diff options
Diffstat (limited to 'lib/utils')
| -rw-r--r-- | lib/utils/APIClients.py | 104 | ||||
| -rw-r--r-- | lib/utils/__init__.py | 0 | ||||
| -rwxr-xr-x | lib/utils/markdown2.py | 1877 | ||||
| -rw-r--r-- | lib/utils/pydelicious.py | 1045 | ||||
| -rw-r--r-- | lib/utils/strutils.py | 50 |
5 files changed, 3076 insertions, 0 deletions
diff --git a/lib/utils/APIClients.py b/lib/utils/APIClients.py new file mode 100644 index 0000000..24ab97b --- /dev/null +++ b/lib/utils/APIClients.py @@ -0,0 +1,104 @@ +# APIClients for grabbing data from popular web services +# By Scott Gilbertson +# Copyright is lame, take what you want, except for those portions noted + +# Dependencies: +import sys, urllib +import xml.etree.cElementTree as xml_parser + + +DEBUG = 0 + +""" +base class -- handles GoodReads.com, but works for any rss feed, just send an empty string for anything you don't need +""" +class APIClient: + def __init__(self, base_path, api_key): + self.api_key = api_key + self.base_path = base_path + + def __getattr__(self, method): + def method(_self=self, _method=method, **params): + url = "%s%s?%s&" % (self.base_path, self.api_key, urllib.urlencode(params)) + if DEBUG: print url + data = self.fetch(url) + return data + + return method + + def fetch(self, url): + u = urllib.FancyURLopener(None) + usock = u.open(url) + rawdata = usock.read() + if DEBUG: print rawdata + usock.close() + return xml_parser.fromstring(rawdata) + +""" + Extend APIClient to work with the ma.gnolia.com API + (http://wiki.ma.gnolia.com/Ma.gnolia_API) + Adds some error handling as well +""" +class MagnoliaError(Exception): + def __init__(self, code, message): + self.code = code + self.message = message + + def __str__(self): + return 'Magnolia Error %s: %s' % (self.code, self.message) + + +class MagnoliaClient(APIClient): + def __getattr__(self, method): + def method(_self=self, _method=method, **params): + url = "%s%s?%s&api_key=%s" % (self.base_path, _method, urllib.urlencode(params), self.api_key) + if DEBUG: print url + data = APIClient.fetch(self, url) + return data + return method + + +""" + Extend APIClient to work with the Flickr API + (http://www.flickr.com/services/api/) + Adds error handling as well +""" + +class FlickrError(Exception): + def __init__(self, code, message): + self.code = code + self.message = message + + def __str__(self): + return 'Flickr Error %s: %s' % (self.code, self.message) + +class FlickrClient(APIClient): + def __getattr__(self, method): + def method(_self=self, _method=method, **params): + _method = _method.replace("_", ".") + url = "%s?method=%s&%s&api_key=%s" % (self.base_path, _method, urllib.urlencode(params), self.api_key) + if DEBUG: print url + data = APIClient.fetch(self, url) + return data + return method + +class TumblrClient: + def __init__(self, base_path): + self.base_path = base_path + + def __getattr__(self, method): + def method(_self=self, _method=method, **params): + url = "%s" % (self.base_path) + if DEBUG: print url + data = self.fetch(url) + return data + + return method + + def fetch(self, url): + u = urllib.FancyURLopener(None) + usock = u.open(url) + rawdata = usock.read() + if DEBUG: print rawdata + usock.close() + return xml_parser.fromstring(rawdata) diff --git a/lib/utils/__init__.py b/lib/utils/__init__.py new file mode 100644 index 0000000..e69de29 --- /dev/null +++ b/lib/utils/__init__.py diff --git a/lib/utils/markdown2.py b/lib/utils/markdown2.py new file mode 100755 index 0000000..d72f414 --- /dev/null +++ b/lib/utils/markdown2.py @@ -0,0 +1,1877 @@ +#!/usr/bin/env python +# Copyright (c) 2007-2008 ActiveState Corp. +# License: MIT (http://www.opensource.org/licenses/mit-license.php) + +r"""A fast and complete Python implementation of Markdown. + +[from http://daringfireball.net/projects/markdown/] +> Markdown is a text-to-HTML filter; it translates an easy-to-read / +> easy-to-write structured text format into HTML. Markdown's text +> format is most similar to that of plain text email, and supports +> features such as headers, *emphasis*, code blocks, blockquotes, and +> links. +> +> Markdown's syntax is designed not as a generic markup language, but +> specifically to serve as a front-end to (X)HTML. You can use span-level +> HTML tags anywhere in a Markdown document, and you can use block level +> HTML tags (like <div> and <table> as well). + +Module usage: + + >>> import markdown2 + >>> markdown2.markdown("*boo!*") # or use `html = markdown_path(PATH)` + u'<p><em>boo!</em></p>\n' + + >>> markdowner = Markdown() + >>> markdowner.convert("*boo!*") + u'<p><em>boo!</em></p>\n' + >>> markdowner.convert("**boom!**") + u'<p><strong>boom!</strong></p>\n' + +This implementation of Markdown implements the full "core" syntax plus a +number of extras (e.g., code syntax coloring, footnotes) as described on +<http://code.google.com/p/python-markdown2/wiki/Extras>. +""" + +cmdln_desc = """A fast and complete Python implementation of Markdown, a +text-to-HTML conversion tool for web writers. +""" + +# Dev Notes: +# - There is already a Python markdown processor +# (http://www.freewisdom.org/projects/python-markdown/). +# - Python's regex syntax doesn't have '\z', so I'm using '\Z'. I'm +# not yet sure if there implications with this. Compare 'pydoc sre' +# and 'perldoc perlre'. + +__version_info__ = (1, 0, 1, 13) # first three nums match Markdown.pl +__version__ = '1.0.1.13' +__author__ = "Trent Mick" + +import os +import sys +from pprint import pprint +import re +import logging +try: + from hashlib import md5 +except ImportError: + from md5 import md5 +import optparse +from random import random +import codecs + + + +#---- Python version compat + +if sys.version_info[:2] < (2,4): + from sets import Set as set + def reversed(sequence): + for i in sequence[::-1]: + yield i + def _unicode_decode(s, encoding, errors='xmlcharrefreplace'): + return unicode(s, encoding, errors) +else: + def _unicode_decode(s, encoding, errors='strict'): + return s.decode(encoding, errors) + + +#---- globals + +DEBUG = False +log = logging.getLogger("markdown") + +DEFAULT_TAB_WIDTH = 4 + +# Table of hash values for escaped characters: +def _escape_hash(s): + # Lame attempt to avoid possible collision with someone actually + # using the MD5 hexdigest of one of these chars in there text. + # Other ideas: random.random(), uuid.uuid() + #return md5(s).hexdigest() # Markdown.pl effectively does this. + return 'md5-'+md5(s).hexdigest() +g_escape_table = dict([(ch, _escape_hash(ch)) + for ch in '\\`*_{}[]()>#+-.!']) + + + +#---- exceptions + +class MarkdownError(Exception): + pass + + + +#---- public api + +def