From f4f73356ff49bfd871e0b586861a3f3d9c185035 Mon Sep 17 00:00:00 2001 From: Bingran Hu Date: Mon, 9 Dec 2024 18:30:14 +0000 Subject: [PATCH] Remove duplicate string utils functions in clp-s and use clp::string_utils --- .../core/src/clp_s/DictionaryReader.hpp | 6 +- components/core/src/clp_s/JsonParser.cpp | 3 +- .../src/clp_s/TimestampDictionaryReader.cpp | 5 +- components/core/src/clp_s/Utils.cpp | 283 +----------------- components/core/src/clp_s/Utils.hpp | 137 --------- components/core/src/clp_s/clp-s.cpp | 6 +- components/core/src/clp_s/search/Output.cpp | 8 +- .../core/src/clp_s/search/clp_search/Grep.cpp | 35 ++- .../core/src/clp_s/search/kql/CMakeLists.txt | 8 +- components/core/src/clp_s/search/kql/kql.cpp | 9 +- components/core/submodules/clp-cpp | 2 +- 11 files changed, 56 insertions(+), 446 deletions(-) diff --git a/components/core/src/clp_s/DictionaryReader.hpp b/components/core/src/clp_s/DictionaryReader.hpp index 175214d88..52de582ac 100644 --- a/components/core/src/clp_s/DictionaryReader.hpp +++ b/components/core/src/clp_s/DictionaryReader.hpp @@ -6,11 +6,13 @@ #include #include +#include #include "DictionaryEntry.hpp" -#include "Utils.hpp" namespace clp_s { +using clp::string_utils::wildcard_match_unsafe; + template class DictionaryReader { public: @@ -200,7 +202,7 @@ void DictionaryReader::get_entries_matching_wildcar std::unordered_set& entries ) const { for (auto const& entry : m_entries) { - if (StringUtils::wildcard_match_unsafe(entry.get_value(), wildcard_string, !ignore_case)) { + if (wildcard_match_unsafe(entry.get_value(), wildcard_string, !ignore_case)) { entries.insert(&entry); } } diff --git a/components/core/src/clp_s/JsonParser.cpp b/components/core/src/clp_s/JsonParser.cpp index 9e8293510..aee9e819b 100644 --- a/components/core/src/clp_s/JsonParser.cpp +++ b/components/core/src/clp_s/JsonParser.cpp @@ -3,6 +3,7 @@ #include #include +#include #include #include @@ -23,7 +24,7 @@ JsonParser::JsonParser(JsonParserOption const& option) if (false == m_timestamp_key.empty()) { if (false - == clp_s::StringUtils::tokenize_column_descriptor(m_timestamp_key, m_timestamp_column)) + == clp::string_utils::tokenize_column_descriptor(m_timestamp_key, m_timestamp_column)) { SPDLOG_ERROR("Can not parse invalid timestamp key: \"{}\"", m_timestamp_key); throw OperationFailed(ErrorCodeBadParam, __FILENAME__, __LINE__); diff --git a/components/core/src/clp_s/TimestampDictionaryReader.cpp b/components/core/src/clp_s/TimestampDictionaryReader.cpp index 15685a97e..fbcfacb87 100644 --- a/components/core/src/clp_s/TimestampDictionaryReader.cpp +++ b/components/core/src/clp_s/TimestampDictionaryReader.cpp @@ -1,9 +1,8 @@ #include "TimestampDictionaryReader.hpp" +#include #include -#include "Utils.hpp" - namespace clp_s { void TimestampDictionaryReader::open(std::string const& dictionary_path) { if (m_is_open) { @@ -44,7 +43,7 @@ void TimestampDictionaryReader::read_new_entries() { TimestampEntry entry; std::vector tokens; entry.try_read_from_file(m_dictionary_decompressor); - if (false == StringUtils::tokenize_column_descriptor(entry.get_key_name(), tokens)) { + if (false == clp::string_utils::tokenize_column_descriptor(entry.get_key_name(), tokens)) { throw OperationFailed(ErrorCodeCorrupt, __FILENAME__, __LINE__); } m_entries.emplace_back(std::move(entry)); diff --git a/components/core/src/clp_s/Utils.cpp b/components/core/src/clp_s/Utils.cpp index acee48851..fa1f7e603 100644 --- a/components/core/src/clp_s/Utils.cpp +++ b/components/core/src/clp_s/Utils.cpp @@ -1,12 +1,16 @@ #include "Utils.hpp" #include +#include #include +namespace clp_s { using std::string; using std::string_view; +using clp::string_utils::is_alphabet; +using clp::string_utils::is_decimal_digit; +using clp::string_utils::is_delim; -namespace clp_s { bool FileUtils::find_all_files(std::string const& path, std::vector& file_paths) { try { if (false == boost::filesystem::is_directory(path)) { @@ -110,68 +114,6 @@ bool StringUtils::get_bounds_of_next_var(string const& msg, size_t& begin_pos, s return (msg_length != begin_pos); } -size_t StringUtils::find_first_of( - string const& haystack, - char const* needles, - size_t search_start_pos, - size_t& needle_ix -) { - size_t haystack_length = haystack.length(); - size_t needles_length = strlen(needles); - for (size_t i = search_start_pos; i < haystack_length; ++i) { - for (needle_ix = 0; needle_ix < needles_length; ++needle_ix) { - if (haystack[i] == needles[needle_ix]) { - return i; - } - } - } - - return string::npos; -} - -string StringUtils::replace_characters( - char const* characters_to_escape, - char const* replacement_characters, - string const& value, - bool escape -) { - string new_value; - size_t search_start_pos = 0; - while (true) { - size_t replace_char_ix; - size_t char_to_replace_pos - = find_first_of(value, characters_to_escape, search_start_pos, replace_char_ix); - if (string::npos == char_to_replace_pos) { - new_value.append(value, search_start_pos, string::npos); - break; - } else { - new_value.append(value, search_start_pos, char_to_replace_pos - search_start_pos); - if (escape) { - new_value += "\\"; - } - new_value += replacement_characters[replace_char_ix]; - search_start_pos = char_to_replace_pos + 1; - } - } - return new_value; -} - -void StringUtils::to_lower(string& str) { - std::transform(str.cbegin(), str.cend(), str.begin(), [](unsigned char c) { - return std::tolower(c); - }); -} - -bool StringUtils::is_wildcard(char c) { - static constexpr char cWildcards[] = "?*"; - for (size_t i = 0; i < strlen(cWildcards); ++i) { - if (cWildcards[i] == c) { - return true; - } - } - return false; -} - bool StringUtils::has_unescaped_wildcards(std::string const& str) { for (size_t i = 0; i < str.size(); ++i) { if ('*' == str[i] || '?' == str[i]) { @@ -184,42 +126,6 @@ bool StringUtils::has_unescaped_wildcards(std::string const& str) { return false; } -string StringUtils::clean_up_wildcard_search_string(string_view str) { - string cleaned_str; - - bool is_escaped = false; - auto str_end = str.cend(); - for (auto current = str.cbegin(); current != str_end;) { - auto c = *current; - if (is_escaped) { - is_escaped = false; - - if (is_wildcard(c) || '\\' == c) { - // Keep escaping if c is a wildcard character or an escape character - cleaned_str += '\\'; - } - cleaned_str += c; - ++current; - } else if ('*' == c) { - cleaned_str += c; - - // Skip over all '*' to find the next non-'*' - do { - ++current; - } while (current != str_end && '*' == *current); - } else { - if ('\\' == c) { - is_escaped = true; - } else { - cleaned_str += c; - } - ++current; - } - } - - return cleaned_str; -} - bool StringUtils::advance_tame_to_next_match( char const*& tame_current, char const*& tame_bookmark, @@ -261,154 +167,6 @@ bool StringUtils::advance_tame_to_next_match( return true; } -bool StringUtils::wildcard_match_unsafe( - string_view tame, - string_view wild, - bool case_sensitive_match -) { - if (case_sensitive_match) { - return wildcard_match_unsafe_case_sensitive(tame, wild); - } else { - // We convert to lowercase (rather than uppercase) anticipating that - // callers use lowercase more frequently, so little will need to change. - string lowercase_tame(tame); - to_lower(lowercase_tame); - string lowercase_wild(wild); - to_lower(lowercase_wild); - return wildcard_match_unsafe_case_sensitive(lowercase_tame, lowercase_wild); - } -} - -/** - * The algorithm basically works as follows: - * Given a wild string "*abc*def*ghi*", it can be broken into groups of - * characters delimited by one or more '*' characters. The goal of the - * algorithm is then to determine whether the tame string contains each of - * those groups in the same order. - * - * Thus, the algorithm: - * 1. searches