You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
1014 lines
39 KiB
1014 lines
39 KiB
#!/usr/bin/python
|
|
# -*- coding: utf-8 -*-
|
|
|
|
# :Id: $Id: smartquotes.py 8376 2019-08-27 19:49:29Z milde $
|
|
# :Copyright: © 2010 Günter Milde,
|
|
# original `SmartyPants`_: © 2003 John Gruber
|
|
# smartypants.py: © 2004, 2007 Chad Miller
|
|
# :Maintainer: docutils-develop@lists.sourceforge.net
|
|
# :License: Released under the terms of the `2-Clause BSD license`_, in short:
|
|
#
|
|
# Copying and distribution of this file, with or without modification,
|
|
# are permitted in any medium without royalty provided the copyright
|
|
# notices and this notice are preserved.
|
|
# This file is offered as-is, without any warranty.
|
|
#
|
|
# .. _2-Clause BSD license: http://www.spdx.org/licenses/BSD-2-Clause
|
|
|
|
|
|
r"""
|
|
=========================
|
|
Smart Quotes for Docutils
|
|
=========================
|
|
|
|
Synopsis
|
|
========
|
|
|
|
"SmartyPants" is a free web publishing plug-in for Movable Type, Blosxom, and
|
|
BBEdit that easily translates plain ASCII punctuation characters into "smart"
|
|
typographic punctuation characters.
|
|
|
|
``smartquotes.py`` is an adaption of "SmartyPants" to Docutils_.
|
|
|
|
* Using Unicode instead of HTML entities for typographic punctuation
|
|
characters, it works for any output format that supports Unicode.
|
|
* Supports `language specific quote characters`__.
|
|
|
|
__ http://en.wikipedia.org/wiki/Non-English_usage_of_quotation_marks
|
|
|
|
|
|
Authors
|
|
=======
|
|
|
|
`John Gruber`_ did all of the hard work of writing this software in Perl for
|
|
`Movable Type`_ and almost all of this useful documentation. `Chad Miller`_
|
|
ported it to Python to use with Pyblosxom_.
|
|
Adapted to Docutils_ by Günter Milde.
|
|
|
|
Additional Credits
|
|
==================
|
|
|
|
Portions of the SmartyPants original work are based on Brad Choate's nifty
|
|
MTRegex plug-in. `Brad Choate`_ also contributed a few bits of source code to
|
|
this plug-in. Brad Choate is a fine hacker indeed.
|
|
|
|
`Jeremy Hedley`_ and `Charles Wiltgen`_ deserve mention for exemplary beta
|
|
testing of the original SmartyPants.
|
|
|
|
`Rael Dornfest`_ ported SmartyPants to Blosxom.
|
|
|
|
.. _Brad Choate: http://bradchoate.com/
|
|
.. _Jeremy Hedley: http://antipixel.com/
|
|
.. _Charles Wiltgen: http://playbacktime.com/
|
|
.. _Rael Dornfest: http://raelity.org/
|
|
|
|
|
|
Copyright and License
|
|
=====================
|
|
|
|
SmartyPants_ license (3-Clause BSD license):
|
|
|
|
Copyright (c) 2003 John Gruber (http://daringfireball.net/)
|
|
All rights reserved.
|
|
|
|
Redistribution and use in source and binary forms, with or without
|
|
modification, are permitted provided that the following conditions are
|
|
met:
|
|
|
|
* Redistributions of source code must retain the above copyright
|
|
notice, this list of conditions and the following disclaimer.
|
|
|
|
* 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.
|
|
|
|
* Neither the name "SmartyPants" nor the names of its contributors
|
|
may be used to endorse or promote products derived from this
|
|
software without specific prior written permission.
|
|
|
|
This software is provided by the copyright holders and contributors
|
|
"as is" and any express 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 the copyright
|
|
owner or 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.
|
|
|
|
smartypants.py license (2-Clause BSD license):
|
|
|
|
smartypants.py is a derivative work of SmartyPants.
|
|
|
|
Redistribution and use in source and binary forms, with or without
|
|
modification, are permitted provided that the following conditions are
|
|
met:
|
|
|
|
* Redistributions of source code must retain the above copyright
|
|
notice, this list of conditions and the following disclaimer.
|
|
|
|
* 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.
|
|
|
|
This software is provided by the copyright holders and contributors
|
|
"as is" and any express 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 the copyright
|
|
owner or 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.
|
|
|
|
.. _John Gruber: http://daringfireball.net/
|
|
.. _Chad Miller: http://web.chad.org/
|
|
|
|
.. _Pyblosxom: http://pyblosxom.bluesock.org/
|
|
.. _SmartyPants: http://daringfireball.net/projects/smartypants/
|
|
.. _Movable Type: http://www.movabletype.org/
|
|
.. _2-Clause BSD license: http://www.spdx.org/licenses/BSD-2-Clause
|
|
.. _Docutils: http://docutils.sf.net/
|
|
|
|
Description
|
|
===========
|
|
|
|
SmartyPants can perform the following transformations:
|
|
|
|
- Straight quotes ( " and ' ) into "curly" quote characters
|
|
- Backticks-style quotes (\`\`like this'') into "curly" quote characters
|
|
- Dashes (``--`` and ``---``) into en- and em-dash entities
|
|
- Three consecutive dots (``...`` or ``. . .``) into an ellipsis entity
|
|
|
|
This means you can write, edit, and save your posts using plain old
|
|
ASCII straight quotes, plain dashes, and plain dots, but your published
|
|
posts (and final HTML output) will appear with smart quotes, em-dashes,
|
|
and proper ellipses.
