv302/browser/StructuredText
Added Files:
ClassicDocumentClass.py ClassicStructuredText.py
DocBookClass.py DocumentClass.py DocumentWithImages.py
HTMLClass.py HTMLWithImages.py ST.py STDOM.py STNG.txt
STletters.py StructuredText.py __init__.py ts_regex.py
Log Message:
First Checkin of the Bug Tracker. A list of features is the README.txt file
and a to-do list is in TODO.txt.
The code features the use of vocabularies and vocabulary fields.
There is still a bit of work to do, but I am pretty close to make it usable
for us.
=== Added File zopeproducts/bugtracker/browser/StructuredText/ClassicDocumentClass.py ===
##############################################################################
#
# Copyright (c) 2001 Zope Corporation and Contributors. All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL). A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE
#
##############################################################################
import re, ST, STDOM
from STletters import letters
from types import StringType, UnicodeType, ListType
StringTypes = (StringType, UnicodeType)
class StructuredTextExample(ST.StructuredTextParagraph):
"""Represents a section of document with literal text, as for examples"""
def __init__(self, subs, **kw):
t=[]; a=t.append
for s in subs: a(s.getNodeValue())
ST.StructuredTextParagraph.__init__(self, '\n\n'.join(t), (), **kw)
def getColorizableTexts(self): return ()
def setColorizableTexts(self, src): pass # never color examples
class StructuredTextBullet(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
class StructuredTextNumbered(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
class StructuredTextDescriptionTitle(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
class StructuredTextDescriptionBody(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
class StructuredTextDescription(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
def __init__(self, title, src, subs, **kw):
ST.StructuredTextParagraph.__init__(self, src, subs, **kw)
self._title=title
def getColorizableTexts(self): return self._title, self._src
def setColorizableTexts(self, src): self._title, self._src = src
def getChildren(self):
return (StructuredTextDescriptionTitle(self._title),
StructuredTextDescriptionBody(self._src, self._subs))
class StructuredTextSectionTitle(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
class StructuredTextSection(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
def __init__(self, src, subs=None, **kw):
ST.StructuredTextParagraph.__init__(
self, StructuredTextSectionTitle(src), subs, **kw)
def getColorizableTexts(self):
return self._src.getColorizableTexts()
def setColorizableTexts(self,src):
self._src.setColorizableTexts(src)
# a StructuredTextTable holds StructuredTextRows
class StructuredTextTable(ST.StructuredTextDocument):
"""
rows is a list of lists containing tuples, which
represent the columns/cells in each rows.
EX
rows = [[('row 1:column1',1)],[('row2:column1',1)]]
"""
def __init__(self, rows, src, subs, **kw):
ST.StructuredTextDocument.__init__(self, subs, **kw)
self._rows = []
for row in rows:
if row:
self._rows.append(StructuredTextRow(row,kw))
def getRows(self):
return [self._rows]
def _getRows(self):
return self.getRows()
def getColorizableTexts(self):
"""
return a tuple where each item is a column/cell's
contents. The tuple, result, will be of this format.
("r1 col1", "r1=col2", "r2 col1", "r2 col2")
"""
#result = ()
result = []
for row in self._rows:
for column in row.getColumns()[0]:
#result = result[:] + (column.getColorizableTexts(),)
result.append(column.getColorizableTexts()[0])
return result
def setColorizableTexts(self,texts):
"""
texts is going to a tuple where each item is the
result of being mapped to the colortext function.
Need to insert the results appropriately into the
individual columns/cells
"""
for row_index in range(len(self._rows)):
for column_index in range(len(self._rows[row_index]._columns)):
self._rows[row_index]._columns[column_index].setColorizableTexts((texts[0],))
texts = texts[1:]
def _getColorizableTexts(self):
return self.getColorizableTexts()
def _setColorizableTexts(self):
return self.setColorizableTexts()
# StructuredTextRow holds StructuredTextColumns
class StructuredTextRow(ST.StructuredTextDocument):
def __init__(self,row,kw):
"""
row is a list of tuples, where each tuple is
the raw text for a cell/column and the span
of that cell/column.
EX
[('this is column one',1), ('this is column two',1)]
"""
ST.StructuredTextDocument.__init__(self, [], **kw)
self._columns = []
for column in row:
self._columns.append(StructuredTextColumn(column[0],column[1],kw))
def getColumns(self):
return [self._columns]
def _getColumns(self):
return [self._columns]
# this holds the raw text of a table cell
class StructuredTextColumn(ST.StructuredTextParagraph):
"""
StructuredTextColumn is a cell/column in a table.
This contains the actual text of a column and is
thus a StructuredTextParagraph. A StructuredTextColumn
also holds the span of its column
"""
def __init__(self,text,span,kw):
ST.StructuredTextParagraph.__init__(self, text, [], **kw)
self._span = span
def getSpan(self):
return self._span
def _getSpan(self):
return self._span
class StructuredTextMarkup(STDOM.Element):
def __init__(self, v, **kw):
self._value=v
self._attributes=kw.keys()
for k, v in kw.items(): setattr(self, k, v)
def getChildren(self, type=type, lt=type([])):
v=self._value
if type(v) is not lt: v=[v]
return v
def getColorizableTexts(self): return self._value,
def setColorizableTexts(self, v): self._value=v[0]
def __repr__(self):
return '%s(%s)' % (self.__class__.__name__, `self._value`)
class StructuredTextLiteral(StructuredTextMarkup):
def getColorizableTexts(self): return ()
def setColorizableTexts(self, v): pass
class StructuredTextEmphasis(StructuredTextMarkup): pass
class StructuredTextStrong(StructuredTextMarkup): pass
class StructuredTextInnerLink(StructuredTextMarkup): pass
class StructuredTextNamedLink(StructuredTextMarkup): pass
class StructuredTextUnderline(StructuredTextMarkup): pass
class StructuredTextLink(StructuredTextMarkup):
"A simple hyperlink"
class DocumentClass:
"""
Class instance calls [ex.=> x()] require a structured text
structure. Doc will then parse each paragraph in the structure
and will find the special structures within each paragraph.
Each special structure will be stored as an instance. Special
structures within another special structure are stored within
the 'top' structure
EX : '-underline this-' => would be turned into an underline
instance. '-underline **this**' would be stored as an underline
instance with a strong instance stored in its string
"""
paragraph_types = [
'doc_bullet',
'doc_numbered',
'doc_description',
'doc_header',
'doc_table',
]
text_types = [
'doc_href1',
'doc_href2',
'doc_strong',
'doc_emphasize',
'doc_literal',
'doc_inner_link',
'doc_named_link',
'doc_underline',
]
def __call__(self, doc):
if type(doc) in StringTypes:
doc=ST.StructuredText(doc)
doc.setSubparagraphs(self.color_paragraphs(
doc.getSubparagraphs()))
else:
doc=ST.StructuredTextDocument(self.color_paragraphs(
doc.getSubparagraphs()))
return doc
def parse(self, raw_string, text_type,
type=type, sts=StringTypes, lt=type([])):
"""
Parse accepts a raw_string, an expr to test the raw_string,
and the raw_string's subparagraphs.
Parse will continue to search through raw_string until
all instances of expr in raw_string are found.
If no instances of expr are found, raw_string is returned.
Otherwise a list of substrings and instances is returned
"""
tmp = [] # the list to be returned if raw_string is split
append=tmp.append
if type(text_type) in sts: text_type=getattr(self, text_type)
while 1:
t = text_type(raw_string)
if not t: break
#an instance of expr was found
t, start, end = t
if start: append(raw_string[0:start])
tt=type(t)
if tt in sts:
# if we get a string back, add it to text to be parsed
raw_string = t+raw_string[end:len(raw_string)]
else:
if tt is lt:
# is we get a list, append it's elements
tmp[len(tmp):]=t
else:
# normal case, an object
append(t)
raw_string = raw_string[end:len(raw_string)]
if not tmp: return raw_string # nothing found
if raw_string: append(raw_string)
elif len(tmp)==1: return tmp[0]
return tmp
def color_text(self, str, types=None):
"""Search the paragraph for each special structure
"""
if types is None: types=self.text_types
for text_type in types:
if type(str) in StringTypes:
str = self.parse(str, text_type)
elif type(str) is ListType:
r=[]; a=r.append
for s in str:
if type(s) in StringTypes:
s=self.parse(s, text_type)
if type(s) is ListType: r[len(r):]=s
else: a(s)
else:
s.setColorizableTexts(
map(self.color_text,
s.getColorizableTexts()
))
a(s)
str=r
else:
r=[]; a=r.append; color=self.color_text
for s in str.getColorizableTexts():
color(s, (text_type,))
a(s)
str.setColorizableTexts(r)
return str
def color_paragraphs(self, raw_paragraphs,
type=type, sequence_types=(type([]), type(())),
sts=StringTypes):
result=[]
for paragraph in raw_paragraphs:
if paragraph.getNodeName() != 'StructuredTextParagraph':
result.append(paragraph)
continue
for pt in self.paragraph_types:
if type(pt) in sts:
# grab the corresponding function
pt=getattr(self, pt)
# evaluate the paragraph
r=pt(paragraph)
if r:
if type(r) not in sequence_types:
r=r,
new_paragraphs=r
for paragraph in new_paragraphs:
paragraph.setSubparagraphs(self.color_paragraphs(paragraph.getSubparagraphs()))
break
else:
new_paragraphs=ST.StructuredTextParagraph(paragraph.getColorizableTexts()[0],
self.color_paragraphs(paragraph.getSubparagraphs()),
indent=paragraph.indent),
# color the inline StructuredText types
# for each StructuredTextParagraph
for paragraph in new_paragraphs:
paragraph.setColorizableTexts(
map(self.color_text,
paragraph.getColorizableTexts()
))
result.append(paragraph)
return result
def doc_table(self,paragraph, expr = re.compile('(\s*)([||]+)').match):
#print "paragraph=>", type(paragraph), paragraph, paragraph._src
text = paragraph.getColorizableTexts()[0]
m = expr(text)
if not (m):
return None
rows = []
# initial split
for row in text.split("\n"):
rows.append(row)
# clean up the rows
for index in range(len(rows)):
tmp = []
rows[index] = rows[index].strip()
l = len(rows[index])-2
result = rows[index][:l].split("||")
for text in result:
if text:
tmp.append(text)
tmp.append('')
else:
tmp.append(text)
rows[index] = tmp
# remove trailing '''s
for index in range(len(rows)):
l = len(rows[index])-1
rows[index] = rows[index][:l]
result = []
for row in rows:
cspan = 0
tmp = []
for item in row:
if item:
tmp.append((item,cspan))
cspan = 0
else:
cspan = cspan + 1
result.append(tmp)
subs = paragraph.getSubparagraphs()
# indent=paragraph.indent
return StructuredTextTable(result,text,subs,indent=paragraph.indent)
def doc_bullet(self, paragraph, expr = re.compile('\s*[-*o]\s+').match):
top=paragraph.getColorizableTexts()[0]
m=expr(top)
if not m:
return None
subs=paragraph.getSubparagraphs()
if top[-2:]=='::':
subs=[StructuredTextExample(subs)]
top=top[:-1]
return StructuredTextBullet(top[m.span()[1]:], subs,
indent=paragraph.indent,
bullet=top[:m.span()[1]]
)
def doc_numbered(
self, paragraph,
expr = re.compile('(\s*[%s]+\.)|(\s*[0-9]+\.)|(\s*[0-9]+\s+)' % letters).match):
# This is the old expression. It had a nasty habit
# of grabbing paragraphs that began with a single
# letter word even if there was no following period.
#expr = re.compile('\s*'
