[GitHub] [nifi-minifi-cpp] arpadboda commented on a change in pull request #580: MINIFICPP-30: Add support for regex with Multiple file mode

[GitBox <gi...@apache.org>]

arpadboda commented on a change in pull request #580: MINIFICPP-30: Add support for regex with Multiple file mode
URL: https://github.com/apache/nifi-minifi-cpp/pull/580#discussion_r296629133
 
 

 ##########
 File path: extensions/standard-processors/processors/TailFile.cpp
 ##########
 @@ -61,34 +66,101 @@ namespace nifi {
 namespace minifi {
 namespace processors {
 
-core::Property TailFile::FileName("File to Tail", "Fully-qualified filename of the file that should be tailed", "");
+core::Property TailFile::FileName("File to Tail", "Fully-qualified filename of the file that should be tailed when using single file mode, or a file regex when using multifile mode", "");
 core::Property TailFile::StateFile("State File", "Specifies the file that should be used for storing state about"
                                    " what data has been ingested so that upon restart NiFi can resume from where it left off",
                                    "TailFileState");
 core::Property TailFile::Delimiter("Input Delimiter", "Specifies the character that should be used for delimiting the data being tailed"
                                    "from the incoming file.",
                                    "");
+
+core::Property TailFile::TailMode(
+    core::PropertyBuilder::createProperty("tail-mode", "Tailing Mode")->withDescription("Specifies the tail file mode. In 'Single file' mode only a single file will be watched. "
+                "In 'Multiple file' mode a regex may be used. Note that in multiple file mode we will still continue to watch for rollover on the initial set of watched files. "
+                "The Regex used to locate multiple files will be run during the schedule phrase. Note that if rotated files are matched by the regex, those files will be tailed.")->isRequired(true)->withAllowableValue<std::string>("Single file")->withAllowableValue("Multiple file")->withDefaultValue(
+        "Single file")->build());
+
+core::Property TailFile::BaseDirectory(core::PropertyBuilder::createProperty("tail-base-directory", "Base Directory")->isRequired(false)->build());
+
 core::Relationship TailFile::Success("success", "All files are routed to success");
 
+const char *TailFile::CURRENT_STR = "CURRENT.";
+const char *TailFile::POSITION_STR = "POSITION.";
+
 void TailFile::initialize() {
   // Set the supported properties
   std::set<core::Property> properties;
   properties.insert(FileName);
   properties.insert(StateFile);
   properties.insert(Delimiter);
+  properties.insert(TailMode);
+  properties.insert(BaseDirectory);
   setSupportedProperties(properties);
   // Set the supported relationships
   std::set<core::Relationship> relationships;
   relationships.insert(Success);
   setSupportedRelationships(relationships);
 }
 
-void TailFile::onSchedule(core::ProcessContext *context, core::ProcessSessionFactory *sessionFactory) {
+void TailFile::onSchedule(const std::shared_ptr<core::ProcessContext> &context, const std::shared_ptr<core::ProcessSessionFactory> &sessionFactory) {
+  std::lock_guard<std::mutex> tail_lock(tail_file_mutex_);
+
   std::string value;
 
   if (context->getProperty(Delimiter.getName(), value)) {
     delimiter_ = value;
   }
+
+  std::string mode;
+  context->getProperty(TailMode.getName(), mode);
+
+  std::string file = "";
+  if (!context->getProperty(FileName.getName(), file)) {
+    throw minifi::Exception(ExceptionType::PROCESSOR_EXCEPTION, "File to Tail is a required property");
+  }
+  if (mode == "Multiple file") {
+    // file is a regex
+    std::string base_dir;
+    if (!context->getProperty(BaseDirectory.getName(), base_dir)) {
+      throw minifi::Exception(ExceptionType::PROCESSOR_EXCEPTION, "Base directory is required for multiple tail mode.");
+    }
+
+    auto fileRegexSelect = [&](const std::string& path, const std::string& filename) -> bool {
+      struct stat sb;
+      std::string fileFullName = path + utils::file::FileUtils::get_separator() + filename;
 
 Review comment:
   This and "stat" seem to be unreferenced. 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services