for the start of one of these groups in wild, - * 2. searches for a group in tame starting with the same character, and then - * 3. checks if the two match. If not, the search repeats with the next group in - * tame. - */ -bool StringUtils::wildcard_match_unsafe_case_sensitive(string_view tame, string_view wild) { - auto const tame_length = tame.length(); - auto const wild_length = wild.length(); - char const* tame_current = tame.data(); - char const* wild_current = wild.data(); - char const* tame_bookmark = nullptr; - char const* wild_bookmark = nullptr; - char const* tame_end = tame_current + tame_length; - char const* wild_end = wild_current + wild_length; - - // Handle wild or tame being empty - if (0 == wild_length) { - return 0 == tame_length; - } else { - if (0 == tame_length) { - return "*" == wild; - } - } - - char w; - char t; - bool is_escaped = false; - while (true) { - w = *wild_current; - if ('*' == w) { - ++wild_current; - if (wild_end == wild_current) { - // Trailing '*' means everything remaining in tame will match - return true; - } - - // Set wild and tame bookmarks - wild_bookmark = wild_current; - if (!advance_tame_to_next_match( - tame_current, - tame_bookmark, - tame_end, - wild_current, - wild_bookmark - )) - { - return false; - } - } else { - // Handle escaped characters - if ('\\' == w) { - is_escaped = true; - ++wild_current; - // This is safe without a bounds check since this the caller - // ensures there are no dangling escape characters - w = *wild_current; - } - - // Handle a mismatch - t = *tame_current; - if (false == ((false == is_escaped && '?' == w) || t == w)) { - if (nullptr == wild_bookmark) { - // No bookmark to return to - return false; - } - - wild_current = wild_bookmark; - tame_current = tame_bookmark + 1; - if (!advance_tame_to_next_match( - tame_current, - tame_bookmark, - tame_end, - wild_current, - wild_bookmark - )) - { - return false; - } - } - } - - ++tame_current; - ++wild_current; - - // Handle reaching the end of tame or wild - if (tame_end == tame_current) { - return (wild_end == wild_current - || ('*' == *wild_current && (wild_current + 1) == wild_end)); - } else { - if (wild_end == wild_current) { - if (nullptr == wild_bookmark) { - // No bookmark to return to - return false; - } else { - wild_current = wild_bookmark; - tame_current = tame_bookmark + 1; - if (!advance_tame_to_next_match( - tame_current, - tame_bookmark, - tame_end, - wild_current, - wild_bookmark - )) - { - return false; - } - } - } - } - } -} - -bool StringUtils::convert_string_to_int64(std::string_view raw, int64_t& converted) { - auto raw_end = raw.cend(); - auto result = std::from_chars(raw.cbegin(), raw_end, converted); - if (raw_end != result.ptr) { - return false; - } else { - return result.ec == std::errc(); - } -} - bool StringUtils::convert_string_to_double(std::string const& raw, double& converted) { if (raw.empty()) { // Can't convert an empty string @@ -426,35 +184,4 @@ bool StringUtils::convert_string_to_double(std::string const& raw, double& conve converted = raw_as_double; return true; } - -bool StringUtils::tokenize_column_descriptor( - std::string const& descriptor, - std::vector& tokens -) { - // TODO: add support for unicode sequences e.g. \u263A - std::string cur_tok; - for (size_t cur = 0; cur < descriptor.size(); ++cur) { - if ('\\' == descriptor[cur]) { - ++cur; - if (cur >= descriptor.size()) { - return false; - } - } else if ('.' == descriptor[cur]) { - if (cur_tok.empty()) { - return false; - } - tokens.push_back(cur_tok); - cur_tok.clear(); - continue; - } - cur_tok.push_back(descriptor[cur]); - } - - if (cur_tok.empty()) { - return false; - } - - tokens.push_back(cur_tok); - return true; -} } // namespace clp_s diff --git a/components/core/src/clp_s/Utils.hpp b/components/core/src/clp_s/Utils.hpp index d6deb3280..f7800fdc0 100644 --- a/components/core/src/clp_s/Utils.hpp +++ b/components/core/src/clp_s/Utils.hpp @@ -28,34 +28,6 @@ class FileUtils { class StringUtils { public: - /** - * Checks if the given character is an alphabet - * @param c - * @return true if c is an alphabet, false otherwise - */ - static inline bool is_alphabet(char c) { - return ('a' <= c && c <= 'z') || ('A' <= c && c <= 'Z'); - } - - /** - * Checks if character is a decimal (base-10) digit - * @param c - * @return true if c is a decimal digit, false otherwise - */ - static inline bool is_decimal_digit(char c) { return '0' <= c && c <= '9'; } - - /** - * Checks if character is a hexadecimal (base-16) digit - * @param c - * @return true if c is a hexadecimal digit, false otherwise - */ - static inline bool is_delim(char c) { - return !( - '+' == c || ('-' <= c && c <= '9') || ('A' <= c && c <= 'Z') || '\\' == c - || '_' == c || ('a' <= c && c <= 'z') - ); - } - /** * Checks if the string could be a hexadecimal value * @param str @@ -92,62 +64,6 @@ class StringUtils { */ static bool get_bounds_of_next_var(std::string const& msg, size_t& begin_pos, size_t& end_pos); - /** - * Searches haystack starting at the given position for one of the given needles - * @param haystack - * @param needles - * @param search_start_pos - * @param needle_ix The index of the needle found - * @return The position of the match or string::npos if none - */ - static size_t find_first_of( - std::string const& haystack, - char const* needles, - size_t search_start_pos, - size_t& needle_ix - ); - - /** - * Replaces the given characters in the given value with the given replacements - * @param characters_to_escape - * @param replacement_characters - * @param value - * @param escape Whether to precede the replacement with a '\' (e.g., so that a - * line-feed character is output as "\n") - * @return The string with replacements - */ - static std::string replace_characters( - char const* characters_to_escape, - char const* replacement_characters, - std::string const& value, - bool escape - ); - - /** - * Converts a string to lowercase - * @param str - */ - static void to_lower(std::string& str); - - /** - * Cleans wildcard search string - *
    - *
  • Removes consecutive '*'
    • - *
  • Removes escaping from non-wildcard characters
    • - *
  • Removes dangling escape character from the end of the string
    • - *
- * @param str Wildcard search string to clean - * @return Cleaned wildcard search string - */ - static std::string clean_up_wildcard_search_string(std::string_view str); - - /** - * Checks if character is a wildcard - * @param c - * @return true if c is a wildcard, false otherwise - */ - static bool is_wildcard(char c); - /** * Checks if the given string has unescaped wildcards * @param str @@ -155,50 +71,6 @@ class StringUtils { */ static bool has_unescaped_wildcards(std::string const& str); - /** - * Same as ``wildcard_match_unsafe_case_sensitive`` except this method - * allows the caller to specify whether the match should be case sensitive. - * - * @param tame The literal string - * @param wild The wildcard string - * @param case_sensitive_match Whether to consider case when matching - * @return Whether the two strings match - */ - static bool wildcard_match_unsafe( - std::string_view tame, - std::string_view wild, - bool case_sensitive_match = true - ); - - /** - * Checks if a string matches a wildcard string. Two wildcards are currently - * supported: '*' to match 0 or more characters, and '?' to match any single - * character. Each can be escaped using a preceding '\'. Other characters which - * are escaped are treated as normal characters. - *
- * This method is optimized for performance by omitting some checks on the - * wildcard string that are unnecessary if the caller cleans up the wildcard - * string as follows: - *
    - *
  • The wildcard string should not contain consecutive '*'.
