--- /dev/null
+#! /usr/bin/env python
+"""Quick-quick implementation of WikiWikiWeb in Python
+"""
+#
+# Copyright (C) 1999, 2000 Martin Pool <mbp@humbug.org.au>
+# This version includes additional changes by Gerardo Poggiali (2002)
+# This version includes additional changes by Bernardo Innocenti (2007)
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but
+# WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+# General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+__version__ = '$Revision: 1.63+gerry+bernie $'[11:-2];
+
+import cgi, sys, string, os, re, errno, time, stat
+from os import path, environ
+from socket import gethostbyaddr
+from time import localtime, strftime
+
+# Regular expression defining a WikiWord
+# (but this definition is also assumed in other places)
+file_re = re.compile(r"^\b([A-Za-z0-9_\.\-]+)\b$")
+word_re = re.compile(r"^\b([A-Z][a-z]+){2,}\b$")
+img_re = re.compile(r"^.*\.(png|gif|jpg|jpeg)$", re.IGNORECASE)
+url_re = re.compile(r"^[a-z]{3,8}://[^\s'\"]+\S$")
+
+title_done = False
+
+def emit_header(type="text/html"):
+ print "Content-type: " + type + "; charset=utf-8"
+ print
+
+
+# Formatting stuff --------------------------------------------------
+
+def get_scriptname():
+ return environ.get('SCRIPT_NAME', '')
+
+def get_hostname(addr):
+ try:
+ return gethostbyaddr(addr)[0] + ' (' + addr + ')'
+ except:
+ return addr;
+
+def send_guru(msg, msg_type):
+ if msg is None or len(msg) == 0: return
+ print '<pre id="guru" onclick="this.style.display = \'none\'" class="' + msg_type + '">'
+ if msg_type == 'error':
+ print ' Software Failure. Press left mouse button to continue.\n'
+ print msg
+ if msg_type == 'error':
+ print ' Guru Meditation #DEADBEEF.ABADC0DE'
+ print '</pre>'
+ # FIXME: This simple JS code is harder to pass than ACID 3.0
+ print """
+ <script language="JavaScript" type="text/javascript">
+ var guru = document.getElementById('guru');
+ // Firefox 2.0 doesn't take border-color, but returns border-top-color fine
+ var color = document.defaultView.getComputedStyle(guru,null).getPropertyValue('border-top-color');
+
+ function guruOn() {
+ guru.style.setProperty('border-color', color, '');
+ setTimeout('guruOff()', 1000);
+ }
+ function guruOff() {
+ guru.style.setProperty('border-color', '#000000', '');
+ setTimeout('guruOn()', 1000);
+ }
+ // Safari 2.0 returns this rgba crap
+ // Konqueror 3.5.6 doesn't seem to support computed properties
+ if (color && color != 'rgba(0, 0, 0, 0)') {
+ //window.alert("enabled! color='" + color + "'");
+ guruOn();
+ }
+ </script>"""
+
+def send_title(name, text="Limbo", msg=None, msg_type = 'error'):
+ global title_done
+ if title_done: return
+
+ # Head
+ emit_header()
+ print """<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
+"""
+ print "<head><title>%s: %s</title>" % (site_name, text)
+ print ' <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />'
+ if not name:
+ print ' <meta name="robots" content="noindex,nofollow">'
+ if css_url:
+ print ' <link rel="stylesheet" type="text/css" href="%s" />' % css_url
+ print '</head>'
+
+ # Body
+ if name and allow_edit:
