From 40deb3f0be4e4f3a9a6b10c9d2117cec24d69954 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Motiejus=20Jak=C5=A1tys?= <motiejus@jakstys.lt>
Date: Mon, 28 Feb 2022 06:14:00 +0200
Subject: [PATCH] preparing for bringing this all together

---
 README.md        | 37 +++++++++++++++++++++++++------------
 src/compress.zig |  7 +++----
 2 files changed, 28 insertions(+), 16 deletions(-)

diff --git a/README.md b/README.md
index 322629b..b81420f 100644
--- a/README.md
+++ b/README.md
@@ -70,6 +70,11 @@ Tight packing places some constraints on the underlying data:
 - Permitted comment ("gecos") length: 0-255 bytes.
 - User name, groupname, gecos and shell must be utf8-encoded.
 
+Sorting is stable. In v0:
+- Groups are sorted by gid, ascending.
+- Users are sorted by their name, ascending by the unicode codepoints
+  (locale-independent).
+
 Checking out and building
 -------------------------
 
@@ -182,10 +187,9 @@ the beginning of the section.
 ```
 const PackedGroup = packed struct {
     gid: u32,
-    // index to a separate structure with a list of members. The memberlist is
-    // 2^5-byte aligned (32b), this is an index there.
-    members_offset: u27,
-    groupname_len: u5,
+    // index to a separate structure with a list of members.
+    members_offset: u32,
+    groupname_len: u8, // max is 32, but have too much space here.
     // a groupname_len-sized string
     groupname []u8;
 }
@@ -281,7 +285,7 @@ Similarly, when user's groups are resolved in (2), they are not always necessary
 (i.e. not part of `struct user*`), therefore the memberships themselves are
 stored out of bound.
 
-`Groupmembers` and `Username2gids` store group and user memberships
+`Groupmembers` and `UserGids` store group and user memberships
 respectively. Membership IDs are used in their entirety — not necessitating
 random access, thus suitable for tight packing and varint encoding.
 
@@ -290,7 +294,7 @@ random access, thus suitable for tight packing and varint encoding.
 - For each user — a list of gids, because `initgroups_dyn` (and friends)
   returns an array of gids.
 
-An entry of `Groupmembers` and `Username2gids` looks like this piece of
+An entry of `Groupmembers` and `UserGids` looks like this piece of
 pseudo-code:
 
 ```
@@ -299,7 +303,7 @@ const PackedList = struct {
     Members: [Length]varint,
 }
 const Groupmembers = PackedList;
-const Username2gids  = PackedList;
+const UserGids  = PackedList;
 ```
 
 Indices
@@ -355,15 +359,24 @@ STATUS  SECTION               SIZE             DESCRIPTION
         idx_groupname2group   len(group)*29/8  bdz->offset Groups
         idx_uid2user          len(user)*29/8   bdz->offset Users
         idx_name2user         len(user)*29/8   bdz->offset Users
-        idx_username2gids     len(user)*29/8   bdz->offset Username2gids
-✅      ShellIndex            len(shells)*2    Shell index array
-✅      ShellBlob             <= 4032          Shell data blob (max 63*64 bytes)
+        idx_username2gids     len(user)*29/8   bdz->offset UserGids
+✅      ShellIndex            len(shells)*2    shell index array
+✅      ShellBlob             <= 4032          shell data blob (max 63*64 bytes)
 ✅      Groups                ?                packed Group entries (8b padding)
 ✅      Users                 ?                packed User entries (8b padding)
-        Groupmembers          ?                per-group memberlist (32b padding)
-        Username2gids         ?                Per-user gidlist entries (8b padding)
+        Groupmembers          ?                per-group memberlist (no padding)
+        UserGids              ?                per-user gidlist entries (8b padding)
 ```
 
+Section creation order:
+
+1. Groupmembers, UserGids. No dependencies.
+2. ShellIndex, ShellBlob. No dependencies.
+3. `bdz_*`. No depdendencies.
+4. Groups. Requires Groupmembers.
+5. Users. Requires Groupmembers and ShellIndex.
+6. `idx_*`. Requires offsets to Groups and Users.
+
 [git-subtrac]: https://apenwarr.ca/log/20191109
 [cmph]: http://cmph.sourceforge.net/
 [id]: https://linux.die.net/man/1/id
diff --git a/src/compress.zig b/src/compress.zig
index 7368251..4677867 100644
--- a/src/compress.zig
+++ b/src/compress.zig
@@ -1,9 +1,8 @@
 //
 // varint64 []const u8 variants
 //
-// Thanks to https://github.com/gsquire/zig-snappy/blob/master/snappy.zig and golang's
-// varint implementation.
-
+// Thanks to https://github.com/gsquire/zig-snappy/blob/master/snappy.zig and
+// golang's varint implementation.
 const std = @import("std");
 
 // compresses a strictly incrementing sorted slice of integers using delta
@@ -96,7 +95,7 @@ pub const Varint = struct {
     bytesRead: usize,
 };
 
-const maxVarintLen64 = 10;
+pub const maxVarintLen64 = 10;
 
 // https://golang.org/pkg/encoding/binary/#Uvarint
 pub fn uvarint(buf: []const u8) error{Overflow}!Varint {