|
|
|
|
SmartyPants does not modify characters within ``<pre>``, ``<code>``, ``<kbd>``,
|
|
``<math>`` or ``<script>`` tag blocks. Typically, these tags are used to
|
|
display text where smart quotes and other "smart punctuation" would not be
|
|
appropriate, such as source code or example markup.
|
|
|
|
|
|
Backslash Escapes
|
|
=================
|
|
|
|
If you need to use literal straight quotes (or plain hyphens and periods),
|
|
`smartquotes` accepts the following backslash escape sequences to force
|
|
ASCII-punctuation. Mind, that you need two backslashes as Docutils expands it,
|
|
too.
|
|
|
|
======== =========
|
|
Escape Character
|
|
======== =========
|
|
``\\`` \\
|
|
``\\"`` \\"
|
|
``\\'`` \\'
|
|
``\\.`` \\.
|
|
``\\-`` \\-
|
|
``\\``` \\`
|
|
======== =========
|
|
|
|
This is useful, for example, when you want to use straight quotes as
|
|
foot and inch marks: 6\\'2\\" tall; a 17\\" iMac.
|
|
|
|
|
|
Caveats
|
|
=======
|
|
|
|
Why You Might Not Want to Use Smart Quotes in Your Weblog
|
|
---------------------------------------------------------
|
|
|
|
For one thing, you might not care.
|
|
|
|
Most normal, mentally stable individuals do not take notice of proper
|
|
typographic punctuation. Many design and typography nerds, however, break
|
|
out in a nasty rash when they encounter, say, a restaurant sign that uses
|
|
a straight apostrophe to spell "Joe's".
|
|
|
|
If you're the sort of person who just doesn't care, you might well want to
|
|
continue not caring. Using straight quotes -- and sticking to the 7-bit
|
|
ASCII character set in general -- is certainly a simpler way to live.
|
|
|
|
Even if you *do* care about accurate typography, you still might want to
|
|
think twice before educating the quote characters in your weblog. One side
|
|
effect of publishing curly quote characters is that it makes your
|
|
weblog a bit harder for others to quote from using copy-and-paste. What
|
|
happens is that when someone copies text from your blog, the copied text
|
|
contains the 8-bit curly quote characters (as well as the 8-bit characters
|
|
for em-dashes and ellipses, if you use these options). These characters
|
|
are not standard across different text encoding methods, which is why they
|
|
need to be encoded as characters.
|
|
|
|
People copying text from your weblog, however, may not notice that you're
|
|
using curly quotes, and they'll go ahead and paste the unencoded 8-bit
|
|
characters copied from their browser into an email message or their own
|
|
weblog. When pasted as raw "smart quotes", these characters are likely to
|
|
get mangled beyond recognition.
|
|
|
|
That said, my own opinion is that any decent text editor or email client
|
|
makes it easy to stupefy smart quote characters into their 7-bit
|
|
equivalents, and I don't consider it my problem if you're using an
|
|
indecent text editor or email client.
|
|
|
|
|
|
Algorithmic Shortcomings
|
|
------------------------
|
|
|
|
One situation in which quotes will get curled the wrong way is when
|
|
apostrophes are used at the start of leading contractions. For example::
|
|
|
|
'Twas the night before Christmas.
|
|
|
|
In the case above, SmartyPants will turn the apostrophe into an opening
|
|
single-quote, when in fact it should be the `right single quotation mark`
|
|
character which is also "the preferred character to use for apostrophe"
|
|
(Unicode). I don't think this problem can be solved in the general case --
|
|
every word processor I've tried gets this wrong as well. In such cases, it's
|
|
best to use the proper character for closing single-quotes (’) by hand.
|
|
|
|
In English, the same character is used for apostrophe and closing single
|
|
quote (both plain and "smart" ones). For other locales (French, Italean,
|
|
Swiss, ...) "smart" single closing quotes differ from the curly apostrophe.
|
|
|
|
.. class:: language-fr
|
|
|
|
Il dit : "C'est 'super' !"
|
|
|
|
If the apostrophe is used at the end of a word, it cannot be distinguished
|
|
from a single quote by the algorithm. Therefore, a text like::
|
|
|
|
.. class:: language-de-CH
|
|
|
|
"Er sagt: 'Ich fass' es nicht.'"
|
|
|
|
will get a single closing guillemet instead of an apostrophe.
|
|
|
|
This can be prevented by use use of the curly apostrophe character (’) in
|
|
the source::
|
|
|
|
- "Er sagt: 'Ich fass' es nicht.'"
|
|
+ "Er sagt: 'Ich fass’ es nicht.'"
|
|
|
|
|
|
Version History
|
|
===============
|
|
|
|
1.8.1 2017-10-25
|
|
- Use open quote after Unicode whitespace, ZWSP, and ZWNJ.
|
|
- Code cleanup.
|
|
|
|
1.8: 2017-04-24
|
|
- Command line front-end.
|
|
|
|
1.7.1: 2017-03-19
|
|
- Update and extend language-dependent quotes.
|
|
- Differentiate apostrophe from single quote.
|
|
|
|
1.7: 2012-11-19
|
|
- Internationalization: language-dependent quotes.
|
|
|
|
1.6.1: 2012-11-06
|
|
- Refactor code, code cleanup,
|
|
- `educate_tokens()` generator as interface for Docutils.
|
|
|
|
1.6: 2010-08-26
|
|
- Adaption to Docutils:
|
|
- Use Unicode instead of HTML entities,
|
|
- Remove code special to pyblosxom.
