Skip to content

Z
Zope
Commit 5d3f14c3 authored by 's avatar
Browse files
Options

Merged StructuredText-Dev

parent 1a7fdfd5
Hide whitespace changes
Inline Side-by-side
Showing with 3917 additions and 27 deletions
lib/python/StructuredText/ClassicDocumentClass.py 0 → 100644
View file @ 5d3f14c3
##############################################################################
#
# Zope Public License (ZPL) Version 1.0
# -------------------------------------
#
# Copyright (c) Digital Creations. All rights reserved.
#
# This license has been certified as Open Source(tm).
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# 1. Redistributions in source code must retain the above copyright
# notice, this list of conditions, and the following disclaimer.
#
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions, and the following disclaimer in
# the documentation and/or other materials provided with the
# distribution.
#
# 3. Digital Creations requests that attribution be given to Zope
# in any manner possible. Zope includes a "Powered by Zope"
# button that is installed by default. While it is not a license
# violation to remove this button, it is requested that the
# attribution remain. A significant investment has been put
# into Zope, and this effort will continue if the Zope community
# continues to grow. This is one way to assure that growth.
#
# 4. All advertising materials and documentation mentioning
# features derived from or use of this software must display
# the following acknowledgement:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# In the event that the product being advertised includes an
# intact Zope distribution (with copyright and license included)
# then this clause is waived.
#
# 5. Names associated with Zope or Digital Creations must not be used to
# endorse or promote products derived from this software without
# prior written permission from Digital Creations.
#
# 6. Modified redistributions of any form whatsoever must retain
# the following acknowledgment:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# Intact (re-)distributions of any official Zope release do not
# require an external acknowledgement.
#
# 7. Modifications are encouraged but must be packaged separately as
# patches to official Zope releases. Distributions that do not
# clearly separate the patches from the original work must be clearly
# labeled as unofficial distributions. Modifications which do not
# carry the name Zope may be packaged in any form, as long as they
# conform to all of the clauses above.
#
#
# Disclaimer
#
# THIS SOFTWARE IS PROVIDED BY DIGITAL CREATIONS ``AS IS'' AND ANY
# EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL DIGITAL CREATIONS OR ITS
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
# USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
# OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
# SUCH DAMAGE.
#
#
# This software consists of contributions made by Digital Creations and
# many individuals on behalf of Digital Creations. Specific
# attributions are listed in the accompanying credits file.
#
##############################################################################
import re, ST, STDOM
from string import split, join, replace, expandtabs, strip, find
StringType=type('')
ListType=type([])
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())
apply(ST.StructuredTextParagraph.__init__,
(self, join(t,'\n\n'), ()),
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):
apply(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):
apply(ST.StructuredTextParagraph.__init__,
(self, StructuredTextSectionTitle(src), subs),
kw)
# 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):
apply(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)]
"""
apply(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):
apply(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_href',
'doc_strong',
'doc_emphasize',
'doc_literal',
'doc_inner_link',
'doc_named_link',
'doc_underline',
]
def __call__(self, doc):
if type(doc) is type(''):
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, st=type(''), 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) is st: 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 is st:
# 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) is StringType:
str = self.parse(str, text_type)
elif type(str) is ListType:
r=[]; a=r.append
for s in str:
if type(s) is StringType:
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(())),
st=type('')):
result=[]
for paragraph in raw_paragraphs:
if paragraph.getNodeName() != 'StructuredTextParagraph':
result.append(paragraph)
continue
for pt in self.paragraph_types:
if type(pt) is st:
# 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):
text = paragraph.getColorizableTexts()[0]
m = expr(text)
if not (m):
return None
rows = []
# initial split
for row in split(text,"\n"):
rows.append(row)
# clean up the rows
for index in range(len(rows)):
tmp = []
rows[index] = strip(rows[index])
l = len(rows[index])-2
result = split(rows[index][:l],"||")
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*[a-zA-Z]+\.)|(\s*[0-9]+\.)|(\s*[0-9]+\s+)').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'[^\0- ]').search,
):
top=paragraph.getColorizableTexts()[0]
d=delim(top)
if not d: return None
start, end = d.span()
title=top[:start]
if find(title, '\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('[ a-zA-Z0-9.:/,-_*<>\?\'\"]+').match
):
subs=paragraph.getSubparagraphs()
if not subs: return None
top=paragraph.getColorizableTexts()[0]
if not strip(top): return None
if top[-2:]=='::':
subs=StructuredTextExample(subs)
if strip(top)=='::': return subs
return ST.StructuredTextParagraph(top[:-1],
[subs],
indent=paragraph.indent,
level=paragraph.level)
if find(top,'\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*\*([ \na-zA-Z0-9.:/;,\'\"\?]+)\*(?!\*|-)').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("\[[a-zA-Z0-9]+\]").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("(\.\.\s)(\[[a-zA-Z0-9]+\])").search):
result = expr(s)
if result:
start,end = result.span(2)
a,b = result.span(1)
str = strip(s[a:b]) + s[start:end]
str = s[start+1:end-1]
st,en = result.span()
return (StructuredTextNamedLink(str),st,en)
#return (StructuredTextNamedLink(s[st:en]),st,en)
return None
def doc_underline(self,
s,
expr=re.compile("\_([a-zA-Z0-9\s\.,\?\/]+)\_").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*\*\*([ \na-zA-Z0-9.:/;\-,!\?\'\"]+)\*\*').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_href(
self, s,
expr1 = re.compile("(\"[ a-zA-Z0-9\n\-\.\,\;\(\)\/\:\/]+\")(:)([a-zA-Z0-9\:\/\.\~\-]+)([,]*\s*)").search,
expr2 = re.compile('(\"[ a-zA-Z0-9\n\-\.\:\;\(\)\/]+\")([,]+\s+)([a-zA-Z0-9\@\.\,\?\!\/\:\;\-\#]+)(\s*)').search):
#expr1=re.compile('\"([ a-zA-Z0-9.:/;,\n\~\(\)\-]+)\"'
