_detab_re = re.compile(r'(.*?)\t', re.M)
def _detab_sub(self, match):
g1 = match.group(1)
return g1 + (' ' * (self.tab_width - len(g1) % self.tab_width))
def _detab(self, text):
r"""Remove (leading?) tabs from a file.
>>> m = Markdown()
>>> m._detab("\tfoo")
' foo'
>>> m._detab(" \tfoo")
' foo'
>>> m._detab("\t foo")
' foo'
>>> m._detab(" foo")
' foo'
>>> m._detab(" foo\n\tbar\tblam")
' foo\n bar blam'
"""
if '\t' not in text:
return text
return self._detab_re.subn(self._detab_sub, text)[0]
_block_tags_a = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|ins|del'
_strict_tag_block_re = re.compile(r"""
( # save in \1
^ # start of line (with re.M)
<(%s) # start tag = \2
\b # word break
(.*\n)*? # any number of lines, minimally matching
# the matching end tag
[ \t]* # trailing spaces/tabs
(?=\n+|\Z) # followed by a newline or end of document
)
""" % _block_tags_a,
re.X | re.M)
_block_tags_b = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math'
_liberal_tag_block_re = re.compile(r"""
( # save in \1
^ # start of line (with re.M)
<(%s) # start tag = \2
\b # word break
(.*\n)*? # any number of lines, minimally matching
.* # the matching end tag
[ \t]* # trailing spaces/tabs
(?=\n+|\Z) # followed by a newline or end of document
)
""" % _block_tags_b,
re.X | re.M)
# Save for usage in coming 'xml' extra.
XXX_liberal_tag_block_re = re.compile(r"""
( # save in \1
^ # start of line (with re.M)
(?:
<(%s|\w+:\w+) # start tag = \2
\b # word break
(?:.*\n)*? # any number of lines, minimally matching
.* # the matching end tag
|
<(\w+:)?\w+ # single tag-start
\b # word break
.*? # any content on one line, minimally matching
/> # end of tag
|
<\?\w+ # start of processing instruction
\b # word break
.*? # any content on one line, minimally matching
\?> # the PI end tag
)
[ \t]* # trailing spaces/tabs
(?=\n+|\Z) # followed by a newline or end of document
)
""" % _block_tags_b,
re.X | re.M)
def _hash_html_block_sub(self, match, raw=False):
html = match.group(1)
if raw and self.safe_mode:
html = self._sanitize_html(html)
key = _hash_text(html)
self.html_blocks[key] = html
return "\n\n" + key + "\n\n"
def _hash_html_blocks(self, text, raw=False):
"""Hashify HTML blocks
We only want to do this for block-level HTML tags, such as headers,
lists, and tables. That's because we still want to wrap s around
"paragraphs" that are wrapped in non-block-level tags, such as anchors,
phrase emphasis, and spans. The list of tags we're looking for is
hard-coded.
@param raw {boolean} indicates if these are raw HTML blocks in
the original source. It makes a difference in "safe" mode.
"""
if '<' not in text:
return text
# Pass `raw` value into our calls to self._hash_html_block_sub.
hash_html_block_sub = _curry(self._hash_html_block_sub, raw=raw)
# First, look for nested blocks, e.g.:
#
#
# tags for inner block must be indented.
#
#
` and stop at the first `
`.
text = self._strict_tag_block_re.sub(hash_html_block_sub, text)
# Now match more liberally, simply from `\n` to `\n`
text = self._liberal_tag_block_re.sub(hash_html_block_sub, text)
# Special case just for
. It was easier to make a special
# case than to make the other regex more complicated.
if "", start_idx) + 3
except ValueError, ex:
break
# Start position for next comment block search.
start = end_idx
# Validate whitespace before comment.
if start_idx:
# - Up to `tab_width - 1` spaces before start_idx.
for i in range(self.tab_width - 1):
if text[start_idx - 1] != ' ':
break
start_idx -= 1
if start_idx == 0:
break
# - Must be preceded by 2 newlines or hit the start of
# the document.
if start_idx == 0:
pass
elif start_idx == 1 and text[0] == '\n':
start_idx = 0 # to match minute detail of Markdown.pl regex
elif text[start_idx-2:start_idx] == '\n\n':
pass
else:
break
# Validate whitespace after comment.
# - Any number of spaces and tabs.
while end_idx < len(text):
if text[end_idx] not in ' \t':
break
end_idx += 1
# - Must be following by 2 newlines or hit end of text.
if text[end_idx:end_idx+2] not in ('', '\n', '\n\n'):
continue
# Escape and hash (must match `_hash_html_block_sub`).
html = text[start_idx:end_idx]
if raw and self.safe_mode:
html = self._sanitize_html(html)
key = _hash_text(html)
self.html_blocks[key] = html
text = text[:start_idx] + "\n\n" + key + "\n\n" + text[end_idx:]
return text
def _strip_link_definitions(self, text):
# Strips link definitions from text, stores the URLs and titles in
# hash references.
less_than_tab = self.tab_width - 1
# Link defs are in the form:
# [id]: url "optional title"
_link_def_re = re.compile(r"""
^[ ]{0,%d}\[(.+)\]: # id = \1
[ \t]*
\n? # maybe *one* newline
[ \t]*
? # url = \2
[ \t]*
(?:
\n? # maybe one newline
[ \t]*
(?<=\s) # lookbehind for whitespace
['"(]
([^\n]*) # title = \3
['")]
[ \t]*
)? # title is optional
(?:\n+|\Z)
""" % less_than_tab, re.X | re.M | re.U)
return _link_def_re.sub(self._extract_link_def_sub, text)
def _extract_link_def_sub(self, match):
id, url, title = match.groups()
key = id.lower() # Link IDs are case-insensitive
self.urls[key] = self._encode_amps_and_angles(url)
if title:
self.titles[key] = title.replace('"', '"')
return ""
def _extract_footnote_def_sub(self, match):
id, text = match.groups()
text = _dedent(text, skip_first_line=not text.startswith('\n')).strip()
normed_id = re.sub(r'\W', '-', id)
# Ensure footnote text ends with a couple newlines (for some
# block gamut matches).
self.footnotes[normed_id] = text + "\n\n"
return ""
def _strip_footnote_definitions(self, text):
"""A footnote definition looks like this:
[^note-id]: Text of the note.
May include one or more indented paragraphs.
Where,
- The 'note-id' can be pretty much anything, though typically it
is the number of the footnote.
- The first paragraph may start on the next line, like so:
[^note-id]:
Text of the note.
"""
less_than_tab = self.tab_width - 1
footnote_def_re = re.compile(r'''
^[ ]{0,%d}\[\^(.+)\]: # id = \1
[ \t]*
( # footnote text = \2
# First line need not start with the spaces.
(?:\s*.*\n+)
(?:
(?:[ ]{%d} | \t) # Subsequent lines must be indented.
.*\n+
)*
)
# Lookahead for non-space at line-start, or end of doc.
(?:(?=^[ ]{0,%d}\S)|\Z)
''' % (less_than_tab, self.tab_width, self.tab_width),
re.X | re.M)
return footnote_def_re.sub(self._extract_footnote_def_sub, text)
_hr_res = [
re.compile(r"^[ ]{0,2}([ ]?\*[ ]?){3,}[ \t]*$", re.M),
re.compile(r"^[ ]{0,2}([ ]?\-[ ]?){3,}[ \t]*$", re.M),
re.compile(r"^[ ]{0,2}([ ]?\_[ ]?){3,}[ \t]*$", re.M),
]
def _run_block_gamut(self, text):
# These are all the transformations that form block-level
# tags like paragraphs, headers, and list items.
text = self._do_headers(text)
# Do Horizontal Rules:
hr = "\n tags around block-level tags.
text = self._hash_html_blocks(text)
text = self._form_paragraphs(text)
return text
def _pyshell_block_sub(self, match):
lines = match.group(0).splitlines(0)
_dedentlines(lines)
indent = ' ' * self.tab_width
s = ('\n' # separate from possible cuddled paragraph
+ indent + ('\n'+indent).join(lines)
+ '\n\n')
return s
def _prepare_pyshell_blocks(self, text):
"""Ensure that Python interactive shell sessions are put in
code blocks -- even if not properly indented.
"""
if ">>>" not in text:
return text
less_than_tab = self.tab_width - 1
_pyshell_block_re = re.compile(r"""
^([ ]{0,%d})>>>[ ].*\n # first line
^(\1.*\S+.*\n)* # any number of subsequent lines
^\n # ends with a blank line
""" % less_than_tab, re.M | re.X)
return _pyshell_block_re.sub(self._pyshell_block_sub, text)
def _run_span_gamut(self, text):
# These are all the transformations that occur *within* block-level
# tags like paragraphs, headers, and list items.
text = self._do_code_spans(text)
text = self._escape_special_chars(text)
# Process anchor and image tags.
text = self._do_links(text)
# Make links out of things like ``
# Must come after _do_links(), because you can use < and >
# delimiters in inline links like [this]().
text = self._do_auto_links(text)
if "link-patterns" in self.extras:
text = self._do_link_patterns(text)
text = self._encode_amps_and_angles(text)
text = self._do_italics_and_bold(text)
# Do hard breaks:
text = re.sub(r" {2,}\n", "
|
# auto-link (e.g., )
<\w+[^>]*>
|
# comment
|
<\?.*?\?> # processing instruction
)
""", re.X)
def _escape_special_chars(self, text):
# Python markdown note: the HTML tokenization here differs from
# that in Markdown.pl, hence the behaviour for subtle cases can
# differ (I believe the tokenizer here does a better job because
# it isn't susceptible to unmatched '<' and '>' in HTML tags).
# Note, however, that '>' is not allowed in an auto-link URL
# here.
escaped = []
is_html_markup = False
for token in self._sorta_html_tokenize_re.split(text):
if is_html_markup:
# Within tags/HTML-comments/auto-links, encode * and _
# so they don't conflict with their use in Markdown for
# italics and strong. We're replacing each such
# character with its corresponding MD5 checksum value;
# this is likely overkill, but it should prevent us from
# colliding with the escape values by accident.
escaped.append(token.replace('*', g_escape_table['*'])
.replace('_', g_escape_table['_']))
else:
escaped.append(self._encode_backslash_escapes(token))
is_html_markup = not is_html_markup
return ''.join(escaped)
def _hash_html_spans(self, text):
# Used for safe_mode.
def _is_auto_link(s):
if ':' in s and self._auto_link_re.match(s):
return True
elif '@' in s and self._auto_email_link_re.match(s):
return True
return False
tokens = []
is_html_markup = False
for token in self._sorta_html_tokenize_re.split(text):
if is_html_markup and not _is_auto_link(token):
sanitized = self._sanitize_html(token)
key = _hash_text(sanitized)
self.html_spans[key] = sanitized
tokens.append(key)
else:
tokens.append(token)
is_html_markup = not is_html_markup
return ''.join(tokens)
def _unhash_html_spans(self, text):
for key, sanitized in self.html_spans.items():
text = text.replace(key, sanitized)
return text
def _sanitize_html(self, s):
if self.safe_mode == "replace":
return self.html_removed_text
elif self.safe_mode == "escape":
replacements = [
('&', '&'),
('<', '<'),
('>', '>'),
]
for before, after in replacements:
s = s.replace(before, after)
return s
else:
raise MarkdownError("invalid value for 'safe_mode': %r (must be "
"'escape' or 'replace')" % self.safe_mode)
_tail_of_inline_link_re = re.compile(r'''
# Match tail of: [text](/url/) or [text](/url/ "title")
\( # literal paren
[ \t]*
(?P # \1
<.*?>
|
.*?
)
[ \t]*
( # \2
(['"]) # quote char = \3
(?P.*?)
\3 # matching quote
)? # title is optional
\)
''', re.X | re.S)
_tail_of_reference_link_re = re.compile(r'''
# Match tail of: [text][id]
[ ]? # one optional space
(?:\n[ ]*)? # one optional newline followed by spaces
\[
(?P<id>.*?)
\]
''', re.X | re.S)
def _do_links(self, text):
"""Turn Markdown link shortcuts into XHTML <a> and <img> tags.
This is a combination of Markdown.pl's _DoAnchors() and
_DoImages(). They are done together because that simplified the
approach. It was necessary to use a different approach than
Markdown.pl because of the lack of atomic matching support in
Python's regex engine used in $g_nested_brackets.
"""
MAX_LINK_TEXT_SENTINEL = 300
# `anchor_allowed_pos` is used to support img links inside
# anchors, but not anchors inside anchors. An anchor's start
# pos must be `>= anchor_allowed_pos`.
anchor_allowed_pos = 0
curr_pos = 0
while True: # Handle the next link.
# The next '[' is the start of:
# - an inline anchor: [text](url "title")
# - a reference anchor: [text][id]
# - an inline img: 
# - a reference img: ![text][id]
# - a footnote ref: [^id]
# (Only if 'footnotes' extra enabled)
# - a footnote defn: [^id]: ...
# (Only if 'footnotes' extra enabled) These have already
# been stripped in _strip_footnote_definitions() so no
# need to watch for them.
# - a link definition: [id]: url "title"
# These have already been stripped in
# _strip_link_definitions() so no need to watch for them.
# - not markup: [...anything else...
try:
start_idx = text.index('[', curr_pos)
except ValueError:
break
text_length = len(text)
# Find the matching closing ']'.
# Markdown.pl allows *matching* brackets in link text so we
# will here too. Markdown.pl *doesn't* currently allow
# matching brackets in img alt text -- we'll differ in that
# regard.
bracket_depth = 0
for p in range(start_idx+1, min(start_idx+MAX_LINK_TEXT_SENTINEL,
text_length)):
ch = text[p]
if ch == ']':
bracket_depth -= 1
if bracket_depth < 0:
break
elif ch == '[':
bracket_depth += 1
else:
# Closing bracket not found within sentinel length.
# This isn't markup.
curr_pos = start_idx + 1
continue
link_text = text[start_idx+1:p]
# Possibly a footnote ref?
if "footnotes" in self.extras and link_text.startswith("^"):
normed_id = re.sub(r'\W', '-', link_text[1:])
if normed_id in self.footnotes:
self.footnote_ids.append(normed_id)
result = '<sup class="footnote-ref" id="fnref-%s">' \
'<a href="#fn-%s">%s</a></sup>' \
% (normed_id, normed_id, len(self.footnote_ids))
text = text[:start_idx] + result + text[p+1:]
else:
# This id isn't defined, leave the markup alone.
curr_pos = p+1
continue
# Now determine what this is by the remainder.
p += 1
if p == text_length:
return text
# Inline anchor or img?
if text[p] == '(': # attempt at perf improvement
match = self._tail_of_inline_link_re.match(text, p)
if match:
# Handle an inline anchor or img.
is_img = start_idx > 0 and text[start_idx-1] == "!"
if is_img:
start_idx -= 1
url, title = match.group("url"), match.group("title")
if url and url[0] == '<':
url = url[1:-1] # '<url>' -> 'url'
# We've got to encode these to avoid conflicting
# with italics/bold.
url = url.replace('*', g_escape_table['*']) \
.replace('_', g_escape_table['_'])
if title:
title_str = ' title="%s"' \
% title.replace('*', g_escape_table['*']) \
.replace('_', g_escape_table['_']) \
.replace('"', '"')
else:
title_str = ''
if is_img:
result = '<img src="%s" alt="%s"%s%s' \
% (url, link_text.replace('"', '"'),
title_str, self.empty_element_suffix)
curr_pos = start_idx + len(result)
text = text[:start_idx] + result + text[match.end():]
elif start_idx >= anchor_allowed_pos:
result_head = '<a href="%s"%s>' % (url, title_str)
result = '%s%s</a>' % (result_head, link_text)
# <img> allowed from curr_pos on, <a> from
# anchor_allowed_pos on.
curr_pos = start_idx + len(result_head)
anchor_allowed_pos = start_idx + len(result)
text = text[:start_idx] + result + text[match.end():]
else:
# Anchor not allowed here.
curr_pos = start_idx + 1
continue
# Reference anchor or img?
else:
match = self._tail_of_reference_link_re.match(text, p)
if match:
# Handle a reference-style anchor or img.
is_img = start_idx > 0 and text[start_idx-1] == "!"
if is_img:
start_idx -= 1
link_id = match.group("id").lower()
if not link_id:
link_id = link_text.lower() # for links like [this][]
if link_id in self.urls:
url = self.urls[link_id]
# We've got to encode these to avoid conflicting
# with italics/bold.
url = url.replace('*', g_escape_table['*']) \
.replace('_', g_escape_table['_'])
title = self.titles.get(link_id)
if title:
title = title.replace('*', g_escape_table['*']) \
.replace('_', g_escape_table['_'])
title_str = ' title="%s"' % title
else:
title_str = ''
if is_img:
result = '<img src="%s" alt="%s"%s%s' \
% (url, link_text.replace('"', '"'),
title_str, self.empty_element_suffix)
curr_pos = start_idx + len(result)
text = text[:start_idx] + result + text[match.end():]
elif start_idx >= anchor_allowed_pos:
result = '<a href="%s"%s>%s</a>' \
% (url, title_str, link_text)
result_head = '<a href="%s"%s>' % (url, title_str)
result = '%s%s</a>' % (result_head, link_text)
# <img> allowed from curr_pos on, <a> from
# anchor_allowed_pos on.
curr_pos = start_idx + len(result_head)
anchor_allowed_pos = start_idx + len(result)
text = text[:start_idx] + result + text[match.end():]
else:
# Anchor not allowed here.
curr_pos = start_idx + 1
else:
# This id isn't defined, leave the markup alone.
curr_pos = match.end()
continue
# Otherwise, it isn't markup.
curr_pos = start_idx + 1
return text
_setext_h_re = re.compile(r'^(.+)[ \t]*\n(=+|-+)[ \t]*\n+', re.M)
def _setext_h_sub(self, match):
n = {"=": 1, "-": 2}[match.group(2)[0]]
demote_headers = self.extras.get("demote-headers")
if demote_headers:
n = min(n + demote_headers, 6)
return "<h%d>%s</h%d>\n\n" \
% (n, self._run_span_gamut(match.group(1)), n)
_atx_h_re = re.compile(r'''
^(\#{1,6}) # \1 = string of #'s
[ \t]*
(.+?) # \2 = Header text
[ \t]*
(?<!\\) # ensure not an escaped trailing '#'
\#* # optional closing #'s (not counted)
\n+
''', re.X | re.M)
def _atx_h_sub(self, match):
n = len(match.group(1))
demote_headers = self.extras.get("demote-headers")
if demote_headers:
n = min(n + demote_headers, 6)
return "<h%d>%s</h%d>\n\n" \
% (n, self._run_span_gamut(match.group(2)), n)
def _do_headers(self, text):
# Setext-style headers:
# Header 1
# ========
#
# Header 2
# --------
text = self._setext_h_re.sub(self._setext_h_sub, text)
# atx-style headers:
# # Header 1
# ## Header 2
# ## Header 2 with closing hashes ##
# ...
# ###### Header 6
text = self._atx_h_re.sub(self._atx_h_sub, text)
return text
_marker_ul_chars = '*+-'
_marker_any = r'(?:[%s]|\d+\.)' % _marker_ul_chars
_marker_ul = '(?:[%s])' % _marker_ul_chars
_marker_ol = r'(?:\d+\.)'
def _list_sub(self, match):
lst = match.group(1)
lst_type = match.group(3) in self._marker_ul_chars and "ul" or "ol"
result = self._process_list_items(lst)
if self.list_level:
return "<%s>\n%s</%s>\n" % (lst_type, result, lst_type)
else:
return "<%s>\n%s</%s>\n\n" % (lst_type, result, lst_type)
def _do_lists(self, text):
# Form HTML ordered (numbered) and unordered (bulleted) lists.
for marker_pat in (self._marker_ul, self._marker_ol):
# Re-usable pattern to match any entire ul or ol list:
less_than_tab = self.tab_width - 1
whole_list = r'''
( # \1 = whole list
( # \2
[ ]{0,%d}
(%s) # \3 = first list item marker
[ \t]+
)
(?:.+?)
( # \4
\Z
|
\n{2,}
(?=\S)
(?! # Negative lookahead for another list item marker
[ \t]*
%s[ \t]+
)
)
)
''' % (less_than_tab, marker_pat, marker_pat)
# We use a different prefix before nested lists than top-level lists.
# See extended comment in _process_list_items().
#
# Note: There's a bit of duplication here. My original implementation
# created a scalar regex pattern as the conditional result of the test on
# $g_list_level, and then only ran the $text =~ s{...}{...}egmx
# substitution once, using the scalar as the pattern. This worked,
# everywhere except when running under MT on my hosting account at Pair
# Networks. There, this caused all rebuilds to be killed by the reaper (or
# perhaps they crashed, but that seems incredibly unlikely given that the
# same script on the same server ran fine *except* under MT. I've spent
# more time trying to figure out why this is happening than I'd like to
# admit. My only guess, backed up by the fact that this workaround works,
# is that Perl optimizes the substition when it can figure out that the
# pattern will never change, and when this optimization isn't on, we run
# afoul of the reaper. Thus, the slightly redundant code to that uses two
# static s/// patterns rather than one conditional pattern.
if self.list_level:
sub_list_re = re.compile("^"+whole_list, re.X | re.M | re.S)
text = sub_list_re.sub(self._list_sub, text)
else:
list_re = re.compile(r"(?:(?<=\n\n)|\A\n?)"+whole_list,
re.X | re.M | re.S)
text = list_re.sub(self._list_sub, text)
return text
_list_item_re = re.compile(r'''
(\n)? # leading line = \1
(^[ \t]*) # leading whitespace = \2
(%s) [ \t]+ # list marker = \3
((?:.+?) # list item text = \4
(\n{1,2})) # eols = \5
(?= \n* (\Z | \2 (%s) [ \t]+))
''' % (_marker_any, _marker_any),
re.M | re.X | re.S)
_last_li_endswith_two_eols = False
def _list_item_sub(self, match):
item = match.group(4)
leading_line = match.group(1)
leading_space = match.group(2)
if leading_line or "\n\n" in item or self._last_li_endswith_two_eols:
item = self._run_block_gamut(self._outdent(item))
else:
# Recursion for sub-lists:
item = self._do_lists(self._outdent(item))
if item.endswith('\n'):
item = item[:-1]
item = self._run_span_gamut(item)
self._last_li_endswith_two_eols = (len(match.group(5)) == 2)
return "<li>%s</li>\n" % item
def _process_list_items(self, list_str):
# Process the contents of a single ordered or unordered list,
# splitting it into individual list items.
# The $g_list_level global keeps track of when we're inside a list.
# Each time we enter a list, we increment it; when we leave a list,
# we decrement. If it's zero, we're not in a list anymore.
#
# We do this because when we're not inside a list, we want to treat
# something like this:
#
# I recommend upgrading to version
# 8. Oops, now this line is treated
# as a sub-list.
#
# As a single paragraph, despite the fact that the second line starts
# with a digit-period-space sequence.
#
# Whereas when we're inside a list (or sub-list), that line will be
# treated as the start of a sub-list. What a kludge, huh? This is
# an aspect of Markdown's syntax that's hard to parse perfectly
# without resorting to mind-reading. Perhaps the solution is to
# change the syntax rules such that sub-lists must start with a
# starting cardinal number; e.g. "1." or "a.".
self.list_level += 1
self._last_li_endswith_two_eols = False
list_str = list_str.rstrip('\n') + '\n'
list_str = self._list_item_re.sub(self._list_item_sub, list_str)
self.list_level -= 1
return list_str
def _get_pygments_lexer(self, lexer_name):
try:
from pygments import lexers, util
except ImportError:
return None
try:
return lexers.get_lexer_by_name(lexer_name)
except util.ClassNotFound:
return None
def _color_with_pygments(self, codeblock, lexer):
import pygments
import pygments.formatters
class HtmlCodeFormatter(pygments.formatters.HtmlFormatter):
def _wrap_code(self, inner):
"""A function for use in a Pygments Formatter which
wraps in <code> tags.
"""
yield 0, "<code>"
for tup in inner:
yield tup
yield 0, "</code>"
def wrap(self, source, outfile):
"""Return the source with a code, pre, and div."""
return self._wrap_div(self._wrap_pre(self._wrap_code(source)))
formatter = HtmlCodeFormatter(cssclass="codehilite")
return pygments.highlight(codeblock, lexer, formatter)
def _code_block_sub(self, match):
codeblock = match.group(1)
codeblock = self._outdent(codeblock)
codeblock = self._detab(codeblock)
codeblock = codeblock.lstrip('\n') # trim leading newlines
codeblock = codeblock.rstrip() # trim trailing whitespace
if "code-color" in self.extras and codeblock.startswith(":::"):
lexer_name, rest = codeblock.split('\n', 1)
lexer_name = lexer_name[3:].strip()
lexer = self._get_pygments_lexer(lexer_name)
codeblock = rest.lstrip("\n") # Remove lexer declaration line.
if lexer:
colored = self._color_with_pygments(codeblock, lexer)
return "\n\n%s\n\n" % colored
codeblock = self._encode_code(codeblock)
return "\n\n<pre><code>%s\n</code></pre>\n\n" % codeblock
def _do_code_blocks(self, text):
"""Process Markdown `<pre><code>` blocks."""
code_block_re = re.compile(r'''
(?:\n\n|\A)
( # $1 = the code block -- one or more lines, starting with a space/tab
(?:
(?:[ ]{%d} | \t) # Lines must start with a tab or a tab-width of spaces
.*\n+
)+
)
((?=^[ ]{0,%d}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
''' % (self.tab_width, self.tab_width),
re.M | re.X)
return code_block_re.sub(self._code_block_sub, text)
# Rules for a code span:
# - backslash escapes are not interpreted in a code span
# - to include one or or a run of more backticks the delimiters must
# be a longer run of backticks
# - cannot start or end a code span with a backtick; pad with a
# space and that space will be removed in the emitted HTML
# See `test/tm-cases/escapes.text` for a number of edge-case
# examples.
_code_span_re = re.compile(r'''
(?<!\\)
(`+) # \1 = Opening run of `
(?!`) # See Note A test/tm-cases/escapes.text
(.+?) # \2 = The code block
(?<!`)
\1 # Matching closer
(?!`)
''', re.X | re.S)
def _code_span_sub(self, match):
c = match.group(2).strip(" \t")
c = self._encode_code(c)
return "<code>%s</code>" % c
def _do_code_spans(self, text):
# * Backtick quotes are used for <code></code> spans.
#
# * You can use multiple backticks as the delimiters if you want to
# include literal backticks in the code span. So, this input:
#
# Just type ``foo `bar` baz`` at the prompt.
#
# Will translate to:
#
# <p>Just type <code>foo `bar` baz</code> at the prompt.</p>
#
# There's no arbitrary limit to the number of backticks you
# can use as delimters. If you need three consecutive backticks
# in your code, use four for delimiters, etc.
#
# * You can use spaces to get literal backticks at the edges:
#
# ... type `` `bar` `` ...
#
# Turns to:
#
# ... type <code>`bar`</code> ...
return self._code_span_re.sub(self._code_span_sub, text)
def _encode_code(self, text):
"""Encode/escape certain characters inside Markdown code runs.
The point is that in code, these characters are literals,
and lose their special Markdown meanings.
"""
replacements = [
# Encode all ampersands; HTML entities are not
# entities within a Markdown code span.
('&', '&'),
# Do the angle bracket song and dance:
('<', '<'),
('>', '>'),
# Now, escape characters that are magic in Markdown:
('*', g_escape_table['*']),
('_', g_escape_table['_']),
('{', g_escape_table['{']),
('}', g_escape_table['}']),
('[', g_escape_table['[']),
(']', g_escape_table[']']),
('\\', g_escape_table['\\']),
]
for before, after in replacements:
text = text.replace(before, after)
return text
_strong_re = re.compile(r"(\*\*|__)(?=\S)(.+?[*_]*)(?<=\S)\1", re.S)
_em_re = re.compile(r"(\*|_)(?=\S)(.+?)(?<=\S)\1", re.S)
_code_friendly_strong_re = re.compile(r"\*\*(?=\S)(.+?[*_]*)(?<=\S)\*\*", re.S)
_code_friendly_em_re = re.compile(r"\*(?=\S)(.+?)(?<=\S)\*", re.S)
def _do_italics_and_bold(self, text):
# <strong> must go first:
if "code-friendly" in self.extras:
text = self._code_friendly_strong_re.sub(r"<strong>\1</strong>", text)
text = self._code_friendly_em_re.sub(r"<em>\1</em>", text)
else:
text = self._strong_re.sub(r"<strong>\2</strong>", text)
text = self._em_re.sub(r"<em>\2</em>", text)
return text
_block_quote_re = re.compile(r'''
( # Wrap whole match in \1
(
^[ \t]*>[ \t]? # '>' at the start of a line
.+\n # rest of the first line
(.+\n)* # subsequent consecutive lines
\n* # blanks
)+
)
''', re.M | re.X)
_bq_one_level_re = re.compile('^[ \t]*>[ \t]?', re.M);
_html_pre_block_re = re.compile(r'(\s*<pre>.+?</pre>)', re.S)
def _dedent_two_spaces_sub(self, match):
return re.sub(r'(?m)^ ', '', match.group(1))
def _block_quote_sub(self, match):
bq = match.group(1)
bq = self._bq_one_level_re.sub('', bq) # trim one level of quoting
bq = self._ws_only_line_re.sub('', bq) # trim whitespace-only lines
bq = self._run_block_gamut(bq) # recurse
bq = re.sub('(?m)^', ' ', bq)
# These leading spaces screw with <pre> content, so we need to fix that:
bq = self._html_pre_block_re.sub(self._dedent_two_spaces_sub, bq)
return "<blockquote>\n%s\n</blockquote>\n\n" % bq
def _do_block_quotes(self, text):
if '>' not in text:
return text
return self._block_quote_re.sub(self._block_quote_sub, text)
def _form_paragraphs(self, text):
# Strip leading and trailing lines:
text = text.strip('\n')
# Wrap <p> tags.
grafs = re.split(r"\n{2,}", text)
for i, graf in enumerate(grafs):
if graf in self.html_blocks:
# Unhashify HTML blocks
grafs[i] = self.html_blocks[graf]
else:
# Wrap <p> tags.
graf = self._run_span_gamut(graf)
grafs[i] = "<p>" + graf.lstrip(" \t") + "</p>"
return "\n\n".join(grafs)
def _add_footnotes(self, text):
if self.footnotes:
footer = [
'<div class="footnotes">',
'<hr' + self.empty_element_suffix,
'<ol>',
]
for i, id in enumerate(self.footnote_ids):
if i != 0:
footer.append('')
footer.append('<li id="fn-%s">' % id)
footer.append(self._run_block_gamut(self.footnotes[id]))
backlink = ('<a href="#fnref-%s" '
'class="footnoteBackLink" '
'title="Jump back to footnote %d in the text.">'
'↩</a>' % (id, i+1))
if footer[-1].endswith("</p>"):
footer[-1] = footer[-1][:-len("</p>")] \
+ ' ' + backlink + "</p>"
else:
footer.append("\n<p>%s</p>" % backlink)
footer.append('</li>')
footer.append('</ol>')
footer.append('</div>')
return text + '\n\n' + '\n'.join(footer)
else:
return text
# Ampersand-encoding based entirely on Nat Irons's Amputator MT plugin:
# http://bumppo.net/projects/amputator/
_ampersand_re = re.compile(r'&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)')
_naked_lt_re = re.compile(r'<(?![a-z/?\$!])', re.I)
def _encode_amps_and_angles(self, text):
# Smart processing for ampersands and angle brackets that need
# to be encoded.
text = self._ampersand_re.sub('&', text)
# Encode naked <'s
text = self._naked_lt_re.sub('<', text)
return text
def _encode_backslash_escapes(self, text):
for ch, escape in g_escape_table.items():
text = text.replace("\\"+ch, escape)
return text
_auto_link_re = re.compile(r'<((https?|ftp):[^\'">\s]+)>', re.I)
def _auto_link_sub(self, match):
g1 = match.group(1)
return '<a href="%s">%s</a>' % (g1, g1)
_auto_email_link_re = re.compile(r"""
<
(?:mailto:)?
(
[-.\w]+
\@
[-\w]+(\.[-\w]+)*\.[a-zA-Z]+
)
>
""", re.I | re.X | re.U)
def _auto_email_link_sub(self, match):
return self._encode_email_address(
self._unescape_special_chars(match.group(1)))
def _do_auto_links(self, text):
text = self._auto_link_re.sub(self._auto_link_sub, text)
text = self._auto_email_link_re.sub(self._auto_email_link_sub, text)
return text
def _encode_email_address(self, addr):
# Input: an email address, e.g. "foo@example.com"
#
# Output: the email address as a mailto link, with each character
# of the address encoded as either a decimal or hex entity, in
# the hopes of foiling most address harvesting spam bots. E.g.:
#
# <a href="mailto:foo@e
# xample.com">foo
# @example.com</a>
#
# Based on a filter by Matthew Wickline, posted to the BBEdit-Talk
# mailing list: <http://tinyurl.com/yu7ue>
chars = [_xml_encode_email_char_at_random(ch)
for ch in "mailto:" + addr]
# Strip the mailto: from the visible part.
addr = '<a href="%s">%s</a>' \
% (''.join(chars), ''.join(chars[7:]))
return addr
def _do_link_patterns(self, text):
"""Caveat emptor: there isn't much guarding against link
patterns being formed inside other standard Markdown links, e.g.
inside a [link def][like this].
Dev Notes: *Could* consider prefixing regexes with a negative
lookbehind assertion to attempt to guard against this.
"""
link_from_hash = {}
for regex, href in self.link_patterns:
replacements = []
for match in regex.finditer(text):
replacements.append((match.span(), match.expand(href)))
for (start, end), href in reversed(replacements):
escaped_href = (
href.replace('"', '"') # b/c of attr quote
# To avoid markdown <em> and <strong>:
.replace('*', g_escape_table['*'])
.replace('_', g_escape_table['_']))
link = '<a href="%s">%s</a>' % (escaped_href, text[start:end])
hash = md5(link).hexdigest()
link_from_hash[hash] = link
text = text[:start] + hash + text[end:]
for hash, link in link_from_hash.items():
text = text.replace(hash, link)
return text
def _unescape_special_chars(self, text):
# Swap back in all the special characters we've hidden.
for ch, hash in g_escape_table.items():
text = text.replace(hash, ch)
return text
def _outdent(self, text):
# Remove one level of line-leading tabs or spaces
return self._outdent_re.sub('', text)
class MarkdownWithExtras(Markdown):
"""A markdowner class that enables most extras:
- footnotes
- code-color (only has effect if 'pygments' Python module on path)
These are not included:
- pyshell (specific to Python-related documenting)
- code-friendly (because it *disables* part of the syntax)
- link-patterns (because you need to specify some actual
link-patterns anyway)
"""
extras = ["footnotes", "code-color"]
#---- internal support functions
# From http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/52549
def _curry(*args, **kwargs):
function, args = args[0], args[1:]
def result(*rest, **kwrest):
combined = kwargs.copy()
combined.update(kwrest)
return function(*args + rest, **combined)
return result
# Recipe: regex_from_encoded_pattern (1.0)
def _regex_from_encoded_pattern(s):
"""'foo' -> re.compile(re.escape('foo'))
'/foo/' -> re.compile('foo')
'/foo/i' -> re.compile('foo', re.I)
"""
if s.startswith('/') and s.rfind('/') != 0:
# Parse it: /PATTERN/FLAGS
idx = s.rfind('/')
pattern, flags_str = s[1:idx], s[idx+1:]
flag_from_char = {
"i": re.IGNORECASE,
"l": re.LOCALE,
"s": re.DOTALL,
"m": re.MULTILINE,
"u": re.UNICODE,
}
flags = 0
for char in flags_str:
try:
flags |= flag_from_char[char]
except KeyError:
raise ValueError("unsupported regex flag: '%s' in '%s' "
"(must be one of '%s')"
% (char, s, ''.join(flag_from_char.keys())))
return re.compile(s[1:idx], flags)
else: # not an encoded regex
return re.compile(re.escape(s))
# Recipe: dedent (0.1.2)
def _dedentlines(lines, tabsize=8, skip_first_line=False):
"""_dedentlines(lines, tabsize=8, skip_first_line=False) -> dedented lines
"lines" is a list of lines to dedent.
