From: Robin Dunn
Date: Fri, 4 May 2001 18:28:27 +0000 (+0000)
Subject: Got a new version of StructuredText from Zope's CVS.
X-Git-Url: https://git.saurik.com/wxWidgets.git/commitdiff_plain/ddfc587a2ea899f654d940c21f102316a39985bd
Got a new version of StructuredText from Zope's CVS.
git-svn-id: https://svn.wxwidgets.org/svn/wx/wxWidgets/trunk@9995 c3d73ce0-8a6f-49c7-b76d-6d57e0e08775
---
diff --git a/wxPython/samples/stxview/StructuredText/ClassicDocumentClass.py b/wxPython/samples/stxview/StructuredText/ClassicDocumentClass.py
index 23b73d6294..69fc9c81bb 100644
--- a/wxPython/samples/stxview/StructuredText/ClassicDocumentClass.py
+++ b/wxPython/samples/stxview/StructuredText/ClassicDocumentClass.py
@@ -1,24 +1,24 @@
##############################################################################
-#
+#
# 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
@@ -26,43 +26,43 @@
# 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
@@ -75,16 +75,17 @@
# 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 STletters import letters,lettpunc,punctuations
StringType=type('')
ListType=type([])
@@ -116,7 +117,7 @@ class StructuredTextDescriptionBody(ST.StructuredTextParagraph):
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
@@ -138,6 +139,12 @@ class StructuredTextSection(ST.StructuredTextParagraph):
(self, StructuredTextSectionTitle(src), subs),
kw)
+ def getColorizableTexts(self):
+ return self._src.getColorizableTexts()
+
+ def setColorizableTexts(self,src):
+ self._src.setColorizableTexts(src)
+
# a StructuredTextTable holds StructuredTextRows
class StructuredTextTable(ST.StructuredTextDocument):
"""
@@ -146,27 +153,27 @@ class StructuredTextTable(ST.StructuredTextDocument):
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:
@@ -174,7 +181,7 @@ class StructuredTextTable(ST.StructuredTextDocument):
#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
@@ -186,35 +193,35 @@ class StructuredTextTable(ST.StructuredTextDocument):
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
+ 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:
+ 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):
"""
@@ -223,19 +230,19 @@ class StructuredTextColumn(ST.StructuredTextParagraph):
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()
@@ -269,7 +276,7 @@ class StructuredTextUnderline(StructuredTextMarkup): pass
class StructuredTextLink(StructuredTextMarkup):
"A simple hyperlink"
-class DocumentClass:
+class DocumentClass:
"""
Class instance calls [ex.=> x()] require a structured text
structure. Doc will then parse each paragraph in the structure
@@ -316,10 +323,10 @@ class DocumentClass:
"""
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.
-
+
+ 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
"""
@@ -351,10 +358,10 @@ class DocumentClass:
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
@@ -386,7 +393,7 @@ class DocumentClass:
for s in str.getColorizableTexts():
color(s, (text_type,))
a(s)
-
+
str.setColorizableTexts(r)
return str
@@ -396,11 +403,11 @@ class DocumentClass:
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
@@ -428,19 +435,20 @@ class DocumentClass:
result.append(paragraph)
return result
-
+
def doc_table(self,paragraph, expr = re.compile('(\s*)([||]+)').match):
+ #print "paragraph=>", type(paragraph), paragraph, paragraph._src
text = paragraph.getColorizableTexts()[0]
m = expr(text)
-
+
if not (m):
return None
rows = []
-
+
# initial split
for row in split(text,"\n"):
- rows.append(row)
-
+ rows.append(row)
+
# clean up the rows
for index in range(len(rows)):
tmp = []
@@ -458,30 +466,30 @@ class DocumentClass:
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)
+ 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)]
@@ -493,17 +501,17 @@ class DocumentClass:
def doc_numbered(
self, paragraph,
- expr = re.compile('(\s*[a-zA-Z]+\.)|(\s*[0-9]+\.)|(\s*[0-9]+\s+)').match):
-
+ expr = re.compile('(\s*[%s]+\.)|(\s*[0-9]+\.)|(\s*[0-9]+\s+)' % letters).match):
+
# This is the old expression. It had a nasty habit
# of grabbing paragraphs that began with a single
# letter word even if there was no following period.
-
+
#expr = re.compile('\s*'
# '(([a-zA-Z]|[0-9]+|[ivxlcdmIVXLCDM]+)\.)*'
# '([a-zA-Z]|[0-9]+|[ivxlcdmIVXLCDM]+)\.?'
# '\s+').match):
-
+
top=paragraph.getColorizableTexts()[0]
m=expr(top)
if not m: return None
@@ -518,7 +526,7 @@ class DocumentClass:
def doc_description(
self, paragraph,
delim = re.compile('\s+--\s+').search,
- nb=re.compile(r'[^\0- ]').search,
+ nb=re.compile(r'[^\000- ]').search,
):
top=paragraph.getColorizableTexts()[0]
@@ -542,7 +550,7 @@ class DocumentClass:
delim=d)
def doc_header(self, paragraph,
- expr = re.compile('[ a-zA-Z0-9.:/,-_*<>\?\'\"]+').match
+ expr = re.compile('[ %s0-9.:/,-_*<>\?\'\"]+' % letters).match
):
subs=paragraph.getSubparagraphs()
if not subs: return None
@@ -562,11 +570,11 @@ class DocumentClass:
def doc_literal(
self, s,
expr=re.compile(
- "(?:\s|^)'" # open
+ "(?:\s|^)'" # open
"([^ \t\n\r\f\v']|[^ \t\n\r\f\v'][^\n']*[^ \t\n\r\f\v'])" # contents
- "'(?:\s|[,.;:!?]|$)" # close
+ "'(?:\s|[,.;:!?]|$)" # close
).search):
-
+
r=expr(s)
if r:
start, end = r.span(1)
@@ -576,7 +584,7 @@ class DocumentClass:
def doc_emphasize(
self, s,
- expr = re.compile('\s*\*([ \na-zA-Z0-9.:/;,\'\"\?]+)\*(?!\*|-)').search
+ expr = re.compile('\s*\*([ \n%s0-9]+)\*(?!\*|-)' % lettpunc).search
):
r=expr(s)
@@ -585,12 +593,12 @@ class DocumentClass:
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):
-
+ expr2 = re.compile("\[[%s0-9]+\]" % letters).search):
+
# make sure we dont grab a named link
if expr2(s) and expr1(s):
start1,end1 = expr1(s).span()
@@ -600,17 +608,17 @@ class DocumentClass:
return None
else:
# the .. is somewhere else, ignore it
- return (StructuredTextInnerLink(s[start2+1,end2-1],start2,end2))
+ 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):
-
+ expr=re.compile("(\.\.\s)(\[[%s0-9]+\])" % letters).search):