# ':'
# '([a-zA-Z0-9.:/;,\n\~]+)(?=(\s+|\.|\!|\?))'
# ).search,
#expr2=re.compile('\"([ a-zA-Z0-9./:]+)\"'
# ',\s+'
# '([ a-zA-Z0-9@.:/;]+)(?=(\s+|\.|\!|\?))'
# ).search,
punctuation = re.compile("[\,\.\?\!\;]+").match
r=expr1(s) or expr2(s)
if r:
# need to grab the href part and the
# beginning part
start,e = r.span(1)
name = s[start:e]
name = replace(name,'"','',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
lib/python/StructuredText/DocBookClass.py 0 → 100644
View file @ 5d3f14c3
##############################################################################
#
# Zope Public License (ZPL) Version 1.0
# -------------------------------------
#
# Copyright (c) Digital Creations. All rights reserved.
#
# This license has been certified as Open Source(tm).
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# 1. Redistributions in source code must retain the above copyright
# notice, this list of conditions, and the following disclaimer.
#
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions, and the following disclaimer in
# the documentation and/or other materials provided with the
# distribution.
#
# 3. Digital Creations requests that attribution be given to Zope
# in any manner possible. Zope includes a "Powered by Zope"
# button that is installed by default. While it is not a license
# violation to remove this button, it is requested that the
# attribution remain. A significant investment has been put
# into Zope, and this effort will continue if the Zope community
# continues to grow. This is one way to assure that growth.
#
# 4. All advertising materials and documentation mentioning
# features derived from or use of this software must display
# the following acknowledgement:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# In the event that the product being advertised includes an
# intact Zope distribution (with copyright and license included)
# then this clause is waived.
#
# 5. Names associated with Zope or Digital Creations must not be used to
# endorse or promote products derived from this software without
# prior written permission from Digital Creations.
#
# 6. Modified redistributions of any form whatsoever must retain
# the following acknowledgment:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# Intact (re-)distributions of any official Zope release do not
# require an external acknowledgement.
#
# 7. Modifications are encouraged but must be packaged separately as
# patches to official Zope releases. Distributions that do not
# clearly separate the patches from the original work must be clearly
# labeled as unofficial distributions. Modifications which do not
# carry the name Zope may be packaged in any form, as long as they
# conform to all of the clauses above.
#
#
# Disclaimer
#
# THIS SOFTWARE IS PROVIDED BY DIGITAL CREATIONS ``AS IS'' AND ANY
# EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL DIGITAL CREATIONS OR ITS
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
# USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
# OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
# SUCH DAMAGE.
#
#
# This software consists of contributions made by Digital Creations and
# many individuals on behalf of Digital Creations. Specific
# attributions are listed in the accompanying credits file.
#
##############################################################################
import string
from string import join, split, find, lstrip
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',
}
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(lstrip(doc.getNodeValue()))
def document(self, doc, level, output):
output('<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook V3.1//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<sect%s>\n' % (level + 1))
children=doc.getChildNodes()
for c in children:
getattr(self, self.element_types[c.getNodeName()])(c, level+1, output)
output('\n</sect%s>\n' % (level + 1))
def sectionTitle(self, doc, level, output):
output('<title>')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
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('<link linkend="%s">' % doc.href)
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
# output('</link>')
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 prestrip(v):
v=string.replace(v, '\r\n', '\n')
v=string.replace(v, '\r', '\n')
v=string.replace(v, '\t', ' ')
lines=string.split(v, '\n')
indent=len(lines[0])
for line in lines:
if not len(line): continue
i=len(line)-len(string.lstrip(line))
if i < indent:
indent=i
nlines=[]
for line in lines:
nlines.append(line[indent:])
return string.join(nlines, '\r\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 V3.1//EN">\n')
output('<article>\n')
children=doc.getChildNodes()
if (children and
children[0].getNodeName() == 'StructuredTextSection'):
output('<artheader>\n<title>%s</title>\n</artheader>\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 V3.1//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()
lib/python/StructuredText/DocumentClass.py 0 → 100644
View file @ 5d3f14c3
##############################################################################
#
# Zope Public License (ZPL) Version 1.0
# -------------------------------------
#
# Copyright (c) Digital Creations. All rights reserved.
#
# This license has been certified as Open Source(tm).
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# 1. Redistributions in source code must retain the above copyright
# notice, this list of conditions, and the following disclaimer.
#
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions, and the following disclaimer in