"tabsize" is the tab width to use for indent width calculations.
"skip_first_line" is a boolean indicating if the first line should
be skipped for calculating the indent width and for dedenting.
This is sometimes useful for docstrings and similar.
Same as dedent() except operates on a sequence of lines. Note: the
lines list is modified **in-place**.
"""
DEBUG = False
if DEBUG:
print "dedent: dedent(..., tabsize=%d, skip_first_line=%r)"\
% (tabsize, skip_first_line)
indents = []
margin = None
for i, line in enumerate(lines):
if i == 0 and skip_first_line: continue
indent = 0
for ch in line:
if ch == ' ':
indent += 1
elif ch == '\t':
indent += tabsize - (indent % tabsize)
elif ch in '\r\n':
continue # skip all-whitespace lines
else:
break
else:
continue # skip all-whitespace lines
if DEBUG: print "dedent: indent=%d: %r" % (indent, line)
if margin is None:
margin = indent
else:
margin = min(margin, indent)
if DEBUG: print "dedent: margin=%r" % margin
if margin is not None and margin > 0:
for i, line in enumerate(lines):
if i == 0 and skip_first_line: continue
removed = 0
for j, ch in enumerate(line):
if ch == ' ':
removed += 1
elif ch == '\t':
removed += tabsize - (removed % tabsize)
elif ch in '\r\n':
if DEBUG: print "dedent: %r: EOL -> strip up to EOL" % line
lines[i] = lines[i][j:]
break
else:
raise ValueError("unexpected non-whitespace char %r in "
"line %r while removing %d-space margin"
% (ch, line, margin))
if DEBUG:
print "dedent: %r: %r -> removed %d/%d"\
% (line, ch, removed, margin)
if removed == margin:
lines[i] = lines[i][j+1:]
break
elif removed > margin:
lines[i] = ' '*(removed-margin) + lines[i][j+1:]
break
else:
if removed:
lines[i] = lines[i][removed:]
return lines
def _dedent(text, tabsize=8, skip_first_line=False):
"""_dedent(text, tabsize=8, skip_first_line=False) -> dedented text
"text" is the text to dedent.
"tabsize" is the tab width to use for indent width calculations.
"skip_first_line" is a boolean indicating if the first line should
be skipped for calculating the indent width and for dedenting.
This is sometimes useful for docstrings and similar.
textwrap.dedent(s), but don't expand tabs to spaces
"""
lines = text.splitlines(1)
_dedentlines(lines, tabsize=tabsize, skip_first_line=skip_first_line)
return ''.join(lines)
class _memoized(object):
"""Decorator that caches a function's return value each time it is called.
If called later with the same arguments, the cached value is returned, and
not re-evaluated.
http://wiki.python.org/moin/PythonDecoratorLibrary
"""
def __init__(self, func):
self.func = func
self.cache = {}
def __call__(self, *args):
try:
return self.cache[args]
except KeyError:
self.cache[args] = value = self.func(*args)
return value
except TypeError:
# uncachable -- for instance, passing a list as an argument.
# Better to not cache than to blow up entirely.
return self.func(*args)
def __repr__(self):
"""Return the function's docstring."""
return self.func.__doc__
def _hr_tag_re_from_tab_width(tab_width):
return re.compile(r"""
(?:
(?<=\n\n) # Starting after a blank line
| # or
\A\n? # the beginning of the doc
)
( # save in \1
[ ]{0,%d}
<(hr) # start tag = \2
\b # word break
([^<>])*? #
/?> # the matching end tag
[ \t]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
""" % (tab_width - 1), re.X)
_hr_tag_re_from_tab_width = _memoized(_hr_tag_re_from_tab_width)
def _xml_encode_email_char_at_random(ch):
r = random()
# Roughly 10% raw, 45% hex, 45% dec.
# '@' *must* be encoded. I [John Gruber] insist.
if r > 0.9 and ch != "@":
return ch
elif r < 0.45:
# The [1:] is to drop leading '0': 0x63 -> x63
return '&#%s;' % hex(ord(ch))[1:]
else:
return '&#%s;' % ord(ch)
def _hash_text(text):
return 'md5:'+md5(text.encode("utf-8")).hexdigest()
#---- mainline
class _NoReflowFormatter(optparse.IndentedHelpFormatter):
"""An optparse formatter that does NOT reflow the description."""
def format_description(self, description):
return description or ""
def _test():
import doctest
doctest.testmod()
def main(argv=sys.argv):
if not logging.root.handlers:
logging.basicConfig()
usage = "usage: %prog [PATHS...]"
version = "%prog "+__version__
parser = optparse.OptionParser(prog="markdown2", usage=usage,
version=version, description=cmdln_desc,
formatter=_NoReflowFormatter())
parser.add_option("-v", "--verbose", dest="log_level",
action="store_const", const=logging.DEBUG,
help="more verbose output")
parser.add_option("--encoding",
help="specify encoding of text content")
parser.add_option("--html4tags", action="store_true", default=False,
help="use HTML 4 style for empty element tags")
parser.add_option("-s", "--safe", metavar="MODE", dest="safe_mode",
help="sanitize literal HTML: 'escape' escapes "
"HTML meta chars, 'replace' replaces with an "
"[HTML_REMOVED] note")
parser.add_option("-x", "--extras", action="append",
help="Turn on specific extra features (not part of "
"the core Markdown spec). Supported values: "
"'code-friendly' disables _/__ for emphasis; "
"'code-color' adds code-block syntax coloring; "
"'link-patterns' adds auto-linking based on patterns; "
"'footnotes' adds the footnotes syntax;"
"'pyshell' to put unindented Python interactive shell sessions in a <code> block.")
parser.add_option("--use-file-vars",
help="Look for and use Emacs-style 'markdown-extras' "
"file var to turn on extras. See "
"<http://code.google.com/p/python-markdown2/wiki/Extras>.")
parser.add_option("--link-patterns-file",
help="path to a link pattern file")
parser.add_option("--self-test", action="store_true",
help="run internal self-tests (some doctests)")
parser.add_option("--compare", action="store_true",
help="run against Markdown.pl as well (for testing)")
parser.set_defaults(log_level=logging.INFO, compare=False,
encoding="utf-8", safe_mode=None, use_file_vars=False)
opts, paths = parser.parse_args()
log.setLevel(opts.log_level)
if opts.self_test:
return _test()
if opts.extras:
extras = {}
for s in opts.extras:
splitter = re.compile("[,;: ]+")
for e in splitter.split(s):
if '=' in e:
ename, earg = e.split('=', 1)
try:
earg = int(earg)
except ValueError:
pass
else:
ename, earg = e, None
extras[ename] = earg
else:
extras = None
if opts.link_patterns_file:
link_patterns = []
f = open(opts.link_patterns_file)
try:
for i, line in enumerate(f.readlines()):
if not line.strip(): continue
if line.lstrip().startswith("#"): continue
try:
pat, href = line.rstrip().rsplit(None, 1)
except ValueError:
raise MarkdownError("%s:%d: invalid link pattern line: %r"
% (opts.link_patterns_file, i+1, line))
link_patterns.append(
(_regex_from_encoded_pattern(pat), href))
finally:
f.close()
else:
link_patterns = None
from os.path import join, dirname, abspath
markdown_pl = join(dirname(dirname(abspath(__file__))), "test",
"Markdown.pl")
for path in paths:
if opts.compare:
print "==== Markdown.pl ===="
perl_cmd = 'perl %s "%s"' % (markdown_pl, path)
o = os.popen(perl_cmd)
perl_html = o.read()
o.close()
sys.stdout.write(perl_html)
print "==== markdown2.py ===="
html = markdown_path(path, encoding=opts.encoding,
html4tags=opts.html4tags,
safe_mode=opts.safe_mode,
extras=extras, link_patterns=link_patterns,
use_file_vars=opts.use_file_vars)
sys.stdout.write(
html.encode(sys.stdout.encoding or "utf-8", 'xmlcharrefreplace'))
if opts.compare:
print "==== match? %r ====" % (perl_html == html)
if __name__ == "__main__":
sys.exit( main(sys.argv) )
./weblog+jinja-1.1/weblog/post.py 0100644 0001750 0000000 00000021054 11063022145 0015727 0 ustar 00henry wheel import re
import email
import codecs
import logging
from os import stat
import datetime
from urllib import quote
try:
from markdown2 import markdown
except ImportError:
def markdown(text, *args):
logging.warning('Markdown syntax not available.'
'Please install markdown2.')
# Ugly but better than nothing :)
return '<pre>%s</pre>' % text
from html_to_xhtml import html_to_xhtml
class PostError(Exception):
'''
Error in post file
'''
def __init__(self, filename, message):
Exception.__init__(self, '%s: %s' % (filename, message))
class Author(unicode):
_AUTHOR_REGEX = re.compile(u'(?P<name>.+[^\s])\s*<(?P<email>[^@]+@.+)>',
re.UNICODE)
def name(self):
r = self._AUTHOR_REGEX.match(self)
if r:
return r.group('name')
else:
return self
def email(self):
r = self._AUTHOR_REGEX.match(self)
if r:
return r.group('email')
else:
return ''
class Post(object):
DEFAULT_ENCODING = u'ascii'
DEFAULT_AUTHOR = u'unknown author'
def __init__(self, f, markup=None):
if isinstance(f, basestring):
self._filename = f
input_file = open(f)
else:
self._filename = None
input_file = f
post_file = email.message_from_file(input_file)
# First get the file's encoding
self.encoding = unicode(post_file.get('encoding') or
self.DEFAULT_ENCODING)
try:
codecs.lookup(self.encoding)
except LookupError, e:
raise PostError(self.get_filename(), str(e))
# Copy all field "into the object" and convert string to unicode.
try:
for key, value in post_file.items():
self.__dict__[key.encode('ascii').lower()] = \
unicode(value, self.encoding)
except UnicodeDecodeError, e:
raise PostError(self.get_filename(), "for key '%s': %s" % (key, e))
if not hasattr(self, 'author'):
self.author = Author(self.DEFAULT_AUTHOR)
else:
self.author = Author(self.author)
# Handle the date. If no date was specified use the file's modification
# time.
if not hasattr(self, 'date'):
if not self._filename:
self.date = None
else:
# Get the date from file's mtime and issue a warning
mtime = stat(self._filename).st_mtime
self.date = datetime.datetime.fromtimestamp(mtime)
logging.warning("No date defined in '%s', using the file's "
"last modification time instead." % \
self._filename)
else:
try:
self.date = self.parse_date(self.date)
except ValueError, e:
raise PostError(self.get_filename(), str(e))
try:
self.ascii_title = self.title.encode('ascii', 'replace')
except UnicodeDecodeError, e:
raise PostError(self.get_filename(), 'Bad encoding in title')
if not post_file.get_payload():
raise PostError(self.get_filename(), 'does not have content')
try:
self.content = unicode(post_file.get_payload(), self.encoding)
except UnicodeDecodeError, e:
# find error line number
for line_number, line in enumerate(post_file.as_string().\
splitlines()):
try:
line.decode('ascii' if self.encoding == 'raw'
else self.encoding)
except UnicodeDecodeError, e:
break
# line_number starts at 0, real line number == line_number + 1
raise PostError(self.get_filename(),
'Bad encoding in content line %d, %s' % \
(line_number + 1, e))
if not markup: # Determine type via file extension
if self._filename and self._filename.endswith('.txt'):
self._markup = 'markdown'
elif self._filename and self._filename.endswith('.html'):
self._markup = 'html'
elif not self._filename:
self._markup = 'html'
else:
logging.warning("Unable to determine '%s' type, falling "
"back to HTML" % self._filename)
self._markup = 'html'
else:
assert markup in ('markdown', 'html')
self._markup = markup
# Transform the 'files' field into a list of string
if hasattr(self, 'files'):
self.files = self.files.split()
else:
self.files = list()
# FIXME prefix & suffix param or members of the class ?
def url(self, prefix=''):
'''
>>> file_content = """title: test
... date: 2008-1-1
...
... test"""
>>> from StringIO import StringIO
>>> Post(StringIO(file_content)).url()
'2008/1/1/test.html'
>>> Post(StringIO(file_content)).url('prefix/')
'prefix/2008/1/1/test.html'
>>> file_content = """title: Weird @!% filename
... date: 2008-1-1
...
... test"""
>>> Post(StringIO(file_content)).url()
'2008/1/1/Weird%20%40%21%25%20filename.html'
'''
return '%s%d/%d/%d/%s.html' % \
(prefix, self.date.year, self.date.month, self.date.day,
quote(self.ascii_title))
_DATE_FORMAT_LIST = ('%Y-%m-%d', '%y-%m-%d')
_DATETIME_FORMAT_LIST = \
tuple('%s %%H:%%M' % f for f in _DATE_FORMAT_LIST) + \
tuple('%s %%H:%%M:%%S' % f for f in _DATE_FORMAT_LIST)
@staticmethod
def parse_date(date_):
"""
>>> Post.parse_date('2006-1-1')
datetime.date(2006, 1, 1)
>>> Post.parse_date('2007-12-31')
datetime.date(2007, 12, 31)
>>> Post.parse_date('2008-4-05 12:35')
datetime.datetime(2008, 4, 5, 12, 35)
>>> Post.parse_date('10000-1-1')
Traceback (most recent call last):
...
ValueError: Unable to parse date '10000-1-1'
(Use YYYY-MM-DD [[HH:MM]:SS] format)
>>> Post.parse_date(2007)
Traceback (most recent call last):
...
TypeError: strptime() argument 1 must be string, not int
"""
for date_format in Post._DATE_FORMAT_LIST:
try:
return datetime.datetime.strptime(date_, date_format).date()
except ValueError:
continue
for date_format in Post._DATETIME_FORMAT_LIST:
try:
return datetime.datetime.strptime(date_, date_format)
except ValueError:
continue
raise ValueError('Unable to parse date \'%s\'\n'
'(Use YYYY-MM-DD [[HH:MM]:SS] format)' %
(date_))
def get_filename(self):
if not self._filename:
return '<unknown filename>'
else:
return self._filename
def get_html(self):
if self._markup == 'markdown':
return markdown(self.content, html4tags=True)
elif self._markup == 'html':
return self.content
else:
assert False, "Unknown type for %r" % self
def get_xhtml(self):
if self._markup == 'markdown':
return markdown(self.content, html4tags=False)
elif self._markup == 'html':
return html_to_xhtml(self.content)
else:
assert False, "Unknown type for %r" % self
def __cmp__(self, other):
'''
>>> file1 = "title: 1\\ndate: 2008-1-1\\n\\ntest"
>>> file2 = "title: 2\\ndate: 2007-12-31\\n\\ntest"
>>> from StringIO import StringIO
>>> Post(StringIO(file1)) > Post(StringIO(file2))
True
>>> Post(StringIO(file1)) == Post(StringIO(file2))
False
>>> Post(StringIO(file1)) == Post(StringIO(file1))
True
>>> l = [Post(StringIO(file2)), Post(StringIO(file1))]
>>> l.index(Post(StringIO(file1)))
1
'''
return cmp(unicode(self.date) + self.title,
unicode(other.date) + other.title)
def __hash__(self):
return hash(str(self.date) + self.title)
def __repr__(self):
return '<%s(%r, %r)>' % (self.__class__.__name__, self.title, self.date)
if __name__ == '__main__':
import doctest
doctest.testmod()
./weblog+jinja-1.1/weblog/publish.py 0100644 0001750 0000000 00000012100 11063022145 0016400 0 ustar 00henry wheel import os
import datetime
import logging
import codecs
from shutil import copy
import weblog
from _jinja_environment import jinja_environment
from html_full_url import html_full_url
from post import Post, PostError
from load import load_post_list, load_configuration
from listing import generate_index_listing
def generate_post_html(post_list, output_dir, post_tmpl, params):
for post in post_list:
logging.debug('Generating HTML file for %r', post)
dir = os.path.join(output_dir,
str(post.date.year),
str(post.date.month),
str(post.date.day))
if not os.path.exists(dir):
logging.debug('Creating \'%s\'', dir)
os.makedirs(dir)
elif not os.path.isdir(dir):
raise IOError('\'%s\' already exists and is not a directory' % dir)
top_dir = '../../../'
r = post_tmpl.render(title=post.title,
date=post.date,
author=post.author,
content=html_full_url(top_dir,
post.get_html()),
top_dir=top_dir,
**dict(((k, v) for k, v in
params.iteritems()
if k != 'title' and k != 'content')))
open(os.path.join(dir, post.ascii_title + '.html'), 'w').write(r)
def command_publish(args, options):
source_dir = options.source_dir
output_dir = options.output_dir
try:
config = load_configuration(options.configuration_file,
source_dir or '.')
except (KeyError, ValueError, IOError), error:
logging.error('Error while loading configuration file \'%s\'' %
options.configuration_file)
raise SystemExit(error)
source_dir = source_dir or config.get('source_dir', '.')
output_dir = output_dir or config.get('output_dir', 'output')
# add the default author & encoding constant to the post class
if 'encoding' in config:
Post.DEFAULT_ENCODING = config['encoding']
author = config.get('author', None)
if author:
Post.DEFAULT_AUTHOR = author
if not os.path.exists(output_dir):
os.mkdir(output_dir)
env = jinja_environment(source_dir)
try:
post_list = list(reversed(sorted(load_post_list(source_dir))))
except (IOError, PostError), e:
logging.error('Error while loading post files.')
raise SystemExit(e)
def generate_all():
params = dict(title=config['title'],
description=config.get('description'),
url=config['url'],
html_head=config.get('html_head'),
html_header=config.get('html_header'),
html_footer=config.get('html_footer'))
# generate the main index page
logging.debug('Generating HTML listings')
index_template = env.get_template('index.html.tmpl')
generate_index_listing(config['post_per_page'],
output_dir,
index_template,
post_list,
params)
logging.debug('Generating HTML posts files')
post_tmpl = env.get_template('post.html.tmpl')
generate_post_html(post_list, output_dir, post_tmpl, params)
# Copy all 'attached' files
for post in post_list:
for filename in post.files:
destination = os.path.join(output_dir, filename)
# Create the destination directory if it does not exist
destination_dir = os.path.dirname(destination)
# isdir returns False if the passed file does not exist
if not os.path.isdir(destination_dir):
os.makedirs(destination_dir)
copy(os.path.join(source_dir, filename), destination)
# Generate Atom feed
template = env.get_template('feed.atom.tmpl')
# Last time the feed was updated
posts = post_list[:config['feed_limit']]
if posts:
feed_updated = max(p.date for p in posts)
else:
feed_updated = datetime.datetime.utcnow()
atom_file = codecs.open(os.path.join(output_dir, 'feed.atom'), 'w',
encoding='utf8')
atom_file.write(template.render(posts=posts,
feed_updated=feed_updated,
weblog_version=weblog.__version__,
**params))
atom_file.close()
for f in config.get('extra_files', '').split():
copy(os.path.join(source_dir, f), output_dir)
if options.debug:
generate_all()
else:
try:
generate_all()
except IOError, e:
logging.error('Error while generating files ...')
raise SystemExit(e)
else:
logging.info('Successfully generated weblog.')
./weblog+jinja-1.1/weblog/rfc3339.py 0100644 0001750 0000000 00000016007 11063022145 0016040 0 ustar 00henry wheel #!/usr/bin/env python
'''
The function `rfc3339` formats dates according to the :RFC:`3339`. `rfc3339`
tries to have as much as possible sensible defaults.
'''
__author__ = 'Henry Precheur <henry@precheur.org>'
__license__ = 'Public Domain'
__version__ = '1'
__all__ = ('rfc3339', )
import datetime
import time
import unittest
def _timezone(utcoffset):
'''
Return a string representing the timezone offset.
>>> _timezone(0)
'+00:00'
>>> _timezone(3600)
'+01:00'
>>> _timezone(-28800)
'-08:00'
'''
# Python's division uses floor(), not round() like in other languages.
# >>> -1 / 2
# -1
hours = int(float(utcoffset)) // 3600
minutes = abs(utcoffset) % 3600 // 60
return '%+03d:%02d' % (hours, minutes)
def _timedelta_to_seconds(timedelta):
'''
>>> _timedelta_to_seconds(datetime.timedelta(hours=3))
10800
>>> _timedelta_to_seconds(datetime.timedelta(hours=3, minutes=15))
11700
'''
return (timedelta.days * 86400 + timedelta.seconds +
timedelta.microseconds // 1000)
def _utc_offset(date, use_system_timezone):
'''
Return the UTC offset of `date`. If `date` does not have any `tzinfo`, use
the timezone informations stored locally on the system.
>>> if time.daylight:
... system_timezone = -time.altzone
... else:
... system_timezone = -time.timezone
>>> _utc_offset(datetime.datetime.now(), True) == system_timezone
True
>>> _utc_offset(datetime.datetime.now(), False)
0
'''
if isinstance(date, datetime.datetime) and date.tzinfo is not None:
return _timedelta_to_seconds(date.dst() or date.utcoffset())
elif use_system_timezone:
if time.daylight:
return -time.altzone
else:
return -time.timezone
else:
return 0
def _utc_string(d):
return d.strftime('%Y-%m-%dT%H:%M:%SZ')
def rfc3339(date, utc=False, use_system_timezone=True):
'''
Return a string formatted according to the :RFC:`3339`. If called with
`utc=True`, it normalizes `date` to the UTC date. If `date` does not have
any timezone information, uses the local timezone::
>>> date = datetime.datetime(2008, 4, 2, 20)
>>> rfc3339(date, utc=True, use_system_timezone=False)
'2008-04-02T20:00:00Z'
>>> rfc3339(date) # doctest: +ELLIPSIS
'2008-04-02T20:00:00...'
If called with `user_system_time=False` don't use the local timezone if
`date` does not have timezone informations and consider the offset to UTC
to be zero::
>>> rfc3339(date, use_system_timezone=False)
'2008-04-02T20:00:00+00:00'
`date` must be a `datetime.datetime`, `datetime.date` or a timestamp as
returned by `time.time()`::
>>> rfc3339(0, utc=True, use_system_timezone=False)
'1970-01-01T00:00:00Z'
>>> rfc3339(datetime.date(2008, 9, 6), utc=True,
... use_system_timezone=False)
'2008-09-06T00:00:00Z'
>>> rfc3339(datetime.date(2008, 9, 6),
... use_system_timezone=False)
'2008-09-06T00:00:00+00:00'
>>> rfc3339('foo bar')
Traceback (most recent call last):
...
TypeError: excepted datetime, got str instead
'''
# Check if `date` is a timestamp.
try:
if utc:
return _utc_string(datetime.datetime.utcfromtimestamp(date))
else:
date = datetime.datetime.fromtimestamp(date)
except TypeError:
pass
if isinstance(date, datetime.date):
utcoffset = _utc_offset(date, use_system_timezone)
if utc:
if not isinstance(date, datetime.datetime):
date = datetime.datetime(*date.timetuple()[:3])
return _utc_string(date + datetime.timedelta(seconds=utcoffset))
else:
return date.strftime('%Y-%m-%dT%H:%M:%S') + _timezone(utcoffset)
else:
raise TypeError('excepted %s, got %s instead' %
(datetime.datetime.__name__, date.__class__.__name__))
class LocalTimeTestCase(unittest.TestCase):
'''
Test the use of the timezone saved locally. Since it is hard to test using
doctest.
'''
def setUp(self):
local_utcoffset = _utc_offset(datetime.datetime.now(), True)
self.local_utcoffset = datetime.timedelta(seconds=local_utcoffset)
self.local_timezone = _timezone(local_utcoffset)
def test_datetime(self):
d = datetime.datetime.now()
self.assertEqual(rfc3339(d),
d.strftime('%Y-%m-%dT%H:%M:%S') + self.local_timezone)
def test_datetime_timezone(self):
class FixedNoDst(datetime.tzinfo):
'A timezone info with fixed offset, not DST'
def utcoffset(self, dt):
return datetime.timedelta(hours=2, minutes=30)
def dst(self, dt):
return None
fixed_no_dst = FixedNoDst()
class Fixed(FixedNoDst):
'A timezone info with DST'
def dst(self, dt):
return datetime.timedelta(hours=3, minutes=15)
fixed = Fixed()
d = datetime.datetime.now().replace(tzinfo=fixed_no_dst)
timezone = _timezone(_timedelta_to_seconds(fixed_no_dst.\
utcoffset(None)))
self.assertEqual(rfc3339(d),
d.strftime('%Y-%m-%dT%H:%M:%S') + timezone)
d = datetime.datetime.now().replace(tzinfo=fixed)
timezone = _timezone(_timedelta_to_seconds(fixed.dst(None)))
self.assertEqual(rfc3339(d),
d.strftime('%Y-%m-%dT%H:%M:%S') + timezone)
def test_datetime_utc(self):
d = datetime.datetime.now()
d_utc = d + self.local_utcoffset
self.assertEqual(rfc3339(d, utc=True),
d_utc.strftime('%Y-%m-%dT%H:%M:%SZ'))
def test_date(self):
d = datetime.date.today()
self.assertEqual(rfc3339(d),
d.strftime('%Y-%m-%dT%H:%M:%S') + self.local_timezone)
def test_date_utc(self):
d = datetime.date.today()
# Convert `date` to `datetime`, since `date` ignores seconds and hours
# in timedeltas:
# >>> datetime.date(2008, 9, 7) + datetime.timedelta(hours=23)
# datetime.date(2008, 9, 7)
d_utc = datetime.datetime(*d.timetuple()[:3]) + self.local_utcoffset
self.assertEqual(rfc3339(d, utc=True),
d_utc.strftime('%Y-%m-%dT%H:%M:%SZ'))
def test_timestamp(self):
d = time.time()
self.assertEqual(rfc3339(d),
datetime.datetime.fromtimestamp(d).\
strftime('%Y-%m-%dT%H:%M:%S') + self.local_timezone)
def test_timestamp_utc(self):
d = time.time()
d_utc = datetime.datetime.utcfromtimestamp(d) + self.local_utcoffset
self.assertEqual(rfc3339(d),
(d_utc.strftime('%Y-%m-%dT%H:%M:%S') +
self.local_timezone))
if __name__ == '__main__':
import doctest
doctest.testmod()
unittest.main()
./weblog+jinja-1.1/weblog/utf8_html_parser.py 0100644 0001750 0000000 00000004370 11063022145 0020232 0 ustar 00henry wheel from cgi import escape
from HTMLParser import HTMLParser
class UTF8HTMLParser(HTMLParser):
'''
Parse a HTML document and convert all nodes to UTF-8::
>>> parser = UTF8HTMLParser()
>>> parser.feed("<p>Hello <a href='crazy'>world</a></p>")
>>> parser.get_value()
u"<p>Hello <a href='crazy'>world</a></p>"
>>> parser.feed('<p>Another sentence.</p>')
>>> parser.get_value()
u"<p>Hello <a href='crazy'>world</a></p><p>Another sentence.</p>"
`reset()` resets the parser::
>>> parser.reset()
>>> parser.get_value()
u''
'''
def __init__(self):
HTMLParser.__init__(self)
self.output = list()
def reset(self):
HTMLParser.reset(self)
self.output = list()
def get_value(self):
return u''.join(self.output)
@staticmethod
def html_attrs(attrs):
'''
>>> UTF8HTMLParser.html_attrs((('src', 'pic.jpg'), ('alt', 'pic')))
u"src='pic.jpg' alt='pic'"
>>> UTF8HTMLParser.html_attrs(list())
u''
>>> UTF8HTMLParser.html_attrs((('href', 'sample?foo=1&bar=2'),))
u"href='sample?foo=1&bar=2'"
'''
# HTMLParser unescape attributes values, we don't want that.
return u' '.join(u'%s=\'%s\'' % (k, escape(v)) for k, v in attrs)
def handle_starttag(self, tag, attrs):
if attrs:
self.output.append(u'<%s %s>' % (tag,
self.html_attrs(attrs)))
else:
self.output.append(u'<%s>' % tag)
def handle_startendtag(self, tag, attrs):
self.handle_starttag(tag, attrs)
def handle_endtag(self, tag):
self.output.append(u'</%s>' % tag)
def handle_data(self, data):
self.output.append(data)
def handle_charref(self, name):
self.output.append(u'&#%s;' % name)
def handle_entityref(self, name):
self.output.append(u'&%s;' % name)
def handle_comment(self, comment):
self.output.append(u'<!-- %s -->' % comment)
def handle_decl(self, decl):
self.output.append(u'<!%s>' % decl)
def handle_pi(self, pi):
self.output.append(u'<?%s>' % pi)
if __name__ == '__main__':
import doctest
doctest.testmod()
./weblog+jinja-1.1/weblog/utils.py 0100644 0001750 0000000 00000003075 11063022145 0016105 0 ustar 00henry wheel import os
import logging
import datetime
from cgi import escape
def load_if_filename(source_dir, f):
'''
If ``f`` is a filename. Read it and returns the content. Else return ``f``.
If ``bool(f)`` is false returns ``None``.
# Assumes that there is no file named 'This is not a file' in the current
# directory ;-)
>>> load_if_filename('.', 'This is not a file')
'This is not a file'
>>> load_if_filename('.', '')
>>> load_if_filename('.', list())
>>> load_if_filename('.', None)
'''
if not f:
return
full = os.path.join(source_dir, f)
if os.path.exists(full):
return file(full).read()
else:
return f
def format_date(date):
'''
Return a string representing a ``date`` or a ``datetime``.
>>> format_date(datetime.datetime(2008, 1, 1, 20, 40, 23, 345))
'2008-01-01 20:40:23'
>>> format_date(datetime.datetime(2008, 1, 1))
'2008-01-01 00:00:00'
>>> format_date(datetime.date(2008, 1, 1))
'2008-01-01'
>>> format_date(datetime.time())
Traceback (most recent call last):
...
TypeError: expected date or datetime, got time instead
'''
if isinstance(date, datetime.datetime):
return date.strftime('%Y-%m-%d %H:%M:%S')
elif isinstance(date, datetime.date):
return str(date)
else:
raise TypeError('expected %s or %s, got %s instead' %
(datetime.date.__name__, datetime.datetime.__name__,
date.__class__.__name__))
if __name__ == '__main__':
import doctest
doctest.testmod()
./weblog+jinja-1.1/jinja2 0040755 0001750 0000000 00000000000 11063003705 0014211 5 ustar 00henry wheel ./weblog+jinja-1.1/jinja2/visitor.py 0100644 0001750 0000000 00000006372 11063022145 0016345 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.visitor
~~~~~~~~~~~~~~
This module implements a visitor for the nodes.
:copyright: Copyright 2008 by Armin Ronacher.
:license: BSD.
"""
from jinja2.nodes import Node
class NodeVisitor(object):
"""Walks the abstract syntax tree and call visitor functions for every
node found. The visitor functions may return values which will be
forwarded by the `visit` method.
Per default the visitor functions for the nodes are ``'visit_'`` +
class name of the node. So a `TryFinally` node visit function would
be `visit_TryFinally`. This behavior can be changed by overriding
the `get_visitor` function. If no visitor function exists for a node
(return value `None`) the `generic_visit` visitor is used instead.
"""
def get_visitor(self, node):
"""Return the visitor function for this node or `None` if no visitor
exists for this node. In that case the generic visit function is
used instead.
"""
method = 'visit_' + node.__class__.__name__
return getattr(self, method, None)
def visit(self, node, *args, **kwargs):
"""Visit a node."""
f = self.get_visitor(node)
if f is not None:
return f(node, *args, **kwargs)
return self.generic_visit(node, *args, **kwargs)
def generic_visit(self, node, *args, **kwargs):
"""Called if no explicit visitor function exists for a node."""
for node in node.iter_child_nodes():
self.visit(node, *args, **kwargs)
class NodeTransformer(NodeVisitor):
"""Walks the abstract syntax tree and allows modifications of nodes.
The `NodeTransformer` will walk the AST and use the return value of the
visitor functions to replace or remove the old node. If the return
value of the visitor function is `None` the node will be removed
from the previous location otherwise it's replaced with the return
value. The return value may be the original node in which case no
replacement takes place.
"""
def generic_visit(self, node, *args, **kwargs):
for field, old_value in node.iter_fields():
if isinstance(old_value, list):
new_values = []
for value in old_value:
if isinstance(value, Node):
value = self.visit(value, *args, **kwargs)
if value is None:
continue
elif not isinstance(value, Node):
new_values.extend(value)
continue
new_values.append(value)
old_value[:] = new_values
elif isinstance(old_value, Node):
new_node = self.visit(old_value, *args, **kwargs)
if new_node is None:
delattr(node, field)
else:
setattr(node, field, new_node)
return node
def visit_list(self, node, *args, **kwargs):
"""As transformers may return lists in some places this method
can be used to enforce a list as return value.
"""
rv = self.visit(node, *args, **kwargs)
if not isinstance(rv, list):
rv = [rv]
return rv
./weblog+jinja-1.1/jinja2/_speedups.c 0100644 0001750 0000000 00000013261 11063022145 0016422 0 ustar 00henry wheel /**
* jinja2._speedups
* ~~~~~~~~~~~~~~~~
*
* This module implements functions for automatic escaping in C for better
* performance. Additionally it defines a `tb_set_next` function to patch the
* debug traceback. If the speedups module is not compiled a ctypes
* implementation of `tb_set_next` and Python implementations of the other
* functions are used.
*
* :copyright: 2008 by Armin Ronacher, Mickaël Guérin.
* :license: BSD.
