hgweb: refactor fake file object proxy for archiving
authorGregory Szorc <gregory.szorc@gmail.com>
Sat, 10 Mar 2018 16:17:51 -0800
changeset 36881 16499427f6de
parent 36880 40193f977a8b
child 36882 97f44b0720e2
hgweb: refactor fake file object proxy for archiving Python's zip file writer operates on a file object. When doing work, it periodically calls write(), flush(), and tell() on that object. In WSGI contexts, the start_response function returns a write() function. That's a function to write data, not a full file object. So, when the archival code was first introduced in 2b03c6733efa in 2006, someone invented a proxy "tellable" type that wrapped a file object like object and kept track of write count so it could implement tell() and satisfy zipfile's needs. When our archival code runs, it attempts to tell() the destination and if that fails, converts it to a "tellable" instance. Our WSGI application passes the "wsgirequest" instance to the archival function. It fails the tell() test and is converted to a "tellable." It's worth noting that "wsgirequest" implements flush(), so "tellable" doesn't. This hackery all seems very specific to the WSGI code. So this commit moves the "tellable" type and the conversion of the destination file object into the WSGI code. There's a chance some other caller may be passing a file object like object that doesn't implement tell(). But I doubt it. As part of the refactor, our new type implements flush() and doesn't implement __getattr__. Given the intended limited use of this type, I want things to fail fast if there is an attempt to access attributes because I think it is important to document which attributes are being used for what purposes. Differential Revision: https://phab.mercurial-scm.org/D2791
mercurial/archival.py
mercurial/hgweb/request.py
mercurial/hgweb/webcommands.py
--- a/mercurial/archival.py	Sat Mar 10 16:27:01 2018 -0800
+++ b/mercurial/archival.py	Sat Mar 10 16:17:51 2018 -0800
@@ -195,34 +195,11 @@
         if self.fileobj:
             self.fileobj.close()
 
-class tellable(object):
-    '''provide tell method for zipfile.ZipFile when writing to http
-    response file object.'''
-
-    def __init__(self, fp):
-        self.fp = fp
-        self.offset = 0
-
-    def __getattr__(self, key):
-        return getattr(self.fp, key)
-
-    def write(self, s):
-        self.fp.write(s)
-        self.offset += len(s)
-
-    def tell(self):
-        return self.offset
-
 class zipit(object):
     '''write archive to zip file or stream.  can write uncompressed,
     or compressed with deflate.'''
 
     def __init__(self, dest, mtime, compress=True):
-        if not isinstance(dest, bytes):
-            try:
-                dest.tell()
-            except (AttributeError, IOError):
-                dest = tellable(dest)
         self.z = zipfile.ZipFile(pycompat.fsdecode(dest), r'w',
                                  compress and zipfile.ZIP_DEFLATED or
                                  zipfile.ZIP_STORED)
--- a/mercurial/hgweb/request.py	Sat Mar 10 16:27:01 2018 -0800
+++ b/mercurial/hgweb/request.py	Sat Mar 10 16:17:51 2018 -0800
@@ -290,6 +290,37 @@
                          headers=headers,
                          bodyfh=bodyfh)
 
+class offsettrackingwriter(object):
+    """A file object like object that is append only and tracks write count.
+
+    Instances are bound to a callable. This callable is called with data
+    whenever a ``write()`` is attempted.
+
+    Instances track the amount of written data so they can answer ``tell()``
+    requests.
+
+    The intent of this class is to wrap the ``write()`` function returned by
+    a WSGI ``start_response()`` function. Since ``write()`` is a callable and
+    not a file object, it doesn't implement other file object methods.
+    """
+    def __init__(self, writefn):
+        self._write = writefn
+        self._offset = 0
+
+    def write(self, s):
+        res = self._write(s)
+        # Some Python objects don't report the number of bytes written.
+        if res is None:
+            self._offset += len(s)
+        else:
+            self._offset += res
+
+    def flush(self):
+        pass
+
+    def tell(self):
+        return self._offset
+
 class wsgiresponse(object):
     """Represents a response to a WSGI request.
 
--- a/mercurial/hgweb/webcommands.py	Sat Mar 10 16:27:01 2018 -0800
+++ b/mercurial/hgweb/webcommands.py	Sat Mar 10 16:17:51 2018 -0800
@@ -24,6 +24,9 @@
     paritygen,
     staticfile,
 )
+from . import (
+    request as requestmod,
+)
 
 from .. import (
     archival,
@@ -1215,7 +1218,9 @@
     req.headers.extend(headers)
     req.respond(HTTP_OK, mimetype)
 
-    archival.archive(web.repo, req, cnode, artype, prefix=name,
+    bodyfh = requestmod.offsettrackingwriter(req.write)
+
+    archival.archive(web.repo, bodyfh, cnode, artype, prefix=name,
                      matchfn=match,
                      subrepos=web.configbool("web", "archivesubrepos"))
     return []