# '(([a-zA-Z]|[0-9]+|[ivxlcdmIVXLCDM]+)\.)*'
# '([a-zA-Z]|[0-9]+|[ivxlcdmIVXLCDM]+)\.?'
# '\s+').match):
top=paragraph.getColorizableTexts()[0]
m=expr(top)
if not m: return None
subs=paragraph.getSubparagraphs()
if top[-2:]=='::':
subs=[StructuredTextExample(subs)]
top=top[:-1]
return StructuredTextNumbered(top[m.span()[1]:], subs,
indent=paragraph.indent,
number=top[:m.span()[1]])
def doc_description(
self, paragraph,
delim = re.compile('\s+--\s+').search,
nb=re.compile(r'[^\000- ]').search,
):
top=paragraph.getColorizableTexts()[0]
d=delim(top)
if not d: return None
start, end = d.span()
title=top[:start]
if title.find('\n') >= 0: return None
if not nb(title): return None
d=top[start:end]
top=top[end:]
subs=paragraph.getSubparagraphs()
if top[-2:]=='::':
subs=[StructuredTextExample(subs)]
top=top[:-1]
return StructuredTextDescription(
title, top, subs,
indent=paragraph.indent,
delim=d)
def doc_header(self, paragraph,
expr = re.compile('[ %s0-9.:/,-_*<>\?\'\"]+' % letters).match
):
subs=paragraph.getSubparagraphs()
if not subs: return None
top=paragraph.getColorizableTexts()[0]
if not top.strip(): return None
if top[-2:]=='::':
subs=StructuredTextExample(subs)
if top.strip()=='::': return subs
return ST.StructuredTextParagraph(top[:-1],
[subs],
indent=paragraph.indent,
level=paragraph.level)
if top.find('\n') >= 0: return None
return StructuredTextSection(top, subs, indent=paragraph.indent, level=paragraph.level)
def doc_literal(
self, s,
expr=re.compile(
"(?:\s|^)'" # open
"([^ \t\n\r\f\v']|[^ \t\n\r\f\v'][^\n']*[^ \t\n\r\f\v'])" # contents
"'(?:\s|[,.;:!?]|$)" # close
).search):
r=expr(s)
if r:
start, end = r.span(1)
return (StructuredTextLiteral(s[start:end]), start-1, end+1)
else:
return None
def doc_emphasize(
self, s,
expr = re.compile('\s*\*([ \n%s0-9.:/;,\'\"\?\=\-\>\<\(\)]+)\*(?!\*|-)' % letters).search
):
r=expr(s)
if r:
start, end = r.span(1)
return (StructuredTextEmphasis(s[start:end]), start-1, end+1)
else:
return None
def doc_inner_link(self,
s,
expr1 = re.compile("\.\.\s*").search,
expr2 = re.compile("\[[%s0-9]+\]" % letters).search):
# make sure we dont grab a named link
if expr2(s) and expr1(s):
start1,end1 = expr1(s).span()
start2,end2 = expr2(s).span()
if end1 == start2:
# uh-oh, looks like a named link
return None
else:
# the .. is somewhere else, ignore it
return (StructuredTextInnerLink(s[start2+1,end2-1]),start2,end2)
return None
elif expr2(s) and not expr1(s):
start,end = expr2(s).span()
return (StructuredTextInnerLink(s[start+1:end-1]),start,end)
return None
def doc_named_link(self,
s,
expr=re.compile(r"(\.\.\s)(\[[%s0-9]+\])" % letters).search):
result = expr(s)
if result:
start,end = result.span(2)
str = s[start+1:end-1]
st,en = result.span()
return (StructuredTextNamedLink(str),st,en)
return None
def doc_underline(self,
s,
expr=re.compile("_([%s0-9\s\.,\?\/]+)_" % letters).search):
result = expr(s)
if result:
start,end = result.span(1)
st,e = result.span()
return (StructuredTextUnderline(s[start:end]),st,e)
else:
return None
def doc_strong(self,
s,
expr = re.compile('\s*\*\*([ \n%s0-9.:/;\-,!\?\'\"]+)\*\*' % letters).search
):
r=expr(s)
if r:
start, end = r.span(1)
return (StructuredTextStrong(s[start:end]), start-2, end+2)
else:
return None
def doc_href1(self, s,
expr=re.compile("(\"[ %s0-9\n\-\.\,\;\(\)\/\:\/\*\']+\")(:)([a-zA-Z0-9\@\.\,\?\!\/\:\;\-\#\~]+)([,]*\s*)" % letters).search
):
return self.doc_href(s, expr)
def doc_href2(self, s,
expr=re.compile('(\"[ %s0-9\n\-\.\:\;\(\)\/\*\']+\")([,]+\s+)([a-zA-Z0-9\@\.\,\?\!\/\:\;\-\#\~]+)(\s*)' % letters).search
):
return self.doc_href(s, expr)
def doc_href(self, s, expr, punctuation = re.compile("[\,\.\?\!\;]+").match):
r=expr(s)
if r:
# need to grab the href part and the
# beginning part
start,e = r.span(1)
name = s[start:e]
name = name.replace('"','',2)
#start = start + 1
st,end = r.span(3)
if punctuation(s[end-1:end]):
end = end -1
link = s[st:end]
#end = end - 1
# name is the href title, link is the target
# of the href
return (StructuredTextLink(name, href=link),
start, end)
#return (StructuredTextLink(s[start:end], href=s[start:end]),
# start, end)
else:
return None
=== Added File zopeproducts/bugtracker/browser/StructuredText/ClassicStructuredText.py ===
#! /usr/bin/env python -- # -*- python -*-
##############################################################################
#
# Copyright (c) 2001 Zope Corporation and Contributors. All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL). A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE
#
##############################################################################
'''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
preceding paragraph that has a lower level.
Special symbology is used to indicate special constructs:
- A single-line paragraph whose immediately succeeding paragraphs are lower
level is treated as a header.
- 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', 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 punctuation 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 punctuation to the right of the second '*')
is emphasized.
- Text surrounded by '**' characters (with white-space to the left of the
first '**' and whitespace or punctuation 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 '<a href="http://www.zope.org/">Zope</a> 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 '<a href="mailto:amos@digicool.com">mail me</a>.'
- 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 <a href="#12">[12]</a> 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 '<a name="12">[12]</a> "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::
<TABLE BORDER=1 CELLPADDING=2>
<TR>
<TD ALIGN=CENTER COLSPAN=2> <strong>Ingredients</strong> </TD>
</TR>
<TR>
<TD ALIGN=CENTER COLSPAN=1> <em>Name</em> </TD>
<TD ALIGN=CENTER COLSPAN=1> <em>Amount</em> </TD>
</TR>
<TR>
<TD ALIGN=CENTER COLSPAN=1>Spam</TD>
<TD ALIGN=CENTER COLSPAN=1>10</TD>
</TR>
<TR>
<TD ALIGN=CENTER COLSPAN=1>Eggs</TD>
<TD ALIGN=CENTER COLSPAN=1>3</TD>
</TR>
</TABLE>
'''
import ts_regex
import string, re
def untabify(aString,
indent_tab=ts_regex.compile('\(\n\|^\)\( *\)\t').search_group,
):
'''\
Convert indentation tabs to spaces.
'''
result=''
rest=aString
while 1:
ts_results = indent_tab(rest, (1,2))
if ts_results:
start, grps = ts_results
lnl=len(grps[0])
indent=len(grps[1])
result=result+rest[:start]
rest="\n%s%s" % (' ' * ((indent/8+1)*8),
rest[start+indent+1+lnl:])
else:
return result+rest
def indent(aString, indent=2):
"""Indent a string the given number of spaces"""
r=untabify(aString).split('\n')
if not r: return ''
if not r[-1]: del r[-1]
tab=' '*indent
return "%s%s\n" % (tab,('\n'+tab).join(r))
def reindent(aString, indent=2, already_untabified=0):
"reindent a block of text, so that the minimum indent is as given"
if not already_untabified: aString=untabify(aString)
l=indent_level(aString)[0]
if indent==l: return aString
r=[]
append=r.append
if indent > l:
tab=' ' * (indent-l)
for s in aString.split('\n'): append(tab+s)
else:
l=l-indent
for s in aString.split('\n'): append(s[l:])
return '\n'.join(r)
def indent_level(aString,
indent_space=ts_regex.compile('\n\( *\)').search_group,
):
'''\
Find the minimum indentation for a string, not counting blank lines.
'''
start=0
text='\n'+aString
indent=l=len(text)
while 1:
ts_results = indent_space(text, (1,2), start)
if ts_results:
start, grps = ts_results
i=len(grps[0])
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
class Table:
CELL=' <TD ALIGN=CENTER COLSPAN=%i>%s</TD>\n'
ROW=' <TR>\n%s </TR>\n'
TABLE='\n<TABLE BORDER=1 CELLPADDING=2>\n%s</TABLE>'
def create(self,aPar,
td_reg=re.compile(r'[ \t\n]*\|\|([^\0|]*)')
):
'''parses a table and returns nested list representing the
table'''
self.table=[]
text=filter(None,aPar.split('\n'))
for line in text:
row=[]
while 1:
mo = td_reg.match(line)
if not mo: return 0
pos = mo.end(1)
row.append(mo.group(1))
if pos==len(line):break
line=line[pos:]
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)
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=ts_regex.compile('\(\r?\n *\)+\r?\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.
'''
pat = ' \"([%s0-9-_,./?=@~&]*)\":' % string.letters+ \
'([-:%s0-9_,./?=@#~&]*?)' % string.letters + \
'([.:?;] )'
p_reg = re.compile(pat,re.M)
aStructuredString = p_reg.sub(r'<a href="\2">\1</a>\3 ' , aStructuredString)
pat = ' \"([%s0-9-_,./?=@~&]*)\", ' % string.letters+ \
'([-:%s0-9_,./?=@#~&]*?)' % string.letters + \
'([.:?;] )'
p_reg = re.compile(pat,re.M)
aStructuredString = p_reg.sub(r'<a href="\2">\1</a>\3 ' , aStructuredString)
protoless = aStructuredString.find('<a href=":')
if protoless != -1:
aStructuredString = re.sub('<a href=":', '<a href="',
aStructuredString)
self.level=level
paragraphs=ts_regex.split(untabify(aStructuredString),
paragraph_divider)
paragraphs=map(indent_level,paragraphs)
self.structure=structure(paragraphs)
def __str__(self):
return str(self.structure)
ctag_prefix=r'([\x00- \\(]|^)'
ctag_suffix=r'([\x00- ,.:;!?\\)]|$)'
ctag_middle=r'[%s]([^\x00- %s][^%s]*[^\x00- %s]|[^%s])[%s]'
ctag_middl2=r'[%s][%s]([^\x00- %s][^%s]*[^\x00- %s]|[^%s])[%s][%s]'
def ctag(s,
em=re.compile(
ctag_prefix+(ctag_middle % (("*",)*6) )+ctag_suffix),
strong=re.compile(
ctag_prefix+(ctag_middl2 % (("*",)*8))+ctag_suffix),
under=re.compile(
ctag_prefix+(ctag_middle % (("_",)*6) )+ctag_suffix),
code=re.compile(
ctag_prefix+(ctag_middle % (("\'",)*6))+ctag_suffix),
):
if s is None: s=''
s=strong.sub(r'\1<strong>\2</strong>\3',s)
s=under.sub( r'\1<u>\2</u>\3',s)
s=code.sub( r'\1<code>\2</code>\3',s)
s=em.sub( r'\1<em>\2</em>\3',s)
return s
class HTML(StructuredText):
'''\
An HTML structured text formatter.
'''\
def __str__(self,
extra_dl=re.compile("</dl>\n<dl>"),
extra_ul=re.compile("</ul>\n<ul>"),
extra_ol=re.compile("</ol>\n<ol>"),
):
'''\
Return an HTML string representation of the structured text data.