+
result = expr(s)
if result:
start,end = result.span(2)
@@ -621,11 +629,11 @@ class DocumentClass:
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):
-
+ expr=re.compile("\s+\_([0-9%s ]+)\_" % lettpunc).search):
+
result = expr(s)
if result:
start,end = result.span(1)
@@ -633,10 +641,10 @@ class DocumentClass:
return (StructuredTextUnderline(s[start:end]),st,e)
else:
return None
-
- def doc_strong(self,
+
+ def doc_strong(self,
s,
- expr = re.compile('\s*\*\*([ \na-zA-Z0-9.:/;\-,!\?\'\"]+)\*\*').search
+ expr = re.compile('\s*\*\*([ \n%s0-9]+)\*\*' % lettpunc).search
):
r=expr(s)
@@ -645,45 +653,32 @@ class DocumentClass:
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
+ expr1 = re.compile("(\"[ %s0-9\n\-\.\,\;\(\)\/\:\/\*\']+\")(:)([a-zA-Z0-9\@\.\,\?\!\/\:\;\-\#\~]+)([,]*\s*)" % letters).search,
+ expr2 = re.compile('(\"[ %s0-9\n\-\.\:\;\(\)\/\*\']+\")([,]+\s+)([a-zA-Z0-9\@\.\,\?\!\/\:\;\-\#\~]+)(\s*)' % letters).search):
+
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
+
+ if s[end-1:end] in punctuations: 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
diff --git a/wxPython/samples/stxview/StructuredText/ClassicStructuredText.py b/wxPython/samples/stxview/StructuredText/ClassicStructuredText.py
new file mode 100644
index 0000000000..b591558f73
--- /dev/null
+++ b/wxPython/samples/stxview/StructuredText/ClassicStructuredText.py
@@ -0,0 +1,625 @@
+#! /usr/bin/env python -- # -*- 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.
+#
+##############################################################################
+'''Structured Text Manipulation
+
+Parse a structured text string into a form that can be used with
+structured formats, like html.
+
+Structured text is text that uses indentation and simple
+symbology to indicate the structure of a document.
+
+A structured string consists of a sequence of paragraphs separated by
+one or more blank lines. Each paragraph has a level which is defined
+as the minimum indentation of the paragraph. A paragraph is a
+sub-paragraph of another paragraph if the other paragraph is the last
+preceding paragraph that has a lower level.
+
+Special symbology is used to indicate special constructs:
+
+- A single-line paragraph whose immediately succeeding paragraphs are lower
+ level is treated as a header.
+
+- A paragraph that begins with a '-', '*', or 'o' is treated as an
+ unordered list (bullet) element.
+
+- A paragraph that begins with a sequence of digits followed by a
+ white-space character is treated as an ordered list element.
+
+- A paragraph that begins with a sequence of sequences, where each
+ sequence is a sequence of digits or a sequence of letters followed
+ by a period, is treated as an ordered list element.
+
+- A paragraph with a first line that contains some text, followed by
+ some white-space and '--' is treated as
+ a descriptive list element. The leading text is treated as the
+ element title.
+
+- Sub-paragraphs of a paragraph that ends in the word 'example' or the
+ word 'examples', or '::' is treated as example code and is output as is.
+
+- Text enclosed single quotes (with white-space to the left of the
+ first quote and whitespace or punctuation to the right of the second quote)
+ is treated as example code.
+
+- Text surrounded by '*' characters (with white-space to the left of the
+ first '*' and whitespace or punctuation to the right of the second '*')
+ is emphasized.
+
+- Text surrounded by '**' characters (with white-space to the left of the
+ first '**' and whitespace or punctuation to the right of the second '**')
+ is made strong.
+
+- Text surrounded by '_' underscore characters (with whitespace to the left
+ and whitespace or punctuation to the right) is made underlined.
+
+- Text encloded by double quotes followed by a colon, a URL, and concluded
+ by punctuation plus white space, *or* just white space, is treated as a
+ hyper link. For example:
+
+ "Zope":http://www.zope.org/ is ...
+
+ Is interpreted as 'Zope is ....'
+ Note: This works for relative as well as absolute URLs.
+
+- Text enclosed by double quotes followed by a comma, one or more spaces,
+ an absolute URL and concluded by punctuation plus white space, or just
+ white space, is treated as a hyper link. For example:
+
+ "mail me", mailto:amos@digicool.com.
+
+ Is interpreted as 'mail me.'
+
+- Text enclosed in brackets which consists only of letters, digits,
+ underscores and dashes is treated as hyper links within the document.
+ For example:
+
+ As demonstrated by Smith [12] this technique is quite effective.
+
+ Is interpreted as '... by Smith [12] this ...'. Together
+ with the next rule this allows easy coding of references or end notes.
+
+- Text enclosed in brackets which is preceded by the start of a line, two
+ periods and a space is treated as a named link. For example:
+
+ .. [12] "Effective Techniques" Smith, Joe ...
+
+ Is interpreted as '[12] "Effective Techniques" ...'.
+ Together with the previous rule this allows easy coding of references or
+ end notes.
+
+
+- A paragraph that has blocks of text enclosed in '||' is treated as a
+ table. The text blocks correspond to table cells and table rows are
+ denoted by newlines. By default the cells are center aligned. A cell
+ can span more than one column by preceding a block of text with an
+ equivalent number of cell separators '||'. Newlines and '|' cannot
+ be a part of the cell text. For example:
+
+ |||| **Ingredients** ||
+ || *Name* || *Amount* ||
+ ||Spam||10||
+ ||Eggs||3||
+
+ is interpreted as::
+
+
+
+
Ingredients
+
+
+
Name
+
Amount
+
+
+
Spam
+
10
+
+
+
Eggs
+
3
+
+
+
+'''
+
+import ts_regex
+import regex
+from ts_regex import gsub
+from string import split, join, strip, find
+import string,re
+
+
+def untabify(aString,
+ indent_tab=ts_regex.compile('\(\n\|^\)\( *\)\t').search_group,
+ ):
+ '''\
+ Convert indentation tabs to spaces.