# the documentation and/or other materials provided with the
# distribution.
#
# 3. Digital Creations requests that attribution be given to Zope
# in any manner possible. Zope includes a "Powered by Zope"
# button that is installed by default. While it is not a license
# violation to remove this button, it is requested that the
# attribution remain. A significant investment has been put
# into Zope, and this effort will continue if the Zope community
# continues to grow. This is one way to assure that growth.
#
# 4. All advertising materials and documentation mentioning
# features derived from or use of this software must display
# the following acknowledgement:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# In the event that the product being advertised includes an
# intact Zope distribution (with copyright and license included)
# then this clause is waived.
#
# 5. Names associated with Zope or Digital Creations must not be used to
# endorse or promote products derived from this software without
# prior written permission from Digital Creations.
#
# 6. Modified redistributions of any form whatsoever must retain
# the following acknowledgment:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# Intact (re-)distributions of any official Zope release do not
# require an external acknowledgement.
#
# 7. Modifications are encouraged but must be packaged separately as
# patches to official Zope releases. Distributions that do not
# clearly separate the patches from the original work must be clearly
# labeled as unofficial distributions. Modifications which do not
# carry the name Zope may be packaged in any form, as long as they
# conform to all of the clauses above.
#
#
# Disclaimer
#
# THIS SOFTWARE IS PROVIDED BY DIGITAL CREATIONS ``AS IS'' AND ANY
# EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL DIGITAL CREATIONS OR ITS
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
# USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
# OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
# SUCH DAMAGE.
#
#
# This software consists of contributions made by Digital Creations and
# many individuals on behalf of Digital Creations. Specific
# attributions are listed in the accompanying credits file.
#
##############################################################################
import re, ST, STDOM
from string import split, join, replace, expandtabs, strip, find, rstrip
StringType=type('')
ListType=type([])
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())
apply(ST.StructuredTextParagraph.__init__,
(self, join(t,'\n\n'), ()),
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):
apply(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):
apply(ST.StructuredTextParagraph.__init__,
(self, StructuredTextSectionTitle(src), subs),
kw)
# 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):
apply(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 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):
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)]
"""
apply(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]
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,kw):
# print "StructuredTextColumn", text, span
apply(ST.StructuredTextParagraph.__init__,(self,text,[]),kw)
self._span = span
def getSpan(self):
return self._span
def _getSpan(self):
return self._span
class StructuredTextTableHeader(ST.StructuredTextDocument): pass
class StructuredTextTableData(ST.StructuredTextDocument): 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, 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 StructuredTextSGML(StructuredTextMarkup): pass
class StructuredTextLink(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
"""
#'doc_table',
paragraph_types = [
'doc_bullet',
'doc_numbered',
'doc_description',
'doc_header',
'doc_table',
]
#'doc_inner_link',
#'doc_named_link',
#'doc_underline',
text_types = [
'doc_href',
'doc_strong',
'doc_emphasize',
'doc_literal',
'doc_sgml'
]
def __call__(self, doc):
if type(doc) is type(''):
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, st=type(''), 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) is st: 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 is st:
# 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) is StringType:
str = self.parse(str, text_type)
elif type(str) is ListType:
r=[]; a=r.append
for s in str:
if type(s) is StringType:
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(())),
st=type('')):
result=[]
for paragraph in raw_paragraphs:
#print type(paragraph)
if paragraph.getNodeName() != 'StructuredTextParagraph':
result.append(paragraph)
continue
for pt in self.paragraph_types:
if type(pt) is st:
# 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:
if paragraph.getNodeName() is "StructuredTextTable":
#print "we have a table"
cells = paragraph.getColumns()
text = paragraph.getColorizableTexts()
text = map(ST.StructuredText,text)
text = map(self.__call__,text)
#for index in range(len(text)):
# text[index].setColorizableTexts(map(self.color_text,text[index].getColorizableTexts()))
paragraph.setColorizableTexts(text)
paragraph.setColorizableTexts(
map(self.color_text,
paragraph.getColorizableTexts()
))
result.append(paragraph)
return result
def doc_table(self, paragraph, expr = re.compile('\s*\|[-]+\|').match):
text = paragraph.getColorizableTexts()[0]
m = expr(text)
subs = paragraph.getSubparagraphs()
if not (m):
return None
rows = []
rows = split(text,'\n')
spans = []
ROWS = []
COLS = []
TDdivider = re.compile("[\-]+").match
THdivider = re.compile("[\=]+").match
# find where the column markers are located
col = re.compile('\|').search
text = strip(text)
rows = split(text,'\n')
for row in range(len(rows)):
rows[row] = strip(rows[row])
for row in rows:
tmp = strip(row)
tmp = row[1:len(tmp)-1] # remove leading and trailing |
offset = 0
if col(tmp):
while col(tmp):
start,end = col(tmp).span()
if not start+offset in spans:
spans.append(start + offset)
COLS.append((tmp[0:start],start+offset))
tmp = " " + tmp[end:]
offset = offset + (start)
if not offset+len(tmp) in spans:
spans.append(offset+len(tmp))
COLS.append((tmp,offset+len(tmp)))
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 # the current column span
tmp = []
C = [] # holds the span of each cell
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 = []