'''
s=self._str(self.structure,self.level)
s=extra_dl.sub('\n',s)
s=extra_ul.sub('\n',s)
s=extra_ol.sub('\n',s)
return s
def ul(self, before, p, after):
if p: p="<p>%s</p>" % ctag(p).strip()
return ('%s<ul><li>%s\n%s\n</li></ul>\n'
% (before,p,after))
def ol(self, before, p, after):
if p: p="<p>%s</p>" % ctag(p).strip()
return ('%s<ol><li>%s\n%s\n</li></ol>\n'
% (before,p,after))
def dl(self, before, t, d, after):
return ('%s<dl><dt>%s</dt><dd><p>%s</p>\n%s\n</dd></dl>\n'
% (before,ctag(t),ctag(d),after))
def head(self, before, t, level, d):
if level > 0 and level < 6:
return ('%s<h%d>%s</h%d>\n%s\n'
% (before,level,ctag(t).strip(),level,d))
t="<p><strong>%s</strong></p>" % ctag(t).strip()
return ('%s<dl><dt>%s\n</dt><dd>%s\n</dd></dl>\n'
% (before,t,d))
def normal(self,before,p,after):
return '%s<p>%s</p>\n%s\n' % (before,ctag(p),after)
def pre(self,structure,tagged=0):
if not structure: return ''
if tagged:
r=''
else:
r='<PRE>\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+'</PRE>\n'
return r
def table(self,before,table,after):
return '%s<p>%s</p>\n%s\n' % (before,ctag(table),after)
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]*\(\([0-9]+\|[%s]+\)[.)]\)+[ \t\n]+\([^\0]*\|$\)' % string.letters
).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:
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
def html_quote(v,
character_entities=(
(re.compile('&'), '&'),
(re.compile("<"), '<' ),
(re.compile(">"), '>' ),
(re.compile('"'), '"')
)): #"
text=str(v)
for re,name in character_entities:
text=re.sub(name,text)
return text
def html_with_references(text, level=1):
text = re.sub(
r'[\0\n]\.\. \[([0-9_%s-]+)\]' % string.letters,
r'\n <a name="\1">[\1]</a>',
text)
text = re.sub(
r'([\x00- ,])\[(?P<ref>[0-9_%s-]+)\]([\x00- ,.:])' % string.letters,
r'\1<a href="#\2">[\2]</a>\3',
text)
text = re.sub(
r'([\0- ,])\[([^]]+)\.html\]([\0- ,.:])',
r'\1<a href="\2.html">[\2]</a>\3',
text)
return HTML(text,level=level)
def main():
import sys, getopt
opts,args=getopt.getopt(sys.argv[1:],'twl')
if args:
[infile]=args
s=open(infile,'r').read()
else:
s=sys.stdin.read()
if opts:
if filter(lambda o: o[0]=='-w', opts):
print 'Content-Type: text/html\n'
if filter(lambda o: o[0]=='-l', opts):
import locale
locale.setlocale(locale.LC_ALL,"")
if s[:2]=='#!':
s=re.sub('^#![^\n]+','',s)
mo = re.compile('([\0-\n]*\n)').match(s)
if mo is not None:
s = s[len(mo.group(0)) :]
s=str(html_with_references(s))
if s[:4]=='<h1>':
t=s[4: s.find('</h1>')]
s='''<html><head><title>%s</title>
</head><body>
%s
</body></html>
''' % (t,s)
print s
else:
print html_with_references(s)
if __name__=="__main__": main()
=== Added File zopeproducts/bugtracker/browser/StructuredText/DocBookClass.py ===
##############################################################################
#
# Copyright (c) 2001 Zope Corporation and Contributors. All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL). A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE
#
##############################################################################
class DocBookClass:
element_types={
'#text': '_text',
'StructuredTextDocument': 'document',
'StructuredTextParagraph': 'paragraph',
'StructuredTextExample': 'example',
'StructuredTextBullet': 'bullet',
'StructuredTextNumbered': 'numbered',
'StructuredTextDescription': 'description',
'StructuredTextDescriptionTitle': 'descriptionTitle',
'StructuredTextDescriptionBody': 'descriptionBody',
'StructuredTextSection': 'section',
'StructuredTextSectionTitle': 'sectionTitle',
'StructuredTextLiteral': 'literal',
'StructuredTextEmphasis': 'emphasis',
'StructuredTextStrong': 'strong',
'StructuredTextLink': 'link',
'StructuredTextXref': 'xref',
'StructuredTextSGML': 'sgml',
}
def dispatch(self, doc, level, output):
getattr(self, self.element_types[doc.getNodeName()])(doc, level, output)
def __call__(self, doc, level=1):
r=[]
self.dispatch(doc, level-1, r.append)
return ''.join(r)
def _text(self, doc, level, output):
if doc.getNodeName() == 'StructuredTextLiteral':
output(doc.getNodeValue())
else:
output(doc.getNodeValue().lstrip())
def document(self, doc, level, output):
output('<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook V4.1//EN">\n')
output('<book>\n')
children=doc.getChildNodes()
if (children and
children[0].getNodeName() == 'StructuredTextSection'):
output('<title>%s</title>' % children[0].getChildNodes()[0].getNodeValue())
for c in children:
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</book>\n')
def section(self, doc, level, output):
output('\n<section>\n')
children=doc.getChildNodes()
for c in children:
getattr(self, self.element_types[c.getNodeName()])(c, level+1, output)
output('\n</section>\n')
def sectionTitle(self, doc, level, output):
output('<title>')
for c in doc.getChildNodes():
try:
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
except:
print "failed", c.getNodeName(), c
output('</title>\n')
def description(self, doc, level, output):
p=doc.getPreviousSibling()
if p is None or p.getNodeName() is not doc.getNodeName():
output('<variablelist>\n')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
n=doc.getNextSibling()
if n is None or n.getNodeName() is not doc.getNodeName():
output('</variablelist>\n')
def descriptionTitle(self, doc, level, output):
output('<varlistentry><term>\n')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</term>\n')
def descriptionBody(self, doc, level, output):
output('<listitem><para>\n')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</para></listitem>\n')
output('</varlistentry>\n')
def bullet(self, doc, level, output):
p=doc.getPreviousSibling()
if p is None or p.getNodeName() is not doc.getNodeName():
output('<itemizedlist>\n')
output('<listitem><para>\n')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
n=doc.getNextSibling()
output('</para></listitem>\n')
if n is None or n.getNodeName() is not doc.getNodeName():
output('</itemizedlist>\n')
def numbered(self, doc, level, output):
p=doc.getPreviousSibling()
if p is None or p.getNodeName() is not doc.getNodeName():
output('<orderedlist>\n')
output('<listitem><para>\n')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
n=doc.getNextSibling()
output('</para></listitem>\n')
if n is None or n.getNodeName() is not doc.getNodeName():
output('</orderedlist>\n')
def example(self, doc, level, output):
i=0
for c in doc.getChildNodes():
if i==0:
output('<programlisting>\n<![CDATA[\n')
##
## eek. A ']]>' in your body will break this...
##
output(prestrip(c.getNodeValue()))
output('\n]]></programlisting>\n')
else:
getattr(self, self.element_types[c.getNodeName()])(
c, level, output)
def paragraph(self, doc, level, output):
output('<para>\n\n')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(
c, level, output)
output('</para>\n\n')
def link(self, doc, level, output):
output('<ulink url="%s">' % doc.href)
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</ulink>')
def emphasis(self, doc, level, output):
output('<emphasis>')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</emphasis> ')
def literal(self, doc, level, output):
output('<literal>')
for c in doc.getChildNodes():
output(c.getNodeValue())
output('</literal>')
def strong(self, doc, level, output):
output('<emphasis>')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</emphasis>')
def xref(self, doc, level, output):
output('<xref linkend="%s"/>' % doc.getNodeValue())
def sgml(self, doc, level, output):
output(doc.getNodeValue())
def prestrip(v):
v=v.replace( '\r\n', '\n')
v=v.replace( '\r', '\n')
v=v.replace( '\t', ' ')
lines=v.split('\n')
indent=len(lines[0])
for line in lines:
if not len(line): continue
i=len(line)-len(line.lstrip())
if i < indent:
indent=i
nlines=[]
for line in lines:
nlines.append(line[indent:])
return '\n'.join(nlines, '\n')
class DocBookChapter(DocBookClass):
def document(self, doc, level, output):
output('<chapter>\n')
children=doc.getChildNodes()
if (children and
children[0].getNodeName() == 'StructuredTextSection'):
output('<title>%s</title>' % children[0].getChildNodes()[0].getNodeValue())
for c in children[0].getChildNodes()[1:]:
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</chapter>\n')
ets = DocBookClass.element_types
ets.update({'StructuredTextImage': 'image'})
class DocBookChapterWithFigures(DocBookChapter):
element_types = ets
def image(self, doc, level, output):
if hasattr(doc, 'key'):
output('<figure id="%s"><title>%s</title>\n' % (doc.key, doc.getNodeValue()) )
else:
output('<figure><title>%s</title>\n' % doc.getNodeValue())
## for c in doc.getChildNodes():
## getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('<graphic fileref="%s"></graphic>\n</figure>\n' % doc.href)
class DocBookArticle(DocBookClass):
def document(self, doc, level, output):
output('<!DOCTYPE article PUBLIC "-//OASIS//DTD DocBook V4.1//EN">\n')
output('<article>\n')
children=doc.getChildNodes()
if (children and
children[0].getNodeName() == 'StructuredTextSection'):
output('<articleinfo>\n<title>%s</title>\n</articleinfo>\n' %
children[0].getChildNodes()[0].getNodeValue())
for c in children:
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</article>\n')
class DocBookBook:
def __init__(self, title=''):
self.title = title
self.chapters = []
def addChapter(self, chapter):
self.chapters.append(chapter)
def read(self):
out = '<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook V4.1//EN">\n<book>\n'
out = out + '<title>%s</title>\n' % self.title
for chapter in self.chapters:
out = out + chapter + '\n</book>\n'
return out
def __str__(self):
return self.read()
=== Added File zopeproducts/bugtracker/browser/StructuredText/DocumentClass.py ===
##############################################################################
#
# Copyright (c) 2001 Zope Corporation and Contributors. All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL). A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE
#
##############################################################################
import re, ST, STDOM
from STletters import letters, digits, literal_punc, under_punc,\
strongem_punc, phrase_delimiters,dbl_quoted_punc
from types import StringType, UnicodeType, ListType
StringTypes = (StringType, UnicodeType)
def flatten(obj, append):
if obj.getNodeType()==STDOM.TEXT_NODE:
append(obj.getNodeValue())
else:
for child in obj.getChildNodes():
flatten(child, append)
class StructuredTextExample(ST.StructuredTextParagraph):
"""Represents a section of document with literal text, as for examples"""
def __init__(self, subs, **kw):
t=[]
a=t.append
for s in subs:
flatten(s, a)
ST.StructuredTextParagraph.__init__(self, '\n\n'.join(t), (), **kw)
def getColorizableTexts(self): return ()
def setColorizableTexts(self, src): pass # never color examples
class StructuredTextBullet(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
class StructuredTextNumbered(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
class StructuredTextDescriptionTitle(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
class StructuredTextDescriptionBody(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
class StructuredTextDescription(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
def __init__(self, title, src, subs, **kw):
ST.StructuredTextParagraph.__init__(self, src, subs, **kw)
self._title=title
def getColorizableTexts(self): return self._title, self._src
def setColorizableTexts(self, src): self._title, self._src = src
def getChildren(self):
return (StructuredTextDescriptionTitle(self._title),
StructuredTextDescriptionBody(self._src, self._subs))
class StructuredTextSectionTitle(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
class StructuredTextSection(ST.StructuredTextParagraph):
"""Represents a section of a document with a title and a body"""
def __init__(self, src, subs=None, **kw):
ST.StructuredTextParagraph.__init__(
self, StructuredTextSectionTitle(src), subs, **kw)
def getColorizableTexts(self):
return self._src.getColorizableTexts()
def setColorizableTexts(self,src):
self._src.setColorizableTexts(src)
# a StructuredTextTable holds StructuredTextRows
class StructuredTextTable(ST.StructuredTextParagraph):
"""
rows is a list of lists containing tuples, which
represent the columns/cells in each rows.
EX
rows = [[('row 1:column1',1)],[('row2:column1',1)]]
"""
def __init__(self, rows, src, subs, **kw):
ST.StructuredTextParagraph.__init__(self, subs, **kw)
self._rows = []
for row in rows:
if row:
self._rows.append(StructuredTextRow(row,kw))
def getRows(self):
return [self._rows]
def _getRows(self):
return self.getRows()
def getColumns(self):
result = []
for row in self._rows:
result.append(row.getColumns())
return result
def _getColumns(self):
return self.getColumns()
def setColumns(self,columns):
for index in range(len(self._rows)):
self._rows[index].setColumns(columns[index])
def _setColumns(self,columns):
return self.setColumns(columns)
def getColorizableTexts(self):
"""
return a tuple where each item is a column/cell's
contents. The tuple, result, will be of this format.
