From 2eb63649bdd884293cc604eb3534e6ea1aea1ad4 Mon Sep 17 00:00:00 2001
From: zvonand <azvonov@altinity.com>
Date: Fri, 22 Sep 2023 00:30:46 +0200
Subject: [PATCH] fix old workflows

---
 src/Storages/HDFS/StorageHDFS.cpp | 42 ++++++++------------------
 src/Storages/StorageFile.cpp      | 49 ++++++++++---------------------
 2 files changed, 29 insertions(+), 62 deletions(-)

diff --git a/src/Storages/HDFS/StorageHDFS.cpp b/src/Storages/HDFS/StorageHDFS.cpp
index 8563a777bb2..ac2635aafaf 100644
--- a/src/Storages/HDFS/StorageHDFS.cpp
+++ b/src/Storages/HDFS/StorageHDFS.cpp
@@ -137,41 +137,25 @@ namespace
         const HDFSFSPtr & fs,
         const String & for_match)
     {
+        /// regexp for {expr1,expr2,expr3} or {M..N}, where M and N - non-negative integers, expr's should be without "{", "}", "*" and ","
+        static const re2::RE2 enum_or_range(R"({([\d]+\.\.[\d]+|[^{}*,]+,[^{}*]*[^{}*,])})");
+
+        std::string_view for_match_view(for_match);
+        std::string_view matched;
+        if (RE2::FindAndConsume(&for_match_view, enum_or_range, &matched))
+        {
+            std::string buffer(matched);
+            if (buffer.find(',') != std::string::npos)
+                return expandSelector(path_for_ls, fs, for_match);
+        }
+
         const size_t first_glob_pos = for_match.find_first_of("*?{");
-        const bool has_glob = first_glob_pos != std::string::npos;
 
         const size_t end_of_path_without_globs = for_match.substr(0, first_glob_pos).rfind('/');
         const String suffix_with_globs = for_match.substr(end_of_path_without_globs);   /// begin with '/'
         const String prefix_without_globs = path_for_ls + for_match.substr(1, end_of_path_without_globs); /// ends with '/'
 
-        bool has_generator = false;
-        bool range_generator = false;
-
-        const size_t next_slash_after_glob_pos = [&]()
-        {
-            if (!has_glob)
-                return suffix_with_globs.find('/', 1);
-
-            bool prev_is_dot = false;
-
-            for (std::string::const_iterator it = ++suffix_with_globs.begin(); it != suffix_with_globs.end(); it++)
-            {
-                if (*it == '{')
-                    has_generator = true;
-                else if (*it == '/')
-                    return size_t(std::distance(suffix_with_globs.begin(), it));
-                else if (*it == '.')
-                {
-                    if (prev_is_dot)
-                        range_generator = true;
-                    prev_is_dot = true;
-                }
-            }
-            return std::string::npos;
-        }();
-
-        if (has_generator && !range_generator)
-            return expandSelector(path_for_ls, fs, for_match);
+        const size_t next_slash_after_glob_pos = suffix_with_globs.find('/', 1);
 
         const std::string current_glob = suffix_with_globs.substr(0, next_slash_after_glob_pos);
 
diff --git a/src/Storages/StorageFile.cpp b/src/Storages/StorageFile.cpp
index eb18842fdaa..5b05dfa687f 100644
--- a/src/Storages/StorageFile.cpp
+++ b/src/Storages/StorageFile.cpp
@@ -106,7 +106,6 @@ namespace ErrorCodes
 
 namespace
 {
-
 /// Forward-declare to use in expandSelector()
 void listFilesWithRegexpMatchingImpl(
     const std::string & path_for_ls,
@@ -171,43 +170,27 @@ void listFilesWithRegexpMatchingImpl(
     std::vector<std::string> & result,
     bool recursive)
 {
+    /// regexp for {expr1,expr2,expr3} or {M..N}, where M and N - non-negative integers, expr's should be without "{", "}", "*" and ","
+    static const re2::RE2 enum_or_range(R"({([\d]+\.\.[\d]+|[^{}*,]+,[^{}*]*[^{}*,])})");
+
+    std::string_view for_match_view(for_match);
+    std::string_view matched;
+    if (RE2::FindAndConsume(&for_match_view, enum_or_range, &matched))
+    {
+        std::string buffer(matched);
+        if (buffer.find(',') != std::string::npos)
+        {
+            expandSelector(path_for_ls, for_match, total_bytes_to_read, result, recursive);
+            return;
+        }
+    }
+
     const size_t first_glob_pos = for_match.find_first_of("*?{");
-    const bool has_glob = first_glob_pos != std::string::npos;
 
     const size_t end_of_path_without_globs = for_match.substr(0, first_glob_pos).rfind('/');
     const std::string suffix_with_globs = for_match.substr(end_of_path_without_globs);   /// begin with '/'
 
-    bool has_generator = false;
-    bool range_generator = false;
-
-    const size_t next_slash_after_glob_pos = [&]()
-    {
-        if (!has_glob)
-            return suffix_with_globs.find('/', 1);
-
-        bool prev_is_dot = false;
-
-        for (std::string::const_iterator it = ++suffix_with_globs.begin(); it != suffix_with_globs.end(); it++)
-        {
-            if (*it == '{')
-                has_generator = true;
-            else if (*it == '/')
-                return size_t(std::distance(suffix_with_globs.begin(), it));
-            else if (*it == '.')
-            {
-                if (prev_is_dot)
-                    range_generator = true;
-                prev_is_dot = true;
-            }
-        }
-        return std::string::npos;
-    }();
-
-    if (has_generator && !range_generator)
-    {
-        expandSelector(path_for_ls, for_match, total_bytes_to_read, result, recursive);
-        return;
-    }
+    const size_t next_slash_after_glob_pos = suffix_with_globs.find('/', 1);
 
     const std::string current_glob = suffix_with_globs.substr(0, next_slash_after_glob_pos);