# make rows contain the cell's text and the span
# of that cell
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
# now munge the table cells together
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] + rstrip(row[index][0]) + "\n"
COLS[index][1] = row[index][1]
return StructuredTextTable(ROWS,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*[a-zA-Z]+\.)|(\s*[0-9]+\.)|(\s*[0-9]+\s+)').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'[^\0- ]').search,
):
top=paragraph.getColorizableTexts()[0]
d=delim(top)
if not d: return None
start, end = d.span()
title=top[:start]
if find(title, '\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('[ a-zA-Z0-9.:/,-_*<>\?\'\"]+').match
):
subs=paragraph.getSubparagraphs()
if not subs: return None
top=paragraph.getColorizableTexts()[0]
if not strip(top): return None
if top[-2:]=='::':
subs=StructuredTextExample(subs)
if strip(top)=='::': return subs
return ST.StructuredTextParagraph(
top[:-1], [subs], indent=paragraph.indent)
if find(top,'\n') >= 0: return None
return StructuredTextSection(top, subs, indent=paragraph.indent)
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*\*([ \na-zA-Z0-9.:/;,\'\"\?]+)\*(?!\*|-)').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("\[[a-zA-Z0-9]+\]").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("(\.\.\s)(\[[a-zA-Z0-9]+\])").search):
result = expr(s)
if result:
start,end = result.span(2)
a,b = result.span(1)
str = strip(s[a:b]) + s[start:end]
st,en = result.span()
return (StructuredTextNamedLink(str),st,en)
#return (StructuredTextNamedLink(s[st:en]),st,en)
return None
def doc_underline(self,
s,
expr=re.compile("\_([a-zA-Z0-9\s\.,\?]+)\_").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*\*\*([ \na-zA-Z0-9.:/;\-,!\?\'\"]+)\*\*').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_href(
self, s,
expr1 = re.compile("(\"[ a-zA-Z0-9\n\-\.\,\;\(\)\/\:\/]+\")(:)([a-zA-Z0-9\:\/\.\~\-]+)([,]*\s*)").search,
expr2 = re.compile('(\"[ a-zA-Z0-9\n\-\.\:\;\(\)\/]+\")([,]+\s+)([a-zA-Z0-9\@\.\,\?\!\/\:\;\-\#]+)(\s*)').search):
punctuation = re.compile("[\,\.\?\!\;]+").match
r=expr1(s) or expr2(s)
if r:
# need to grab the href part and the
# beginning part
start,e = r.span(1)
name = s[start:e]
name = replace(name,'"','',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("\<[a-zA-Z0-9\.\=\'\"\:\/\-\#\+\s]+\>").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)
lib/python/StructuredText/DocumentWithImages.py 0 → 100644
View file @ 5d3f14c3
##############################################################################
#
# Zope Public License (ZPL) Version 1.0
# -------------------------------------
#
# Copyright (c) Digital Creations. All rights reserved.
#
# This license has been certified as Open Source(tm).
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# 1. Redistributions in source code must retain the above copyright
# notice, this list of conditions, and the following disclaimer.
#
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions, and the following disclaimer in
# the documentation and/or other materials provided with the
# distribution.
#
# 3. Digital Creations requests that attribution be given to Zope
# in any manner possible. Zope includes a "Powered by Zope"
# button that is installed by default. While it is not a license
# violation to remove this button, it is requested that the
# attribution remain. A significant investment has been put
# into Zope, and this effort will continue if the Zope community
# continues to grow. This is one way to assure that growth.
#
# 4. All advertising materials and documentation mentioning
# features derived from or use of this software must display
# the following acknowledgement:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# In the event that the product being advertised includes an
# intact Zope distribution (with copyright and license included)
# then this clause is waived.
#
# 5. Names associated with Zope or Digital Creations must not be used to
# endorse or promote products derived from this software without
# prior written permission from Digital Creations.
#
# 6. Modified redistributions of any form whatsoever must retain
# the following acknowledgment:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# Intact (re-)distributions of any official Zope release do not
# require an external acknowledgement.
#
# 7. Modifications are encouraged but must be packaged separately as
# patches to official Zope releases. Distributions that do not
# clearly separate the patches from the original work must be clearly
# labeled as unofficial distributions. Modifications which do not
# carry the name Zope may be packaged in any form, as long as they
# conform to all of the clauses above.
#
#
# Disclaimer
#
# THIS SOFTWARE IS PROVIDED BY DIGITAL CREATIONS ``AS IS'' AND ANY
# EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL DIGITAL CREATIONS OR ITS
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
# USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
# OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
# SUCH DAMAGE.
#
#
# This software consists of contributions made by Digital Creations and
# many individuals on behalf of Digital Creations. Specific
# attributions are listed in the accompanying credits file.
#
##############################################################################
import re, ST, STDOM
from string import split, join, replace, expandtabs, strip, find
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:
startt, endt = r.span(1)
startk, endk = r.span(2)
starth, endh = r.span(3)
start, end = r.span()
return (StructuredTextImage(s[startt:endt], href=s[starth:endh], key=s[startk:endk]),
start, end)
else:
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
lib/python/StructuredText/HTMLClass.py 0 → 100644
View file @ 5d3f14c3
##############################################################################
#
# Zope Public License (ZPL) Version 1.0
# -------------------------------------
#
# Copyright (c) Digital Creations. All rights reserved.
#
# This license has been certified as Open Source(tm).
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# 1. Redistributions in source code must retain the above copyright
# notice, this list of conditions, and the following disclaimer.
#
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions, and the following disclaimer in