("r1 col1", "r1=col2", "r2 col1", "r2 col2")
"""
result = []
for row in self._rows:
for column in row.getColumns()[0]:
result.append(column.getColorizableTexts()[0])
return result
def setColorizableTexts(self,texts):
"""
texts is going to a tuple where each item is the
result of being mapped to the colortext function.
Need to insert the results appropriately into the
individual columns/cells
"""
for row_index in range(len(self._rows)):
for column_index in range(len(self._rows[row_index]._columns)):
self._rows[row_index]._columns[column_index].setColorizableTexts((texts[0],))
texts = texts[1:]
def _getColorizableTexts(self):
return self.getColorizableTexts()
def _setColorizableTexts(self, texts):
return self.setColorizableTexts(texts)
# StructuredTextRow holds StructuredTextColumns
class StructuredTextRow(ST.StructuredTextParagraph):
def __init__(self,row,kw):
"""
row is a list of tuples, where each tuple is
the raw text for a cell/column and the span
of that cell/column.
EX
[('this is column one',1), ('this is column two',1)]
"""
ST.StructuredTextParagraph.__init__(self, [], **kw)
self._columns = []
for column in row:
self._columns.append(StructuredTextColumn(column[0],
column[1],
column[2],
column[3],
column[4],
kw))
def getColumns(self):
return [self._columns]
def _getColumns(self):
return [self._columns]
def setColumns(self,columns):
self._columns = columns
def _setColumns(self,columns):
return self.setColumns(columns)
# this holds the text of a table cell
class StructuredTextColumn(ST.StructuredTextParagraph):
"""
StructuredTextColumn is a cell/column in a table.
A cell can hold multiple paragraphs. The cell
is either classified as a StructuredTextTableHeader
or StructuredTextTableData.
"""
def __init__(self,text,span,align,valign,typ,kw):
ST.StructuredTextParagraph.__init__(self, text, [], **kw)
self._span = span
self._align = align
self._valign = valign
self._type = typ
def getSpan(self):
return self._span
def _getSpan(self):
return self._span
def getAlign(self):
return self._align
def _getAlign(self):
return self.getAlign()
def getValign(self):
return self._valign
def _getValign(self):
return self.getValign()
def getType(self):
return self._type
def _getType(self):
return self.getType()
class StructuredTextTableHeader(ST.StructuredTextParagraph): pass
class StructuredTextTableData(ST.StructuredTextParagraph): pass
class StructuredTextMarkup(STDOM.Element):
def __init__(self, v, **kw):
self._value=v
self._attributes=kw.keys()
for k, v in kw.items(): setattr(self, k, v)
def getChildren(self):
v=self._value
if not isinstance(v, ListType): v=[v]
return v
def getColorizableTexts(self): return self._value,
def setColorizableTexts(self, v): self._value=v[0]
def __repr__(self):
return '%s(%s)' % (self.__class__.__name__, `self._value`)
class StructuredTextLiteral(StructuredTextMarkup):
def getColorizableTexts(self): return ()
def setColorizableTexts(self, v): pass
class StructuredTextEmphasis(StructuredTextMarkup): pass
class StructuredTextStrong(StructuredTextMarkup): pass
class StructuredTextInnerLink(StructuredTextMarkup): pass
class StructuredTextNamedLink(StructuredTextMarkup): pass
class StructuredTextUnderline(StructuredTextMarkup): pass
class StructuredTextSGML(StructuredTextMarkup): pass
class StructuredTextLink(StructuredTextMarkup): pass
class StructuredTextXref(StructuredTextMarkup): pass
class DocumentClass:
"""
Class instance calls [ex.=> x()] require a structured text
structure. Doc will then parse each paragraph in the structure
and will find the special structures within each paragraph.
Each special structure will be stored as an instance. Special
structures within another special structure are stored within
the 'top' structure
EX : '-underline this-' => would be turned into an underline
instance. '-underline **this**' would be stored as an underline
instance with a strong instance stored in its string
"""
paragraph_types = [
'doc_bullet',
'doc_numbered',
'doc_description',
'doc_header',
'doc_table',
]
#'doc_inner_link',
#'doc_named_link',
#'doc_underline'
text_types = [
'doc_literal',
'doc_sgml',
'doc_inner_link',
'doc_named_link',
'doc_href1',
'doc_href2',
'doc_strong',
'doc_emphasize',
'doc_underline',
'doc_sgml',
'doc_xref',
]
def __call__(self, doc):
if type(doc) in StringTypes:
doc=ST.StructuredText(doc)
doc.setSubparagraphs(self.color_paragraphs(
doc.getSubparagraphs()))
else:
doc=ST.StructuredTextDocument(self.color_paragraphs(
doc.getSubparagraphs()))
return doc
def parse(self, raw_string, text_type,
type=type, sts=StringTypes, lt=type([])):
"""
Parse accepts a raw_string, an expr to test the raw_string,
and the raw_string's subparagraphs.
Parse will continue to search through raw_string until
all instances of expr in raw_string are found.
If no instances of expr are found, raw_string is returned.
Otherwise a list of substrings and instances is returned
"""
tmp = [] # the list to be returned if raw_string is split
append=tmp.append
if type(text_type) in sts: text_type=getattr(self, text_type)
while 1:
t = text_type(raw_string)
if not t: break
#an instance of expr was found
t, start, end = t
if start: append(raw_string[0:start])
tt=type(t)
if tt in sts:
# if we get a string back, add it to text to be parsed
raw_string = t+raw_string[end:len(raw_string)]
else:
if tt is lt:
# is we get a list, append it's elements
tmp[len(tmp):]=t
else:
# normal case, an object
append(t)
raw_string = raw_string[end:len(raw_string)]
if not tmp: return raw_string # nothing found
if raw_string: append(raw_string)
elif len(tmp)==1: return tmp[0]
return tmp
def color_text(self, str, types=None):
"""Search the paragraph for each special structure
"""
if types is None: types=self.text_types
for text_type in types:
if type(str) in StringTypes:
str = self.parse(str, text_type)
elif type(str) is ListType:
r=[]; a=r.append
for s in str:
if type(s) in StringTypes:
s=self.parse(s, text_type)
if type(s) is ListType: r[len(r):]=s
else: a(s)
else:
s.setColorizableTexts(
map(self.color_text,
s.getColorizableTexts()
))
a(s)
str=r
else:
r=[]; a=r.append; color=self.color_text
for s in str.getColorizableTexts():
color(s, (text_type,))
a(s)
str.setColorizableTexts(r)
return str
def color_paragraphs(self, raw_paragraphs,
type=type, sequence_types=(type([]), type(())),
sts=StringTypes):
result=[]
for paragraph in raw_paragraphs:
if paragraph.getNodeName() != 'StructuredTextParagraph':
result.append(paragraph)
continue
for pt in self.paragraph_types:
if type(pt) in sts:
# grab the corresponding function
pt=getattr(self, pt)
# evaluate the paragraph
r=pt(paragraph)
if r:
if type(r) not in sequence_types:
r=r,
new_paragraphs=r
for paragraph in new_paragraphs:
subs = self.color_paragraphs(paragraph.getSubparagraphs())
paragraph.setSubparagraphs(subs)
break
else:
# copy, retain attributes
kw = {}
atts = getattr(paragraph, '_attributes', [])
for att in atts: kw[att] = getattr(paragraph, att)
subs = self.color_paragraphs(paragraph.getSubparagraphs())
new_paragraphs=ST.StructuredTextParagraph(
paragraph. getColorizableTexts()[0], subs, **kw),
# color the inline StructuredText types
# for each StructuredTextParagraph
for paragraph in new_paragraphs:
if paragraph.getNodeName() is "StructuredTextTable":
# cells = paragraph.getColumns()
text = paragraph.getColorizableTexts()
text = map(ST.StructuredText,text)
text = map(self.__call__,text)
for t in range(len(text)):
text[t] = text[t].getSubparagraphs()
paragraph.setColorizableTexts(text)
paragraph.setColorizableTexts(
map(self.color_text,
paragraph.getColorizableTexts()
))
result.append(paragraph)
return result
def doc_table(self, paragraph, expr = re.compile(r'\s*\|[-]+\|').match):
text = paragraph.getColorizableTexts()[0]
m = expr(text)
subs = paragraph.getSubparagraphs()
if not (m):
return None
rows = []
spans = []
ROWS = []
COLS = []
indexes = []
ignore = []
TDdivider = re.compile("[\-]+").match
THdivider = re.compile("[\=]+").match
col = re.compile('\|').search
innertable = re.compile('\|([-]+|[=]+)\|').search
text = text.strip()
rows = text.split('\n')
foo = ""
for row in range(len(rows)):
rows[row] = rows[row].strip()
# have indexes store if a row is a divider
# or a cell part
for index in range(len(rows)):
tmpstr = rows[index][1:len(rows[index])-1]
if TDdivider(tmpstr):
indexes.append("TDdivider")
elif THdivider(tmpstr):
indexes.append("THdivider")
else:
indexes.append("cell")
for index in range(len(indexes)):
if indexes[index] is "TDdivider" or indexes[index] is "THdivider":
ignore = [] # reset ignore
#continue # skip dividers
tmp = rows[index].strip() # clean the row up
tmp = tmp[1:len(tmp)-1] # remove leading + trailing |
offset = 0
# find the start and end of inner
# tables. ignore everything between
if innertable(tmp):
tmpstr = tmp.strip()
while innertable(tmpstr):
start,end = innertable(tmpstr).span()
if not (start,end-1) in ignore:
ignore.append((start,end-1))
tmpstr = " " + tmpstr[end:]
# find the location of column dividers
# NOTE: |'s in inner tables do not count
# as column dividers
if col(tmp):
while col(tmp):
bar = 1 # true if start is not in ignore
start,end = col(tmp).span()
if not start+offset in spans:
for s,e in ignore:
if start+offset >= s or start+offset <= e:
bar = None
break
if bar: # start is clean
spans.append(start+offset)
if not bar:
foo = foo + tmp[:end]
tmp = tmp[end:]
offset = offset + end
else:
COLS.append((foo + tmp[0:start],start+offset))
foo = ""
tmp = " " + tmp[end:]
offset = offset + start
if not offset+len(tmp) in spans:
spans.append(offset+len(tmp))
COLS.append((foo + tmp,offset+len(tmp)))
foo = ""
ROWS.append(COLS)
COLS = []
spans.sort()
ROWS = ROWS[1:len(ROWS)]
# find each column span
cols = []
tmp = []
for row in ROWS:
for c in row:
tmp.append(c[1])
cols.append(tmp)
tmp = []
cur = 1
tmp = []
C = []
for col in cols:
for span in spans:
if not span in col:
cur = cur + 1
else:
tmp.append(cur)
cur = 1
C.append(tmp)
tmp = []
for index in range(len(C)):
for i in range(len(C[index])):
ROWS[index][i] = (ROWS[index][i][0],C[index][i])
rows = ROWS
# label things as either TableData or
# Table header
TD = []
TH = []
all = []
for index in range(len(indexes)):
if indexes[index] is "TDdivider":
TD.append(index)
all.append(index)
if indexes[index] is "THdivider":
TH.append(index)
all.append(index)
TD = TD[1:]
dividers = all[1:]
#print "TD => ", TD
#print "TH => ", TH
#print "all => ", all, "\n"
for div in dividers:
if div in TD:
index = all.index(div)
for rowindex in range(all[index-1],all[index]):
for i in range(len(rows[rowindex])):
rows[rowindex][i] = (rows[rowindex][i][0],
rows[rowindex][i][1],
"td")
else:
index = all.index(div)
for rowindex in range(all[index-1],all[index]):
for i in range(len(rows[rowindex])):
rows[rowindex][i] = (rows[rowindex][i][0],
rows[rowindex][i][1],
"th")
# now munge the multi-line cells together
# as paragraphs
ROWS = []
COLS = []
for row in rows:
for index in range(len(row)):
if not COLS:
COLS = range(len(row))
for i in range(len(COLS)):
COLS[i] = ["",1,""]
if TDdivider(row[index][0]) or THdivider(row[index][0]):
ROWS.append(COLS)
COLS = []
else:
COLS[index][0] = COLS[index][0] + (row[index][0]) + "\n"
COLS[index][1] = row[index][1]
COLS[index][2] = row[index][2]
