changeset 47393:7a0ec25d5836

revlog: move entry documentation alongside new related constants Accessing individual index-entry element is usually done using integer directly. This is presumably for "performance reasons". However as the index entry gain more and more element it seems useful to get the option to use symbolic constant to access item, for both clarify and versatility. We will probably keep using integer for performance critical path, but less critical code may start using them now that they are declared. Differential Revision: https://phab.mercurial-scm.org/D10791
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Sat, 22 May 2021 00:06:22 +0200
parents 8089d0fa8400
children ac60a1366a49
files mercurial/revlog.py mercurial/revlogutils/constants.py
diffstat 2 files changed, 77 insertions(+), 60 deletions(-) [+]
line wrap: on
line diff
--- a/mercurial/revlog.py	Fri May 21 20:08:11 2021 +0200
+++ b/mercurial/revlog.py	Sat May 22 00:06:22 2021 +0200
@@ -310,66 +310,8 @@
     the current position in the file handle is valid, and log/warn/fail (by
     raising).
 
-
-    Internal details
-    ----------------
-
-    A large part of the revlog logic deals with revisions' "index entries", tuple
-    objects that contains the same "items" whatever the revlog version.
-    Different versions will have different ways of storing these items (sometimes
-    not having them at all), but the tuple will always be the same. New fields
-    are usually added at the end to avoid breaking existing code that relies
-    on the existing order. The field are defined as follows:
-
-    [0] offset:
-            The byte index of the start of revision data chunk.
-            That value is shifted up by 16 bits. use "offset = field >> 16" to
-            retrieve it.
-
-        flags:
-            A flag field that carries special information or changes the behavior
-            of the revision. (see `REVIDX_*` constants for details)
-            The flag field only occupies the first 16 bits of this field,
-            use "flags = field & 0xFFFF" to retrieve the value.
-
-    [1] compressed length:
-            The size, in bytes, of the chunk on disk
-
-    [2] uncompressed length:
-            The size, in bytes, of the full revision once reconstructed.
-
-    [3] base rev:
-            Either the base of the revision delta chain (without general
-            delta), or the base of the delta (stored in the data chunk)
-            with general delta.
-
-    [4] link rev:
-            Changelog revision number of the changeset introducing this
-            revision.
-
-    [5] parent 1 rev:
-            Revision number of the first parent
-
-    [6] parent 2 rev:
-            Revision number of the second parent
-
-    [7] node id:
-            The node id of the current revision
-
-    [8] sidedata offset:
-            The byte index of the start of the revision's side-data chunk.
-
-    [9] sidedata chunk length:
-            The size, in bytes, of the revision's side-data chunk.
-
-    [10] data compression mode:
-            two bits that detail the way the data chunk is compressed on disk.
-            (see "COMP_MODE_*" constants for details). For revlog version 0 and
-            1 this will always be COMP_MODE_INLINE.
-
-    [11] side-data compression mode:
-            two bits that detail the way the sidedata chunk is compressed on disk.
-            (see "COMP_MODE_*" constants for details)
+    See mercurial/revlogutils/contants.py for details about the content of an
+    index entry.
     """
 
     _flagserrorclass = error.RevlogError
--- a/mercurial/revlogutils/constants.py	Fri May 21 20:08:11 2021 +0200
+++ b/mercurial/revlogutils/constants.py	Sat May 22 00:06:22 2021 +0200
@@ -27,6 +27,81 @@
     KIND_OTHER,
 }
 
+### Index entry key
+#
+#
+#    Internal details
+#    ----------------
+#
+#    A large part of the revlog logic deals with revisions' "index entries", tuple
+#    objects that contains the same "items" whatever the revlog version.
+#    Different versions will have different ways of storing these items (sometimes
+#    not having them at all), but the tuple will always be the same. New fields
+#    are usually added at the end to avoid breaking existing code that relies
+#    on the existing order. The field are defined as follows:
+
+#    [0] offset:
+#            The byte index of the start of revision data chunk.
+#            That value is shifted up by 16 bits. use "offset = field >> 16" to
+#            retrieve it.
+#
+#        flags:
+#            A flag field that carries special information or changes the behavior
+#            of the revision. (see `REVIDX_*` constants for details)
+#            The flag field only occupies the first 16 bits of this field,
+#            use "flags = field & 0xFFFF" to retrieve the value.
+ENTRY_DATA_OFFSET = 0
+
+#    [1] compressed length:
+#            The size, in bytes, of the chunk on disk
+ENTRY_DATA_COMPRESSED_LENGTH = 1
+
+#    [2] uncompressed length:
+#            The size, in bytes, of the full revision once reconstructed.
+ENTRY_DATA_UNCOMPRESSED_LENGTH = 2
+
+#    [3] base rev:
+#            Either the base of the revision delta chain (without general
+#            delta), or the base of the delta (stored in the data chunk)
+#            with general delta.
+ENTRY_DELTA_BASE = 3
+
+#    [4] link rev:
+#            Changelog revision number of the changeset introducing this
+#            revision.
+ENTRY_LINK_REV = 4
+
+#    [5] parent 1 rev:
+#            Revision number of the first parent
+ENTRY_PARENT_1 = 5
+
+#    [6] parent 2 rev:
+#            Revision number of the second parent
+ENTRY_PARENT_2 = 6
+
+#    [7] node id:
+#            The node id of the current revision
+ENTRY_NODE_ID = 7
+
+#    [8] sidedata offset:
+#            The byte index of the start of the revision's side-data chunk.
+ENTRY_SIDEDATA_OFFSET = 8
+
+#    [9] sidedata chunk length:
+#            The size, in bytes, of the revision's side-data chunk.
+ENTRY_SIDEDATA_COMPRESSED_LENGTH = 9
+
+#    [10] data compression mode:
+#            two bits that detail the way the data chunk is compressed on disk.
+#            (see "COMP_MODE_*" constants for details). For revlog version 0 and
+#            1 this will always be COMP_MODE_INLINE.
+ENTRY_DATA_COMPRESSION_MODE = 10
+
+#    [11] side-data compression mode:
+#            two bits that detail the way the sidedata chunk is compressed on disk.
+#            (see "COMP_MODE_*" constants for details)
+ENTRY_SIDEDATA_COMPRESSION_MODE = 11
+
 ### main revlog header
 
 # We cannot rely on  Struct.format is inconsistent for python <=3.6 versus above