    • - *
  • The wildcard string should not contain an escape character without a - * character following it.
    • - *
- * - * @param tame The literal string - * @param wild The wildcard string - * @return Whether the two strings match - */ - static bool wildcard_match_unsafe_case_sensitive(std::string_view tame, std::string_view wild); - - /** - * Converts the given string to a 64-bit integer if possible - * @param raw - * @param converted - * @return true if the conversion was successful, false otherwise - */ - static bool convert_string_to_int64(std::string_view raw, int64_t& converted); - /** * Converts the given string to a double if possible * @param raw @@ -207,15 +79,6 @@ class StringUtils { */ static bool convert_string_to_double(std::string const& raw, double& converted); - /** - * Converts a string column descriptor delimited by '.' into a list of tokens - * @param descriptor - * @param tokens - * @return true if the descriptor was tokenized successfully, false otherwise - */ - [[nodiscard]] static bool - tokenize_column_descriptor(std::string const& descriptor, std::vector& tokens); - private: /** * Helper for ``wildcard_match_unsafe_case_sensitive`` to advance the diff --git a/components/core/src/clp_s/clp-s.cpp b/components/core/src/clp_s/clp-s.cpp index a74693e33..377e0fc80 100644 --- a/components/core/src/clp_s/clp-s.cpp +++ b/components/core/src/clp_s/clp-s.cpp @@ -6,6 +6,7 @@ #include #include +#include #include #include #include @@ -33,14 +34,13 @@ #include "search/SchemaMatch.hpp" #include "TimestampPattern.hpp" #include "TraceableException.hpp" -#include "Utils.hpp" using namespace clp_s::search; +using clp::string_utils::tokenize_column_descriptor; using clp_s::cArchiveFormatDevelopmentVersionFlag; using clp_s::cEpochTimeMax; using clp_s::cEpochTimeMin; using clp_s::CommandLineArguments; -using clp_s::StringUtils; namespace { /** @@ -192,7 +192,7 @@ bool search_archive( try { for (auto const& column : command_line_arguments.get_projection_columns()) { std::vector descriptor_tokens; - if (false == StringUtils::tokenize_column_descriptor(column, descriptor_tokens)) { + if (false == tokenize_column_descriptor(column, descriptor_tokens)) { SPDLOG_ERROR("Can not tokenize invalid column: \"{}\"", column); return false; } diff --git a/components/core/src/clp_s/search/Output.cpp b/components/core/src/clp_s/search/Output.cpp index c9954779b..ef2b6eae8 100644 --- a/components/core/src/clp_s/search/Output.cpp +++ b/components/core/src/clp_s/search/Output.cpp @@ -3,6 +3,8 @@ #include #include +#include + #include "../../clp/type_utils.hpp" #include "../Utils.hpp" #include "AndExpr.hpp" @@ -17,6 +19,8 @@ #define eval(op, a, b) (((op) == FilterOperation::EQ) ? ((a) == (b)) : ((a) != (b))) namespace clp_s::search { +using clp::string_utils::wildcard_match_unsafe; + bool Output::filter() { auto top_level_expr = m_expr; @@ -484,7 +488,7 @@ bool Output::evaluate_clp_string_filter( for (auto const& subquery : q->get_sub_queries()) { if (subquery.matches_logtype(id) && subquery.matches_vars(vars)) { if (subquery.wildcard_match_required()) { - matched = StringUtils::wildcard_match_unsafe( + matched = wildcard_match_unsafe( std::get(reader->extract_value(m_cur_message)), q->get_search_string(), !q->get_ignore_case() @@ -496,7 +500,7 @@ bool Output::evaluate_clp_string_filter( } } } else { - matched = StringUtils::wildcard_match_unsafe( + matched = wildcard_match_unsafe( std::get(reader->extract_value(m_cur_message)), q->get_search_string(), !q->get_ignore_case() diff --git a/components/core/src/clp_s/search/clp_search/Grep.cpp b/components/core/src/clp_s/search/clp_search/Grep.cpp index 40ffb456f..f2b39c300 100644 --- a/components/core/src/clp_s/search/clp_search/Grep.cpp +++ b/components/core/src/clp_s/search/clp_search/Grep.cpp @@ -6,14 +6,21 @@ #include #include -#include "../../Utils.hpp" +#include + #include "../../VariableEncoder.hpp" #include "EncodedVariableInterpreter.hpp" +namespace clp_s::search::clp_search { +using clp::string_utils::clean_up_wildcard_search_string; +using clp::string_utils::is_alphabet; +using clp::string_utils::is_decimal_digit; +using clp::string_utils::is_delim; +using clp::string_utils::is_wildcard; +using clp::string_utils::wildcard_match_unsafe; using std::string; using std::vector; -namespace clp_s::search::clp_search { // Local types enum class SubQueryMatchabilityResult { MayMatch, // The subquery might match a message @@ -422,13 +429,13 @@ std::optional Grep::process_raw_query( } // Clean-up search string - processed_search_string = StringUtils::clean_up_wildcard_search_string(processed_search_string); + processed_search_string = clean_up_wildcard_search_string(processed_search_string); // Replace non-greedy wildcards with greedy wildcards since we currently have no support for // searching compressed files with non-greedy wildcards std::replace(processed_search_string.begin(), processed_search_string.end(), '?', '*'); // Clean-up in case any instances of "?*" or "*?" were changed into "**" - processed_search_string = StringUtils::clean_up_wildcard_search_string(processed_search_string); + processed_search_string = clean_up_wildcard_search_string(processed_search_string); // Split search_string into tokens with wildcards vector query_tokens; @@ -528,7 +535,7 @@ bool Grep::get_bounds_of_next_potential_var( if (is_escaped) { is_escaped = false; - if (StringUtils::is_delim(c)) { + if (is_delim(c)) { // Found escaped non-delimiter, so reverse the index to retain the escape // character --begin_pos; @@ -538,11 +545,11 @@ bool Grep::get_bounds_of_next_potential_var( // Escape character is_escaped = true; } else { - if (StringUtils::is_wildcard(c)) { + if (is_wildcard(c)) { contains_wildcard = true; break; } - if (false == StringUtils::is_delim(c)) { + if (false == is_delim(c)) { break; } } @@ -560,7 +567,7 @@ bool Grep::get_bounds_of_next_potential_var( if (is_escaped) { is_escaped = false; - if (StringUtils::is_delim(c)) { + if (is_delim(c)) { // Found escaped delimiter, so reverse the index to retain the escape // character --end_pos; @@ -570,17 +577,17 @@ bool Grep::get_bounds_of_next_potential_var( // Escape character is_escaped = true; } else { - if (StringUtils::is_wildcard(c)) { + if (is_wildcard(c)) { contains_wildcard = true; - } else if (StringUtils::is_delim(c)) { + } else if (is_delim(c)) { // Found delimiter that's not also