# the documentation and/or other materials provided with the
# distribution.
#
# 3. Digital Creations requests that attribution be given to Zope
# in any manner possible. Zope includes a "Powered by Zope"
# button that is installed by default. While it is not a license
# violation to remove this button, it is requested that the
# attribution remain. A significant investment has been put
# into Zope, and this effort will continue if the Zope community
# continues to grow. This is one way to assure that growth.
#
# 4. All advertising materials and documentation mentioning
# features derived from or use of this software must display
# the following acknowledgement:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# In the event that the product being advertised includes an
# intact Zope distribution (with copyright and license included)
# then this clause is waived.
#
# 5. Names associated with Zope or Digital Creations must not be used to
# endorse or promote products derived from this software without
# prior written permission from Digital Creations.
#
# 6. Modified redistributions of any form whatsoever must retain
# the following acknowledgment:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# Intact (re-)distributions of any official Zope release do not
# require an external acknowledgement.
#
# 7. Modifications are encouraged but must be packaged separately as
# patches to official Zope releases. Distributions that do not
# clearly separate the patches from the original work must be clearly
# labeled as unofficial distributions. Modifications which do not
# carry the name Zope may be packaged in any form, as long as they
# conform to all of the clauses above.
#
#
# Disclaimer
#
# THIS SOFTWARE IS PROVIDED BY DIGITAL CREATIONS ``AS IS'' AND ANY
# EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL DIGITAL CREATIONS OR ITS
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
# USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
# OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
# SUCH DAMAGE.
#
#
# This software consists of contributions made by Digital Creations and
# many individuals on behalf of Digital Creations. Specific
# attributions are listed in the accompanying credits file.
#
##############################################################################
from string import join, split, find
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):
r=[]
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):
output('<html>\n')
children=doc.getChildNodes()
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)
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('<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('</ul>\n')
def numbered(self, doc, level, output):
p=doc.getPreviousSibling()
if p is None or p.getNodeName() is not doc.getNodeName():
output('<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('</ol>\n')
def example(self, doc, level, output):
i=0
for c in doc.getChildNodes():
if i==0:
output('<pre>')
output(html_quote(c.getNodeValue()))
output('</pre>\n')
else:
getattr(self, self.element_types[c.getNodeName()])(
c, level, output)
def paragraph(self, doc, level, output):
i=0
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>')
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(html_quote(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="#');
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="')
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 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]:
str = "<td colspan=%s>" % column.getSpan()
output(str)
#for c in doc.getChildNodes():
# getattr(self, self.element_types[c.getNodeName()])(c, level, output)
for c in column.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output("</td>\n")
output("</tr>\n")
output("</table>\n")
def html_quote(v, name='(Unknown name)', md={},
character_entities=(
(('&'), '&amp;'),
(('<'), '&lt;' ),
(('>'), '&gt;' ),
(('\213'), '&lt;' ),
(('\233'), '&gt;' ),
(('"'), '&quot;'))): #"
text=str(v)
for re,name in character_entities:
if find(text, re) >= 0: text=join(split(text,re),name)
return text
lib/python/StructuredText/HTMLWithImages.py 0 → 100644
View file @ 5d3f14c3
##############################################################################
#
# Zope Public License (ZPL) Version 1.0
# -------------------------------------
#
# Copyright (c) Digital Creations. All rights reserved.
#
# This license has been certified as Open Source(tm).
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# 1. Redistributions in source code must retain the above copyright
# notice, this list of conditions, and the following disclaimer.
#
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions, and the following disclaimer in
# the documentation and/or other materials provided with the
# distribution.
#
# 3. Digital Creations requests that attribution be given to Zope
# in any manner possible. Zope includes a "Powered by Zope"
# button that is installed by default. While it is not a license
# violation to remove this button, it is requested that the
# attribution remain. A significant investment has been put
# into Zope, and this effort will continue if the Zope community
# continues to grow. This is one way to assure that growth.
#
# 4. All advertising materials and documentation mentioning
# features derived from or use of this software must display
# the following acknowledgement:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# In the event that the product being advertised includes an
# intact Zope distribution (with copyright and license included)
# then this clause is waived.
#
# 5. Names associated with Zope or Digital Creations must not be used to
# endorse or promote products derived from this software without
# prior written permission from Digital Creations.
#
# 6. Modified redistributions of any form whatsoever must retain
# the following acknowledgment:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# Intact (re-)distributions of any official Zope release do not
