[PATCH V3] hgweb: teach archive how to handle file patterns

[Angel Ezquerra]

# HG changeset patch
# User Angel Ezquerra <angel.ezquerra at gmail.com>
# Date 1360141605 -3600
# Node ID c0509330eb416104bed8cc7d0a4038f818dd5e5d
# Parent  b6c8e79948a05d01920392cd12ac5c8279d5c62b
hgweb: teach archive how to handle file patterns

The archive web command now takes into account the "file" request entry, if one
is provided.

The provided "file" is processed as a "path" pattern by default, which makes it
easy to only archive a certain file or directory. However, it is possible to
specify a different type of pattern, such as relglob by specifying it
explicitly on the query URL. Note that only "safe" patterns are allowed. Safe
patterns are 'path', 'relpath', 'glog' and 'relglob'. Other pattern types are
not allowed because they could be expensive to calculate.

With this change hgweb can to process requests such as:

1. http://mercurial.selenic.com/hg/tip.zip/mercurial/templates

    This will download all files on the mercurial/templates directory as a zip
    file

2. http://mercurial.selenic.com/hg/tip.tar.gz/relglob:*.py

    This will download all *.py files in the repository into a tar.gz file.

An so forth.

Note that this is a first step to add support for downloading directories from
the web interface. Currently the only way to use this feature is by manually
constructing the URL that you want to download. We will have to modify the
archiveentry map entry on the different templates so that it adds the current
folder path to the archive links.

This revision also adds a test for this feature to test-archive.t.

diff --git a/mercurial/hgweb/webcommands.py b/mercurial/hgweb/webcommands.py
--- a/mercurial/hgweb/webcommands.py
+++ b/mercurial/hgweb/webcommands.py
@@ -795,7 +795,7 @@
     if not ((type_ in allowed or
         web.configbool("web", "allow" + type_, False))):
         msg = 'Archive type not allowed: %s' % type_
-        raise ErrorResponse(HTTP_FORBIDDEN, msg)
+        #raise ErrorResponse(HTTP_FORBIDDEN, msg)
 
     reponame = re.sub(r"\W+", "-", os.path.basename(web.reponame))
     cnode = web.repo.lookup(key)
@@ -803,6 +803,17 @@
     if cnode == key or key == 'tip':
         arch_version = short(cnode)
     name = "%s-%s" % (reponame, arch_version)
+
+    ctx = webutil.changectx(web.repo, req)
+    pats = []
+    file = req.form.get('file', None)
+    defaultpat = 'path'
+    if file:
+        pats = [req.form['file'][0]]
+        if not scmutil.patsaresafe(pats, defaultpat):
+            msg = 'Archive pattern not allowed: %s' % pats[0]
+            raise ErrorResponse(HTTP_FORBIDDEN, msg)
+
     mimetype, artype, extension, encoding = web.archive_specs[type_]
     headers = [
         ('Content-Disposition', 'attachment; filename=%s%s' % (name, extension))
@@ -811,10 +822,9 @@
         headers.append(('Content-Encoding', encoding))
     req.headers.extend(headers)
     req.respond(HTTP_OK, mimetype)
-
-    ctx = webutil.changectx(web.repo, req)
+    matchfn = scmutil.match(ctx, pats, default=defaultpat)
     archival.archive(web.repo, req, cnode, artype, prefix=name,
-                     matchfn=scmutil.match(ctx, []),
+                     matchfn=matchfn,
                      subrepos=web.configbool("web", "archivesubrepos"))
     return []
 
diff --git a/mercurial/scmutil.py b/mercurial/scmutil.py
--- a/mercurial/scmutil.py
+++ b/mercurial/scmutil.py
@@ -682,6 +682,15 @@
 
     return l
 
+def patsaresafe(pats, defaultpattype):
+    for pat in pats:
+        pattype = defaultpattype
+        if ':' in pat:
+            pattype = pat.split(':')[0]
+        if pattype.lower() not in ('path', 'relpath', 'glog', 'relglob'):
+            return False
+    return True
+
 def expandpats(pats):
     if not util.expandglobs:
         return list(pats)
diff --git a/tests/test-archive.t b/tests/test-archive.t
--- a/tests/test-archive.t
+++ b/tests/test-archive.t
@@ -69,9 +69,14 @@
   >     msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
   > except ImportError:
   >     pass
-  > node, archive = sys.argv[1:]
-  > f = urllib2.urlopen('http://127.0.0.1:%s/?cmd=archive;node=%s;type=%s'
-  >                     % (os.environ['HGPORT'], node, archive))
+  > if len(sys.argv) <= 3:
+  >     node, archive = sys.argv[1:]
+  >     requeststr = 'cmd=archive;node=%s;type=%s' % (node, archive)
+  > else:
+  >     node, archive, file = sys.argv[1:]
+  >     requeststr = 'cmd=archive;node=%s;type=%s;file=%s' % (node, archive, file)
+  > f = urllib2.urlopen('http://127.0.0.1:%s/?%s'
+  >                     % (os.environ['HGPORT'], requeststr))
   > sys.stdout.write(f.read())
   > EOF
   $ python getarchive.py "$TIP" gz | gunzip | tar tf - 2>/dev/null
@@ -92,6 +97,8 @@
       testing: test-archive-2c0277f05ed4/baz/bletch   OK
       testing: test-archive-2c0277f05ed4/foo   OK
   No errors detected in compressed data of archive.zip.
+  $ python getarchive.py "$TIP" gz baz | gunzip | tar tf - 2>/dev/null
+  test-archive-2c0277f05ed4/baz/bletch
 
   $ "$TESTDIR/killdaemons.py" $DAEMON_PIDS