*/
#include <Python.h>
#define ESCAPED_CHARS_TABLE_SIZE 63
#define UNICHR(x) (((PyUnicodeObject*)PyUnicode_DecodeASCII(x, strlen(x), NULL))->str);
#if PY_VERSION_HEX < 0x02050000 && !defined(PY_SSIZE_T_MIN)
typedef int Py_ssize_t;
#define PY_SSIZE_T_MAX INT_MAX
#define PY_SSIZE_T_MIN INT_MIN
#endif
static PyObject* markup;
static Py_ssize_t escaped_chars_delta_len[ESCAPED_CHARS_TABLE_SIZE];
static Py_UNICODE *escaped_chars_repl[ESCAPED_CHARS_TABLE_SIZE];
static int
init_constants(void)
{
PyObject *module;
/* happing of characters to replace */
escaped_chars_repl['"'] = UNICHR(""");
escaped_chars_repl['\''] = UNICHR("'");
escaped_chars_repl['&'] = UNICHR("&");
escaped_chars_repl['<'] = UNICHR("<");
escaped_chars_repl['>'] = UNICHR(">");
/* lengths of those characters when replaced - 1 */
memset(escaped_chars_delta_len, 0, sizeof (escaped_chars_delta_len));
escaped_chars_delta_len['"'] = escaped_chars_delta_len['\''] = \
escaped_chars_delta_len['&'] = 4;
escaped_chars_delta_len['<'] = escaped_chars_delta_len['>'] = 3;
/* import markup type so that we can mark the return value */
module = PyImport_ImportModule("jinja2.utils");
if (!module)
return 0;
markup = PyObject_GetAttrString(module, "Markup");
Py_DECREF(module);
return 1;
}
static PyObject*
escape_unicode(PyUnicodeObject *in)
{
PyUnicodeObject *out;
Py_UNICODE *inp = in->str;
const Py_UNICODE *inp_end = in->str + in->length;
Py_UNICODE *next_escp;
Py_UNICODE *outp;
Py_ssize_t delta=0, erepl=0, delta_len=0;
/* First we need to figure out how long the escaped string will be */
while (*(inp) || inp < inp_end) {
if (*inp < ESCAPED_CHARS_TABLE_SIZE && escaped_chars_delta_len[*inp]) {
delta += escaped_chars_delta_len[*inp];
++erepl;
}
++inp;
}
/* Do we need to escape anything at all? */
if (!erepl) {
Py_INCREF(in);
return (PyObject*)in;
}
out = (PyUnicodeObject*)PyUnicode_FromUnicode(NULL, in->length + delta);
if (!out)
return NULL;
outp = out->str;
inp = in->str;
while (erepl-- > 0) {
/* look for the next substitution */
next_escp = inp;
while (next_escp < inp_end) {
if (*next_escp < ESCAPED_CHARS_TABLE_SIZE &&
(delta_len = escaped_chars_delta_len[*next_escp])) {
++delta_len;
break;
}
++next_escp;
}
if (next_escp > inp) {
/* copy unescaped chars between inp and next_escp */
Py_UNICODE_COPY(outp, inp, next_escp-inp);
outp += next_escp - inp;
}
/* escape 'next_escp' */
Py_UNICODE_COPY(outp, escaped_chars_repl[*next_escp], delta_len);
outp += delta_len;
inp = next_escp + 1;
}
if (inp < inp_end)
Py_UNICODE_COPY(outp, inp, in->length - (inp - in->str));
return (PyObject*)out;
}
static PyObject*
escape(PyObject *self, PyObject *text)
{
PyObject *s = NULL, *rv = NULL, *html;
/* we don't have to escape integers, bools or floats */
if (PyInt_CheckExact(text) || PyLong_CheckExact(text) ||
PyFloat_CheckExact(text) || PyBool_Check(text) ||
text == Py_None)
return PyObject_CallFunctionObjArgs(markup, text, NULL);
/* if the object has an __html__ method that performs the escaping */
html = PyObject_GetAttrString(text, "__html__");
if (html) {
rv = PyObject_CallObject(html, NULL);
Py_DECREF(html);
return rv;
}
/* otherwise make the object unicode if it isn't, then escape */
PyErr_Clear();
if (!PyUnicode_Check(text)) {
PyObject *unicode = PyObject_Unicode(text);
if (!unicode)
return NULL;
s = escape_unicode((PyUnicodeObject*)unicode);
Py_DECREF(unicode);
}
else
s = escape_unicode((PyUnicodeObject*)text);
/* convert the unicode string into a markup object. */
rv = PyObject_CallFunctionObjArgs(markup, (PyObject*)s, NULL);
Py_DECREF(s);
return rv;
}
static PyObject*
soft_unicode(PyObject *self, PyObject *s)
{
if (!PyUnicode_Check(s))
return PyObject_Unicode(s);
Py_INCREF(s);
return s;
}
static PyObject*
tb_set_next(PyObject *self, PyObject *args)
{
PyTracebackObject *tb, *old;
PyObject *next;
if (!PyArg_ParseTuple(args, "O!O:tb_set_next", &PyTraceBack_Type, &tb, &next))
return NULL;
if (next == Py_None)
next = NULL;
else if (!PyTraceBack_Check(next)) {
PyErr_SetString(PyExc_TypeError,
"tb_set_next arg 2 must be traceback or None");
return NULL;
}
else
Py_INCREF(next);
old = tb->tb_next;
tb->tb_next = (PyTracebackObject*)next;
Py_XDECREF(old);
Py_INCREF(Py_None);
return Py_None;
}
static PyMethodDef module_methods[] = {
{"escape", (PyCFunction)escape, METH_O,
"escape(s) -> markup\n\n"
"Convert the characters &, <, >, ', and \" in string s to HTML-safe\n"
"sequences. Use this if you need to display text that might contain\n"
"such characters in HTML. Marks return value as markup string."},
{"soft_unicode", (PyCFunction)soft_unicode, METH_O,
"soft_unicode(object) -> string\n\n"
"Make a string unicode if it isn't already. That way a markup\n"
"string is not converted back to unicode."},
{"tb_set_next", (PyCFunction)tb_set_next, METH_VARARGS,
"Set the tb_next member of a traceback object."},
{NULL, NULL, 0, NULL} /* Sentinel */
};
#ifndef PyMODINIT_FUNC /* declarations for DLL import/export */
#define PyMODINIT_FUNC void
#endif
PyMODINIT_FUNC
init_speedups(void)
{
if (!init_constants())
return;
Py_InitModule3("jinja2._speedups", module_methods, "");
}
./weblog+jinja-1.1/jinja2/compiler.py 0100644 0001750 0000000 00000145462 11063022145 0016464 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.compiler
~~~~~~~~~~~~~~~
Compiles nodes into python code.
:copyright: Copyright 2008 by Armin Ronacher.
:license: BSD.
"""
from copy import copy
from keyword import iskeyword
from cStringIO import StringIO
from itertools import chain
from jinja2 import nodes
from jinja2.visitor import NodeVisitor, NodeTransformer
from jinja2.exceptions import TemplateAssertionError
from jinja2.utils import Markup, concat, escape
operators = {
'eq': '==',
'ne': '!=',
'gt': '>',
'gteq': '>=',
'lt': '<',
'lteq': '<=',
'in': 'in',
'notin': 'not in'
}
try:
exec '(0 if 0 else 0)'
except SyntaxError:
have_condexpr = False
else:
have_condexpr = True
def generate(node, environment, name, filename, stream=None):
"""Generate the python source for a node tree."""
if not isinstance(node, nodes.Template):
raise TypeError('Can\'t compile non template nodes')
generator = CodeGenerator(environment, name, filename, stream)
generator.visit(node)
if stream is None:
return generator.stream.getvalue()
def has_safe_repr(value):
"""Does the node have a safe representation?"""
if value is None or value is NotImplemented or value is Ellipsis:
return True
if isinstance(value, (bool, int, long, float, complex, basestring,
xrange, Markup)):
return True
if isinstance(value, (tuple, list, set, frozenset)):
for item in value:
if not has_safe_repr(item):
return False
return True
elif isinstance(value, dict):
for key, value in value.iteritems():
if not has_safe_repr(key):
return False
if not has_safe_repr(value):
return False
return True
return False
def find_undeclared(nodes, names):
"""Check if the names passed are accessed undeclared. The return value
is a set of all the undeclared names from the sequence of names found.
"""
visitor = UndeclaredNameVisitor(names)
try:
for node in nodes:
visitor.visit(node)
except VisitorExit:
pass
return visitor.undeclared
class Identifiers(object):
"""Tracks the status of identifiers in frames."""
def __init__(self):
# variables that are known to be declared (probably from outer
# frames or because they are special for the frame)
self.declared = set()
# undeclared variables from outer scopes
self.outer_undeclared = set()
# names that are accessed without being explicitly declared by
# this one or any of the outer scopes. Names can appear both in
# declared and undeclared.
self.undeclared = set()
# names that are declared locally
self.declared_locally = set()
# names that are declared by parameters
self.declared_parameter = set()
def add_special(self, name):
"""Register a special name like `loop`."""
self.undeclared.discard(name)
self.declared.add(name)
def is_declared(self, name, local_only=False):
"""Check if a name is declared in this or an outer scope."""
if name in self.declared_locally or name in self.declared_parameter:
return True
if local_only:
return False
return name in self.declared
def find_shadowed(self):
"""Find all the shadowed names."""
return (self.declared | self.outer_undeclared) & \
(self.declared_locally | self.declared_parameter)
class Frame(object):
"""Holds compile time information for us."""
def __init__(self, parent=None):
self.identifiers = Identifiers()
# a toplevel frame is the root + soft frames such as if conditions.
self.toplevel = False
# the root frame is basically just the outermost frame, so no if
# conditions. This information is used to optimize inheritance
# situations.
self.rootlevel = False
# inside some tags we are using a buffer rather than yield statements.
# this for example affects {% filter %} or {% macro %}. If a frame
# is buffered this variable points to the name of the list used as
# buffer.
self.buffer = None
# the name of the block we're in, otherwise None.
self.block = parent and parent.block or None
# the parent of this frame
self.parent = parent
if parent is not None:
self.identifiers.declared.update(
parent.identifiers.declared |
parent.identifiers.declared_locally |
parent.identifiers.declared_parameter |
parent.identifiers.undeclared
)
self.identifiers.outer_undeclared.update(
parent.identifiers.undeclared -
self.identifiers.declared
)
self.buffer = parent.buffer
def copy(self):
"""Create a copy of the current one."""
rv = copy(self)
rv.identifiers = copy(self.identifiers)
return rv
def inspect(self, nodes, hard_scope=False):
"""Walk the node and check for identifiers. If the scope is hard (eg:
enforce on a python level) overrides from outer scopes are tracked
differently.
"""
visitor = FrameIdentifierVisitor(self.identifiers, hard_scope)
for node in nodes:
visitor.visit(node)
def inner(self):
"""Return an inner frame."""
return Frame(self)
def soft(self):
"""Return a soft frame. A soft frame may not be modified as
standalone thing as it shares the resources with the frame it
was created of, but it's not a rootlevel frame any longer.
"""
rv = copy(self)
rv.rootlevel = False
return rv
class VisitorExit(RuntimeError):
"""Exception used by the `UndeclaredNameVisitor` to signal a stop."""
class DependencyFinderVisitor(NodeVisitor):
"""A visitor that collects filter and test calls."""
def __init__(self):
self.filters = set()
self.tests = set()
def visit_Filter(self, node):
self.generic_visit(node)
self.filters.add(node.name)
def visit_Test(self, node):
self.generic_visit(node)
self.tests.add(node.name)
def visit_Block(self, node):
"""Stop visiting at blocks."""
class UndeclaredNameVisitor(NodeVisitor):
"""A visitor that checks if a name is accessed without being
declared. This is different from the frame visitor as it will
not stop at closure frames.
"""
def __init__(self, names):
self.names = set(names)
self.undeclared = set()
def visit_Name(self, node):
if node.ctx == 'load' and node.name in self.names:
self.undeclared.add(node.name)
if self.undeclared == self.names:
raise VisitorExit()
else:
self.names.discard(node.name)
def visit_Block(self, node):
"""Stop visiting a blocks."""
class FrameIdentifierVisitor(NodeVisitor):
"""A visitor for `Frame.inspect`."""
def __init__(self, identifiers, hard_scope):
self.identifiers = identifiers
self.hard_scope = hard_scope
def visit_Name(self, node):
"""All assignments to names go through this function."""
if node.ctx == 'store':
self.identifiers.declared_locally.add(node.name)
elif node.ctx == 'param':
self.identifiers.declared_parameter.add(node.name)
elif node.ctx == 'load' and not \
self.identifiers.is_declared(node.name, self.hard_scope):
self.identifiers.undeclared.add(node.name)
def visit_Macro(self, node):
self.identifiers.declared_locally.add(node.name)
def visit_Import(self, node):
self.generic_visit(node)
self.identifiers.declared_locally.add(node.target)
def visit_FromImport(self, node):
self.generic_visit(node)
for name in node.names:
if isinstance(name, tuple):
self.identifiers.declared_locally.add(name[1])
else:
self.identifiers.declared_locally.add(name)
def visit_Assign(self, node):
"""Visit assignments in the correct order."""
self.visit(node.node)
self.visit(node.target)
def visit_For(self, node):
"""Visiting stops at for blocks. However the block sequence
is visited as part of the outer scope.
"""
self.visit(node.iter)
def visit_CallBlock(self, node):
for child in node.iter_child_nodes(exclude=('body',)):
self.visit(child)
def visit_FilterBlock(self, node):
self.visit(node.filter)
def visit_Block(self, node):
"""Stop visiting at blocks."""
class CompilerExit(Exception):
"""Raised if the compiler encountered a situation where it just
doesn't make sense to further process the code. Any block that
raises such an exception is not further processed.
"""
class CodeGenerator(NodeVisitor):
def __init__(self, environment, name, filename, stream=None):
if stream is None:
stream = StringIO()
self.environment = environment
self.name = name
self.filename = filename
self.stream = stream
# aliases for imports
self.import_aliases = {}
# a registry for all blocks. Because blocks are moved out
# into the global python scope they are registered here
self.blocks = {}
# the number of extends statements so far
self.extends_so_far = 0
# some templates have a rootlevel extends. In this case we
# can safely assume that we're a child template and do some
# more optimizations.
self.has_known_extends = False
# the current line number
self.code_lineno = 1
# registry of all filters and tests (global, not block local)
self.tests = {}
self.filters = {}
# the debug information
self.debug_info = []
self._write_debug_info = None
# the number of new lines before the next write()
self._new_lines = 0
# the line number of the last written statement
self._last_line = 0
# true if nothing was written so far.
self._first_write = True
# used by the `temporary_identifier` method to get new
# unique, temporary identifier
self._last_identifier = 0
# the current indentation
self._indentation = 0
# -- Various compilation helpers
def fail(self, msg, lineno):
"""Fail with a `TemplateAssertionError`."""
raise TemplateAssertionError(msg, lineno, self.name, self.filename)
def temporary_identifier(self):
"""Get a new unique identifier."""
self._last_identifier += 1
return 't_%d' % self._last_identifier
def buffer(self, frame):
"""Enable buffering for the frame from that point onwards."""
frame.buffer = self.temporary_identifier()
self.writeline('%s = []' % frame.buffer)
def return_buffer_contents(self, frame):
"""Return the buffer contents of the frame."""
if self.environment.autoescape:
self.writeline('return Markup(concat(%s))' % frame.buffer)
else:
self.writeline('return concat(%s)' % frame.buffer)
def indent(self):
"""Indent by one."""
self._indentation += 1
def outdent(self, step=1):
"""Outdent by step."""
self._indentation -= step
def start_write(self, frame, node=None):
"""Yield or write into the frame buffer."""
if frame.buffer is None:
self.writeline('yield ', node)
else:
self.writeline('%s.append(' % frame.buffer, node)
def end_write(self, frame):
"""End the writing process started by `start_write`."""
if frame.buffer is not None:
self.write(')')
def simple_write(self, s, frame, node=None):
"""Simple shortcut for start_write + write + end_write."""
self.start_write(frame, node)
self.write(s)
self.end_write(frame)
def blockvisit(self, nodes, frame, force_generator=True):
"""Visit a list of nodes as block in a frame. If the current frame
is no buffer a dummy ``if 0: yield None`` is written automatically
unless the force_generator parameter is set to False.
"""
if frame.buffer is None and force_generator:
self.writeline('if 0: yield None')
try:
for node in nodes:
self.visit(node, frame)
except CompilerExit:
pass
def write(self, x):
"""Write a string into the output stream."""
if self._new_lines:
if not self._first_write:
self.stream.write('\n' * self._new_lines)
self.code_lineno += self._new_lines
if self._write_debug_info is not None:
self.debug_info.append((self._write_debug_info,
self.code_lineno))
self._write_debug_info = None
self._first_write = False
self.stream.write(' ' * self._indentation)
self._new_lines = 0
self.stream.write(x)
def writeline(self, x, node=None, extra=0):
"""Combination of newline and write."""
self.newline(node, extra)
self.write(x)
def newline(self, node=None, extra=0):
"""Add one or more newlines before the next write."""
self._new_lines = max(self._new_lines, 1 + extra)
if node is not None and node.lineno != self._last_line:
self._write_debug_info = node.lineno
self._last_line = node.lineno
def signature(self, node, frame, extra_kwargs=None):
"""Writes a function call to the stream for the current node.
A leading comma is added automatically. The extra keyword
arguments may not include python keywords otherwise a syntax
error could occour. The extra keyword arguments should be given
as python dict.
"""
# if any of the given keyword arguments is a python keyword
# we have to make sure that no invalid call is created.
kwarg_workaround = False
for kwarg in chain((x.key for x in node.kwargs), extra_kwargs or ()):
if iskeyword(kwarg):
kwarg_workaround = True
break
for arg in node.args:
self.write(', ')
self.visit(arg, frame)
if not kwarg_workaround:
for kwarg in node.kwargs:
self.write(', ')
self.visit(kwarg, frame)
if extra_kwargs is not None:
for key, value in extra_kwargs.iteritems():
self.write(', %s=%s' % (key, value))
if node.dyn_args:
self.write(', *')
self.visit(node.dyn_args, frame)
if kwarg_workaround:
if node.dyn_kwargs is not None:
self.write(', **dict({')
else:
self.write(', **{')
for kwarg in node.kwargs:
self.write('%r: ' % kwarg.key)
self.visit(kwarg.value, frame)
self.write(', ')
if extra_kwargs is not None:
for key, value in extra_kwargs.iteritems():
self.write('%r: %s, ' % (key, value))
if node.dyn_kwargs is not None:
self.write('}, **')
self.visit(node.dyn_kwargs, frame)
self.write(')')
else:
self.write('}')
elif node.dyn_kwargs is not None:
self.write(', **')
self.visit(node.dyn_kwargs, frame)
def pull_locals(self, frame):
"""Pull all the references identifiers into the local scope."""
for name in frame.identifiers.undeclared:
self.writeline('l_%s = context.resolve(%r)' % (name, name))
def pull_dependencies(self, nodes):
"""Pull all the dependencies."""
visitor = DependencyFinderVisitor()
for node in nodes:
visitor.visit(node)
for dependency in 'filters', 'tests':
mapping = getattr(self, dependency)
for name in getattr(visitor, dependency):
if name not in mapping:
mapping[name] = self.temporary_identifier()
self.writeline('%s = environment.%s[%r]' %
(mapping[name], dependency, name))
def collect_shadowed(self, frame):
"""This function returns all the shadowed variables in a dict
in the form name: alias and will write the required assignments
into the current scope. No indentation takes place.
"""
aliases = {}
for name in frame.identifiers.find_shadowed():
aliases[name] = ident = self.temporary_identifier()
self.writeline('%s = l_%s' % (ident, name))
return aliases
def restore_shadowed(self, aliases):
"""Restore all aliases."""
for name, alias in aliases.iteritems():
self.writeline('l_%s = %s' % (name, alias))
def function_scoping(self, node, frame, children=None,
find_special=True):
"""In Jinja a few statements require the help of anonymous
functions. Those are currently macros and call blocks and in
the future also recursive loops. As there is currently
technical limitation that doesn't allow reading and writing a
variable in a scope where the initial value is coming from an
outer scope, this function tries to fall back with a common
error message. Additionally the frame passed is modified so
that the argumetns are collected and callers are looked up.
This will return the modified frame.
"""
# we have to iterate twice over it, make sure that works
if children is None:
children = node.iter_child_nodes()
children = list(children)
func_frame = frame.inner()
func_frame.inspect(children, hard_scope=True)
# variables that are undeclared (accessed before declaration) and
# declared locally *and* part of an outside scope raise a template
# assertion error. Reason: we can't generate reasonable code from
# it without aliasing all the variables. XXX: alias them ^^
overriden_closure_vars = (
func_frame.identifiers.undeclared &
func_frame.identifiers.declared &
(func_frame.identifiers.declared_locally |
func_frame.identifiers.declared_parameter)
)
if overriden_closure_vars:
self.fail('It\'s not possible to set and access variables '
'derived from an outer scope! (affects: %s' %
', '.join(sorted(overriden_closure_vars)), node.lineno)
# remove variables from a closure from the frame's undeclared
# identifiers.
func_frame.identifiers.undeclared -= (
func_frame.identifiers.undeclared &
func_frame.identifiers.declared
)
# no special variables for this scope, abort early
if not find_special:
return func_frame
func_frame.accesses_kwargs = False
func_frame.accesses_varargs = False
func_frame.accesses_caller = False
func_frame.arguments = args = ['l_' + x.name for x in node.args]
undeclared = find_undeclared(children, ('caller', 'kwargs', 'varargs'))
if 'caller' in undeclared:
func_frame.accesses_caller = True
func_frame.identifiers.add_special('caller')
args.append('l_caller')
if 'kwargs' in undeclared:
func_frame.accesses_kwargs = True
func_frame.identifiers.add_special('kwargs')
args.append('l_kwargs')
if 'varargs' in undeclared:
func_frame.accesses_varargs = True
func_frame.identifiers.add_special('varargs')
args.append('l_varargs')
return func_frame
def macro_body(self, node, frame, children=None):
"""Dump the function def of a macro or call block."""
frame = self.function_scoping(node, frame, children)
args = frame.arguments
self.writeline('def macro(%s):' % ', '.join(args), node)
self.indent()
self.buffer(frame)
self.pull_locals(frame)
self.blockvisit(node.body, frame)
self.return_buffer_contents(frame)
self.outdent()
return frame
def macro_def(self, node, frame):
"""Dump the macro definition for the def created by macro_body."""
arg_tuple = ', '.join(repr(x.name) for x in node.args)
name = getattr(node, 'name', None)
if len(node.args) == 1:
arg_tuple += ','
self.write('Macro(environment, macro, %r, (%s), (' %
(name, arg_tuple))
for arg in node.defaults:
self.visit(arg, frame)
self.write(', ')
self.write('), %r, %r, %r)' % (
bool(frame.accesses_kwargs),
bool(frame.accesses_varargs),
bool(frame.accesses_caller)
))
def position(self, node):
"""Return a human readable position for the node."""
rv = 'line %d' % node.lineno
if self.name is not None:
rv += ' in' + repr(self.name)
return rv
# -- Statement Visitors
def visit_Template(self, node, frame=None):
assert frame is None, 'no root frame allowed'
from jinja2.runtime import __all__ as exported
self.writeline('from __future__ import division')
self.writeline('from jinja2.runtime import ' + ', '.join(exported))
# do we have an extends tag at all? If not, we can save some
# overhead by just not processing any inheritance code.
have_extends = node.find(nodes.Extends) is not None
# find all blocks
for block in node.find_all(nodes.Block):
if block.name in self.blocks:
self.fail('block %r defined twice' % block.name, block.lineno)
self.blocks[block.name] = block
# find all imports and import them
for import_ in node.find_all(nodes.ImportedName):
if import_.importname not in self.import_aliases:
imp = import_.importname
self.import_aliases[imp] = alias = self.temporary_identifier()
if '.' in imp:
module, obj = imp.rsplit('.', 1)
self.writeline('from %s import %s as %s' %
(module, obj, alias))
else:
self.writeline('import %s as %s' % (imp, alias))
# add the load name
self.writeline('name = %r' % self.name)
# generate the root render function.
self.writeline('def root(context, environment=environment):', extra=1)
# process the root
frame = Frame()
frame.inspect(node.body)
frame.toplevel = frame.rootlevel = True
self.indent()
if have_extends:
self.writeline('parent_template = None')
if 'self' in find_undeclared(node.body, ('self',)):
frame.identifiers.add_special('self')
self.writeline('l_self = TemplateReference(context)')
self.pull_locals(frame)
self.pull_dependencies(node.body)
self.blockvisit(node.body, frame)
self.outdent()
# make sure that the parent root is called.
if have_extends:
if not self.has_known_extends:
self.indent()
self.writeline('if parent_template is not None:')
self.indent()
self.writeline('for event in parent_template.'
'root_render_func(context):')
self.indent()
self.writeline('yield event')
self.outdent(2 + (not self.has_known_extends))
# at this point we now have the blocks collected and can visit them too.
for name, block in self.blocks.iteritems():
block_frame = Frame()
block_frame.inspect(block.body)
block_frame.block = name
self.writeline('def block_%s(context, environment=environment):'
% name, block, 1)
self.indent()
undeclared = find_undeclared(block.body, ('self', 'super'))
if 'self' in undeclared:
block_frame.identifiers.add_special('self')
self.writeline('l_self = TemplateReference(context)')
if 'super' in undeclared:
block_frame.identifiers.add_special('super')
self.writeline('l_super = context.super(%r, '
'block_%s)' % (name, name))
self.pull_locals(block_frame)
self.pull_dependencies(block.body)
self.blockvisit(block.body, block_frame)
self.outdent()
self.writeline('blocks = {%s}' % ', '.join('%r: block_%s' % (x, x)
for x in self.blocks),
extra=1)
# add a function that returns the debug info
self.writeline('debug_info = %r' % '&'.join('%s=%s' % x for x
in self.debug_info))
def visit_Block(self, node, frame):
"""Call a block and register it for the template."""
level = 1
if frame.toplevel:
# if we know that we are a child template, there is no need to
# check if we are one
if self.has_known_extends:
return
if self.extends_so_far > 0:
self.writeline('if parent_template is None:')
self.indent()
level += 1
self.writeline('for event in context.blocks[%r][0](context):' %
node.name, node)
self.indent()
self.simple_write('event', frame)
self.outdent(level)
def visit_Extends(self, node, frame):
"""Calls the extender."""
if not frame.toplevel:
self.fail('cannot use extend from a non top-level scope',
node.lineno)
# if the number of extends statements in general is zero so
# far, we don't have to add a check if something extended
# the template before this one.
if self.extends_so_far > 0:
# if we have a known extends we just add a template runtime
# error into the generated code. We could catch that at compile
# time too, but i welcome it not to confuse users by throwing the
# same error at different times just "because we can".
if not self.has_known_extends:
self.writeline('if parent_template is not None:')
self.indent()
self.writeline('raise TemplateRuntimeError(%r)' %
'extended multiple times')
# if we have a known extends already we don't need that code here
# as we know that the template execution will end here.
if self.has_known_extends:
raise CompilerExit()
self.outdent()
self.writeline('parent_template = environment.get_template(', node)
self.visit(node.template, frame)
self.write(', %r)' % self.name)
self.writeline('for name, parent_block in parent_template.'
'blocks.iteritems():')
self.indent()
self.writeline('context.blocks.setdefault(name, []).'
'append(parent_block)')
self.outdent()
# if this extends statement was in the root level we can take
# advantage of that information and simplify the generated code
# in the top level from this point onwards
if frame.rootlevel:
self.has_known_extends = True
# and now we have one more
self.extends_so_far += 1
def visit_Include(self, node, frame):
"""Handles includes."""
if node.with_context:
self.writeline('template = environment.get_template(', node)
self.visit(node.template, frame)
self.write(', %r)' % self.name)
self.writeline('for event in template.root_render_func('
'template.new_context(context.parent, True)):')
else:
self.writeline('for event in environment.get_template(', node)
self.visit(node.template, frame)
self.write(', %r).module._body_stream:' %
self.name)
self.indent()
self.simple_write('event', frame)
self.outdent()
def visit_Import(self, node, frame):
"""Visit regular imports."""
self.writeline('l_%s = ' % node.target, node)
if frame.toplevel:
self.write('context.vars[%r] = ' % node.target)
self.write('environment.get_template(')
self.visit(node.template, frame)
self.write(', %r).' % self.name)
if node.with_context:
self.write('make_module(context.parent, True)')
else:
self.write('module')
if frame.toplevel and not node.target.startswith('_'):
self.writeline('context.exported_vars.discard(%r)' % node.target)
def visit_FromImport(self, node, frame):
"""Visit named imports."""
self.newline(node)
self.write('included_template = environment.get_template(')
self.visit(node.template, frame)
self.write(', %r).' % self.name)
if node.with_context:
self.write('make_module(context.parent, True)')
else:
self.write('module')
var_names = []
discarded_names = []
for name in node.names:
if isinstance(name, tuple):
name, alias = name
else:
alias = name
self.writeline('l_%s = getattr(included_template, '
'%r, missing)' % (alias, name))
self.writeline('if l_%s is missing:' % alias)
self.indent()
self.writeline('l_%s = environment.undefined(%r %% '
'included_template.__name__, '
'name=%r)' %
(alias, 'the template %%r (imported on %s) does '
'not export the requested name %s' % (
self.position(node),
repr(name)
), name))
self.outdent()
if frame.toplevel:
var_names.append(alias)
if not alias.startswith('_'):
discarded_names.append(alias)
if var_names:
if len(var_names) == 1:
name = var_names[0]
self.writeline('context.vars[%r] = l_%s' % (name, name))
else:
self.writeline('context.vars.update({%s})' % ', '.join(
'%r: l_%s' % (name, name) for name in var_names
))
if discarded_names:
if len(discarded_names) == 1:
self.writeline('context.exported_vars.discard(%r)' %
discarded_names[0])
else:
self.writeline('context.exported_vars.difference_'
'update((%s))' % ', '.join(map(repr, discarded_names)))
def visit_For(self, node, frame):
# when calculating the nodes for the inner frame we have to exclude
# the iterator contents from it
children = node.iter_child_nodes(exclude=('iter',))
if node.recursive:
loop_frame = self.function_scoping(node, frame, children,
find_special=False)
else:
loop_frame = frame.inner()
loop_frame.inspect(children)
# try to figure out if we have an extended loop. An extended loop
# is necessary if the loop is in recursive mode if the special loop
# variable is accessed in the body.
extended_loop = node.recursive or 'loop' in \
find_undeclared(node.iter_child_nodes(
only=('body',)), ('loop',))
# make sure the loop variable is a special one and raise a template
# assertion error if a loop tries to write to loop
loop_frame.identifiers.add_special('loop')
for name in node.find_all(nodes.Name):
if name.ctx == 'store' and name.name == 'loop':
self.fail('Can\'t assign to special loop variable '
'in for-loop target', name.lineno)
# if we don't have an recursive loop we have to find the shadowed
# variables at that point
if not node.recursive:
aliases = self.collect_shadowed(loop_frame)
# otherwise we set up a buffer and add a function def
else:
self.writeline('def loop(reciter, loop_render_func):', node)
self.indent()
self.buffer(loop_frame)
aliases = {}
self.pull_locals(loop_frame)
if node.else_:
iteration_indicator = self.temporary_identifier()
self.writeline('%s = 1' % iteration_indicator)
# Create a fake parent loop if the else or test section of a
# loop is accessing the special loop variable and no parent loop
# exists.
if 'loop' not in aliases and 'loop' in find_undeclared(
node.iter_child_nodes(only=('else_', 'test')), ('loop',)):
self.writeline("l_loop = environment.undefined(%r, name='loop')" %
("'loop' is undefined. the filter section of a loop as well "
"as the else block doesn't have access to the special 'loop'"
" variable of the current loop. Because there is no parent "
"loop it's undefined. Happened in loop on %s" %
self.position(node)))
self.writeline('for ', node)
self.visit(node.target, loop_frame)
self.write(extended_loop and ', l_loop in LoopContext(' or ' in ')
# if we have an extened loop and a node test, we filter in the
# "outer frame".
if extended_loop and node.test is not None:
self.write('(')
self.visit(node.target, loop_frame)
self.write(' for ')
self.visit(node.target, loop_frame)
self.write(' in ')
if node.recursive:
self.write('reciter')
else:
self.visit(node.iter, loop_frame)
self.write(' if (')
test_frame = loop_frame.copy()
self.visit(node.test, test_frame)
self.write('))')
elif node.recursive:
self.write('reciter')
else:
self.visit(node.iter, loop_frame)
if node.recursive:
self.write(', recurse=loop_render_func):')
else:
self.write(extended_loop and '):' or ':')
# tests in not extended loops become a continue
if not extended_loop and node.test is not None:
self.indent()
self.writeline('if not ')
self.visit(node.test, loop_frame)
self.write(':')
self.indent()
self.writeline('continue')
self.outdent(2)
self.indent()
self.blockvisit(node.body, loop_frame, force_generator=True)
if node.else_:
self.writeline('%s = 0' % iteration_indicator)
self.outdent()
if node.else_:
self.writeline('if %s:' % iteration_indicator)
self.indent()
self.blockvisit(node.else_, loop_frame, force_generator=False)
self.outdent()
# reset the aliases if there are any.
self.restore_shadowed(aliases)
# if the node was recursive we have to return the buffer contents
# and start the iteration code
if node.recursive:
self.return_buffer_contents(loop_frame)
self.outdent()
self.start_write(frame, node)
self.write('loop(')
self.visit(node.iter, frame)
self.write(', loop)')
self.end_write(frame)
def visit_If(self, node, frame):
if_frame = frame.soft()
self.writeline('if ', node)
self.visit(node.test, if_frame)
self.write(':')
self.indent()
self.blockvisit(node.body, if_frame)
self.outdent()
if node.else_:
self.writeline('else:')
self.indent()
self.blockvisit(node.else_, if_frame)
self.outdent()
def visit_Macro(self, node, frame):
macro_frame = self.macro_body(node, frame)
self.newline()
if frame.toplevel:
if not node.name.startswith('_'):
self.write('context.exported_vars.add(%r)' % node.name)
self.writeline('context.vars[%r] = ' % node.name)
self.write('l_%s = ' % node.name)
self.macro_def(node, macro_frame)
def visit_CallBlock(self, node, frame):
children = node.iter_child_nodes(exclude=('call',))
call_frame = self.macro_body(node, frame, children)
self.writeline('caller = ')
self.macro_def(node, call_frame)
self.start_write(frame, node)
self.visit_Call(node.call, call_frame, forward_caller=True)
self.end_write(frame)
def visit_FilterBlock(self, node, frame):
filter_frame = frame.inner()
filter_frame.inspect(node.iter_child_nodes())
aliases = self.collect_shadowed(filter_frame)
self.pull_locals(filter_frame)
self.buffer(filter_frame)
self.blockvisit(node.body, filter_frame, force_generator=False)
self.start_write(frame, node)
self.visit_Filter(node.filter, filter_frame)
self.end_write(frame)
self.restore_shadowed(aliases)
def visit_ExprStmt(self, node, frame):
self.newline(node)
self.visit(node.node, frame)
def visit_Output(self, node, frame):
# if we have a known extends statement, we don't output anything
if self.has_known_extends and frame.toplevel:
return
if self.environment.finalize:
finalize = lambda x: unicode(self.environment.finalize(x))
else:
finalize = unicode
self.newline(node)
# if we are in the toplevel scope and there was already an extends
# statement we have to add a check that disables our yield(s) here
# so that they don't appear in the output.
outdent_later = False
if frame.toplevel and self.extends_so_far != 0:
self.writeline('if parent_template is None:')
self.indent()
outdent_later = True
# try to evaluate as many chunks as possible into a static
# string at compile time.
body = []
for child in node.nodes:
try:
const = child.as_const()
except nodes.Impossible:
body.append(child)
continue
try:
if self.environment.autoescape:
if hasattr(const, '__html__'):
const = const.__html__()
else:
const = escape(const)
const = finalize(const)
except:
# if something goes wrong here we evaluate the node
# at runtime for easier debugging
body.append(child)
continue
if body and isinstance(body[-1], list):
body[-1].append(const)
else:
body.append([const])
# if we have less than 3 nodes or a buffer we yield or extend/append
if len(body) < 3 or frame.buffer is not None:
if frame.buffer is not None:
# for one item we append, for more we extend
if len(body) == 1:
self.writeline('%s.append(' % frame.buffer)
else:
self.writeline('%s.extend((' % frame.buffer)
self.indent()
for item in body:
if isinstance(item, list):
val = repr(concat(item))
if frame.buffer is None:
self.writeline('yield ' + val)
else:
self.writeline(val + ', ')
else:
if frame.buffer is None:
self.writeline('yield ', item)
else:
self.newline(item)
close = 1
if self.environment.autoescape:
self.write('escape(')
else:
self.write('unicode(')
if self.environment.finalize is not None:
self.write('environment.finalize(')
close += 1
self.visit(item, frame)
self.write(')' * close)
if frame.buffer is not None:
self.write(', ')
if frame.buffer is not None:
# close the open parentheses
self.outdent()
self.writeline(len(body) == 1 and ')' or '))')
# otherwise we create a format string as this is faster in that case
else:
format = []
arguments = []
for item in body:
if isinstance(item, list):
format.append(concat(item).replace('%', '%%'))
else:
format.append('%s')
arguments.append(item)
self.writeline('yield ')
self.write(repr(concat(format)) + ' % (')
idx = -1
self.indent()
for argument in arguments:
self.newline(argument)
close = 0
if self.environment.autoescape:
self.write('escape(')
close += 1
if self.environment.finalize is not None:
self.write('environment.finalize(')
close += 1
self.visit(argument, frame)
self.write(')' * close + ', ')
self.outdent()
self.writeline(')')
if outdent_later:
self.outdent()
def visit_Assign(self, node, frame):
self.newline(node)
# toplevel assignments however go into the local namespace and
# the current template's context. We create a copy of the frame
# here and add a set so that the Name visitor can add the assigned
# names here.
if frame.toplevel:
assignment_frame = frame.copy()
assignment_frame.assigned_names = set()
else:
assignment_frame = frame
self.visit(node.target, assignment_frame)
self.write(' = ')
self.visit(node.node, frame)