|
|
|
|
1.5_1.6: Fri, 27 Jul 2007 07:06:40 -0400
|
|
- Fixed bug where blocks of precious unalterable text was instead
|
|
interpreted. Thanks to Le Roux and Dirk van Oosterbosch.
|
|
|
|
1.5_1.5: Sat, 13 Aug 2005 15:50:24 -0400
|
|
- Fix bogus magical quotation when there is no hint that the
|
|
user wants it, e.g., in "21st century". Thanks to Nathan Hamblen.
|
|
- Be smarter about quotes before terminating numbers in an en-dash'ed
|
|
range.
|
|
|
|
1.5_1.4: Thu, 10 Feb 2005 20:24:36 -0500
|
|
- Fix a date-processing bug, as reported by jacob childress.
|
|
- Begin a test-suite for ensuring correct output.
|
|
- Removed import of "string", since I didn't really need it.
|
|
(This was my first every Python program. Sue me!)
|
|
|
|
1.5_1.3: Wed, 15 Sep 2004 18:25:58 -0400
|
|
- Abort processing if the flavour is in forbidden-list. Default of
|
|
[ "rss" ] (Idea of Wolfgang SCHNERRING.)
|
|
- Remove stray virgules from en-dashes. Patch by Wolfgang SCHNERRING.
|
|
|
|
1.5_1.2: Mon, 24 May 2004 08:14:54 -0400
|
|
- Some single quotes weren't replaced properly. Diff-tesuji played
|
|
by Benjamin GEIGER.
|
|
|
|
1.5_1.1: Sun, 14 Mar 2004 14:38:28 -0500
|
|
- Support upcoming pyblosxom 0.9 plugin verification feature.
|
|
|
|
1.5_1.0: Tue, 09 Mar 2004 08:08:35 -0500
|
|
- Initial release
|
|
"""
|
|
from __future__ import print_function
|
|
|
|
options = r"""
|
|
Options
|
|
=======
|
|
|
|
Numeric values are the easiest way to configure SmartyPants' behavior:
|
|
|
|
:0: Suppress all transformations. (Do nothing.)
|
|
|
|
:1: Performs default SmartyPants transformations: quotes (including
|
|
\`\`backticks'' -style), em-dashes, and ellipses. "``--``" (dash dash)
|
|
is used to signify an em-dash; there is no support for en-dashes
|
|
|
|
:2: Same as smarty_pants="1", except that it uses the old-school typewriter
|
|
shorthand for dashes: "``--``" (dash dash) for en-dashes, "``---``"
|
|
(dash dash dash)
|
|
for em-dashes.
|
|
|
|
:3: Same as smarty_pants="2", but inverts the shorthand for dashes:
|
|
"``--``" (dash dash) for em-dashes, and "``---``" (dash dash dash) for
|
|
en-dashes.
|
|
|
|
:-1: Stupefy mode. Reverses the SmartyPants transformation process, turning
|
|
the characters produced by SmartyPants into their ASCII equivalents.
|
|
E.g. the LEFT DOUBLE QUOTATION MARK (“) is turned into a simple
|
|
double-quote (\"), "—" is turned into two dashes, etc.
|
|
|
|
|
|
The following single-character attribute values can be combined to toggle
|
|
individual transformations from within the smarty_pants attribute. For
|
|
example, ``"1"`` is equivalent to ``"qBde"``.
|
|
|
|
:q: Educates normal quote characters: (") and (').
|
|
|
|
:b: Educates \`\`backticks'' -style double quotes.
|
|
|
|
:B: Educates \`\`backticks'' -style double quotes and \`single' quotes.
|
|
|
|
:d: Educates em-dashes.
|
|
|
|
:D: Educates em-dashes and en-dashes, using old-school typewriter shorthand:
|
|
(dash dash) for en-dashes, (dash dash dash) for em-dashes.
|
|
|
|
:i: Educates em-dashes and en-dashes, using inverted old-school typewriter
|
|
shorthand: (dash dash) for em-dashes, (dash dash dash) for en-dashes.
|
|
|
|
:e: Educates ellipses.
|
|
|
|
:w: Translates any instance of ``"`` into a normal double-quote character.
|
|
This should be of no interest to most people, but of particular interest
|
|
to anyone who writes their posts using Dreamweaver, as Dreamweaver
|
|
inexplicably uses this entity to represent a literal double-quote
|
|
character. SmartyPants only educates normal quotes, not entities (because
|
|
ordinarily, entities are used for the explicit purpose of representing the
|
|
specific character they represent). The "w" option must be used in
|
|
conjunction with one (or both) of the other quote options ("q" or "b").