markdown_path(path, encoding="utf-8", + html4tags=False, tab_width=DEFAULT_TAB_WIDTH, + safe_mode=None, extras=None, link_patterns=None, + use_file_vars=False): + text = codecs.open(path, 'r', encoding).read() + return Markdown(html4tags=html4tags, tab_width=tab_width, + safe_mode=safe_mode, extras=extras, + link_patterns=link_patterns, + use_file_vars=use_file_vars).convert(text) + +def markdown(text, html4tags=False, tab_width=DEFAULT_TAB_WIDTH, + safe_mode=None, extras=None, link_patterns=None, + use_file_vars=False): + return Markdown(html4tags=html4tags, tab_width=tab_width, + safe_mode=safe_mode, extras=extras, + link_patterns=link_patterns, + use_file_vars=use_file_vars).convert(text) + +class Markdown(object): + # The dict of "extras" to enable in processing -- a mapping of + # extra name to argument for the extra. Most extras do not have an + # argument, in which case the value is None. + # + # This can be set via (a) subclassing and (b) the constructor + # "extras" argument. + extras = None + + urls = None + titles = None + html_blocks = None + html_spans = None + html_removed_text = "[HTML_REMOVED]" # for compat with markdown.py + + # Used to track when we're inside an ordered or unordered list + # (see _ProcessListItems() for details): + list_level = 0 + + _ws_only_line_re = re.compile(r"^[ \t]+$", re.M) + + def __init__(self, html4tags=False, tab_width=4, safe_mode=None, + extras=None, link_patterns=None, use_file_vars=False): + if html4tags: + self.empty_element_suffix = ">" + else: + self.empty_element_suffix = " />" + self.tab_width = tab_width + + # For compatibility with earlier markdown2.py and with + # markdown.py's safe_mode being a boolean, + # safe_mode == True -> "replace" + if safe_mode is True: + self.safe_mode = "replace" + else: + self.safe_mode = safe_mode + + if self.extras is None: + self.extras = {} + elif not isinstance(self.extras, dict): + self.extras = dict([(e, None) for e in self.extras]) + if extras: + if not isinstance(extras, dict): + extras = dict([(e, None) for e in extras]) + self.extras.update(extras) + assert isinstance(self.extras, dict) + self._instance_extras = self.extras.copy() + self.link_patterns = link_patterns + self.use_file_vars = use_file_vars + self._outdent_re = re.compile(r'^(\t|[ ]{1,%d})' % tab_width, re.M) + + def reset(self): + self.urls = {} + self.titles = {} + self.html_blocks = {} + self.html_spans = {} + self.list_level = 0 + self.extras = self._instance_extras.copy() + if "footnotes" in self.extras: + self.footnotes = {} + self.footnote_ids = [] + + def convert(self, text): + """Convert the given text.""" + # Main function. The order in which other subs are called here is + # essential. Link and image substitutions need to happen before + # _EscapeSpecialChars(), so that any *'s or _'s in the <a> + # and <img> tags get encoded. + + # Clear the global hashes. If we don't clear these, you get conflicts + # from other articles when generating a page which contains more than + # one article (e.g. an index page that shows the N most recent + # articles): + self.reset() + + if not isinstance(text, unicode): + #TODO: perhaps shouldn't presume UTF-8 for string input? + text = unicode(text, 'utf-8') + + if self.use_file_vars: + # Look for emacs-style file variable hints. + emacs_vars = self._get_emacs_vars(text) + if "markdown-extras" in emacs_vars: + splitter = re.compile("[ ,]+") + for e in splitter.split(emacs_vars["markdown-extras"]): + if '=' in e: + ename, earg = e.split('=', 1) + try: + earg = int(earg) + except ValueError: + pass + else: + ename, earg = e, None + self.extras[ename] = earg + + # Standardize line endings: + text = re.sub("\r\n|\r", "\n", text) + + # Make sure $text ends with a couple of newlines: + text += "\n\n" + + # Convert all tabs to spaces. + text = self._detab(text) + + # Strip any lines consisting only of spaces and tabs. + # This makes subsequent regexen easier to write, because we can + # match consecutive blank lines with /\n+/ instead of something + # contorted like /[ \t]*\n+/ . + text = self._ws_only_line_re.sub("", text) + + if self.safe_mode: + text = self._hash_html_spans(text) + + # Turn block-level HTML blocks into hash entries + text = self._hash_html_blocks(text, raw=True) + + # Strip link definitions, store in hashes. + if "footnotes" in self.extras: + # Must do footnotes first because an unlucky footnote defn + # looks like a link defn: + # [^4]: this "looks like a link defn" + text = self._strip_footnote_definitions(text) + text = self._strip_link_definitions(text) + + text = self._run_block_gamut(text) + + text = self._unescape_special_chars(text) + + if "footnotes" in self.extras: + text = self._add_footnotes(text) + + if self.safe_mode: + text = self._unhash_html_spans(text) + + text += "\n" + return text + + _emacs_oneliner_vars_pat = re.compile(r"-\*-\s*([^\r\n]*?)\s*-\*-", re.UNICODE) + # This regular expression is intended to match blocks like this: + # PREFIX Local Variables: SUFFIX + # PREFIX mode: Tcl SUFFIX + # PREFIX End: SUFFIX + # Some notes: + # - "[ \t]" is used instead of "\s" to specifically exclude newlines + # - "(\r\n|\n|\r)" is used instead of "$" because the sre engine does + # not like anything other than Unix-style line terminators. + _emacs_local_vars_pat = re.compile(r"""^ + (?P<prefix>(?:[^\r\n|\n|\r])*?) + [\ \t]*Local\ Variables:[\ \t]* + (?P<suffix>.*?)(?:\r\n|\n|\r) + (?P<content>.*?\1End:) + """, re.IGNORECASE | re.MULTILINE | re.DOTALL | re.VERBOSE) + + def _get_emacs_vars(self, text): + """Return a dictionary of emacs-style local variables. + + Parsing is done loosely according to this spec (and according to + some in-practice deviations from this): + http://www.gnu.org/software/emacs/manual/html_node/emacs/Specifying-File-Variables.html#Specifying-File-Variables + """ + emacs_vars = {} + SIZE = pow(2, 13) # 8kB + + # Search near the start for a '-*-'-style one-liner of variables. + head = text[:SIZE] + if "-*-" in head: + match = self._emacs_oneliner_vars_pat.search(head) + if match: + emacs_vars_str = match.group(1) + assert '\n' not in emacs_vars_str + emacs_var_strs = [s.strip() for s in emacs_vars_str.split(';') + if s.strip()] + if len(emacs_var_strs) == 1 and ':' not in emacs_var_strs[0]: + # While not in the spec, this form is allowed by emacs: + # -*- Tcl -*- + # where the implied "variable" is "mode". This form + # is only allowed if there are no other variables. + emacs_vars["mode"] = emacs_var_strs[0].strip() + else: + for emacs_var_str in emacs_var_strs: + try: + variable, value = emacs_var_str.strip().split(':', 1) + except ValueError: + log.debug("emacs variables error: malformed -*- " + "line: %r", emacs_var_str) + continue + # Lowercase the variable name because Emacs allows "Mode" + # or "mode" or "MoDe", etc. + emacs_vars[variable.lower()] = value.strip() + + tail = text[-SIZE:] + if "Local Variables" in tail: + match = self._emacs_local_vars_pat.search(tail) + if match: + prefix = match.group("prefix") + suffix = match.group("suffix") + lines = match.group("content").splitlines(0) + #print "prefix=%r, suffix=%r, content=%r, lines: %s"\ + # % (prefix, suffix, match.group("content"), lines) + + # Validate the Local Variables block: proper prefix and suffix + # usage. + for i, line in enumerate(lines): + if not line.startswith(prefix): + log.debug("emacs variables error: line '%s' " + "does not use proper prefix '%s'" + % (line, prefix)) + return {} + # Don't validate suffix on last line. Emacs doesn't care, + # neither should we. + if i != len(lines)-1 and not line.endswith(suffix): + log.debug("emacs variables error: line '%s' " + "does not use proper suffix '%s'" + % (line, suffix)) + return {} + + # Parse out one emacs var per line. + continued_for = None + for line in lines[:-1]: # no var on the last line ("PREFIX End:") + if prefix: line = line[len(prefix):] # strip prefix + if suffix: line = line[:-len(suffix)] # strip suffix + line = line.strip() + if continued_for: + variable = continued_for + if line.endswith('\\'): + line = line[:-1].rstrip() + else: + continued_for = None + emacs_vars[variable] += ' ' + line + else: + try: + variable, value = line.split(':', 1) + except ValueError: + log.debug("local variables error: missing colon " + "in local variables entry: '%s'" % line) + continue + # Do NOT lowercase the variable name, because Emacs only + # allows "mode" (and not "Mode", "MoDe", etc.) in this block. + value = value.strip() + if value.endswith('\\'): + value = value[:-1].rstrip() + continued_for = variable + else: + continued_for = None + emacs_vars[variable] = value + + # Unquote values. + for var, val in emacs_vars.items(): + if len(val) > 1 and (val.startswith('"') and val.endswith('"') + or val.startswith('"') and val.endswith('"')): + emacs_vars[var] = val[1:-1] + + return emacs_vars + + # Cribbed from a post by Bart Lateur: + # <http://www.nntp.perl.org/group/perl.macperl.anyperl/154> + _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 + </\2> # 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 + .*</\2> # 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) + + 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 <p>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.: + # <div> + # <div> + # tags for inner block must be indented. + # </div> + # </div> + # + # The outermost tags must start at the left margin for this to match, and + # the inner nested divs must be indented. + # We need to do this before the next, more liberal match, because the next + # match will start at the first `<div>` and stop at the first `</div>`. + text = self._strict_tag_block_re.sub(hash_html_block_sub, text) + + # Now match more liberally, simply from `\n<tag>` to `</tag>\n` + text = self._liberal_tag_block_re.sub(hash_html_block_sub, text) + + # Special case just for <hr />. It was easier to make a special + # case than to make the other regex more complicated. + if "<hr" in text: + _hr_tag_re = _hr_tag_re_from_tab_width(self.tab_width) + text = _hr_tag_re.sub(hash_html_block_sub, text) + + # Special case for standalone HTML comments: + if "<!--" in text: + start = 0 + while True: + # Delimiters for next comment block. + try: + start_idx = text.index("<!--", start) + except ValueError, ex: + break + try: + end_idx = text.index("-->", 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:] + + if "xml" in self.extras: + # Treat XML processing instructions and namespaced one-liner + # tags as if they were block HTML tags. E.g., if standalone + # (i.e. are their own paragraph), the following do not get + # wrapped in a <p> tag: + # <?foo bar?> + # + # <xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="chapter_1.md"/> + _xml_oneliner_re = _xml_oneliner_re_from_tab_width(self.tab_width) + text = _xml_oneliner_re.sub(hash_html_block_sub, text) + + 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<hr"+self.empty_element_suffix+"\n" + for hr_re in self._hr_res: + text = hr_re.sub(hr, text) + + text = self._do_lists(text) + + if "pyshell" in self.extras: + text = self._prepare_pyshell_blocks(text) + + text = self._do_code_blocks(text) + + text = self._do_block_quotes(text) + + # We already ran _HashHTMLBlocks() before, in Markdown(), but that + # was to escape raw HTML in the original Markdown source. This time, + # we're escaping the markup we've just created, so that we don't wrap + # <p> 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 `<http://example.com/>` + # Must come after _do_links(), because you can use < and > + # delimiters in inline links like [this](<url>). + 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", " <br%s\n" % self.empty_element_suffix, text) + + return text + + # "Sorta" because auto-links are identified as "tag" tokens. + _sorta_html_tokenize_re = re.compile(r""" + ( + # tag + </? + (?:\w+) # tag name + (?:\s+(?:[\w-]+:)?[\w-]+=(?:".*?"|'.*?'))* # attributes + \s*/?> + | + # auto-link (e.g., <http://www.activestate.com/>) + <\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") + \( # literal paren + [ \t]* + (?P<url> # \1 + <.*?> + | + .*? + ) + [ \t]* + ( # \2 + (['"]) # quote char = \3 + (?P<title>.*?) + \3 # matching quote + )? # title is optional + \) + ''', 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 = 3000 # markdown2 issue 24 + + # `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, **formatter_opts): + 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", **formatter_opts) + 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: + formatter_opts = self.extras['code-color'] or {} + colored = self._color_with_pygments(codeblock, lexer, + **formatter_opts) + 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) + _naked_gt_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) + + # Encode naked >'s + # Note: Other markdown implementations (e.g. Markdown.pl, PHP + # Markdown) don't do this. + text = self._naked_gt_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-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, repl in self.link_patterns: + replacements = [] + for match in regex.finditer(text): + if hasattr(repl, "__call__"): + href = repl(match) + else: + href = match.expand(repl) + replacements.append((match.span(), 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 _xml_oneliner_re_from_tab_width(tab_width): + """Standalone XML processing instruction regex.""" + return re.compile(r""" + (?: + (?