+ '''
+ result=''
+ rest=aString
+ while 1:
+ ts_results = indent_tab(rest, (1,2))
+ if ts_results:
+ start, grps = ts_results
+ lnl=len(grps[0])
+ indent=len(grps[1])
+ result=result+rest[:start]
+ rest="\n%s%s" % (' ' * ((indent/8+1)*8),
+ rest[start+indent+1+lnl:])
+ else:
+ return result+rest
+
+def indent(aString, indent=2):
+ """Indent a string the given number of spaces"""
+ r=split(untabify(aString),'\n')
+ if not r: return ''
+ if not r[-1]: del r[-1]
+ tab=' '*level
+ return "%s%s\n" % (tab,join(r,'\n'+tab))
+
+def reindent(aString, indent=2, already_untabified=0):
+ "reindent a block of text, so that the minimum indent is as given"
+
+ if not already_untabified: aString=untabify(aString)
+
+ l=indent_level(aString)[0]
+ if indent==l: return aString
+
+ r=[]
+
+ append=r.append
+
+ if indent > l:
+ tab=' ' * (indent-l)
+ for s in split(aString,'\n'): append(tab+s)
+ else:
+ l=l-indent
+ for s in split(aString,'\n'): append(s[l:])
+
+ return join(r,'\n')
+
+def indent_level(aString,
+ indent_space=ts_regex.compile('\n\( *\)').search_group,
+ ):
+ '''\
+ Find the minimum indentation for a string, not counting blank lines.
+ '''
+ start=0
+ text='\n'+aString
+ indent=l=len(text)
+ while 1:
+
+ ts_results = indent_space(text, (1,2), start)
+ if ts_results:
+ start, grps = ts_results
+ i=len(grps[0])
+ start=start+i+1
+ if start < l and text[start] != '\n': # Skip blank lines
+ if not i: return (0,aString)
+ if i < indent: indent = i
+ else:
+ return (indent,aString)
+
+def paragraphs(list,start):
+ l=len(list)
+ level=list[start][0]
+ i=start+1
+ while i < l and list[i][0] > level: i=i+1
+ return i-1-start
+
+def structure(list):
+ if not list: return []
+ i=0
+ l=len(list)
+ r=[]
+ while i < l:
+ sublen=paragraphs(list,i)
+ i=i+1
+ r.append((list[i-1][1],structure(list[i:i+sublen])))
+ i=i+sublen
+ return r
+
+
+class Table:
+ CELL='
%s
\n'
+ ROW='
\n%s
\n'
+ TABLE='\n
\n%s
'
+
+ def create(self,aPar,
+ td_reg=re.compile(r'[ \t\n]*\|\|([^\0x00|]*)')
+ ):
+ '''parses a table and returns nested list representing the
+ table'''
+ self.table=[]
+ text=filter(None,split(aPar,'\n'))
+ for line in text:
+ row=[]
+ while 1:
+ mo = td_reg.match(line)
+ if not mo: return 0
+ pos = mo.end(1)
+ row.append(mo.group(1))
+ if pos==len(line):break
+ line=line[pos:]
+ self.table.append(row)
+ return 1
+
+ def html(self):
+ '''Creates an HTML representation of table'''
+ htmltable=[]
+ for row in self.table:
+ htmlrow=[]
+ colspan=1
+ for cell in row:
+ if cell=='':
+ colspan=colspan+1
+ continue
+ else:
+ htmlrow.append(self.CELL%(colspan,cell))
+ colspan=1
+ htmltable.append(self.ROW%join(htmlrow,''))
+ return self.TABLE%join(htmltable,'')
+
+table=Table()
+
+class StructuredText:
+
+ """Model text as structured collection of paragraphs.
+
+ Structure is implied by the indentation level.
+
+ This class is intended as a base classes that do actual text
+ output formatting.
+ """
+
+ def __init__(self, aStructuredString, level=0,
+ paragraph_divider=regex.compile('\(\r?\n *\)+\r?\n'),
+ ):
+ '''Convert a structured text string into a structured text object.
+
+ Aguments:
+
+ aStructuredString -- The string to be parsed.
+ level -- The level of top level headings to be created.
+ '''
+
+
+ pat = ' \"([%s0-9-_,./?=@~&]*)\":' % string.letters+ \
+ '([-:%s0-9_,./?=@#~&]*?)' % string.letters + \
+ '([.:?;] )'
+
+ p_reg = re.compile(pat,re.M)
+
+ aStructuredString = p_reg.sub(r'\1\3 ' , aStructuredString)
+
+ pat = ' \"([%s0-9-_,./?=@~&]*)\", ' % string.letters+ \
+ '([-:%s0-9_,./?=@#~&]*?)' % string.letters + \
+ '([.:?;] )'
+
+ p_reg = re.compile(pat,re.M)
+
+ aStructuredString = p_reg.sub(r'\1\3 ' , aStructuredString)
+
+
+ protoless = find(aStructuredString, '\2\3',s)
+ s=under.sub( r'\1\2\3',s)
+ s=code.sub( r'\1\2\3',s)
+ s=em.sub( r'\1\2\3',s)
+ return s
+
+class HTML(StructuredText):
+
+ '''\
+ An HTML structured text formatter.