# make sure toplevel assignments are added to the context.
if frame.toplevel:
public_names = [x for x in assignment_frame.assigned_names
if not x.startswith('_')]
if len(assignment_frame.assigned_names) == 1:
name = iter(assignment_frame.assigned_names).next()
self.writeline('context.vars[%r] = l_%s' % (name, name))
else:
self.writeline('context.vars.update({')
for idx, name in enumerate(assignment_frame.assigned_names):
if idx:
self.write(', ')
self.write('%r: l_%s' % (name, name))
self.write('})')
if public_names:
if len(public_names) == 1:
self.writeline('context.exported_vars.add(%r)' %
public_names[0])
else:
self.writeline('context.exported_vars.update((%s))' %
', '.join(map(repr, public_names)))
# -- Expression Visitors
def visit_Name(self, node, frame):
if node.ctx == 'store' and frame.toplevel:
frame.assigned_names.add(node.name)
self.write('l_' + node.name)
def visit_Const(self, node, frame):
val = node.value
if isinstance(val, float):
self.write(str(val))
else:
self.write(repr(val))
def visit_TemplateData(self, node, frame):
self.write(repr(node.as_const()))
def visit_Tuple(self, node, frame):
self.write('(')
idx = -1
for idx, item in enumerate(node.items):
if idx:
self.write(', ')
self.visit(item, frame)
self.write(idx == 0 and ',)' or ')')
def visit_List(self, node, frame):
self.write('[')
for idx, item in enumerate(node.items):
if idx:
self.write(', ')
self.visit(item, frame)
self.write(']')
def visit_Dict(self, node, frame):
self.write('{')
for idx, item in enumerate(node.items):
if idx:
self.write(', ')
self.visit(item.key, frame)
self.write(': ')
self.visit(item.value, frame)
self.write('}')
def binop(operator):
def visitor(self, node, frame):
self.write('(')
self.visit(node.left, frame)
self.write(' %s ' % operator)
self.visit(node.right, frame)
self.write(')')
return visitor
def uaop(operator):
def visitor(self, node, frame):
self.write('(' + operator)
self.visit(node.node, frame)
self.write(')')
return visitor
visit_Add = binop('+')
visit_Sub = binop('-')
visit_Mul = binop('*')
visit_Div = binop('/')
visit_FloorDiv = binop('//')
visit_Pow = binop('**')
visit_Mod = binop('%')
visit_And = binop('and')
visit_Or = binop('or')
visit_Pos = uaop('+')
visit_Neg = uaop('-')
visit_Not = uaop('not ')
del binop, uaop
def visit_Concat(self, node, frame):
self.write('%s((' % (self.environment.autoescape and
'markup_join' or 'unicode_join'))
for arg in node.nodes:
self.visit(arg, frame)
self.write(', ')
self.write('))')
def visit_Compare(self, node, frame):
self.visit(node.expr, frame)
for op in node.ops:
self.visit(op, frame)
def visit_Operand(self, node, frame):
self.write(' %s ' % operators[node.op])
self.visit(node.expr, frame)
def visit_Getattr(self, node, frame):
self.write('environment.getattr(')
self.visit(node.node, frame)
self.write(', %r)' % node.attr)
def visit_Getitem(self, node, frame):
# slices or integer subscriptions bypass the getitem
# method if we can determine that at compile time.
if isinstance(node.arg, nodes.Slice) or \
(isinstance(node.arg, nodes.Const) and
isinstance(node.arg.value, (int, long))):
self.visit(node.node, frame)
self.write('[')
self.visit(node.arg, frame)
self.write(']')
else:
self.write('environment.getitem(')
self.visit(node.node, frame)
self.write(', ')
self.visit(node.arg, frame)
self.write(')')
def visit_Slice(self, node, frame):
if node.start is not None:
self.visit(node.start, frame)
self.write(':')
if node.stop is not None:
self.visit(node.stop, frame)
if node.step is not None:
self.write(':')
self.visit(node.step, frame)
def visit_Filter(self, node, frame):
self.write(self.filters[node.name] + '(')
func = self.environment.filters.get(node.name)
if func is None:
self.fail('no filter named %r' % node.name, node.lineno)
if getattr(func, 'contextfilter', False):
self.write('context, ')
elif getattr(func, 'environmentfilter', False):
self.write('environment, ')
# if the filter node is None we are inside a filter block
# and want to write to the current buffer
if node.node is not None:
self.visit(node.node, frame)
elif self.environment.autoescape:
self.write('Markup(concat(%s))' % frame.buffer)
else:
self.write('concat(%s)' % frame.buffer)
self.signature(node, frame)
self.write(')')
def visit_Test(self, node, frame):
self.write(self.tests[node.name] + '(')
if node.name not in self.environment.tests:
self.fail('no test named %r' % node.name, node.lineno)
self.visit(node.node, frame)
self.signature(node, frame)
self.write(')')
def visit_CondExpr(self, node, frame):
def write_expr2():
if node.expr2 is not None:
return self.visit(node.expr2, frame)
self.write('environment.undefined(%r)' % ('the inline if-'
'expression on %s evaluated to false and '
'no else section was defined.' % self.position(node)))
if not have_condexpr:
self.write('((')
self.visit(node.test, frame)
self.write(') and (')
self.visit(node.expr1, frame)
self.write(',) or (')
write_expr2()
self.write(',))[0]')
else:
self.write('(')
self.visit(node.expr1, frame)
self.write(' if ')
self.visit(node.test, frame)
self.write(' else ')
write_expr2()
self.write(')')
def visit_Call(self, node, frame, forward_caller=False):
if self.environment.sandboxed:
self.write('environment.call(context, ')
else:
self.write('context.call(')
self.visit(node.node, frame)
extra_kwargs = forward_caller and {'caller': 'caller'} or None
self.signature(node, frame, extra_kwargs)
self.write(')')
def visit_Keyword(self, node, frame):
self.write(node.key + '=')
self.visit(node.value, frame)
# -- Unused nodes for extensions
def visit_MarkSafe(self, node, frame):
self.write('Markup(')
self.visit(node.expr, frame)
self.write(')')
def visit_EnvironmentAttribute(self, node, frame):
self.write('environment.' + node.name)
def visit_ExtensionAttribute(self, node, frame):
self.write('environment.extensions[%r].%s' % (node.identifier, node.name))
def visit_ImportedName(self, node, frame):
self.write(self.import_aliases[node.importname])
def visit_InternalName(self, node, frame):
self.write(node.name)
def visit_ContextReference(self, node, frame):
self.write('context')
def visit_Continue(self, node, frame):
self.writeline('continue', node)
def visit_Break(self, node, frame):
self.writeline('break', node)
./weblog+jinja-1.1/jinja2/constants.py 0100644 0001750 0000000 00000003126 11063022145 0016654 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja.constants
~~~~~~~~~~~~~~~
Various constants.
:copyright: 2007 by Armin Ronacher.
:license: BSD, see LICENSE for more details.
"""
#: list of lorem ipsum words used by the lipsum() helper function
LOREM_IPSUM_WORDS = u'''\
a ac accumsan ad adipiscing aenean aliquam aliquet amet ante aptent arcu at
auctor augue bibendum blandit class commodo condimentum congue consectetuer
consequat conubia convallis cras cubilia cum curabitur curae cursus dapibus
diam dictum dictumst dignissim dis dolor donec dui duis egestas eget eleifend
elementum elit enim erat eros est et etiam eu euismod facilisi facilisis fames
faucibus felis fermentum feugiat fringilla fusce gravida habitant habitasse hac
hendrerit hymenaeos iaculis id imperdiet in inceptos integer interdum ipsum
justo lacinia lacus laoreet lectus leo libero ligula litora lobortis lorem
luctus maecenas magna magnis malesuada massa mattis mauris metus mi molestie
mollis montes morbi mus nam nascetur natoque nec neque netus nibh nisi nisl non
nonummy nostra nulla nullam nunc odio orci ornare parturient pede pellentesque
penatibus per pharetra phasellus placerat platea porta porttitor posuere
potenti praesent pretium primis proin pulvinar purus quam quis quisque rhoncus
ridiculus risus rutrum sagittis sapien scelerisque sed sem semper senectus sit
sociis sociosqu sodales sollicitudin suscipit suspendisse taciti tellus tempor
tempus tincidunt torquent tortor tristique turpis ullamcorper ultrices
ultricies urna ut varius vehicula vel velit venenatis vestibulum vitae vivamus
viverra volutpat vulputate'''
./weblog+jinja-1.1/jinja2/debug.py 0100644 0001750 0000000 00000013707 11063022145 0015734 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.debug
~~~~~~~~~~~~
Implements the debug interface for Jinja. This module does some pretty
ugly stuff with the Python traceback system in order to achieve tracebacks
with correct line numbers, locals and contents.
:copyright: Copyright 2008 by Armin Ronacher.
:license: BSD.
"""
import sys
from types import CodeType
def translate_exception(exc_info):
"""If passed an exc_info it will automatically rewrite the exceptions
all the way down to the correct line numbers and frames.
"""
result_tb = prev_tb = None
initial_tb = tb = exc_info[2].tb_next
while tb is not None:
template = tb.tb_frame.f_globals.get('__jinja_template__')
if template is not None:
lineno = template.get_corresponding_lineno(tb.tb_lineno)
tb = fake_exc_info(exc_info[:2] + (tb,), template.filename,
lineno, prev_tb)[2]
if result_tb is None:
result_tb = tb
prev_tb = tb
tb = tb.tb_next
return exc_info[:2] + (result_tb or initial_tb,)
def translate_syntax_error(error):
"""When passed a syntax error it will generate a new traceback with
more debugging information.
"""
filename = error.filename
if filename is None:
filename = '<template>'
elif isinstance(filename, unicode):
filename = filename.encode('utf-8')
code = compile('\n' * (error.lineno - 1) + 'raise __jinja_exception__',
filename, 'exec')
try:
exec code in {'__jinja_exception__': error}
except:
exc_info = sys.exc_info()
return exc_info[:2] + (exc_info[2].tb_next,)
def fake_exc_info(exc_info, filename, lineno, tb_back=None):
"""Helper for `translate_exception`."""
exc_type, exc_value, tb = exc_info
# figure the real context out
real_locals = tb.tb_frame.f_locals.copy()
ctx = real_locals.get('context')
if ctx:
locals = ctx.get_all()
else:
locals = {}
for name, value in real_locals.iteritems():
if name.startswith('l_'):
locals[name[2:]] = value
# if there is a local called __jinja_exception__, we get
# rid of it to not break the debug functionality.
locals.pop('__jinja_exception__', None)
# assamble fake globals we need
globals = {
'__name__': filename,
'__file__': filename,
'__jinja_exception__': exc_info[:2]
}
# and fake the exception
code = compile('\n' * (lineno - 1) + 'raise __jinja_exception__[0], ' +
'__jinja_exception__[1]', filename, 'exec')
# if it's possible, change the name of the code. This won't work
# on some python environments such as google appengine
try:
function = tb.tb_frame.f_code.co_name
if function == 'root':
location = 'top-level template code'
elif function.startswith('block_'):
location = 'block "%s"' % function[6:]
else:
location = 'template'
code = CodeType(0, code.co_nlocals, code.co_stacksize,
code.co_flags, code.co_code, code.co_consts,
code.co_names, code.co_varnames, filename,
location, code.co_firstlineno,
code.co_lnotab, (), ())
except:
pass
# execute the code and catch the new traceback
try:
exec code in globals, locals
except:
exc_info = sys.exc_info()
new_tb = exc_info[2].tb_next
# now we can patch the exc info accordingly
if tb_set_next is not None:
if tb_back is not None:
tb_set_next(tb_back, new_tb)
if tb is not None:
tb_set_next(new_tb, tb.tb_next)
# return without this frame
return exc_info[:2] + (new_tb,)
def _init_ugly_crap():
"""This function implements a few ugly things so that we can patch the
traceback objects. The function returned allows resetting `tb_next` on
any python traceback object.
"""
import ctypes
from types import TracebackType
# figure out side of _Py_ssize_t
if hasattr(ctypes.pythonapi, 'Py_InitModule4_64'):
_Py_ssize_t = ctypes.c_int64
else:
_Py_ssize_t = ctypes.c_int
# regular python
class _PyObject(ctypes.Structure):
pass
_PyObject._fields_ = [
('ob_refcnt', _Py_ssize_t),
('ob_type', ctypes.POINTER(_PyObject))
]
# python with trace
if object.__basicsize__ != ctypes.sizeof(_PyObject):
class _PyObject(ctypes.Structure):
pass
_PyObject._fields_ = [
('_ob_next', ctypes.POINTER(_PyObject)),
('_ob_prev', ctypes.POINTER(_PyObject)),
('ob_refcnt', _Py_ssize_t),
('ob_type', ctypes.POINTER(_PyObject))
]
class _Traceback(_PyObject):
pass
_Traceback._fields_ = [
('tb_next', ctypes.POINTER(_Traceback)),
('tb_frame', ctypes.POINTER(_PyObject)),
('tb_lasti', ctypes.c_int),
('tb_lineno', ctypes.c_int)
]
def tb_set_next(tb, next):
"""Set the tb_next attribute of a traceback object."""
if not (isinstance(tb, TracebackType) and
(next is None or isinstance(next, TracebackType))):
raise TypeError('tb_set_next arguments must be traceback objects')
obj = _Traceback.from_address(id(tb))
if tb.tb_next is not None:
old = _Traceback.from_address(id(tb.tb_next))
old.ob_refcnt -= 1
if next is None:
obj.tb_next = ctypes.POINTER(_Traceback)()
else:
next = _Traceback.from_address(id(next))
next.ob_refcnt += 1
obj.tb_next = ctypes.pointer(next)
return tb_set_next
# try to get a tb_set_next implementation
try:
from jinja2._speedups import tb_set_next
except ImportError:
try:
tb_set_next = _init_ugly_crap()
except:
tb_set_next = None
del _init_ugly_crap
./weblog+jinja-1.1/jinja2/defaults.py 0100644 0001750 0000000 00000001545 11063022145 0016452 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.defaults
~~~~~~~~~~~~~~~
Jinja default filters and tags.
:copyright: 2007-2008 by Armin Ronacher.
:license: BSD, see LICENSE for more details.
"""
from jinja2.utils import generate_lorem_ipsum
# defaults for the parser / lexer
BLOCK_START_STRING = '{%'
BLOCK_END_STRING = '%}'
VARIABLE_START_STRING = '{{'
VARIABLE_END_STRING = '}}'
COMMENT_START_STRING = '{#'
COMMENT_END_STRING = '#}'
LINE_STATEMENT_PREFIX = None
TRIM_BLOCKS = False
NEWLINE_SEQUENCE = '\n'
# default filters, tests and namespace
from jinja2.filters import FILTERS as DEFAULT_FILTERS
from jinja2.tests import TESTS as DEFAULT_TESTS
DEFAULT_NAMESPACE = {
'range': xrange,
'dict': lambda **kw: kw,
'lipsum': generate_lorem_ipsum
}
# export all constants
__all__ = tuple(x for x in locals() if x.isupper())
./weblog+jinja-1.1/jinja2/environment.py 0100644 0001750 0000000 00000071106 11063022145 0017207 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.environment
~~~~~~~~~~~~~~~~~~
Provides a class that holds runtime and parsing time options.
:copyright: 2008 by Armin Ronacher.
:license: BSD, see LICENSE for more details.
"""
import sys
from jinja2.defaults import *
from jinja2.lexer import Lexer, TokenStream
from jinja2.parser import Parser
from jinja2.optimizer import optimize
from jinja2.compiler import generate
from jinja2.runtime import Undefined, Context
from jinja2.exceptions import TemplateSyntaxError
from jinja2.utils import import_string, LRUCache, Markup, missing, concat
# for direct template usage we have up to ten living environments
_spontaneous_environments = LRUCache(10)
def get_spontaneous_environment(*args):
"""Return a new spontaneus environment. A spontaneus environment is an
unnamed and unaccessable (in theory) environment that is used for
template generated from a string and not from the file system.
"""
try:
env = _spontaneous_environments.get(args)
except TypeError:
return Environment(*args)
if env is not None:
return env
_spontaneous_environments[args] = env = Environment(*args)
env.shared = True
return env
def create_cache(size):
"""Return the cache class for the given size."""
if size == 0:
return None
if size < 0:
return {}
return LRUCache(size)
def load_extensions(environment, extensions):
"""Load the extensions from the list and bind it to the environment.
Returns a dict of instanciated environments.
"""
result = {}
for extension in extensions:
if isinstance(extension, basestring):
extension = import_string(extension)
result[extension.identifier] = extension(environment)
return result
def _environment_sanity_check(environment):
"""Perform a sanity check on the environment."""
assert issubclass(environment.undefined, Undefined), 'undefined must ' \
'be a subclass of undefined because filters depend on it.'
assert environment.block_start_string != \
environment.variable_start_string != \
environment.comment_start_string, 'block, variable and comment ' \
'start strings must be different'
assert environment.newline_sequence in ('\r', '\r\n', '\n'), \
'newline_sequence set to unknown line ending string.'
return environment
class Environment(object):
r"""The core component of Jinja is the `Environment`. It contains
important shared variables like configuration, filters, tests,
globals and others. Instances of this class may be modified if
they are not shared and if no template was loaded so far.
Modifications on environments after the first template was loaded
will lead to surprising effects and undefined behavior.
Here the possible initialization parameters:
`block_start_string`
The string marking the begin of a block. Defaults to ``'{%'``.
`block_end_string`
The string marking the end of a block. Defaults to ``'%}'``.
`variable_start_string`
The string marking the begin of a print statement.
Defaults to ``'{{'``.
`variable_end_string`
The string marking the end of a print statement. Defaults to
``'}}'``.
`comment_start_string`
The string marking the begin of a comment. Defaults to ``'{#'``.
`comment_end_string`
The string marking the end of a comment. Defaults to ``'#}'``.
`line_statement_prefix`
If given and a string, this will be used as prefix for line based
statements. See also :ref:`line-statements`.
`trim_blocks`
If this is set to ``True`` the first newline after a block is
removed (block, not variable tag!). Defaults to `False`.
`newline_sequence`
The sequence that starts a newline. Must be one of ``'\r'``,
``'\n'`` or ``'\r\n'``. The default is ``'\n'`` which is a
useful default for Linux and OS X systems as well as web
applications.
`extensions`
List of Jinja extensions to use. This can either be import paths
as strings or extension classes. For more information have a
look at :ref:`the extensions documentation <jinja-extensions>`.
`optimized`
should the optimizer be enabled? Default is `True`.
`undefined`
:class:`Undefined` or a subclass of it that is used to represent
undefined values in the template.
`finalize`
A callable that finalizes the variable. Per default no finalizing
is applied.
`autoescape`
If set to true the XML/HTML autoescaping feature is enabled.
`loader`
The template loader for this environment.
`cache_size`
The size of the cache. Per default this is ``50`` which means
that if more than 50 templates are loaded the loader will clean
out the least recently used template. If the cache size is set to
``0`` templates are recompiled all the time, if the cache size is
``-1`` the cache will not be cleaned.
`auto_reload`
Some loaders load templates from locations where the template
sources may change (ie: file system or database). If
`auto_reload` is set to `True` (default) every time a template is
requested the loader checks if the source changed and if yes, it
will reload the template. For higher performance it's possible to
disable that.
"""
#: if this environment is sandboxed. Modifying this variable won't make
#: the environment sandboxed though. For a real sandboxed environment
#: have a look at jinja2.sandbox
sandboxed = False
#: True if the environment is just an overlay
overlay = False
#: the environment this environment is linked to if it is an overlay
linked_to = None
#: shared environments have this set to `True`. A shared environment
#: must not be modified
shared = False
def __init__(self,
block_start_string=BLOCK_START_STRING,
block_end_string=BLOCK_END_STRING,
variable_start_string=VARIABLE_START_STRING,
variable_end_string=VARIABLE_END_STRING,
comment_start_string=COMMENT_START_STRING,
comment_end_string=COMMENT_END_STRING,
line_statement_prefix=LINE_STATEMENT_PREFIX,
trim_blocks=TRIM_BLOCKS,
newline_sequence=NEWLINE_SEQUENCE,
extensions=(),
optimized=True,
undefined=Undefined,
finalize=None,
autoescape=False,
loader=None,
cache_size=50,
auto_reload=True):
# !!Important notice!!
# The constructor accepts quite a few arguments that should be
# passed by keyword rather than position. However it's important to
# not change the order of arguments because it's used at least
# internally in those cases:
# - spontaneus environments (i18n extension and Template)
# - unittests
# If parameter changes are required only add parameters at the end
# and don't change the arguments (or the defaults!) of the arguments
# existing already.
# lexer / parser information
self.block_start_string = block_start_string
self.block_end_string = block_end_string
self.variable_start_string = variable_start_string
self.variable_end_string = variable_end_string
self.comment_start_string = comment_start_string
self.comment_end_string = comment_end_string
self.line_statement_prefix = line_statement_prefix
self.trim_blocks = trim_blocks
self.newline_sequence = newline_sequence
# runtime information
self.undefined = undefined
self.optimized = optimized
self.finalize = finalize
self.autoescape = autoescape
# defaults
self.filters = DEFAULT_FILTERS.copy()
self.tests = DEFAULT_TESTS.copy()
self.globals = DEFAULT_NAMESPACE.copy()
# set the loader provided
self.loader = loader
self.cache = create_cache(cache_size)
self.auto_reload = auto_reload
# load extensions
self.extensions = load_extensions(self, extensions)
_environment_sanity_check(self)
def extend(self, **attributes):
"""Add the items to the instance of the environment if they do not exist
yet. This is used by :ref:`extensions <writing-extensions>` to register
callbacks and configuration values without breaking inheritance.
"""
for key, value in attributes.iteritems():
if not hasattr(self, key):
setattr(self, key, value)
def overlay(self, block_start_string=missing, block_end_string=missing,
variable_start_string=missing, variable_end_string=missing,
comment_start_string=missing, comment_end_string=missing,
line_statement_prefix=missing, trim_blocks=missing,
extensions=missing, optimized=missing, undefined=missing,
finalize=missing, autoescape=missing, loader=missing,
cache_size=missing, auto_reload=missing):
"""Create a new overlay environment that shares all the data with the
current environment except of cache and the overriden attributes.
Extensions cannot be removed for a overlayed environment. A overlayed
environment automatically gets all the extensions of the environment it
is linked to plus optional extra extensions.
Creating overlays should happen after the initial environment was set
up completely. Not all attributes are truly linked, some are just
copied over so modifications on the original environment may not shine
through.
"""
args = dict(locals())
del args['self'], args['cache_size'], args['extensions']
rv = object.__new__(self.__class__)
rv.__dict__.update(self.__dict__)
rv.overlay = True
rv.linked_to = self
for key, value in args.iteritems():
if value is not missing:
setattr(rv, key, value)
if cache_size is not missing:
rv.cache = create_cache(cache_size)
rv.extensions = {}
for key, value in self.extensions.iteritems():
rv.extensions[key] = value.bind(rv)
if extensions is not missing:
rv.extensions.update(load_extensions(extensions))
return _environment_sanity_check(rv)
@property
def lexer(self):
"""Return a fresh lexer for the environment."""
return Lexer(self)
def getitem(self, obj, argument):
"""Get an item or attribute of an object but prefer the item."""
try:
return obj[argument]
except (TypeError, LookupError):
if isinstance(argument, basestring):
try:
attr = str(argument)
except:
pass
else:
try:
return getattr(obj, attr)
except AttributeError:
pass
return self.undefined(obj=obj, name=argument)
def getattr(self, obj, attribute):
"""Get an item or attribute of an object but prefer the attribute.
Unlike :meth:`getitem` the attribute *must* be a bytestring.
"""
try:
return getattr(obj, attribute)
except AttributeError:
pass
try:
return obj[attribute]
except (TypeError, LookupError, AttributeError):
return self.undefined(obj=obj, name=attribute)
def parse(self, source, name=None, filename=None):
"""Parse the sourcecode and return the abstract syntax tree. This
tree of nodes is used by the compiler to convert the template into
executable source- or bytecode. This is useful for debugging or to
extract information from templates.
If you are :ref:`developing Jinja2 extensions <writing-extensions>`
this gives you a good overview of the node tree generated.
"""
if isinstance(filename, unicode):
filename = filename.encode('utf-8')
try:
return Parser(self, source, name, filename).parse()
except TemplateSyntaxError, e:
from jinja2.debug import translate_syntax_error
exc_type, exc_value, tb = translate_syntax_error(e)
raise exc_type, exc_value, tb
def lex(self, source, name=None, filename=None):
"""Lex the given sourcecode and return a generator that yields
tokens as tuples in the form ``(lineno, token_type, value)``.
This can be useful for :ref:`extension development <writing-extensions>`
and debugging templates.
This does not perform preprocessing. If you want the preprocessing
of the extensions to be applied you have to filter source through
the :meth:`preprocess` method.
"""
return self.lexer.tokeniter(unicode(source), name, filename)
def preprocess(self, source, name=None, filename=None):
"""Preprocesses the source with all extensions. This is automatically
called for all parsing and compiling methods but *not* for :meth:`lex`
because there you usually only want the actual source tokenized.
"""
return reduce(lambda s, e: e.preprocess(s, name, filename),
self.extensions.itervalues(), unicode(source))
def _tokenize(self, source, name, filename=None):
"""Called by the parser to do the preprocessing and filtering
for all the extensions. Returns a :class:`~jinja2.lexer.TokenStream`.
"""
source = self.preprocess(source, name, filename)
stream = self.lexer.tokenize(source, name, filename)
for ext in self.extensions.itervalues():
stream = ext.filter_stream(stream)
if not isinstance(stream, TokenStream):
stream = TokenStream(stream, name, filename)
return stream
def compile(self, source, name=None, filename=None, raw=False):
"""Compile a node or template source code. The `name` parameter is
the load name of the template after it was joined using
:meth:`join_path` if necessary, not the filename on the file system.
the `filename` parameter is the estimated filename of the template on
the file system. If the template came from a database or memory this
can be omitted.
The return value of this method is a python code object. If the `raw`
parameter is `True` the return value will be a string with python
code equivalent to the bytecode returned otherwise. This method is
mainly used internally.
"""
if isinstance(source, basestring):
source = self.parse(source, name, filename)
if self.optimized:
node = optimize(source, self)
source = generate(node, self, name, filename)
if raw:
return source
if filename is None:
filename = '<template>'
elif isinstance(filename, unicode):
filename = filename.encode('utf-8')
return compile(source, filename, 'exec')
def join_path(self, template, parent):
"""Join a template with the parent. By default all the lookups are
relative to the loader root so this method returns the `template`
parameter unchanged, but if the paths should be relative to the
parent template, this function can be used to calculate the real
template name.
Subclasses may override this method and implement template path
joining here.
"""
return template
def get_template(self, name, parent=None, globals=None):
"""Load a template from the loader. If a loader is configured this
method ask the loader for the template and returns a :class:`Template`.
If the `parent` parameter is not `None`, :meth:`join_path` is called
to get the real template name before loading.
The `globals` parameter can be used to provide temlate wide globals.
These variables are available in the context at render time.
If the template does not exist a :exc:`TemplateNotFound` exception is
raised.
"""
if self.loader is None:
raise TypeError('no loader for this environment specified')
if parent is not None:
name = self.join_path(name, parent)
if self.cache is not None:
template = self.cache.get(name)
if template is not None and (not self.auto_reload or \
template.is_up_to_date):
return template
template = self.loader.load(self, name, self.make_globals(globals))
if self.cache is not None:
self.cache[name] = template
return template
def from_string(self, source, globals=None, template_class=None):
"""Load a template from a string. This parses the source given and
returns a :class:`Template` object.
"""
globals = self.make_globals(globals)
cls = template_class or self.template_class
return cls.from_code(self, self.compile(source), globals, None)
def make_globals(self, d):
"""Return a dict for the globals."""
if not d:
return self.globals
return dict(self.globals, **d)
class Template(object):
"""The central template object. This class represents a compiled template
and is used to evaluate it.
Normally the template object is generated from an :class:`Environment` but
it also has a constructor that makes it possible to create a template
instance directly using the constructor. It takes the same arguments as
the environment constructor but it's not possible to specify a loader.
Every template object has a few methods and members that are guaranteed
to exist. However it's important that a template object should be
considered immutable. Modifications on the object are not supported.
Template objects created from the constructor rather than an environment
do have an `environment` attribute that points to a temporary environment
that is probably shared with other templates created with the constructor
and compatible settings.
>>> template = Template('Hello {{ name }}!')
>>> template.render(name='John Doe')
u'Hello John Doe!'
>>> stream = template.stream(name='John Doe')
>>> stream.next()
u'Hello John Doe!'
>>> stream.next()
Traceback (most recent call last):
...
StopIteration
"""
def __new__(cls, source,
block_start_string=BLOCK_START_STRING,
block_end_string=BLOCK_END_STRING,
variable_start_string=VARIABLE_START_STRING,
variable_end_string=VARIABLE_END_STRING,
comment_start_string=COMMENT_START_STRING,
comment_end_string=COMMENT_END_STRING,
line_statement_prefix=LINE_STATEMENT_PREFIX,
trim_blocks=TRIM_BLOCKS,
newline_sequence=NEWLINE_SEQUENCE,
extensions=(),
optimized=True,
undefined=Undefined,
finalize=None,
autoescape=False):
env = get_spontaneous_environment(
block_start_string, block_end_string, variable_start_string,
variable_end_string, comment_start_string, comment_end_string,
line_statement_prefix, trim_blocks, newline_sequence,
frozenset(extensions), optimized, undefined, finalize,
autoescape, None, 0, False)
return env.from_string(source, template_class=cls)
@classmethod
def from_code(cls, environment, code, globals, uptodate=None):
"""Creates a template object from compiled code and the globals. This
is used by the loaders and environment to create a template object.
"""
t = object.__new__(cls)
namespace = {
'environment': environment,
'__jinja_template__': t
}
exec code in namespace
t.environment = environment
t.globals = globals
t.name = namespace['name']
t.filename = code.co_filename
t.blocks = namespace['blocks']
# render function and module
t.root_render_func = namespace['root']
t._module = None
# debug and loader helpers
t._debug_info = namespace['debug_info']
t._uptodate = uptodate
return t
def render(self, *args, **kwargs):
"""This method accepts the same arguments as the `dict` constructor:
A dict, a dict subclass or some keyword arguments. If no arguments
are given the context will be empty. These two calls do the same::
template.render(knights='that say nih')
template.render({'knights': 'that say nih'})
This will return the rendered template as unicode string.
"""
vars = dict(*args, **kwargs)
try:
return concat(self.root_render_func(self.new_context(vars)))
except:
from jinja2.debug import translate_exception
exc_type, exc_value, tb = translate_exception(sys.exc_info())
raise exc_type, exc_value, tb
def stream(self, *args, **kwargs):
"""Works exactly like :meth:`generate` but returns a
:class:`TemplateStream`.
"""
return TemplateStream(self.generate(*args, **kwargs))
def generate(self, *args, **kwargs):
"""For very large templates it can be useful to not render the whole
template at once but evaluate each statement after another and yield
piece for piece. This method basically does exactly that and returns
a generator that yields one item after another as unicode strings.
It accepts the same arguments as :meth:`render`.
"""
vars = dict(*args, **kwargs)
try:
for event in self.root_render_func(self.new_context(vars)):
yield event
except:
from jinja2.debug import translate_exception
exc_type, exc_value, tb = translate_exception(sys.exc_info())
raise exc_type, exc_value, tb
def new_context(self, vars=None, shared=False):
"""Create a new :class:`Context` for this template. The vars
provided will be passed to the template. Per default the globals
are added to the context, if shared is set to `True` the data
provided is used as parent namespace. This is used to share the
same globals in multiple contexts without consuming more memory.
(This works because the context does not modify the parent dict)
"""
if vars is None:
vars = {}
if shared:
parent = vars
else:
parent = dict(self.globals, **vars)
return Context(self.environment, parent, self.name, self.blocks)
def make_module(self, vars=None, shared=False):
"""This method works like the :attr:`module` attribute when called
without arguments but it will evaluate the template every call
rather then caching the template. It's also possible to provide
a dict which is then used as context. The arguments are the same
as for the :meth:`new_context` method.
"""
return TemplateModule(self, self.new_context(vars, shared))
@property
def module(self):
"""The template as module. This is used for imports in the
template runtime but is also useful if one wants to access
exported template variables from the Python layer:
>>> t = Template('{% macro foo() %}42{% endmacro %}23')
>>> unicode(t.module)
u'23'
>>> t.module.foo()
u'42'
"""
if self._module is not None:
return self._module
self._module = rv = self.make_module()
return rv
def get_corresponding_lineno(self, lineno):
"""Return the source line number of a line number in the
generated bytecode as they are not in sync.
"""
for template_line, code_line in reversed(self.debug_info):
if code_line <= lineno:
return template_line
return 1
@property
def is_up_to_date(self):
"""If this variable is `False` there is a newer version available."""
if self._uptodate is None:
return True
return self._uptodate()
@property
def debug_info(self):
"""The debug info mapping."""
return [tuple(map(int, x.split('='))) for x in
self._debug_info.split('&')]
def __repr__(self):
if self.name is None:
name = 'memory:%x' % id(self)
else:
name = repr(self.name)
return '<%s %s>' % (self.__class__.__name__, name)
class TemplateModule(object):
"""Represents an imported template. All the exported names of the
template are available as attributes on this object. Additionally
converting it into an unicode- or bytestrings renders the contents.
"""
def __init__(self, template, context):
self._body_stream = list(template.root_render_func(context))
self.__dict__.update(context.get_exported())
self.__name__ = template.name
__unicode__ = lambda x: concat(x._body_stream)
__html__ = lambda x: Markup(concat(x._body_stream))
def __str__(self):
return unicode(self).encode('utf-8')
def __repr__(self):
if self.__name__ is None:
name = 'memory:%x' % id(self)
else:
name = repr(self.__name__)
return '<%s %s>' % (self.__class__.__name__, name)
class TemplateStream(object):
"""A template stream works pretty much like an ordinary python generator
but it can buffer multiple items to reduce the number of total iterations.
Per default the output is unbuffered which means that for every unbuffered
instruction in the template one unicode string is yielded.
If buffering is enabled with a buffer size of 5, five items are combined
into a new unicode string. This is mainly useful if you are streaming
big templates to a client via WSGI which flushes after each iteration.
"""
def __init__(self, gen):
self._gen = gen
self.disable_buffering()
def dump(self, fp, encoding=None, errors='strict'):
"""Dump the complete stream into a file or file-like object.
Per default unicode strings are written, if you want to encode
before writing specifiy an `encoding`.
Example usage::
Template('Hello {{ name }}!').stream(name='foo').dump('hello.html')
"""
close = False
if isinstance(fp, basestring):
fp = file(fp, 'w')
close = True
try:
if encoding is not None:
iterable = (x.encode(encoding, errors) for x in self)
else:
iterable = self
if hasattr(fp, 'writelines'):
fp.writelines(iterable)
else:
for item in iterable:
fp.write(item)
finally:
if close:
fp.close()
def disable_buffering(self):
"""Disable the output buffering."""
self._next = self._gen.next
self.buffered = False
def enable_buffering(self, size=5):
"""Enable buffering. Buffer `size` items before yielding them."""
if size <= 1:
raise ValueError('buffer size too small')
def generator(next):
buf = []
c_size = 0
push = buf.append
while 1:
try:
while c_size < size:
c = next()
push(c)
if c:
c_size += 1
except StopIteration:
if not c_size:
return
yield concat(buf)
del buf[:]
c_size = 0
self.buffered = True
self._next = generator(self._gen.next).next
def __iter__(self):
return self
def next(self):
return self._next()
# hook in default template class. if anyone reads this comment: ignore that
# it's possible to use custom templates ;-)
Environment.template_class = Template
./weblog+jinja-1.1/jinja2/exceptions.py 0100644 0001750 0000000 00000004262 11063022145 0017023 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.exceptions
~~~~~~~~~~~~~~~~~
Jinja exceptions.
:copyright: 2008 by Armin Ronacher.
:license: BSD, see LICENSE for more details.
"""
class TemplateError(Exception):
"""Baseclass for all template errors."""
class TemplateNotFound(IOError, LookupError, TemplateError):
"""Raised if a template does not exist."""
def __init__(self, name):
IOError.__init__(self, name)
self.name = name
class TemplateSyntaxError(TemplateError):
"""Raised to tell the user that there is a problem with the template."""
def __init__(self, message, lineno, name=None, filename=None):
if name is not None:
extra = '%s, line %d' % (name.encode('utf-8'), lineno)
else:
extra = 'line %d' % lineno
# if the message was provided as unicode we have to encode it
# to utf-8 explicitly
if isinstance(message, unicode):
message = message.encode('utf-8')
# otherwise make sure it's a in fact valid utf-8
else:
message = message.decode('utf-8', 'ignore').encode('utf-8')
TemplateError.__init__(self, '%s (%s)' % (message, extra))
self.message = message
self.lineno = lineno
self.name = name
self.filename = filename
class TemplateAssertionError(TemplateSyntaxError):
"""Like a template syntax error, but covers cases where something in the
template caused an error at compile time that wasn't necessarily caused
by a syntax error. However it's a direct subclass of
:exc:`TemplateSyntaxError` and has the same attributes.
