First version of the dupe prevention trigger. Works for INSERTs and UPDATEs.

diff --git a/dbscripts/create_pg.sql b/dbscripts/create_pg.sql
index 86bd687..57a7ff4 100755 (executable)
--- a/dbscripts/create_pg.sql
+++ b/dbscripts/create_pg.sql
@@ -292,6 +292,7 @@ CREATE TABLE "comment" (
        "to_language" integer DEFAULT '0' NOT NULL,
        "to_media" integer NOT NULL,
        "to_comment_status" smallint,
+       "checksum" integer, 
        Constraint "comment_pkey" Primary Key ("id")
 );
 

diff --git a/dbscripts/dupetrigger/INSTALL b/dbscripts/dupetrigger/INSTALL
new file mode 100755 (executable)
index 0000000..8571231
--- /dev/null
+++ b/dbscripts/dupetrigger/INSTALL
@@ -0,0 +1,9 @@
+To install the trigger do the following:
+
+# make
+(This makes the trigger binary and places it in /tmp with permissions 644)
+
+# psql -U postgres Mir < postgresql.script
+(This installs the the trigger binary and creates a new trigger.)
+
+# rm /tmp/trigger.so

diff --git a/dbscripts/dupetrigger/Makefile b/dbscripts/dupetrigger/Makefile
new file mode 100755 (executable)
index 0000000..ad1c52c
--- /dev/null
+++ b/dbscripts/dupetrigger/Makefile
@@ -0,0 +1,21 @@
+# Makefile
+
+CC=gcc
+PGINC=/usr/include/postgresql
+
+trigger.so: trigger.o
+       $(CC) -shared -dynamic -o trigger.so trigger.o
+       cp trigger.so /tmp
+       chmod 755 /tmp/trigger.so
+
+trigger.o: trigger.c
+       $(CC) -I$(PGINC) -c trigger.c -o trigger.o
+
+
+clean:
+       rm -rf trigger.o trigger.so
+
+
+tidy: clean
+       rm -rf *~
+       
\ No newline at end of file

diff --git a/dbscripts/dupetrigger/README b/dbscripts/dupetrigger/README
new file mode 100755 (executable)
index 0000000..5856177
--- /dev/null
+++ b/dbscripts/dupetrigger/README
@@ -0,0 +1,16 @@
+Dupe check Trigger
+by Matthias "Trigger Hippy" Jordan <mjordan@code-fu.de>
+
+The files in this directory are needed to create a PostgreSQL trigger that
+is used to ensure that no comment and no article is posted twice. This
+happens very often by accident and is very disturbing so we have to prevent
+this somehow. Because Indymedia databases will hopefully grow big very fast,
+we want to do this check as fast as possible. 
+
+So Mir simply issues the INSERT. By this INSERT statement, a trigger gets,
+well, triggered that calculate a CRC-32 checksum of the comment and searches
+for rows with the same checksum. If it finds the checksum, the INSERT gets
+aborted. If the checksum isn't found, it is appended to the row and the
+INSERT is executed.
+
+The trigger works for INSERTs and UPDATEs.

diff --git a/dbscripts/dupetrigger/postgresql.sript b/dbscripts/dupetrigger/postgresql.sript
new file mode 100755 (executable)
index 0000000..d1f43c4
--- /dev/null
+++ b/dbscripts/dupetrigger/postgresql.sript
@@ -0,0 +1,5 @@
+\connect - postgres
+DROP FUNCTION dupecheck();
+DROP TRIGGER dupetrigger ON comment;
+CREATE FUNCTION dupecheck() RETURNS OPAQUE AS '/tmp/trigger.so' LANGUAGE 'C';
+CREATE TRIGGER dupetrigger BEFORE INSERT OR UPDATE ON comment FOR EACH ROW EXECUTE PROCEDURE dupecheck();

diff --git a/dbscripts/dupetrigger/trigger.c b/dbscripts/dupetrigger/trigger.c
new file mode 100755 (executable)
index 0000000..66f61e1
--- /dev/null
+++ b/dbscripts/dupetrigger/trigger.c
@@ -0,0 +1,209 @@
+//
+//
+// This File contructs a PostgreSQL trigger.