<=\n\n) # Starting after a blank line + | # or + \A\n? # the beginning of the doc + ) + ( # save in $1 + [ ]{0,%d} + (?: + <\?\w+\b\s+.*?\?> # XML processing instruction + | + <\w+:\w+\b\s+.*?/> # namespaced single tag + ) + [ \t]* + (?=\n{2,}|\Z) # followed by a blank line or end of document + ) + """ % (tab_width - 1), re.X) +_xml_oneliner_re_from_tab_width = _memoized(_xml_oneliner_re_from_tab_width) + +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. + # Issue 26: '_' must be encoded. + if r > 0.9 and ch not in "@_": + 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=None): + if argv is None: + 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;" + "'xml' passes one-liner processing instructions and namespaced XML tags;" + "'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, exists + 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: + test_dir = join(dirname(dirname(abspath(__file__))), "test") + if exists(join(test_dir, "test_markdown2.py")): + sys.path.insert(0, test_dir) + from test_markdown2 import norm_html_from_html + norm_html = norm_html_from_html(html) + norm_perl_html = norm_html_from_html(perl_html) + else: + norm_html = html + norm_perl_html = perl_html + print "==== match? %r ====" % (norm_perl_html == norm_html) + + +if __name__ == "__main__": + sys.exit( main(sys.argv) ) + diff --git a/lib/utils/pydelicious.py b/lib/utils/pydelicious.py new file mode 100644 index 0000000..8e45843 --- /dev/null +++ b/lib/utils/pydelicious.py @@ -0,0 +1,1045 @@ +"""Library to access del.icio.us data via Python. + +An introduction to the project is given in the README. +pydelicious is released under the BSD license. See license.txt for details +and the copyright holders. + +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. + +TODO: + - distribute license, readme docs via setup.py? + - automatic release build? +""" +import sys +import os +import time +import datetime +import locale +import httplib +import urllib2 +from urllib import urlencode, quote_plus +from StringIO import StringIO +from pprint import pformat + +v = sys.version_info +if v[0] >= 2 and v[1] >= 5: + from hashlib import md5 +else: + from md5 import md5 + +try: + from elementtree.ElementTree import parse as parse_xml +except ImportError: + # Python 2.5 and higher + from xml.etree.ElementTree import parse as parse_xml + +try: + import feedparser +except ImportError: + print >>sys.stderr, \ + "Feedparser not available, no RSS parsing." + feedparser = None + + +### Static config + +__version__ = '0.5.3' +__author__ = 'Frank Timmermann <regenkind_at_gmx_dot_de>' + # GP: does not respond to emails +__contributors__ = [ + 'Greg Pinero', + 'Berend van Berkum <berend+pydelicious@dotmpe.com>'] +__url__ = 'http://code.google.com/p/pydelicious/' +# Old URL: 'http://deliciouspython.python-hosting.com/' +__author_email__ = "" +__docformat__ = "restructuredtext en" +__description__ = "pydelicious.py allows you to access the web service of " \ + "del.icio.us via it's API through Python." +__long_description__ = "The goal is to design an easy to use and fully " \ + "functional Python interface to del.icio.us." + +DLCS_OK_MESSAGES = ('done', 'ok') +"Known text values of positive del.icio.us <result/> answers" +DLCS_WAIT_TIME = 4 +"Time to wait between API requests" +DLCS_REQUEST_TIMEOUT = 444 +"Seconds before socket triggers timeout" +#DLCS_API_REALM = 'del.icio.us API' +DLCS_API_HOST = 'api.del.icio.us' +DLCS_API_PATH = 'v1' +DLCS_API = "https://%s/%s" % (DLCS_API_HOST, DLCS_API_PATH) +DLCS_RSS = 'http://del.icio.us/rss/' +DLCS_FEEDS = 'http://feeds.delicious.com/v2/' + +PREFERRED_ENCODING = locale.getpreferredencoding() +# XXX: might need to check sys.platform/encoding combinations here, ie +#if sys.platform == 'darwin' || PREFERRED_ENCODING == 'macroman: +# PREFERRED_ENCODING = 'utf-8' +if not PREFERRED_ENCODING: + PREFERRED_ENCODING = 'iso-8859-1' + +ISO_8601_DATETIME = '%Y-%m-%dT%H:%M:%SZ' + +USER_AGENT = 'pydelicious/%s %s' % (__version__, __url__) + +DEBUG = 0 +if 'DLCS_DEBUG' in os.environ: + DEBUG = int(os.environ['DLCS_DEBUG']) + if DEBUG: + print >>sys.stderr, \ + "Set DEBUG to %i from DLCS_DEBUG env." % DEBUG + +HTTP_PROXY = None +if 'HTTP_PROXY' in os.environ: + HTTP_PROXY = os.environ['HTTP_PROXY'] + if DEBUG: + print >>sys.stderr, \ + "Set HTTP_PROXY to %i from env." % HTTP_PROXY + +### Timeoutsocket hack taken from FeedParser.py + +# timeoutsocket allows feedparser to time out rather than hang forever on ultra- +# slow servers. Python 2.3 now has this functionality available in the standard +# socket library, so under 2.3 you don't need to install anything. But you +# probably should anyway, because the socket module is buggy and timeoutsocket +# is better. +try: + import timeoutsocket # http://www.timo-tasi.org/python/timeoutsocket.py + timeoutsocket.setDefaultSocketTimeout(DLCS_REQUEST_TIMEOUT) +except ImportError: + import socket + if hasattr(socket, 'setdefaulttimeout'): + socket.setdefaulttimeout(DLCS_REQUEST_TIMEOUT) +if DEBUG: print >>sys.stderr, \ + "Set socket timeout to %s seconds" % DLCS_REQUEST_TIMEOUT + + +### Utility classes + +class _Waiter: + """Waiter makes sure a certain amount of time passes between + successive calls of `Waiter()`. + + Some attributes: + :last: time of last call + :wait: the minimum time needed between calls + :waited: the number of calls throttled + + pydelicious.Waiter is an instance created when the module is loaded. + """ + def __init__(self, wait): + self.wait = wait + self.waited = 0 + self.lastcall = 0; + + def __call__(self): + tt = time.time() + wait = self.wait + + timeago = tt - self.lastcall + + if timeago < wait: + wait = wait - timeago + if DEBUG>0: print >>sys.stderr, "Waiting %s seconds." % wait + time.sleep(wait) + self.waited += 1 + self.lastcall = tt + wait + else: + self.lastcall = tt + +Waiter = _Waiter(DLCS_WAIT_TIME) + + +class PyDeliciousException(Exception): + """Standard pydelicious error""" +class PyDeliciousThrottled(Exception): pass +class PyDeliciousUnauthorized(Exception): pass + +class DeliciousError(Exception): + """Raised when the server responds with a negative answer""" + + @staticmethod + def raiseFor(error_string, path, **params): + if error_string == 'item already exists': + raise DeliciousItemExistsError, params['url'] + else: + raise DeliciousError, "%s, while calling <%s?