+ '''\
+
+ def __str__(self,
+ extra_dl=re.compile("\n
')]
+ s='''%s
+
+ %s
+
+ ''' % (t,s)
+ print s
+ else:
+ print html_with_references(s)
+
+if __name__=="__main__": main()
diff --git a/wxPython/samples/stxview/StructuredText/DocBookClass.py b/wxPython/samples/stxview/StructuredText/DocBookClass.py
index b126878bde..5a14f33d78 100644
--- a/wxPython/samples/stxview/StructuredText/DocBookClass.py
+++ b/wxPython/samples/stxview/StructuredText/DocBookClass.py
@@ -88,238 +88,245 @@ 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('\n')
- output('\n')
- children=doc.getChildNodes()
- if (children and
- children[0].getNodeName() == 'StructuredTextSection'):
- output('%s' % children[0].getChildNodes()[0].getNodeValue())
- for c in children:
+ element_types={
+ '#text': '_text',
+ 'StructuredTextDocument': 'document',
+ 'StructuredTextParagraph': 'paragraph',
+ 'StructuredTextExample': 'example',
+ 'StructuredTextBullet': 'bullet',
+ 'StructuredTextNumbered': 'numbered',
+ 'StructuredTextDescription': 'description',
+ 'StructuredTextDescriptionTitle': 'descriptionTitle',
+ 'StructuredTextDescriptionBody': 'descriptionBody',
+ 'StructuredTextSection': 'section',
+ 'StructuredTextSectionTitle': 'sectionTitle',
+ 'StructuredTextLiteral': 'literal',
+ 'StructuredTextEmphasis': 'emphasis',
+ 'StructuredTextStrong': 'strong',
+ 'StructuredTextLink': 'link',
+ 'StructuredTextXref': 'xref',
+ 'StructuredTextSGML': 'sgml',
+ }
+
+ def dispatch(self, doc, level, output):
+ getattr(self, self.element_types[doc.getNodeName()])(doc, level, output)
+
+ def __call__(self, doc, level=1):
+ r=[]
+ self.dispatch(doc, level-1, r.append)
+ return join(r,'')
+
+ def _text(self, doc, level, output):
+ if doc.getNodeName() == 'StructuredTextLiteral':
+ output(doc.getNodeValue())
+ else:
+ output(lstrip(doc.getNodeValue()))
+
+ def document(self, doc, level, output):
+ output('\n')
+ output('\n')
+ children=doc.getChildNodes()
+ if (children and
+ children[0].getNodeName() == 'StructuredTextSection'):
+ output('%s' % children[0].getChildNodes()[0].getNodeValue())
+ for c in children:
+ getattr(self, self.element_types[c.getNodeName()])(c, level, output)
+ output('\n')
+
+ def section(self, doc, level, output):
+ output('\n\n')
+ children=doc.getChildNodes()
+ for c in children:
+ getattr(self, self.element_types[c.getNodeName()])(c, level+1, output)
+ output('\n\n')
+
+ def sectionTitle(self, doc, level, output):
+ output('')
+ for c in doc.getChildNodes():
+ try:
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
- output('\n')
-
- def section(self, doc, level, output):
- output('\n\n' % (level + 1))
- children=doc.getChildNodes()
- for c in children:
- getattr(self, self.element_types[c.getNodeName()])(c, level+1, output)
- output('\n\n' % (level + 1))
-
- def sectionTitle(self, doc, level, output):
- output('')
- for c in doc.getChildNodes():
- getattr(self, self.element_types[c.getNodeName()])(c, level, output)
- output('\n')
-
- def description(self, doc, level, output):
- p=doc.getPreviousSibling()
- if p is None or p.getNodeName() is not doc.getNodeName():
- output('\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('\n')
-
- def descriptionTitle(self, doc, level, output):
- output('\n')
- for c in doc.getChildNodes():
- getattr(self, self.element_types[c.getNodeName()])(c, level, output)
- output('\n')
-
- def descriptionBody(self, doc, level, output):
- output('\n')
- for c in doc.getChildNodes():
- getattr(self, self.element_types[c.getNodeName()])(c, level, output)
- output('\n')
- output('\n')
+ except:
+ print "failed", c.getNodeName(), c
+ output('\n')
+
+ def description(self, doc, level, output):
+ p=doc.getPreviousSibling()
+ if p is None or p.getNodeName() is not doc.getNodeName():
+ output('\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('\n')
+
+ def descriptionTitle(self, doc, level, output):
+ output('\n')
+ for c in doc.getChildNodes():
+ getattr(self, self.element_types[c.getNodeName()])(c, level, output)
+ output('\n')
+
+ def descriptionBody(self, doc, level, output):
+ output('\n')
+ for c in doc.getChildNodes():
+ getattr(self, self.element_types[c.getNodeName()])(c, level, output)
+ output('\n')
+ output('\n')
+
+ def bullet(self, doc, level, output):
+ p=doc.getPreviousSibling()
+ if p is None or p.getNodeName() is not doc.getNodeName():
+ output('\n')
+ output('\n')
+
+ for c in doc.getChildNodes():
+ getattr(self, self.element_types[c.getNodeName()])(c, level, output)
+ n=doc.getNextSibling()
+ output('\n')
+ if n is None or n.getNodeName() is not doc.getNodeName():
+ output('\n')
+
+ def numbered(self, doc, level, output):
+ p=doc.getPreviousSibling()
+ if p is None or p.getNodeName() is not doc.getNodeName():
+ output('\n')
+ output('\n')
+ for c in doc.getChildNodes():
+ getattr(self, self.element_types[c.getNodeName()])(c, level, output)
+ n=doc.getNextSibling()
+ output('\n')
+ if n is None or n.getNodeName() is not doc.getNodeName():
+ output('\n')
+
+ def example(self, doc, level, output):
+ i=0
+ for c in doc.getChildNodes():
+ if i==0:
+ output('\n' in your body will break this...
+ ##
+ output(prestrip(c.getNodeValue()))
+ output('\n]]>\n')
+ else:
+ getattr(self, self.element_types[c.getNodeName()])(
+ c, level, output)
+
+ def paragraph(self, doc, level, output):
+ output('\n\n')
+ for c in doc.getChildNodes():
+ getattr(self, self.element_types[c.getNodeName()])(
+ c, level, output)
+ output('\n\n')
+
+ def link(self, doc, level, output):
+ output('' % doc.href)
+ for c in doc.getChildNodes():
+ getattr(self, self.element_types[c.getNodeName()])(c, level, output)
+ output('')
- def bullet(self, doc, level, output):
- p=doc.getPreviousSibling()
- if p is None or p.getNodeName() is not doc.getNodeName():
- output('\n')
- output('\n')
+ def emphasis(self, doc, level, output):
+ output('')
+ 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)
- n=doc.getNextSibling()
- output('\n')
- if n is None or n.getNodeName() is not doc.getNodeName():
- output('\n')
-
- def numbered(self, doc, level, output):
- p=doc.getPreviousSibling()
- if p is None or p.getNodeName() is not doc.getNodeName():
- output('\n')
- output('\n')
- for c in doc.getChildNodes():
- getattr(self, self.element_types[c.getNodeName()])(c, level, output)
- n=doc.getNextSibling()
- output('\n')
- if n is None or n.getNodeName() is not doc.getNodeName():
- output('\n')
-
- def example(self, doc, level, output):
- i=0
- for c in doc.getChildNodes():
- if i==0:
- output('\n' in your body will break this...