# require an external acknowledgement.
#
# 7. Modifications are encouraged but must be packaged separately as
# patches to official Zope releases. Distributions that do not
# clearly separate the patches from the original work must be clearly
# labeled as unofficial distributions. Modifications which do not
# carry the name Zope may be packaged in any form, as long as they
# conform to all of the clauses above.
#
#
# Disclaimer
#
# THIS SOFTWARE IS PROVIDED BY DIGITAL CREATIONS ``AS IS'' AND ANY
# EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL DIGITAL CREATIONS OR ITS
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
# USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
# OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
# SUCH DAMAGE.
#
#
# This software consists of contributions made by Digital Creations and
# many individuals on behalf of Digital Creations. Specific
# attributions are listed in the accompanying credits file.
#
##############################################################################
from string import join, split, find
import re, sys, ST
import time
from HTMLClass import HTMLClass
ets = HTMLClass.element_types
ets.update({'StructuredTextImage': 'image'})
class HTMLWithImages(HTMLClass):
element_types = ets
def document(self, doc, level, output):
output('<html>\n')
children=doc.getChildNodes()
if (children and
children[0].getNodeName() == 'StructuredTextSection'):
output('<head>\n<title>%s</title>\n</head>\n' %
children[0].getChildNodes()[0].getNodeValue())
output('<body bgcolor="#FFFFFF">\n')
for c in children:
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
output('</body>\n')
output('</html>\n')
def image(self, doc, level, output):
output('<img src="%s" alt="%s">' % (doc.href, doc.getNodeValue()))
def image(self, doc, level, output):
if hasattr(doc, 'key'):
output('<a name="%s"></a>\n<img src="%s" alt="%s">' % (doc.key, doc.href, doc.getNodeValue()))
else:
output('<img src="%s" alt="%s">' % (doc.href, doc.getNodeValue()))
def xref(self, doc, level, output):
val = doc.getNodeValue()
output('<a href="#%s">%s</a>' % (val, val) )
lib/python/StructuredText/ST.py 0 → 100644
View file @ 5d3f14c3
import re, STDOM
from string import split, join, replace, expandtabs, strip, find
#####################################################################
# Updated functions #
#####################################################################
def indention(str,front = re.compile("^\s+").match):
"""
Convert all tabs to the appropriate number of spaces.
Find the number of leading spaces. If none, return 0
"""
if front(str):
start,end = front(str).span()
return end-start-1
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)):
return None
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
#####################################################################
# Golly, the capitalization of this function always makes me think it's a class
def StructuredText(paragraphs, paragraph_delimiter=re.compile('\n\s*\n')):
"""
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 = filter(
strip,
paragraph_delimiter.split(expandtabs('\n\n'+paragraphs+'\n\n'))
)
if not paragraphs: return []
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
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
currentindet = 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, type=type, lt=type([])):
src=self._src
if type(src) is not lt: 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))
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 join(r,'\n')
"""
create aliases for all above functions in the pythony way.
"""
def _get_Children(self, type=type, lt=type([])):
return self.getChildren(type,lt)
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):
apply(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 join(r,'\n')
"""
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)
lib/python/StructuredText/STDOM.py 0 → 100644
View file @ 5d3f14c3
##############################################################################
#
# Zope Public License (ZPL) Version 1.0
# -------------------------------------
#
# Copyright (c) Digital Creations. All rights reserved.
#
# This license has been certified as Open Source(tm).
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# 1. Redistributions in source code must retain the above copyright
# notice, this list of conditions, and the following disclaimer.
#
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions, and the following disclaimer in
# the documentation and/or other materials provided with the
# distribution.
#
# 3. Digital Creations requests that attribution be given to Zope
# in any manner possible. Zope includes a "Powered by Zope"
# button that is installed by default. While it is not a license
# violation to remove this button, it is requested that the
# attribution remain. A significant investment has been put
# into Zope, and this effort will continue if the Zope community
# continues to grow. This is one way to assure that growth.
#
# 4. All advertising materials and documentation mentioning
# features derived from or use of this software must display
# the following acknowledgement:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# In the event that the product being advertised includes an
# intact Zope distribution (with copyright and license included)
# then this clause is waived.
#
# 5. Names associated with Zope or Digital Creations must not be used to
# endorse or promote products derived from this software without
# prior written permission from Digital Creations.
#
# 6. Modified redistributions of any form whatsoever must retain
# the following acknowledgment:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# Intact (re-)distributions of any official Zope release do not
# require an external acknowledgement.
#
# 7. Modifications are encouraged but must be packaged separately as
# patches to official Zope releases. Distributions that do not
# clearly separate the patches from the original work must be clearly
# labeled as unofficial distributions. Modifications which do not
# carry the name Zope may be packaged in any form, as long as they
# conform to all of the clauses above.
#
#
# Disclaimer
#
# THIS SOFTWARE IS PROVIDED BY DIGITAL CREATIONS ``AS IS'' AND ANY
# EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL DIGITAL CREATIONS OR ITS
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
# USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
# OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
# SUCH DAMAGE.
#
#
# This software consists of contributions made by Digital Creations and
# many individuals on behalf of Digital Creations. Specific
# attributions are listed in the accompanying credits file.
#
##############################################################################
"""
DOM implementation in StructuredText : Read-Only methods
All standard Zope objects support DOM to a limited extent.
"""
import string
# 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, st=type('')):
"""
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) is st: n=TextNode(n)
r.append(n.__of__(self))
return NodeList(r)
def getFirstChild(self, type=type, st=type('')):
"""
The first child of this node. If there is no such node
this returns None
"""
children = self.getChildren()
if not children:
return None
n=chidren[0]
if type(n) is st:
n=TextNode(n)
return n.__of__(self)
def getLastChild(self, type=type, st=type('')):
"""
The last child of this node. If there is no such node
this returns None.
"""
children = self.getChildren()
if not children: return None
n=chidren[-1]
if type(n) is st: n=TextNode(n)
return n.__of__(self)
"""
create aliases for all above functions in the pythony way.
