init

1 files changed, 54 insertions, 0 deletions

diff --git a/db_init.c b/db_init.c
new file mode 100644
index 0000000..b3a93db
--- /dev/null
+++ b/db_init.c
@@ -0,0 +1,54 @@
+#include <stdio.h>
+#include <sqlite3.h>
+#include "db_init.h"
+
+static const char *SCHEMA =
+	"PRAGMA journal_mode = WAL;"
+	"PRAGMA busy_timeout = 5000;"
+	"CREATE TABLE IF NOT EXISTS urls ("
+	"    id      INTEGER PRIMARY KEY,"
+	"    url     TEXT UNIQUE NOT NULL,"
+	"    status  TEXT NOT NULL DEFAULT 'pending'"
+	"            CHECK (status IN ('pending','in_progress','done','failed','skipped'))"
+	");"
+	"CREATE INDEX IF NOT EXISTS idx_urls_status ON urls(status);"
+	"CREATE TABLE IF NOT EXISTS links ("
+	"    from_id INTEGER NOT NULL REFERENCES urls(id),"
+	"    to_id   INTEGER NOT NULL REFERENCES urls(id),"
+	"    UNIQUE(from_id, to_id)"
+	");"
+	/* crash recovery: anything left mid-fetch from a previous run goes back to pending */
+	"UPDATE urls SET status = 'pending' WHERE status = 'in_progress';";
+
+/* Opens (creating if needed) and initializes the DB. Returns NULL on failure. */
+sqlite3 *db_init(const char *path) {
+	sqlite3 *db;
+	if (sqlite3_open(path, &db) != SQLITE_OK) {
+		fprintf(stderr, "db_init: cannot open %s: %s\n", path, sqlite3_errmsg(db));
+		sqlite3_close(db);
+		return NULL;
+	}
+	
+	char *err = NULL;
+	if (sqlite3_exec(db, SCHEMA, NULL, NULL, &err) != SQLITE_OK) {
+		fprintf(stderr, "db_init: schema error: %s\n", err);
+		sqlite3_free(err);
+		sqlite3_close(db);
+		return NULL;
+	}
+	
+	return db;
+}
+
+/* Each worker thread should open its own connection with the same PRAGMAs
+ * (WAL is persisted in the file, but busy_timeout is per-connection): */
+sqlite3 *db_open_worker(const char *path) {
+	sqlite3 *db;
+	if (sqlite3_open(path, &db) != SQLITE_OK) {
+		fprintf(stderr, "db_open_worker: cannot open %s: %s\n", path, sqlite3_errmsg(db));
+		sqlite3_close(db);
+		return NULL;
+	}
+	sqlite3_exec(db, "PRAGMA busy_timeout = 5000;", NULL, NULL, NULL);
+	return db;
+}