+ print '<body ondblclick="location.href=\'?edit=' + name + '\'">'
+ else:
+ print '<body>'
+
+ send_guru(msg, msg_type)
+
+ # Navbar
+ print '<div class="navigator">'
+ print '<b>' + site_name + ': '
+ if name:
+ print link_tag('?fullsearch=' + name, text) + '</b> '
+ else:
+ print text + '</b> '
+ print ' | ' + link_tag('FrontPage', 'Front Page', 'navlink')
+ print ' | ' + link_tag('FindPage', 'Find Page', 'navlink')
+ print ' | <a href="/wikigit/wiki.git" class="navlink">Recent Changes</a>'
+ if name:
+ print ' | <a href="/wikigit/wiki.git?a=history;f=' + name + '" class="navlink">Page History</a>'
+ print ' | ' + link_tag('?raw=' + name, 'Raw Text', 'navlink')
+ if allow_edit:
+ print ' | ' + link_tag('?edit=' + name, 'Edit Page', 'navlink')
+ else:
+ print ' | <i>Immutable Page</i>'
+ print '</div>'
+
+ title_done = True
+
+
+def link_tag(params, text=None, ss_class=None):
+ if text is None:
+ text = params # default
+ classattr = ''
+ # Prevent crawlers from following links to generated pages
+ # and links added by potential spammers
+ if ss_class == 'external' or ss_class == 'navlink':
+ classattr += 'rel="nofollow" '
+ if ss_class:
+ classattr += 'class="%s" ' % ss_class
+ return '<a %shref="%s/%s">%s</a>' % (classattr, get_scriptname(),
+ params, text)
+
+# Search ---------------------------------------------------
+
+def do_fullsearch(needle):
+ send_title(None, 'Full text search for "%s"' % (needle))
+
+ needle_re = re.compile(needle, re.IGNORECASE)
+ hits = []
+ all_pages = page_list()
+ for page_name in all_pages:
+ body = Page(page_name).get_raw_body()
+ count = len(needle_re.findall(body))
+ if count:
+ hits.append((count, page_name))
+
+ # The default comparison for tuples compares elements in order,
+ # so this sorts by number of hits
+ hits.sort()
+ hits.reverse()
+
+ print "<ul>"
+ for (count, page_name) in hits:
+ print '<li><p>' + Page(page_name).link_to()
+ print ' . . . . ' + `count`
+ print ['match', 'matches'][count <> 1]
+ print '</p></li>'
+ print "</ul>"
+
+ print_search_stats(len(hits), len(all_pages))
+
+
+def do_titlesearch(needle):
+ # TODO: check needle is legal -- but probably we can just accept any RE
+ send_title(None, "Title search for \"" + needle + '"')
+
+ needle_re = re.compile(needle, re.IGNORECASE)
+ all_pages = page_list()
+ hits = filter(needle_re.search, all_pages)
+
+ print "<ul>"
+ for filename in hits:
+ print '<li><p>' + Page(filename).link_to() + "</p></li>"
+ print "</ul>"
+
+ print_search_stats(len(hits), len(all_pages))
+
+
+def print_search_stats(hits, searched):
+ print "<p>%d hits out of %d pages searched.</p>" % (hits, searched)
+
+def do_edit(pagename):
+ Page(pagename).send_editor()
+
+def do_raw(pagename):
+ Page(pagename).send_raw()
+
+def do_savepage(pagename):
+ if not allow_edit:
+ raise 'editing disallowed for ' + pagename
+
+ global form
+ pg = Page(pagename)
+ if 'preview' in form:
+ pg.send_editor(form['savetext'].value)
+ elif 'save' in form:
+ pg.save_text(form['savetext'].value)
+ pg.send_page()
+ elif 'cancel' in form:
+ pg.msg = 'Editing cancelled'
+ pg.msg_type = 'notice'
+ pg.send_page()
+ else:
+ raise 'What did you press?'