# now that each cell has been munged together,
# determine the cell's alignment.
# Default is to center. Also determine the cell's
# vertical alignment, top, middle, bottom. Default is
# to middle
rows = []
cols = []
for row in ROWS:
for index in range(len(row)):
topindent = 0
bottomindent = 0
leftindent = 0
rightindent = 0
left = []
right = []
text = row[index][0]
text = text.split('\n')
text = text[:len(text)-1]
align = ""
valign = ""
for t in text:
t = t.strip()
if not t:
topindent = topindent + 1
else:
break
text.reverse()
for t in text:
t = t.strip()
if not t:
bottomindent = bottomindent + 1
else:
break
text.reverse()
tmp = '\n'.join(text[topindent:len(text)-bottomindent])
pars = re.compile("\n\s*\n").split(tmp)
for par in pars:
if index > 0:
par = par[1:]
par = par.split(' ')
for p in par:
if not p:
leftindent = leftindent+1
else:
break
left.append(leftindent)
leftindent = 0
par.reverse()
for p in par:
if not p:
rightindent = rightindent + 1
else:
break
right.append(rightindent)
rightindent = 0
left.sort()
right.sort()
if topindent == bottomindent:
valign="middle"
elif topindent < 1:
valign="top"
elif bottomindent < 1:
valign="bottom"
else:
valign="middle"
if left[0] < 1:
align = "left"
elif right[0] < 1:
align = "right"
elif left[0] > 1 and right[0] > 1:
align="center"
else:
align="left"
cols.append((row[index][0],row[index][1],align,valign,row[index][2]))
rows.append(cols)
cols = []
return StructuredTextTable(rows,text,subs,indent=paragraph.indent)
def doc_bullet(self, paragraph, expr = re.compile(r'\s*[-*o]\s+').match):
top=paragraph.getColorizableTexts()[0]
m=expr(top)
if not m:
return None
subs=paragraph.getSubparagraphs()
if top[-2:]=='::':
subs=[StructuredTextExample(subs)]
top=top[:-1]
return StructuredTextBullet(top[m.span()[1]:], subs,
indent=paragraph.indent,
bullet=top[:m.span()[1]]
)
def doc_numbered(
self, paragraph,
expr = re.compile(r'(\s*[%s]\.)|(\s*[0-9]+\.)|(\s*[0-9]+\s+)' % letters).match):
# This is the old expression. It had a nasty habit
# of grabbing paragraphs that began with a single
# letter word even if there was no following period.
#expr = re.compile('\s*'
# '(([a-zA-Z]|[0-9]+|[ivxlcdmIVXLCDM]+)\.)*'
# '([a-zA-Z]|[0-9]+|[ivxlcdmIVXLCDM]+)\.?'
# '\s+').match):
top=paragraph.getColorizableTexts()[0]
m=expr(top)
if not m: return None
subs=paragraph.getSubparagraphs()
if top[-2:]=='::':
subs=[StructuredTextExample(subs)]
top=top[:-1]
return StructuredTextNumbered(top[m.span()[1]:], subs,
indent=paragraph.indent,
number=top[:m.span()[1]])
def doc_description(
self, paragraph,
delim = re.compile(r'\s+--\s+').search,
nb=re.compile(r'[^\000- ]').search,
):
top=paragraph.getColorizableTexts()[0]
d=delim(top)
if not d: return None
start, end = d.span()
title=top[:start]
if title.find('\n') >= 0: return None
if not nb(title): return None
d=top[start:end]
top=top[end:]
subs=paragraph.getSubparagraphs()
if top[-2:]=='::':
subs=[StructuredTextExample(subs)]
top=top[:-1]
return StructuredTextDescription(
title, top, subs,
indent=paragraph.indent,
delim=d)
def doc_header(self, paragraph):
subs=paragraph.getSubparagraphs()
if not subs: return None
top=paragraph.getColorizableTexts()[0]
if not top.strip(): return None
if top[-2:]=='::':
subs=StructuredTextExample(subs)
if top.strip()=='::': return subs
# copy attrs when returning a paragraph
kw = {}
atts = getattr(paragraph, '_attributes', [])
for att in atts: kw[att] = getattr(paragraph, att)
return ST.StructuredTextParagraph(top[:-1], [subs], **kw)
if top.find('\n') >= 0: return None
return StructuredTextSection(top, subs, indent=paragraph.indent)
def doc_literal(
self, s,
expr = re.compile(r"(\W+|^)'([%s%s%s\s]+)'([%s]+|$)" % (letters, digits, literal_punc, phrase_delimiters)).search,):
# old expr... failed to cross newlines.
# expr=re.compile(
# r"(?:\s|^)'" # open
# r"([^ \t\n\r\f\v']|[^ \t\n\r\f\v'][^\n\r']*[^ \t\n\r\f\v'])" # contents
# r"'(?:\s|[,.;:!?]|$)" # close
# ).search):
r=expr(s) #or expr2(s)
if r:
start, end = r.span(2)
return (StructuredTextLiteral(s[start:end]), start-1, end+1)
else:
return None
def doc_emphasize(
self, s,
expr = re.compile(r'\*([%s%s%s\s]+?)\*' % (letters, digits, strongem_punc)).search
#expr = re.compile(r'\s*\*([ \n\r%s0-9.:/;,\'\"\?\-\_\/\=\-\>\<\(\)]+)\*(?!\*|-)' % letters).search # old expr, inconsistent punctuation
):
r=expr(s)
if r:
start, end = r.span(1)
return (StructuredTextEmphasis(s[start:end]), start-1, end+1)
else:
return None
def doc_inner_link(self,
s,
expr1 = re.compile(r"\.\.\s*").search,
expr2 = re.compile(r"\[[%s%s]+\]" % (letters, digits) ).search):
# make sure we dont grab a named link
if expr2(s) and expr1(s):
start1,end1 = expr1(s).span()
start2,end2 = expr2(s).span()
if end1 == start2:
# uh-oh, looks like a named link
return None
else:
# the .. is somewhere else, ignore it
return (StructuredTextInnerLink(s[start2+1:end2-1]),start2,end2)
return None
elif expr2(s) and not expr1(s):
start,end = expr2(s).span()
return (StructuredTextInnerLink(s[start+1:end-1]),start,end)
return None
def doc_named_link(self,
s,
expr=re.compile(r"(\.\.\s)(\[[%s0-9]+\])" % letters).search):
result = expr(s)
if result:
start,end = result.span(2)
str = s[start+1:end-1]
st,en = result.span()
return (StructuredTextNamedLink(str),st,en)
return None
def doc_underline(self,
s,
expr=re.compile(r'_([%s%s%s\s]+)_([\s%s]|$)' % (letters, digits, under_punc,phrase_delimiters)).search):
result = expr(s)
if result:
if result.group(1)[:1] == '_':
return None # no double unders
start,end = result.span(1)
st,e = result.span()
return (StructuredTextUnderline(s[start:end]),st,e-len(result.group(2)))
else:
return None
def doc_strong(self,
s,
expr = re.compile(r'\*\*([%s%s%s\s]+?)\*\*' % (letters, digits, strongem_punc)).search
#expr = re.compile(r'\s*\*\*([ \n\r%s0-9.:/;,\'\"\?\-\_\/\=\-\>\<\(\)]+)\*\*(?!\*|-)' % letters).search, # old expr, inconsistent punc, failed to cross newlines.
):
r=expr(s)
if r:
start, end = r.span(1)
return (StructuredTextStrong(s[start:end]), start-2, end+2)
else:
return None
## Some constants to make the doc_href() regex easier to read.
_DQUOTEDTEXT = r'("[ %s0-9\n\r%s]+")' % (letters,dbl_quoted_punc) ## double quoted text
_ABSOLUTE_URL=r'((http|https|ftp|mailto|file|about)[:/]+?[%s0-9_\@\.\,\?\!\/\:\;\-\#\~\=\&\%%\+]+)' % letters
_ABS_AND_RELATIVE_URL=r'([%s0-9_\@\.\,\?\!\/\:\;\-\#\~\=\&\%%\+]+)' % letters
_SPACES = r'(\s*)'
def doc_href1(self, s,
expr=re.compile(_DQUOTEDTEXT + "(:)" + _ABS_AND_RELATIVE_URL + _SPACES).search
):
return self.doc_href(s, expr)
def doc_href2(self, s,
expr=re.compile(_DQUOTEDTEXT + r'(\,\s+)' + _ABSOLUTE_URL + _SPACES).search
):
return self.doc_href(s, expr)
def doc_href(self, s, expr, punctuation=re.compile(r"[\,\.\?\!\;]+").match):
r=expr(s)
if r:
# need to grab the href part and the
# beginning part
start,e = r.span(1)
name = s[start:e]
name = name.replace('"','',2)
#start = start + 1
st,end = r.span(3)
if punctuation(s[end-1:end]):
end = end -1
link = s[st:end]
#end = end - 1
# name is the href title, link is the target
# of the href
return (StructuredTextLink(name, href=link),
start, end)
#return (StructuredTextLink(s[start:end], href=s[start:end]),
# start, end)
else:
return None
def doc_sgml(self,s,expr=re.compile(r"\<[%s0-9\.\=\'\"\:\/\-\#\+\s\*]+\>" % letters).search):
"""
SGML text is ignored and outputed as-is
"""
r = expr(s)
if r:
start,end = r.span()
text = s[start:end]
return (StructuredTextSGML(text),start,end)
else:
return None
def doc_xref(self, s,
expr = re.compile('\[([%s0-9\-.:/;,\n\r\~]+)\]' % letters).search
):
r = expr(s)
if r:
start, end = r.span(1)
return (StructuredTextXref(s[start:end]), start-1, end+1)
else:
return None
=== Added File zopeproducts/bugtracker/browser/StructuredText/DocumentWithImages.py ===
##############################################################################
#
# Copyright (c) 2001 Zope Corporation and Contributors. All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL). A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE
#
##############################################################################
import re
from DocumentClass import *
class StructuredTextImage(StructuredTextMarkup):
"A simple embedded image"
class DocumentWithImages(DocumentClass):
"""
"""
text_types = [
'doc_img',
] + DocumentClass.text_types
def doc_img(
self, s,
expr1=re.compile('\"([ _a-zA-Z0-9*.:/;,\-\n\~]+)\":img:([a-zA-Z0-9\_\-.:/;,\n\~]+)').search,
expr2=re.compile('\"([ _a-zA-Z0-9*.:/;,\-\n\~]+)\":img:([a-zA-Z0-9\_\-.:/;,\n\~]+):([a-zA-Z0-9_\-.:/;,\n\~]+)').search
):
r = expr2(s)
if r:
# Warning: the regex are getting confused when the string after :img:
# is an URL containing ":" (Collector #2276)
# Ugly workaround: check if have an absolute URL here. Not a cool solution,
# but it works !
if not r.group(2) in ['http','file','ftp']:
startt, endt = r.span(1)
startk, endk = r.span(2)
starth, endh = r.span(3)
start, end = r.span()
key = s[startk:endk]
return (StructuredTextImage(s[startt:endt], href=s[starth:endh], key=s[startk:endk]),
start, end)
r=expr1(s)
if r:
startt, endt = r.span(1)
starth, endh = r.span(2)
start, end = r.span()
return (StructuredTextImage(s[startt:endt], href=s[starth:endh]),
start, end)
return None
=== Added File zopeproducts/bugtracker/browser/StructuredText/HTMLClass.py ===
##############################################################################
#
# Copyright (c) 2001 Zope Corporation and Contributors. All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL). A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE
#
##############################################################################
from cgi import escape
import re, sys, ST
class HTMLClass:
element_types={
'#text': '_text',
'StructuredTextDocument': 'document',
'StructuredTextParagraph': 'paragraph',
'StructuredTextExample': 'example',
'StructuredTextBullet': 'bullet',
'StructuredTextNumbered': 'numbered',
'StructuredTextDescription': 'description',
'StructuredTextDescriptionTitle': 'descriptionTitle',
'StructuredTextDescriptionBody': 'descriptionBody',
'StructuredTextSection': 'section',
'StructuredTextSectionTitle': 'sectionTitle',
'StructuredTextLiteral': 'literal',
'StructuredTextEmphasis': 'emphasis',
'StructuredTextStrong': 'strong',
'StructuredTextLink': 'link',
'StructuredTextXref': 'xref',
'StructuredTextInnerLink':'innerLink',
'StructuredTextNamedLink':'namedLink',
'StructuredTextUnderline':'underline',
'StructuredTextTable':'table',
'StructuredTextSGML':'sgml',
}
def dispatch(self, doc, level, output):
getattr(self, self.element_types[doc.getNodeName()])(doc, level, output)
def __call__(self, doc, level=1, header=1):
r=[]
self.header = header
self.dispatch(doc, level-1, r.append)
return ''.join(r)
def _text(self, doc, level, output):
output(doc.getNodeValue())
def document(self, doc, level, output):
children=doc.getChildNodes()
if self.header:
output('<html>\n')
if (children and
children[0].getNodeName() == 'StructuredTextSection'):
output('<head>\n<title>%s</title>\n</head>\n' %
children[0].getChildNodes()[0].getNodeValue())
output('<body>\n')
for c in children:
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
if self.header:
output('</body>\n')
output('</html>\n')
def section(self, doc, level, output):
children=doc.getChildNodes()
for c in children:
getattr(self, self.element_types[c.getNodeName()])(c, level+1, output)
def sectionTitle(self, doc, level, output):
output('<h%d>' % (level))
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</h%d>\n' % (level))
def description(self, doc, level, output):
p=doc.getPreviousSibling()
if p is None or p.getNodeName() is not doc.getNodeName():
output('<dl>\n')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
n=doc.getNextSibling()
if n is None or n.getNodeName() is not doc.getNodeName():
output('</dl>\n')
def descriptionTitle(self, doc, level, output):
output('<dt>')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</dt>\n')
def descriptionBody(self, doc, level, output):
output('<dd>')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</dd>\n')
def bullet(self, doc, level, output):
p=doc.getPreviousSibling()
if p is None or p.getNodeName() is not doc.getNodeName():
output('\n<ul>\n')
output('<li>')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
n=doc.getNextSibling()
output('</li>\n')
if n is None or n.getNodeName() is not doc.getNodeName():
output('\n</ul>\n')
def numbered(self, doc, level, output):
p=doc.getPreviousSibling()
if p is None or p.getNodeName() is not doc.getNodeName():
output('\n<ol>\n')
output('<li>')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
n=doc.getNextSibling()
output('</li>\n')
if n is None or n.getNodeName() is not doc.getNodeName():
output('\n</ol>\n')
def example(self, doc, level, output):
i=0
for c in doc.getChildNodes():
if i==0:
output('\n<pre>\n')
output(escape(c.getNodeValue()))
output('\n</pre>\n')
else:
getattr(self, self.element_types[c.getNodeName()])(
c, level, output)
def paragraph(self, doc, level, output):
output('<p>')
for c in doc.getChildNodes():
if c.getNodeName() in ['StructuredTextParagraph']:
getattr(self, self.element_types[c.getNodeName()])(
c, level, output)
else:
getattr(self, self.element_types[c.getNodeName()])(
c, level, output)
output('</p>\n')
def link(self, doc, level, output):
output('<a href="%s">' % doc.href)
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</a>')
def emphasis(self, doc, level, output):
output('<em>')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</em>')
def literal(self, doc, level, output):
output('<code>')
for c in doc.getChildNodes():
output(escape(c.getNodeValue()))
output('</code>')
def strong(self, doc, level, output):
output('<strong>')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</strong>')
def underline(self, doc, level, output):
output("<u>")
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output("</u>")
def innerLink(self, doc, level, output):
output('<a href="#ref');
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('">[')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output(']</a>')
def namedLink(self, doc, level, output):
output('<a name="ref')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('">[')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output(']</a>')
def sgml(self,doc,level,output):
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
def xref(self, doc, level, output):
val = doc.getNodeValue()
output('<a href="#ref%s">[%s]</a>' % (val, val) )
def table(self,doc,level,output):
"""
A StructuredTextTable holds StructuredTextRow(s) which
holds StructuredTextColumn(s). A StructuredTextColumn
is a type of StructuredTextParagraph and thus holds
the actual data.
"""
output('<table border="1" cellpadding="2">\n')
for row in doc.getRows()[0]:
output("<tr>\n")
for column in row.getColumns()[0]:
if hasattr(column,"getAlign"):
str = '<%s colspan="%s" align="%s" valign="%s">' % (column.getType(),
column.getSpan(),
column.getAlign(),
column.getValign())
else:
str = '<td colspan="%s">' % column.getSpan()
output(str)
for c in column.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
if hasattr(column,"getType"):
output("</"+column.getType()+">\n")
else:
output("</td>\n")
output("</tr>\n")
output("</table>\n")
=== Added File zopeproducts/bugtracker/browser/StructuredText/HTMLWithImages.py ===
##############################################################################
#
# Copyright (c) 2001 Zope Corporation and Contributors. All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL). A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE
#
##############################################################################
from HTMLClass import HTMLClass
ets = HTMLClass.element_types
ets.update({'StructuredTextImage': 'image'})
class HTMLWithImages(HTMLClass):
element_types = ets
def image(self, doc, level, output):
if hasattr(doc, 'key'):
output('<a name="%s"></a>\n' % doc.key)
output('<img src="%s" alt="%s">\n' % (doc.href, doc.getNodeValue()))
if doc.getNodeValue() and hasattr(doc, 'key'):
output('<p><b>Figure %s</b> %s</p>\n' % (doc.key, doc.getNodeValue()))
=== Added File zopeproducts/bugtracker/browser/StructuredText/ST.py ===
##############################################################################
#
# Copyright (c) 2001 Zope Corporation and Contributors. All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL). A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE
#
##############################################################################
import re, STDOM
from types import ListType
#####################################################################
# Updated functions #
#####################################################################
def indention(str,front = re.compile("^\s+").match):
"""
Find the number of leading spaces. If none, return 0.
"""
result = front(str)
if result is not None:
start, end = result.span()
return end-start
else:
return 0 # no leading spaces
def insert(struct, top, level):
"""
find what will be the parant paragraph of
a sentence and return that paragraph's
sub-paragraphs. The new paragraph will be
appended to those sub-paragraphs
"""
#print "struct", struct, top-1
if not top-1 in range(len(struct)):
if struct:
return struct[len(struct)-1].getSubparagraphs()
return struct
run = struct[top-1]
i = 0
while i+1 < level:
run = run.getSubparagraphs()[len(run.getSubparagraphs())-1]
i = i + 1
#print "parent for level ", level, " was => ", run.getColorizableTexts()
return run.getSubparagraphs()
def display(struct):
"""
runs through the structure and prints out
the paragraphs. If the insertion works
correctly, display's results should mimic
the orignal paragraphs.
"""
if struct.getColorizableTexts():
print join(struct.getColorizableTexts()),"\n"
if struct.getSubparagraphs():
for x in struct.getSubparagraphs():
display(x)
def display2(struct):
"""
runs through the structure and prints out
the paragraphs. If the insertion works
correctly, display's results should mimic
the orignal paragraphs.
"""
if struct.getNodeValue():
print struct.getNodeValue(),"\n"
if struct.getSubparagraphs():
for x in struct.getSubparagraphs():
display(x)
def findlevel(levels,indent):
"""
remove all level information of levels
with a greater level of indentation.
Then return which level should insert this
paragraph
"""
keys = levels.keys()
for key in keys:
if levels[key] > indent:
del(levels[key])
keys = levels.keys()
if not(keys):
return 0
else:
for key in keys:
if levels[key] == indent:
return key
highest = 0
for key in keys:
if key > highest:
highest = key
return highest-1
para_delim = r'(\n\s*\n|\r\n\s*\r\n)' # UNIX or DOS line endings, respectively
#####################################################################
# Golly, the capitalization of this function always makes me think it's a class
def StructuredText(paragraphs, delimiter=re.compile(para_delim)):
"""
StructuredText accepts paragraphs, which is a list of
lines to be parsed. StructuredText creates a structure
which mimics the structure of the paragraphs.
Structure => [paragraph,[sub-paragraphs]]
"""
currentlevel = 0
currentindent = 0
levels = {0:0}
level = 0 # which header are we under
struct = [] # the structure to be returned
run = struct
paragraphs = paragraphs.expandtabs()
paragraphs = '%s%s%s' % ('\n\n', paragraphs, '\n\n')
paragraphs = delimiter.split(paragraphs)
paragraphs = [ x for x in paragraphs if x.strip() ]
if not paragraphs: return StructuredTextDocument()
ind = [] # structure based on indention levels
for paragraph in paragraphs:
ind.append([indention(paragraph), paragraph])
currentindent = indention(paragraphs[0])
levels[0] = currentindent
#############################################################
# updated #
#############################################################
for indent,paragraph in ind :
if indent == 0:
level = level + 1
currentlevel = 0
currentindent = 0
levels = {0:0}
struct.append(StructuredTextParagraph(paragraph, indent=indent, level=currentlevel))
elif indent > currentindent:
currentlevel = currentlevel + 1
currentindent = indent
levels[currentlevel] = indent
run = insert(struct,level,currentlevel)
run.append(StructuredTextParagraph(paragraph, indent=indent, level=currentlevel))
elif indent < currentindent:
result = findlevel(levels,indent)
if result > 0:
currentlevel = result
currentindent = indent
if not level:
struct.append(StructuredTextParagraph(paragraph, indent=indent, level=currentlevel))
else:
run = insert(struct,level,currentlevel)
run.append(StructuredTextParagraph(paragraph, indent=indent, level=currentlevel))
else:
if insert(struct,level,currentlevel):
run = insert(struct,level,currentlevel)
else:
run = struct
currentindent = indent
run.append(StructuredTextParagraph(paragraph, indent=indent, level=currentlevel))
return StructuredTextDocument(struct)
Basic = StructuredText
class StructuredTextParagraph(STDOM.Element):
indent=0
def __init__(self, src, subs=None, **kw):
if subs is None: subs=[]
self._src=src
self._subs=list(subs)
self._attributes=kw.keys()
for k, v in kw.items(): setattr(self, k, v)
def getChildren(self):
src=self._src
if not isinstance(src, ListType): src=[src]
return src+self._subs
def getAttribute(self, name):
return getattr(self, name, None)
def getAttributeNode(self, name):
if hasattr(self, name):
return STDOM.Attr(name, getattr(self, name))
else:
return None
def getAttributes(self):
d={}
for a in self._attributes:
d[a]=getattr(self, a, '')
return STDOM.NamedNodeMap(d)
def getSubparagraphs(self):
return self._subs
def setSubparagraphs(self, subs):
self._subs=subs
def getColorizableTexts(self):
return (self._src,)
def setColorizableTexts(self, src):
self._src=src[0]
def __repr__(self):
r=[]; a=r.append
a((' '*(self.indent or 0))+
('%s(' % self.__class__.__name__)
+str(self._src)+', ['
)
for p in self._subs: a(`p`)
a((' '*(self.indent or 0))+'])')
return '\n'.join(r)
"""
create aliases for all above functions in the pythony way.
"""
def _get_Children(self):
return self.getChildren()
def _get_Attribute(self, name):
return self.getAttribute(name)
def _get_AttributeNode(self, name):
return self.getAttributeNode(name)
def _get_Attributes(self):
return self.getAttributes()
def _get_Subparagraphs(self):
return self.getSubparagraphs()
def _set_Subparagraphs(self, subs):
return self.setSubparagraphs(subs)
def _get_ColorizableTexts(self):
return self.getColorizableTexts()
def _set_ColorizableTexts(self, src):
return self.setColorizableTexts(src)
class StructuredTextDocument(StructuredTextParagraph):
"""
A StructuredTextDocument holds StructuredTextParagraphs
as its subparagraphs.
"""
_attributes=()
def __init__(self, subs=None, **kw):
StructuredTextParagraph.__init__(self, '', subs, **kw)
def getChildren(self):
return self._subs
def getColorizableTexts(self):
return ()
def setColorizableTexts(self, src):
pass
def __repr__(self):
r=[]; a=r.append
a('%s([' % self.__class__.__name__)
for p in self._subs: a(`p`+',')
a('])')
return '\n'.join(r)
"""
create aliases for all above functions in the pythony way.
