![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
diff --git a/src/parser/scanner.l b/src/parser/scanner.l
--- /dev/null
+++ b/src/parser/scanner.l
@@ -0,0 +1,308 @@
+/*
+ * SysDB - src/parser/scanner.l
+ * Copyright (C) 2013-2015 Sebastian 'tokkee' Harl <sh@tokkee.org>
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR
+ * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+ * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+%{
+
+#if HAVE_CONFIG_H
+# include "config.h"
+#endif /* HAVE_CONFIG_H */
+
+#include "core/data.h"
+
+#include "parser/parser.h"
+#include "parser/grammar.h"
+
+#include "utils/error.h"
+
+#include <assert.h>
+#include <errno.h>
+
+#include <string.h>
+#include <stdlib.h>
+
+#include <time.h>
+
+#define YY_EXTRA_TYPE sdb_parser_yyextra_t *
+
+static struct {
+ const char *name;
+ int id;
+} reserved_words[] = {
+ { "ALL", ALL },
+ { "AND", AND },
+ { "ANY", ANY },
+ { "END", END },
+ { "FETCH", FETCH },
+ { "FILTER", FILTER },
+ { "IN", IN },
+ { "IS", IS },
+ { "LAST", LAST },
+ { "LIST", LIST },
+ { "LOOKUP", LOOKUP },
+ { "MATCHING", MATCHING },
+ { "NOT", NOT },
+ { "NULL", NULL_T },
+ { "OR", OR },
+ { "START", START },
+ { "STORE", STORE },
+ { "TIMESERIES", TIMESERIES },
+ { "UPDATE", UPDATE },
+
+ /* object types */
+ { "host", HOST_T },
+ { "hosts", HOSTS_T },
+ { "service", SERVICE_T },
+ { "services", SERVICES_T },
+ { "metric", METRIC_T },
+ { "metrics", METRICS_T },
+ { "attribute", ATTRIBUTE_T },
+ { "attributes", ATTRIBUTES_T },
+ /* queryable fields */
+ { "name", NAME_T },
+ { "last_update", LAST_UPDATE_T },
+ { "age", AGE_T },
+ { "interval", INTERVAL_T },
+ { "backend", BACKEND_T },
+ { "value", VALUE_T },
+};
+
+void
+sdb_parser_yyerror(YYLTYPE *lval, sdb_parser_yyscan_t scanner, const char *msg);
+
+%}
+
+%option never-interactive
+%option reentrant
+%option bison-bridge
+%option bison-locations
+%option 8bit
+%option yylineno
+%option nodefault
+%option noinput
+%option nounput
+%option noyywrap
+%option verbose
+%option warn
+%option prefix="sdb_parser_yy" outfile="lex.yy.c"
+
+%x CSC
+
+whitespace ([ \t\n\r\f]+)
+simple_comment ("--"[^\n\r]*)
+
+/*
+ * C style comments
+ */
+csc_start \/\*
+csc_inside ([^*/]+|[^*]\/|\*[^/])
+csc_end \*\/
+
+/*
+ * Strings and identifiers.
+ */
+identifier ([A-Za-z_][A-Za-z_0-9$]*)
+/* TODO: fully support SQL strings */
+string ('([^']|'')*')
+
+/*
+ * Numeric constants.
+ */
+dec ([\+\-]?[0-9]+)
+exp ([\+\-]?[0-9]+[Ee]\+?[0-9]+)
+integer ({dec}|{exp})
+float1 ([\+\-]?[0-9]+\.[0-9]*([Ee][\+\-]?[0-9]+)?)
+float2 ([\+\-]?[0-9]*\.[0-9]+([Ee][\+\-]?[0-9]+)?)
+float3 ([\+\-]?[0-9]+[Ee]\-[0-9]+)
+float4 ([\+\-]?[Ii][Nn][Ff]([Ii][Nn][Ii][Tt][Yy])?)
+float5 ([Nn][Aa][Nn])
+float ({float1}|{float2}|{float3}|{float4}|{float5})
+
+/*
+ * Time constants.
+ */
+date ([0-9]{4}-[0-9]{2}-[0-9]{2})
+time ([0-9]{1,2}:[0-9]{1,2}(:[0-9]{1,2}(\.[0-9]{1,9})?)?)