+
+def make_index_key():
+ s = '<p><center>'
+ links = map(lambda ch: '<a href="#%s">%s</a>' % (ch, ch),
+ string.lowercase)
+ s = s + string.join(links, ' | ')
+ s = s + '</center></p>'
+ return s
+
+
+def page_list():
+ return filter(word_re.match, os.listdir(text_dir))
+
+
+def send_footer(name, mod_string=None):
+ print '<div class="footer">'
+ if mod_string:
+ print "last modified %s" % mod_string
+ print '</div></body></html>'
+
+
+# ----------------------------------------------------------
+# Macros
+def _macro_TitleSearch():
+ return _macro_search("titlesearch")
+
+def _macro_FullSearch():
+ return _macro_search("fullsearch")
+
+def _macro_search(type):
+ if form.has_key('value'):
+ default = form["value"].value
+ else:
+ default = ''
+ return """<form method="get"><input name="%s" size="30" value="%s"><input type="submit" value="Go"></form>""" % (type, default)
+
+def _macro_WordIndex():
+ s = make_index_key()
+ pages = list(page_list())
+ map = {}
+ word_re = re.compile('[A-Z][a-z]+')
+ for name in pages:
+ for word in word_re.findall(name):
+ try:
+ map[word].append(name)
+ except KeyError:
+ map[word] = [name]
+
+ all_words = map.keys()
+ all_words.sort()
+ last_letter = None
+ # set title
+ for word in all_words:
+ letter = string.lower(word[0])
+ if letter <> last_letter:
+ s = s + '; <a name="%s"><h3>%s</h3></a>' % (letter, letter)
+ last_letter = letter
+
+ s = s + '<b>%s</b><ul>' % word
+ links = map[word]
+ links.sort()
+ last_page = None
+ for name in links:
+ if name == last_page: continue
+ s = s + '<li>' + Page(name).link_to()
+ s = s + '</ul>'
+ return s
+
+
+def _macro_TitleIndex():
+ s = make_index_key()
+ pages = list(page_list())
+ pages.sort()
+ current_letter = None
+ for name in pages:
+ letter = string.lower(name[0])
+ if letter <> current_letter:
+ s = s + '<a name="%s"><h3>%s</h3></a>' % (letter, letter)
+ current_letter = letter
+ else:
+ s = s + '<br />'
+ s = s + Page(name).link_to()
+ return s
+
+
+# ----------------------------------------------------------
+class PageFormatter:
+ """Object that turns Wiki markup into HTML.
+
+ All formatting commands can be parsed one line at a time, though
+ some state is carried over between lines.
+ """
+ def __init__(self, raw):
+ self.raw = raw
+ self.is_em = self.is_b = 0
+ self.h_level = 0
+ self.list_indents = []
+ self.in_pre = 0
+ self.in_var = 0
+ self.in_header = True
+
+ def _emph_repl(self, word):
+ if len(word) == 3:
+ self.is_b = not self.is_b
+ return ['</b>', '<b>'][self.is_b]
+ else:
+ self.is_em = not self.is_em
+ return ['</em>', '<em>'][self.is_em]
+
+ def _tit_repl(self, word):
+ if self.h_level:
+ result = "</h%d>" % self.h_level
+ self.h_level = 0
+ else:
+ self.h_level = len(word) - 1
+ result = "<h%d>" % self.h_level
+ return result;
+
+ def _rule_repl(self, word):
+ s = self._undent()
+ if len(word) <= 3:
+ s = s + "\n<hr size='1' noshade=\"noshade\" />\n"
+ else:
+ s = s + "\n<hr size='%d' noshade=\"noshade\" />\n" % (len(word) - 2 )
+ return s
+
+ def _word_repl(self, word):
+ return Page(word).link_to()
+
+ def _img_repl(self, word):
+ return '<img border="0" src="%s/%s" />' % (get_scriptname(), word)
+
+ def _url_repl(self, word):
+ if img_re.match(word):