a wildcard break; } } - if (StringUtils::is_decimal_digit(c)) { + if (is_decimal_digit(c)) { contains_decimal_digit = true; - } else if (StringUtils::is_alphabet(c)) { + } else if (is_alphabet(c)) { contains_alphabet = true; } } @@ -604,13 +611,13 @@ bool Grep::get_bounds_of_next_potential_var( if (is_escaped) { is_escaped = false; - if (StringUtils::is_alphabet(c)) { + if (is_alphabet(c)) { break; } } else if ('\\' == c) { // Escape character is_escaped = true; - } else if (StringUtils::is_wildcard(c)) { + } else if (is_wildcard(c)) { found_wildcard_before_alphabet = true; break; } diff --git a/components/core/src/clp_s/search/kql/CMakeLists.txt b/components/core/src/clp_s/search/kql/CMakeLists.txt index ee36ee124..a8593bd37 100644 --- a/components/core/src/clp_s/search/kql/CMakeLists.txt +++ b/components/core/src/clp_s/search/kql/CMakeLists.txt @@ -7,7 +7,6 @@ ANTLR_TARGET( add_library( kql - ../../Utils.hpp ../AndExpr.hpp ../BooleanLiteral.hpp ../ColumnDescriptor.hpp @@ -25,4 +24,9 @@ add_library( ) target_compile_features(kql PRIVATE cxx_std_20) target_include_directories(kql PRIVATE ${ANTLR_KqlParser_OUTPUT_DIR}) -target_link_libraries(kql PRIVATE antlr4_static Boost::filesystem) +target_link_libraries(kql + PRIVATE + antlr4_static + Boost::filesystem + clp::string_utils +) diff --git a/components/core/src/clp_s/search/kql/kql.cpp b/components/core/src/clp_s/search/kql/kql.cpp index 972e44ad7..312dad9c7 100644 --- a/components/core/src/clp_s/search/kql/kql.cpp +++ b/components/core/src/clp_s/search/kql/kql.cpp @@ -3,6 +3,7 @@ #include #include +#include #include #include "KqlBaseVisitor.h" @@ -11,7 +12,6 @@ // If redlining may want to add ${workspaceFolder}/build/** // to include path for vscode C/C++ utils -#include "../../Utils.hpp" #include "../AndExpr.hpp" #include "../BooleanLiteral.hpp" #include "../ColumnDescriptor.hpp" @@ -27,6 +27,9 @@ using namespace antlr4; using namespace kql; namespace clp_s::search::kql { +using clp::string_utils::clean_up_wildcard_search_string; +using clp::string_utils::tokenize_column_descriptor; + class ErrorListener : public BaseErrorListener { public: void syntaxError( @@ -92,7 +95,7 @@ class ParseTreeVisitor : public KqlBaseVisitor { } else if (auto ret = NullLiteral::create_from_string(token)) { return ret; } else { - return StringLiteral::create(StringUtils::clean_up_wildcard_search_string(token)); + return StringLiteral::create(clean_up_wildcard_search_string(token)); } } @@ -112,7 +115,7 @@ class ParseTreeVisitor : public KqlBaseVisitor { std::string column = unquote_string(ctx->LITERAL()->getText()); std::vector descriptor_tokens; - if (false == StringUtils::tokenize_column_descriptor(column, descriptor_tokens)) { + if (false == tokenize_column_descriptor(column, descriptor_tokens)) { SPDLOG_ERROR("Can not tokenize invalid column: \"{}\"", column); return nullptr; } diff --git a/components/core/submodules/clp-cpp b/components/core/submodules/clp-cpp index 852b07533..e39f7688f 160000 --- a/components/core/submodules/clp-cpp +++ b/components/core/submodules/clp-cpp @@ -1 +1 @@ -Subproject commit 852b075335ae5fcfb4e2843798b16cd2e1209a26 +Subproject commit e39f7688fc3798e87bd3372995c04a00b4508ed0