|
|
Thus, if you wish to apply all SmartyPants transformations (quotes, en-
|
|
and em-dashes, and ellipses) and also translate ``"`` entities into
|
|
regular quotes so SmartyPants can educate them, you should pass the
|
|
following to the smarty_pants attribute:
|
|
"""
|
|
|
|
|
|
default_smartypants_attr = "1"
|
|
|
|
|
|
import re, sys
|
|
|
|
class smartchars(object):
|
|
"""Smart quotes and dashes
|
|
"""
|
|
|
|
endash = u'–' # "–" EN DASH
|
|
emdash = u'—' # "—" EM DASH
|
|
ellipsis = u'…' # "…" HORIZONTAL ELLIPSIS
|
|
apostrophe = u'’' # "’" RIGHT SINGLE QUOTATION MARK
|
|
|
|
# quote characters (language-specific, set in __init__())
|
|
# [1] http://en.wikipedia.org/wiki/Non-English_usage_of_quotation_marks
|
|
# [2] http://de.wikipedia.org/wiki/Anf%C3%BChrungszeichen#Andere_Sprachen
|
|
# [3] https://fr.wikipedia.org/wiki/Guillemet
|
|
# [4] http://typographisme.net/post/Les-espaces-typographiques-et-le-web
|
|
# [5] http://www.btb.termiumplus.gc.ca/tpv2guides/guides/redac/index-fra.html
|
|
# [6] https://en.wikipedia.org/wiki/Hebrew_punctuation#Quotation_marks
|
|
# [7] http://www.tustep.uni-tuebingen.de/bi/bi00/bi001t1-anfuehrung.pdf
|
|
# [8] http://www.korrekturavdelingen.no/anforselstegn.htm
|
|
# [9] Typografisk håndbok. Oslo: Spartacus. 2000. s. 67. ISBN 8243001530.
|
|
# [10] http://www.typografi.org/sitat/sitatart.html
|
|
#
|
|
# See also configuration option "smartquote-locales".
|
|
quotes = {'af': u'“”‘’',
|
|
'af-x-altquot': u'„”‚’',
|
|
'bg': u'„“‚‘', # Bulgarian, https://bg.wikipedia.org/wiki/Кавички
|
|
'ca': u'«»“”',
|
|
'ca-x-altquot': u'“”‘’',
|
|
'cs': u'„“‚‘',
|
|
'cs-x-altquot': u'»«›‹',
|
|
'da': u'»«›‹',
|
|
'da-x-altquot': u'„“‚‘',
|
|
# 'da-x-altquot2': u'””’’',
|
|
'de': u'„“‚‘',
|
|
'de-x-altquot': u'»«›‹',
|
|
'de-ch': u'«»‹›',
|
|
'el': u'«»“”',
|
|
'en': u'“”‘’',
|
|
'en-uk-x-altquot': u'‘’“”', # Attention: " → ‘ and ' → “ !
|
|
'eo': u'“”‘’',
|
|
'es': u'«»“”',
|
|
'es-x-altquot': u'“”‘’',
|
|
'et': u'„“‚‘', # no secondary quote listed in
|
|
'et-x-altquot': u'«»‹›', # the sources above (wikipedia.org)
|
|
'eu': u'«»‹›',
|
|
'fi': u'””’’',
|
|
'fi-x-altquot': u'»»››',
|
|
'fr': (u'« ', u' »', u'“', u'”'), # full no-break space
|
|
'fr-x-altquot': (u'« ', u' »', u'“', u'”'), # narrow no-break space
|
|
'fr-ch': u'«»‹›',
|
|
'fr-ch-x-altquot': (u'« ', u' »', u'‹ ', u' ›'), # narrow no-break space, http://typoguide.ch/
|
|
'gl': u'«»“”',
|
|
'he': u'”“»«', # Hebrew is RTL, test position:
|
|
'he-x-altquot': u'„”‚’', # low quotation marks are opening.
|
|
# 'he-x-altquot': u'“„‘‚', # RTL: low quotation marks opening
|
|
'hr': u'„”‘’', # http://hrvatska-tipografija.com/polunavodnici/
|
|
'hr-x-altquot': u'»«›‹',
|
|
'hsb': u'„“‚‘',
|
|
'hsb-x-altquot': u'»«›‹',
|
|
'hu': u'„”«»',
|
|
'is': u'„“‚‘',
|
|
'it': u'«»“”',
|
|
'it-ch': u'«»‹›',
|
|
'it-x-altquot': u'“”‘’',
|
|
# 'it-x-altquot2': u'“„‘‚', # [7] in headlines
|
|
'ja': u'「」『』',
|
|
'ko': u'《》〈〉',
|
|
'lt': u'„“‚‘',
|
|
'lv': u'„“‚‘',
|
|
'mk': u'„“‚‘', # Macedonian, https://mk.wikipedia.org/wiki/Правопис_и_правоговор_на_македонскиот_јазик
|
|
'nl': u'“”‘’',
|
|
'nl-x-altquot': u'„”‚’',
|
|
# 'nl-x-altquot2': u'””’’',
|
|
'nb': u'«»’’', # Norsk bokmål (canonical form 'no')
|
|
'nn': u'«»’’', # Nynorsk [10]
|
|
'nn-x-altquot': u'«»‘’', # [8], [10]
|
|
# 'nn-x-altquot2': u'«»«»', # [9], [10
|
|
# 'nn-x-altquot3': u'„“‚‘', # [10]
|
|
'no': u'«»’’', # Norsk bokmål [10]
|
|
'no-x-altquot': u'«»‘’', # [8], [10]
