Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix spaces removal on digests with control chars #4554

Merged
merged 4 commits into from
May 24, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions lib/c_tokenizer.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -1267,10 +1267,10 @@ void stage_1_parsing(shared_st* shared_st, stage_1_st* stage_1_st, options* opts
// Q: `SELECT\s\s 1`
// ^ address used to be replaced by next char
// ```
if (shared_st->prev_char == ' ' && is_space_char(*shared_st->q)) {
if (is_space_char(shared_st->prev_char) && is_space_char(*shared_st->q)) {
// if current position in result buffer is the first space found, we move to the next
// position, in order to respect the first space char.
if (*(shared_st->res_cur_pos-1) != ' ') {
if (!is_space_char(*(shared_st->res_cur_pos-1))) {
shared_st->res_cur_pos++;
}

Expand Down Expand Up @@ -2393,17 +2393,17 @@ char* mysql_query_digest_and_first_comment_one_it(char* q, int q_len, char** fst
// suppress all the double spaces.
// ==============================
//
// The supression is performed using the address of the second space found as the
// The suppression is performed using the address of the second space found as the
// pivoting point for further space suppression in the result buffer:
//
// ```
// Q: `SELECT\s\s 1`
// ^ address used to be replaced by next char
// ```
if (shared_st.prev_char == ' ' && is_space_char(*shared_st.q)) {
if (is_space_char(shared_st.prev_char) && is_space_char(*shared_st.q)) {
// if current position in result buffer is the first space found, we move to the next
// position, in order to respect the first space char.
if (*(shared_st.res_cur_pos-1) != ' ') {
if (!is_space_char(*(shared_st.res_cur_pos-1))) {
shared_st.res_cur_pos++;
}

Expand Down
8 changes: 5 additions & 3 deletions test/tap/tests/test_mysql_query_digests_stages-t.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -32,11 +32,11 @@
#include <random>
#include <vector>
#include <string>
#include <regex>

#include "json.hpp"
#include "proxysql.h"
#include "proxysql_utils.h"
#include "re2/re2.h"
#include "command_line.h"
#include "tap.h"

Expand Down Expand Up @@ -151,8 +151,10 @@ nlohmann::json get_tests_defs(const string& filepath) {
std::ifstream file_stream(filepath);
std::string test_file_contents((std::istreambuf_iterator<char>(file_stream)), (std::istreambuf_iterator<char>()));

std::regex comment_pattern { ".*\\/\\/.*[\\r\\n]" };
string test_file_no_comments { std::regex_replace(test_file_contents, comment_pattern, "") };
std::string comment_pattern { ".*\\/\\/.*[\\r\\n]" };
string test_file_no_comments { test_file_contents };

re2::RE2::GlobalReplace(&test_file_no_comments, comment_pattern, "");
nlohmann::json j_test_defs = nlohmann::json::parse(test_file_no_comments, nullptr, true);

return j_test_defs;
Expand Down
78 changes: 78 additions & 0 deletions test/tap/tests/tokenizer_payloads/regular_tokenizer_digests.hjson
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,84 @@
"s3": "select ?",
"s4": "select ?"
},
// Space compression; control characters, digits and literals
{
"q": [
"SELECT\r\n\t1",
"SELECT\r\n\t 1",
"SELECT \r\n\t1",
"SELECT \r\n\t 1",
"SELECT \r\n\t 1\r\n\t",
"SELECT \r\n\t 1 \r\n\t"
],
"s1": "SELECT ?",
"s2": "SELECT ?",
"s3": "SELECT ?",
"s4": "SELECT ?"
},
{
"q": [
"SELECT\n'foo',\n\t4\n\t",
"SELECT\n\t 'foo',\n\t4\n\t",
"SELECT\n\t 'foo' ,\n\t4\n\t",
"SELECT \n\t 'foo' ,\n\t4\n\t",
"SELECT \n\t 'foo' \n\t ,\n\t4\n\t",
"SELECT\n\t \n\t'foo',\n\t4\n\t",
"SELECT\n\t \n\t'foo',\n\t \n\t4\n\t",
"SELECT\n\t \n\t'foo',\n\t \n\t4\n\t"
],
"s2": "SELECT ?,?",
"s3": "SELECT ?,?",
"s4": "SELECT ?,?"
},
// Space compression; control characters, digits, literals and operators
{
"q": [
"SELECT\n\t-\t'1'",
"SELECT\n\t-\t'1'\n\t",
"SELECT\n\t -\t'1'\n\t",
"SELECT\n\t - \t'1'",
"SELECT\n\t -\n\t '1'",
"SELECT\n\t - \n\t '1' \n\t"
],
"s1": "SELECT - ?",
"s2": "SELECT ?",
"s3": "SELECT ?",
"s4": "SELECT ?"
},
{
"q": [ "SELECT (\n \t + \t\t 2 / 2 \t\t)" ],
"s1": "SELECT ( + ? / ? )"
},
{
"q": [ "SELECT (\t\t+2/2\t\t)" ],
"s1": "SELECT ( +?/? )"
},
{
"q": [
"SELECT (\t\t+2/2\t\t)",
"SELECT (\n \t + \t\t 2 / 2 \t\t)"
],
"s2": "SELECT (?/?)",
"s3": "SELECT (?/?)",
"s4": "SELECT (?/?)"
},
{
"q": [
"SELECT 1,\n-4",
"SELECT 1, \n-4",
"SELECT 1,\n -4",
"SELECT 1, \n -4",
"SELECT 'foo',\n\t-4",
"SELECT 'foo', \n\t-4",
"SELECT 'foo',\n\t -4",
"SELECT 'foo', \n\t -4"
],
"s1": "SELECT ?, -?",
"s2": "SELECT ?,?",
"s3": "SELECT ?,?",
"s4": "SELECT ?,?"
},
// Final spaces and ending query delimiters (';')
{
"q": [
Expand Down
Loading