"""
def _get_Children(self):
return self.getChildren()
def _get_ColorizableTexts(self):
return self.getColorizableTexts()
def _set_ColorizableTexts(self, src):
return self.setColorizableTexts(src)
=== Added File zopeproducts/bugtracker/browser/StructuredText/STDOM.py ===
##############################################################################
#
# Copyright (c) 2001 Zope Corporation and Contributors. All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL). A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE
#
##############################################################################
"""
DOM implementation in StructuredText : Read-Only methods
All standard Zope objects support DOM to a limited extent.
"""
from types import StringType, UnicodeType
StringTypes = (StringType, UnicodeType)
# Node type codes
# ---------------
ELEMENT_NODE = 1
ATTRIBUTE_NODE = 2
TEXT_NODE = 3
CDATA_SECTION_NODE = 4
ENTITY_REFERENCE_NODE = 5
ENTITY_NODE = 6
PROCESSING_INSTRUCTION_NODE = 7
COMMENT_NODE = 8
DOCUMENT_NODE = 9
DOCUMENT_TYPE_NODE = 10
DOCUMENT_FRAGMENT_NODE = 11
NOTATION_NODE = 12
# Exception codes
# ---------------
INDEX_SIZE_ERR = 1
DOMSTRING_SIZE_ERR = 2
HIERARCHY_REQUEST_ERR = 3
WRONG_DOCUMENT_ERR = 4
INVALID_CHARACTER_ERR = 5
NO_DATA_ALLOWED_ERR = 6
NO_MODIFICATION_ALLOWED_ERR = 7
NOT_FOUND_ERR = 8
NOT_SUPPORTED_ERR = 9
INUSE_ATTRIBUTE_ERR = 10
# Exceptions
# ----------
class DOMException(Exception):
pass
class IndexSizeException(DOMException):
code = INDEX_SIZE_ERR
class DOMStringSizeException(DOMException):
code = DOMSTRING_SIZE_ERR
class HierarchyRequestException(DOMException):
code = HIERARCHY_REQUEST_ERR
class WrongDocumentException(DOMException):
code = WRONG_DOCUMENT_ERR
class InvalidCharacterException(DOMException):
code = INVALID_CHARACTER_ERR
class NoDataAllowedException(DOMException):
code = NO_DATA_ALLOWED_ERR
class NoModificationAllowedException(DOMException):
code = NO_MODIFICATION_ALLOWED_ERR
class NotFoundException(DOMException):
code = NOT_FOUND_ERR
class NotSupportedException(DOMException):
code = NOT_SUPPORTED_ERR
class InUseAttributeException(DOMException):
code = INUSE_ATTRIBUTE_ERR
# Node classes
# ------------
class ParentNode:
"""
A node that can have children, or, more precisely, that implements
the child access methods of the DOM.
"""
def getChildNodes(self, type=type, sts=StringTypes):
"""
Returns a NodeList that contains all children of this node.
If there are no children, this is a empty NodeList
"""
r=[]
for n in self.getChildren():
if type(n) in sts: n=TextNode(n)
r.append(n.__of__(self))
return NodeList(r)
def getFirstChild(self, type=type, sts=StringTypes):
"""
The first child of this node. If there is no such node
this returns None
"""
children = self.getChildren()
if not children:
return None
n=children[0]
if type(n) in sts:
n=TextNode(n)
return n.__of__(self)
def getLastChild(self, type=type, sts=StringTypes):
"""
The last child of this node. If there is no such node
this returns None.
"""
children = self.getChildren()
if not children: return None
n=children[-1]
if type(n) in sts: n=TextNode(n)
return n.__of__(self)
"""
create aliases for all above functions in the pythony way.
"""
def _get_ChildNodes(self, type=type, sts=StringTypes):
return self.getChildNodes(type,sts)
def _get_FirstChild(self, type=type, sts=StringTypes):
return self.getFirstChild(type,sts)
def _get_LastChild(self, type=type, sts=StringTypes):
return self.getLastChild(type,sts)
class NodeWrapper(ParentNode):
"""
This is an acquisition-like wrapper that provides parent access for
DOM sans circular references!
"""
def __init__(self, aq_self, aq_parent):
self.aq_self=aq_self
self.aq_parent=aq_parent
def __getattr__(self, name):
return getattr(self.aq_self, name)
def getParentNode(self):
"""
The parent of this node. All nodes except Document
DocumentFragment and Attr may have a parent
"""
return self.aq_parent
def _getDOMIndex(self, children, getattr=getattr):
i=0
self=self.aq_self
for child in children:
if getattr(child, 'aq_self', child) is self:
self._DOMIndex=i
return i
i=i+1
return None
def getPreviousSibling(self):
"""
The node immediately preceding this node. If
there is no such node, this returns None.
"""
children = self.aq_parent.getChildren()
if not children:
return None
index=getattr(self, '_DOMIndex', None)
if index is None:
index=self._getDOMIndex(children)
if index is None: return None
index=index-1
if index < 0: return None
try: n=children[index]
except IndexError: return None
else:
if type(n) in StringTypes:
n=TextNode(n)
n._DOMIndex=index
return n.__of__(self)
def getNextSibling(self):
"""
The node immediately preceding this node. If
there is no such node, this returns None.
"""
children = self.aq_parent.getChildren()
if not children:
return None
index=getattr(self, '_DOMIndex', None)
if index is None:
index=self._getDOMIndex(children)
if index is None:
return None
index=index+1
try: n=children[index]
except IndexError:
return None
else:
if type(n) in StringTypes:
n=TextNode(n)
n._DOMIndex=index
return n.__of__(self)
def getOwnerDocument(self):
"""
The Document object associated with this node, if any.
"""
return self.aq_parent.getOwnerDocument()
"""
create aliases for all above functions in the pythony way.
"""
def _get_ParentNode(self):
return self.getParentNode()
def _get_DOMIndex(self, children, getattr=getattr):
return self._getDOMIndex(children,getattr)
def _get_PreviousSibling(self):
return self.getPreviousSibling()
def _get_NextSibling(self):
return self.getNextSibling()
def _get_OwnerDocument(self):
return self.getOwnerDocument()
class Node(ParentNode):
"""
Node Interface
"""
# Get a DOM wrapper with a parent link
def __of__(self, parent):
return NodeWrapper(self, parent)
# DOM attributes
# --------------
def getNodeName(self):
"""
The name of this node, depending on its type
"""
def getNodeValue(self):
"""
The value of this node, depending on its type
"""
return None
def getParentNode(self):
"""
The parent of this node. All nodes except Document
DocumentFragment and Attr may have a parent
"""
def getChildren(self):
"""
Get a Python sequence of children
"""
return ()
def getPreviousSibling(self,
type=type,
sts=StringTypes,
getattr=getattr):
"""
The node immediately preceding this node. If
there is no such node, this returns None.
"""
def getNextSibling(self, type=type, sts=StringTypes):
"""
The node immediately preceding this node. If
there is no such node, this returns None.
"""
def getAttributes(self):
"""
Returns a NamedNodeMap containing the attributes
of this node (if it is an element) or None otherwise.
"""
return None
def getOwnerDocument(self):
"""
The Document object associated with this node, if any.
"""
# DOM Methods
# -----------
def hasChildNodes(self):
"""
Returns true if the node has any children, false
if it doesn't.
"""
return len(self.getChildren())
"""
create aliases for all above functions in the pythony way.
"""
def _get_NodeName(self):
return self.getNodeName()
def _get_NodeValue(self):
return self.getNodeValue()
def _get_ParentNode(self):
return self.getParentNode()
def _get_Children(self):
return self.getChildren()
def _get_PreviousSibling(self):
return self.getPreviousSibling()
def _get_NextSibling(self):
return self.getNextSibling()
def _get_Attributes(self):
return self.getAttributes()
def _get_OwnerDocument(self):
return self.getOwnerDocument()
def _has_ChildNodes(self):
return self.hasChildNodes()
class TextNode(Node):
def __init__(self, str): self._value=str
def getNodeType(self):
return TEXT_NODE
def getNodeName(self):
return '#text'
def getNodeValue(self):
return self._value
"""
create aliases for all above functions in the pythony way.
"""
def _get_NodeType(self):
return self.getNodeType()
def _get_NodeName(self):
return self.getNodeName()
def _get_NodeValue(self):
return self.getNodeValue()
class Element(Node):
"""
Element interface
"""
# Element Attributes
# ------------------
def getTagName(self):
"""The name of the element"""
return self.__class__.__name__
def getNodeName(self):
"""The name of this node, depending on its type"""
return self.__class__.__name__
def getNodeType(self):
"""A code representing the type of the node."""
return ELEMENT_NODE
def getNodeValue(self):
r=[]
for c in self.getChildren():
if type(c) not in StringTypes:
c=c.getNodeValue()
r.append(c)
return ''.join(r)
def getParentNode(self):
"""
The parent of this node. All nodes except Document
DocumentFragment and Attr may have a parent
"""
# Element Methods
# ---------------
_attributes=()
def getAttribute(self, name): return getattr(self, name, None)
def getAttributeNode(self, name):
if hasattr(self, name):
return Attr(name, getattr(self, name))
def getAttributes(self):
d={}
for a in self._attributes:
d[a]=getattr(self, a, '')
return NamedNodeMap(d)
def getAttribute(self, name):
"""Retrieves an attribute value by name."""
return None
def getAttributeNode(self, name):
""" Retrieves an Attr node by name or None if
there is no such attribute. """
return None
def getElementsByTagName(self, tagname):
"""
Returns a NodeList of all the Elements with a given tag
name in the order in which they would be encountered in a
preorder traversal of the Document tree. Parameter: tagname
The name of the tag to match (* = all tags). Return Value: A new
NodeList object containing all the matched Elements.
"""
nodeList = []
for child in self.getChildren():
if not hasattr(child, 'getNodeType'): continue
if (child.getNodeType()==ELEMENT_NODE and \
child.getTagName()==tagname or tagname== '*'):
nodeList.append(child)
if hasattr(child, 'getElementsByTagName'):
n1 = child.getElementsByTagName(tagname)
nodeList = nodeList + n1._data
return NodeList(nodeList)
"""
create aliases for all above functions in the pythony way.
"""
def _get_TagName(self):
return self.getTagName()
def _get_NodeName(self):
return self.getNodeName()
def _get_NodeType(self):
return self.getNodeType()
def _get_NodeValue(self):
return self.getNodeValue()
def _get_ParentNode(self):
return self.getParentNode()
def _get_Attribute(self, name):
return self.getAttribute(name)
def _get_AttributeNode(self, name):
return self.getAttributeNode(name)
def _get_Attributes(self):
return self.getAttributes()
def _get_Attribute(self, name):
return self.getAttribute(name)
def _get_AttributeNode(self, name):
return self.getAttributeNode(name)
def _get_ElementsByTagName(self, tagname):
return self.getElementsByTagName(tagname)
class NodeList:
"""
NodeList interface - Provides the abstraction of an ordered
collection of nodes.
Python extensions: can use sequence-style 'len', 'getitem', and
'for..in' constructs.
"""
def __init__(self,list=None):
self._data = list or []
def __getitem__(self, index, type=type, sts=StringTypes):
return self._data[index]
def __getslice__(self, i, j):
return self._data[i:j]
def item(self, index):
"""
Returns the index-th item in the collection
"""
try: return self._data[index]
except IndexError: return None
def getLength(self):
"""
The length of the NodeList
"""
return len(self._data)
__len__=getLength
"""
create aliases for all above functions in the pythony way.
"""
def _get_Length(self):
return self.getLength()
class NamedNodeMap:
"""
NamedNodeMap interface - Is used to represent collections
of nodes that can be accessed by name. NamedNodeMaps are not
maintained in any particular order.
Python extensions: can use sequence-style 'len', 'getitem', and
'for..in' constructs, and mapping-style 'getitem'.
