Update of /cvsroot/docstring/dps/dps
In directory usw-pr-cvs1:/tmp/cvs-serv23805/dps/dps
Modified Files:
utils.py
Log Message:
- Added name -> id conversion, ``id()``.
- Updated extension attribute support.
Index: utils.py
===================================================================
RCS file: /cvsroot/docstring/dps/dps/utils.py,v
retrieving revision 1.18
retrieving revision 1.19
diff -C2 -d -r1.18 -r1.19
*** utils.py 13 Mar 2002 02:43:47 -0000 1.18
--- utils.py 16 Mar 2002 05:57:30 -0000 1.19
***************
*** 11,15 ****
"""
! import sys
import nodes
--- 11,15 ----
"""
! import sys, re
import nodes
***************
*** 184,188 ****
class ExtensionAttributeError(Exception): pass
! class BadAttributeLineError(ExtensionAttributeError): pass
class BadAttributeDataError(ExtensionAttributeError): pass
class DuplicateAttributeError(ExtensionAttributeError): pass
--- 184,188 ----
class ExtensionAttributeError(Exception): pass
! class BadAttributeError(ExtensionAttributeError): pass
class BadAttributeDataError(ExtensionAttributeError): pass
class DuplicateAttributeError(ExtensionAttributeError): pass
***************
*** 204,208 ****
function).
- `DuplicateAttributeError` for duplicate attributes.
! - `BadAttributeError` for input lines not enclosed in brackets.
- `BadAttributeDataError` for invalid attribute data (missing name,
missing data, bad quotes, etc.).
--- 204,208 ----
function).
- `DuplicateAttributeError` for duplicate attributes.
! - `BadAttributeError` for invalid fields.
- `BadAttributeDataError` for invalid attribute data (missing name,
missing data, bad quotes, etc.).
***************
*** 221,225 ****
:Exceptions:
! - `BadAttributeError` for input lines not enclosed in brackets.?
- `BadAttributeDataError` for invalid attribute data (missing name,
missing data, bad quotes, etc.).
--- 221,225 ----
:Exceptions:
! - `BadAttributeError` for invalid fields.
- `BadAttributeDataError` for invalid attribute data (missing name,
missing data, bad quotes, etc.).
***************
*** 232,241 ****
name = field[0].astext().lower()
body = field[1]
! if len(body) != 1 or not isinstance(body[0], nodes.paragraph) \
or len(body[0]) != 1 or not isinstance(body[0][0], nodes.Text):
raise BadAttributeDataError(
! 'extension attribute field body may consist of\n'
'a single paragraph only (attribute "%s")' % name)
! data = body[0][0].astext()
attlist.append((name, data))
return attlist
--- 232,244 ----
name = field[0].astext().lower()
body = field[1]
! if len(body) == 0:
! data = None
! elif len(body) > 1 or not isinstance(body[0], nodes.paragraph) \
or len(body[0]) != 1 or not isinstance(body[0][0], nodes.Text):
raise BadAttributeDataError(
! 'extension attribute field body may contain\n'
'a single paragraph only (attribute "%s")' % name)
! else:
! data = body[0][0].astext()
attlist.append((name, data))
return attlist
***************
*** 264,269 ****
try:
attributes[name] = convertor(value)
! except ValueError, detail:
! raise ValueError('(attribute "%s") %s' % (name, detail))
return attributes
--- 267,273 ----
try:
attributes[name] = convertor(value)
! except (ValueError, TypeError), detail:
! raise detail.__class__('(attribute "%s", value "%r") %s'
! % (name, value, detail))
return attributes
***************
*** 320,323 ****
--- 324,369 ----
"""Return a case- and whitespace-normalized name."""
return ' '.join(name.lower().split())
+
+ def id(string):
+ """
+ Convert `string` into an identifier and return it.
+
+ Docutils identifiers will conform to the regular expression
+ ``[a-z][-a-z0-9]*``. For CSS compatibility, identifiers (the "class" and
+ "id" attributes) should have no underscores, colons, or periods. Hyphens
+ may be used.
+
+ - The `HTML 4.01 spec`_ defines identifiers based on SGML tokens:
+
+ ID and NAME tokens must begin with a letter ([A-Za-z]) and may be
+ followed by any number of letters, digits ([0-9]), hyphens ("-"),
+ underscores ("_"), colons (":"), and periods (".").
+
+ - However the `CSS1 spec`_ defines identifiers based on the "name" token,
+ a tighter interpretation ("flex" tokenizer notation; "latin1" and
+ "escape" 8-bit characters have been replaced with entities)::
+
+ unicode \\[0-9a-f]{1,4}
+ latin1 [¡-ÿ]
+ escape {unicode}|\\[ -~¡-ÿ]
+ nmchar [-a-z0-9]|{latin1}|{escape}
+ name {nmchar}+
+
+ The CSS1 "nmchar" rule does not include underscores ("_"), colons (":"),
+ or periods ("."), therefore "class" and "id" attributes should not contain
+ these characters. They should be replaced with hyphens ("-"). Combined
+ with HTML's requirements (the first character must be a letter; no
+ "unicode", "latin1", or "escape" characters), this results in the
+ ``[a-z][-a-z0-9]*`` pattern.
+
+ .. _HTML 4.01 spec: http://www.w3.org/TR/html401
+ .. _CSS1 spec: http://www.w3.org/TR/REC-CSS1
+ """
+ id = non_id_chars.sub('-', normname(string))
+ id = non_id_at_ends.sub('', id)
+ return str(id)
+
+ non_id_chars = re.compile('[^a-z0-9]+')
+ non_id_at_ends = re.compile('^[-0-9]+|-+$')
def newdocument(languagecode='en', warninglevel=2, errorlevel=4,
|
