Merge branch 'release/2.3.4'

CHANGELOG.textile

@@ -1,5 +1,16 @@
 h1. Textile Changelog
 
+h2. Version 2.3.4
+* Bugfix: fix an issue with extended block code
+* Remove misplaced shebang on non-callable files.
+* Packaging: Add test-command to setup.py directly.
+* Packaging: Included the tests/ directory for source-tarballs, useful for packaging checks. ("#33":https://github.com/textile/python-textile/issues/33)
+* Add a cli tool `pytextile` which takes textile input and prints html output.  See `pytextile -h` for details.
+
+h2. Version 2.3.3
+* Bugfix: Unicode in URL titles no longer break everything ("#30":https://github.com/textile/python-textile/issues/30)
+* Display DeprecationWarning when using textile on Python 2.6.
+
 h2. Version 2.3.2
 * Bugfix: properly handle @":"@ as text, not a link.
 

MANIFEST.in

@@ -0,0 +1,11 @@
+exclude .gitignore
+exclude TODO.textile
+exclude .travis.yml
+include CHANGELOG.textile
+include CONTRIBUTORS.txt
+include .coveragerc
+include LICENSE.txt
+include MANIFEST.in
+include pytest.ini
+include README.textile
+include requirements.txt

README.textile

@@ -14,9 +14,7 @@ Optional dependencies include:
 
 h2. Usage
 
-<pre>
-<code>
->>> import textile
+bc.. import textile
 >>> s = """
 ... _This_ is a *test.*
 ...
@@ -38,8 +36,6 @@ h2. Usage
 
 	<p>Link to <a href="http://slashdot.org/">Slashdot</a></p>
 >>>
-</code>
-</pre>
 
 h3. Notes:
 

setup.py

@@ -1,6 +1,7 @@
 from setuptools import setup, find_packages
 import os
 import sys
+import pytest
 
 def get_version():
     basedir = os.path.dirname(__file__)
@@ -13,6 +14,8 @@ def get_version():
 setup(
     name='textile',
     version=get_version(),
+    author='Dennis Burke',
+    author_email='[email protected]',
     description='Textile processing for python.',
     url='http://github.com/textile/python-textile',
     packages=find_packages(),
@@ -40,8 +43,10 @@ def get_version():
         ':python_version=="2.6"': ['ordereddict>=1.1'],
         'develop': ['regex', 'pytest', 'pytest-cov'],
     },
+    entry_points={'console_scripts': ['pytextile=textile.__main__:main']},
     setup_requires=['pytest-runner'],
     tests_require=['pytest', 'pytest-cov'],
+    cmdclass = {'test': pytest},
     include_package_data=True,
     zip_safe=False,
 )

tests/fixtures/README.txt

@@ -0,0 +1,46 @@
+	<p><a href="https://travis-ci.org/textile/python-textile"><img alt="" src="https://travis-ci.org/textile/python-textile.svg" /></a> <a href="https://coveralls.io/github/textile/python-textile?branch=master"><img alt="" src="https://coveralls.io/repos/github/textile/python-textile/badge.svg" /></a> <a href="https://codecov.io/github/textile/python-textile"><img alt="" src="https://codecov.io/github/textile/python-textile/coverage.svg" /></a></p>
+
+	<h1>python-textile</h1>
+
+	<p>python-textile is a Python port of <a href="http://txstyle.org/">Textile</a>, Dean Allen&#8217;s humane web text generator.</p>
+
+	<h2>Installation</h2>
+
+	<p><code>pip install textile</code></p>
+
+	<p>Optional dependencies include:
+	<ul>
+		<li><a href="http://python-pillow.github.io/"><span class="caps">PIL</span>/Pillow</a> (for checking images size)</li>
+		<li><a href="https://pypi.python.org/pypi/regex">regex</a> (for faster unicode-aware string matching).</li>
+	</ul></p>
+
+	<h2>Usage</h2>
+
+<pre><code>import textile
+&gt;&gt;&gt; s = &quot;&quot;&quot;
+... _This_ is a *test.*
+...
+... * One
+... * Two
+... * Three
+...
+... Link to &quot;Slashdot&quot;:http://slashdot.org/
+... &quot;&quot;&quot;
+&gt;&gt;&gt; html = textile.textile(s)
+&gt;&gt;&gt; print html
+	&lt;p&gt;&lt;em&gt;This&lt;/em&gt; is a &lt;strong&gt;test.&lt;/strong&gt;&lt;/p&gt;
+
+	&lt;ul&gt;
+		&lt;li&gt;One&lt;/li&gt;
+		&lt;li&gt;Two&lt;/li&gt;
+		&lt;li&gt;Three&lt;/li&gt;
+	&lt;/ul&gt;
+
+	&lt;p&gt;Link to &lt;a href=&quot;http://slashdot.org/&quot;&gt;Slashdot&lt;/a&gt;&lt;/p&gt;
+&gt;&gt;&gt;</code></pre>
+
+	<h3>Notes:</h3>
+
+	<ul>
+		<li>Active development supports Python 2.6 or later (including Python 3.2+).</li>
+	</ul>