+ return '<img border="0" src="%s" />' % word
+ else:
+ return '<a href="%s" rel="nofollow" class="external">%s</a>' % (word, word)
+
+ def _hurl_repl(self, word):
+ m = re.compile("\[\[(\S+)\ (.+)\]\]").match(word)
+ anchor = m.group(1)
+ descr = m.group(2)
+ if img_re.match(anchor):
+ return '<img border="0" src="%s" alt="%s" />' % (anchor, descr)
+ elif url_re.match(anchor):
+ return '<a href="%s" rel="nofollow" class="external">%s</a>' % (anchor, descr)
+ elif anchor.startswith('/'):
+ return '<a href="%s">%s</a>' % (anchor, descr)
+ else:
+ return link_tag(anchor, descr)
+
+ def _email_repl(self, word):
+ return '<a href="mailto:%s">%s</a>' % (word, word)
+
+
+ def _ent_repl(self, s):
+ return {'&': '&',
+ '<': '<',
+ '>': '>'}[s]
+
+
+ def _li_repl(self, match):
+ return '<li>'
+
+
+ def _pre_repl(self, word):
+ if word == '{{{' and not self.in_pre:
+ self.in_pre = 1
+ return '<pre>'
+ elif self.in_pre:
+ self.in_pre = 0
+ return '</pre>'
+ else:
+ return ''
+
+ def _var_repl(self, word):
+ if word == '{{' and not self.in_var:
+ self.in_var = 1
+ return '<code>'
+ elif self.in_var:
+ self.in_var = 0
+ return '</code>'
+ else:
+ return ''
+ def _macro_repl(self, word):
+ macro_name = word[2:-2]
+ # TODO: Somehow get the default value into the search field
+ return apply(globals()['_macro_' + macro_name], ())
+
+ def _indent_level(self):
+ return len(self.list_indents) and self.list_indents[-1]
+
+ def _indent_to(self, new_level):
+ if self._indent_level() == new_level:
+ return ''
+ s = '</p>'
+ while self._indent_level() > new_level:
+ del(self.list_indents[-1])
+ s += '</ul>\n'
+ while self._indent_level() < new_level:
+ self.list_indents.append(new_level)
+ s += '<ul>\n'
+ s += '<p>'
+ return s
+
+ def _undent(self):
+ res = '</p>'
+ res += '</ul>' * len(self.list_indents)
+ res += '<p>'
+ self.list_indents = []
+ return res
+
+ def replace(self, match):
+ for type, hit in match.groupdict().items():
+ if hit:
+ return apply(getattr(self, '_' + type + '_repl'), (hit,))
+ else:
+ raise "Can't handle match " + `match`
+
+ def print_html(self):
+ print "<div class='wiki'><p>"
+
+ # For each line, we scan through looking for magic
+ # strings, outputting verbatim any intervening text
+ scan_re = re.compile(
+ r"(?:"
+ + r"(?P<emph>'{2,3})"
+ + r"|(?P<tit>\={2,6})"
+ + r"|(?P<ent>[<>&])"
+ + r"|(?P<img>\b[a-zA-Z0-9_-]+\.(png|gif|jpg|jpeg|bmp))"
+ + r"|(?P<word>\b(?:[A-Z][a-z]+){2,}\b)"
+ + r"|(?P<rule>^-{3,})"
+ + r"|(?P<hurl>\[\[\S+\s+.+\]\])"
+ + r"|(?P<url>(http|ftp|nntp|news|mailto)\:[^\s'\"]+\S)"
+ + r"|(?P<email>[-\w._+]+\@[\w.-]+)"
+ + r"|(?P<li>^\s+\*)"
+ + r"|(?P<pre>(\{\{\{|\s*\}\}\}))"
+ + r"|(?P<var>(\{\{|\}\}))"
+ + r"|(?P<macro>\[\[(TitleSearch|FullSearch|WordIndex|TitleIndex)\]\])"
+ + r")")
+ pre_re = re.compile(
+ r"(?:"
+ + r"(?P<pre>\s*\}\}\})"
+ + r")")
+ blank_re = re.compile("^\s*$")
+ indent_re = re.compile("^\s*")
+ eol_re = re.compile(r'\r?\n')
+ raw = string.expandtabs(self.raw)
+ for line in eol_re.split(raw):
+ # Skip ACLs
+ if self.in_header:
+ if line.startswith('#'):
+ continue
+ self.in_header = False
+ if self.in_pre:
+ print re.sub(pre_re, self.replace, line)
+ else:
+ # XXX: Should we check these conditions in this order?