- ##
- output(prestrip(c.getNodeValue()))
- output('\n]]>\n')
- else:
- getattr(self, self.element_types[c.getNodeName()])(
- c, level, output)
-
- def paragraph(self, doc, level, output):
-
- output('\n\n')
- for c in doc.getChildNodes():
- getattr(self, self.element_types[c.getNodeName()])(
- c, level, output)
- output('\n\n')
-
- def link(self, doc, level, output):
-# output('' % doc.href)
- for c in doc.getChildNodes():
- getattr(self, self.element_types[c.getNodeName()])(c, level, output)
-# output('')
+ def literal(self, doc, level, output):
+ output('')
+ for c in doc.getChildNodes():
+ output(c.getNodeValue())
+ output('')
- def emphasis(self, doc, level, output):
- output('')
- for c in doc.getChildNodes():
- getattr(self, self.element_types[c.getNodeName()])(c, level, output)
- output(' ')
+ def strong(self, doc, level, output):
+ output('')
+ for c in doc.getChildNodes():
+ getattr(self, self.element_types[c.getNodeName()])(c, level, output)
+ output('')
- def literal(self, doc, level, output):
- output('')
- for c in doc.getChildNodes():
- output(c.getNodeValue())
- output('')
+ def xref(self, doc, level, output):
+ output('' % doc.getNodeValue())
- def strong(self, doc, level, output):
- output('')
- for c in doc.getChildNodes():
- getattr(self, self.element_types[c.getNodeName()])(c, level, output)
- output('')
+ def sgml(self, doc, level, output):
+ output(doc.getNodeValue())
- def xref(self, doc, level, output):
- output('' % 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')
+ 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, '\n')
class DocBookChapter(DocBookClass):
- def document(self, doc, level, output):
- output('\n')
- children=doc.getChildNodes()
- if (children and
- children[0].getNodeName() == 'StructuredTextSection'):
- output('%s' % children[0].getChildNodes()[0].getNodeValue())
- for c in children[0].getChildNodes()[1:]:
- getattr(self, self.element_types[c.getNodeName()])(c, level, output)
- output('\n')
+ def document(self, doc, level, output):
+ output('\n')
+ children=doc.getChildNodes()
+ if (children and
+ children[0].getNodeName() == 'StructuredTextSection'):
+ output('%s' % children[0].getChildNodes()[0].getNodeValue())
+ for c in children[0].getChildNodes()[1:]:
+ getattr(self, self.element_types[c.getNodeName()])(c, level, output)
+ output('\n')
ets = DocBookClass.element_types
-ets.update({'StructuredTextImage': 'image'})
+ets.update({'StructuredTextImage': 'image'})
class DocBookChapterWithFigures(DocBookChapter):
- element_types = ets
+ element_types = ets
- def image(self, doc, level, output):
- if hasattr(doc, 'key'):
- output('%s\n' % (doc.key, doc.getNodeValue()) )
- else:
- output('%s\n' % doc.getNodeValue())
-## for c in doc.getChildNodes():
-## getattr(self, self.element_types[c.getNodeName()])(c, level, output)
- output('\n\n' % doc.href)
+ def image(self, doc, level, output):
+ if hasattr(doc, 'key'):
+ output('%s\n' % (doc.key, doc.getNodeValue()) )
+ else:
+ output('%s\n' % doc.getNodeValue())
+## for c in doc.getChildNodes():
+## getattr(self, self.element_types[c.getNodeName()])(c, level, output)
+ output('\n\n' % doc.href)
class DocBookArticle(DocBookClass):
- def document(self, doc, level, output):
- output('\n')
- output('\n')
- children=doc.getChildNodes()
- if (children and
- children[0].getNodeName() == 'StructuredTextSection'):
- output('\n%s\n\n' %
- children[0].getChildNodes()[0].getNodeValue())
- for c in children:
- getattr(self, self.element_types[c.getNodeName()])(c, level, output)
- output('\n')
+ def document(self, doc, level, output):
+ output('\n')
+ output('\n')
+ children=doc.getChildNodes()
+ if (children and
+ children[0].getNodeName() == 'StructuredTextSection'):
+ output('\n%s\n\n' %
+ children[0].getChildNodes()[0].getNodeValue())
+ for c in children:
+ getattr(self, self.element_types[c.getNodeName()])(c, level, output)
+ output('\n')
class DocBookBook:
- def __init__(self, title=''):
- self.title = title
- self.chapters = []
+ def __init__(self, title=''):
+ self.title = title
+ self.chapters = []
- def addChapter(self, chapter):
- self.chapters.append(chapter)
+ def addChapter(self, chapter):
+ self.chapters.append(chapter)
- def read(self):
- out = '\n\n'
- out = out + '%s\n' % self.title
- for chapter in self.chapters:
- out = out + chapter + '\n\n'
+ def read(self):
+ out = '\n\n'
+ out = out + '%s\n' % self.title
+ for chapter in self.chapters:
+ out = out + chapter + '\n\n'
- return out
+ return out
- def __str__(self):
- return self.read()
-
+ def __str__(self):
+ return self.read()
+
diff --git a/wxPython/samples/stxview/StructuredText/DocumentClass.py b/wxPython/samples/stxview/StructuredText/DocumentClass.py
index ec6dc402a4..405f35e25d 100644
--- a/wxPython/samples/stxview/StructuredText/DocumentClass.py
+++ b/wxPython/samples/stxview/StructuredText/DocumentClass.py
@@ -85,19 +85,31 @@
import re, ST, STDOM
from string import split, join, replace, expandtabs, strip, find, rstrip
+from STletters import *
+
StringType=type('')
ListType=type([])
+def flatten(obj, append):
+ if obj.getNodeType()==STDOM.TEXT_NODE:
+ append(obj.getNodeValue())
+ else:
+ for child in obj.getChildNodes():
+ flatten(child, append)
+
+
class StructuredTextExample(ST.StructuredTextParagraph):
"""Represents a section of document with literal text, as for examples"""
def __init__(self, subs, **kw):
- t=[]; a=t.append
- for s in subs: a(s.getNodeValue())
- apply(ST.StructuredTextParagraph.__init__,
- (self, join(t,'\n\n'), ()),
- kw)
+ t=[]
+ a=t.append
+ for s in subs:
+ flatten(s, a)
+ apply(ST.StructuredTextParagraph.__init__,
+ (self, join(t,'\n\n'), ()),
+ kw)
def getColorizableTexts(self): return ()
def setColorizableTexts(self, src): pass # never color examples
@@ -137,9 +149,15 @@ class StructuredTextSection(ST.StructuredTextParagraph):
apply(ST.StructuredTextParagraph.__init__,
(self, StructuredTextSectionTitle(src), subs),
kw)
-
+
+ def getColorizableTexts(self):
+ return self._src.getColorizableTexts()
+
+ def setColorizableTexts(self,src):
+ self._src.setColorizableTexts(src)
+
# a StructuredTextTable holds StructuredTextRows
-class StructuredTextTable(ST.StructuredTextDocument):
+class StructuredTextTable(ST.StructuredTextParagraph):
"""
rows is a list of lists containing tuples, which
represent the columns/cells in each rows.