+// The trigger is fired BEFORE an INSERT or UPDATE of an article
+// or comment. It first calculates a CRC32 checksum of the row to be
+// inserted or updated and checks whether there exists already another
+// row with the same checksum and the same content. In this case,
+// the trigger returns NULL and thus, aborts the SQL command.
+//
+// Author: Matthias Jordan <mjordan@code-fu.de>
+//
+
+
+#include "executor/spi.h"
+#include "commands/trigger.h"
+#include "string.h"
+
+extern Datum dupecheck(PG_FUNCTION_ARGS);
+
+PG_FUNCTION_INFO_V1(dupecheck);
+
+
+
+
+//
+//
+// CRC32 stuff
+//
+
+// crc32 table based on the following polynom
+#define CRC32_POLY 0x04c11db7     /* AUTODIN II, Ethernet, & FDDI */
+
+u_long crc32_table[256] = 
+       {0x0000000, 0x04c11db7, 0x09823b6e, 0x0d4326d9, 0x130476dc, 0x17c56b6b,
+       0x1a864db2, 0x1e475005, 0x2608edb8, 0x22c9f00f, 0x2f8ad6d6, 0x2b4bcb61,
+       0x350c9b64, 0x31cd86d3, 0x3c8ea00a, 0x384fbdbd, 0x4c11db70, 0x48d0c6c7,
+       0x4593e01e, 0x4152fda9, 0x5f15adac, 0x5bd4b01b, 0x569796c2, 0x52568b75,
+       0x6a1936c8, 0x6ed82b7f, 0x639b0da6, 0x675a1011, 0x791d4014, 0x7ddc5da3,
+       0x709f7b7a, 0x745e66cd, 0x9823b6e0, 0x9ce2ab57, 0x91a18d8e, 0x95609039,
+       0x8b27c03c, 0x8fe6dd8b, 0x82a5fb52, 0x8664e6e5, 0xbe2b5b58, 0xbaea46ef,
+       0xb7a96036, 0xb3687d81, 0xad2f2d84, 0xa9ee3033, 0xa4ad16ea, 0xa06c0b5d,
+       0xd4326d90, 0xd0f37027, 0xddb056fe, 0xd9714b49, 0xc7361b4c, 0xc3f706fb,
+       0xceb42022, 0xca753d95, 0xf23a8028, 0xf6fb9d9f, 0xfbb8bb46, 0xff79a6f1,
+       0xe13ef6f4, 0xe5ffeb43, 0xe8bccd9a, 0xec7dd02d, 0x34867077, 0x30476dc0,
+       0x3d044b19, 0x39c556ae, 0x278206ab, 0x23431b1c, 0x2e003dc5, 0x2ac12072,
+       0x128e9dcf, 0x164f8078, 0x1b0ca6a1, 0x1fcdbb16, 0x018aeb13, 0x54bf6a4,
+       0x0808d07d, 0x0cc9cdca, 0x7897ab07, 0x7c56b6b0, 0x71159069, 0x75d48dde,
+       0x6b93dddb, 0x6f52c06c, 0x6211e6b5, 0x66d0fb02, 0x5e9f46bf, 0x5a5e5b08,
+       0x571d7dd1, 0x53dc6066, 0x4d9b3063, 0x495a2dd4, 0x44190b0d, 0x40d816ba,
+       0xaca5c697, 0xa864db20, 0xa527fdf9, 0xa1e6e04e, 0xbfa1b04b, 0xbb60adfc,
+       0xb6238b25, 0xb2e29692, 0x8aad2b2f, 0x8e6c3698, 0x832f1041, 0x87ee0df6,
+       0x99a95df3, 0x9d684044, 0x902b669d, 0x94ea7b2a, 0xe0b41de7, 0xe4750050,
+       0xe9362689, 0xedf73b3e, 0xf3b06b3b, 0xf771768c, 0xfa325055, 0xfef34de2,
+       0xc6bcf05f, 0xc27dede8, 0xcf3ecb31, 0xcbffd686, 0xd5b88683, 0xd1799b34,
+       0xdc3abded, 0xd8fba05a, 0x690ce0ee, 0x6dcdfd59, 0x608edb80, 0x644fc637,
+       0x7a089632, 0x7ec98b85, 0x738aad5c, 0x774bb0eb, 0x4f040d56, 0x4bc510e1,
+       0x46863638, 0x42472b8f, 0x5c007b8a, 0x58c1663d, 0x558240e4, 0x51435d53,
+       0x251d3b9e, 0x21dc2629, 0x2c9f00f0, 0x285e1d47, 0x36194d42, 0x32d850f5,
+       0x3f9b762c, 0x3b5a6b9b, 0x0315d626, 0x07d4cb91, 0x0a97ed48, 0xe56f0ff,