"""
class TemplateRuntimeError(TemplateError):
"""A generic runtime error in the template engine. Under some situations
Jinja may raise this exception.
"""
class UndefinedError(TemplateRuntimeError):
"""Raised if a template tries to operate on :class:`Undefined`."""
class SecurityError(TemplateRuntimeError):
"""Raised if a template tries to do something insecure if the
sandbox is enabled.
"""
class FilterArgumentError(TemplateRuntimeError):
"""This error is raised if a filter was called with inappropriate
arguments
"""
./weblog+jinja-1.1/jinja2/ext.py 0100644 0001750 0000000 00000041424 11063022145 0015443 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.ext
~~~~~~~~~~
Jinja extensions allow to add custom tags similar to the way django custom
tags work. By default two example extensions exist: an i18n and a cache
extension.
:copyright: Copyright 2008 by Armin Ronacher.
:license: BSD.
"""
from collections import deque
from jinja2 import nodes
from jinja2.defaults import *
from jinja2.environment import get_spontaneous_environment
from jinja2.runtime import Undefined, concat
from jinja2.exceptions import TemplateAssertionError, TemplateSyntaxError
from jinja2.utils import contextfunction, import_string, Markup
# the only real useful gettext functions for a Jinja template. Note
# that ugettext must be assigned to gettext as Jinja doesn't support
# non unicode strings.
GETTEXT_FUNCTIONS = ('_', 'gettext', 'ngettext')
class ExtensionRegistry(type):
"""Gives the extension an unique identifier."""
def __new__(cls, name, bases, d):
rv = type.__new__(cls, name, bases, d)
rv.identifier = rv.__module__ + '.' + rv.__name__
return rv
class Extension(object):
"""Extensions can be used to add extra functionality to the Jinja template
system at the parser level. Custom extensions are bound to an environment
but may not store environment specific data on `self`. The reason for
this is that an extension can be bound to another environment (for
overlays) by creating a copy and reassigning the `environment` attribute.
As extensions are created by the environment they cannot accept any
arguments for configuration. One may want to work around that by using
a factory function, but that is not possible as extensions are identified
by their import name. The correct way to configure the extension is
storing the configuration values on the environment. Because this way the
environment ends up acting as central configuration storage the
attributes may clash which is why extensions have to ensure that the names
they choose for configuration are not too generic. ``prefix`` for example
is a terrible name, ``fragment_cache_prefix`` on the other hand is a good
name as includes the name of the extension (fragment cache).
"""
__metaclass__ = ExtensionRegistry
#: if this extension parses this is the list of tags it's listening to.
tags = set()
def __init__(self, environment):
self.environment = environment
def bind(self, environment):
"""Create a copy of this extension bound to another environment."""
rv = object.__new__(self.__class__)
rv.__dict__.update(self.__dict__)
rv.environment = environment
return rv
def preprocess(self, source, name, filename=None):
"""This method is called before the actual lexing and can be used to
preprocess the source. The `filename` is optional. The return value
must be the preprocessed source.
"""
return source
def filter_stream(self, stream):
"""It's passed a :class:`~jinja2.lexer.TokenStream` that can be used
to filter tokens returned. This method has to return an iterable of
:class:`~jinja2.lexer.Token`\s, but it doesn't have to return a
:class:`~jinja2.lexer.TokenStream`.
In the `ext` folder of the Jinja2 source distribution there is a file
called `inlinegettext.py` which implements a filter that utilizes this
method.
"""
return stream
def parse(self, parser):
"""If any of the :attr:`tags` matched this method is called with the
parser as first argument. The token the parser stream is pointing at
is the name token that matched. This method has to return one or a
list of multiple nodes.
"""
raise NotImplementedError()
def attr(self, name, lineno=None):
"""Return an attribute node for the current extension. This is useful
to pass constants on extensions to generated template code::
self.attr('_my_attribute', lineno=lineno)
"""
return nodes.ExtensionAttribute(self.identifier, name, lineno=lineno)
def call_method(self, name, args=None, kwargs=None, dyn_args=None,
dyn_kwargs=None, lineno=None):
"""Call a method of the extension. This is a shortcut for
:meth:`attr` + :class:`jinja2.nodes.Call`.
"""
if args is None:
args = []
if kwargs is None:
kwargs = []
return nodes.Call(self.attr(name, lineno=lineno), args, kwargs,
dyn_args, dyn_kwargs, lineno=lineno)
@contextfunction
def _gettext_alias(context, string):
return context.resolve('gettext')(string)
class InternationalizationExtension(Extension):
"""This extension adds gettext support to Jinja2."""
tags = set(['trans'])
def __init__(self, environment):
Extension.__init__(self, environment)
environment.globals['_'] = _gettext_alias
environment.extend(
install_gettext_translations=self._install,
install_null_translations=self._install_null,
uninstall_gettext_translations=self._uninstall,
extract_translations=self._extract
)
def _install(self, translations):
self.environment.globals.update(
gettext=translations.ugettext,
ngettext=translations.ungettext
)
def _install_null(self):
self.environment.globals.update(
gettext=lambda x: x,
ngettext=lambda s, p, n: (n != 1 and (p,) or (s,))[0]
)
def _uninstall(self, translations):
for key in 'gettext', 'ngettext':
self.environment.globals.pop(key, None)
def _extract(self, source, gettext_functions=GETTEXT_FUNCTIONS):
if isinstance(source, basestring):
source = self.environment.parse(source)
return extract_from_ast(source, gettext_functions)
def parse(self, parser):
"""Parse a translatable tag."""
lineno = parser.stream.next().lineno
# find all the variables referenced. Additionally a variable can be
# defined in the body of the trans block too, but this is checked at
# a later state.
plural_expr = None
variables = {}
while parser.stream.current.type is not 'block_end':
if variables:
parser.stream.expect('comma')
# skip colon for python compatibility
if parser.stream.skip_if('colon'):
break
name = parser.stream.expect('name')
if name.value in variables:
parser.fail('translatable variable %r defined twice.' %
name.value, name.lineno,
exc=TemplateAssertionError)
# expressions
if parser.stream.current.type is 'assign':
parser.stream.next()
variables[name.value] = var = parser.parse_expression()
else:
variables[name.value] = var = nodes.Name(name.value, 'load')
if plural_expr is None:
plural_expr = var
parser.stream.expect('block_end')
plural = plural_names = None
have_plural = False
referenced = set()
# now parse until endtrans or pluralize
singular_names, singular = self._parse_block(parser, True)
if singular_names:
referenced.update(singular_names)
if plural_expr is None:
plural_expr = nodes.Name(singular_names[0], 'load')
# if we have a pluralize block, we parse that too
if parser.stream.current.test('name:pluralize'):
have_plural = True
parser.stream.next()
if parser.stream.current.type is not 'block_end':
plural_expr = parser.parse_expression()
parser.stream.expect('block_end')
plural_names, plural = self._parse_block(parser, False)
parser.stream.next()
referenced.update(plural_names)
else:
parser.stream.next()
# register free names as simple name expressions
for var in referenced:
if var not in variables:
variables[var] = nodes.Name(var, 'load')
# no variables referenced? no need to escape
if not referenced:
singular = singular.replace('%%', '%')
if plural:
plural = plural.replace('%%', '%')
if not have_plural:
plural_expr = None
elif plural_expr is None:
parser.fail('pluralize without variables', lineno)
if variables:
variables = nodes.Dict([nodes.Pair(nodes.Const(x, lineno=lineno), y)
for x, y in variables.items()])
else:
variables = None
node = self._make_node(singular, plural, variables, plural_expr)
node.set_lineno(lineno)
return node
def _parse_block(self, parser, allow_pluralize):
"""Parse until the next block tag with a given name."""
referenced = []
buf = []
while 1:
if parser.stream.current.type is 'data':
buf.append(parser.stream.current.value.replace('%', '%%'))
parser.stream.next()
elif parser.stream.current.type is 'variable_begin':
parser.stream.next()
name = parser.stream.expect('name').value
referenced.append(name)
buf.append('%%(%s)s' % name)
parser.stream.expect('variable_end')
elif parser.stream.current.type is 'block_begin':
parser.stream.next()
if parser.stream.current.test('name:endtrans'):
break
elif parser.stream.current.test('name:pluralize'):
if allow_pluralize:
break
parser.fail('a translatable section can have only one '
'pluralize section')
parser.fail('control structures in translatable sections are '
'not allowed')
elif parser.stream.eos:
parser.fail('unclosed translation block')
else:
assert False, 'internal parser error'
return referenced, concat(buf)
def _make_node(self, singular, plural, variables, plural_expr):
"""Generates a useful node from the data provided."""
# singular only:
if plural_expr is None:
gettext = nodes.Name('gettext', 'load')
node = nodes.Call(gettext, [nodes.Const(singular)],
[], None, None)
# singular and plural
else:
ngettext = nodes.Name('ngettext', 'load')
node = nodes.Call(ngettext, [
nodes.Const(singular),
nodes.Const(plural),
plural_expr
], [], None, None)
# mark the return value as safe if we are in an
# environment with autoescaping turned on
if self.environment.autoescape:
node = nodes.MarkSafe(node)
if variables:
node = nodes.Mod(node, variables)
return nodes.Output([node])
class ExprStmtExtension(Extension):
"""Adds a `do` tag to Jinja2 that works like the print statement just
that it doesn't print the return value.
"""
tags = set(['do'])
def parse(self, parser):
node = nodes.ExprStmt(lineno=parser.stream.next().lineno)
node.node = parser.parse_tuple()
return node
class LoopControlExtension(Extension):
"""Adds break and continue to the template engine."""
tags = set(['break', 'continue'])
def parse(self, parser):
token = parser.stream.next()
if token.value == 'break':
return nodes.Break(lineno=token.lineno)
return nodes.Continue(lineno=token.lineno)
def extract_from_ast(node, gettext_functions=GETTEXT_FUNCTIONS,
babel_style=True):
"""Extract localizable strings from the given template node. Per
default this function returns matches in babel style that means non string
parameters as well as keyword arguments are returned as `None`. This
allows Babel to figure out what you really meant if you are using
gettext functions that allow keyword arguments for placeholder expansion.
If you don't want that behavior set the `babel_style` parameter to `False`
which causes only strings to be returned and parameters are always stored
in tuples. As a consequence invalid gettext calls (calls without a single
string parameter or string parameters after non-string parameters) are
skipped.
This example explains the behavior:
>>> from jinja2 import Environment
>>> env = Environment()
>>> node = env.parse('{{ (_("foo"), _(), ngettext("foo", "bar", 42)) }}')
>>> list(extract_from_ast(node))
[(1, '_', 'foo'), (1, '_', ()), (1, 'ngettext', ('foo', 'bar', None))]
>>> list(extract_from_ast(node, babel_style=False))
[(1, '_', ('foo',)), (1, 'ngettext', ('foo', 'bar'))]
For every string found this function yields a ``(lineno, function,
message)`` tuple, where:
* ``lineno`` is the number of the line on which the string was found,
* ``function`` is the name of the ``gettext`` function used (if the
string was extracted from embedded Python code), and
* ``message`` is the string itself (a ``unicode`` object, or a tuple
of ``unicode`` objects for functions with multiple string arguments).
"""
for node in node.find_all(nodes.Call):
if not isinstance(node.node, nodes.Name) or \
node.node.name not in gettext_functions:
continue
strings = []
for arg in node.args:
if isinstance(arg, nodes.Const) and \
isinstance(arg.value, basestring):
strings.append(arg.value)
else:
strings.append(None)
for arg in node.kwargs:
strings.append(None)
if node.dyn_args is not None:
strings.append(None)
if node.dyn_kwargs is not None:
strings.append(None)
if not babel_style:
strings = tuple(x for x in strings if x is not None)
if not strings:
continue
else:
if len(strings) == 1:
strings = strings[0]
else:
strings = tuple(strings)
yield node.lineno, node.node.name, strings
def babel_extract(fileobj, keywords, comment_tags, options):
"""Babel extraction method for Jinja templates.
:param fileobj: the file-like object the messages should be extracted from
:param keywords: a list of keywords (i.e. function names) that should be
recognized as translation functions
:param comment_tags: a list of translator tags to search for and include
in the results. (Unused)
:param options: a dictionary of additional options (optional)
:return: an iterator over ``(lineno, funcname, message, comments)`` tuples.
(comments will be empty currently)
"""
extensions = set()
for extension in options.get('extensions', '').split(','):
extension = extension.strip()
if not extension:
continue
extensions.add(import_string(extension))
if InternationalizationExtension not in extensions:
extensions.add(InternationalizationExtension)
environment = get_spontaneous_environment(
options.get('block_start_string', BLOCK_START_STRING),
options.get('block_end_string', BLOCK_END_STRING),
options.get('variable_start_string', VARIABLE_START_STRING),
options.get('variable_end_string', VARIABLE_END_STRING),
options.get('comment_start_string', COMMENT_START_STRING),
options.get('comment_end_string', COMMENT_END_STRING),
options.get('line_statement_prefix') or LINE_STATEMENT_PREFIX,
str(options.get('trim_blocks', TRIM_BLOCKS)).lower() in \
('1', 'on', 'yes', 'true'),
NEWLINE_SEQUENCE, frozenset(extensions),
# fill with defaults so that environments are shared
# with other spontaneus environments. The rest of the
# arguments are optimizer, undefined, finalize, autoescape,
# loader, cache size and auto reloading setting
True, Undefined, None, False, None, 0, False
)
source = fileobj.read().decode(options.get('encoding', 'utf-8'))
try:
node = environment.parse(source)
except TemplateSyntaxError, e:
# skip templates with syntax errors
return
for lineno, func, message in extract_from_ast(node, keywords):
yield lineno, func, message, []
#: nicer import names
i18n = InternationalizationExtension
do = ExprStmtExtension
loopcontrols = LoopControlExtension
./weblog+jinja-1.1/jinja2/filters.py 0100644 0001750 0000000 00000051211 11063022145 0016306 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.filters
~~~~~~~~~~~~~~
Bundled jinja filters.
:copyright: 2008 by Armin Ronacher, Christoph Hack.
:license: BSD, see LICENSE for more details.
"""
import re
import math
import textwrap
from random import choice
from operator import itemgetter
from itertools import imap, groupby
from jinja2.utils import Markup, escape, pformat, urlize, soft_unicode
from jinja2.runtime import Undefined
from jinja2.exceptions import FilterArgumentError, SecurityError
_word_re = re.compile(r'\w+')
def contextfilter(f):
"""Decorator for marking context dependent filters. The current
:class:`Context` will be passed as first argument.
"""
if getattr(f, 'environmentfilter', False):
raise TypeError('filter already marked as environment filter')
f.contextfilter = True
return f
def environmentfilter(f):
"""Decorator for marking evironment dependent filters. The current
:class:`Environment` is passed to the filter as first argument.
"""
if getattr(f, 'contextfilter', False):
raise TypeError('filter already marked as context filter')
f.environmentfilter = True
return f
def do_forceescape(value):
"""Enforce HTML escaping. This will probably double escape variables."""
if hasattr(value, '__html__'):
value = value.__html__()
return escape(unicode(value))
@environmentfilter
def do_replace(environment, s, old, new, count=None):
"""Return a copy of the value with all occurrences of a substring
replaced with a new one. The first argument is the substring
that should be replaced, the second is the replacement string.
If the optional third argument ``count`` is given, only the first
``count`` occurrences are replaced:
.. sourcecode:: jinja
{{ "Hello World"|replace("Hello", "Goodbye") }}
-> Goodbye World
{{ "aaaaargh"|replace("a", "d'oh, ", 2) }}
-> d'oh, d'oh, aaargh
"""
if count is None:
count = -1
if not environment.autoescape:
return unicode(s).replace(unicode(old), unicode(new), count)
if hasattr(old, '__html__') or hasattr(new, '__html__') and \
not hasattr(s, '__html__'):
s = escape(s)
else:
s = soft_unicode(s)
return s.replace(soft_unicode(old), soft_unicode(new), count)
def do_upper(s):
"""Convert a value to uppercase."""
return soft_unicode(s).upper()
def do_lower(s):
"""Convert a value to lowercase."""
return soft_unicode(s).lower()
@environmentfilter
def do_xmlattr(_environment, d, autospace=True):
"""Create an SGML/XML attribute string based on the items in a dict.
All values that are neither `none` nor `undefined` are automatically
escaped:
.. sourcecode:: html+jinja
<ul{{ {'class': 'my_list', 'missing': none,
'id': 'list-%d'|format(variable)}|xmlattr }}>
...
</ul>
Results in something like this:
.. sourcecode:: html
<ul class="my_list" id="list-42">
...
</ul>
As you can see it automatically prepends a space in front of the item
if the filter returned something unless the second parameter is false.
"""
rv = u' '.join(
u'%s="%s"' % (escape(key), escape(value))
for key, value in d.iteritems()
if value is not None and not isinstance(value, Undefined)
)
if autospace and rv:
rv = u' ' + rv
if _environment.autoescape:
rv = Markup(rv)
return rv
def do_capitalize(s):
"""Capitalize a value. The first character will be uppercase, all others
lowercase.
"""
return soft_unicode(s).capitalize()
def do_title(s):
"""Return a titlecased version of the value. I.e. words will start with
uppercase letters, all remaining characters are lowercase.
"""
return soft_unicode(s).title()
def do_dictsort(value, case_sensitive=False, by='key'):
""" Sort a dict and yield (key, value) pairs. Because python dicts are
unsorted you may want to use this function to order them by either
key or value:
.. sourcecode:: jinja
{% for item in mydict|dictsort %}
sort the dict by key, case insensitive
{% for item in mydict|dicsort(true) %}
sort the dict by key, case sensitive
{% for item in mydict|dictsort(false, 'value') %}
sort the dict by key, case insensitive, sorted
normally and ordered by value.
"""
if by == 'key':
pos = 0
elif by == 'value':
pos = 1
else:
raise FilterArgumentError('You can only sort by either '
'"key" or "value"')
def sort_func(item):
value = item[pos]
if isinstance(value, basestring):
value = unicode(value)
if not case_sensitive:
value = value.lower()
return value
return sorted(value.items(), key=sort_func)
def do_default(value, default_value=u'', boolean=False):
"""If the value is undefined it will return the passed default value,
otherwise the value of the variable:
.. sourcecode:: jinja
{{ my_variable|default('my_variable is not defined') }}
This will output the value of ``my_variable`` if the variable was
defined, otherwise ``'my_variable is not defined'``. If you want
to use default with variables that evaluate to false you have to
set the second parameter to `true`:
.. sourcecode:: jinja
{{ ''|default('the string was empty', true) }}
"""
if (boolean and not value) or isinstance(value, Undefined):
return default_value
return value
@environmentfilter
def do_join(environment, value, d=u''):
"""Return a string which is the concatenation of the strings in the
sequence. The separator between elements is an empty string per
default, you can define it with the optional parameter:
.. sourcecode:: jinja
{{ [1, 2, 3]|join('|') }}
-> 1|2|3
{{ [1, 2, 3]|join }}
-> 123
"""
# no automatic escaping? joining is a lot eaiser then
if not environment.autoescape:
return unicode(d).join(imap(unicode, value))
# if the delimiter doesn't have an html representation we check
# if any of the items has. If yes we do a coercion to Markup
if not hasattr(d, '__html__'):
value = list(value)
do_escape = False
for idx, item in enumerate(value):
if hasattr(item, '__html__'):
do_escape = True
else:
value[idx] = unicode(item)
if do_escape:
d = escape(d)
else:
d = unicode(d)
return d.join(value)
# no html involved, to normal joining
return soft_unicode(d).join(imap(soft_unicode, value))
def do_center(value, width=80):
"""Centers the value in a field of a given width."""
return unicode(value).center(width)
@environmentfilter
def do_first(environment, seq):
"""Return the first item of a sequence."""
try:
return iter(seq).next()
except StopIteration:
return environment.undefined('No first item, sequence was empty.')
@environmentfilter
def do_last(environment, seq):
"""Return the last item of a sequence."""
try:
return iter(reversed(seq)).next()
except StopIteration:
return environment.undefined('No last item, sequence was empty.')
@environmentfilter
def do_random(environment, seq):
"""Return a random item from the sequence."""
try:
return choice(seq)
except IndexError:
return environment.undefined('No random item, sequence was empty.')
def do_filesizeformat(value, binary=False):
"""Format the value like a 'human-readable' file size (i.e. 13 KB,
4.1 MB, 102 bytes, etc). Per default decimal prefixes are used (mega,
giga etc.), if the second parameter is set to `True` the binary
prefixes are (mebi, gibi).
"""
bytes = float(value)
base = binary and 1024 or 1000
middle = binary and 'i' or ''
if bytes < base:
return "%d Byte%s" % (bytes, bytes != 1 and 's' or '')
elif bytes < base * base:
return "%.1f K%sB" % (bytes / base, middle)
elif bytes < base * base * base:
return "%.1f M%sB" % (bytes / (base * base), middle)
return "%.1f G%sB" % (bytes / (base * base * base), middle)
def do_pprint(value, verbose=False):
"""Pretty print a variable. Useful for debugging.
With Jinja 1.2 onwards you can pass it a parameter. If this parameter
is truthy the output will be more verbose (this requires `pretty`)
"""
return pformat(value, verbose=verbose)
@environmentfilter
def do_urlize(environment, value, trim_url_limit=None, nofollow=False):
"""Converts URLs in plain text into clickable links.
If you pass the filter an additional integer it will shorten the urls
to that number. Also a third argument exists that makes the urls
"nofollow":
.. sourcecode:: jinja
{{ mytext|urlize(40, true) }}
links are shortened to 40 chars and defined with rel="nofollow"
"""
rv = urlize(soft_unicode(value), trim_url_limit, nofollow)
if environment.autoescape:
rv = Markup(rv)
return rv
def do_indent(s, width=4, indentfirst=False):
"""Return a copy of the passed string, each line indented by
4 spaces. The first line is not indented. If you want to
change the number of spaces or indent the first line too
you can pass additional parameters to the filter:
.. sourcecode:: jinja
{{ mytext|indent(2, true) }}
indent by two spaces and indent the first line too.
"""
indention = ' ' * width
if indentfirst:
return u'\n'.join(indention + line for line in s.splitlines())
return s.replace('\n', '\n' + indention)
def do_truncate(s, length=255, killwords=False, end='...'):
"""Return a truncated copy of the string. The length is specified
with the first parameter which defaults to ``255``. If the second
parameter is ``true`` the filter will cut the text at length. Otherwise
it will try to save the last word. If the text was in fact
truncated it will append an ellipsis sign (``"..."``). If you want a
different ellipsis sign than ``"..."`` you can specify it using the
third parameter.
.. sourcecode jinja::
{{ mytext|truncate(300, false, '»') }}
truncate mytext to 300 chars, don't split up words, use a
right pointing double arrow as ellipsis sign.
"""
if len(s) <= length:
return s
elif killwords:
return s[:length] + end
words = s.split(' ')
result = []
m = 0
for word in words:
m += len(word) + 1
if m > length:
break
result.append(word)
result.append(end)
return u' '.join(result)
def do_wordwrap(s, width=79, break_long_words=True):
"""
Return a copy of the string passed to the filter wrapped after
``79`` characters. You can override this default using the first
parameter. If you set the second parameter to `false` Jinja will not
split words apart if they are longer than `width`.
"""
return u'\n'.join(textwrap.wrap(s, width=width, expand_tabs=False,
replace_whitespace=False,
break_long_words=break_long_words))
def do_wordcount(s):
"""Count the words in that string."""
return len(_word_re.findall(s))
def do_int(value, default=0):
"""Convert the value into an integer. If the
conversion doesn't work it will return ``0``. You can
override this default using the first parameter.
"""
try:
return int(value)
except (TypeError, ValueError):
# this quirk is necessary so that "42.23"|int gives 42.
try:
return int(float(value))
except (TypeError, ValueError):
return default
def do_float(value, default=0.0):
"""Convert the value into a floating point number. If the
conversion doesn't work it will return ``0.0``. You can
override this default using the first parameter.
"""
try:
return float(value)
except (TypeError, ValueError):
return default
def do_format(value, *args, **kwargs):
"""
Apply python string formatting on an object:
.. sourcecode:: jinja
{{ "%s - %s"|format("Hello?", "Foo!") }}
-> Hello? - Foo!
"""
if args and kwargs:
raise FilterArgumentError('can\'t handle positional and keyword '
'arguments at the same time')
return soft_unicode(value) % (kwargs or args)
def do_trim(value):
"""Strip leading and trailing whitespace."""
return soft_unicode(value).strip()
def do_striptags(value):
"""Strip SGML/XML tags and replace adjacent whitespace by one space.
"""
if hasattr(value, '__html__'):
value = value.__html__()
return Markup(unicode(value)).striptags()
def do_slice(value, slices, fill_with=None):
"""Slice an iterator and return a list of lists containing
those items. Useful if you want to create a div containing
three div tags that represent columns:
.. sourcecode:: html+jinja
<div class="columwrapper">
{%- for column in items|slice(3) %}
<ul class="column-{{ loop.index }}">
{%- for item in column %}
<li>{{ item }}</li>
{%- endfor %}
</ul>
{%- endfor %}
</div>
If you pass it a second argument it's used to fill missing
values on the last iteration.
"""
seq = list(value)
length = len(seq)
items_per_slice = length // slices
slices_with_extra = length % slices
offset = 0
for slice_number in xrange(slices):
start = offset + slice_number * items_per_slice
if slice_number < slices_with_extra:
offset += 1
end = offset + (slice_number + 1) * items_per_slice
tmp = seq[start:end]
if fill_with is not None and slice_number >= slices_with_extra:
tmp.append(fill_with)
yield tmp
def do_batch(value, linecount, fill_with=None):
"""
A filter that batches items. It works pretty much like `slice`
just the other way round. It returns a list of lists with the
given number of items. If you provide a second parameter this
is used to fill missing items. See this example:
.. sourcecode:: html+jinja
<table>
{%- for row in items|batch(3, ' ') %}
<tr>
{%- for column in row %}
<tr>{{ column }}</td>
{%- endfor %}
</tr>
{%- endfor %}
</table>
"""
result = []
tmp = []
for item in value:
if len(tmp) == linecount:
yield tmp
tmp = []
tmp.append(item)
if tmp:
if fill_with is not None and len(tmp) < linecount:
tmp += [fill_with] * (linecount - len(tmp))
yield tmp
def do_round(value, precision=0, method='common'):
"""Round the number to a given precision. The first
parameter specifies the precision (default is ``0``), the
second the rounding method:
- ``'common'`` rounds either up or down
- ``'ceil'`` always rounds up
- ``'floor'`` always rounds down
If you don't specify a method ``'common'`` is used.
.. sourcecode:: jinja
{{ 42.55|round }}
-> 43
{{ 42.55|round(1, 'floor') }}
-> 42.5
"""
if not method in ('common', 'ceil', 'floor'):
raise FilterArgumentError('method must be common, ceil or floor')
if precision < 0:
raise FilterArgumentError('precision must be a postive integer '
'or zero.')
if method == 'common':
return round(value, precision)
func = getattr(math, method)
if precision:
return func(value * 10 * precision) / (10 * precision)
else:
return func(value)
def do_sort(value, reverse=False):
"""Sort a sequence. Per default it sorts ascending, if you pass it
true as first argument it will reverse the sorting.
"""
return sorted(value, reverse=reverse)
@environmentfilter
def do_groupby(environment, value, attribute):
"""Group a sequence of objects by a common attribute.
If you for example have a list of dicts or objects that represent persons
with `gender`, `first_name` and `last_name` attributes and you want to
group all users by genders you can do something like the following
snippet:
.. sourcecode:: html+jinja
<ul>
{% for group in persons|groupby('gender') %}
<li>{{ group.grouper }}<ul>
{% for person in group.list %}
<li>{{ person.first_name }} {{ person.last_name }}</li>
{% endfor %}</ul></li>
{% endfor %}
</ul>
Additionally it's possible to use tuple unpacking for the grouper and
list:
.. sourcecode:: html+jinja
<ul>
{% for grouper, list in persons|groupby('gender') %}
...
{% endfor %}
</ul>
As you can see the item we're grouping by is stored in the `grouper`
attribute and the `list` contains all the objects that have this grouper
in common.
"""
expr = lambda x: environment.getitem(x, attribute)
return sorted(map(_GroupTuple, groupby(sorted(value, key=expr), expr)))
class _GroupTuple(tuple):
__slots__ = ()
grouper = property(itemgetter(0))
list = property(itemgetter(1))
def __new__(cls, (key, value)):
return tuple.__new__(cls, (key, list(value)))
def do_list(value):
"""Convert the value into a list. If it was a string the returned list
will be a list of characters.
"""
return list(value)
def do_mark_safe(value):
"""Mark the value as safe which means that in an environment with automatic
escaping enabled this variable will not be escaped.
"""
return Markup(value)
def do_mark_unsafe(value):
"""Mark a value as unsafe. This is the reverse operation for :func:`safe`."""
return unicode(value)
def do_reverse(value):
"""Reverse the object or return an iterator the iterates over it the other
way round.
"""
if isinstance(value, basestring):
return value[::-1]
try:
return reversed(value)
except TypeError:
try:
rv = list(value)
rv.reverse()
return rv
except TypeError:
raise FilterArgumentError('argument must be iterable')
@environmentfilter
def do_attr(environment, obj, name):
"""Get an attribute of an object. ``foo|attr("bar")`` works like
``foo["bar"]`` just that always an attribute is returned and items are not
looked up.
See :ref:`Notes on subscriptions <notes-on-subscriptions>` for more details.
"""
try:
value = getattr(obj, name)
except AttributeError:
return environment.undefined(obj=obj, name=name)
if environment.sandboxed and not \
environment.is_safe_attribute(obj, name, value):
return environment.unsafe_undefined(obj, name)
return value
FILTERS = {
'attr': do_attr,
'replace': do_replace,
'upper': do_upper,
'lower': do_lower,
'escape': escape,
'e': escape,
'forceescape': do_forceescape,
'capitalize': do_capitalize,
'title': do_title,
'default': do_default,
'd': do_default,
'join': do_join,
'count': len,
'dictsort': do_dictsort,
'length': len,
'reverse': do_reverse,
'center': do_center,
'indent': do_indent,
'title': do_title,
'capitalize': do_capitalize,
'first': do_first,
'last': do_last,
'random': do_random,
'filesizeformat': do_filesizeformat,
'pprint': do_pprint,
'truncate': do_truncate,
'wordwrap': do_wordwrap,
'wordcount': do_wordcount,
'int': do_int,
'float': do_float,
'string': soft_unicode,
'list': do_list,
'urlize': do_urlize,
'format': do_format,
'trim': do_trim,
'striptags': do_striptags,
'slice': do_slice,
'batch': do_batch,
'sum': sum,
'abs': abs,
'round': do_round,
'sort': do_sort,
'groupby': do_groupby,
'safe': do_mark_safe,
'xmlattr': do_xmlattr
}
./weblog+jinja-1.1/jinja2/lexer.py 0100644 0001750 0000000 00000051757 11063022145 0015774 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.lexer
~~~~~~~~~~~~
This module implements a Jinja / Python combination lexer. The
`Lexer` class provided by this module is used to do some preprocessing
for Jinja.
On the one hand it filters out invalid operators like the bitshift
operators we don't allow in templates. On the other hand it separates
template code and python code in expressions.
:copyright: 2007-2008 by Armin Ronacher.
:license: BSD, see LICENSE for more details.
"""
import re
import unicodedata
from operator import itemgetter
from collections import deque
from jinja2.exceptions import TemplateSyntaxError
from jinja2.utils import LRUCache
# cache for the lexers. Exists in order to be able to have multiple
# environments with the same lexer
_lexer_cache = LRUCache(50)
# static regular expressions
whitespace_re = re.compile(r'\s+(?um)')
string_re = re.compile(r"('([^'\\]*(?:\\.[^'\\]*)*)'"
r'|"([^"\\]*(?:\\.[^"\\]*)*)")(?ms)')
integer_re = re.compile(r'\d+')
name_re = re.compile(r'\b[a-zA-Z_][a-zA-Z0-9_]*\b')
float_re = re.compile(r'\d+\.\d+')
newline_re = re.compile(r'(\r\n|\r|\n)')
# bind operators to token types
operators = {
'+': 'add',
'-': 'sub',
'/': 'div',
'//': 'floordiv',
'*': 'mul',
'%': 'mod',
'**': 'pow',
'~': 'tilde',
'[': 'lbracket',
']': 'rbracket',
'(': 'lparen',
')': 'rparen',
'{': 'lbrace',
'}': 'rbrace',
'==': 'eq',
'!=': 'ne',
'>': 'gt',
'>=': 'gteq',
'<': 'lt',
'<=': 'lteq',
'=': 'assign',
'.': 'dot',
':': 'colon',
'|': 'pipe',
',': 'comma',
';': 'semicolon'
}
reverse_operators = dict([(v, k) for k, v in operators.iteritems()])
assert len(operators) == len(reverse_operators), 'operators dropped'
operator_re = re.compile('(%s)' % '|'.join(re.escape(x) for x in
sorted(operators, key=lambda x: -len(x))))
def count_newlines(value):
"""Count the number of newline characters in the string. This is
useful for extensions that filter a stream.
"""
return len(newline_re.findall(value))
class Failure(object):
"""Class that raises a `TemplateSyntaxError` if called.
Used by the `Lexer` to specify known errors.
"""
def __init__(self, message, cls=TemplateSyntaxError):
self.message = message
self.error_class = cls
def __call__(self, lineno, filename):
raise self.error_class(self.message, lineno, filename)
class Token(tuple):
"""Token class."""
__slots__ = ()
lineno, type, value = (property(itemgetter(x)) for x in range(3))
def __new__(cls, lineno, type, value):
return tuple.__new__(cls, (lineno, intern(str(type)), value))
def __str__(self):
if self.type in reverse_operators:
return reverse_operators[self.type]
elif self.type is 'name':
return self.value
return self.type
def test(self, expr):
"""Test a token against a token expression. This can either be a
token type or ``'token_type:token_value'``. This can only test
against string values and types.
"""
# here we do a regular string equality check as test_any is usually
# passed an iterable of not interned strings.
if self.type == expr:
return True
elif ':' in expr:
return expr.split(':', 1) == [self.type, self.value]
return False
def test_any(self, *iterable):
"""Test against multiple token expressions."""
for expr in iterable:
if self.test(expr):
return True
return False
def __repr__(self):
return 'Token(%r, %r, %r)' % (
self.lineno,
self.type,
self.value
)
class TokenStreamIterator(object):
"""The iterator for tokenstreams. Iterate over the stream
until the eof token is reached.
"""
def __init__(self, stream):
self.stream = stream
def __iter__(self):
return self
def next(self):
token = self.stream.current
if token.type == 'eof':
self.stream.close()
raise StopIteration()
self.stream.next()
return token
class TokenStream(object):
"""A token stream is an iterable that yields :class:`Token`\s. The
parser however does not iterate over it but calls :meth:`next` to go
one token ahead. The current active token is stored as :attr:`current`.
"""
def __init__(self, generator, name, filename):
self._next = iter(generator).next
self._pushed = deque()
self.name = name
self.filename = filename
self.closed = False
self.current = Token(1, 'initial', '')
self.next()
def __iter__(self):
return TokenStreamIterator(self)
def __nonzero__(self):
"""Are we at the end of the stream?"""
return bool(self._pushed) or self.current.type != 'eof'
eos = property(lambda x: not x.__nonzero__(), doc=__nonzero__.__doc__)
def push(self, token):
"""Push a token back to the stream."""
self._pushed.append(token)
def look(self):
"""Look at the next token."""
old_token = self.next()
result = self.current
self.push(result)
self.current = old_token
return result
def skip(self, n=1):
"""Got n tokens ahead."""
for x in xrange(n):
self.next()
def next_if(self, expr):
"""Perform the token test and return the token if it matched.
Otherwise the return value is `None`.
"""
if self.current.test(expr):
return self.next()
def skip_if(self, expr):
"""Like :meth:`next_if` but only returns `True` or `False`."""
return self.next_if(expr) is not None
def next(self):
"""Go one token ahead and return the old one"""
rv = self.current
if self._pushed:
self.current = self._pushed.popleft()
elif self.current.type is not 'eof':
try:
self.current = self._next()
except StopIteration:
self.close()
return rv
def close(self):
"""Close the stream."""
self.current = Token(self.current.lineno, 'eof', '')
self._next = None
self.closed = True
def expect(self, expr):
"""Expect a given token type and return it. This accepts the same
argument as :meth:`jinja2.lexer.Token.test`.
