revlog: make the index always return the same tuple

It is simpler to manage the diferrence in on disk format in the internal index
code itself and lets the rest of the code always handle the same object.

This will become even more important when the data we store will be entirely
different (for example the changelog does not need the "linkrev" field.

We start with item reading, we will deal with item writing in the next
changesets.

Differential Revision: https://phab.mercurial-scm.org/D10568

mercurial/cext/revlog.c

@@ -335,18 +335,17 b' static PyObject *index_get(indexObject *'
 	c_node_id = data + 32;
 
 	if (self->entry_size == v1_entry_size) {
-		return Py_BuildValue(v1_tuple_format, offset_flags, comp_len,
-		                     uncomp_len, base_rev, link_rev, parent_1,
-		                     parent_2, c_node_id, self->nodelen);
+		sidedata_offset = 0;
+		sidedata_comp_len = 0;
 	} else {
 		sidedata_offset = getbe64(data + 64);
 		sidedata_comp_len = getbe32(data + 72);
+	}
 
 		return Py_BuildValue(v2_tuple_format, offset_flags, comp_len,
-		                     uncomp_len, base_rev, link_rev, parent_1,
-		                     parent_2, c_node_id, self->nodelen,
-		                     sidedata_offset, sidedata_comp_len);
-	}
+	                     uncomp_len, base_rev, link_rev, parent_1, parent_2,
+	                     c_node_id, self->nodelen, sidedata_offset,
+	                     sidedata_comp_len);
 }
 /*
  * Pack header information in binary
@@ -2769,15 +2768,9 b' static int index_init(indexObject *self,'
 		self->entry_size = v1_entry_size;
 	}
 
-	if (self->format_version == format_v1) {
 		self->nullentry =
-		    Py_BuildValue(PY23("iiiiiiis#", "iiiiiiiy#"), 0, 0, 0, -1,
-		                  -1, -1, -1, nullid, self->nodelen);
-	} else {
-		self->nullentry =
-		    Py_BuildValue(PY23("iiiiiiis#ii", "iiiiiiiy#ii"), 0, 0, 0,
-		                  -1, -1, -1, -1, nullid, self->nodelen, 0, 0);
-	}
+	    Py_BuildValue(PY23("iiiiiiis#ii", "iiiiiiiy#ii"), 0, 0, 0, -1, -1,
+	                  -1, -1, nullid, self->nodelen, 0, 0);
 
 	if (!self->nullentry)
 		return -1;

mercurial/pure/parsers.py

@@ -53,7 +53,7 b' class BaseIndexObject(object):'
     # Size of a C long int, platform independent
     int_size = struct.calcsize(b'>i')
     # An empty index entry, used as a default value to be overridden, or nullrev
-    null_item = (0, 0, 0, -1, -1, -1, -1, sha1nodeconstants.nullid)
+    null_item = (0, 0, 0, -1, -1, -1, -1, sha1nodeconstants.nullid, 0, 0)
 
     @util.propertycache
     def entry_size(self):
@@ -122,11 +122,16 b' class BaseIndexObject(object):'
         else:
             index = self._calculate_index(i)
             data = self._data[index : index + self.entry_size]
-        r = self.index_format.unpack(data)
+        r = self._unpack_entry(data)
         if self._lgt and i == 0:
             r = (offset_type(0, gettype(r[0])),) + r[1:]
         return r
 
+    def _unpack_entry(self, data):
+        r = self.index_format.unpack(data)
+        r = r + (0, 0)
+        return r
+
     def pack_header(self, header):
         """pack header information as binary"""
         v_fmt = revlog_constants.INDEX_HEADER
@@ -135,7 +140,7 b' class BaseIndexObject(object):'
     def entry_binary(self, rev):
         """return the raw binary string representing a revision"""
         entry = self[rev]
-        p = revlog_constants.INDEX_ENTRY_V1.pack(*entry)
+        p = revlog_constants.INDEX_ENTRY_V1.pack(*entry[:8])
         if rev == 0:
             p = p[revlog_constants.INDEX_HEADER.size :]
         return p
@@ -266,7 +271,6 b' def parse_index2(data, inline, revlogv2='
 
 class Index2Mixin(object):
     index_format = revlog_constants.INDEX_ENTRY_V2
-    null_item = (0, 0, 0, -1, -1, -1, -1, sha1nodeconstants.nullid, 0, 0)
 
     def replace_sidedata_info(
         self, i, sidedata_offset, sidedata_length, offset_flags
@@ -292,6 +296,9 b' class Index2Mixin(object):'
             msg = b"cannot rewrite entries outside of this transaction"
             raise KeyError(msg)
 
+    def _unpack_entry(self, data):
+        return self.index_format.unpack(data)
+
     def entry_binary(self, rev):
         """return the raw binary string representing a revision"""
         entry = self[rev]

mercurial/revlogutils/revlogv0.py

@@ -135,6 +135,8 b' def parse_index_v0(data, inline):'
             nodemap.get(e[4], node.nullrev),
             nodemap.get(e[5], node.nullrev),
             e[6],
+            0,  # no side data support
+            0,  # no side data support
         )
         index.append(e2)
         nodemap[e[6]] = n

mercurial/unionrepo.py

@@ -54,7 +54,18 b' class unionrevlog(revlog.revlog):'
         for rev2 in self.revlog2:
             rev = self.revlog2.index[rev2]
             # rev numbers - in revlog2, very different from self.rev
-            _start, _csize, rsize, base, linkrev, p1rev, p2rev, node = rev
+            (
+                _start,
+                _csize,
+                rsize,
+                base,
+                linkrev,
+                p1rev,
+                p2rev,
+                node,
+                _sdo,
+                _sds,
+            ) = rev
             flags = _start & 0xFFFF
 
             if linkmapper is None:  # link is to same revlog

tests/test-parseindex2.py

@@ -49,6 +49,7 b' def py_parseindex(data, inline):'
         cache = (0, data)
         while off <= l:
             e = struct.unpack(indexformatng, data[off : off + s])
+            e = e + (0, 0)
             nodemap[e[7]] = n
             append(e)
             n += 1
@@ -58,6 +59,7 b' def py_parseindex(data, inline):'
     else:
         while off <= l:
             e = struct.unpack(indexformatng, data[off : off + s])
+            e = e + (0, 0)
             nodemap[e[7]] = n
             append(e)
             n += 1
@@ -240,7 +242,7 b' class parseindex2tests(unittest.TestCase'
                 break
 
     def testminusone(self):
-        want = (0, 0, 0, -1, -1, -1, -1, sha1nodeconstants.nullid)
+        want = (0, 0, 0, -1, -1, -1, -1, sha1nodeconstants.nullid, 0, 0)
         index, junk = parsers.parse_index2(data_inlined, True)
         got = index[-1]
         self.assertEqual(want, got)  # inline data