Update contrib/libs/apache/orc to 2.0.1

855bd01a1b384d08c59ee86c6b493ea32190ef19

7 files changed, 95 insertions, 26 deletions

diff --git a/contrib/libs/apache/orc/c++/include/orc/OrcFile.hh b/contrib/libs/apache/orc/c++/include/orc/OrcFile.hh
index 6e4a07bf7c..a9ad692d42 100644
--- a/contrib/libs/apache/orc/c++/include/orc/OrcFile.hh
+++ b/contrib/libs/apache/orc/c++/include/orc/OrcFile.hh
@@ -127,8 +127,8 @@ namespace orc {
    * @param path the uri of the file in HDFS
    * @param metrics the metrics of the reader
    */
-  std::unique_ptr<InputStream> readHdfsFile(const std::string& path,
-                                            ReaderMetrics* metrics = nullptr);
+  [[deprecated("readHdfsFile is deprecated in 2.0.1")]] std::unique_ptr<InputStream> readHdfsFile(
+      const std::string& path, ReaderMetrics* metrics = nullptr);
 
   /**
    * Create a reader to read the ORC file.
diff --git a/contrib/libs/apache/orc/c++/include/orc/orc-config.hh b/contrib/libs/apache/orc/c++/include/orc/orc-config.hh
index ab1e16fa15..eb79be002a 100644
--- a/contrib/libs/apache/orc/c++/include/orc/orc-config.hh
+++ b/contrib/libs/apache/orc/c++/include/orc/orc-config.hh
@@ -19,7 +19,7 @@
 #ifndef ORC_CONFIG_HH
 #define ORC_CONFIG_HH
 
-#define ORC_VERSION "2.0.0"
+#define ORC_VERSION "2.0.1"
 
 #define ORC_CXX_HAS_CSTDINT
 
diff --git a/contrib/libs/apache/orc/c++/src/Adaptor-linux.hh b/contrib/libs/apache/orc/c++/src/Adaptor-linux.hh
index b11cdf74cd..286188e3a1 100644
--- a/contrib/libs/apache/orc/c++/src/Adaptor-linux.hh
+++ b/contrib/libs/apache/orc/c++/src/Adaptor-linux.hh
@@ -109,6 +109,7 @@ typedef SSIZE_T ssize_t;
 namespace orc {
   std::string to_string(double val);
   std::string to_string(int64_t val);
+  bool fileExists(const char* path);
 }
 
 #ifdef HAS_BUILTIN_OVERFLOW_CHECK
diff --git a/contrib/libs/apache/orc/c++/src/Adaptor.cc b/contrib/libs/apache/orc/c++/src/Adaptor.cc
index d9390131b6..d5dd7802f3 100644
--- a/contrib/libs/apache/orc/c++/src/Adaptor.cc
+++ b/contrib/libs/apache/orc/c++/src/Adaptor.cc
@@ -53,6 +53,12 @@ ssize_t pread(int fd, void* buf, size_t size, off_t offset) {
 #endif
 #endif
 
+#ifdef _MSC_VER
+#include <Windows.h>
+#else
+#include <sys/stat.h>
+#endif
+
 namespace orc {
 #ifdef HAS_DOUBLE_TO_STRING
   std::string to_string(double val) {
@@ -73,4 +79,14 @@ namespace orc {
     return std::to_string(static_cast<long long int>(val));
   }
 #endif
+
+  bool fileExists(const char* path) {
+#ifdef _MSC_VER
+    return GetFileAttributesA(path) != INVALID_FILE_ATTRIBUTES;
+#else
+    struct stat st;
+    return stat(path, &st) == 0;
+#endif
+  }
+
 }  // namespace orc
diff --git a/contrib/libs/apache/orc/c++/src/Timezone.cc b/contrib/libs/apache/orc/c++/src/Timezone.cc
index 27e14480d5..4c78a53a29 100644
--- a/contrib/libs/apache/orc/c++/src/Timezone.cc
+++ b/contrib/libs/apache/orc/c++/src/Timezone.cc
@@ -24,7 +24,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <time.h>
-#include <filesystem>
+#include <atomic>
 #include <map>
 #include <sstream>
 
@@ -656,26 +656,25 @@ namespace orc {
     epoch = utcEpoch - getVariant(utcEpoch).gmtOffset;
   }
 
-  const char* getTimezoneDirectory() {
+  std::string getTimezoneDirectory() {
     const char* dir = getenv("TZDIR");
     if (!dir) {
-      dir = DEFAULT_TZDIR;
+      // this is present if we're in an activated conda environment
+      const char* condaPrefix = getenv("CONDA_PREFIX");
+      if (condaPrefix) {
+        std::string condaDir(condaPrefix);
+        condaDir += "/share/zoneinfo";
+        return condaDir;
+      } else {
+        dir = DEFAULT_TZDIR;
+      }
     }
     return dir;
   }
 