+ if blank_re.match(line):
+ print '</p><p>'
+ continue
+ indent = indent_re.match(line)
+ print self._indent_to(len(indent.group(0)))
+ print re.sub(scan_re, self.replace, line)
+ if self.in_pre: print '</pre>'
+ print self._undent()
+ print "</p></div>"
+
+# ----------------------------------------------------------
+class Page:
+ def __init__(self, page_name):
+ self.page_name = page_name
+ self.remote_user = 'AnonymousCoward'
+ self.remote_host = environ.get('REMOTE_ADDR', '')
+ self.msg = ''
+ self.msg_type = 'error'
+ self.attrs = {}
+
+ def split_title(self):
+ # look for the end of words and the start of a new word,
+ # and insert a space there
+ return re.sub('([a-z])([A-Z])', r'\1 \2', self.page_name)
+
+
+ def _text_filename(self):
+ return path.join(text_dir, self.page_name)
+
+
+ def _tmp_filename(self):
+ return path.join(text_dir, ('#' + self.page_name + '.' + `os.getpid()` + '#'))
+
+
+ def exists(self):
+ try:
+ os.stat(self._text_filename())
+ return 1
+ except OSError, er:
+ if er.errno == errno.ENOENT:
+ return 0
+ else:
+ raise er
+
+ def link_to(self):
+ word = self.page_name
+ if self.exists():
+ return link_tag(word, word, 'wikilink')
+ else:
+ if nonexist_qm:
+ return link_tag(word, '?', 'nonexistent') + word
+ else:
+ return link_tag(word, word, 'nonexistent')
+
+
+ def get_raw_body(self):
+ try:
+ return open(self._text_filename(), 'rt').read()
+ except IOError, er:
+ if er.errno == errno.ENOENT:
+ # just doesn't exist, use default
+ return 'Describe %s here.' % self.page_name
+ else:
+ raise er
+
+ def get_attrs(self):
+ if self.attrs:
+ return self.attrs
+ try:
+ file = open(self._text_filename(), 'rt')
+ attr_re = re.compile(r"^#(\S*)(.*)$")
+ for line in file:
+ m = attr_re.match(line)
+ if not m:
+ break
+ self.attrs[m.group(1)] = m.group(2).strip()
+ #print "bernie: attrs[" + m.group(1) + "] = " + m.group(2) + "<br>\n"
+ except IOError, er:
+ if er.errno != errno.ENOENT:
+ raise er
+ return self.attrs
+
+ def can_edit(self):
+ attrs = self.get_attrs()
+ try:
+ # SomeUser:read,write All:read
+ acl = attrs["acl"]
+ for rule in acl.split():
+ (user,perms) = acl.split(':')
+ if user == self.remote_user or user == "All":
+ if 'write' in perms.split(','):
+ return True
+ return False
+ except:
+ pass
+ return True
+
+ def send_page(self):
+ page_name = None
+ if self.can_edit():
+ page_name = self.page_name
+ send_title(page_name, self.split_title(), msg=self.msg, msg_type=self.msg_type)
+ PageFormatter(self.get_raw_body()).print_html()
+ send_footer(page_name, self._last_modified())
+
+ def _last_modified(self):
+ if not self.exists():
+ return None
+ modtime = localtime(os.stat(self._text_filename())[stat.ST_MTIME])
+ return strftime(datetime_fmt, modtime)
+
+ def send_editor(self, preview=None):
+ send_title(None, 'Edit ' + self.split_title(), msg=self.msg, msg_type=self.msg_type)
+
+ print ('<p><b>Editing ' + self.page_name
+ + ' for ' + self.remote_user
+ + ' from ' + get_hostname(self.remote_host)
+ + '</b></p>')
+ print '<div class="editor"><form method="post" action="%s/%s">' % (get_scriptname(), self.page_name)
+ print '<input type="hidden" name="savepage" value="%s">' % (self.page_name)