"""
def __init__(self, data=None):
if data is None:
data = {}
self._data = data
def item(self, index):
"""
Returns the index-th item in the map
"""
try: return self._data.values()[index]
except IndexError: return None
def __getitem__(self, key):
if type(key)==type(1):
return self._data.values()[key]
else:
return self._data[key]
def getLength(self):
"""
The length of the NodeList
"""
return len(self._data)
__len__ = getLength
def getNamedItem(self, name):
"""
Retrieves a node specified by name. Parameters:
name Name of a node to retrieve. Return Value A Node (of any
type) with the specified name, or None if the specified name
did not identify any node in the map.
"""
if self._data.has_key(name):
return self._data[name]
return None
"""
create aliases for all above functions in the pythony way.
"""
def _get_Length(self):
return self.getLength()
def _get_NamedItem(self, name):
return self.getNamedItem(name)
class Attr(Node):
"""
Attr interface - The Attr interface represents an attriubte in an
Element object. Attr objects inherit the Node Interface
"""
def __init__(self, name, value, specified=1):
self.name = name
self.value = value
self.specified = specified
def getNodeName(self):
"""
The name of this node, depending on its type
"""
return self.name
def getName(self):
"""
Returns the name of this attribute.
"""
return self.name
def getNodeValue(self):
"""
The value of this node, depending on its type
"""
return self.value
def getNodeType(self):
"""
A code representing the type of the node.
"""
return ATTRIBUTE_NODE
def getSpecified(self):
"""
If this attribute was explicitly given a value in the
original document, this is true; otherwise, it is false.
"""
return self.specified
"""
create aliases for all above functions in the pythony way.
"""
def _get_NodeName(self):
return self.getNodeName()
def _get_Name(self):
return self.getName()
def _get_NodeValue(self):
return self.getNodeValue()
def _get_NodeType(self):
return self.getNodeType()
def _get_Specified(self):
return self.getSpecified()
=== Added File zopeproducts/bugtracker/browser/StructuredText/STNG.txt ===
Using Structured Text
The goal of StructuredText is to make it possible to express
structured text using a relatively simple plain text format. Simple
structures, like bullets or headings are indicated through
conventions that are natural, for some definition of
"natural". Hierarchical structures are indicated through
indentation. The use of indentation to express hierarchical
structure is inspired by the Python programming language.
Use of StructuredText consists of one to three logical steps. In the
first step, a text string is converted to a network of objects using
the 'StructuredText.Basic' facility, as in the following
example::
raw=open("mydocument.txt").read()
import StructuredText
st=StructuredText.Basic(raw)
The output of 'StructuredText.Basic' is simply a
StructuredTextDocument object containing StructuredTextParagraph
objects arranged in a hierarchy. Paragraphs are delimited by strings
of two or more whitespace characters beginning and ending with
newline characters. Hierarchy is indicated by indentation. The
indentation of a paragraph is the minimum number of leading spaces
in a line containing non-white-space characters after converting tab
characters to spaces (assuming a tab stop every eight characters).
StructuredTextNode objects support the read-only subset of the
Document Object Model (DOM) API. It should be possible to process
'StructuredTextNode' hierarchies using XML tools such as XSLT.
The second step in using StructuredText is to apply additional
structuring rules based on text content. A variety of differentText
rules can be used. Typically, these are used to implement a
structured text language for producing documents, but any sort of
structured text language could be implemented in the second
step. For example, it is possible to use StructuredText to implement
structured text formats for representing structured data. The second
step, which could consist of multiple processing steps, is
performed by processing, or "coloring", the hierarchy of generic
StructuredTextParagraph objects into a network of more specialized
objects. Typically, the objects produced should also implement the DOM
API to allow processing with XML tools.
A document processor is provided to convert a StructuredTextDocument
object containing only StructuredStructuredTextParagraph objects
into a StructuredTextDocument object containing a richer collection
of objects such as bullets, headings, emphasis, and so on using
hints in the text. Hints are selected based on conventions of the
sort typically seen in electronic mail or news-group postings. It
should be noted, however, that these conventions are somewhat
culturally dependent, fortunately, the document processor is easily
customized to implement alternative rules. Here's an example of
using the DOC processor to convert the output of the previous example::
doc=StructuredText.Document(st)
The final step is to process the colored networks produced from the
second step to produce additional outputs. The final step could be
performed by Python programs, or by XML tools. A Python outputter is
provided for the document processor output that produces Hypertext Markup
Language (HTML) text::
html=StructuredText.HTML(doc)
Customizing the document processor
The document processor is driven by two tables. The first table,
named 'paragraph_types', is a sequence of callable objects or method
names for coloring paragraphs. If a table entry is a string, then it
is the name of a method of the document processor to be used. For
each input paragraph, the objects in the table are called until one
returns a value (not 'None'). The value returned replaces the
original input paragraph in the output. If none of the objects in
the paragraph types table return a value, then a copy of the
original paragraph is used. The new object returned by calling a
paragraph type should implement the ReadOnlyDOM,
StructuredTextColorizable, and StructuredTextSubparagraphContainer
interfaces. See the 'Document.py' source file for examples.
A paragraph type may return a list or tuple of replacement
paragraphs, this allowing a paragraph to be split into multiple
paragraphs.
The second table, 'text_types', is a sequence of callable objects or
method names for coloring text. The callable objects in this table
are used in sequence to transform the input text into new text or
objects. The callable objects are passed a string and return
nothing ('None') or a three-element tuple consisting of:
- a replacement object,
- a starting position, and
- an ending position
The text from the starting position is (logically) replaced with the
replacement object. The replacement object is typically an object
that implements that implements the ReadOnlyDOM, and
StructuredTextColorizable interfaces. The replacement object can
also be a string or a list of strings or objects. Replacement is
done from beginning to end and text after the replacement ending
position will be passed to the character type objects for processing.
Example: adding wiki links
We want to add support for Wiki links. A Wiki link is a string of
text containing mixed-case letters, such that at least two of the
letters are upper case and such that the first letter is upper case.
=== Added File zopeproducts/bugtracker/browser/StructuredText/STletters.py ===
import string
def punc_func(exclude):
punc = r''
for char in string.punctuation:
if char not in exclude:
punc = punc + r'\%s' % char
return punc
digits = string.digits
letters = string.letters
literal_punc = punc_func("'")
dbl_quoted_punc = punc_func("\"")
strongem_punc = punc_func('*')
under_punc = punc_func('_<>')
phrase_delimiters = r'\s\.\,\?\/\!\&\(\)'
=== Added File zopeproducts/bugtracker/browser/StructuredText/StructuredText.py ===
##############################################################################
#
# Copyright (c) 2001 Zope Corporation and Contributors. All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL). A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE
#
##############################################################################
""" Alias module for StructuredTextClassic compatibility which makes
use of StructuredTextNG """
import HTMLClass, DocumentClass
import DocumentWithImages, HTMLWithImages
from ST import Basic
import re, sys
from STletters import letters
Document = DocumentClass.DocumentClass()
HTMLNG = HTMLClass.HTMLClass()
DocumentImages = DocumentWithImages.DocumentWithImages()
HTMLNGImages = HTMLWithImages.HTMLWithImages()
def HTML(aStructuredString, level=1, header=1):
st = Basic(aStructuredString)
doc = DocumentImages(st)
return HTMLNGImages(doc,header=header,level=level)
def StructuredText(aStructuredString, level=1):
return HTML(aStructuredString,level)
def html_with_references(text, level=1, header=1):
text = re.sub(
r'[\000\n]\.\. \[([0-9_%s-]+)\]' % letters,
r'\n <a name="\1">[\1]</a>',
text)
text = re.sub(
r'([\000- ,])\[(?P<ref>[0-9_%s-]+)\]([\000- ,.:])' % letters,
r'\1<a href="#\2">[\2]</a>\3',
text)
text = re.sub(
r'([\000- ,])\[([^]]+)\.html\]([\000- ,.:])',
r'\1<a href="\2.html">[\2]</a>\3',
text)
return HTML(text,level=level,header=header)
def html_quote(v,
character_entities=(
(re.compile('&'), '&'),
(re.compile("<"), '<' ),
(re.compile(">"), '>' ),
(re.compile('"'), '"')
)): #"
text=str(v)
for re,name in character_entities:
text=re.sub(name,text)
return text
if __name__=='__main__':
import getopt
opts,args = getopt.getopt(sys.argv[1:],'',[])
for k,v in opts:
pass
for f in args:
print HTML(open(f).read())
=== Added File zopeproducts/bugtracker/browser/StructuredText/__init__.py ===
##############################################################################
#
# Copyright (c) 2001 Zope Corporation and Contributors. All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL). A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE
#
##############################################################################
import HTMLClass, DocumentClass
import ClassicDocumentClass
from StructuredText import html_with_references, HTML, html_quote
from ST import Basic
import DocBookClass
import HTMLWithImages
from types import StringType, UnicodeType
import DocumentWithImages
ClassicHTML=HTML
HTMLNG=HTMLClass.HTMLClass()
def HTML(src, level=1):
if isinstance(src, StringType) or isinstance(src, UnicodeType):
return ClassicHTML(src, level)
return HTMLNG(src, level)
Classic=ClassicDocumentClass.DocumentClass()
Document=DocumentClass.DocumentClass()
DocumentWithImages=DocumentWithImages.DocumentWithImages()
HTMLWithImages=HTMLWithImages.HTMLWithImages()
DocBookBook=DocBookClass.DocBookBook()
DocBookChapter=DocBookClass.DocBookChapter()
DocBookChapterWithFigures=DocBookClass.DocBookChapterWithFigures()
DocBookArticle=DocBookClass.DocBookArticle()
=== Added File zopeproducts/bugtracker/browser/StructuredText/ts_regex.py ===
##############################################################################
#
# Copyright (c) 2001 Zope Corporation and Contributors. All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL). A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE
#
##############################################################################
"""Provide a thread-safe interface to regex
"""
import regex, regsub #, Sync
from regex import *
from regsub import split, sub, gsub, splitx, capwords
try:
import thread
except:
class allocate_lock:
def acquire(*args): pass
def release(*args): pass
else:
class SafeFunction:
_l=thread.allocate_lock()
_a=_l.acquire
_r=_l.release
def __init__(self, f):
self._f=f
def __call__(self, *args, **kw):
self._a()
try: return self._f(*args, **kw)
finally: self._r()
split=SafeFunction(split)
sub=SafeFunction(sub)
gsub=SafeFunction(gsub)
splitx=SafeFunction(splitx)
capwords=SafeFunction(capwords)
allocate_lock=thread.allocate_lock
class compile:
_r=None
groupindex=None
def __init__(self, *args):
self._r=r=regex(*compile, **args)
self._init(r)
def _init(self, r):
lock=allocate_lock()
self.__a=lock.acquire
self.__r=lock.release
self.translate=r.translate
self.givenpat=r.givenpat
self.realpat=r.realpat
def match(self, string, pos=0):
self.__a()
try: return self._r.match(string, pos)
finally: self.__r()
def search(self, string, pos=0):
self.__a()
try: return self._r.search(string, pos)
finally: self.__r()
def search_group(self, str, group, pos=0):
"""Search a string for a pattern.
If the pattern was not found, then None is returned,
otherwise, the location where the pattern was found,
as well as any specified group are returned.
"""
self.__a()
try:
r=self._r
l=r.search(str, pos)
if l < 0: return None
return l, r.group(*group)
finally: self.__r()
def match_group(self, str, group, pos=0):
"""Match a pattern against a string
If the string does not match the pattern, then None is
returned, otherwise, the length of the match, as well
as any specified group are returned.
"""
self.__a()
try:
r=self._r
l=r.match(str, pos)
if l < 0: return None
return l, r.group(*group)
finally: self.__r()
def search_regs(self, str, pos=0):
"""Search a string for a pattern.
If the pattern was not found, then None is returned,
otherwise, the 'regs' attribute of the expression is
returned.
"""
self.__a()
try:
r=self._r
r.search(str, pos)
return r.regs
finally: self.__r()
def match_regs(self, str, pos=0):
"""Match a pattern against a string
If the string does not match the pattern, then None is
returned, otherwise, the 'regs' attribute of the expression is
returned.
"""
self.__a()
try:
r=self._r
r.match(str, pos)
return r.regs
finally: self.__r()
class symcomp(compile):
def __init__(self, *args):
self._r=r=regex.symcomp(*args)
self._init(r)
self.groupindex=r.groupindex