|
|
# 'no-x-altquot2': u'«»«»', # [9], [10
|
|
# 'no-x-altquot3': u'„“‚‘', # [10]
|
|
'pl': u'„”«»',
|
|
'pl-x-altquot': u'«»‚’',
|
|
# 'pl-x-altquot2': u'„”‚’', # https://pl.wikipedia.org/wiki/Cudzys%C5%82%C3%B3w
|
|
'pt': u'«»“”',
|
|
'pt-br': u'“”‘’',
|
|
'ro': u'„”«»',
|
|
'ru': u'«»„“',
|
|
'sh': u'„”‚’', # Serbo-Croatian
|
|
'sh-x-altquot': u'»«›‹',
|
|
'sk': u'„“‚‘', # Slovak
|
|
'sk-x-altquot': u'»«›‹',
|
|
'sl': u'„“‚‘', # Slovenian
|
|
'sl-x-altquot': u'»«›‹',
|
|
'sq': u'«»‹›', # Albanian
|
|
'sq-x-altquot': u'“„‘‚',
|
|
'sr': u'„”’’',
|
|
'sr-x-altquot': u'»«›‹',
|
|
'sv': u'””’’',
|
|
'sv-x-altquot': u'»»››',
|
|
'tr': u'“”‘’',
|
|
'tr-x-altquot': u'«»‹›',
|
|
# 'tr-x-altquot2': u'“„‘‚', # [7] antiquated?
|
|
'uk': u'«»„“',
|
|
'uk-x-altquot': u'„“‚‘',
|
|
'zh-cn': u'“”‘’',
|
|
'zh-tw': u'「」『』',
|
|
}
|
|
|
|
def __init__(self, language='en'):
|
|
self.language = language
|
|
try:
|
|
(self.opquote, self.cpquote,
|
|
self.osquote, self.csquote) = self.quotes[language.lower()]
|
|
except KeyError:
|
|
self.opquote, self.cpquote, self.osquote, self.csquote = u'""\'\''
|
|
|
|
|
|
def smartyPants(text, attr=default_smartypants_attr, language='en'):
|
|
"""Main function for "traditional" use."""
|
|
|
|
return "".join([t for t in educate_tokens(tokenize(text),
|
|
attr, language)])
|
|
|
|
|
|
def educate_tokens(text_tokens, attr=default_smartypants_attr, language='en'):
|
|
"""Return iterator that "educates" the items of `text_tokens`.
|
|
"""
|
|
|
|
# Parse attributes:
|
|
# 0 : do nothing
|
|
# 1 : set all
|
|
# 2 : set all, using old school en- and em- dash shortcuts
|
|
# 3 : set all, using inverted old school en and em- dash shortcuts
|
|
#
|
|
# q : quotes
|
|
# b : backtick quotes (``double'' only)
|
|
# B : backtick quotes (``double'' and `single')
|
|
# d : dashes
|
|
# D : old school dashes
|
|
# i : inverted old school dashes
|
|
# e : ellipses
|
|
# w : convert " entities to " for Dreamweaver users
|
|
|
|
convert_quot = False # translate " entities into normal quotes?
|
|
do_dashes = False
|
|
do_backticks = False
|
|
do_quotes = False
|
|
do_ellipses = False
|
|
do_stupefy = False
|
|
|
|
# if attr == "0": # pass tokens unchanged (see below).
|
|
if attr == "1": # Do everything, turn all options on.
|
|
do_quotes = True
|
|
do_backticks = True
|
|
do_dashes = 1
|
|
do_ellipses = True
|
|
elif attr == "2":
|
|
# Do everything, turn all options on, use old school dash shorthand.
|
|
do_quotes = True
|
|
do_backticks = True
|
|
do_dashes = 2
|
|
do_ellipses = True
|
|
elif attr == "3":
|
|
# Do everything, use inverted old school dash shorthand.
|
|
do_quotes = True
|
|
do_backticks = True
|
|
do_dashes = 3
|
|
do_ellipses = True
|
|
elif attr == "-1": # Special "stupefy" mode.
|
|
do_stupefy = True
|
|
else:
|
|
if "q" in attr: do_quotes = True
|
|
if "b" in attr: do_backticks = True
|
|
if "B" in attr: do_backticks = 2
|
|
if "d" in attr: do_dashes = 1
|
|
if "D" in attr: do_dashes = 2
|
|
if "i" in attr: do_dashes = 3
|
|
if "e" in attr: do_ellipses = True
|
|
if "w" in attr: convert_quot = True
|
|
|
|
prev_token_last_char = " "
|
|
# Last character of the previous text token. Used as
|
|
# context to curl leading quote characters correctly.
|
|
|
|
for (ttype, text) in text_tokens:
|
|
|
|
# skip HTML and/or XML tags as well as emtpy text tokens
|
|
# without updating the last character
|
|
if ttype == 'tag' or not text:
|
|
yield text
|
|
continue
|
|
|
|
# skip literal text (math, literal, raw, ...)
|
|
if ttype == 'literal':
|
|
prev_token_last_char = text[-1:]
|
|
yield text
|
|
continue
|
|
|
|
last_char = text[-1:] # Remember last char before processing.
|
|
|
|
text = processEscapes(text)
|
|
|
|
if convert_quot:
|
|
text = re.sub('"', '"', text)
|
|
|
|
if do_dashes == 1:
|
|
text = educateDashes(text)
|
|
elif do_dashes == 2:
|
|
text = educateDashesOldSchool(text)
|
|
elif do_dashes == 3:
|
|
text = educateDashesOldSchoolInverted(text)
|
|
|
|
if do_ellipses:
|
|
text = educateEllipses(text)
|
|
|
|
# Note: backticks need to be processed before quotes.
|
|
if do_backticks:
|
|
text = educateBackticks(text, language)
|
|
|
|
if do_backticks == 2:
|
|
text = educateSingleBackticks(text, language)
|
|
|
|
if do_quotes:
|
|
# Replace plain quotes in context to prevent converstion to
|
|
# 2-character sequence in French.
|
|
context = prev_token_last_char.replace('"', ';').replace("'", ';')
|
|
text = educateQuotes(context+text, language)[1:]
|
|
|
|
if do_stupefy:
|
|
text = stupefyEntities(text, language)
|
|
|
|
# Remember last char as context for the next token
|
|
prev_token_last_char = last_char
|
|
|
|
text = processEscapes(text, restore=True)
|
|
|
|
yield text
|
|
|
|
|
|
|
|
def educateQuotes(text, language='en'):
|
|
"""
|
|
Parameter: - text string (unicode or bytes).
