szaszm commented on code in PR #1682:
URL: https://github.com/apache/nifi-minifi-cpp/pull/1682#discussion_r1452325647


##########
extensions/standard-processors/processors/SplitText.cpp:
##########
@@ -0,0 +1,378 @@
+/**
+ * @file SplitText.cpp
+ * SplitText class implementation
+ *
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+#include "SplitText.h"
+#include "core/ProcessContext.h"
+#include "core/ProcessSession.h"
+#include "core/Resource.h"
+#include "core/FlowFile.h"
+#include "utils/gsl.h"
+#include "utils/ProcessorConfigUtils.h"
+
+namespace org::apache::nifi::minifi::processors {
+
+namespace detail {
+
+LineReader::LineReader(const std::shared_ptr<io::InputStream>& stream)
+    : stream_(stream) {
+  if (!stream_ || stream_->size() == 0) {
+    state_ = StreamReadState::EndOfStream;
+  }
+}
+
+uint8_t LineReader::getEndLineSize(size_t newline_index) {
+  gsl_Expects(buffer_.size() > newline_index);
+  if (buffer_[newline_index] != '\n') {
+    return 0;
+  }
+  if (newline_index == 0 || buffer_[newline_index - 1] != '\r') {
+    return 1;
+  }
+  return 2;
+}
+
+void LineReader::setLastLineInfoAttributes(uint8_t endline_size, const 
std::optional<std::string>& starts_with) {
+  const uint64_t size_from_beginning_of_stream = (current_buffer_count_ - 1) * 
SPLIT_TEXT_BUFFER_SIZE + buffer_offset_;
+  if (last_line_info_) {
+    LineInfo previous_line_info = *last_line_info_;
+    last_line_info_->offset = previous_line_info.offset + 
previous_line_info.size;
+    last_line_info_->size = size_from_beginning_of_stream - 
previous_line_info.offset - previous_line_info.size;
+    last_line_info_->endline_size = endline_size;
+    last_line_info_->matches_starts_with = true;
+  } else {
+    last_line_info_ = LineInfo{.offset = 0, .size = read_size_ - 
last_read_size_ + buffer_offset_, .endline_size = endline_size, 
.matches_starts_with = true};
+  }
+
+  if (starts_with) {
+    last_line_info_->matches_starts_with = last_line_info_->size >= 
starts_with->size() &&
+      std::equal(starts_with->begin(), starts_with->end(), buffer_.begin() + 
last_line_info_->offset, buffer_.begin() + last_line_info_->offset + 
starts_with->size());
+  }
+}
+
+bool LineReader::readNextBuffer() {
+  buffer_offset_ = 0;
+  last_read_size_ = (std::min)(gsl::narrow<size_t>(stream_->size() - 
read_size_), SPLIT_TEXT_BUFFER_SIZE);
+  const auto read_ret = 
stream_->read(as_writable_bytes(std::span(buffer_).subspan(0, 
last_read_size_)));
+  read_size_ += read_ret;
+  if (io::isError(read_ret)) {
+    state_ = StreamReadState::StreamReadError;
+    return false;
+  }
+  ++current_buffer_count_;
+  return true;
+}
+
+std::optional<LineReader::LineInfo> LineReader::finalizeLineInfo(uint8_t 
endline_size, const std::optional<std::string>& starts_with) {
+  setLastLineInfoAttributes(endline_size, starts_with);
+  if (last_line_info_->size == 0) {
+    return std::nullopt;
+  }
+  return last_line_info_;
+}
+
+std::optional<LineReader::LineInfo> LineReader::readNextLine(const 
std::optional<std::string>& starts_with) {
+  if (state_ != StreamReadState::Ok) {
+    return std::nullopt;
+  }
+
+  const auto isLastReadProcessed = [this]() { return last_read_size_ <= 
buffer_offset_; };
+  while (read_size_ < stream_->size() || !isLastReadProcessed()) {
+    if (isLastReadProcessed() && !readNextBuffer()) {
+      return std::nullopt;
+    }
+
+    for (auto i = buffer_offset_; i < last_read_size_; ++i) {
+      if (buffer_[i] == '\n') {
+        buffer_offset_ = i + 1;
+        return finalizeLineInfo(getEndLineSize(i), starts_with);
+      }
+    }
+    buffer_offset_ = last_read_size_;
+  }
+
+  state_ = StreamReadState::EndOfStream;