%s>" % (error_string, + path, urlencode(params)) + +class DeliciousItemExistsError(DeliciousError): + """Raised then adding an already existing post.""" + + +class HTTPErrorHandler(urllib2.HTTPDefaultErrorHandler): + + def http_error_401(self, req, fp, code, msg, headers): + raise PyDeliciousUnauthorized, "Check credentials." + + def http_error_503(self, req, fp, code, msg, headers): + # Retry-After? + errmsg = "Try again later." + if 'Retry-After' in headers: + errmsg = "You may try again after %s" % headers['Retry-After'] + raise PyDeliciousThrottled, errmsg + + +### Utility functions + +def dict0(d): + "Removes empty string values from dictionary" + return dict([(k,v) for k,v in d.items() + if v=='' and isinstance(v, basestring)]) + + +def delicious_datetime(str): + """Parse a ISO 8601 formatted string to a Python datetime ... + """ + return datetime.datetime(*time.strptime(str, ISO_8601_DATETIME)[0:6]) + + +def http_request(url, user_agent=USER_AGENT, retry=4, opener=None): + """Retrieve the contents referenced by the URL using urllib2. + + Retries up to four times (default) on exceptions. + """ + request = urllib2.Request(url, headers={'User-Agent':user_agent}) + + if not opener: + opener = urllib2.build_opener() + + # Remember last error + e = None + + # Repeat request on time-out errors + tries = retry; + while tries: + try: + return opener.open(request) + + except urllib2.HTTPError, e: + # reraise unexpected protocol errors as PyDeliciousException + raise PyDeliciousException, "%s" % e + + except urllib2.URLError, e: + # xxx: Ugly check for time-out errors + #if len(e)>0 and 'timed out' in arg[0]: + print >> sys.stderr, "%s, %s tries left." % (e, tries) + Waiter() + tries = tries - 1 + #else: + # tries = None + + # Give up + raise PyDeliciousException, \ + "Unable to retrieve data at '%s', %s" % (url, e) + + +def build_api_opener(host, user, passwd, extra_handlers=() ): + """ + Build a urllib2 style opener with HTTP Basic authorization for one host + and additional error handling. If HTTP_PROXY is set a proxyhandler is also + added. + """ + + global DEBUG + + if DEBUG: httplib.HTTPConnection.debuglevel = 1 + + password_manager = urllib2.HTTPPasswordMgrWithDefaultRealm() + password_manager.add_password(None, host, user, passwd) + auth_handler = urllib2.HTTPBasicAuthHandler(password_manager) + + extra_handlers += ( HTTPErrorHandler(), ) + if HTTP_PROXY: + extra_handlers += ( urllib2.ProxyHandler( {'http': HTTP_PROXY} ), ) + + return urllib2.build_opener(auth_handler, *extra_handlers) + + +def dlcs_api_opener(user, passwd): + "Build an opener for DLCS_API_HOST, see build_api_opener()" + + return build_api_opener(DLCS_API_HOST, user, passwd) + + +def dlcs_api_request(path, params='', user='', passwd='', throttle=True, + opener=None): + """Retrieve/query a path within the del.icio.us API. + + This implements a minimum interval between calls to avoid + throttling. [#]_ Use param 'throttle' to turn this behaviour off. + + .. [#] http://del.icio.us/help/api/ + """ + if throttle: + Waiter() + + if params: + url = "%s/%s?%s" % (DLCS_API, path, urlencode(params)) + else: + url = "%s/%s" % (DLCS_API, path) + + if DEBUG: print >>sys.stderr, \ + "dlcs_api_request: %s" % url + + if not opener: + opener = dlcs_api_opener(user, passwd) + + fl = http_request(url, opener=opener) + + if DEBUG>2: print >>sys.stderr, \ + pformat(fl.info().headers) + + return fl + + +def dlcs_encode_params(params, usercodec=PREFERRED_ENCODING): + """Turn all param values (int, list, bool) into utf8 encoded strings. + """ + + if params: + for key in params.keys(): + if isinstance(params[key], bool): + if params[key]: + params[key] = 'yes' + else: + params[key] = 'no' + + elif isinstance(params[key], int): + params[key] = str(params[key]) + + elif not params[key]: + # strip/ignore empties other than False or 0 + del params[key] + continue + + elif isinstance(params[key], list): + params[key] = " ".join(params[key]) + + elif not isinstance(params[key], unicode): + params[key] = params[key].decode(usercodec) + + assert isinstance(params[key], basestring) + + params = dict([ (k, v.encode('utf8')) + for k, v in params.items() if v]) + + return params + + +def dlcs_parse_xml(data, split_tags=False): + """Parse any del.icio.us XML document and return Python data structure. + + Recognizes all XML document formats as returned by the version 1 API and + translates to a JSON-like data structure (dicts 'n lists). + + Returned instance is always a dictionary. Examples:: + + {'posts': [{'url':'...','hash':'...',},],} + {'tags':['tag1', 'tag2',]} + {'dates': [{'count':'...','date':'...'},], 'tag':'', 'user':'...'} + {'result':(True, "done")} + # etcetera. + """ + # TODO: split_tags is not implemented + + if DEBUG>3: print >>sys.stderr, "dlcs_parse_xml: parsing from ", data + + if not hasattr(data, 'read'): + data = StringIO(data) + + doc = parse_xml(data) + root = doc.getroot() + fmt = root.tag + + # Split up into three cases: Data, Result or Update + if fmt in ('tags', 'posts', 'dates', 'bundles'): + + # Data: expect a list of data elements, 'resources'. + # Use `fmt` (without last 's') to find data elements, elements + # don't have contents, attributes contain all the data we need: + # append to list + elist = [el.attrib for el in doc.findall(fmt[:-1])] + + # Return list in dict, use tagname of rootnode as keyname. + data = {fmt: elist} + + # Root element might have attributes too, append dict. + data.update(root.attrib) + + return data + + elif fmt == 'result': + + # Result: answer to operations + if root.attrib.has_key('code'): + msg = root.attrib['code'] + else: + msg = root.text + + # XXX: Return {'result':(True, msg)} for /known/ O.K. messages, + # use (False, msg) otherwise. Move this to DeliciousAPI? + v = msg in DLCS_OK_MESSAGES + return {fmt: (v, msg)} + + elif fmt == 'update': + + # Update: "time" + return {fmt: { + 'time':time.strptime(root.attrib['time'], ISO_8601_DATETIME) }} + + else: + raise PyDeliciousException, "Unknown XML document format '%s'" % fmt + + +def dlcs_rss_request(tag="", popular=0, user="", url=''): + """Parse a RSS request. + + This requests old (now undocumented?) URL paths that still seem to work. + """ + + tag = quote_plus(tag) + user = quote_plus(user) + + if url != '': + # http://del.icio.us/rss/url/efbfb246d886393d48065551434dab54 + url = DLCS_RSS + 'url/%s' % md5(url).hexdigest() + + elif user != '' and tag != '': + url = DLCS_RSS + '%(user)s/%(tag)s' % {'user':user, 'tag':tag} + + elif user != '' and tag == '': + # http://del.icio.us/rss/delpy + url = DLCS_RSS + '%s' % user + + elif popular == 0 and tag == '': + url = DLCS_RSS + + elif popular == 0 and tag != '': + # http://del.icio.us/rss/tag/apple + # http://del.icio.us/rss/tag/web2.0 + url = DLCS_RSS + "tag/%s" % tag + + elif popular == 1 and tag == '': + url = DLCS_RSS + 'popular/' + + elif popular == 1 and tag != '': + url = DLCS_RSS + 'popular/%s' % tag + + if DEBUG: + print 'dlcs_rss_request', url + + rss = http_request(url).read() + + # assert feedparser, "dlcs_rss_request requires feedparser to be installed." + if not feedparser: + return rss + + rss = feedparser.parse(rss) + + posts = [] + for e in rss.entries: + if e.has_key("links") and e["links"]!