+ print """<textarea wrap="virtual" id="editor" name="savetext" rows="17" cols="80">%s</textarea>""" % (preview or self.get_raw_body())
+ print """
+ <br />
+ <input type="submit" name="save" value="Save" />
+ <input type="submit" name="preview" value="Preview" />
+ <input type="reset" value="Reset" />
+ <input type="submit" name="cancel" value="Cancel" />
+ <br />
+ </form></div>"""
+ print "<p>" + Page('EditingTips').link_to() + "</p>"
+ if preview:
+ print "<div class='preview'>"
+ PageFormatter(preview).print_html()
+ print "</div>"
+
+ def send_raw(self):
+ emit_header("text/plain")
+ print self.get_raw_body()
+
+ def _write_file(self, text):
+ tmp_filename = self._tmp_filename()
+ open(tmp_filename, 'wt').write(text.replace('\r\n', '\n'))
+ text = self._text_filename()
+ if os.name == 'nt':
+ # Bad Bill! POSIX rename ought to replace. :-(
+ try:
+ os.remove(text)
+ except OSError, er:
+ if er.errno <> errno.ENOENT: raise er
+ os.rename(tmp_filename, text)
+
+ def save_text(self, newtext):
+ self._write_file(newtext)
+ rc = 0
+ if post_edit_hook:
+ cmd = ( post_edit_hook
+ + ' ' + text_dir + '/' + self.page_name
+ + ' ' + self.remote_user
+ + ' ' + self.remote_host
+ )
+ out = os.popen(cmd)
+ msg = out.read()
+ rc = out.close()
+ if rc:
+ self.msg += "Post-editing hook returned %d.\n" % rc
+ self.msg += 'Command was: ' + cmd + '\n'
+ if msg:
+ self.msg += 'Output follows:\n' + msg
+ else:
+ self.msg = 'Thankyou for your contribution. Your attention to detail is appreciated.'
+ self.msg_type = 'success'
+
+def send_verbatim(filename, mime_type='application/octet-stream'):
+ pathname = path.join(text_dir, filename)
+ data = open(pathname, 'rb').read()
+ emit_header(mime_type)
+ sys.stdout.write(data)
+
+# ---------------------------------------------------------------
+try:
+ # Configuration values
+ data_dir = '/home/bernie/public_html/wiki'
+ text_dir = path.join(data_dir, 'text')
+ allow_edit = True # Is it possible to edit pages?
+ site_name = 'codewiz.org'
+ changed_time_fmt = '[%I:%M %p] '
+ date_fmt = '%a %d %b %Y'
+ datetime_fmt = '%a %d %b %Y %I:%M %p'
+ show_hosts = True # show hostnames?
+ css_url = '../wikidata/pikiplus.css' # stylesheet link, or ''
+ nonexist_qm = False # show '?' for nonexistent?
+ post_edit_hook = './post_edit_hook.sh'
+
+ form = cgi.FieldStorage()
+
+ handlers = { 'fullsearch': do_fullsearch,
+ 'titlesearch': do_titlesearch,
+ 'edit': do_edit,
+ 'raw': do_raw,
+ 'savepage': do_savepage }
+
+ for cmd in handlers.keys():
+ if form.has_key(cmd):
+ apply(handlers[cmd], (form[cmd].value,))
+ break
+ else:
+ path_info = environ.get('PATH_INFO', '')
+ if len(path_info) and path_info[0] == '/':
+ query = path_info[1:] or 'FrontPage'
+ else:
+ query = environ.get('QUERY_STRING', '') or 'FrontPage'
+
+ if file_re.match(query):
+ if word_re.match(query):
+ Page(query).send_page()
+ elif img_re.match(query):
+ send_verbatim(query, 'image/jpeg')
+ else:
+ send_verbatim(query)
+ else:
+ # TODO: return 404?
+ send_title(None, msg='Can\'t work out query: ' + query)
+except:
+ import traceback
+ msg=traceback.format_exc()
+ if title_done:
+ send_guru(msg, "error")
+ else:
+ send_title(None, msg=msg)
+ send_footer(None)
+
+sys.stdout.flush()
projects / geekigeeki.git / commitdiff