diff --git a/pelican/bloggenerator.py b/pelican/bloggenerator.py index dcccd86c..96dc1053 100644 --- a/pelican/bloggenerator.py +++ b/pelican/bloggenerator.py @@ -13,6 +13,7 @@ from feedgenerator import Atom1Feed # import the directives to have pygments support import rstdirectives +from utils import truncate_html_words ## Constants ########################################################## @@ -58,6 +59,13 @@ def generate_blog(path=None, theme=None, output_path=None, markup=None, # get the list of files to parse if not path: raise Exception('you need to specify a path to search the docs on !') + + # remove all the existing content from the output folder + try: + shutil.rmtree(os.path.join(output_path)) + except: + pass + files = [] for root, dirs, temp_files in os.walk(path, followlinks=True): files.extend([os.sep.join((root, f)) for f in temp_files @@ -119,14 +127,9 @@ def generate_blog(path=None, theme=None, output_path=None, markup=None, # copy static paths to output for path in context['STATIC_PATHS']: try: - real_output = os.path.join(output_path, path) - theme_path = os.path.join(theme, path) - - print "updating %s" % real_output - shutil.rmtree(real_output) - shutil.copytree(theme_path, real_output) - - except OSError as e: + shutil.copytree(os.path.join(theme, path), + os.path.join(output_path, path)) + except OSError: pass @@ -304,4 +307,4 @@ class Article(object): @property def summary(self): - return self.content + return truncate_html_words(self.content, 50) diff --git a/pelican/utils.py b/pelican/utils.py new file mode 100644 index 00000000..197bacd3 --- /dev/null +++ b/pelican/utils.py @@ -0,0 +1,67 @@ +import re + +def truncate_html_words(s, num, end_text='...'): + """Truncates HTML to a certain number of words (not counting tags and + comments). Closes opened tags if they were correctly closed in the given + html. Takes an optional argument of what should be used to notify that the + string has been truncated, defaulting to ellipsis (...). + + Newlines in the HTML are preserved. + From the django framework. + """ + length = int(num) + if length <= 0: + return u'' + html4_singlets = ('br', 'col', 'link', 'base', 'img', 'param', 'area', 'hr', 'input') + # Set up regular expressions + re_words = re.compile(r'&.*?;|<.*?>|(\w[\w-]*)', re.U) + re_tag = re.compile(r'<(/)?([^ ]+?)(?: (/)| .*?)?>') + # Count non-HTML words and keep note of open tags + pos = 0 + end_text_pos = 0 + words = 0 + open_tags = [] + while words <= length: + m = re_words.search(s, pos) + if not m: + # Checked through whole string + break + pos = m.end(0) + if m.group(1): + # It's an actual non-HTML word + words += 1 + if words == length: + end_text_pos = pos + continue + # Check for tag + tag = re_tag.match(m.group(0)) + if not tag or end_text_pos: + # Don't worry about non tags or tags after our truncate point + continue + closing_tag, tagname, self_closing = tag.groups() + tagname = tagname.lower() # Element names are always case-insensitive + if self_closing or tagname in html4_singlets: + pass + elif closing_tag: + # Check for match in open tags list + try: + i = open_tags.index(tagname) + except ValueError: + pass + else: + # SGML: An end tag closes, back to the matching start tag, all unclosed intervening start tags with omitted end tags + open_tags = open_tags[i+1:] + else: + # Add it to the start of the open tags list + open_tags.insert(0, tagname) + if words <= length: + # Don't try to close tags if we don't need to truncate + return s + out = s[:end_text_pos] + if end_text: + out += ' ' + end_text + # Close any tags still open + for tag in open_tags: + out += '' % tag + # Return string + return out diff --git a/samples/themes/notmyidea/css/main.css b/samples/themes/notmyidea/css/main.css index 4431f59d..14ec30b8 100644 --- a/samples/themes/notmyidea/css/main.css +++ b/samples/themes/notmyidea/css/main.css @@ -34,9 +34,12 @@ h2, h3, h4, h5, h6 { font-weight: 400; line-height: 1.1; margin-bottom: .8em; - margin-top: .8em; } + +h3, h4, h5, h6 { margin-top: .8em; } +hr { border: 2px solid #EEEEEE; } + /* Anchors */ a {outline: 0;} a img {border: 0px; text-decoration: none;} @@ -54,7 +57,6 @@ a:hover, a:active { /* Paragraphs */ p {margin-bottom: 1.143em;} -* p:last-child {margin-bottom: 0;} strong, b {font-weight: bold;} em, i {font-style: italic;} @@ -73,6 +75,14 @@ ol { margin: 1em 0 1.5em 1.5em; } +.post-info { + float:right; + margin:10px; + padding:5px; +} + +.readmore { float: right } + dl {margin: 0 0 1.5em 0;} dt {font-weight: bold;} dd {margin-left: 1.5em;} @@ -121,7 +131,7 @@ img.left, figure.left {float: right; margin: 0 0 2em 2em;} } /* Banner */ - #banner h1 {font-size: 3.571em; line-height: .6;} + #banner h1 {font-size: 3.571em; line-height: 0;} #banner h1 a:link, #banner h1 a:visited { color: #000305; display: block; @@ -324,7 +334,7 @@ img.left, figure.left {float: right; margin: 0 0 2em 2em;} li:last-child .hentry, #content > .hentry {border: 0; margin: 0;} #content > .hentry {padding: 1em 0;} -.entry-title {font-size: 1.429em; margin-bottom: 5px; margin-top: 0; } +.entry-title {font-size: 2em; margin-bottom: 5px; margin-top: 0; } .entry-title a:link, .entry-title a:visited {text-decoration: none;} .hentry .post-info * {font-style: normal;} diff --git a/samples/themes/notmyidea/templates/article.html b/samples/themes/notmyidea/templates/article.html index 3bc28f47..cc2ffb9d 100644 --- a/samples/themes/notmyidea/templates/article.html +++ b/samples/themes/notmyidea/templates/article.html @@ -1,19 +1,19 @@ {% extends "base.html" %} {% block content %}
-
+
+
{% endblock %} diff --git a/samples/themes/notmyidea/templates/base.html b/samples/themes/notmyidea/templates/base.html index 503f57d2..1999e892 100644 --- a/samples/themes/notmyidea/templates/base.html +++ b/samples/themes/notmyidea/templates/base.html @@ -22,7 +22,7 @@