@@ -148,7 +166,7 @@ class StructuredTextTable(ST.StructuredTextDocument):
"""
def __init__(self, rows, src, subs, **kw):
- apply(ST.StructuredTextDocument.__init__,(self,subs),kw)
+ apply(ST.StructuredTextParagraph.__init__,(self,subs),kw)
self._rows = []
for row in rows:
if row:
@@ -208,34 +226,40 @@ class StructuredTextTable(ST.StructuredTextDocument):
return self.setColorizableTexts()
# StructuredTextRow holds StructuredTextColumns
-class StructuredTextRow(ST.StructuredTextDocument):
+class StructuredTextRow(ST.StructuredTextParagraph):
def __init__(self,row,kw):
"""
row is a list of tuples, where each tuple is
the raw text for a cell/column and the span
- of that cell/column".
+ of that cell/column.
EX
[('this is column one',1), ('this is column two',1)]
"""
- apply(ST.StructuredTextDocument.__init__,(self,[]),kw)
+ apply(ST.StructuredTextParagraph.__init__,(self,[]),kw)
+
self._columns = []
- for column in row:
- self._columns.append(StructuredTextColumn(column[0],column[1],kw))
-
+ for column in row:
+ self._columns.append(StructuredTextColumn(column[0],
+ column[1],
+ column[2],
+ column[3],
+ column[4],
+ kw))
+
def getColumns(self):
return [self._columns]
-
+
def _getColumns(self):
return [self._columns]
def setColumns(self,columns):
self._columns = columns
-
+
def _setColumns(self,columns):
return self.setColumns(columns)
-
+
# this holds the text of a table cell
class StructuredTextColumn(ST.StructuredTextParagraph):
"""
@@ -245,20 +269,40 @@ class StructuredTextColumn(ST.StructuredTextParagraph):
or StructuredTextTableData.
"""
- def __init__(self,text,span,kw):
- # print "StructuredTextColumn", text, span
+ def __init__(self,text,span,align,valign,typ,kw):
apply(ST.StructuredTextParagraph.__init__,(self,text,[]),kw)
self._span = span
+ self._align = align
+ self._valign = valign
+ self._type = typ
def getSpan(self):
return self._span
def _getSpan(self):
return self._span
+
+ def getAlign(self):
+ return self._align
+
+ def _getAlign(self):
+ return self.getAlign()
+
+ def getValign(self):
+ return self._valign
+
+ def _getValign(self):
+ return self.getValign()
+
+ def getType(self):
+ return self._type
+
+ def _getType(self):
+ return self.getType()
+
+class StructuredTextTableHeader(ST.StructuredTextParagraph): pass
-class StructuredTextTableHeader(ST.StructuredTextDocument): pass
-
-class StructuredTextTableData(ST.StructuredTextDocument): pass
+class StructuredTextTableData(ST.StructuredTextParagraph): pass
class StructuredTextMarkup(STDOM.Element):
@@ -266,22 +310,22 @@ class StructuredTextMarkup(STDOM.Element):
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
@@ -294,9 +338,11 @@ class StructuredTextUnderline(StructuredTextMarkup): pass
class StructuredTextSGML(StructuredTextMarkup): pass
-class StructuredTextLink(StructuredTextMarkup): pass
+class StructuredTextLink(StructuredTextMarkup): pass
+
+class StructuredTextXref(StructuredTextMarkup): pass
-class DocumentClass:
+class DocumentClass:
"""
Class instance calls [ex.=> x()] require a structured text
structure. Doc will then parse each paragraph in the structure
@@ -309,7 +355,6 @@ class DocumentClass:
instance with a strong instance stored in its string
"""
- #'doc_table',
paragraph_types = [
'doc_bullet',
'doc_numbered',
@@ -322,13 +367,15 @@ class DocumentClass:
#'doc_named_link',
#'doc_underline',
text_types = [
+ 'doc_sgml',
'doc_href',
'doc_strong',
'doc_emphasize',
'doc_literal',
- 'doc_sgml'
+ 'doc_sgml',
+ 'doc_xref',
]
-
+
def __call__(self, doc):
if type(doc) is type(''):
doc=ST.StructuredText(doc)
@@ -338,10 +385,10 @@ class DocumentClass:
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.
