dirstate: change added/modified placeholder hash length to 20 bytes
authorDurham Goode <durham@fb.com>
Thu, 10 Nov 2016 02:19:16 -0800
changeset 30361 1070df141718
parent 30360 0298a07f64d9
child 30362 3c6893ba2d36
dirstate: change added/modified placeholder hash length to 20 bytes Previously the added/modified placeholder hash for manifests generated from the dirstate was a 21byte long string consisting of the p1 file hash plus a single character to indicate an add or a modify. Normal hashes are only 20 bytes long. This makes it complicated to implement more efficient manifest implementations which rely on the hashes being fixed length. Let's change this hash to just be 20 bytes long, and rely on the astronomical improbability of an actual hash being these 20 bytes (just like we rely on no hash every being the nullid). This changes the possible behavior slightly in that the hash for all added/modified entries in the dirstate manifest will now be the same (so simple node comparisons would say they are equal), but we should never be doing simple node comparisons on these nodes even with the old hashes, because they did not accurately represent the content (i.e. two files based off the same p1 file node, with different working copy contents would have the same hash (even with the appended character) in the old scheme too, so we couldn't depend on the hashes period).
mercurial/context.py
mercurial/copies.py
mercurial/merge.py
mercurial/node.py
--- a/mercurial/context.py	Thu Nov 10 02:17:22 2016 -0800
+++ b/mercurial/context.py	Thu Nov 10 02:19:16 2016 -0800
@@ -14,8 +14,10 @@
 
 from .i18n import _
 from .node import (
+    addednodeid,
     bin,
     hex,
+    modifiednodeid,
     newnodeid,
     nullid,
     nullrev,
@@ -1232,23 +1234,13 @@
         """
         parents = self.parents()
 
-        man1 = parents[0].manifest()
-        man = man1.copy()
-        if len(parents) > 1:
-            man2 = self.p2().manifest()
-            def getman(f):
-                if f in man1:
-                    return man1
-                return man2
-        else:
-            getman = lambda f: man1
+        man = parents[0].manifest().copy()
 
-        copied = self._repo.dirstate.copies()
         ff = self._flagfunc
-        for i, l in (("a", self._status.added), ("m", self._status.modified)):
+        for i, l in ((addednodeid, self._status.added),
+                     (modifiednodeid, self._status.modified)):
             for f in l:
-                orig = copied.get(f, f)
-                man[f] = getman(orig).get(orig, nullid) + i
+                man[f] = i
                 try:
                     man.setflag(f, ff(f))
                 except OSError:
--- a/mercurial/copies.py	Thu Nov 10 02:17:22 2016 -0800
+++ b/mercurial/copies.py	Thu Nov 10 02:19:16 2016 -0800
@@ -278,7 +278,7 @@
         ac = repo.changelog.ancestors(revs, inclusive=True)
         ctx._ancestrycontext = ac
     def makectx(f, n):
-        if len(n) != 20 or n in node.wdirnodes:  # in a working context?
+        if n in node.wdirnodes:  # in a working context?
             if ctx.rev() is None:
                 return ctx.filectx(f)
             return repo[None][f]
--- a/mercurial/merge.py	Thu Nov 10 02:17:22 2016 -0800
+++ b/mercurial/merge.py	Thu Nov 10 02:19:16 2016 -0800
@@ -15,6 +15,7 @@
 
 from .i18n import _
 from .node import (
+    addednodeid,
     bin,
     hex,
     nullhex,
@@ -873,7 +874,7 @@
                     else:
                         actions[f] = ('cd', (f, None, f, False, pa.node()),
                                       "prompt changed/deleted")
-                elif n1[20:] == 'a':
+                elif n1 == addednodeid:
                     # This extra 'a' is added by working copy manifest to mark
                     # the file as locally added. We should forget it instead of
                     # deleting it.
--- a/mercurial/node.py	Thu Nov 10 02:17:22 2016 -0800
+++ b/mercurial/node.py	Thu Nov 10 02:19:16 2016 -0800
@@ -20,8 +20,10 @@
 # Phony node value to stand-in for new files in some uses of
 # manifests.
 newnodeid = '!' * 20
+addednodeid = ('0' * 15) + 'added'
+modifiednodeid = ('0' * 12) + 'modified'
 
-wdirnodes = set((newnodeid,))
+wdirnodes = set((newnodeid, addednodeid, modifiednodeid))
 
 # pseudo identifiers for working directory
 # (they are experimental, so don't add too many dependencies on them)