t1055/t1055-list_links-r7194.diff

diff -r 4663bf114c66 trunk/tracrpc/util.py

--- a/trunk/tracrpc/util.py	Thu Nov 26 15:30:46 2009 +0100

+++ b/trunk/tracrpc/util.py	Sun Dec 20 02:15:14 2009 -0500

@@ -10,7 +10,10 @@

 import time

 import xmlrpclib

+from genshi.builder import Element

+

 from trac.util.datefmt import utc

+from trac.wiki.formatter import Formatter

 ### PUBLIC

@@ -44,3 +47,75 @@

     from trac.util.text import empty

 except ImportError:

     empty = None

+

+class TracLinksFormatter(Formatter):

+    r"""A wiki formatter that pays attention to nothing but trac 

+    links.

+    

+    Verbatim copy of tracgviz.ig.wiki.TracLinksFormatter

+    """

+    for fmt_name in (x for x in Formatter.__dict__ \

+            if x.endswith('_formatter') and \

+            x not in ['_lhref_formatter', '_shref_formatter']):

+        locals()[fmt_name] = lambda *args, **kwds: ''

+    del fmt_name

+

+class WikiCrawler(TracLinksFormatter):

+    r"""Gather the all links found in a piece of text.

+    """

+    def __init__(self, env, context):

+        super(WikiCrawler, self).__init__(env, context)

+        self._links = []

+    

+    def handle_match(self, fullmatch):

+        r"""Modified version of `trac.wiki.formatter.Formatter.handle_match` 

+        needed to gather links generated by external wiki syntax 

+        providers (e.g. CamelCase).

+        """

+        def ext_wrapper(ext_handler):

+            def _ext_wrapper(fmt, match, fullmatch):

+                result = ext_handler(fmt, match, fullmatch)

+                if isinstance(result, Element) and str(result.tag) == 'a':

+                    self._links.append(result)

+                return result

+            return _ext_wrapper

+

+        for itype, match in fullmatch.groupdict().items():

+            if match and not itype in self.wikiparser.helper_patterns:

+                # Check for preceding escape character '!'

+                if match[0] == '!':

+                    return escape(match[1:])

+                if itype in self.wikiparser.external_handlers:

+                    external_handler = self.wikiparser.external_handlers[itype]

+                    return ext_wrapper(external_handler)(self, match, fullmatch)

+                else:

+                    internal_handler = getattr(self, '_%s_formatter' % itype)

+                    return internal_handler(match, fullmatch)

+

+    def _lhref_formatter(self, match, fullmatch):

+        link = super(WikiCrawler, self)._lhref_formatter(match, fullmatch)

+        self.env.log.debug("RPC(util) LinkFormatter LHREF rule triggered. "

+                        "Match= '%s' Full match= '%s' Link= '%s'", 

+                        match, fullmatch, link)

+        self._links.append(link)

+        return link

+        

+    def _shref_formatter(self, match, fullmatch):

+        link = super(WikiCrawler, self)._shref_formatter(match, fullmatch)

+        self.env.log.debug("RPC(util) LinkFormatter SHREF rule triggered. "

+                        "Match= '%s' Full match= '%s' Link= '%s'", 

+                        match, fullmatch, link)

+        self._links.append(link)

+        return link

+    

+    def extract_link(self, lnk_obj):

+        raise TracError('Unable to extract TracLink from DOM object.')

+    

+    def iter_urls(self):

+        for link in self._links :

+          if not link:

+              pass

+          elif isinstance(link, Element):

+              yield link.attrib.get('href')

+          else:

+              yield self.extract_link(link)

diff -r 4663bf114c66 trunk/tracrpc/wiki.py

--- a/trunk/tracrpc/wiki.py	Thu Nov 26 15:30:46 2009 +0100

+++ b/trunk/tracrpc/wiki.py	Sun Dec 20 02:15:14 2009 -0500

@@ -10,10 +10,12 @@

     from cStringIO import StringIO

 except ImportError:

     from StringIO import StringIO

+from itertools import chain

 import xmlrpclib

 import os

 from trac.core import *

+from trac.mimeview.api import Context

 from trac.resource import Resource

 from trac.util.datefmt import to_timestamp, to_datetime, utc

 from trac.wiki.api import WikiSystem

@@ -22,6 +24,7 @@

 from trac.attachment import Attachment

 from tracrpc.api import IXMLRPCHandler, expose_rpc

+from tracrpc.util import WikiCrawler

 class WikiRPC(Component):

     """Superset of the

@@ -199,8 +202,17 @@

         return True

     def listLinks(self, req, pagename):

-        """ ''Not implemented'' """

-        return []

+        """ List all URLs in links found in a wiki page. Supports both 

+        TracLinks and CamelCase"""

+        text = self.getPage(req, pagename)

+        env = self.env

+        ctx = Context.from_request(req, absurls=True)

+        abs_ref, href = req.abs_href, req.href

+        lf = WikiCrawler(env, ctx)

+        lf.format(text)

+        files = self.listAttachments(req, pagename)

+        href = self.env.abs_href.attachment

+        return chain(lf.iter_urls(), (href('wiki', f) for f in files))

     def wikiToHtml(self, req, text):

         """ Render arbitrary Wiki text as HTML. """