Add hash-based document metadata storage option (#10945)

This option saves metadata sidecar (sdr) directories not next to the book or in koreader/docsettings/, but in koreader/hashdocsettings/ using the partial md5 hash of each documents, allowing users to move, rename, and copy their documents outside of KOReader without accidentally losing their highlights/notes/progress. Included are various warnings and info to users of the benefits and drawbacks of this non-default option.

Closes #10892.

frontend/document/document.lua

@@ -9,6 +9,7 @@ local Math = require("optmath")
 local TileCacheItem = require("document/tilecacheitem")
 local lfs = require("libs/libkoreader-lfs")
 local logger = require("logger")
+local util = require("util")
 
 --[[
 This is an abstract interface to a document
@@ -145,16 +146,6 @@ end
 
 -- calculate partial digest of the document and store in its docsettings to avoid document saving
 -- feature to change its checksum.
---
--- To the calculating mechanism itself.
--- since only PDF documents could be modified by KOReader by appending data
--- at the end of the files when highlighting, we use a non-even sampling
--- algorithm which samples with larger weight at file head and much smaller
--- weight at file tail, thus reduces the probability that appended data may change
--- the digest value.
--- Note that if PDF file size is around 1024, 4096, 16384, 65536, 262144
--- 1048576, 4194304, 16777216, 67108864, 268435456 or 1073741824, appending data
--- by highlighting in KOReader may change the digest value.
 function Document:fastDigest(docsettings)
     if not self.file then return end
     local file = io.open(self.file, 'rb')
@@ -167,21 +158,7 @@ function Document:fastDigest(docsettings)
         local result = docsettings:readSetting("partial_md5_checksum")
         if not result then
             logger.dbg("computing and storing partial_md5_checksum")
-            local bit = require("bit")
-            local md5 = require("ffi/sha2").md5
-            local lshift = bit.lshift
-            local step, size = 1024, 1024
-            local update = md5()
-            for i = -1, 10 do
-                file:seek("set", lshift(step, 2*i))
-                local sample = file:read(size)
-                if sample then
-                    update(sample)
-                else
-                    break
-                end
-            end
-            result = update()
+            result = util.partialMD5(file)
             docsettings:saveSetting("partial_md5_checksum", result)
         end
         if tmp_docsettings then