@@ -425,7 +472,6 @@ class DocumentClass:
st=type('')):
result=[]
for paragraph in raw_paragraphs:
- #print type(paragraph)
if paragraph.getNodeName() != 'StructuredTextParagraph':
result.append(paragraph)
continue
@@ -445,23 +491,22 @@ class DocumentClass:
break
else:
new_paragraphs=ST.StructuredTextParagraph(paragraph.getColorizableTexts()[0],
- self.color_paragraphs(paragraph.getSubparagraphs()),
- indent=paragraph.indent),
+ 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()))
+ for t in range(len(text)):
+ text[t] = text[t].getSubparagraphs()
paragraph.setColorizableTexts(text)
-
+
paragraph.setColorizableTexts(
map(self.color_text,
paragraph.getColorizableTexts()
@@ -470,7 +515,7 @@ class DocumentClass:
return result
- def doc_table(self, paragraph, expr = re.compile('\s*\|[-]+\|').match):
+ def doc_table(self, paragraph, expr = re.compile(r'\s*\|[-]+\|').match):
text = paragraph.getColorizableTexts()[0]
m = expr(text)
@@ -479,58 +524,102 @@ class DocumentClass:
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
+ indexes = []
+ ignore = []
+
+ TDdivider = re.compile("[\-]+").match
+ THdivider = re.compile("[\=]+").match
+ col = re.compile('\|').search
+ innertable = re.compile('\|([-]+|[=]+)\|').search
+
text = strip(text)
rows = split(text,'\n')
+ foo = ""
+
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
+
+ # have indexes store if a row is a divider
+ # or a cell part
+ for index in range(len(rows)):
+ tmpstr = rows[index][1:len(rows[index])-1]
+ if TDdivider(tmpstr):
+ indexes.append("TDdivider")
+ elif THdivider(tmpstr):
+ indexes.append("THdivider")
+ else:
+ indexes.append("cell")
+
+ for index in range(len(indexes)):
+ if indexes[index] is "TDdivider" or indexes[index] is THdivider:
+ ignore = [] # reset ignore
+ #continue # skip dividers
+
+ tmp = strip(rows[index]) # clean the row up
+ tmp = tmp[1:len(tmp)-1] # remove leading + trailing |
+ offset = 0
+
+ # find the start and end of inner
+ # tables. ignore everything between
+ if innertable(tmp):
+ tmpstr = strip(tmp)
+ while innertable(tmpstr):
+ start,end = innertable(tmpstr).span()
+ if not (start,end-1) in ignore:
+ ignore.append(start,end-1)
+ tmpstr = " " + tmpstr[end:]
+
+ # find the location of column dividers
+ # NOTE: |'s in inner tables do not count
+ # as column dividers
if col(tmp):
while col(tmp):
- start,end = col(tmp).span()
+ bar = 1 # true if start is not in ignore
+ 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)
+ for s,e in ignore:
+ if start+offset >= s or start+offset <= e:
+ bar = None
+ break
+ if bar: # start is clean
+ spans.append(start+offset)
+ if not bar:
+ foo = foo + tmp[:end]
+ tmp = tmp[end:]
+ offset = offset + end
+ else:
+ COLS.append((foo + tmp[0:start],start+offset))
+ foo = ""
+ tmp = " " + tmp[end:]
+ offset = offset + start
if not offset+len(tmp) in spans:
spans.append(offset+len(tmp))
- COLS.append((tmp,offset+len(tmp)))
+ COLS.append((foo + tmp,offset+len(tmp)))
+ foo = ""
ROWS.append(COLS)
COLS = []
-
- spans.sort()
-
- ROWS = ROWS[1:len(ROWS)]
+ 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
+
+ cur = 1
+ tmp = []
+ C = []
for col in cols:
for span in spans:
if not span in col:
@@ -541,14 +630,47 @@ class DocumentClass:
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
+ # label things as either TableData or
+ # Table header
+ TD = []
+ TH = []
+ all = []
+ for index in range(len(indexes)):
+ if indexes[index] is "TDdivider":
+ TD.append(index)
+ all.append(index)
+ if indexes[index] is "THdivider":
+ TH.append(index)
+ all.append(index)
+ TD = TD[1:]
+ dividers = all[1:]
+ #print "TD => ", TD
+ #print "TH => ", TH
+ #print "all => ", all, "\n"
+
+ for div in dividers:
+ if div in TD:
+ index = all.index(div)
+ for rowindex in range(all[index-1],all[index]):
+ for i in range(len(rows[rowindex])):
+ rows[rowindex][i] = (rows[rowindex][i][0],
+ rows[rowindex][i][1],
+ "td")
+ else:
+ index = all.index(div)
+ for rowindex in range(all[index-1],all[index]):
+ for i in range(len(rows[rowindex])):
+ rows[rowindex][i] = (rows[rowindex][i][0],
+ rows[rowindex][i][1],
+ "th")
+
+ # now munge the multi-line cells together
+ # as paragraphs
ROWS = []
COLS = []
for row in rows:
@@ -556,16 +678,97 @@ class DocumentClass:
if not COLS:
COLS = range(len(row))
for i in range(len(COLS)):
- COLS[i] = ["",1]
+ 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][0] = COLS[index][0] + (row[index][0]) + "\n"
COLS[index][1] = row[index][1]
- return StructuredTextTable(ROWS,text,subs,indent=paragraph.indent)
+ COLS[index][2] = row[index][2]
+
+ # now that each cell has been munged together,
+ # determine the cell's alignment.
+ # Default is to center. Also determine the cell's
+ # vertical alignment, top, middle, bottom. Default is
+ # to middle
+ rows = []
+ cols = []
+ for row in ROWS:
+ for index in range(len(row)):
+ topindent = 0
+ bottomindent = 0
+ leftindent = 0
+ rightindent = 0
+ left = []
+ right = []
+ text = row[index][0]
+ text = split(text,'\n')
+ text = text[:len(text)-1]
+ align = ""
+ valign = ""
+ for t in text:
+ t = strip(t)
+ if not t:
+ topindent = topindent + 1
+ else:
+ break
+ text.reverse()
+ for t in text:
+ t = strip(t)
+ if not t:
+ bottomindent = bottomindent + 1
+ else:
+ break
+ text.reverse()
+ tmp = join(text[topindent:len(text)-bottomindent],"\n")
+ pars = re.compile("\n\s*\n").split(tmp)
+ for par in pars:
+ if index > 0:
+ par = par[1:]
+ par = split(par, ' ')
+ for p in par:
+ if not p:
+ leftindent = leftindent+1
+ else:
+ break
+ left.append(leftindent)
+ leftindent = 0
+ par.reverse()
+ for p in par:
+ if not p:
+ rightindent = rightindent + 1
+ else:
+ break
+ right.append(rightindent)
+ rightindent = 0
+ left.sort()
+ right.sort()
+
+ if topindent == bottomindent:
+ valign="middle"