-  /**
-   * Get a timezone by absolute filename.
-   * Results are cached.
-   */
-  const Timezone& getTimezoneByFilename(const std::string& filename) {
-    // ORC-110
-    std::lock_guard<std::mutex> timezone_lock(timezone_mutex);
-    std::map<std::string, std::shared_ptr<Timezone> >::iterator itr = timezoneCache.find(filename);
-    if (itr != timezoneCache.end()) {
-      return *(itr->second).get();
-    }
-    if (!std::filesystem::exists(std::filesystem::path(filename))) {
+  static std::vector<unsigned char> loadTZDB(const std::string& filename) {
+    std::vector<unsigned char> buffer;
+    if (!fileExists(filename.c_str())) {
       std::stringstream ss;
       ss << "Time zone file " << filename << " does not exist."
          << " Please install IANA time zone database and set TZDIR env.";
@@ -684,12 +683,65 @@ namespace orc {
     try {
       std::unique_ptr<InputStream> file = readFile(filename);
       size_t size = static_cast<size_t>(file->getLength());
-      std::vector<unsigned char> buffer(size);
+      buffer.resize(size);
       file->read(&buffer[0], size, 0);
-      timezoneCache[filename] = std::make_shared<TimezoneImpl>(filename, buffer);
     } catch (ParseError& err) {
       throw TimezoneError(err.what());
     }
+    return buffer;
+  }
+
+  class LazyTimezone : public Timezone {
+   private:
+    std::string filename_;
+    mutable std::unique_ptr<TimezoneImpl> impl_;
+    mutable std::once_flag initialized_;
+
+    TimezoneImpl* getImpl() const {
+      std::call_once(initialized_, [&]() {
+        auto buffer = loadTZDB(filename_);
+        impl_ = std::make_unique<TimezoneImpl>(filename_, std::move(buffer));
+      });
+      return impl_.get();
+    }
+
+   public:
+    LazyTimezone(const std::string& filename) : filename_(filename) {}
+
+    const TimezoneVariant& getVariant(int64_t clk) const override {
+      return getImpl()->getVariant(clk);
+    }
+    int64_t getEpoch() const override {
+      return getImpl()->getEpoch();
+    }
+    void print(std::ostream& os) const override {
+      return getImpl()->print(os);
+    }
+    uint64_t getVersion() const override {
+      return getImpl()->getVersion();
+    }
+
+    int64_t convertToUTC(int64_t clk) const override {
+      return getImpl()->convertToUTC(clk);
+    }
+
+    int64_t convertFromUTC(int64_t clk) const override {
+      return getImpl()->convertFromUTC(clk);
+    }
+  };
+
+  /**
+   * Get a timezone by absolute filename.
+   * Results are cached.
+   */
+  const Timezone& getTimezoneByFilename(const std::string& filename) {
+    // ORC-110
+    std::lock_guard<std::mutex> timezone_lock(timezone_mutex);
+    std::map<std::string, std::shared_ptr<Timezone> >::iterator itr = timezoneCache.find(filename);
+    if (itr != timezoneCache.end()) {
+      return *(itr->second).get();
+    }
+    timezoneCache[filename] = std::make_shared<LazyTimezone>(filename);
     return *timezoneCache[filename].get();
   }
 
diff --git a/contrib/libs/apache/orc/c++/src/sargs/SargsApplier.cc b/contrib/libs/apache/orc/c++/src/sargs/SargsApplier.cc
index 7032a88126..0e369bf453 100644
--- a/contrib/libs/apache/orc/c++/src/sargs/SargsApplier.cc
+++ b/contrib/libs/apache/orc/c++/src/sargs/SargsApplier.cc
@@ -160,12 +160,12 @@ namespace orc {
     }
 
     bool ret = evaluateColumnStatistics(stripeStats.col_stats());
+    if (mMetrics != nullptr) {
+      mMetrics->EvaluatedRowGroupCount.fetch_add(stripeRowGroupCount);
+    }
     if (!ret) {
       // reset mNextSkippedRows when the current stripe does not satisfy the PPD
       mNextSkippedRows.clear();
-      if (mMetrics != nullptr) {
-        mMetrics->EvaluatedRowGroupCount.fetch_add(stripeRowGroupCount);
-      }
     }
     return ret;
   }
@@ -177,7 +177,7 @@ namespace orc {
         mFileStatsEvalResult = true;
       } else {
         mFileStatsEvalResult = evaluateColumnStatistics(footer.statistics());
-        if (!mFileStatsEvalResult && mMetrics != nullptr) {
+        if (mMetrics != nullptr) {
           mMetrics->EvaluatedRowGroupCount.fetch_add(numRowGroupsInStripeRange);
         }
       }
diff --git a/contrib/libs/apache/orc/ya.make b/contrib/libs/apache/orc/ya.make
index ec4d745340..da0621ed3f 100644
--- a/contrib/libs/apache/orc/ya.make
+++ b/contrib/libs/apache/orc/ya.make
@@ -6,9 +6,9 @@ LICENSE(Apache-2.0)
 
 LICENSE_TEXTS(.yandex_meta/licenses.list.txt)
 
-VERSION(2.0.0)
+VERSION(2.0.1)
 
-ORIGINAL_SOURCE(https://github.com/apache/orc/archive/rel/release-2.0.0.tar.gz)
+ORIGINAL_SOURCE(https://github.com/apache/orc/archive/rel/release-2.0.1.tar.gz)
 
 PEERDIR(
     contrib/libs/apache/orc-format