"""
def _get_ChildNodes(self, type=type, st=type('')):
return self.getChildNodes(type,st)
def _get_FirstChild(self, type=type, st=type('')):
return self.getFirstChild(type,st)
def _get_LastChild(self, type=type, st=type('')):
return self.getLastChild(type,st)
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,
type=type,
st=type(''),
getattr=getattr,
None=None):
"""
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) is st:
n=TextNode(n)
n._DOMIndex=index
return n.__of__(self)
def getNextSibling(self, type=type, st=type('')):
"""
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) is st:
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,
type=type,
st=type(''),
getattr=getattr,
None=None):
return self.getPreviousSibling(type,st,getattr,None)
def _get_NextSibling(self, type=type, st=type('')):
return self.getNextSibling(type,st)
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,
st=type(''),
getattr=getattr,
None=None):
"""
The node immediately preceding this node. If
there is no such node, this returns None.
"""
def getNextSibling(self, type=type, st=type('')):
"""
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,
type=type,
st=type(''),
getattr=getattr,
None=None):
return self.getPreviousSibling(type,st,getattr,None)
def _get_NextSibling(self, type=type, st=type('')):
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, type=type, st=type('')):
r=[]
for c in self.getChildren():
if type(c) is not st:
c=c.getNodeValue()
r.append(c)
return string.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 (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, type=type, st=type('')):
return self.GetNodeValue(type,st)
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, st=type('')):
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()
lib/python/StructuredText/STNG.txt 0 → 100644
View file @ 5d3f14c3
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
StructuredTextDocumemt 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.
lib/python/StructuredText/StructuredText.py
View file @ 5d3f14c3
......@@ -204,7 +204,7 @@ Special symbology is used to indicate special constructs:
</TABLE>
$Id: StructuredText.py,v 1.29 2000/11/10 16:55:56 brian Exp $'''
$Id: StructuredText.py,v 1.30 2001/01/04 15:01:59 brian Exp $'''
# Copyright
#
# Copyright 1996 Digital Creations, L.C., 910 Princess Anne
......@@ -256,6 +256,9 @@ $Id: StructuredText.py,v 1.29 2000/11/10 16:55:56 brian Exp $'''
# (540) 371-6909
#
# $Log: StructuredText.py,v $
# Revision 1.30 2001/01/04 15:01:59 brian
# Merged StructuredText-Dev
#
# Revision 1.29 2000/11/10 16:55:56 brian
# Fixed stx to allow ampersands in urls.
#
......
lib/python/StructuredText/Zwiki.py 0 → 100644
View file @ 5d3f14c3
#!/usr/bin/python
##############################################################################
#
# Zope Public License (ZPL) Version 1.0
# -------------------------------------
#
# Copyright (c) Digital Creations. All rights reserved.
#
# This license has been certified as Open Source(tm).
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# 1. Redistributions in source code must retain the above copyright
# notice, this list of conditions, and the following disclaimer.
#
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions, and the following disclaimer in
# the documentation and/or other materials provided with the
# distribution.
#
# 3. Digital Creations requests that attribution be given to Zope
# in any manner possible. Zope includes a "Powered by Zope"
# button that is installed by default. While it is not a license
# violation to remove this button, it is requested that the
# attribution remain. A significant investment has been put
# into Zope, and this effort will continue if the Zope community
# continues to grow. This is one way to assure that growth.
#
# 4. All advertising materials and documentation mentioning
# features derived from or use of this software must display
# the following acknowledgement:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# In the event that the product being advertised includes an
# intact Zope distribution (with copyright and license included)
# then this clause is waived.
#
# 5. Names associated with Zope or Digital Creations must not be used to
# endorse or promote products derived from this software without
# prior written permission from Digital Creations.
#
# 6. Modified redistributions of any form whatsoever must retain
# the following acknowledgment:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# Intact (re-)distributions of any official Zope release do not
# require an external acknowledgement.
#
# 7. Modifications are encouraged but must be packaged separately as
# patches to official Zope releases. Distributions that do not
# clearly separate the patches from the original work must be clearly
# labeled as unofficial distributions. Modifications which do not
# carry the name Zope may be packaged in any form, as long as they
# conform to all of the clauses above.
#
#
# Disclaimer
#
# THIS SOFTWARE IS PROVIDED BY DIGITAL CREATIONS ``AS IS'' AND ANY
# EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL DIGITAL CREATIONS OR ITS
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
# USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
# OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
# SUCH DAMAGE.
#
#
# This software consists of contributions made by Digital Creations and
# many individuals on behalf of Digital Creations. Specific
# attributions are listed in the accompanying credits file.
#
##############################################################################
from Html import HTML
from string import split
from ST import DOC
import re
"""
This is the new structured text type.
"""
class Zwiki_Title:
def __init__(self,str=''):
self.expr1 = re.compile('([A-Z]+[A-Z]+[a-zA-Z]*)').search
self.expr2 = re.compile('([A-Z]+[a-z]+[A-Z]+[a-zA-Z]*)').search
self.str = [str]
self.typ = "Zwiki_Title"
def type(self):
return '%s' % self.typ
def string(self):
return self.str
def __getitem__(self,index):
return self.str[index]
def __call__(self,raw_string,subs):
"""
The raw_string is checked to see if it matches the rules
for this structured text expression. If the raw_string does,
it is parsed for the sub-string which matches and a doc_inner_link
instance is returned whose string is the matching substring.
If raw_string does not match, nothing is returned.