+ elif topindent < 1:
+ valign="top"
+ elif bottomindent < 1:
+ valign="bottom"
+ else:
+ valign="middle"
+
+ if left[0] < 1:
+ align = "left"
+ elif right[0] < 1:
+ align = "right"
+ elif left[0] > 1 and right[0] > 1:
+ align="center"
+ else:
+ align="left"
+
+ cols.append(row[index][0],row[index][1],align,valign,row[index][2])
+ rows.append(cols)
+ cols = []
+ return StructuredTextTable(rows,text,subs,indent=paragraph.indent)
- def doc_bullet(self, paragraph, expr = re.compile('\s*[-*o]\s+').match):
+ def doc_bullet(self, paragraph, expr = re.compile(r'\s*[-*o]\s+').match):
top=paragraph.getColorizableTexts()[0]
m=expr(top)
@@ -583,7 +786,7 @@ class DocumentClass:
def doc_numbered(
self, paragraph,
- expr = re.compile('(\s*[a-zA-Z]+\.)|(\s*[0-9]+\.)|(\s*[0-9]+\s+)').match):
+ expr = re.compile(r'(\s*[%s]+\.)|(\s*[0-9]+\.)|(\s*[0-9]+\s+)' % letters).match):
# This is the old expression. It had a nasty habit
# of grabbing paragraphs that began with a single
@@ -607,8 +810,8 @@ class DocumentClass:
def doc_description(
self, paragraph,
- delim = re.compile('\s+--\s+').search,
- nb=re.compile(r'[^\0- ]').search,
+ delim = re.compile(r'\s+--\s+').search,
+ nb=re.compile(r'[^\000- ]').search,
):
top=paragraph.getColorizableTexts()[0]
@@ -632,7 +835,7 @@ class DocumentClass:
delim=d)
def doc_header(self, paragraph,
- expr = re.compile('[ a-zA-Z0-9.:/,-_*<>\?\'\"]+').match
+ expr = re.compile(r'[ %s0-9.:/,-_*<>\?\'\"]+' % letters).match
):
subs=paragraph.getSubparagraphs()
if not subs: return None
@@ -650,9 +853,9 @@ class DocumentClass:
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|[,.;:!?]|$)" # close
+ r"(?:\s|^)'" # open
+ r"([^ \t\n\r\f\v']|[^ \t\n\r\f\v'][^\n']*[^ \t\n\r\f\v'])" # contents
+ r"'(?:\s|[,.;:!?]|$)" # close
).search):
r=expr(s)
@@ -664,7 +867,7 @@ class DocumentClass:
def doc_emphasize(
self, s,
- expr = re.compile('\s*\*([ \na-zA-Z0-9.:/;,\'\"\?]+)\*(?!\*|-)').search
+ expr = re.compile(r'\s*\*([ \n%s0-9]+)\*(?!\*|-)' % lettpunc).search
):
r=expr(s)
@@ -676,8 +879,8 @@ class DocumentClass:
def doc_inner_link(self,
s,
- expr1 = re.compile("\.\.\s*").search,
- expr2 = re.compile("\[[a-zA-Z0-9]+\]").search):
+ expr1 = re.compile(r"\.\.\s*").search,
+ expr2 = re.compile(r"\[[%s0-9]+\]" % letters ).search):
# make sure we dont grab a named link
if expr2(s) and expr1(s):
@@ -697,7 +900,7 @@ class DocumentClass:
def doc_named_link(self,
s,
- expr=re.compile("(\.\.\s)(\[[a-zA-Z0-9]+\])").search):
+ expr=re.compile(r"(\.\.\s)(\[[%s0-9]+\])" % letters).search):
result = expr(s)
if result:
@@ -711,7 +914,7 @@ class DocumentClass:
def doc_underline(self,
s,
- expr=re.compile("\_([a-zA-Z0-9\s\.,\?]+)\_").search):
+ expr=re.compile(r"\s+\_([%s0-9\s]+)\_" % lettpunc).search):
result = expr(s)
if result:
@@ -723,7 +926,7 @@ class DocumentClass:
def doc_strong(self,
s,
- expr = re.compile('\s*\*\*([ \na-zA-Z0-9.:/;\-,!\?\'\"]+)\*\*').search
+ expr = re.compile(r'\s*\*\*([ \n%s0-9]+)\*\*' % lettpunc).search
):
r=expr(s)
@@ -732,14 +935,17 @@ class DocumentClass:
return (StructuredTextStrong(s[start:end]), start-2, end+2)
else:
return None
+
+ ## Some constants to make the doc_href() regex easier to read.
+ _DQUOTEDTEXT = r'("[%s0-9\n\-\.\,\;\(\)\/\:\/\*\']+")' % letters ## double quoted text
+ _URL_AND_PUNC = r'([%s0-9\@\.\,\?\!\/\:\;\-\#\~]+)' % letters
+ _SPACES = r'(\s*)'
- 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):
+ def doc_href(self, s,
+ expr1 = re.compile(_DQUOTEDTEXT + "(:)" + _URL_AND_PUNC + _SPACES).search,
+ expr2 = re.compile(_DQUOTEDTEXT + r'(\,\s+)' + _URL_AND_PUNC + _SPACES).search):
- punctuation = re.compile("[\,\.\?\!\;]+").match
+ punctuation = re.compile(r"[\,\.\?\!\;]+").match
r=expr1(s) or expr2(s)
if r:
@@ -766,7 +972,7 @@ class DocumentClass:
else:
return None
- def doc_sgml(self,s,expr=re.compile("\<[a-zA-Z0-9\.\=\'\"\:\/\-\#\+\s]+\>").search):
+ def doc_sgml(self,s,expr=re.compile(r"\<[%s0-9\.\=\'\"\:\/\-\#\+\s\*]+\>" % letters).search):
"""
SGML text is ignored and outputed as-is
"""
@@ -775,3 +981,18 @@ class DocumentClass:
start,end = r.span()
text = s[start:end]
return (StructuredTextSGML(text),start,end)
+
+
+ def doc_xref(self, s,
+ expr = re.compile('\[([%s0-9\-.:/;,\n\~]+)\]' % letters).search
+ ):
+ r = expr(s)
+ if r:
+ start, end = r.span(1)
+ return (StructuredTextXref(s[start:end]), start-1, end+1)
+ else:
+ return None
+
+
+
+
diff --git a/wxPython/samples/stxview/StructuredText/HTMLClass.py b/wxPython/samples/stxview/StructuredText/HTMLClass.py
index d5c03d8357..951aec4c97 100644
--- a/wxPython/samples/stxview/StructuredText/HTMLClass.py
+++ b/wxPython/samples/stxview/StructuredText/HTMLClass.py
@@ -84,6 +84,7 @@
##############################################################################
from string import join, split, find
+from cgi import escape
import re, sys, ST
class HTMLClass:
@@ -172,34 +173,34 @@ class HTMLClass:
def bullet(self, doc, level, output):
p=doc.getPreviousSibling()
if p is None or p.getNodeName() is not doc.getNodeName():
- output('
\n')
+ output('\n
\n')
output('
')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
n=doc.getNextSibling()
output('
\n')
if n is None or n.getNodeName() is not doc.getNodeName():
- output('
\n')
+ output('\n
\n')
def numbered(self, doc, level, output):
p=doc.getPreviousSibling()
if p is None or p.getNodeName() is not doc.getNodeName():
- output('\n')
+ output('\n\n')
output('
')
for c in doc.getChildNodes():
getattr(self, self.element_types[c.getNodeName()])(c, level, output)
n=doc.getNextSibling()
output('
\n')
if n is None or n.getNodeName() is not doc.getNodeName():
- output('\n')
+ output('\n\n')
def example(self, doc, level, output):
i=0
for c in doc.getChildNodes():
if i==0:
- output('
" % 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("