"""
if not self.current.test(expr):
if ':' in expr:
expr = expr.split(':')[1]
if self.current.type is 'eof':
raise TemplateSyntaxError('unexpected end of template, '
'expected %r.' % expr,
self.current.lineno,
self.name, self.filename)
raise TemplateSyntaxError("expected token %r, got %r" %
(expr, str(self.current)),
self.current.lineno,
self.name, self.filename)
try:
return self.current
finally:
self.next()
class LexerMeta(type):
"""Metaclass for the lexer that caches instances for
the same configuration in a weak value dictionary.
"""
def __call__(cls, environment):
key = (environment.block_start_string,
environment.block_end_string,
environment.variable_start_string,
environment.variable_end_string,
environment.comment_start_string,
environment.comment_end_string,
environment.line_statement_prefix,
environment.trim_blocks,
environment.newline_sequence)
lexer = _lexer_cache.get(key)
if lexer is None:
lexer = type.__call__(cls, environment)
_lexer_cache[key] = lexer
return lexer
class Lexer(object):
"""Class that implements a lexer for a given environment. Automatically
created by the environment class, usually you don't have to do that.
Note that the lexer is not automatically bound to an environment.
Multiple environments can share the same lexer.
"""
__metaclass__ = LexerMeta
def __init__(self, environment):
# shortcuts
c = lambda x: re.compile(x, re.M | re.S)
e = re.escape
# lexing rules for tags
tag_rules = [
(whitespace_re, 'whitespace', None),
(float_re, 'float', None),
(integer_re, 'integer', None),
(name_re, 'name', None),
(string_re, 'string', None),
(operator_re, 'operator', None)
]
# assamble the root lexing rule. because "|" is ungreedy
# we have to sort by length so that the lexer continues working
# as expected when we have parsing rules like <% for block and
# <%= for variables. (if someone wants asp like syntax)
# variables are just part of the rules if variable processing
# is required.
root_tag_rules = [
('comment', environment.comment_start_string),
('block', environment.block_start_string),
('variable', environment.variable_start_string)
]
root_tag_rules.sort(key=lambda x: -len(x[1]))
# now escape the rules. This is done here so that the escape
# signs don't count for the lengths of the tags.
root_tag_rules = [(a, e(b)) for a, b in root_tag_rules]
# if we have a line statement prefix we need an extra rule for
# that. We add this rule *after* all the others.
if environment.line_statement_prefix is not None:
prefix = e(environment.line_statement_prefix)
root_tag_rules.insert(0, ('linestatement', '^\s*' + prefix))
# block suffix if trimming is enabled
block_suffix_re = environment.trim_blocks and '\\n?' or ''
self.newline_sequence = environment.newline_sequence
# global lexing rules
self.rules = {
'root': [
# directives
(c('(.*?)(?:%s)' % '|'.join(
['(?P<raw_begin>(?:\s*%s\-|%s)\s*raw\s*%s)' % (
e(environment.block_start_string),
e(environment.block_start_string),
e(environment.block_end_string)
)] + [
'(?P<%s_begin>\s*%s\-|%s)' % (n, r, r)
for n, r in root_tag_rules
])), ('data', '#bygroup'), '#bygroup'),
# data
(c('.+'), 'data', None)
],
# comments
'comment_begin': [
(c(r'(.*?)((?:\-%s\s*|%s)%s)' % (
e(environment.comment_end_string),
e(environment.comment_end_string),
block_suffix_re
)), ('comment', 'comment_end'), '#pop'),
(c('(.)'), (Failure('Missing end of comment tag'),), None)
],
# blocks
'block_begin': [
(c('(?:\-%s\s*|%s)%s' % (
e(environment.block_end_string),
e(environment.block_end_string),
block_suffix_re
)), 'block_end', '#pop'),
] + tag_rules,
# variables
'variable_begin': [
(c('\-%s\s*|%s' % (
e(environment.variable_end_string),
e(environment.variable_end_string)
)), 'variable_end', '#pop')
] + tag_rules,
# raw block
'raw_begin': [
(c('(.*?)((?:\s*%s\-|%s)\s*endraw\s*(?:\-%s\s*|%s%s))' % (
e(environment.block_start_string),
e(environment.block_start_string),
e(environment.block_end_string),
e(environment.block_end_string),
block_suffix_re
)), ('data', 'raw_end'), '#pop'),
(c('(.)'), (Failure('Missing end of raw directive'),), None)
],
# line statements
'linestatement_begin': [
(c(r'\s*(\n|$)'), 'linestatement_end', '#pop')
] + tag_rules
}
def _normalize_newlines(self, value):
"""Called for strings and template data to normlize it to unicode."""
return newline_re.sub(self.newline_sequence, value)
def tokenize(self, source, name=None, filename=None):
"""Calls tokeniter + tokenize and wraps it in a token stream.
"""
stream = self.tokeniter(source, name, filename)
return TokenStream(self.wrap(stream, name, filename), name, filename)
def wrap(self, stream, name=None, filename=None):
"""This is called with the stream as returned by `tokenize` and wraps
every token in a :class:`Token` and converts the value.
"""
for lineno, token, value in stream:
if token in ('comment_begin', 'comment', 'comment_end',
'whitespace'):
continue
elif token == 'linestatement_begin':
token = 'block_begin'
elif token == 'linestatement_end':
token = 'block_end'
# we are not interested in those tokens in the parser
elif token in ('raw_begin', 'raw_end'):
continue
elif token == 'data':
value = self._normalize_newlines(value)
elif token == 'keyword':
token = value
elif token == 'name':
value = str(value)
elif token == 'string':
# try to unescape string
try:
value = self._normalize_newlines(value[1:-1]) \
.encode('ascii', 'backslashreplace') \
.decode('unicode-escape')
except Exception, e:
msg = str(e).split(':')[-1].strip()
raise TemplateSyntaxError(msg, lineno, name, filename)
# if we can express it as bytestring (ascii only)
# we do that for support of semi broken APIs
# as datetime.datetime.strftime
try:
value = str(value)
except UnicodeError:
pass
elif token == 'integer':
value = int(value)
elif token == 'float':
value = float(value)
elif token == 'operator':
token = operators[value]
yield Token(lineno, token, value)
def tokeniter(self, source, name, filename=None):
"""This method tokenizes the text and returns the tokens in a
generator. Use this method if you just want to tokenize a template.
"""
source = '\n'.join(unicode(source).splitlines())
pos = 0
lineno = 1
stack = ['root']
statetokens = self.rules['root']
source_length = len(source)
balancing_stack = []
while 1:
# tokenizer loop
for regex, tokens, new_state in statetokens:
m = regex.match(source, pos)
# if no match we try again with the next rule
if m is None:
continue
# we only match blocks and variables if brances / parentheses
# are balanced. continue parsing with the lower rule which
# is the operator rule. do this only if the end tags look
# like operators
if balancing_stack and \
tokens in ('variable_end', 'block_end',
'linestatement_end'):
continue
# tuples support more options
if isinstance(tokens, tuple):
for idx, token in enumerate(tokens):
# failure group
if token.__class__ is Failure:
raise token(lineno, filename)
# bygroup is a bit more complex, in that case we
# yield for the current token the first named
# group that matched
elif token == '#bygroup':
for key, value in m.groupdict().iteritems():
if value is not None:
yield lineno, key, value
lineno += value.count('\n')
break
else:
raise RuntimeError('%r wanted to resolve '
'the token dynamically'
' but no group matched'
% regex)
# normal group
else:
data = m.group(idx + 1)
if data:
yield lineno, token, data
lineno += data.count('\n')
# strings as token just are yielded as it.
else:
data = m.group()
# update brace/parentheses balance
if tokens == 'operator':
if data == '{':
balancing_stack.append('}')
elif data == '(':
balancing_stack.append(')')
elif data == '[':
balancing_stack.append(']')
elif data in ('}', ')', ']'):
if not balancing_stack:
raise TemplateSyntaxError('unexpected "%s"' %
data, lineno, name,
filename)
expected_op = balancing_stack.pop()
if expected_op != data:
raise TemplateSyntaxError('unexpected "%s", '
'expected "%s"' %
(data, expected_op),
lineno, name,
filename)
# yield items
yield lineno, tokens, data
lineno += data.count('\n')
# fetch new position into new variable so that we can check
# if there is a internal parsing error which would result
# in an infinite loop
pos2 = m.end()
# handle state changes
if new_state is not None:
# remove the uppermost state
if new_state == '#pop':
stack.pop()
# resolve the new state by group checking
elif new_state == '#bygroup':
for key, value in m.groupdict().iteritems():
if value is not None:
stack.append(key)
break
else:
raise RuntimeError('%r wanted to resolve the '
'new state dynamically but'
' no group matched' %
regex)
# direct state name given
else:
stack.append(new_state)
statetokens = self.rules[stack[-1]]
# we are still at the same position and no stack change.
# this means a loop without break condition, avoid that and
# raise error
elif pos2 == pos:
raise RuntimeError('%r yielded empty string without '
'stack change' % regex)
# publish new function and start again
pos = pos2
break
# if loop terminated without break we havn't found a single match
# either we are at the end of the file or we have a problem
else:
# end of text
if pos >= source_length:
return
# something went wrong
raise TemplateSyntaxError('unexpected char %r at %d' %
(source[pos], pos), lineno,
name, filename)
./weblog+jinja-1.1/jinja2/loaders.py 0100644 0001750 0000000 00000024116 11063022145 0016273 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.loaders
~~~~~~~~~~~~~~
Jinja loader classes.
:copyright: 2008 by Armin Ronacher.
:license: BSD, see LICENSE for more details.
"""
from os import path
try:
from hashlib import sha1
except ImportError:
from sha import new as sha1
from jinja2.exceptions import TemplateNotFound
from jinja2.utils import LRUCache
def split_template_path(template):
"""Split a path into segments and perform a sanity check. If it detects
'..' in the path it will raise a `TemplateNotFound` error.
"""
pieces = []
for piece in template.split('/'):
if path.sep in piece \
or (path.altsep and path.altsep in piece) or \
piece == path.pardir:
raise TemplateNotFound(template)
elif piece and piece != '.':
pieces.append(piece)
return pieces
class BaseLoader(object):
"""Baseclass for all loaders. Subclass this and override `get_source` to
implement a custom loading mechanism. The environment provides a
`get_template` method that calls the loader's `load` method to get the
:class:`Template` object.
A very basic example for a loader that looks up templates on the file
system could look like this::
from jinja2 import BaseLoader, TemplateNotFound
from os.path import join, exists, getmtime
class MyLoader(BaseLoader):
def __init__(self, path):
self.path = path
def get_source(self, environment, template):
path = join(self.path, template)
if not exists(path):
raise TemplateNotFound(template)
mtime = getmtime(path)
with file(path) as f:
source = f.read().decode('utf-8')
return source, path, lambda: mtime == getmtime(path)
"""
def get_source(self, environment, template):
"""Get the template source, filename and reload helper for a template.
It's passed the environment and template name and has to return a
tuple in the form ``(source, filename, uptodate)`` or raise a
`TemplateNotFound` error if it can't locate the template.
The source part of the returned tuple must be the source of the
template as unicode string or a ASCII bytestring. The filename should
be the name of the file on the filesystem if it was loaded from there,
otherwise `None`. The filename is used by python for the tracebacks
if no loader extension is used.
The last item in the tuple is the `uptodate` function. If auto
reloading is enabled it's always called to check if the template
changed. No arguments are passed so the function must store the
old state somewhere (for example in a closure). If it returns `False`
the template will be reloaded.
"""
raise TemplateNotFound(template)
def load(self, environment, name, globals=None):
"""Loads a template. This method looks up the template in the cache
or loads one by calling :meth:`get_source`. Subclasses should not
override this method as loaders working on collections of other
loaders (such as :class:`PrefixLoader` or :class:`ChoiceLoader`)
will not call this method but `get_source` directly.
"""
if globals is None:
globals = {}
source, filename, uptodate = self.get_source(environment, name)
code = environment.compile(source, name, filename)
return environment.template_class.from_code(environment, code,
globals, uptodate)
class FileSystemLoader(BaseLoader):
"""Loads templates from the file system. This loader can find templates
in folders on the file system and is the preferred way to load them.
The loader takes the path to the templates as string, or if multiple
locations are wanted a list of them which is then looked up in the
given order:
>>> loader = FileSystemLoader('/path/to/templates')
>>> loader = FileSystemLoader(['/path/to/templates', '/other/path'])
Per default the template encoding is ``'utf-8'`` which can be changed
by setting the `encoding` parameter to something else.
"""
def __init__(self, searchpath, encoding='utf-8'):
if isinstance(searchpath, basestring):
searchpath = [searchpath]
self.searchpath = list(searchpath)
self.encoding = encoding
def get_source(self, environment, template):
pieces = split_template_path(template)
for searchpath in self.searchpath:
filename = path.join(searchpath, *pieces)
if not path.isfile(filename):
continue
f = file(filename)
try:
contents = f.read().decode(self.encoding)
finally:
f.close()
old = path.getmtime(filename)
return contents, filename, lambda: path.getmtime(filename) == old
raise TemplateNotFound(template)
class PackageLoader(BaseLoader):
"""Load templates from python eggs or packages. It is constructed with
the name of the python package and the path to the templates in that
package:
>>> loader = PackageLoader('mypackage', 'views')
If the package path is not given, ``'templates'`` is assumed.
Per default the template encoding is ``'utf-8'`` which can be changed
by setting the `encoding` parameter to something else. Due to the nature
of eggs it's only possible to reload templates if the package was loaded
from the file system and not a zip file.
"""
def __init__(self, package_name, package_path='templates',
encoding='utf-8'):
from pkg_resources import DefaultProvider, ResourceManager, get_provider
provider = get_provider(package_name)
self.encoding = encoding
self.manager = ResourceManager()
self.filesystem_bound = isinstance(provider, DefaultProvider)
self.provider = provider
self.package_path = package_path
def get_source(self, environment, template):
pieces = split_template_path(template)
p = '/'.join((self.package_path,) + tuple(pieces))
if not self.provider.has_resource(p):
raise TemplateNotFound(template)
filename = uptodate = None
if self.filesystem_bound:
filename = self.provider.get_resource_filename(self.manager, p)
mtime = path.getmtime(filename)
def uptodate():
return path.getmtime(filename) == mtime
source = self.provider.get_resource_string(self.manager, p)
return source.decode(self.encoding), filename, uptodate
class DictLoader(BaseLoader):
"""Loads a template from a python dict. It's passed a dict of unicode
strings bound to template names. This loader is useful for unittesting:
>>> loader = DictLoader({'index.html': 'source here'})
Because auto reloading is rarely useful this is disabled per default.
"""
def __init__(self, mapping):
self.mapping = mapping
def get_source(self, environment, template):
if template in self.mapping:
source = self.mapping[template]
return source, None, lambda: source != self.mapping[template]
raise TemplateNotFound(template)
class FunctionLoader(BaseLoader):
"""A loader that is passed a function which does the loading. The
function becomes the name of the template passed and has to return either
an unicode string with the template source, a tuple in the form ``(source,
filename, uptodatefunc)`` or `None` if the template does not exist.
>>> def load_template(name):
... if name == 'index.html'
... return '...'
...
>>> loader = FunctionLoader(load_template)
The `uptodatefunc` is a function that is called if autoreload is enabled
and has to return `True` if the template is still up to date. For more
details have a look at :meth:`BaseLoader.get_source` which has the same
return value.
"""
def __init__(self, load_func):
self.load_func = load_func
def get_source(self, environment, template):
rv = self.load_func(template)
if rv is None:
raise TemplateNotFound(template)
elif isinstance(rv, basestring):
return rv, None, None
return rv
class PrefixLoader(BaseLoader):
"""A loader that is passed a dict of loaders where each loader is bound
to a prefix. The prefix is delimited from the template by a slash per
default, which can be changed by setting the `delimiter` argument to
something else.
>>> loader = PrefixLoader({
... 'app1': PackageLoader('mypackage.app1'),
... 'app2': PackageLoader('mypackage.app2')
... })
By loading ``'app1/index.html'`` the file from the app1 package is loaded,
by loading ``'app2/index.html'`` the file from the second.
"""
def __init__(self, mapping, delimiter='/'):
self.mapping = mapping
self.delimiter = delimiter
def get_source(self, environment, template):
try:
prefix, template = template.split(self.delimiter, 1)
loader = self.mapping[prefix]
except (ValueError, KeyError):
raise TemplateNotFound(template)
return loader.get_source(environment, template)
class ChoiceLoader(BaseLoader):
"""This loader works like the `PrefixLoader` just that no prefix is
specified. If a template could not be found by one loader the next one
is tried.
>>> loader = ChoiceLoader([
... FileSystemLoader('/path/to/user/templates'),
... PackageLoader('mypackage')
... ])
This is useful if you want to allow users to override builtin templates
from a different location.
"""
def __init__(self, loaders):
self.loaders = loaders
def get_source(self, environment, template):
for loader in self.loaders:
try:
return loader.get_source(environment, template)
except TemplateNotFound:
pass
raise TemplateNotFound(template)
./weblog+jinja-1.1/jinja2/nodes.py 0100644 0001750 0000000 00000057130 11063022145 0015754 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.nodes
~~~~~~~~~~~~
This module implements additional nodes derived from the ast base node.
It also provides some node tree helper functions like `in_lineno` and
`get_nodes` used by the parser and translator in order to normalize
python and jinja nodes.
:copyright: 2008 by Armin Ronacher.
:license: BSD, see LICENSE for more details.
"""
import operator
from copy import copy
from itertools import chain, izip
from collections import deque
from jinja2.utils import Markup
_binop_to_func = {
'*': operator.mul,
'/': operator.truediv,
'//': operator.floordiv,
'**': operator.pow,
'%': operator.mod,
'+': operator.add,
'-': operator.sub
}
_uaop_to_func = {
'not': operator.not_,
'+': operator.pos,
'-': operator.neg
}
_cmpop_to_func = {
'eq': operator.eq,
'ne': operator.ne,
'gt': operator.gt,
'gteq': operator.ge,
'lt': operator.lt,
'lteq': operator.le,
'in': lambda a, b: a in b,
'notin': lambda a, b: a not in b
}
class Impossible(Exception):
"""Raised if the node could not perform a requested action."""
class NodeType(type):
"""A metaclass for nodes that handles the field and attribute
inheritance. fields and attributes from the parent class are
automatically forwarded to the child."""
def __new__(cls, name, bases, d):
for attr in 'fields', 'attributes':
storage = []
storage.extend(getattr(bases[0], attr, ()))
storage.extend(d.get(attr, ()))
assert len(bases) == 1, 'multiple inheritance not allowed'
assert len(storage) == len(set(storage)), 'layout conflict'
d[attr] = tuple(storage)
d.setdefault('abstract', False)
return type.__new__(cls, name, bases, d)
class Node(object):
"""Baseclass for all Jinja2 nodes. There are a number of nodes available
of different types. There are three major types:
- :class:`Stmt`: statements
- :class:`Expr`: expressions
- :class:`Helper`: helper nodes
- :class:`Template`: the outermost wrapper node
All nodes have fields and attributes. Fields may be other nodes, lists,
or arbitrary values. Fields are passed to the constructor as regular
positional arguments, attributes as keyword arguments. Each node has
two attributes: `lineno` (the line number of the node) and `environment`.
The `environment` attribute is set at the end of the parsing process for
all nodes automatically.
"""
__metaclass__ = NodeType
fields = ()
attributes = ('lineno', 'environment')
abstract = True
def __init__(self, *fields, **attributes):
if self.abstract:
raise TypeError('abstract nodes are not instanciable')
if fields:
if len(fields) != len(self.fields):
if not self.fields:
raise TypeError('%r takes 0 arguments' %
self.__class__.__name__)
raise TypeError('%r takes 0 or %d argument%s' % (
self.__class__.__name__,
len(self.fields),
len(self.fields) != 1 and 's' or ''
))
for name, arg in izip(self.fields, fields):
setattr(self, name, arg)
for attr in self.attributes:
setattr(self, attr, attributes.pop(attr, None))
if attributes:
raise TypeError('unknown attribute %r' %
iter(attributes).next())
def iter_fields(self, exclude=None, only=None):
"""This method iterates over all fields that are defined and yields
``(key, value)`` tuples. Per default all fields are returned, but
it's possible to limit that to some fields by providing the `only`
parameter or to exclude some using the `exclude` parameter. Both
should be sets or tuples of field names.
"""
for name in self.fields:
if (exclude is only is None) or \
(exclude is not None and name not in exclude) or \
(only is not None and name in only):
try:
yield name, getattr(self, name)
except AttributeError:
pass
def iter_child_nodes(self, exclude=None, only=None):
"""Iterates over all direct child nodes of the node. This iterates
over all fields and yields the values of they are nodes. If the value
of a field is a list all the nodes in that list are returned.
"""
for field, item in self.iter_fields(exclude, only):
if isinstance(item, list):
for n in item:
if isinstance(n, Node):
yield n
elif isinstance(item, Node):
yield item
def find(self, node_type):
"""Find the first node of a given type. If no such node exists the
return value is `None`.
"""
for result in self.find_all(node_type):
return result
def find_all(self, node_type):
"""Find all the nodes of a given type."""
for child in self.iter_child_nodes():
if isinstance(child, node_type):
yield child
for result in child.find_all(node_type):
yield result
def copy(self):
"""Return a deep copy of the node."""
result = object.__new__(self.__class__)
for field, value in self.iter_fields():
if isinstance(value, Node):
new_value = value.copy()
elif isinstance(value, list):
new_value = []
for item in value:
if isinstance(item, Node):
item = item.copy()
else:
item = copy(item)
new_value.append(item)
else:
new_value = copy(value)
setattr(result, field, new_value)
for attr in self.attributes:
try:
setattr(result, attr, getattr(self, attr))
except AttributeError:
pass
return result
def set_ctx(self, ctx):
"""Reset the context of a node and all child nodes. Per default the
parser will all generate nodes that have a 'load' context as it's the
most common one. This method is used in the parser to set assignment
targets and other nodes to a store context.
"""
todo = deque([self])
while todo:
node = todo.popleft()
if 'ctx' in node.fields:
node.ctx = ctx
todo.extend(node.iter_child_nodes())
return self
def set_lineno(self, lineno, override=False):
"""Set the line numbers of the node and children."""
todo = deque([self])
while todo:
node = todo.popleft()
if 'lineno' in node.attributes:
if node.lineno is None or override:
node.lineno = lineno
todo.extend(node.iter_child_nodes())
return self
def set_environment(self, environment):
"""Set the environment for all nodes."""
todo = deque([self])
while todo:
node = todo.popleft()
node.environment = environment
todo.extend(node.iter_child_nodes())
return self
def __eq__(self, other):
return type(self) is type(other) and \
tuple(self.iter_fields()) == tuple(other.iter_fields())
def __ne__(self, other):
return not self.__eq__(other)
def __repr__(self):
return '%s(%s)' % (
self.__class__.__name__,
', '.join('%s=%r' % (arg, getattr(self, arg, None)) for
arg in self.fields)
)
class Stmt(Node):
"""Base node for all statements."""
abstract = True
class Helper(Node):
"""Nodes that exist in a specific context only."""
abstract = True
class Template(Node):
"""Node that represents a template. This must be the outermost node that
is passed to the compiler.
"""
fields = ('body',)
class Output(Stmt):
"""A node that holds multiple expressions which are then printed out.
This is used both for the `print` statement and the regular template data.
"""
fields = ('nodes',)
class Extends(Stmt):
"""Represents an extends statement."""
fields = ('template',)
class For(Stmt):
"""The for loop. `target` is the target for the iteration (usually a
:class:`Name` or :class:`Tuple`), `iter` the iterable. `body` is a list
of nodes that are used as loop-body, and `else_` a list of nodes for the
`else` block. If no else node exists it has to be an empty list.
For filtered nodes an expression can be stored as `test`, otherwise `None`.
"""
fields = ('target', 'iter', 'body', 'else_', 'test', 'recursive')
class If(Stmt):
"""If `test` is true, `body` is rendered, else `else_`."""
fields = ('test', 'body', 'else_')
class Macro(Stmt):
"""A macro definition. `name` is the name of the macro, `args` a list of
arguments and `defaults` a list of defaults if there are any. `body` is
a list of nodes for the macro body.
"""
fields = ('name', 'args', 'defaults', 'body')
class CallBlock(Stmt):
"""Like a macro without a name but a call instead. `call` is called with
the unnamed macro as `caller` argument this node holds.
"""
fields = ('call', 'args', 'defaults', 'body')
class Set(Stmt):
"""Allows defining own variables."""
fields = ('name', 'expr')
class FilterBlock(Stmt):
"""Node for filter sections."""
fields = ('body', 'filter')
class Block(Stmt):
"""A node that represents a block."""
fields = ('name', 'body')
class Include(Stmt):
"""A node that represents the include tag."""
fields = ('template', 'with_context')
class Import(Stmt):
"""A node that represents the import tag."""
fields = ('template', 'target', 'with_context')
class FromImport(Stmt):
"""A node that represents the from import tag. It's important to not
pass unsafe names to the name attribute. The compiler translates the
attribute lookups directly into getattr calls and does *not* use the
subscript callback of the interface. As exported variables may not
start with double underscores (which the parser asserts) this is not a
problem for regular Jinja code, but if this node is used in an extension
extra care must be taken.
The list of names may contain tuples if aliases are wanted.
"""
fields = ('template', 'names', 'with_context')
class ExprStmt(Stmt):
"""A statement that evaluates an expression and discards the result."""
fields = ('node',)
class Assign(Stmt):
"""Assigns an expression to a target."""
fields = ('target', 'node')
class Expr(Node):
"""Baseclass for all expressions."""
abstract = True
def as_const(self):
"""Return the value of the expression as constant or raise
:exc:`Impossible` if this was not possible:
>>> Add(Const(23), Const(42)).as_const()
65
>>> Add(Const(23), Name('var', 'load')).as_const()
Traceback (most recent call last):
...
Impossible
This requires the `environment` attribute of all nodes to be
set to the environment that created the nodes.
"""
raise Impossible()
def can_assign(self):
"""Check if it's possible to assign something to this node."""
return False
class BinExpr(Expr):
"""Baseclass for all binary expressions."""
fields = ('left', 'right')
operator = None
abstract = True
def as_const(self):
f = _binop_to_func[self.operator]
try:
return f(self.left.as_const(), self.right.as_const())
except:
raise Impossible()
class UnaryExpr(Expr):
"""Baseclass for all unary expressions."""
fields = ('node',)
operator = None
abstract = True
def as_const(self):
f = _uaop_to_func[self.operator]
try:
return f(self.node.as_const())
except:
raise Impossible()
class Name(Expr):
"""Looks up a name or stores a value in a name.
The `ctx` of the node can be one of the following values:
- `store`: store a value in the name
- `load`: load that name
- `param`: like `store` but if the name was defined as function parameter.
"""
fields = ('name', 'ctx')
def can_assign(self):
return self.name not in ('true', 'false', 'none',
'True', 'False', 'None')
class Literal(Expr):
"""Baseclass for literals."""
abstract = True
class Const(Literal):
"""All constant values. The parser will return this node for simple
constants such as ``42`` or ``"foo"`` but it can be used to store more
complex values such as lists too. Only constants with a safe
representation (objects where ``eval(repr(x)) == x`` is true).
"""
fields = ('value',)
def as_const(self):
return self.value
@classmethod
def from_untrusted(cls, value, lineno=None, environment=None):
"""Return a const object if the value is representable as
constant value in the generated code, otherwise it will raise
an `Impossible` exception.
"""
from compiler import has_safe_repr
if not has_safe_repr(value):
raise Impossible()
return cls(value, lineno=lineno, environment=environment)
class TemplateData(Literal):
"""A constant template string."""
fields = ('data',)
def as_const(self):
if self.environment.autoescape:
return Markup(self.data)
return self.data
class Tuple(Literal):
"""For loop unpacking and some other things like multiple arguments
for subscripts. Like for :class:`Name` `ctx` specifies if the tuple
is used for loading the names or storing.
"""
fields = ('items', 'ctx')
def as_const(self):
return tuple(x.as_const() for x in self.items)
def can_assign(self):
for item in self.items:
if not item.can_assign():
return False
return True
class List(Literal):
"""Any list literal such as ``[1, 2, 3]``"""
fields = ('items',)
def as_const(self):
return [x.as_const() for x in self.items]
class Dict(Literal):
"""Any dict literal such as ``{1: 2, 3: 4}``. The items must be a list of
:class:`Pair` nodes.
"""
fields = ('items',)
def as_const(self):
return dict(x.as_const() for x in self.items)
class Pair(Helper):
"""A key, value pair for dicts."""
fields = ('key', 'value')
def as_const(self):
return self.key.as_const(), self.value.as_const()
class Keyword(Helper):
"""A key, value pair for keyword arguments where key is a string."""
fields = ('key', 'value')
class CondExpr(Expr):
"""A conditional expression (inline if expression). (``{{
foo if bar else baz }}``)
"""
fields = ('test', 'expr1', 'expr2')
def as_const(self):
if self.test.as_const():
return self.expr1.as_const()
# if we evaluate to an undefined object, we better do that at runtime
if self.expr2 is None:
raise Impossible()
return self.expr2.as_const()
class Filter(Expr):
"""This node applies a filter on an expression. `name` is the name of
the filter, the rest of the fields are the same as for :class:`Call`.
If the `node` of a filter is `None` the contents of the last buffer are
filtered. Buffers are created by macros and filter blocks.
"""
fields = ('node', 'name', 'args', 'kwargs', 'dyn_args', 'dyn_kwargs')
def as_const(self, obj=None):
if self.node is obj is None:
raise Impossible()
filter = self.environment.filters.get(self.name)
if filter is None or getattr(filter, 'contextfilter', False):
raise Impossible()
if obj is None:
obj = self.node.as_const()
args = [x.as_const() for x in self.args]
if getattr(filter, 'environmentfilter', False):
args.insert(0, self.environment)
kwargs = dict(x.as_const() for x in self.kwargs)
if self.dyn_args is not None:
try:
args.extend(self.dyn_args.as_const())
except:
raise Impossible()
if self.dyn_kwargs is not None:
try:
kwargs.update(self.dyn_kwargs.as_const())
except:
raise Impossible()
try:
return filter(obj, *args, **kwargs)
except:
raise Impossible()
class Test(Expr):
"""Applies a test on an expression. `name` is the name of the test, the
rest of the fields are the same as for :class:`Call`.
"""
fields = ('node', 'name', 'args', 'kwargs', 'dyn_args', 'dyn_kwargs')
class Call(Expr):
"""Calls an expression. `args` is a list of arguments, `kwargs` a list
of keyword arguments (list of :class:`Keyword` nodes), and `dyn_args`
and `dyn_kwargs` has to be either `None` or a node that is used as
node for dynamic positional (``*args``) or keyword (``**kwargs``)
arguments.
"""
fields = ('node', 'args', 'kwargs', 'dyn_args', 'dyn_kwargs')
def as_const(self):
obj = self.node.as_const()
# don't evaluate context functions
args = [x.as_const() for x in self.args]
if getattr(obj, 'contextfunction', False):
raise Impossible()
elif getattr(obj, 'environmentfunction', False):
args.insert(0, self.environment)
kwargs = dict(x.as_const() for x in self.kwargs)
if self.dyn_args is not None:
try:
args.extend(self.dyn_args.as_const())
except:
raise Impossible()
if self.dyn_kwargs is not None:
try:
kwargs.update(self.dyn_kwargs.as_const())
except:
raise Impossible()
try:
return obj(*args, **kwargs)
except:
raise Impossible()
class Getitem(Expr):
"""Get an attribute or item from an expression and prefer the item."""
fields = ('node', 'arg', 'ctx')
def as_const(self):
if self.ctx != 'load':
raise Impossible()
try:
return self.environment.getitem(self.node.as_const(),
self.arg.as_const())
except:
raise Impossible()
def can_assign(self):
return False
class Getattr(Expr):
"""Get an attribute or item from an expression that is a ascii-only
bytestring and prefer the attribute.
"""
fields = ('node', 'attr', 'ctx')
def as_const(self):
if self.ctx != 'load':
raise Impossible()
try:
return self.environment.getattr(self.node.as_const(), arg)
except:
raise Impossible()
def can_assign(self):
return False
class Slice(Expr):
"""Represents a slice object. This must only be used as argument for
:class:`Subscript`.
"""
fields = ('start', 'stop', 'step')
def as_const(self):
def const(obj):
if obj is None:
return obj
return obj.as_const()
return slice(const(self.start), const(self.stop), const(self.step))
class Concat(Expr):
"""Concatenates the list of expressions provided after converting them to
unicode.
"""
fields = ('nodes',)
def as_const(self):
return ''.join(unicode(x.as_const()) for x in self.nodes)
class Compare(Expr):
"""Compares an expression with some other expressions. `ops` must be a
list of :class:`Operand`\s.
"""
fields = ('expr', 'ops')
def as_const(self):
result = value = self.expr.as_const()
try:
for op in self.ops:
new_value = op.expr.as_const()
result = _cmpop_to_func[op.op](value, new_value)
value = new_value
except:
raise Impossible()
return result
class Operand(Helper):
"""Holds an operator and an expression."""
fields = ('op', 'expr')
if __debug__:
Operand.__doc__ += '\nThe following operators are available: ' + \
', '.join(sorted('``%s``' % x for x in set(_binop_to_func) |
set(_uaop_to_func) | set(_cmpop_to_func)))
class Mul(BinExpr):
"""Multiplies the left with the right node."""
operator = '*'
class Div(BinExpr):
"""Divides the left by the right node."""
operator = '/'
class FloorDiv(BinExpr):
"""Divides the left by the right node and truncates conver the
result into an integer by truncating.
"""
operator = '//'
class Add(BinExpr):
"""Add the left to the right node."""
operator = '+'
class Sub(BinExpr):
"""Substract the right from the left node."""
operator = '-'
class Mod(BinExpr):
"""Left modulo right."""
operator = '%'
class Pow(BinExpr):
"""Left to the power of right."""
operator = '**'
class And(BinExpr):
"""Short circuited AND."""
operator = 'and'
def as_const(self):
return self.left.as_const() and self.right.as_const()
class Or(BinExpr):
"""Short circuited OR."""
operator = 'or'
def as_const(self):
return self.left.as_const() or self.right.as_const()
class Not(UnaryExpr):
"""Negate the expression."""
operator = 'not'
class Neg(UnaryExpr):
"""Make the expression negative."""
operator = '-'
class Pos(UnaryExpr):
"""Make the expression positive (noop for most expressions)"""
operator = '+'
# Helpers for extensions
class EnvironmentAttribute(Expr):
"""Loads an attribute from the environment object. This is useful for
extensions that want to call a callback stored on the environment.
"""
fields = ('name',)
class ExtensionAttribute(Expr):
"""Returns the attribute of an extension bound to the environment.
The identifier is the identifier of the :class:`Extension`.
This node is usually constructed by calling the
:meth:`~jinja2.ext.Extension.attr` method on an extension.
"""
fields = ('identifier', 'name')
class ImportedName(Expr):
"""If created with an import name the import name is returned on node
access. For example ``ImportedName('cgi.escape')`` returns the `escape`
function from the cgi module on evaluation. Imports are optimized by the
compiler so there is no need to assign them to local variables.
"""
fields = ('importname',)
class InternalName(Expr):
"""An internal name in the compiler. You cannot create these nodes
yourself but the parser provides a
:meth:`~jinja2.parser.Parser.free_identifier` method that creates
a new identifier for you. This identifier is not available from the
template and is not threated specially by the compiler.
"""
fields = ('name',)
def __init__(self):
raise TypeError('Can\'t create internal names. Use the '
'`free_identifier` method on a parser.')
class MarkSafe(Expr):
"""Mark the wrapped expression as safe (wrap it as `Markup`)."""
fields = ('expr',)
def as_const(self):
return Markup(self.expr.as_const())
class ContextReference(Expr):
"""Returns the current template context."""
class Continue(Stmt):
"""Continue a loop."""
class Break(Stmt):
"""Break a loop."""