tests/test_block.py

@@ -1,6 +1,6 @@
 from __future__ import unicode_literals
 
-from textile import Textile
+import textile
 from textile.objects import Block
 
 try:
@@ -9,7 +9,7 @@
     from ordereddict import OrderedDict
 
 def test_block():
-    t = Textile()
+    t = textile.Textile()
     result = t.block('h1. foobar baby')
     expect = '\t<h1>foobar baby</h1>'
     assert result == expect
@@ -41,9 +41,24 @@ def test_block():
     assert result == expect
 
 def test_block_tags_false():
-    t = Textile(block_tags=False)
+    t = textile.Textile(block_tags=False)
     assert t.block_tags is False
 
     result = t.parse('test')
     expect = 'test'
     assert result == expect
+
+def test_blockcode_extended():
+    input = 'bc.. text\nmoretext\n\nevenmoretext\n\nmoremoretext\n\np. test'
+    expect = '<pre><code>text\nmoretext\n\nevenmoretext\n\nmoremoretext</code></pre>\n\n\t<p>test</p>'
+    t = textile.Textile()
+    result = t.parse(input)
+    assert result == expect
+
+def test_blockcode_in_README():
+    with open('README.textile') as f:
+        readme = ''.join(f.readlines())
+    result = textile.textile(readme)
+    with open('tests/fixtures/README.txt') as f:
+        expect = ''.join(f.readlines())
+    assert result == expect

tests/test_cli.py

@@ -0,0 +1,16 @@
+import six
+import subprocess
+
+def test_console_script():
+    command = ['python', '-m', 'textile', 'README.textile']
+    try:
+        result = subprocess.check_output(command)
+    except AttributeError:
+        command[2] = 'textile.__main__'
+        result = subprocess.Popen(command,
+                stdout=subprocess.PIPE).communicate()[0]
+    with open('tests/fixtures/README.txt') as f:
+        expect = ''.join(f.readlines())
+    if type(result) == bytes:
+        result = result.decode('utf-8')
+    assert result == expect

tests/test_github_issues.py

@@ -79,3 +79,9 @@ def parseWapProfile(self, url):
 
 \t<p>Of course there&#8217;s a lot more error handling to do (and useful data to glean off the <a href="XML"><span class="caps">XML</span></a>), but being able to cut through all the usual parsing crap is immensely gratifying.</p>""")
     assert result == expect
+
+def test_github_issue_30():
+    text ='"Tëxtíle (Tëxtíle)":http://lala.com'
+    result = textile.textile(text)
+    expect = '\t<p><a href="http://lala.com" title="Tëxtíle">Tëxtíle</a></p>'
+    assert result == expect

tests/test_values.py

@@ -150,7 +150,7 @@
 
     ('<script>alert("hello");</script>', '\t<p><script>alert(&#8220;hello&#8221;);</script></p>'),
 
-    ('pre.. Hello\n\nHello Again\n\np. normal text', '<pre>Hello\n\nHello Again\n</pre>\n\n\t<p>normal text</p>'),
+    ('pre.. Hello\n\nHello Again\n\np. normal text', '<pre>Hello\n\nHello Again</pre>\n\n\t<p>normal text</p>'),
 
     ('<pre>this is in a pre tag</pre>', '<pre>this is in a pre tag</pre>'),
 
@@ -180,7 +180,7 @@
 
     ('h2. A header\n\n\n\n\n\nsome text', '\t<h2>A header</h2>\n\n\t<p>some text</p>'),
 
-    ('pre.. foo bar baz\nquux', '<pre>foo bar baz\nquux\n</pre>'),
+    ('pre.. foo bar baz\nquux', '<pre>foo bar baz\nquux</pre>'),
 