=[] and e["links"][0].has_key("href"): + url = e["links"][0]["href"] + elif e.has_key("link"): + url = e["link"] + elif e.has_key("id"): + url = e["id"] + else: + url = "" + if e.has_key("title"): + description = e['title'] + elif e.has_key("title_detail") and e["title_detail"].has_key("title"): + description = e["title_detail"]['value'] + else: + description = '' + try: tags = e['categories'][0][1] + except: + try: tags = e["category"] + except: tags = "" + if e.has_key("modified"): + dt = e['modified'] + else: + dt = "" + if e.has_key("summary"): + extended = e['summary'] + elif e.has_key("summary_detail"): + e['summary_detail']["value"] + else: + extended = "" + if e.has_key("author"): + user = e['author'] + else: + user = "" + # time = dt ist weist auf ein problem hin + # die benennung der variablen ist nicht einheitlich + # api senden und + # xml bekommen sind zwei verschiedene schuhe :( + posts.append({'url':url, 'description':description, 'tags':tags, + 'dt':dt, 'extended':extended, 'user':user}) + return posts + + +delicious_v2_feeds = { + #"Bookmarks from the hotlist" + '': "%(format)s", + #"Recent bookmarks" + 'recent': "%(format)s/recent", + #"Recent bookmarks by tag" + 'tagged': "%(format)s/tag/%(tags)s", + #"Popular bookmarks" + 'popular': "%(format)s/popular", + #"Popular bookmarks by tag" + 'popular_tagged': "%(format)s/popular/%(tag)s", + #"Recent site alerts (as seen in the top-of-page alert bar on the site)" + 'alerts': "%(format)s/alerts", + #"Bookmarks for a specific user" + 'user': "%(format)s/%(username)s", + #"Bookmarks for a specific user by tag(s)" + 'user_tagged': "%(format)s/%(username)s/%(tags)s", + #"Public summary information about a user (as seen in the network badge)" + 'user_info': "%(format)s/userinfo/%(username)s", + #"A list of all public tags for a user" + 'user_tags': "%(format)s/tags/%(username)s", + #"Bookmarks from a user's subscriptions" + 'user_subscription': "%(format)s/subscriptions/%(username)s", + #"Private feed for a user's inbox bookmarks from others" + 'user_inbox': "%(format)s/inbox/%(username)s?private=%(key)s", + #"Bookmarks from members of a user's network" + 'user_network': "%(format)s/network/%(username)s", + #"Bookmarks from members of a user's network by tag" + 'user_network_tagged': "%(format)s/network/%(username)s/%(tags)s", + #"A list of a user's network members" + 'user_network_member': "%(format)s/networkmembers/%(username)s", + #"A list of a user's network fans" + 'user_network_fan': "%(format)s/networkfans/%(username)s", + #"Recent bookmarks for a URL" + 'url': "%(format)s/url/%(urlmd5)s", + #"Summary information about a URL (as seen in the tagometer)" + 'urlinfo': "json/urlinfo/%(urlmd5)s", +} + +def dlcs_feed(name_or_url, url_map=delicious_v2_feeds, count=15, **params): + + """ + Request and parse a feed. See delicious_v2_feeds for available names and + required parameters. Format defaults to json. + """ + +# http://delicious.com/help/feeds +# TODO: plain or fancy + + format = params.setdefault('format', 'json') + if count == 'all': +# TODO: fetch all + print >>sys.stderr, "! Maxcount 100 " + count = 100 + + if name_or_url in url_map: + params['count'] = count + url = DLCS_FEEDS + url_map[name_or_url] % params + + else: + url = name_or_url + + if DEBUG: + print 'dlcs_feed', url + + feed = http_request(url).read() + + if format == 'rss': + if feedparser: + rss = feedparser.parse(feed) + return rss + + else: + return feed + + elif format == 'json': + return feed + + +### Main module class + +class DeliciousAPI: + + """A single-user Python facade to the del.icio.us HTTP API. + + See http://delicious.com/help/api. + + Methods ``request`` and ``request_raw`` represent the core. For all API + paths there are furthermore methods (e.g. posts_add for 'posts/all') with + an explicit declaration of parameters and documentation. + """ + + def __init__(self, user, passwd, codec=PREFERRED_ENCODING, + api_request=dlcs_api_request, xml_parser=dlcs_parse_xml, + build_opener=dlcs_api_opener, encode_params=dlcs_encode_params): + + """Initialize access to the API for ``user`` with ``passwd``. + + ``codec`` sets the encoding of the arguments, which defaults to the + users preferred locale. + + The ``api_request`` and ``xml_parser`` parameters by default point to + functions within this package with standard implementations which + request and parse a resource. See ``dlcs_api_request()`` and + ``dlcs_parse_xml()``. + + Parameter ``build_opener`` is a callable that, provided with the + credentials, should build a urllib2 opener for the delicious API server + with HTTP authentication. See ``dlcs_api_opener()`` for the default + implementation. + + ``encode_params`` finally preprocesses API parameters before + they are passed to ``api_request``. + """ + + assert user != "" + self.user = user + self.passwd = passwd + self.codec = codec + + # Implement communication to server and parsing of respons messages: + assert callable(encode_params) + self._encode_params = encode_params + assert callable(build_opener) + self._opener = build_opener(user, passwd) + assert callable(api_request) + self._api_request = api_request + assert callable(xml_parser) + self._parse_response = xml_parser + + ### Core functionality + + def request(self, path, _raw=False, **params): + """Sends a request message to `path` in the API, and parses the results + from XML. Use with ``_raw=True`` or ``call request_raw()`` directly + to get the filehandler and process the response message manually. + + Calls to some paths will return a `result` message, i.e.:: + + <result code="..." /> + + or:: + + <result>...