Add a comment to explain how the FTS integrity-check works.

FossilOrigin-Name: 64e8a116f39434a3b7347f01a47f88eef3276742

diff --git a/ext/fts3/fts3_write.c b/ext/fts3/fts3_write.c
index 872b1f0d60786dc234eafe9fa4b5d3c40dc7b02a..b0f38b72e83fdbac030c1fbdb7a608612cac5577 100644 (file)
--- a/ext/fts3/fts3_write.c
+++ b/ext/fts3/fts3_write.c
@@ -4901,6 +4901,29 @@ static int fts3IntegrityCheck(Fts3Table *p, int *pbOk){
 **
 ** Or, if an error (e.g. an OOM or IO error) occurs, return an SQLite 
 ** error code.
+**
+** The integrity-check works as follows. For each token and indexed token
+** prefix in the document set, a 64-bit checksum is calculated (by code
+** in fts3ChecksumEntry()) based on the following:
+**
+**     + The index number (0 for the main index, 1 for the first prefix
+**       index etc.),
+**     + The token (or token prefix) text itself, 
+**     + The language-id of the row it appears in,
+**     + The docid of the row it appears in,
+**     + The column it appears in, and
+**     + The tokens position within that column.
+**
+** The checksums for all entries in the index are XORed together to create
+** a single checksum for the entire index.
+**
+** The integrity-check code calculates the same checksum in two ways:
+**
+**     1. By scanning the contents of the FTS index, and 
+**     2. By scanning and tokenizing the content table.
+**
+** If the two checksums are identical, the integrity-check is deemed to have
+** passed.
 */
 static int fts3DoIntegrityCheck(
   Fts3Table *p                    /* FTS3 table handle */

diff --git a/manifest b/manifest
index 418d5baf3b1b6a8eee3100493b4fd5ce5ec204a7..f0ab85f06c527a1b7daf4d58ffd17a66c04a8278 100644 (file)
--- a/manifest
+++ b/manifest
@@ -1,5 +1,5 @@
-C Add\san\sexperimental\sintegrity-check\sfunction\sto\sFTS.
-D 2012-03-26T10:36:55.434
+C Add\sa\scomment\sto\sexplain\show\sthe\sFTS\sintegrity-check\sworks.
+D 2012-03-26T10:47:03.798
 F Makefile.arm-wince-mingw32ce-gcc d6df77f1f48d690bd73162294bbba7f59507c72f
 F Makefile.in 2f37e468503dbe79d35c9f6dffcf3fae1ae9ec20
 F Makefile.linux-gcc 91d710bdc4998cb015f39edf3cb314ec4f4d7e23
@@ -78,7 +78,7 @@ F ext/fts3/fts3_test.c 6b7cc68aef4efb084e1449f7d20c4b20d3bdf6b4
 F ext/fts3/fts3_tokenizer.c 3da7254a9881f7e270ab28e2004e0d22b3212bce
 F ext/fts3/fts3_tokenizer.h 66dec98e365854b6cd2d54f1a96bb6d428fc5a68
 F ext/fts3/fts3_tokenizer1.c 5c98225a53705e5ee34824087478cf477bdb7004
-F ext/fts3/fts3_write.c a95e0f29a438bbba69ef686c75f03fbdf7ac79ac
+F ext/fts3/fts3_write.c 554368a941e89bf556d653d72eac4ceb8c5a30ef
 F ext/fts3/fts3speed.tcl b54caf6a18d38174f1a6e84219950d85e98bb1e9
 F ext/fts3/mkfts3amal.tcl 252ecb7fe6467854f2aa237bf2c390b74e71f100
 F ext/icu/README.txt bf8461d8cdc6b8f514c080e4e10dc3b2bbdfefa9
@@ -999,7 +999,7 @@ F tool/tostr.awk e75472c2f98dd76e06b8c9c1367f4ab07e122d06
 F tool/vdbe-compress.tcl d70ea6d8a19e3571d7ab8c9b75cba86d1173ff0f
 F tool/warnings-clang.sh 9f406d66e750e8ac031c63a9ef3248aaa347ef2a
 F tool/warnings.sh fbc018d67fd7395f440c28f33ef0f94420226381
-P 3cb6a879f1220db03a66429d63330e27e8ca6e49
-R a8a5e3d4a755c2fc6211bbe12afb7dcc
+P 40fc8804743dfb005991e9c5ef7b0ebcb3c2e731
+R a29b15091e6e8965fd03216fe1c6e4ff
 U dan
-Z 32d9f92fc095c5c84155b7497aaefe53
+Z 4197780953b43ba749fe7b7fcb72124a

diff --git a/manifest.uuid b/manifest.uuid
index afcb8fab6b383b9b5c8197f25b40eb1b1aea083b..427ed8ce6b743e42d3f41075682458f131c709ab 100644 (file)
--- a/manifest.uuid
+++ b/manifest.uuid
@@ -1 +1 @@
-40fc8804743dfb005991e9c5ef7b0ebcb3c2e731
\ No newline at end of file
+64e8a116f39434a3b7347f01a47f88eef3276742
\ No newline at end of file