     ('line of text\n\n    leading spaces',
      '\t<p>line of text</p>\n\n    leading spaces'),
@@ -286,11 +286,11 @@
     # issue 2 escaping
     ('"foo ==(bar)==":#foobar', '\t<p><a href="#foobar">foo (bar)</a></p>'),
     # issue 14 newlines in extended pre blocks
-    ("pre.. Hello\n\nAgain\n\np. normal text", '<pre>Hello\n\nAgain\n</pre>\n\n\t<p>normal text</p>'),
+    ("pre.. Hello\n\nAgain\n\np. normal text", '<pre>Hello\n\nAgain</pre>\n\n\t<p>normal text</p>'),
     # url with parentheses
     ('"python":http://en.wikipedia.org/wiki/Python_(programming_language)', '\t<p><a href="http://en.wikipedia.org/wiki/Python_%28programming_language%29">python</a></p>'),
     # table with hyphen styles
-    ('table(linkblog-thumbnail).\n|(linkblog-thumbnail-cell). apple|bear|', '\t<table class="linkblog-thumbnail">\n\t\t<tr>\n\t\t\t<td class="linkblog-thumbnail-cell" style="vertical-align:middle;">apple</td>\n\t\t\t<td>bear</td>\n\t\t</tr>\n\t</table>'),
+    ('table(linkblog-thumbnail).\n|(linkblog-thumbnail-cell). apple|bear|', '\t<table class="linkblog-thumbnail">\n\t\t<tr>\n\t\t\t<td class="linkblog-thumbnail-cell">apple</td>\n\t\t\t<td>bear</td>\n\t\t</tr>\n\t</table>'),
     # issue 32 empty table cells
     ("|thing|||otherthing|", "\t<table>\n\t\t<tr>\n\t\t\t<td>thing</td>\n\t\t\t<td></td>\n\t\t\t<td></td>\n\t\t\t<td>otherthing</td>\n\t\t</tr>\n\t</table>"),
     # issue 36 link reference names http and https

textile/__init__.py

@@ -1,8 +1,20 @@
 from __future__ import unicode_literals
 
+import sys
+import warnings
+
 from .core import textile, textile_restricted, Textile
 from .version import VERSION
 
 __all__ = ['textile', 'textile_restricted']
 
 __version__ = VERSION
+
+
+if sys.version_info[:2] == (2, 6):
+    warnings.warn(
+        "Python 2.6 is no longer supported by the Python core team, please "
+        "upgrade your Python. A future version of textile will drop support "
+        "for Python 2.6",
+        DeprecationWarning
+    )

textile/__main__.py

@@ -0,0 +1,31 @@
+import argparse
+import sys
+import textile
+
+
+def main():
+    """A CLI tool in the style of python's json.tool.  In fact, this is mostly
+    copied directly from that module.  This allows us to create a stand-alone
+    tool as well as invoking it via `python -m textile`."""
+    prog = 'textile'
+    description = ('A simple command line interface for textile module '
+                   'to convert textile input to HTML output.  This script '
+                   'accepts input as a file or stdin and can write out to '
+                   'a file or stdout.')
+    parser = argparse.ArgumentParser(prog=prog, description=description)
+    parser.add_argument('infile', nargs='?', type=argparse.FileType(),
+                        help='a textile file to be converted')
+    parser.add_argument('outfile', nargs='?', type=argparse.FileType('w'),
+                        help='write the output of infile to outfile')
+    options = parser.parse_args()
+
+    infile = options.infile or sys.stdin
+    outfile = options.outfile or sys.stdout
+    with infile:
+        output = textile.textile(''.join(infile.readlines()))
+    with outfile:
+        outfile.write(output)
+
+
+if __name__ == '__main__': #pragma: no cover
+    main()

textile/core.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
@@ -421,6 +420,7 @@ def block(self, text):
         tag = 'p'
         atts = cite = graf = ext = ''
 