+
+%%
+
+{whitespace} |
+{simple_comment} { /* ignore */ }
+
+{csc_start} { BEGIN(CSC); }
+<CSC>{csc_inside} { /* ignore */ }
+<CSC>{csc_end} { BEGIN(INITIAL); }
+<CSC><<EOF>> {
+ sdb_parser_yyerror(yylloc, yyscanner, "unterminated C-style comment");
+ return SCANNER_ERROR;
+ }
+
+{identifier} {
+ size_t i;
+ for (i = 0; i < SDB_STATIC_ARRAY_LEN(reserved_words); ++i)
+ if (! strcasecmp(reserved_words[i].name, yytext))
+ return reserved_words[i].id;
+
+ yylval->str = strdup(yytext);
+ return IDENTIFIER;
+ }
+{string} {
+ char *quot;
+ size_t len;
+
+ /* remove the leading and trailing quote */
+ yytext[yyleng - 1] = '\0';
+ yylval->str = strdup(yytext + 1);
+
+ quot = yylval->str;
+ len = yyleng - 2;
+ while ((quot = strstr(quot, "''")) != NULL) {
+ memmove(quot, quot + 1, len - (quot - yylval->str) - 1);
+ yylval->str[len - 1] = '\0';
+ --len;
+ ++quot;
+ }
+ return STRING;
+ }
+{integer} {
+ yylval->data.data.integer = (int64_t)strtoll(yytext, NULL, 10);
+ yylval->data.type = SDB_TYPE_INTEGER;
+ return INTEGER;
+ }
+{float} {
+ yylval->data.data.decimal = strtod(yytext, NULL);
+ yylval->data.type = SDB_TYPE_DECIMAL;
+ return FLOAT;
+ }
+
+{date} {
+ struct tm tm;
+ memset(&tm, 0, sizeof(tm));
+ if (! strptime(yytext, "%Y-%m-%d", &tm)) {
+ char errmsg[1024];
+ snprintf(errmsg, sizeof(errmsg),
+ "Failed to parse '%s' as date", yytext);
+ sdb_parser_yyerror(yylloc, yyscanner, errmsg);
+ return SCANNER_ERROR;
+ }
+ yylval->datetime = SECS_TO_SDB_TIME(mktime(&tm));
+ return DATE;
+ }
+{time} {
+ struct tm tm;
+ char time[9], ns[10];
+ char *tmp;
+ int t;
+
+ memset(&tm, 0, sizeof(tm));
+ memset(time, '\0', sizeof(time));
+ memset(ns, '0', sizeof(ns));
+ ns[sizeof(ns) - 1] = '\0';
+
+ tmp = strchr(yytext, '.');
+ if (tmp) {
+ size_t i;
+ *tmp = '\0';
+ ++tmp;
+ strncpy(ns, tmp, sizeof(ns));
+ for (i = strlen(ns); i < 9; ++i)
+ ns[i] = '0';
+ }
+ strncpy(time, yytext, sizeof(time));
+ if (tmp) {
+ /* reset for better error messages */
+ --tmp;
+ *tmp = '.';
+ }
+
+ tmp = strchr(time, ':');
+ assert(tmp);
+ tmp = strchr(tmp + 1, ':');
+ if (! tmp)
+ strncat(time, ":00", sizeof(time) - strlen(time) - 1);
+
+ if (! strptime(time, "%H:%M:%S", &tm)) {
+ char errmsg[1024];
+ snprintf(errmsg, sizeof(errmsg),
+ "Failed to parse '%s' as time", yytext);
+ sdb_parser_yyerror(yylloc, yyscanner, errmsg);
+ return SCANNER_ERROR;
+ }
+
+ t = tm.tm_sec + 60 * tm.tm_min + 3600 * tm.tm_hour;
+ yylval->datetime = SECS_TO_SDB_TIME(t);
+ yylval->datetime += (sdb_time_t)strtoll(ns, NULL, 10);
+ return TIME;
+ }
+
+= { return CMP_EQUAL; }
+!= { return CMP_NEQUAL; }
+=~ { return CMP_REGEX; }
+!~ { return CMP_NREGEX; }
+\< { return CMP_LT; }
+\<= { return CMP_LE; }
+\>= { return CMP_GE; }
+\> { return CMP_GT; }
+\|\| { return CONCAT; }
+
+. { /* XXX: */ return yytext[0]; }
+
+%%
+
+sdb_parser_yyscan_t
+sdb_parser_scanner_init(const char *str, int len, sdb_parser_yyextra_t *yyext)
+{
+ yyscan_t scanner;
+
+ if (! str)
+ return NULL;
+
+ if (sdb_parser_yylex_init(&scanner)) {
+ char errbuf[1024];
+ sdb_strbuf_sprintf(yyext->errbuf, "yylex_init_failed: %s",
+ sdb_strerror(errno, errbuf, sizeof(errbuf)));
+ return NULL;
+ }
+
+ sdb_parser_yyset_extra(yyext, scanner);
+
+ if (len < 0)
+ len = strlen(str);
+
+ /* the newly allocated buffer state (YY_BUFFER_STATE) is stored inside the
+ * scanner and, thus, will be freed by yylex_destroy */
+ sdb_parser_yy_scan_bytes(str, len, scanner);
+ return scanner;
+} /* sdb_parser_scanner_init */
+
+void
+sdb_parser_scanner_destroy(sdb_parser_yyscan_t scanner)
+{
+ sdb_parser_yylex_destroy(scanner);
+} /* sdb_parser_scanner_destroy */
+
+/* vim: set tw=78 sw=4 ts=4 noexpandtab : */
+