"""
if self.expr1(raw_string):
start,end = self.expr1(raw_string).span()
result = Zwiki_Title(raw_string[start:end])
result.start,result.end = self.expr1(raw_string).span()
return result
elif self.expr2(raw_string):
start,end = self.expr2(raw_string).span()
result = Zwiki_Title(raw_string[start:end])
result.start,result.end = self.expr2(raw_string).span()
return result
else:
return None
def span(self):
return self.start,self.end
class Zwiki_doc(DOC):
def __init__(self):
DOC.__init__(self)
"""
Add the new type to self.types
"""
self.types.append(Zwiki_Title())
class Zwiki_parser(HTML):
def __init__(self):
HTML.__init__(self)
self.types["Zwiki_Title"] = self.zwiki_title
def zwiki_title(self,object):
result = ""
for x in object.string():
result = result + x
result = "<a href=%s>%s</a>" % (result,result)
#result = "<dtml-wikiname %s>" % result
self.string = self.string + result
lib/python/StructuredText/__init__.py
View file @ 5d3f14c3
......@@ -82,4 +82,31 @@
# attributions are listed in the accompanying credits file.
#
##############################################################################
import HTMLClass, DocumentClass
import ClassicDocumentClass
from StructuredText import html_with_references, HTML
from ST import Basic
import DocBookClass
import HTMLWithImages
import DocumentWithImages
ClassicHTML=HTML
HTMLNG=HTMLClass.HTMLClass()
def HTML(src, level=0, type=type, StringType=type('')):
if type(src) is StringType:
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()
lib/python/StructuredText/regressions/examples.stx
View file @ 5d3f14c3
......@@ -10,6 +10,23 @@ Small Trials for Structured Text Formatting
- A word: _underlined_.
- A word **strong**.
- An inline example: '1+2'.
- Another example with a different format:
``x='spam''' or ``y='spam''' or ``<dtml-var spam>''.'
We can use expressions in the DTML var tag as
in ``<dtml-var "x+'.txt'">''
- A mult-line example::
blah
*foo bar*
<dtml-var yeha>
.. [1] (The referring text should be a paragraph, not a header, and
should contain a reference to this footnote, footnote "[1]".)
......
lib/python/StructuredText/regressions/regress deleted 100755 → 0
View file @ 1a7fdfd5
#!/bin/sh
# Compare current StructuredText.py processing against prior versions.
# You should see no output if there are no discrepancies.
regressdir=`dirname $0`
PYTHONPATH=`cd $regressdir/../..; pwd`:$PYTHONPATH
export PYTHONPATH
differences=""
for i in *.stx; do
stx=$i
base=`basename $i .stx`
ref=$base.ref
new=$base.new
python ../StructuredText.py $stx > $new
if cmp $ref $new; then
:
else
differences="$differences $stx"
fi
done
if [ -n "$differences" ]; then
echo "Differences encountered processing$differences."
fi
lib/python/StructuredText/ts_regex.py 0 → 100644
View file @ 5d3f14c3
##############################################################################
#
# Zope Public License (ZPL) Version 1.0
# -------------------------------------
#
# Copyright (c) Digital Creations. All rights reserved.
#
# This license has been certified as Open Source(tm).
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# 1. Redistributions in source code must retain the above copyright
# notice, this list of conditions, and the following disclaimer.
#
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions, and the following disclaimer in
# the documentation and/or other materials provided with the
# distribution.
#
# 3. Digital Creations requests that attribution be given to Zope
# in any manner possible. Zope includes a "Powered by Zope"
# button that is installed by default. While it is not a license
# violation to remove this button, it is requested that the
# attribution remain. A significant investment has been put
# into Zope, and this effort will continue if the Zope community
# continues to grow. This is one way to assure that growth.
#
# 4. All advertising materials and documentation mentioning
# features derived from or use of this software must display
# the following acknowledgement:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# In the event that the product being advertised includes an
# intact Zope distribution (with copyright and license included)
# then this clause is waived.
#
# 5. Names associated with Zope or Digital Creations must not be used to
# endorse or promote products derived from this software without
# prior written permission from Digital Creations.
#
# 6. Modified redistributions of any form whatsoever must retain
# the following acknowledgment:
#
# "This product includes software developed by Digital Creations
# for use in the Z Object Publishing Environment
# (http://www.zope.org/)."
#
# Intact (re-)distributions of any official Zope release do not
# require an external acknowledgement.
#
# 7. Modifications are encouraged but must be packaged separately as
# patches to official Zope releases. Distributions that do not
# clearly separate the patches from the original work must be clearly
# labeled as unofficial distributions. Modifications which do not
# carry the name Zope may be packaged in any form, as long as they
# conform to all of the clauses above.
#
#
# Disclaimer
#
# THIS SOFTWARE IS PROVIDED BY DIGITAL CREATIONS ``AS IS'' AND ANY
# EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL DIGITAL CREATIONS OR ITS
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
# USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
# OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
# SUCH DAMAGE.
#
#
# This software consists of contributions made by Digital Creations and
# many individuals on behalf of Digital Creations. Specific
# attributions are listed in the accompanying credits file.
#
##############################################################################
"""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 apply(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=apply(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, apply(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, apply(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=apply(regex.symcomp,args)
self._init(r)
self.groupindex=r.groupindex
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7