+       0x1011a0fa, 0x14d0bd4d, 0x19939b94, 0x1d528623, 0xf12f560e, 0xf5ee4bb9,
+       0xf8ad6d60, 0xfc6c70d7, 0xe22b20d2, 0xe6ea3d65, 0xeba91bbc, 0xef68060b,
+       0xd727bbb6, 0xd3e6a601, 0xdea580d8, 0xda649d6f, 0xc423cd6a, 0xc0e2d0dd,
+       0xcda1f604, 0xc960ebb3, 0xbd3e8d7e, 0xb9ff90c9, 0xb4bcb610, 0xb07daba7,
+       0xae3afba2, 0xaafbe615, 0xa7b8c0cc, 0xa379dd7b, 0x9b3660c6, 0x9ff77d71,
+       0x92b45ba8, 0x9675461f, 0x8832161a, 0x8cf30bad, 0x81b02d74, 0x857130c3,
+       0x5d8a9099, 0x594b8d2e, 0x5408abf7, 0x50c9b640, 0x4e8ee645, 0x4a4ffbf2,
+       0x470cdd2b, 0x43cdc09c, 0x7b827d21, 0x7f436096, 0x7200464f, 0x76c15bf8,
+       0x68860bfd, 0x6c47164a, 0x61043093, 0x65c52d24, 0x119b4be9, 0x155a565e,
+       0x18197087, 0x1cd86d30, 0x029f3d35, 0x065e2082, 0x0b1d065b, 0xfdc1bec,
+       0x3793a651, 0x3352bbe6, 0x3e119d3f, 0x3ad08088, 0x2497d08d, 0x2056cd3a,
+       0x2d15ebe3, 0x29d4f654, 0xc5a92679, 0xc1683bce, 0xcc2b1d17, 0xc8ea00a0,
+       0xd6ad50a5, 0xd26c4d12, 0xdf2f6bcb, 0xdbee767c, 0xe3a1cbc1, 0xe760d676,
+       0xea23f0af, 0xeee2ed18, 0xf0a5bd1d, 0xf464a0aa, 0xf9278673, 0xfde69bc4,
+       0x89b8fd09, 0x8d79e0be, 0x803ac667, 0x84fbdbd0, 0x9abc8bd5, 0x9e7d9662,
+       0x933eb0bb, 0x97ffad0c, 0xafb010b1, 0xab710d06, 0xa6322bdf, 0xa2f33668,
+       0xbcb4666d, 0xb8757bda, 0xb5365d03, 0xb1f740b4};
+
+
+static u_long crc32(u_char *buf, unsigned len)
+{
+        u_char *p;
+        u_long  crc;
+
+        crc = 0xffffffff;       /* preload shift register, per CRC-32 spec */
+        for (p = buf; len > 0; ++p, --len)
+        {
+                crc = (crc << 8) ^ crc32_table[(crc >> 24) ^ *p];
+        }
+        return ~crc;            /* transmit complement, per CRC-32 spec */
+} /* crc32 */
+
+
+
+
+
+//
+//
+// Trigger stuff
+//
+
+
+
+
+Datum dupecheck(PG_FUNCTION_ARGS)
+{
+       TriggerData *trigdata = (TriggerData *) fcinfo->context;
+       TupleDesc       tupdesc;
+       HeapTuple       rettuple;
+       bool            isnull;
+       int                     ret = 0, i, fnumber;
+       long rowstrlen = 0,
+               crc;
+       int maxitems = 3,
+               num;
+       char *items[maxitems],
+               *rowstring,
+               *query;
+       
+
+       /* Make sure trigdata is pointing at what I expect */
+       if (!CALLED_AS_TRIGGER(fcinfo))
+               elog(ERROR, "dupecheck: not fired by trigger manager");
+       
+       /* tuple to return to Executor */
+       if (TRIGGER_FIRED_BY_UPDATE(trigdata->tg_event))
+               rettuple = trigdata->tg_newtuple;
+       else
+               rettuple = trigdata->tg_trigtuple;
+       
+       if (TRIGGER_FIRED_BY_DELETE(trigdata->tg_event))
+               return PointerGetDatum(NULL);
+       
