Samuel L. Bayer:

- same fixes from webchecker.py
- incorporated small diff between current webchecker.py and 1.5.2
- fixed bug where "extra roots" added with the -t argument were being
  checked as real roots, not just as possible continuations
- added -a argument to suppress checking of name anchors

[And untabified --GvR]

Tools/webchecker/wcnew.py

@@ -124,6 +124,7 @@ Options:
 -t root   -- specify root dir which should be treated as internal (can repeat)
 -v        -- verbose operation; repeating -v will increase verbosity
 -x        -- don't check external links (these are often slow to check)
+-a        -- don't check name anchors
 
 Arguments:
 
@@ -166,6 +167,7 @@ MAXPAGE = 150000                        # Ignore files bigger than this
 ROUNDSIZE = 50                          # Number of links processed per round
 DUMPFILE = "@webchecker.pickle"         # Pickled checkpoint
 AGENTNAME = "webchecker"                # Agent name for robots.txt parser
+NONAMES = 0                             # Force name anchor checking
 
 
 # Global variables
@@ -183,7 +185,7 @@ def main():
     try:
 
         # Begin SLB 2/24/99: Added -t option here.
-        opts, args = getopt.getopt(sys.argv[1:], 'Rd:m:nqr:t:vx')
+        opts, args = getopt.getopt(sys.argv[1:], 'Rd:m:nqr:t:vxa')
         # End SLB 2/24/99
 
     except getopt.error, msg:
@@ -195,6 +197,7 @@ def main():
     # Begin SLB 2/24/99: Added extra_roots variable to
     # collect extra roots.
     extra_roots = []
+    nonames = NONAMES
     # End SLB 2/24/99
 
     for o, a in opts:
@@ -215,6 +218,8 @@ def main():
         # -t option.
         if o == '-t':
             extra_roots.append(a)
+        if o == '-a':
+            nonames = not nonames
         # End SLB 2/24/99
 
         if o == '-v':
@@ -231,7 +236,9 @@ def main():
         c = Checker()
 
     c.setflags(checkext=checkext, verbose=verbose,
-               maxpage=maxpage, roundsize=roundsize)
+               maxpage=maxpage, roundsize=roundsize,
+               nonames=nonames
+               )
 
     if not restart and not args:
         args.append(DEFROOT)
@@ -249,7 +256,7 @@ def main():
             # directory component.
             if root[-1] != "/":
                 root = root + "/"
-	    c.addroot(root)
+            c.addroot(root, add_to_do = 0)
     # End SLB 2/24/99
 
     try:
@@ -294,6 +301,7 @@ class Checker:
     verbose = VERBOSE
     maxpage = MAXPAGE
     roundsize = ROUNDSIZE
+    nonames = NONAMES
 
     validflags = tuple(dir())
 
@@ -348,7 +356,7 @@ class Checker:
         for url in self.bad.keys():
             self.markerror(url)
 
-    def addroot(self, root):
+    def addroot(self, root, add_to_do = 1):
         if root not in self.roots:
             troot = root
             scheme, netloc, path, params, query, fragment = \
@@ -363,6 +371,7 @@ class Checker:
             # Begin SLB 2/24/99: Modified this call to respect
             # the fact that the "done" and "todo" dictionaries
             # are now (URL, fragment) pairs
+            if add_to_do:
                 self.newlink((root, ""), ("<root>", root))
             # End SLB 2/24/99
 
@@ -441,9 +450,12 @@ class Checker:
                           "  from", self.todo[url_pair])
             else:
                 self.message("Check %s", self.format_url(url_pair))
+        url, local_fragment = url_pair
+        if local_fragment and self.nonames:
+            self.markdone(url_pair)
+            return
         page = self.getpage(url_pair)
         if page:
-	    url, local_fragment = url_pair
             # Store the page which corresponds to this URL.
             self.name_table[url] = page
             # If there is a fragment in this url_pair, and it's not
@@ -473,12 +485,23 @@ class Checker:
             self.newtodolink(url, origin)
 
     def newdonelink(self, url, origin):
+
+        if origin not in self.done[url]:
             self.done[url].append(origin)
 
         # Begin SLB 2/24/99: changed reference to URL
         # to call self.format_url(), since the URL here
         # is now a (URL, fragment) pair.
         self.note(3, "  Done link %s", self.format_url(url))
+
+        # SLB 11/11/99: Make sure that if it's bad, that
+        # the origin gets added.
+
+        if self.bad.has_key(url):
+            source, rawlink = origin
+            triple = url, rawlink, self.bad[url]
+            self.seterror(source, triple)
+
         # End SLB 2/24/99
 
     def newtodolink(self, url, origin):
@@ -487,6 +510,7 @@ class Checker:
         # to call self.format_url(), since the URL here
         # is now a (URL, fragment) pair.
         if self.todo.has_key(url):
+            if origin not in self.todo[url]:
                 self.todo[url].append(origin)
             self.note(3, "  Seen todo link %s", self.format_url(url))
         else:
@@ -793,9 +817,9 @@ class MyURLopener(urllib.FancyURLopener):
 
     def open_file(self, url):
         path = urllib.url2pathname(urllib.unquote(url))
+        if os.path.isdir(path):
             if path[-1] != os.sep:
                 url = url + '/'
-        if os.path.isdir(path):
             indexpath = os.path.join(path, "index.html")
             if os.path.exists(indexpath):
                 return self.open_file(url + "index.html")
@@ -812,7 +836,7 @@ class MyURLopener(urllib.FancyURLopener):
                 s.write('<A HREF="%s">%s</A>\n' % (q, q))
             s.seek(0)
             return s
-        return urllib.FancyURLopener.open_file(self, path)
+        return urllib.FancyURLopener.open_file(self, url)
 
 
 class MyHTMLParser(sgmllib.SGMLParser):