</result> + + These should all be parsed to ``{'result':(Boolean, MessageString)}``, + this method raises a ``DeliciousError`` on negative `result` answers. + Positive answers are silently accepted and nothing is returned. + + Using ``_raw=True`` bypasses all parsing and never raises + ``DeliciousError``. + + See ``dlcs_parse_xml()`` and ``self.request_raw()``.""" + + if _raw: + # return answer + return self.request_raw(path, **params) + + else: + params = self._encode_params(params, self.codec) + + # get answer and parse + fl = self._api_request(path, params=params, opener=self._opener) + rs = self._parse_response(fl) + + if type(rs) == dict and 'result' in rs: + if not rs['result'][0]: + # Raise an error for negative 'result' answers + errmsg = "" + if len(rs['result'])>0: + errmsg = rs['result'][1] + DeliciousError.raiseFor(errmsg, path, **params) + + else: + # not out-of-the-oridinary result, OK + return + + return rs + + def request_raw(self, path, **params): + """Calls the path in the API, returns the filehandle. Returned file- + like instances have an ``HTTPMessage`` instance with HTTP header + information available. Use ``filehandle.info()`` or refer to the + ``urllib2.openurl`` documentation. + """ + # see `request()` on how the response can be handled + params = self._encode_params(params, self.codec) + return self._api_request(path, params=params, opener=self._opener) + + ### Explicit declarations of API paths, their parameters and docs + + # Tags + def tags_get(self, **kwds): + """Returns a list of tags and the number of times it is used by the + user. + :: + + <tags> + <tag tag="TagName" count="888"> + """ + return self.request("tags/get", **kwds) + + def tags_delete(self, tag, **kwds): + """Delete an existing tag. + + &tag={TAG} + (required) Tag to delete + """ + return self.request('tags/delete', tag=tag, **kwds) + + def tags_rename(self, old, new, **kwds): + """Rename an existing tag with a new tag name. Returns a `result` + message or raises an ``DeliciousError``. See ``self.request()``. + + &old={TAG} + (required) Tag to rename. + &new={TAG} + (required) New tag name. + """ + return self.request("tags/rename", old=old, new=new, **kwds) + + # Posts + def posts_update(self, **kwds): + """Returns the last update time for the user. Use this before calling + `posts_all` to see if the data has changed since the last fetch. + :: + + <update time="CCYY-MM-DDThh:mm:ssZ"> + """ + return self.request("posts/update", **kwds) + + def posts_dates(self, tag="", **kwds): + """Returns a list of dates with the number of posts at each date. + :: + + <dates> + <date date="CCYY-MM-DD" count="888"> + + &tag={TAG} + (optional) Filter by this tag + """ + return self.request("posts/dates", tag=tag, **kwds) + + def posts_get(self, tag="", dt="", url="", hashes=[], meta=True, **kwds): + """Returns posts matching the arguments. If no date or url is given, + most recent date will be used. + :: + + <posts dt="CCYY-MM-DD" tag="..." user="..."> + <post ...> + + &tag={TAG} {TAG} ... {TAG} + (optional) Filter by this/these tag(s). + &dt={CCYY-MM-DDThh:mm:ssZ} + (optional) Filter by this date, defaults to the most recent date on + which bookmarks were saved. + &url={URL} + (optional) Fetch a bookmark for this URL, regardless of date. + &hashes={MD5} {MD5} ... {MD5} + (optional) Fetch multiple bookmarks by one or more URL MD5s + regardless of date. + &meta=yes + (optional) Include change detection signatures on each item in a + 'meta' attribute. Clients wishing to maintain a synchronized local + store of bookmarks should retain the value of this attribute - its + value will change when any significant field of the bookmark + changes. + """ + return self.request("posts/get", tag=tag, dt=dt, url=url, + hashes=hashes, meta=meta, **kwds) + + def posts_recent(self, tag="", count="", **kwds): + """Returns a list of the most recent posts, filtered by argument. + :: + + <posts tag="..." user="..."> + <post ...> + + &tag={TAG} + (optional) Filter by this tag. + &count={1..100} + (optional) Number of items to retrieve (Default:15, Maximum:100). + """ + return self.request("posts/recent", tag=tag, count=count, **kwds) + + def posts_all(self, tag="", start=None, results=None, fromdt=None, + todt=None, meta=True, hashes=False, **kwds): + """Returns all posts. Please use sparingly. Call the `posts_update` + method to see if you need to fetch this at all. + :: + + <posts tag="..." user="..." update="CCYY-MM-DDThh:mm:ssZ"> + <post ...> + + &tag + (optional) Filter by this tag. + &start={#} + (optional) Start returning posts this many results into the set. + &results={#} + (optional) Return this many results. + &fromdt={CCYY-MM-DDThh:mm:ssZ} + (optional) Filter for posts on this date or later + &todt={CCYY-MM-DDThh:mm:ssZ} + (optional) Filter for posts on this date or earlier + &meta=yes + (optional) Include change detection signatures on each item in a + 'meta' attribute. Clients wishing to maintain a synchronized local + store of bookmarks should retain the value of this attribute - its + value will change when any significant field of the bookmark + changes. + &hashes + (optional, exclusive) Do not fetch post details but a posts + manifest with url- and meta-hashes. Other options do not apply. + """ + if hashes: + return self.request("posts/all", hashes=hashes, **kwds) + else: + return self.request("posts/all", tag=tag, fromdt=fromdt, todt=todt, + start=start, results=results, meta=meta, **kwds) + + def posts_add(self, url, description, extended="", tags="", dt="", + replace=False, shared=True, **kwds): + """Add a post to del.icio.us. Returns a `result` message or raises an + ``DeliciousError``. See ``self.request()``. + + &url (required) + the url of the item. + &description (required) + the description of the item. + &extended (optional) + notes for the item. + &tags (optional) + tags for the item (space delimited). + &dt (optional) + datestamp of the item (format "CCYY-MM-DDThh:mm:ssZ"). + Requires a LITERAL "T" and "Z" like in ISO8601 at + http://www.cl.cam.ac.uk/~mgk25/iso-time.html for example: + "1984-09-01T14:21:31Z" + &replace=no (optional) - don't replace post if given url has already + been posted. + &shared=yes (optional) - wether the item is public. + """ + return self.request("posts/add", url=url, description=description, + extended=extended, tags=tags, dt=dt, + replace=replace, shared=shared, **kwds) + + def posts_delete(self, url, **kwds): + """Delete a post from del.icio.us. Returns a `result` message or + raises an ``DeliciousError``. See ``self.request()``. + + &url (required) + the url of the item. + """ + return self.request("posts/delete", url=url, **kwds) + + # Bundles + def bundles_all(self, **kwds): + """Retrieve user bundles from del.icio.us. + :: + + <bundles> + <bundel name="..." tags=..."