+        last_item_is_a_shelf = False
         out = []
 
         for line in text:
@@ -430,6 +430,16 @@ def block(self, text):
             match = re.search(pattern, line, flags=re.S | re.U)
             # tag specified on this line.
             if match:
+                # if we had a previous extended tag but not this time, close up
+                # the tag
+                if out:
+                    last_item_is_a_shelf = out[-1] in self.shelf
+                if ext and match.group('tag') and last_item_is_a_shelf:
+                    content = out.pop()
+                    content = generate_tag(block.inner_tag, content,
+                            block.inner_atts)
+                    out.append(generate_tag(block.outer_tag, content,
+                        block.outer_atts))
                 tag, atts, ext, cite, content = match.groups()
                 block = Block(self, **match.groupdict())
                 inner_block = generate_tag(block.inner_tag, block.content,
@@ -450,7 +460,7 @@ def block(self, text):
                 # if we're inside an extended block, add the text from the
                 # previous extension to the front
                 if ext:
-                    line = '{0}\n{1}'.format(out.pop(), line)
+                    line = '{0}\n\n{1}'.format(out.pop(), line)
                 whitespace = ' \t\n\r\f\v'
                 if ext or not line[0] in whitespace:
                     block = Block(self, tag, atts, ext, cite, line)
@@ -459,6 +469,8 @@ def block(self, text):
                     else:
                         line = generate_tag(block.outer_tag, block.content,
                                 block.outer_atts)
+                        if block.inner_tag == 'code':
+                            line = block.content
                         if block.outer_tag != 'pre' and not has_raw_text(line):
                             line = "\t{0}".format(line)
                 else:
@@ -874,7 +886,10 @@ def _casesdefault(c, pop, popped, url_chars, counts, pre):
         url = self.shelveURL(self.encode_url(urlunsplit(uri_parts)))
         attributes = parse_attributes(atts)
         if title:
-            attributes['title'] = title
+            # if the title contains unicode data, it is annoying to get Python
+            # 2.6 and all the latter versions working properly.  But shelving
+            # the title is a quick and dirty solution.
+            attributes['title'] = self.shelve(title)
         attributes['href'] = url
         if self.rel:
             attributes['rel'] = self.rel

textile/objects/block.py

@@ -99,8 +99,10 @@ def process(self):
             i_tag = ''
             if self.tag == 'bc':
                 i_tag = 'code'
-            self.content = self.textile.shelve(encode_html('{0}\n'.format(
-                self.content.rstrip("\n"))))
+            content = encode_html(self.content)
+            if not self.ext:
+                content = '{0}\n'.format(content)
+            self.content = self.textile.shelve(content)
             self.outer_tag = 'pre'
             self.outer_atts = self.attributes
             self.inner_tag = i_tag

textile/regex_strings.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 

textile/utils.py

@@ -50,24 +50,24 @@ def generate_tag(tag, content, attributes=None):
     content are strings, the attributes argument is a dictionary.  As
     a convenience, if the content is ' /', a self-closing tag is generated."""
     content = six.text_type(content)
-    element = ElementTree.Element(tag, attrib=attributes)
     enc = 'unicode'
     if six.PY2:
         enc = 'UTF-8'
     if not tag:
         return content
+    element = ElementTree.Element(tag, attrib=attributes)
     # FIXME: Kind of an ugly hack.  There *must* be a cleaner way.  I tried
-    # adding text by assigning it to a.text.  That results in non-ascii text
-    # being html-entity encoded.  Not bad, but not entirely matching
-    # php-textile either.
+    # adding text by assigning it to element_tag.text.  That results in
+    # non-ascii text being html-entity encoded.  Not bad, but not entirely
+    # matching php-textile either.
     try:
         element_tag = ElementTree.tostringlist(element, encoding=enc,
                 method='html')
         element_tag.insert(len(element_tag) - 1, content)
         element_text = ''.join(element_tag)
     except AttributeError:
         # Python 2.6 doesn't have the tostringlist method, so we have to treat
-        # it different.
+        # it differently.
         element_tag = ElementTree.tostring(element, encoding=enc)
         element_text = re.sub(r"<\?xml version='1.0' encoding='UTF-8'\?>\n",
                 '', element_tag)
@@ -143,7 +143,7 @@ def parse_attributes(block_attributes, element=None, include_id=True):
             rowspan = m.group(1)
 
     if element == 'td' or element == 'tr':
-        m = re.search(r'({0})'.format(valign_re_s), matched)
+        m = re.search(r'(^{0})'.format(valign_re_s), matched)
         if m:
             style.append("vertical-align:{0}".format(vAlign[m.group(1)]))
 

textile/version.py

@@ -1 +1 @@
-VERSION = '2.3.2'
+VERSION = '2.3.4'