|
|
- language (`BCP 47` language tag.)
|
|
Returns: The `text`, with "educated" curly quote characters.
|
|
|
|
Example input: "Isn't this fun?"
|
|
Example output: “Isn’t this fun?“;
|
|
"""
|
|
|
|
smart = smartchars(language)
|
|
|
|
punct_class = r"""[!"#\$\%'()*+,-.\/:;<=>?\@\[\\\]\^_`{|}~]"""
|
|
close_class = r"""[^\ \t\r\n\[\{\(\-]"""
|
|
open_class = u'[\u200B\u200C]' # ZWSP, ZWNJ
|
|
dec_dashes = r"""–|—"""
|
|
|
|
# Special case if the very first character is a quote
|
|
# followed by punctuation at a non-word-break.
|
|
# Close the quotes by brute force:
|
|
text = re.sub(r"^'(?=%s\\B)" % (punct_class,), smart.csquote, text)
|
|
text = re.sub(r'^"(?=%s\\B)' % (punct_class,), smart.cpquote, text)
|
|
|
|
# Special case for double sets of quotes, e.g.:
|
|
# <p>He said, "'Quoted' words in a larger quote."</p>
|
|
text = re.sub(r""""'(?=\w)""", smart.opquote+smart.osquote, text)
|
|
text = re.sub(r"""'"(?=\w)""", smart.osquote+smart.opquote, text)
|
|
|
|
# Special case for decade abbreviations (the '80s):
|
|
if language.startswith('en'): # TODO similar cases in other languages?
|
|
text = re.sub(r"'(?=\d{2}s)", smart.apostrophe, text)
|
|
|
|
# Get most opening single quotes:
|
|
opening_single_quotes_regex = re.compile(u"""
|
|
(# ?<= # look behind fails: requires fixed-width pattern
|
|
\\s | # a whitespace char, or
|
|
%s | # another separating char, or
|
|
| # a non-breaking space entity, or
|
|
[\u2013 \u2014 ] | # literal dashes, or
|
|
-- | # dumb dashes, or
|
|
&[mn]dash; | # dash entities (named or
|
|
%s | # decimal or
|
|
&\\#x201[34]; # hex)
|
|
)
|
|
' # the quote
|
|
(?=\\w) # followed by a word character
|
|
""" % (open_class, dec_dashes), re.VERBOSE | re.UNICODE)
|
|
|
|
text = opening_single_quotes_regex.sub(r'\1'+smart.osquote, text)
|
|
|
|
# In many locales, single closing quotes are different from apostrophe:
|
|
if smart.csquote != smart.apostrophe:
|
|
apostrophe_regex = re.compile(r"(?<=(\w|\d))'(?=\w)", re.UNICODE)
|
|
text = apostrophe_regex.sub(smart.apostrophe, text)
|
|
# TODO: keep track of quoting level to recognize apostrophe in, e.g.,
|
|
# "Ich fass' es nicht."
|
|
|
|
closing_single_quotes_regex = re.compile(r"""
|
|
(?<=%s)
|
|
'
|
|
""" % close_class, re.VERBOSE)
|
|
text = closing_single_quotes_regex.sub(smart.csquote, text)
|
|
|
|
# Any remaining single quotes should be opening ones:
|
|
text = re.sub(r"""'""", smart.osquote, text)
|
|
|
|
# Get most opening double quotes:
|
|
opening_double_quotes_regex = re.compile(u"""
|
|
(
|
|
\\s | # a whitespace char, or
|
|
%s | # another separating char, or
|
|
| # a non-breaking space entity, or
|
|
[\u2013 \u2014 ] | # literal dashes, or
|
|
-- | # dumb dashes, or
|
|
&[mn]dash; | # dash entities (named or
|
|
%s | # decimal or
|
|
&\\#x201[34]; # hex)
|
|
)
|
|
" # the quote
|
|
(?=\\w) # followed by a word character
|
|
""" % (open_class, dec_dashes), re.VERBOSE | re.UNICODE)
|
|
|
|
text = opening_double_quotes_regex.sub(r'\1'+smart.opquote, text)
|
|
|
|
# Double closing quotes:
|
|
closing_double_quotes_regex = re.compile(r"""
|
|
(
|
|
(?<=%s)" | # char indicating the quote should be closing
|
|
"(?=\s) # whitespace behind
|
|
)
|
|
""" % (close_class,), re.VERBOSE | re.UNICODE)
|
|
text = closing_double_quotes_regex.sub(smart.cpquote, text)
|
|
|
|
# Any remaining quotes should be opening ones.
|
|
text = re.sub(r'"', smart.opquote, text)
|
|
|
|
return text
|
|
|
|
|
|
def educateBackticks(text, language='en'):
|
|
"""
|
|
Parameter: String (unicode or bytes).
|
|
Returns: The `text`, with ``backticks'' -style double quotes
|
|
translated into HTML curly quote entities.
|
|
Example input: ``Isn't this fun?''
|
|
Example output: “Isn't this fun?“;
|
|
"""
|
|
smart = smartchars(language)
|
|
|
|
text = re.sub(r"""``""", smart.opquote, text)
|
|
text = re.sub(r"""''""", smart.cpquote, text)
|
|
return text
|
|
|
|
|
|
def educateSingleBackticks(text, language='en'):
|
|
"""
|
|
Parameter: String (unicode or bytes).