# make sure nobody creates custom nodes
def _failing_new(*args, **kwargs):
raise TypeError('can\'t create custom node types')
NodeType.__new__ = staticmethod(_failing_new); del _failing_new
./weblog+jinja-1.1/jinja2/optimizer.py 0100644 0001750 0000000 00000004424 11063022145 0016664 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.optimizer
~~~~~~~~~~~~~~~~
The jinja optimizer is currently trying to constant fold a few expressions
and modify the AST in place so that it should be easier to evaluate it.
Because the AST does not contain all the scoping information and the
compiler has to find that out, we cannot do all the optimizations we
want. For example loop unrolling doesn't work because unrolled loops would
have a different scoping.
The solution would be a second syntax tree that has the scoping rules stored.
:copyright: Copyright 2008 by Christoph Hack, Armin Ronacher.
:license: BSD.
"""
from jinja2 import nodes
from jinja2.visitor import NodeTransformer
def optimize(node, environment):
"""The context hint can be used to perform an static optimization
based on the context given."""
optimizer = Optimizer(environment)
return optimizer.visit(node)
class Optimizer(NodeTransformer):
def __init__(self, environment):
self.environment = environment
def visit_If(self, node):
"""Eliminate dead code."""
# do not optimize ifs that have a block inside so that it doesn't
# break super().
if node.find(nodes.Block) is not None:
return self.generic_visit(node)
try:
val = self.visit(node.test).as_const()
except nodes.Impossible:
return self.generic_visit(node)
if val:
body = node.body
else:
body = node.else_
result = []
for node in body:
result.extend(self.visit_list(node))
return result
def fold(self, node):
"""Do constant folding."""
node = self.generic_visit(node)
try:
return nodes.Const.from_untrusted(node.as_const(),
lineno=node.lineno,
environment=self.environment)
except nodes.Impossible:
return node
visit_Add = visit_Sub = visit_Mul = visit_Div = visit_FloorDiv = \
visit_Pow = visit_Mod = visit_And = visit_Or = visit_Pos = visit_Neg = \
visit_Not = visit_Compare = visit_Getitem = visit_Getattr = visit_Call = \
visit_Filter = visit_Test = visit_CondExpr = fold
del fold
./weblog+jinja-1.1/jinja2/parser.py 0100644 0001750 0000000 00000073254 11063022145 0016145 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.parser
~~~~~~~~~~~~~
Implements the template parser.
:copyright: 2008 by Armin Ronacher.
:license: BSD, see LICENSE for more details.
"""
from jinja2 import nodes
from jinja2.exceptions import TemplateSyntaxError, TemplateAssertionError
_statement_keywords = frozenset(['for', 'if', 'block', 'extends', 'print',
'macro', 'include', 'from', 'import',
'set'])
_compare_operators = frozenset(['eq', 'ne', 'lt', 'lteq', 'gt', 'gteq'])
class Parser(object):
"""This is the central parsing class Jinja2 uses. It's passed to
extensions and can be used to parse expressions or statements.
"""
def __init__(self, environment, source, name=None, filename=None):
self.environment = environment
self.stream = environment._tokenize(source, name, filename)
self.name = name
self.filename = filename
self.closed = False
self.extensions = {}
for extension in environment.extensions.itervalues():
for tag in extension.tags:
self.extensions[tag] = extension.parse
self._last_identifier = 0
def fail(self, msg, lineno=None, exc=TemplateSyntaxError):
"""Convenience method that raises `exc` with the message, passed
line number or last line number as well as the current name and
filename.
"""
if lineno is None:
lineno = self.stream.current.lineno
raise exc(msg, lineno, self.name, self.filename)
def is_tuple_end(self, extra_end_rules=None):
"""Are we at the end of a tuple?"""
if self.stream.current.type in ('variable_end', 'block_end', 'rparen'):
return True
elif extra_end_rules is not None:
return self.stream.current.test_any(extra_end_rules)
return False
def free_identifier(self, lineno=None):
"""Return a new free identifier as :class:`~jinja2.nodes.InternalName`."""
self._last_identifier += 1
rv = object.__new__(nodes.InternalName)
nodes.Node.__init__(rv, 'fi%d' % self._last_identifier, lineno=lineno)
return rv
def parse_statement(self):
"""Parse a single statement."""
token = self.stream.current
if token.type is not 'name':
self.fail('tag name expected', token.lineno)
if token.value in _statement_keywords:
return getattr(self, 'parse_' + self.stream.current.value)()
if token.value == 'call':
return self.parse_call_block()
if token.value == 'filter':
return self.parse_filter_block()
ext = self.extensions.get(token.value)
if ext is not None:
return ext(self)
self.fail('unknown tag %r' % token.value, token.lineno)
def parse_statements(self, end_tokens, drop_needle=False):
"""Parse multiple statements into a list until one of the end tokens
is reached. This is used to parse the body of statements as it also
parses template data if appropriate. The parser checks first if the
current token is a colon and skips it if there is one. Then it checks
for the block end and parses until if one of the `end_tokens` is
reached. Per default the active token in the stream at the end of
the call is the matched end token. If this is not wanted `drop_needle`
can be set to `True` and the end token is removed.
"""
# the first token may be a colon for python compatibility
self.stream.skip_if('colon')
# in the future it would be possible to add whole code sections
# by adding some sort of end of statement token and parsing those here.
self.stream.expect('block_end')
result = self.subparse(end_tokens)
if drop_needle:
self.stream.next()
return result
def parse_set(self):
"""Parse an assign statement."""
lineno = self.stream.next().lineno
target = self.parse_assign_target()
self.stream.expect('assign')
expr = self.parse_tuple()
return nodes.Assign(target, expr, lineno=lineno)
def parse_for(self):
"""Parse a for loop."""
lineno = self.stream.expect('name:for').lineno
target = self.parse_assign_target(extra_end_rules=('name:in',))
self.stream.expect('name:in')
iter = self.parse_tuple(with_condexpr=False,
extra_end_rules=('name:recursive',))
test = None
if self.stream.skip_if('name:if'):
test = self.parse_expression()
recursive = self.stream.skip_if('name:recursive')
body = self.parse_statements(('name:endfor', 'name:else'))
if self.stream.next().value == 'endfor':
else_ = []
else:
else_ = self.parse_statements(('name:endfor',), drop_needle=True)
return nodes.For(target, iter, body, else_, test,
recursive, lineno=lineno)
def parse_if(self):
"""Parse an if construct."""
node = result = nodes.If(lineno=self.stream.expect('name:if').lineno)
while 1:
node.test = self.parse_tuple(with_condexpr=False)
node.body = self.parse_statements(('name:elif', 'name:else',
'name:endif'))
token = self.stream.next()
if token.test('name:elif'):
new_node = nodes.If(lineno=self.stream.current.lineno)
node.else_ = [new_node]
node = new_node
continue
elif token.test('name:else'):
node.else_ = self.parse_statements(('name:endif',),
drop_needle=True)
else:
node.else_ = []
break
return result
def parse_block(self):
node = nodes.Block(lineno=self.stream.next().lineno)
node.name = self.stream.expect('name').value
node.body = self.parse_statements(('name:endblock',), drop_needle=True)
self.stream.skip_if('name:' + node.name)
return node
def parse_extends(self):
node = nodes.Extends(lineno=self.stream.next().lineno)
node.template = self.parse_expression()
return node
def parse_import_context(self, node, default):
if self.stream.current.test_any('name:with', 'name:without') and \
self.stream.look().test('name:context'):
node.with_context = self.stream.next().value == 'with'
self.stream.skip()
else:
node.with_context = default
return node
def parse_include(self):
node = nodes.Include(lineno=self.stream.next().lineno)
node.template = self.parse_expression()
return self.parse_import_context(node, True)
def parse_import(self):
node = nodes.Import(lineno=self.stream.next().lineno)
node.template = self.parse_expression()
self.stream.expect('name:as')
node.target = self.parse_assign_target(name_only=True).name
return self.parse_import_context(node, False)
def parse_from(self):
node = nodes.FromImport(lineno=self.stream.next().lineno)
node.template = self.parse_expression()
self.stream.expect('name:import')
node.names = []
def parse_context():
if self.stream.current.value in ('with', 'without') and \
self.stream.look().test('name:context'):
node.with_context = self.stream.next().value == 'with'
self.stream.skip()
return True
return False
while 1:
if node.names:
self.stream.expect('comma')
if self.stream.current.type is 'name':
if parse_context():
break
target = self.parse_assign_target(name_only=True)
if target.name.startswith('_'):
self.fail('names starting with an underline can not '
'be imported', target.lineno,
exc=TemplateAssertionError)
if self.stream.skip_if('name:as'):
alias = self.parse_assign_target(name_only=True)
node.names.append((target.name, alias.name))
else:
node.names.append(target.name)
if parse_context() or self.stream.current.type is not 'comma':
break
else:
break
if not hasattr(node, 'with_context'):
node.with_context = False
self.stream.skip_if('comma')
return node
def parse_signature(self, node):
node.args = args = []
node.defaults = defaults = []
self.stream.expect('lparen')
while self.stream.current.type is not 'rparen':
if args:
self.stream.expect('comma')
arg = self.parse_assign_target(name_only=True)
arg.set_ctx('param')
if self.stream.skip_if('assign'):
defaults.append(self.parse_expression())
args.append(arg)
self.stream.expect('rparen')
def parse_call_block(self):
node = nodes.CallBlock(lineno=self.stream.next().lineno)
if self.stream.current.type is 'lparen':
self.parse_signature(node)
else:
node.args = []
node.defaults = []
node.call = self.parse_expression()
if not isinstance(node.call, nodes.Call):
self.fail('expected call', node.lineno)
node.body = self.parse_statements(('name:endcall',), drop_needle=True)
return node
def parse_filter_block(self):
node = nodes.FilterBlock(lineno=self.stream.next().lineno)
node.filter = self.parse_filter(None, start_inline=True)
node.body = self.parse_statements(('name:endfilter',),
drop_needle=True)
return node
def parse_macro(self):
node = nodes.Macro(lineno=self.stream.next().lineno)
node.name = self.parse_assign_target(name_only=True).name
self.parse_signature(node)
node.body = self.parse_statements(('name:endmacro',),
drop_needle=True)
return node
def parse_print(self):
node = nodes.Output(lineno=self.stream.next().lineno)
node.nodes = []
while self.stream.current.type is not 'block_end':
if node.nodes:
self.stream.expect('comma')
node.nodes.append(self.parse_expression())
return node
def parse_assign_target(self, with_tuple=True, name_only=False,
extra_end_rules=None):
"""Parse an assignment target. As Jinja2 allows assignments to
tuples, this function can parse all allowed assignment targets. Per
default assignments to tuples are parsed, that can be disable however
by setting `with_tuple` to `False`. If only assignments to names are
wanted `name_only` can be set to `True`. The `extra_end_rules`
parameter is forwarded to the tuple parsing function.
"""
if name_only:
token = self.stream.expect('name')
target = nodes.Name(token.value, 'store', lineno=token.lineno)
else:
if with_tuple:
target = self.parse_tuple(simplified=True,
extra_end_rules=extra_end_rules)
else:
target = self.parse_primary(with_postfix=False)
target.set_ctx('store')
if not target.can_assign():
self.fail('can\'t assign to %r' % target.__class__.
__name__.lower(), target.lineno)
return target
def parse_expression(self, with_condexpr=True):
"""Parse an expression. Per default all expressions are parsed, if
the optional `with_condexpr` parameter is set to `False` conditional
expressions are not parsed.
"""
if with_condexpr:
return self.parse_condexpr()
return self.parse_or()
def parse_condexpr(self):
lineno = self.stream.current.lineno
expr1 = self.parse_or()
while self.stream.skip_if('name:if'):
expr2 = self.parse_or()
if self.stream.skip_if('name:else'):
expr3 = self.parse_condexpr()
else:
expr3 = None
expr1 = nodes.CondExpr(expr2, expr1, expr3, lineno=lineno)
lineno = self.stream.current.lineno
return expr1
def parse_or(self):
lineno = self.stream.current.lineno
left = self.parse_and()
while self.stream.skip_if('name:or'):
right = self.parse_and()
left = nodes.Or(left, right, lineno=lineno)
lineno = self.stream.current.lineno
return left
def parse_and(self):
lineno = self.stream.current.lineno
left = self.parse_compare()
while self.stream.skip_if('name:and'):
right = self.parse_compare()
left = nodes.And(left, right, lineno=lineno)
lineno = self.stream.current.lineno
return left
def parse_compare(self):
lineno = self.stream.current.lineno
expr = self.parse_add()
ops = []
while 1:
token_type = self.stream.current.type
if token_type in _compare_operators:
self.stream.next()
ops.append(nodes.Operand(token_type, self.parse_add()))
elif self.stream.skip_if('name:in'):
ops.append(nodes.Operand('in', self.parse_add()))
elif self.stream.current.test('name:not') and \
self.stream.look().test('name:in'):
self.stream.skip(2)
ops.append(nodes.Operand('notin', self.parse_add()))
else:
break
lineno = self.stream.current.lineno
if not ops:
return expr
return nodes.Compare(expr, ops, lineno=lineno)
def parse_add(self):
lineno = self.stream.current.lineno
left = self.parse_sub()
while self.stream.current.type is 'add':
self.stream.next()
right = self.parse_sub()
left = nodes.Add(left, right, lineno=lineno)
lineno = self.stream.current.lineno
return left
def parse_sub(self):
lineno = self.stream.current.lineno
left = self.parse_concat()
while self.stream.current.type is 'sub':
self.stream.next()
right = self.parse_concat()
left = nodes.Sub(left, right, lineno=lineno)
lineno = self.stream.current.lineno
return left
def parse_concat(self):
lineno = self.stream.current.lineno
args = [self.parse_mul()]
while self.stream.current.type is 'tilde':
self.stream.next()
args.append(self.parse_mul())
if len(args) == 1:
return args[0]
return nodes.Concat(args, lineno=lineno)
def parse_mul(self):
lineno = self.stream.current.lineno
left = self.parse_div()
while self.stream.current.type is 'mul':
self.stream.next()
right = self.parse_div()
left = nodes.Mul(left, right, lineno=lineno)
lineno = self.stream.current.lineno
return left
def parse_div(self):
lineno = self.stream.current.lineno
left = self.parse_floordiv()
while self.stream.current.type is 'div':
self.stream.next()
right = self.parse_floordiv()
left = nodes.Div(left, right, lineno=lineno)
lineno = self.stream.current.lineno
return left
def parse_floordiv(self):
lineno = self.stream.current.lineno
left = self.parse_mod()
while self.stream.current.type is 'floordiv':
self.stream.next()
right = self.parse_mod()
left = nodes.FloorDiv(left, right, lineno=lineno)
lineno = self.stream.current.lineno
return left
def parse_mod(self):
lineno = self.stream.current.lineno
left = self.parse_pow()
while self.stream.current.type is 'mod':
self.stream.next()
right = self.parse_pow()
left = nodes.Mod(left, right, lineno=lineno)
lineno = self.stream.current.lineno
return left
def parse_pow(self):
lineno = self.stream.current.lineno
left = self.parse_unary()
while self.stream.current.type is 'pow':
self.stream.next()
right = self.parse_unary()
left = nodes.Pow(left, right, lineno=lineno)
lineno = self.stream.current.lineno
return left
def parse_unary(self):
token_type = self.stream.current.type
lineno = self.stream.current.lineno
if token_type is 'name' and self.stream.current.value == 'not':
self.stream.next()
node = self.parse_unary()
return nodes.Not(node, lineno=lineno)
if token_type is 'sub':
self.stream.next()
node = self.parse_unary()
return nodes.Neg(node, lineno=lineno)
if token_type is 'add':
self.stream.next()
node = self.parse_unary()
return nodes.Pos(node, lineno=lineno)
return self.parse_primary()
def parse_primary(self, with_postfix=True):
token = self.stream.current
if token.type is 'name':
if token.value in ('true', 'false', 'True', 'False'):
node = nodes.Const(token.value in ('true', 'True'),
lineno=token.lineno)
elif token.value in ('none', 'None'):
node = nodes.Const(None, lineno=token.lineno)
else:
node = nodes.Name(token.value, 'load', lineno=token.lineno)
self.stream.next()
elif token.type is 'string':
self.stream.next()
buf = [token.value]
lineno = token.lineno
while self.stream.current.type is 'string':
buf.append(self.stream.current.value)
self.stream.next()
node = nodes.Const(''.join(buf), lineno=lineno)
elif token.type in ('integer', 'float'):
self.stream.next()
node = nodes.Const(token.value, lineno=token.lineno)
elif token.type is 'lparen':
self.stream.next()
node = self.parse_tuple()
self.stream.expect('rparen')
elif token.type is 'lbracket':
node = self.parse_list()
elif token.type is 'lbrace':
node = self.parse_dict()
else:
self.fail("unexpected token '%s'" % (token,), token.lineno)
if with_postfix:
node = self.parse_postfix(node)
return node
def parse_tuple(self, simplified=False, with_condexpr=True,
extra_end_rules=None):
"""Works like `parse_expression` but if multiple expressions are
delimited by a comma a :class:`~jinja2.nodes.Tuple` node is created.
This method could also return a regular expression instead of a tuple
if no commas where found.
The default parsing mode is a full tuple. If `simplified` is `True`
only names and literals are parsed. The `no_condexpr` parameter is
forwarded to :meth:`parse_expression`.
Because tuples do not require delimiters and may end in a bogus comma
an extra hint is needed that marks the end of a tuple. For example
for loops support tuples between `for` and `in`. In that case the
`extra_end_rules` is set to ``['name:in']``.
"""
lineno = self.stream.current.lineno
if simplified:
parse = lambda: self.parse_primary(with_postfix=False)
elif with_condexpr:
parse = self.parse_expression
else:
parse = lambda: self.parse_expression(with_condexpr=False)
args = []
is_tuple = False
while 1:
if args:
self.stream.expect('comma')
if self.is_tuple_end(extra_end_rules):
break
args.append(parse())
if self.stream.current.type is 'comma':
is_tuple = True
else:
break
lineno = self.stream.current.lineno
if not is_tuple and args:
return args[0]
return nodes.Tuple(args, 'load', lineno=lineno)
def parse_list(self):
token = self.stream.expect('lbracket')
items = []
while self.stream.current.type is not 'rbracket':
if items:
self.stream.expect('comma')
if self.stream.current.type == 'rbracket':
break
items.append(self.parse_expression())
self.stream.expect('rbracket')
return nodes.List(items, lineno=token.lineno)
def parse_dict(self):
token = self.stream.expect('lbrace')
items = []
while self.stream.current.type is not 'rbrace':
if items:
self.stream.expect('comma')
if self.stream.current.type == 'rbrace':
break
key = self.parse_expression()
self.stream.expect('colon')
value = self.parse_expression()
items.append(nodes.Pair(key, value, lineno=key.lineno))
self.stream.expect('rbrace')
return nodes.Dict(items, lineno=token.lineno)
def parse_postfix(self, node):
while 1:
token_type = self.stream.current.type
if token_type is 'dot' or token_type is 'lbracket':
node = self.parse_subscript(node)
elif token_type is 'lparen':
node = self.parse_call(node)
elif token_type is 'pipe':
node = self.parse_filter(node)
elif token_type is 'name' and self.stream.current.value == 'is':
node = self.parse_test(node)
else:
break
return node
def parse_subscript(self, node):
token = self.stream.next()
if token.type is 'dot':
attr_token = self.stream.current
self.stream.next()
if attr_token.type is 'name':
return nodes.Getattr(node, attr_token.value, 'load',
lineno=token.lineno)
elif attr_token.type is not 'integer':
self.fail('expected name or number', attr_token.lineno)
arg = nodes.Const(attr_token.value, lineno=attr_token.lineno)
return nodes.Getitem(node, arg, 'load', lineno=token.lineno)
if token.type is 'lbracket':
priority_on_attribute = False
args = []
while self.stream.current.type is not 'rbracket':
if args:
self.stream.expect('comma')
args.append(self.parse_subscribed())
self.stream.expect('rbracket')
if len(args) == 1:
arg = args[0]
else:
arg = nodes.Tuple(args, self.lineno, self.filename)
return nodes.Getitem(node, arg, 'load', lineno=token.lineno)
self.fail('expected subscript expression', self.lineno)
def parse_subscribed(self):
lineno = self.stream.current.lineno
if self.stream.current.type is 'colon':
self.stream.next()
args = [None]
else:
node = self.parse_expression()
if self.stream.current.type is not 'colon':
return node
self.stream.next()
args = [node]
if self.stream.current.type is 'colon':
args.append(None)
elif self.stream.current.type not in ('rbracket', 'comma'):
args.append(self.parse_expression())
else:
args.append(None)
if self.stream.current.type is 'colon':
self.stream.next()
if self.stream.current.type not in ('rbracket', 'comma'):
args.append(self.parse_expression())
else:
args.append(None)
else:
args.append(None)
return nodes.Slice(lineno=lineno, *args)
def parse_call(self, node):
token = self.stream.expect('lparen')
args = []
kwargs = []
dyn_args = dyn_kwargs = None
require_comma = False
def ensure(expr):
if not expr:
self.fail('invalid syntax for function call expression',
token.lineno)
while self.stream.current.type is not 'rparen':
if require_comma:
self.stream.expect('comma')
# support for trailing comma
if self.stream.current.type is 'rparen':
break
if self.stream.current.type is 'mul':
ensure(dyn_args is None and dyn_kwargs is None)
self.stream.next()
dyn_args = self.parse_expression()
elif self.stream.current.type is 'pow':
ensure(dyn_kwargs is None)
self.stream.next()
dyn_kwargs = self.parse_expression()
else:
ensure(dyn_args is None and dyn_kwargs is None)
if self.stream.current.type is 'name' and \
self.stream.look().type is 'assign':
key = self.stream.current.value
self.stream.skip(2)
value = self.parse_expression()
kwargs.append(nodes.Keyword(key, value,
lineno=value.lineno))
else:
ensure(not kwargs)
args.append(self.parse_expression())
require_comma = True
self.stream.expect('rparen')
if node is None:
return args, kwargs, dyn_args, dyn_kwargs
return nodes.Call(node, args, kwargs, dyn_args, dyn_kwargs,
lineno=token.lineno)
def parse_filter(self, node, start_inline=False):
while self.stream.current.type == 'pipe' or start_inline:
if not start_inline:
self.stream.next()
token = self.stream.expect('name')
name = token.value
while self.stream.current.type is 'dot':
self.stream.next()
name += '.' + self.stream.expect('name').value
if self.stream.current.type is 'lparen':
args, kwargs, dyn_args, dyn_kwargs = self.parse_call(None)
else:
args = []
kwargs = []
dyn_args = dyn_kwargs = None
node = nodes.Filter(node, name, args, kwargs, dyn_args,
dyn_kwargs, lineno=token.lineno)
start_inline = False
return node
def parse_test(self, node):
token = self.stream.next()
if self.stream.current.test('name:not'):
self.stream.next()
negated = True
else:
negated = False
name = self.stream.expect('name').value
while self.stream.current.type is 'dot':
self.stream.next()
name += '.' + self.stream.expect('name').value
dyn_args = dyn_kwargs = None
kwargs = []
if self.stream.current.type is 'lparen':
args, kwargs, dyn_args, dyn_kwargs = self.parse_call(None)
elif self.stream.current.type in ('name', 'string', 'integer',
'float', 'lparen', 'lbracket',
'lbrace') and not \
self.stream.current.test_any('name:else', 'name:or',
'name:and'):
if self.stream.current.test('name:is'):
self.fail('You cannot chain multiple tests with is')
args = [self.parse_expression()]
else:
args = []
node = nodes.Test(node, name, args, kwargs, dyn_args,
dyn_kwargs, lineno=token.lineno)
if negated:
node = nodes.Not(node, lineno=token.lineno)
return node
def subparse(self, end_tokens=None):
body = []
data_buffer = []
add_data = data_buffer.append
def flush_data():
if data_buffer:
lineno = data_buffer[0].lineno
body.append(nodes.Output(data_buffer[:], lineno=lineno))
del data_buffer[:]
while self.stream:
token = self.stream.current
if token.type is 'data':
if token.value:
add_data(nodes.TemplateData(token.value,
lineno=token.lineno))
self.stream.next()
elif token.type is 'variable_begin':
self.stream.next()
add_data(self.parse_tuple(with_condexpr=True))
self.stream.expect('variable_end')
elif token.type is 'block_begin':
flush_data()
self.stream.next()
if end_tokens is not None and \
self.stream.current.test_any(*end_tokens):
return body
rv = self.parse_statement()
if isinstance(rv, list):
body.extend(rv)
else:
body.append(rv)
self.stream.expect('block_end')
else:
raise AssertionError('internal parsing error')
flush_data()
return body
def parse(self):
"""Parse the whole template into a `Template` node."""
result = nodes.Template(self.subparse(), lineno=1)
result.set_environment(self.environment)
return result
./weblog+jinja-1.1/jinja2/runtime.py 0100644 0001750 0000000 00000036131 11063022145 0016325 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.runtime
~~~~~~~~~~~~~~
Runtime helpers.
:copyright: Copyright 2008 by Armin Ronacher.
:license: BSD.
"""
import sys
from types import FunctionType, MethodType
from itertools import chain, imap
from jinja2.utils import Markup, partial, soft_unicode, escape, missing, concat
from jinja2.exceptions import UndefinedError, TemplateRuntimeError
# these variables are exported to the template runtime
__all__ = ['LoopContext', 'Context', 'TemplateReference', 'Macro', 'Markup',
'TemplateRuntimeError', 'missing', 'concat', 'escape',
'markup_join', 'unicode_join']
_context_function_types = (FunctionType, MethodType)
def markup_join(seq):
"""Concatenation that escapes if necessary and converts to unicode."""
buf = []
iterator = imap(soft_unicode, seq)
for arg in iterator:
buf.append(arg)
if hasattr(arg, '__html__'):
return Markup(u'').join(chain(buf, iterator))
return concat(buf)
def unicode_join(seq):
"""Simple args to unicode conversion and concatenation."""
return concat(imap(unicode, seq))
class Context(object):
"""The template context holds the variables of a template. It stores the
values passed to the template and also the names the template exports.
Creating instances is neither supported nor useful as it's created
automatically at various stages of the template evaluation and should not
be created by hand.
The context is immutable. Modifications on :attr:`parent` **must not**
happen and modifications on :attr:`vars` are allowed from generated
template code only. Template filters and global functions marked as
:func:`contextfunction`\s get the active context passed as first argument
and are allowed to access the context read-only.
The template context supports read only dict operations (`get`,
`keys`, `values`, `items`, `iterkeys`, `itervalues`, `iteritems`,
`__getitem__`, `__contains__`). Additionally there is a :meth:`resolve`
method that doesn't fail with a `KeyError` but returns an
:class:`Undefined` object for missing variables.
"""
__slots__ = ('parent', 'vars', 'environment', 'exported_vars', 'name',
'blocks')
def __init__(self, environment, parent, name, blocks):
self.parent = parent
self.vars = vars = {}
self.environment = environment
self.exported_vars = set()
self.name = name
# create the initial mapping of blocks. Whenever template inheritance
# takes place the runtime will update this mapping with the new blocks
# from the template.
self.blocks = dict((k, [v]) for k, v in blocks.iteritems())
def super(self, name, current):
"""Render a parent block."""
try:
blocks = self.blocks[name]
block = blocks[blocks.index(current) + 1]
except LookupError:
return self.environment.undefined('there is no parent block '
'called %r.' % name,
name='super')
wrap = self.environment.autoescape and Markup or (lambda x: x)
render = lambda: wrap(concat(block(self)))
render.__name__ = render.name = name
return render
def get(self, key, default=None):
"""Returns an item from the template context, if it doesn't exist
`default` is returned.
"""
try:
return self[key]
except KeyError:
return default
def resolve(self, key):
"""Looks up a variable like `__getitem__` or `get` but returns an
:class:`Undefined` object with the name of the name looked up.
"""
if key in self.vars:
return self.vars[key]
if key in self.parent:
return self.parent[key]
return self.environment.undefined(name=key)
def get_exported(self):
"""Get a new dict with the exported variables."""
return dict((k, self.vars[k]) for k in self.exported_vars)
def get_all(self):
"""Return a copy of the complete context as dict including the
exported variables.
"""
return dict(self.parent, **self.vars)
def call(__self, __obj, *args, **kwargs):
"""Call the callable with the arguments and keyword arguments
provided but inject the active context or environment as first
argument if the callable is a :func:`contextfunction` or
:func:`environmentfunction`.
"""
if __debug__:
__traceback_hide__ = True
if isinstance(__obj, _context_function_types):
if getattr(__obj, 'contextfunction', 0):
args = (__self,) + args
elif getattr(__obj, 'environmentfunction', 0):
args = (__self.environment,) + args
return __obj(*args, **kwargs)
def _all(meth):
proxy = lambda self: getattr(self.get_all(), meth)()
proxy.__doc__ = getattr(dict, meth).__doc__
proxy.__name__ = meth
return proxy
keys = _all('keys')
values = _all('values')
items = _all('items')
iterkeys = _all('iterkeys')
itervalues = _all('itervalues')
iteritems = _all('iteritems')
del _all
def __contains__(self, name):
return name in self.vars or name in self.parent
def __getitem__(self, key):
"""Lookup a variable or raise `KeyError` if the variable is
undefined.
"""
item = self.resolve(key)
if isinstance(item, Undefined):
raise KeyError(key)
return item
def __repr__(self):
return '<%s %s of %r>' % (
self.__class__.__name__,
repr(self.get_all()),
self.name
)
# register the context as mutable mapping if possible
try:
from collections import MutableMapping
MutableMapping.register(Context)
except ImportError:
pass
class TemplateReference(object):
"""The `self` in templates."""
def __init__(self, context):
self.__context = context
def __getitem__(self, name):
func = self.__context.blocks[name][0]
wrap = self.__context.environment.autoescape and \
Markup or (lambda x: x)
render = lambda: wrap(concat(func(self.__context)))
render.__name__ = render.name = name
return render
def __repr__(self):
return '<%s %r>' % (
self.__class__.__name__,
self._context.name
)
class LoopContext(object):
"""A loop context for dynamic iteration."""
def __init__(self, iterable, recurse=None):
self._iterator = iter(iterable)
self._recurse = recurse
self.index0 = -1
# try to get the length of the iterable early. This must be done
# here because there are some broken iterators around where there
# __len__ is the number of iterations left (i'm looking at your
# listreverseiterator!).
try:
self._length = len(iterable)
except (TypeError, AttributeError):
self._length = None
def cycle(self, *args):
"""Cycles among the arguments with the current loop index."""
if not args:
raise TypeError('no items for cycling given')
return args[self.index0 % len(args)]
first = property(lambda x: x.index0 == 0)
last = property(lambda x: x.index0 + 1 == x.length)
index = property(lambda x: x.index0 + 1)
revindex = property(lambda x: x.length - x.index0)
revindex0 = property(lambda x: x.length - x.index)
def __len__(self):
return self.length
def __iter__(self):
return LoopContextIterator(self)
def loop(self, iterable):
if self._recurse is None:
raise TypeError('Tried to call non recursive loop. Maybe you '
"forgot the 'recursive' modifier.")
return self._recurse(iterable, self._recurse)
# a nifty trick to enhance the error message if someone tried to call
# the the loop without or with too many arguments.
__call__ = loop; del loop
@property
def length(self):
if self._length is None:
# if was not possible to get the length of the iterator when
# the loop context was created (ie: iterating over a generator)
# we have to convert the iterable into a sequence and use the
# length of that.
iterable = tuple(self._iterator)
self._iterator = iter(iterable)
self._length = len(iterable) + self.index0 + 1
return self._length
def __repr__(self):
return '<%s %r/%r>' % (
self.__class__.__name__,
self.index,
self.length
)
class LoopContextIterator(object):
"""The iterator for a loop context."""
__slots__ = ('context',)
def __init__(self, context):
self.context = context
def __iter__(self):
return self
def next(self):
ctx = self.context
ctx.index0 += 1
return ctx._iterator.next(), ctx
class Macro(object):
"""Wraps a macro."""
def __init__(self, environment, func, name, arguments, defaults,
catch_kwargs, catch_varargs, caller):
self._environment = environment
self._func = func
self._argument_count = len(arguments)
self.name = name
self.arguments = arguments
self.defaults = defaults
self.catch_kwargs = catch_kwargs
self.catch_varargs = catch_varargs
self.caller = caller
def __call__(self, *args, **kwargs):
arguments = []
for idx, name in enumerate(self.arguments):
try:
value = args[idx]
except:
try:
value = kwargs.pop(name)
except:
try:
value = self.defaults[idx - self._argument_count]
except:
value = self._environment.undefined(
'parameter %r was not provided' % name, name=name)
arguments.append(value)
# it's important that the order of these arguments does not change
# if not also changed in the compiler's `function_scoping` method.
# the order is caller, keyword arguments, positional arguments!
if self.caller:
caller = kwargs.pop('caller', None)
if caller is None:
caller = self._environment.undefined('No caller defined',
name='caller')
arguments.append(caller)
if self.catch_kwargs:
arguments.append(kwargs)
elif kwargs:
raise TypeError('macro %r takes no keyword argument %r' %
(self.name, iter(kwargs).next()))
if self.catch_varargs:
arguments.append(args[self._argument_count:])
elif len(args) > self._argument_count:
raise TypeError('macro %r takes not more than %d argument(s)' %
(self.name, len(self.arguments)))
return self._func(*arguments)
def __repr__(self):
return '<%s %s>' % (
self.__class__.__name__,
self.name is None and 'anonymous' or repr(self.name)
)
class Undefined(object):
"""The default undefined type. This undefined type can be printed and
iterated over, but every other access will raise an :exc:`UndefinedError`:
>>> foo = Undefined(name='foo')
>>> str(foo)
''
>>> not foo
True
>>> foo + 42
Traceback (most recent call last):
...
UndefinedError: 'foo' is undefined
"""
__slots__ = ('_undefined_hint', '_undefined_obj', '_undefined_name',
'_undefined_exception')
def __init__(self, hint=None, obj=None, name=None, exc=UndefinedError):
self._undefined_hint = hint
self._undefined_obj = obj
self._undefined_name = name
self._undefined_exception = exc
def _fail_with_undefined_error(self, *args, **kwargs):
"""Regular callback function for undefined objects that raises an
`UndefinedError` on call.
"""
if self._undefined_hint is None:
if self._undefined_obj is None:
hint = '%r is undefined' % self._undefined_name
elif not isinstance(self._undefined_name, basestring):
hint = '%r object has no element %r' % (
self._undefined_obj.__class__.__name__,
self._undefined_name
)
else:
hint = '%r object has no attribute %r' % (
self._undefined_obj.__class__.__name__,
self._undefined_name
)
else:
hint = self._undefined_hint
raise self._undefined_exception(hint)
__add__ = __radd__ = __mul__ = __rmul__ = __div__ = __rdiv__ = \
__realdiv__ = __rrealdiv__ = __floordiv__ = __rfloordiv__ = \
__mod__ = __rmod__ = __pos__ = __neg__ = __call__ = \
__getattr__ = __getitem__ = __lt__ = __le__ = __gt__ = __ge__ = \
__int__ = __float__ = __complex__ = _fail_with_undefined_error
def __str__(self):
return self.__unicode__().encode('utf-8')
def __unicode__(self):
return u''
def __len__(self):
return 0
def __iter__(self):
if 0:
yield None
def __nonzero__(self):
return False
def __repr__(self):
return 'Undefined'
class DebugUndefined(Undefined):
"""An undefined that returns the debug info when printed.
>>> foo = DebugUndefined(name='foo')
>>> str(foo)
'{{ foo }}'
>>> not foo
True
>>> foo + 42
Traceback (most recent call last):
...
UndefinedError: 'foo' is undefined
"""
__slots__ = ()
def __unicode__(self):
if self._undefined_hint is None:
if self._undefined_obj is None:
return u'{{ %s }}' % self._undefined_name
return '{{ no such element: %s[%r] }}' % (
self._undefined_obj.__class__.__name__,
self._undefined_name
)
return u'{{ undefined value printed: %s }}' % self._undefined_hint
class StrictUndefined(Undefined):
"""An undefined that barks on print and iteration as well as boolean
tests and all kinds of comparisons. In other words: you can do nothing
with it except checking if it's defined using the `defined` test.