> + """ + return self.request("tags/bundles/all", **kwds) + + def bundles_set(self, bundle, tags, **kwds): + """Assign a set of tags to a single bundle, wipes away previous + settings for bundle. Returns a `result` messages or raises an + ``DeliciousError``. See ``self.request()``. + + &bundle (required) + the bundle name. + &tags (required) + list of tags. + """ + if type(tags)==list: + tags = " ".join(tags) + return self.request("tags/bundles/set", bundle=bundle, tags=tags, + **kwds) + + def bundles_delete(self, bundle, **kwds): + """Delete a bundle from del.icio.us. Returns a `result` message or + raises an ``DeliciousError``. See ``self.request()``. + + &bundle (required) + the bundle name. + """ + return self.request("tags/bundles/delete", bundle=bundle, **kwds) + + ### Utils + + # Lookup table for del.icio.us url-path to DeliciousAPI method. + paths = { + 'tags/get': 'tags_get', + 'tags/delete': 'tags_delete', + 'tags/rename': 'tags_rename', + 'posts/update': 'posts_update', + 'posts/dates': 'posts_dates', + 'posts/get': 'posts_get', + 'posts/recent': 'posts_recent', + 'posts/all': 'posts_all', + 'posts/add': 'posts_add', + 'posts/delete': 'posts_delete', + 'tags/bundles/all': 'bundles_all', + 'tags/bundles/set': 'bundles_set', + 'tags/bundles/delete': 'bundles_delete', + } + def get_method(self, path): + return getattr(self, self.paths[path]) + + def get_url(self, url): + """Return the del.icio.us url at which the HTML page with posts for + ``url`` can be found. + """ + return "http://del.icio.us/url/?url=%s" % (url,) + + def __repr__(self): + return "DeliciousAPI(%s)" % self.user + + +### Convenience functions on this package + +def apiNew(user, passwd): + "Creates a new DeliciousAPI object, requires user(name) and passwd." + return DeliciousAPI(user=user, passwd=passwd) + +def add(user, passwd, url, description, tags="", extended="", dt=None, + replace=False): + apiNew(user, passwd).posts_add(url=url, description=description, + extended=extended, tags=tags, dt=dt, replace=replace) + +def get(user, passwd, tag="", dt=None, count=0, hashes=[]): + "Returns a list of posts for the user" + posts = apiNew(user, passwd).posts_get( + tag=tag, dt=dt, hashes=hashes)['posts'] + if count: posts = posts[:count] + return posts + +def get_update(user, passwd): + "Returns the last update time for the user." + return apiNew(user, passwd).posts_update()['update']['time'] + +def get_all(user, passwd, tag="", start=0, results=100, fromdt=None, + todt=None): + "Returns a list with all posts. Please use sparingly. See `get_updated`" + return apiNew(user, passwd).posts_all(tag=tag, start=start, + results=results, fromdt=fromdt, todt=todt, meta=True)['posts'] + +def get_tags(user, passwd): + "Returns a list with all tags for user." + return apiNew(user=user, passwd=passwd).tags_get()['tags'] + +def delete(user, passwd, url): + "Delete the URL from the del.icio.us account." + apiNew(user, passwd).posts_delete(url=url) + +def rename_tag(user, passwd, oldtag, newtag): + "Rename the tag for the del.icio.us account." + apiNew(user=user, passwd=passwd).tags_rename(old=oldtag, new=newtag) + + +### RSS functions + +def getrss(tag="", popular=0, url='', user=""): + """Get posts from del.icio.us via parsing RSS. + + tag (opt) sort by tag + popular (opt) look for the popular stuff + user (opt) get the posts by a user, this striks popular + url (opt) get the posts by url + """ + return dlcs_rss_request(tag=tag, popular=popular, user=user, url=url) + +def get_userposts(user): + "parse RSS for user" + return getrss(user=user) + +def get_tagposts(tag): + "parse RSS for tag" + return getrss(tag=tag) + +def get_urlposts(url): + "parse RSS for URL" + return getrss(url=url) + +def get_popular(tag=""): + "parse RSS for popular URLS for tag" + return getrss(tag=tag, popular=1) + + +### JSON feeds +# TODO: untested + +def json_posts(user, count=15, tag=None, raw=True): + """ + user + count=### the number of posts you want to get (default is 15, maximum + is 100) + raw a raw JSON object is returned, instead of an object named + Delicious.posts + """ + url = "http://del.icio.us/feeds/json/" + \ + dlcs_encode_params({0:user})[0] + if tag: url += '/'+dlcs_encode_params({0:tag})[0] + + return dlcs_feed(url, count=count, raw=raw) + + +def json_tags(user, atleast, count, sort='alpha', raw=True, callback=None): + """ + user + atleast=### include only tags for which there are at least ### + number of posts. + count=### include ### tags, counting down from the top. + sort={alpha|count} construct the object with tags in alphabetic order + (alpha), or by count of posts (count). + callback=NAME wrap the object definition in a function call NAME(...), + thus invoking that function when the feed is executed. + raw a pure JSON object is returned, instead of code that + will construct an object named Delicious.tags. + """ + url = 'http://del.icio.us/feeds/json/tags/' + \ + dlcs_encode_params({0:user})[0] + return dlcs_feed(url, atleast=atleast, count=count, sort=sort, raw=raw, + callback=callback) + + +def json_network(user, raw=True, callback=None): + """ + callback=NAME wrap the object definition in a function call NAME(...) + ?raw a raw JSON object is returned, instead of an object named + Delicious.posts + """ + url = 'http://del.icio.us/feeds/json/network/' + \ + dlcs_encode_params({0:user})[0] + return dlcs_feed(url, raw=raw, callback=callback) + + +def json_fans(user, raw=True, callback=None): + """ + callback=NAME wrap the object definition in a function call NAME(...) + ?raw a pure JSON object is returned, instead of an object named + Delicious. + """ + url = 'http://del.icio.us/feeds/json/fans/' + \ + dlcs_encode_params({0:user})[0] + return dlcs_feed(url, raw=raw, callback=callback) + + +### delicious V2 feeds + +def getfeed(name, **params): + return dlcs_feed(name, **params) + diff --git a/lib/utils/strutils.py b/lib/utils/strutils.py new file mode 100644 index 0000000..368d3d8 --- /dev/null +++ b/lib/utils/strutils.py @@ -0,0 +1,50 @@ + +# +# String/unicode conversion utils. +# + +def safestr(s): + """ + Safely corerce *anything* to a string. If the object can't be str'd, an + empty string will be returned. + + You can (and I do) use this for really crappy unicode handling, but it's + a bit like killing a mosquito with a bazooka. + """ + if s is None: + return "" + if isinstance(s, unicode): + return s.encode('ascii', 'xmlcharrefreplace') + else: + try: + return str(s) + except: + return "" + +def safeint(s): + """Like safestr(), but always returns an int. Returns 0 on failure.""" + try: + return int(safestr(s)) + except ValueError: + return 0 + + +def convertentity(m): + import htmlentitydefs + """Convert a HTML entity into normal string (ISO-8859-1)""" + if m.group(1)=='#': + try: + return chr(int(m.group(2))) + except ValueError: + return '&#%s;' % m.group(2) + try: + return htmlentitydefs.entitydefs[m.group(2)] + except KeyError: + return '&%s;' % m.group(2) + +def unquotehtml(s): + import re + """Convert a HTML quoted string into normal string (ISO-8859-1). + + Works with &#XX; and with > etc.""" + return re.sub(r'&(#?)(.+?);',convertentity,s) |