|
|
Returns: The `text`, with `backticks' -style single quotes
|
|
translated into HTML curly quote entities.
|
|
|
|
Example input: `Isn't this fun?'
|
|
Example output: ‘Isn’t this fun?’
|
|
"""
|
|
smart = smartchars(language)
|
|
|
|
text = re.sub(r"""`""", smart.osquote, text)
|
|
text = re.sub(r"""'""", smart.csquote, text)
|
|
return text
|
|
|
|
|
|
def educateDashes(text):
|
|
"""
|
|
Parameter: String (unicode or bytes).
|
|
Returns: The `text`, with each instance of "--" translated to
|
|
an em-dash character.
|
|
"""
|
|
|
|
text = re.sub(r"""---""", smartchars.endash, text) # en (yes, backwards)
|
|
text = re.sub(r"""--""", smartchars.emdash, text) # em (yes, backwards)
|
|
return text
|
|
|
|
|
|
def educateDashesOldSchool(text):
|
|
"""
|
|
Parameter: String (unicode or bytes).
|
|
Returns: The `text`, with each instance of "--" translated to
|
|
an en-dash character, and each "---" translated to
|
|
an em-dash character.
|
|
"""
|
|
|
|
text = re.sub(r"""---""", smartchars.emdash, text)
|
|
text = re.sub(r"""--""", smartchars.endash, text)
|
|
return text
|
|
|
|
|
|
def educateDashesOldSchoolInverted(text):
|
|
"""
|
|
Parameter: String (unicode or bytes).
|
|
Returns: The `text`, with each instance of "--" translated to
|
|
an em-dash character, and each "---" translated to
|
|
an en-dash character. Two reasons why: First, unlike the
|
|
en- and em-dash syntax supported by
|
|
EducateDashesOldSchool(), it's compatible with existing
|
|
entries written before SmartyPants 1.1, back when "--" was
|
|
only used for em-dashes. Second, em-dashes are more
|
|
common than en-dashes, and so it sort of makes sense that
|
|
the shortcut should be shorter to type. (Thanks to Aaron
|
|
Swartz for the idea.)
|
|
"""
|
|
text = re.sub(r"""---""", smartchars.endash, text) # em
|
|
text = re.sub(r"""--""", smartchars.emdash, text) # en
|
|
return text
|
|
|
|
|
|
|
|
def educateEllipses(text):
|
|
"""
|
|
Parameter: String (unicode or bytes).
|
|
Returns: The `text`, with each instance of "..." translated to
|
|
an ellipsis character.
|
|
|
|
Example input: Huh...?
|
|
Example output: Huh…?
|
|
"""
|
|
|
|
text = re.sub(r"""\.\.\.""", smartchars.ellipsis, text)
|
|
text = re.sub(r"""\. \. \.""", smartchars.ellipsis, text)
|
|
return text
|
|
|
|
|
|
def stupefyEntities(text, language='en'):
|
|
"""
|
|
Parameter: String (unicode or bytes).
|
|
Returns: The `text`, with each SmartyPants character translated to
|
|
its ASCII counterpart.
|
|
|
|
Example input: “Hello — world.”
|
|
Example output: "Hello -- world."
|
|
"""
|
|
smart = smartchars(language)
|
|
|
|
text = re.sub(smart.endash, "-", text) # en-dash
|
|
text = re.sub(smart.emdash, "--", text) # em-dash
|
|
|
|
text = re.sub(smart.osquote, "'", text) # open single quote
|
|
text = re.sub(smart.csquote, "'", text) # close single quote
|
|
|
|
text = re.sub(smart.opquote, '"', text) # open double quote
|
|
text = re.sub(smart.cpquote, '"', text) # close double quote
|
|
|
|
text = re.sub(smart.ellipsis, '...', text)# ellipsis
|
|
|
|
return text
|
|
|
|
|
|
def processEscapes(text, restore=False):
|
|
r"""
|
|
Parameter: String (unicode or bytes).
|
|
Returns: The `text`, with after processing the following backslash
|
|
escape sequences. This is useful if you want to force a "dumb"
|
|
quote or other character to appear.
|
|
|
|
Escape Value
|
|
------ -----
|
|
\\ \
|
|
\" "
|
|
\' '
|
|
\. .
|
|
\- -
|
|
\` `
|
|
"""
|
|
replacements = ((r'\\', r'\'),
|
|
(r'\"', r'"'),
|
|
(r"\'", r'''),
|
|
(r'\.', r'.'),
|
|
(r'\-', r'-'),
|
|
(r'\`', r'`'))
|
|
if restore:
|
|
for (ch, rep) in replacements:
|
|
text = text.replace(rep, ch[1])
|
|
else:
|
|
for (ch, rep) in replacements:
|
|
text = text.replace(ch, rep)
|
|
|
|
return text
|
|
|
|
|
|
def tokenize(text):
|
|
"""
|
|
Parameter: String containing HTML markup.
|
|
Returns: An iterator that yields the tokens comprising the input
|
|
string. Each token is either a tag (possibly with nested,
|
|
tags contained therein, such as <a href="<MTFoo>">, or a
|
|
run of text between tags. Each yielded element is a
|
|
two-element tuple; the first is either 'tag' or 'text';
|
|
the second is the actual value.
|
|
|
|
Based on the _tokenize() subroutine from Brad Choate's MTRegex plugin.