>>> foo = StrictUndefined(name='foo')
>>> str(foo)
Traceback (most recent call last):
...
UndefinedError: 'foo' is undefined
>>> not foo
Traceback (most recent call last):
...
UndefinedError: 'foo' is undefined
>>> foo + 42
Traceback (most recent call last):
...
UndefinedError: 'foo' is undefined
"""
__slots__ = ()
__iter__ = __unicode__ = __len__ = __nonzero__ = __eq__ = __ne__ = \
Undefined._fail_with_undefined_error
# remove remaining slots attributes, after the metaclass did the magic they
# are unneeded and irritating as they contain wrong data for the subclasses.
del Undefined.__slots__, DebugUndefined.__slots__, StrictUndefined.__slots__
./weblog+jinja-1.1/jinja2/sandbox.py 0100644 0001750 0000000 00000021342 11063022145 0016276 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.sandbox
~~~~~~~~~~~~~~
Adds a sandbox layer to Jinja as it was the default behavior in the old
Jinja 1 releases. This sandbox is slightly different from Jinja 1 as the
default behavior is easier to use.
The behavior can be changed by subclassing the environment.
:copyright: Copyright 2008 by Armin Ronacher.
:license: BSD.
"""
import operator
from types import FunctionType, MethodType, TracebackType, CodeType, \
FrameType, GeneratorType
from jinja2.runtime import Undefined
from jinja2.environment import Environment
from jinja2.exceptions import SecurityError
#: maximum number of items a range may produce
MAX_RANGE = 100000
#: attributes of function objects that are considered unsafe.
UNSAFE_FUNCTION_ATTRIBUTES = set(['func_closure', 'func_code', 'func_dict',
'func_defaults', 'func_globals'])
#: unsafe method attributes. function attributes are unsafe for methods too
UNSAFE_METHOD_ATTRIBUTES = set(['im_class', 'im_func', 'im_self'])
from collections import deque
from sets import Set, ImmutableSet
from UserDict import UserDict, DictMixin
from UserList import UserList
_mutable_set_types = (ImmutableSet, Set, set)
_mutable_mapping_types = (UserDict, DictMixin, dict)
_mutable_sequence_types = (UserList, list)
#: register Python 2.6 abstract base classes
try:
from collections import MutableSet, MutableMapping, MutableSequence
_mutable_set_types += (MutableSet,)
_mutable_mapping_types += (MutableMapping,)
_mutable_sequence_types += (MutableSequence,)
except ImportError:
pass
_mutable_spec = (
(_mutable_set_types, frozenset([
'add', 'clear', 'difference_update', 'discard', 'pop', 'remove',
'symmetric_difference_update', 'update'
])),
(_mutable_mapping_types, frozenset([
'clear', 'pop', 'popitem', 'setdefault', 'update'
])),
(_mutable_sequence_types, frozenset([
'append', 'reverse', 'insert', 'sort', 'extend', 'remove'
])),
(deque, frozenset([
'append', 'appendleft', 'clear', 'extend', 'extendleft', 'pop',
'popleft', 'remove', 'rotate'
]))
)
def safe_range(*args):
"""A range that can't generate ranges with a length of more than
MAX_RANGE items.
"""
rng = xrange(*args)
if len(rng) > MAX_RANGE:
raise OverflowError('range too big, maximum size for range is %d' %
MAX_RANGE)
return rng
def unsafe(f):
"""
Mark a function or method as unsafe::
@unsafe
def delete(self):
pass
"""
f.unsafe_callable = True
return f
def is_internal_attribute(obj, attr):
"""Test if the attribute given is an internal python attribute. For
example this function returns `True` for the `func_code` attribute of
python objects. This is useful if the environment method
:meth:`~SandboxedEnvironment.is_safe_attribute` is overriden.
>>> from jinja2.sandbox import is_internal_attribute
>>> is_internal_attribute(lambda: None, "func_code")
True
>>> is_internal_attribute((lambda x:x).func_code, 'co_code')
True
>>> is_internal_attribute(str, "upper")
False
"""
if isinstance(obj, FunctionType):
if attr in UNSAFE_FUNCTION_ATTRIBUTES:
return True
elif isinstance(obj, MethodType):
if attr in UNSAFE_FUNCTION_ATTRIBUTES or \
attr in UNSAFE_METHOD_ATTRIBUTES:
return True
elif isinstance(obj, type):
if attr == 'mro':
return True
elif isinstance(obj, (CodeType, TracebackType, FrameType)):
return True
elif isinstance(obj, GeneratorType):
if attr == 'gi_frame':
return True
return attr.startswith('__')
def modifies_known_mutable(obj, attr):
"""This function checks if an attribute on a builtin mutable object
(list, dict, set or deque) would modify it if called. It also supports
the "user"-versions of the objects (`sets.Set`, `UserDict.*` etc.) and
with Python 2.6 onwards the abstract base classes `MutableSet`,
`MutableMapping`, and `MutableSequence`.
>>> modifies_known_mutable({}, "clear")
True
>>> modifies_known_mutable({}, "keys")
False
>>> modifies_known_mutable([], "append")
True
>>> modifies_known_mutable([], "index")
False
If called with an unsupported object (such as unicode) `False` is
returned.
>>> modifies_known_mutable("foo", "upper")
False
"""
for typespec, unsafe in _mutable_spec:
if isinstance(obj, typespec):
return attr in unsafe
return False
class SandboxedEnvironment(Environment):
"""The sandboxed environment. It works like the regular environment but
tells the compiler to generate sandboxed code. Additionally subclasses of
this environment may override the methods that tell the runtime what
attributes or functions are safe to access.
If the template tries to access insecure code a :exc:`SecurityError` is
raised. However also other exceptions may occour during the rendering so
the caller has to ensure that all exceptions are catched.
"""
sandboxed = True
def __init__(self, *args, **kwargs):
Environment.__init__(self, *args, **kwargs)
self.globals['range'] = safe_range
def is_safe_attribute(self, obj, attr, value):
"""The sandboxed environment will call this method to check if the
attribute of an object is safe to access. Per default all attributes
starting with an underscore are considered private as well as the
special attributes of internal python objects as returned by the
:func:`is_internal_attribute` function.
"""
return not (attr.startswith('_') or is_internal_attribute(obj, attr))
def is_safe_callable(self, obj):
"""Check if an object is safely callable. Per default a function is
considered safe unless the `unsafe_callable` attribute exists and is
True. Override this method to alter the behavior, but this won't
affect the `unsafe` decorator from this module.
"""
return not (getattr(obj, 'unsafe_callable', False) or \
getattr(obj, 'alters_data', False))
def getitem(self, obj, argument):
"""Subscribe an object from sandboxed code."""
try:
return obj[argument]
except (TypeError, LookupError):
if isinstance(argument, basestring):
try:
attr = str(argument)
except:
pass
else:
try:
value = getattr(obj, attr)
except AttributeError:
pass
else:
if self.is_safe_attribute(obj, argument, value):
return value
return self.unsafe_undefined(obj, argument)
return self.undefined(obj=obj, name=argument)
def getattr(self, obj, attribute):
"""Subscribe an object from sandboxed code and prefer the
attribute. The attribute passed *must* be a bytestring.
"""
try:
value = getattr(obj, attribute)
except AttributeError:
try:
return obj[argument]
except (TypeError, LookupError):
pass
else:
if self.is_safe_attribute(obj, attribute, value):
return value
return self.unsafe_undefined(obj, attribute)
return self.undefined(obj=obj, name=argument)
def unsafe_undefined(self, obj, attribute):
"""Return an undefined object for unsafe attributes."""
return self.undefined('access to attribute %r of %r '
'object is unsafe.' % (
attribute,
obj.__class__.__name__
), name=attribute, obj=obj, exc=SecurityError)
def call(__self, __context, __obj, *args, **kwargs):
"""Call an object from sandboxed code."""
# the double prefixes are to avoid double keyword argument
# errors when proxying the call.
if not __self.is_safe_callable(__obj):
raise SecurityError('%r is not safely callable' % (__obj,))
return __context.call(__obj, *args, **kwargs)
class ImmutableSandboxedEnvironment(SandboxedEnvironment):
"""Works exactly like the regular `SandboxedEnvironment` but does not
permit modifications on the builtin mutable objects `list`, `set`, and
`dict` by using the :func:`modifies_known_mutable` function.
"""
def is_safe_attribute(self, obj, attr, value):
if not SandboxedEnvironment.is_safe_attribute(self, obj, attr, value):
return False
return not modifies_known_mutable(obj, attr)
./weblog+jinja-1.1/jinja2/tests.py 0100644 0001750 0000000 00000006103 11063022145 0016000 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.tests
~~~~~~~~~~~~
Jinja test functions. Used with the "is" operator.
:copyright: 2007 by Armin Ronacher.
:license: BSD, see LICENSE for more details.
"""
import re
from jinja2.runtime import Undefined
number_re = re.compile(r'^-?\d+(\.\d+)?$')
regex_type = type(number_re)
def test_odd(value):
"""Return true if the variable is odd."""
return value % 2 == 1
def test_even(value):
"""Return true if the variable is even."""
return value % 2 == 0
def test_divisibleby(value, num):
"""Check if a variable is divisible by a number."""
return value % num == 0
def test_defined(value):
"""Return true if the variable is defined:
.. sourcecode:: jinja
{% if variable is defined %}
value of variable: {{ variable }}
{% else %}
variable is not defined
{% endif %}
See the :func:`default` filter for a simple way to set undefined
variables.
"""
return not isinstance(value, Undefined)
def test_undefined(value):
"""Like :func:`defined` but the other way round."""
return isinstance(value, Undefined)
def test_none(value):
"""Return true if the variable is none."""
return value is None
def test_lower(value):
"""Return true if the variable is lowercased."""
return unicode(value).islower()
def test_upper(value):
"""Return true if the variable is uppercased."""
return unicode(value).isupper()
def test_string(value):
"""Return true if the object is a string."""
return isinstance(value, basestring)
def test_number(value):
"""Return true if the variable is a number."""
return isinstance(value, (int, long, float, complex))
def test_sequence(value):
"""Return true if the variable is a sequence. Sequences are variables
that are iterable.
"""
try:
len(value)
value.__getitem__
except:
return False
return True
def test_sameas(value, other):
"""Check if an object points to the same memory address than another
object:
.. sourcecode:: jinja
{% if foo.attribute is sameas false %}
the foo attribute really is the `False` singleton
{% endif %}
"""
return value is other
def test_iterable(value):
"""Check if it's possible to iterate over an object."""
try:
iter(value)
except TypeError:
return False
return True
def test_escaped(value):
"""Check if the value is escaped."""
return hasattr(value, '__html__')
TESTS = {
'odd': test_odd,
'even': test_even,
'divisibleby': test_divisibleby,
'defined': test_defined,
'undefined': test_undefined,
'none': test_none,
'lower': test_lower,
'upper': test_upper,
'string': test_string,
'number': test_number,
'sequence': test_sequence,
'iterable': test_iterable,
'callable': callable,
'sameas': test_sameas,
'escaped': test_escaped
}
./weblog+jinja-1.1/jinja2/utils.py 0100644 0001750 0000000 00000052537 11063022145 0016012 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2.utils
~~~~~~~~~~~~
Utility functions.
:copyright: 2008 by Armin Ronacher.
:license: BSD, see LICENSE for more details.
"""
import re
import sys
import string
try:
from thread import allocate_lock
except ImportError:
from dummy_thread import allocate_lock
from htmlentitydefs import name2codepoint
from collections import deque
from copy import deepcopy
from itertools import imap
_word_split_re = re.compile(r'(\s+)')
_punctuation_re = re.compile(
'^(?P<lead>(?:%s)*)(?P<middle>.*?)(?P<trail>(?:%s)*)$' % (
'|'.join(imap(re.escape, ('(', '<', '<'))),
'|'.join(imap(re.escape, ('.', ',', ')', '>', '\n', '>')))
)
)
_simple_email_re = re.compile(r'^\S+@[a-zA-Z0-9._-]+\.[a-zA-Z0-9._-]+$')
_striptags_re = re.compile(r'(<!--.*?-->|<[^>]*>)')
_entity_re = re.compile(r'&([^;]+);')
_entities = name2codepoint.copy()
_entities['apos'] = 39
# special singleton representing missing values for the runtime
missing = type('MissingType', (), {'__repr__': lambda x: 'missing'})()
# concatenate a list of strings and convert them to unicode.
# unfortunately there is a bug in python 2.4 and lower that causes
# unicode.join trash the traceback.
_concat = u''.join
try:
def _test_gen_bug():
raise TypeError(_test_gen_bug)
yield None
_concat(_test_gen_bug())
except TypeError, _error:
if not _error.args or _error.args[0] is not _test_gen_bug:
def concat(gen):
try:
return _concat(list(gen))
except:
# this hack is needed so that the current frame
# does not show up in the traceback.
exc_type, exc_value, tb = sys.exc_info()
raise exc_type, exc_value, tb.tb_next
else:
concat = _concat
del _test_gen_bug, _error
def contextfunction(f):
"""This decorator can be used to mark a function or method context callable.
A context callable is passed the active :class:`Context` as first argument when
called from the template. This is useful if a function wants to get access
to the context or functions provided on the context object. For example
a function that returns a sorted list of template variables the current
template exports could look like this::
@contextfunction
def get_exported_names(context):
return sorted(context.exported_vars)
"""
f.contextfunction = True
return f
def environmentfunction(f):
"""This decorator can be used to mark a function or method as environment
callable. This decorator works exactly like the :func:`contextfunction`
decorator just that the first argument is the active :class:`Environment`
and not context.
"""
f.environmentfunction = True
return f
def is_undefined(obj):
"""Check if the object passed is undefined. This does nothing more than
performing an instance check against :class:`Undefined` but looks nicer.
This can be used for custom filters or tests that want to react to
undefined variables. For example a custom default filter can look like
this::
def default(var, default=''):
if is_undefined(var):
return default
return var
"""
from jinja2.runtime import Undefined
return isinstance(obj, Undefined)
def clear_caches():
"""Jinja2 keeps internal caches for environments and lexers. These are
used so that Jinja2 doesn't have to recreate environments and lexers all
the time. Normally you don't have to care about that but if you are
messuring memory consumption you may want to clean the caches.
"""
from jinja2.environment import _spontaneous_environments
from jinja2.lexer import _lexer_cache
_spontaneous_environments.clear()
_lexer_cache.clear()
def import_string(import_name, silent=False):
"""Imports an object based on a string. This use useful if you want to
use import paths as endpoints or something similar. An import path can
be specified either in dotted notation (``xml.sax.saxutils.escape``)
or with a colon as object delimiter (``xml.sax.saxutils:escape``).
If the `silent` is True the return value will be `None` if the import
fails.
:return: imported object
"""
try:
if ':' in import_name:
module, obj = import_name.split(':', 1)
elif '.' in import_name:
items = import_name.split('.')
module = '.'.join(items[:-1])
obj = items[-1]
else:
return __import__(import_name)
return getattr(__import__(module, None, None, [obj]), obj)
except (ImportError, AttributeError):
if not silent:
raise
def pformat(obj, verbose=False):
"""Prettyprint an object. Either use the `pretty` library or the
builtin `pprint`.
"""
try:
from pretty import pretty
return pretty(obj, verbose=verbose)
except ImportError:
from pprint import pformat
return pformat(obj)
def urlize(text, trim_url_limit=None, nofollow=False):
"""Converts any URLs in text into clickable links. Works on http://,
https:// and www. links. Links can have trailing punctuation (periods,
commas, close-parens) and leading punctuation (opening parens) and
it'll still do the right thing.
If trim_url_limit is not None, the URLs in link text will be limited
to trim_url_limit characters.
If nofollow is True, the URLs in link text will get a rel="nofollow"
attribute.
"""
trim_url = lambda x, limit=trim_url_limit: limit is not None \
and (x[:limit] + (len(x) >=limit and '...'
or '')) or x
words = _word_split_re.split(text)
nofollow_attr = nofollow and ' rel="nofollow"' or ''
for i, word in enumerate(words):
match = _punctuation_re.match(word)
if match:
lead, middle, trail = match.groups()
if middle.startswith('www.') or (
'@' not in middle and
not middle.startswith('http://') and
len(middle) > 0 and
middle[0] in string.letters + string.digits and (
middle.endswith('.org') or
middle.endswith('.net') or
middle.endswith('.com')
)):
middle = '<a href="http://%s"%s>%s</a>' % (middle,
nofollow_attr, trim_url(middle))
if middle.startswith('http://') or \
middle.startswith('https://'):
middle = '<a href="%s"%s>%s</a>' % (middle,
nofollow_attr, trim_url(middle))
if '@' in middle and not middle.startswith('www.') and \
not ':' in middle and _simple_email_re.match(middle):
middle = '<a href="mailto:%s">%s</a>' % (middle, middle)
if lead + middle + trail != word:
words[i] = lead + middle + trail
return u''.join(words)
def generate_lorem_ipsum(n=5, html=True, min=20, max=100):
"""Generate some lorem impsum for the template."""
from jinja2.constants import LOREM_IPSUM_WORDS
from random import choice, random, randrange
words = LOREM_IPSUM_WORDS.split()
result = []
for _ in xrange(n):
next_capitalized = True
last_comma = last_fullstop = 0
word = None
last = None
p = []
# each paragraph contains out of 20 to 100 words.
for idx, _ in enumerate(xrange(randrange(min, max))):
while True:
word = choice(words)
if word != last:
last = word
break
if next_capitalized:
word = word.capitalize()
next_capitalized = False
# add commas
if idx - randrange(3, 8) > last_comma:
last_comma = idx
last_fullstop += 2
word += ','
# add end of sentences
if idx - randrange(10, 20) > last_fullstop:
last_comma = last_fullstop = idx
word += '.'
next_capitalized = True
p.append(word)
# ensure that the paragraph ends with a dot.
p = u' '.join(p)
if p.endswith(','):
p = p[:-1] + '.'
elif not p.endswith('.'):
p += '.'
result.append(p)
if not html:
return u'\n\n'.join(result)
return Markup(u'\n'.join(u'<p>%s</p>' % escape(x) for x in result))
class Markup(unicode):
r"""Marks a string as being safe for inclusion in HTML/XML output without
needing to be escaped. This implements the `__html__` interface a couple
of frameworks and web applications use. :class:`Markup` is a direct
subclass of `unicode` and provides all the methods of `unicode` just that
it escapes arguments passed and always returns `Markup`.
The `escape` function returns markup objects so that double escaping can't
happen. If you want to use autoescaping in Jinja just set the finalizer
of the environment to `escape`.
The constructor of the :class:`Markup` class can be used for three
different things: When passed an unicode object it's assumed to be safe,
when passed an object with an HTML representation (has an `__html__`
method) that representation is used, otherwise the object passed is
converted into a unicode string and then assumed to be safe:
>>> Markup("Hello <em>World</em>!")
Markup(u'Hello <em>World</em>!')
>>> class Foo(object):
... def __html__(self):
... return '<a href="#">foo</a>'
...
>>> Markup(Foo())
Markup(u'<a href="#">foo</a>')
If you want object passed being always treated as unsafe you can use the
:meth:`escape` classmethod to create a :class:`Markup` object:
>>> Markup.escape("Hello <em>World</em>!")
Markup(u'Hello <em>World</em>!')
Operations on a markup string are markup aware which means that all
arguments are passed through the :func:`escape` function:
>>> em = Markup("<em>%s</em>")
>>> em % "foo & bar"
Markup(u'<em>foo & bar</em>')
>>> strong = Markup("<strong>%(text)s</strong>")
>>> strong % {'text': '<blink>hacker here</blink>'}
Markup(u'<strong><blink>hacker here</blink></strong>')
>>> Markup("<em>Hello</em> ") + "<foo>"
Markup(u'<em>Hello</em> <foo>')
"""
__slots__ = ()
def __new__(cls, base=u'', encoding=None, errors='strict'):
if hasattr(base, '__html__'):
base = base.__html__()
if encoding is None:
return unicode.__new__(cls, base)
return unicode.__new__(cls, base, encoding, errors)
def __html__(self):
return self
def __add__(self, other):
if hasattr(other, '__html__') or isinstance(other, basestring):
return self.__class__(unicode(self) + unicode(escape(other)))
return NotImplemented
def __radd__(self, other):
if hasattr(other, '__html__') or isinstance(other, basestring):
return self.__class__(unicode(escape(other)) + unicode(self))
return NotImplemented
def __mul__(self, num):
if isinstance(num, (int, long)):
return self.__class__(unicode.__mul__(self, num))
return NotImplemented
__rmul__ = __mul__
def __mod__(self, arg):
if isinstance(arg, tuple):
arg = tuple(imap(_MarkupEscapeHelper, arg))
else:
arg = _MarkupEscapeHelper(arg)
return self.__class__(unicode.__mod__(self, arg))
def __repr__(self):
return '%s(%s)' % (
self.__class__.__name__,
unicode.__repr__(self)
)
def join(self, seq):
return self.__class__(unicode.join(self, imap(escape, seq)))
join.__doc__ = unicode.join.__doc__
def split(self, *args, **kwargs):
return map(self.__class__, unicode.split(self, *args, **kwargs))
split.__doc__ = unicode.split.__doc__
def rsplit(self, *args, **kwargs):
return map(self.__class__, unicode.rsplit(self, *args, **kwargs))
rsplit.__doc__ = unicode.rsplit.__doc__
def splitlines(self, *args, **kwargs):
return map(self.__class__, unicode.splitlines(self, *args, **kwargs))
splitlines.__doc__ = unicode.splitlines.__doc__
def unescape(self):
r"""Unescape markup again into an unicode string. This also resolves
known HTML4 and XHTML entities:
>>> Markup("Main » <em>About</em>").unescape()
u'Main \xbb <em>About</em>'
"""
def handle_match(m):
name = m.group(1)
if name in _entities:
return unichr(_entities[name])
try:
if name[:2] in ('#x', '#X'):
return unichr(int(name[2:], 16))
elif name.startswith('#'):
return unichr(int(name[1:]))
except ValueError:
pass
return u''
return _entity_re.sub(handle_match, unicode(self))
def striptags(self):
r"""Unescape markup into an unicode string and strip all tags. This
also resolves known HTML4 and XHTML entities. Whitespace is
normalized to one:
>>> Markup("Main » <em>About</em>").striptags()
u'Main \xbb About'
"""
stripped = u' '.join(_striptags_re.sub('', self).split())
return Markup(stripped).unescape()
@classmethod
def escape(cls, s):
"""Escape the string. Works like :func:`escape` with the difference
that for subclasses of :class:`Markup` this function would return the
correct subclass.
"""
rv = escape(s)
if rv.__class__ is not cls:
return cls(rv)
return rv
def make_wrapper(name):
orig = getattr(unicode, name)
def func(self, *args, **kwargs):
args = _escape_argspec(list(args), enumerate(args))
_escape_argspec(kwargs, kwargs.iteritems())
return self.__class__(orig(self, *args, **kwargs))
func.__name__ = orig.__name__
func.__doc__ = orig.__doc__
return func
for method in '__getitem__', '__getslice__', 'capitalize', \
'title', 'lower', 'upper', 'replace', 'ljust', \
'rjust', 'lstrip', 'rstrip', 'center', 'strip', \
'translate', 'expandtabs', 'swapcase', 'zfill':
locals()[method] = make_wrapper(method)
# new in python 2.5
if hasattr(unicode, 'partition'):
partition = make_wrapper('partition'),
rpartition = make_wrapper('rpartition')
# new in python 2.6
if hasattr(unicode, 'format'):
format = make_wrapper('format')
del method, make_wrapper
def _escape_argspec(obj, iterable):
"""Helper for various string-wrapped functions."""
for key, value in iterable:
if hasattr(value, '__html__') or isinstance(value, basestring):
obj[key] = escape(value)
return obj
class _MarkupEscapeHelper(object):
"""Helper for Markup.__mod__"""
def __init__(self, obj):
self.obj = obj
__getitem__ = lambda s, x: _MarkupEscapeHelper(s.obj[x])
__unicode__ = lambda s: unicode(escape(s.obj))
__str__ = lambda s: str(escape(s.obj))
__repr__ = lambda s: str(escape(repr(s.obj)))
__int__ = lambda s: int(s.obj)
__float__ = lambda s: float(s.obj)
class LRUCache(object):
"""A simple LRU Cache implementation."""
# this is fast for small capacities (something below 1000) but doesn't
# scale. But as long as it's only used as storage for templates this
# won't do any harm.
def __init__(self, capacity):
self.capacity = capacity
self._mapping = {}
self._queue = deque()
self._postinit()
def _postinit(self):
# alias all queue methods for faster lookup
self._popleft = self._queue.popleft
self._pop = self._queue.pop
if hasattr(self._queue, 'remove'):
self._remove = self._queue.remove
self._wlock = allocate_lock()
self._append = self._queue.append
def _remove(self, obj):
"""Python 2.4 compatibility."""
for idx, item in enumerate(self._queue):
if item == obj:
del self._queue[idx]
break
def __getstate__(self):
return {
'capacity': self.capacity,
'_mapping': self._mapping,
'_queue': self._queue
}
def __setstate__(self, d):
self.__dict__.update(d)
self._postinit()
def __getnewargs__(self):
return (self.capacity,)
def copy(self):
"""Return an shallow copy of the instance."""
rv = self.__class__(self.capacity)
rv._mapping.update(self._mapping)
rv._queue = deque(self._queue)
return rv
def get(self, key, default=None):
"""Return an item from the cache dict or `default`"""
try:
return self[key]
except KeyError:
return default
def setdefault(self, key, default=None):
"""Set `default` if the key is not in the cache otherwise
leave unchanged. Return the value of this key.
"""
try:
return self[key]
except KeyError:
self[key] = default
return default
def clear(self):
"""Clear the cache."""
self._wlock.acquire()
try:
self._mapping.clear()
self._queue.clear()
finally:
self._wlock.release()
def __contains__(self, key):
"""Check if a key exists in this cache."""
return key in self._mapping
def __len__(self):
"""Return the current size of the cache."""
return len(self._mapping)
def __repr__(self):
return '<%s %r>' % (
self.__class__.__name__,
self._mapping
)
def __getitem__(self, key):
"""Get an item from the cache. Moves the item up so that it has the
highest priority then.
Raise an `KeyError` if it does not exist.
"""
rv = self._mapping[key]
if self._queue[-1] != key:
self._remove(key)
self._append(key)
return rv
def __setitem__(self, key, value):
"""Sets the value for an item. Moves the item up so that it
has the highest priority then.
"""
self._wlock.acquire()
try:
if key in self._mapping:
self._remove(key)
elif len(self._mapping) == self.capacity:
del self._mapping[self._popleft()]
self._append(key)
self._mapping[key] = value
finally:
self._wlock.release()
def __delitem__(self, key):
"""Remove an item from the cache dict.
Raise an `KeyError` if it does not exist.
"""
self._wlock.acquire()
try:
del self._mapping[key]
self._remove(key)
finally:
self._wlock.release()
def items(self):
"""Return a list of items."""
result = [(key, self._mapping[key]) for key in list(self._queue)]
result.reverse()
return result
def iteritems(self):
"""Iterate over all items."""
return iter(self.items())
def values(self):
"""Return a list of all values."""
return [x[1] for x in self.items()]
def itervalue(self):
"""Iterate over all values."""
return iter(self.values())
def keys(self):
"""Return a list of all keys ordered by most recent usage."""
return list(self)
def iterkeys(self):
"""Iterate over all keys in the cache dict, ordered by
the most recent usage.
"""
return reversed(tuple(self._queue))
__iter__ = iterkeys
def __reversed__(self):
"""Iterate over the values in the cache dict, oldest items
coming first.
"""
return iter(tuple(self._queue))
__copy__ = copy
# register the LRU cache as mutable mapping if possible
try:
from collections import MutableMapping
MutableMapping.register(LRUCache)
except ImportError:
pass
# we have to import it down here as the speedups module imports the
# markup type which is define above.
try:
from jinja2._speedups import escape, soft_unicode
except ImportError:
def escape(s):
"""Convert the characters &, <, >, ' and " in string s to HTML-safe
sequences. Use this if you need to display text that might contain
such characters in HTML. Marks return value as markup string.
"""
if hasattr(s, '__html__'):
return s.__html__()
return Markup(unicode(s)
.replace('&', '&')
.replace('>', '>')
.replace('<', '<')
.replace("'", ''')
.replace('"', '"')
)
def soft_unicode(s):
"""Make a string unicode if it isn't already. That way a markup
string is not converted back to unicode.
"""
if not isinstance(s, unicode):
s = unicode(s)
return s
# partials
try:
from functools import partial
except ImportError:
class partial(object):
def __init__(self, _func, *args, **kwargs):
self._func = _func
self._args = args
self._kwargs = kwargs
def __call__(self, *args, **kwargs):
kwargs.update(self._kwargs)
return self._func(*(self._args + args), **kwargs)
./weblog+jinja-1.1/jinja2/__init__.py 0100644 0001750 0000000 00000003741 11063022145 0016402 0 ustar 00henry wheel # -*- coding: utf-8 -*-
"""
jinja2
~~~~~~
Jinja2 is a template engine written in pure Python. It provides a
Django inspired non-XML syntax but supports inline expressions and
an optional sandboxed environment.
Nutshell
--------
Here a small example of a Jinja2 template::
{% extends 'base.html' %}
{% block title %}Memberlist{% endblock %}
{% block content %}
<ul>
{% for user in users %}
<li><a href="{{ user.url }}">{{ user.username }}</a></li>
{% endfor %}
</ul>
{% endblock %}
:copyright: 2008 by Armin Ronacher, Christoph Hack.
:license: BSD, see LICENSE for more details.
"""
__docformat__ = 'restructuredtext en'
try:
__version__ = __import__('pkg_resources') \
.get_distribution('Jinja2').version
except:
__version__ = 'unknown'
# high level interface
from jinja2.environment import Environment, Template
# loaders
from jinja2.loaders import BaseLoader, FileSystemLoader, PackageLoader, \
DictLoader, FunctionLoader, PrefixLoader, ChoiceLoader
# undefined types
from jinja2.runtime import Undefined, DebugUndefined, StrictUndefined
# exceptions
from jinja2.exceptions import TemplateError, UndefinedError, \
TemplateNotFound, TemplateSyntaxError, TemplateAssertionError
# decorators and public utilities
from jinja2.filters import environmentfilter, contextfilter
from jinja2.utils import Markup, escape, clear_caches, \
environmentfunction, contextfunction, is_undefined
__all__ = [
'Environment', 'Template', 'BaseLoader', 'FileSystemLoader',
'PackageLoader', 'DictLoader', 'FunctionLoader', 'PrefixLoader',
'ChoiceLoader', 'Undefined', 'DebugUndefined', 'StrictUndefined',
'TemplateError', 'UndefinedError', 'TemplateNotFound',
'TemplateSyntaxError', 'TemplateAssertionError', 'environmentfilter',
'contextfilter', 'Markup', 'escape', 'environmentfunction',
'contextfunction', 'clear_caches', 'is_undefined'
]
./weblog+jinja-1.1/jinja2/LICENSE 0100644 0001750 0000000 00000003021 11063022145 0015265 0 ustar 00henry wheel Copyright (c) 2006-2008 by the respective authors (see AUTHORS file).
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.
* The names of the contributors may not 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.
./weblog+jinja-1.1/jinja2/AUTHORS 0100644 0001750 0000000 00000000433 11063022145 0015334 0 ustar 00henry wheel Jinja is written and maintained by Armin Ronacher <armin.ronacher@active-4.com>.
Other contributors (as mentionend in :copyright:s) are:
- Armin Ronacher <armin.ronacher@active-4.com>
- Georg Brandl
- Lawrence Journal-World.
- Bryan McLemore
- Mickaël Guérin <kael@crocobox.org>
./weblog+jinja-1.1/weblog_run.py 0100755 0001750 0000000 00000000375 11063022145 0015634 0 ustar 00henry wheel #!/usr/bin/env python
import imp
from os import path
filename = path.join(path.dirname(__file__), 'bin', 'weblog')
module = imp.load_module('weblog_executable', file(filename), filename,
('', 'r', imp.PY_SOURCE))
module.main()
Then edit ``weblog.ini`` and add the following lines::
html_header = html/header.html
extra_files = my_fancy_logo.png
This insert the content of the file ``html/header.html`` before the blog's
title, and copy the file ``my_fancy_logo.png``.
CSS resources
-------------
Learning and developing with CSS is hard. The CSS syntax tend to be confusing
for beginners. The numerous browser incompatibilities makes the designer's work
even more complicated. Here is a list of useful resources regarding this
subject:
* SitePoint_ CSS Reference is helpful if you are a beginner with CSS. It lists
all CSS properties and document how well they are supported by the different
browsers.
* HtmlHelp_ contains a complete HTML 4 reference.
.. _HtmlHelp: http://htmlhelp.com/reference/html40/
.. _SitePoint: http://reference.sitepoint.com/css
.. vim:se tw=80 sw=2 ts=2 et encoding=utf-8:
./weblog+jinja-1.1/doc/weblog.rst 0100644 0001750 0000000 00000026315 11063022145 0015674 0 ustar 00henry wheel Weblog manual
=============
:Author: Henry Prêcheur 
a file
It will copy ``picture.png`` and ``directory/file``. If ``directory`` does not exist,
it will be created.
How URI's are handled
---------------------
Relative links (````) are rewritten in the RSS file and in
some HTML files. In the RSS file ``base_url`` is prepended to the link to make
sure it always points to the correct URI.
Absolute links (````) are not rewritten. It should
always point to the correct location regardless of the context.
Note that Weblog considers ``/`` as the root directory. If ``base_url`` is
``http://example.com/``; ``test.html`` and ``/test.html`` are both rewritten to
``http://example.com/test.html``.
Command line parameters
-----------------------
Usage: weblog [options]
Options:
-h, --help show this help message and exit
-s DIR, --source-dir=DIR
The source directory where the blog posts and the file
weblog.ini are located
-o DIR, --output-dir=DIR
The directory where all the generated files are
written. If it does not exist it is created.
-q, --quiet Do not output anything except critical error messages
Configuration file
------------------
All configuration options are in the ``weblog`` section. Learn more about the
format of the configuration file:
http://docs.python.org/lib/module-ConfigParser.html.
A sample configuration file::
[weblog]
title: Blog's title
url: http://example.com/
description: A sample blog.
source_dir: path/to/my/posts
output_dir: path/to/output/directory
encoding: latin-1
author: Me 
some random text.
... bar
... »~
...
...
... More ..........""")
>>> print p.get_value() #doctest: +NORMALIZE_WHITESPACE
foo
"
'''
if attrs:
if tag == u'a':
attrs = self.make_full_url(u'href', attrs)
elif tag == u'img':
attrs = self.make_full_url(u'src', attrs)
elif tag == u'object':
attrs = self.make_full_url(u'data', attrs)
attrs = self.make_full_url(u'codebase', attrs)
elif tag == u'script':
attrs = self.make_full_url(u'src', attrs)
return u'<%s %s%s>' % (tag,
self.html_attrs(attrs),
endtag)
else:
return u'<%s%s>' % (tag, endtag)
def handle_starttag(self, tag, attrs):
self.output.append(self.rewrite_tag(tag, attrs))
def handle_startendtag(self, tag, attrs):
self.output.append(self.rewrite_tag(tag, attrs, endtag=u'/'))
def html_full_url(base_url, text):
'''
Appends ``base_url`` to relative uri's in the HTML
document ``text``.
Example with ``base_url=http://example.com``::
'' becomes ''
'
' becomes '
'
but
' is not changed since it is an
*absolute* URI.
>>> html_full_url('http://example.com', '')
u""
>>> html_full_url('http://example.com', '
')
u"
"
'''
p = FullUrlHtmlParser(base_url)
p.feed(text)
return p.get_value()
if __name__ == '__main__':
import doctest
doctest.testmod()
./weblog+jinja-1.1/weblog/__init__.py 0100644 0001750 0000000 00000001530 11063022145 0016476 0 ustar 00henry wheel from load import load_configuration, load_post_list
from post import Post, PostError
from _jinja_environment import jinja_environment
from html_full_url import html_full_url
from publish import command_publish
from date import command_date
import listing
__author__ = 'Henry Precheur