+       tupdesc = trigdata->tg_relation->rd_att;
+       
+       /* Connect to SPI manager */
+       if ((ret = SPI_connect()) < 0)
+       ret = SPI_connect();
+       elog(NOTICE, "dupecheck: SPI_connect returned %d", ret);
+
+       // Now we are connected to the database's SPI manager
+       // We will now construct a string of some important row values. 
+       // First, we determine how long the string will be to allocate memory
+       // To include an additional item, add another SPI_getvalue line and
+       // increase maxitems above by 1
+       
+       items[0] = SPI_getvalue(rettuple, tupdesc, SPI_fnumber(tupdesc, "creator"));
+       items[1] = SPI_getvalue(rettuple, tupdesc, SPI_fnumber(tupdesc, "title"));
+       items[2] = SPI_getvalue(rettuple, tupdesc, SPI_fnumber(tupdesc, "description"));
+
+       for (i=0; (i < maxitems); i++)
+       {
+               rowstrlen += strlen(items[i]);
+       }
+       rowstrlen++; // add space for 0-terminator
+       
+       rowstring = malloc(rowstrlen);
+       if (rowstring == NULL)
+       {
+               // Big problem.
+               return PointerGetDatum(NULL);
+       }
+
+       *rowstring = 0;
+       for (i=0; (i < maxitems); i++)
+       {
+               strcat(rowstring, items[i]);
+       }
+
+       // rowstring now contains the data of the maxitems important
+       // items of the table record. Now we calculate the CRC-32 checksum
+       // of the rowstring
+
+       crc = crc32(rowstring, rowstrlen - 1); 
+
+       // Now we allocate some space and construct the SQL query
+       query = malloc(47 + 11 + 2 + 1); // SELECT part + crc32 + "';" + 0-term
+       if (query == NULL)
+       {
+               // Big problem
+               return PointerGetDatum(NULL);
+       }
+       
+       sprintf(query, "SELECT count(*) FROM comment WHERE checksum='%ld';", crc);
+       ret = SPI_exec(query, 2);
+       num = SPI_getbinval(SPI_tuptable->vals[0], SPI_tuptable->tupdesc, 1, &isnull);
+
+       if ((ret == SPI_OK_SELECT) && (num > 0))
+       {
+               elog(NOTICE, "dupecheck: UBD prevented (dupe dropped)");
+               return PointerGetDatum(NULL);
+       }
+       else
+       {
+               // The checksum wasn't found. So we modify the tuple to be 
+               // inserted and add the fresh checksum.
+               int attnum;
+               Datum value;
+               char nulls = 0;
+               
+               elog(NOTICE, "dupecheck: Adding checksum to INSERT");
+               attnum = SPI_fnumber(tupdesc, "checksum");
+               value = (Datum) crc;
+               rettuple = SPI_modifytuple(trigdata->tg_relation, rettuple, 1, &attnum, &value, &nulls);
+       }
+
+       SPI_finish();
+       return PointerGetDatum(rettuple);
+}
+