|
|
<http://www.bradchoate.com/past/mtregex.php>
|
|
"""
|
|
|
|
pos = 0
|
|
length = len(text)
|
|
# tokens = []
|
|
|
|
depth = 6
|
|
nested_tags = "|".join(['(?:<(?:[^<>]',] * depth) + (')*>)' * depth)
|
|
#match = r"""(?: <! ( -- .*? -- \s* )+ > ) | # comments
|
|
# (?: <\? .*? \?> ) | # directives
|
|
# %s # nested tags """ % (nested_tags,)
|
|
tag_soup = re.compile(r"""([^<]*)(<[^>]*>)""")
|
|
|
|
token_match = tag_soup.search(text)
|
|
|
|
previous_end = 0
|
|
while token_match is not None:
|
|
if token_match.group(1):
|
|
yield ('text', token_match.group(1))
|
|
|
|
yield ('tag', token_match.group(2))
|
|
|
|
previous_end = token_match.end()
|
|
token_match = tag_soup.search(text, token_match.end())
|
|
|
|
if previous_end < len(text):
|
|
yield ('text', text[previous_end:])
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
import itertools
|
|
try:
|
|
import locale # module missing in Jython
|
|
locale.setlocale(locale.LC_ALL, '') # set to user defaults
|
|
defaultlanguage = locale.getdefaultlocale()[0]
|
|
except:
|
|
defaultlanguage = 'en'
|
|
|
|
# Normalize and drop unsupported subtags:
|
|
defaultlanguage = defaultlanguage.lower().replace('-', '_')
|
|
# split (except singletons, which mark the following tag as non-standard):
|
|
defaultlanguage = re.sub(r'_([a-zA-Z0-9])_', r'_\1-', defaultlanguage)
|
|
_subtags = [subtag for subtag in defaultlanguage.split('_')]
|
|
_basetag = _subtags.pop(0)
|
|
# find all combinations of subtags
|
|
for n in range(len(_subtags), 0, -1):
|
|
for tags in itertools.combinations(_subtags, n):
|
|
_tag = '-'.join((_basetag,)+tags)
|
|
if _tag in smartchars.quotes:
|
|
defaultlanguage = _tag
|
|
break
|
|
else:
|
|
if _basetag in smartchars.quotes:
|
|
defaultlanguage = _basetag
|
|
else:
|
|
defaultlanguage = 'en'
|
|
|
|
|
|
import argparse
|
|
parser = argparse.ArgumentParser(
|
|
description='Filter stdin making ASCII punctuation "smart".')
|
|
# parser.add_argument("text", help="text to be acted on")
|
|
parser.add_argument("-a", "--action", default="1",
|
|
help="what to do with the input (see --actionhelp)")
|
|
parser.add_argument("-e", "--encoding", default="utf8",
|
|
help="text encoding")
|
|
parser.add_argument("-l", "--language", default=defaultlanguage,
|
|
help="text language (BCP47 tag), "
|
|
"Default: %s"% defaultlanguage)
|
|
parser.add_argument("-q", "--alternative-quotes", action="store_true",
|
|
help="use alternative quote style")
|
|
parser.add_argument("--doc", action="store_true",
|
|
help="print documentation")
|
|
parser.add_argument("--actionhelp", action="store_true",
|
|
help="list available actions")
|
|
parser.add_argument("--stylehelp", action="store_true",
|
|
help="list available quote styles")
|
|
parser.add_argument("--test", action="store_true",
|
|
help="perform short self-test")
|
|
args = parser.parse_args()
|
|
|
|
if args.doc:
|
|
print(__doc__)
|
|
elif args.actionhelp:
|
|
print(options)
|
|
elif args.stylehelp:
|
|
print()
|
|
print("Available styles (primary open/close, secondary open/close)")
|
|
print("language tag quotes")
|
|
print("============ ======")
|
|
for key in sorted(smartchars.quotes.keys()):
|
|
print("%-14s %s" % (key, smartchars.quotes[key]))
|
|
elif args.test:
|
|
# Unit test output goes to stderr.
|
|
import unittest
|
|
|
|
class TestSmartypantsAllAttributes(unittest.TestCase):
|
|
# the default attribute is "1", which means "all".
|
|
def test_dates(self):
|
|
self.assertEqual(smartyPants("1440-80's"), u"1440-80’s")
|
|
self.assertEqual(smartyPants("1440-'80s"), u"1440-’80s")
|
|
self.assertEqual(smartyPants("1440---'80s"), u"1440–’80s")
|
|
self.assertEqual(smartyPants("1960's"), u"1960’s")
|
|
self.assertEqual(smartyPants("one two '60s"), u"one two ’60s")
|
|
self.assertEqual(smartyPants("'60s"), u"’60s")
|
|
|
|
def test_educated_quotes(self):
|
|
self.assertEqual(smartyPants('"Isn\'t this fun?"'), u'“Isn’t this fun?”')
|
|
|
|
def test_html_tags(self):
|
|
text = '<a src="foo">more</a>'
|
|
self.assertEqual(smartyPants(text), text)
|
|
|
|
suite = unittest.TestLoader().loadTestsFromTestCase(
|
|
TestSmartypantsAllAttributes)
|
|
unittest.TextTestRunner().run(suite)
|
|
|
|
else:
|
|
if args.alternative_quotes:
|
|
if '-x-altquot' in args.language:
|
|
args.language = args.language.replace('-x-altquot', '')
|
|
else:
|
|
args.language += '-x-altquot'
|
|
text = sys.stdin.read().decode(args.encoding)
|
|
print(smartyPants(text, attr=args.action,
|
|
language=args.language).encode(args.encoding))
|
|
|