+  return finalizeLineInfo(0, starts_with);
+}
+
+SplitTextFragmentGenerator::SplitTextFragmentGenerator(const 
std::shared_ptr<io::InputStream>& stream, const SplitTextConfiguration& 
split_text_config)
+    : line_reader_(stream),
+      split_text_config_(split_text_config) {
+}
+
+void SplitTextFragmentGenerator::finalizeFragmentOffset(Fragment& 
current_fragment) {
+  current_fragment.fragment_offset = flow_file_offset_;
+  flow_file_offset_ += current_fragment.fragment_size;
+}
+
+void SplitTextFragmentGenerator::addLineToFragment(Fragment& current_fragment, 
const LineReader::LineInfo& line) {
+  if (line.endline_size == line.size) {  // if line consists only of endline 
characters, we need to append the fragment trim size
+    current_fragment.endline_size += line.endline_size;
+  } else {
+    current_fragment.endline_size = line.endline_size;
+  }
+  current_fragment.text_line_count += line.endline_size == line.size ? 0 : 1;
+  current_fragment.fragment_size += line.size;
+}
+
+bool SplitTextFragmentGenerator::lineSizeWouldExceedMaxFragmentSize(const 
LineReader::LineInfo& line, uint64_t fragment_size) const {
+  return split_text_config_.maximum_fragment_size && fragment_size + line.size 
+ header_fragment_size_ > split_text_config_.maximum_fragment_size.value();
+}
+
+nonstd::expected<SplitTextFragmentGenerator::Fragment, std::string> 
SplitTextFragmentGenerator::createHeaderFragmentUsingLineCount() {
+  Fragment header_fragment;
+  for (uint64_t i = 0; i < split_text_config_.header_line_count; ++i) {
+    auto line = line_reader_.readNextLine();
+    if (!line) {
+      if (getState() == StreamReadState::EndOfStream) {
+        return nonstd::make_unexpected("The flow file's line count is less 
than the specified header line count!");
+      } else {
+        return nonstd::make_unexpected("Error while reading flow file 
stream!");
+      }
+    }
+    if (lineSizeWouldExceedMaxFragmentSize(*line, 
header_fragment.fragment_size)) {
+      return nonstd::make_unexpected("Header line would exceed the maximum 
fragment size!");
+    }
+
+    addLineToFragment(header_fragment, *line);
+  }
+
+  flow_file_offset_ += header_fragment.fragment_size;
+  header_fragment_size_ = header_fragment.fragment_size;
+  return header_fragment;
+}
+
+nonstd::expected<SplitTextFragmentGenerator::Fragment, std::string> 
SplitTextFragmentGenerator::createHeaderFragmentUsingHeaderMarkerCharacters() {
+  Fragment header_fragment;
+  while (auto line = 
line_reader_.readNextLine(split_text_config_.header_line_marker_characters)) {
+    if (line->size < split_text_config_.header_line_marker_characters->size() 
|| !line->matches_starts_with) {
+      buffered_line_info_ = line;
+      break;
+    }
+    if (lineSizeWouldExceedMaxFragmentSize(*line, 
header_fragment.fragment_size)) {
+      return nonstd::make_unexpected("Header line would exceed the maximum 
fragment size!");
+    }
+
+    addLineToFragment(header_fragment, *line);
+  }
+
+  flow_file_offset_ += header_fragment.fragment_size;
+  header_fragment_size_ = header_fragment.fragment_size;
+  return header_fragment;
+}
+
+nonstd::expected<SplitTextFragmentGenerator::Fragment, std::string> 
SplitTextFragmentGenerator::readHeaderFragment() {
+  gsl_Expects(flow_file_offset_ == 0 && (split_text_config_.header_line_count 
> 0 || split_text_config_.header_line_marker_characters));
+  if (split_text_config_.header_line_count > 0) {
+    return createHeaderFragmentUsingLineCount();
+  }
+
+  return createHeaderFragmentUsingHeaderMarkerCharacters();
+}
+
+std::optional<SplitTextFragmentGenerator::Fragment> 
SplitTextFragmentGenerator::readNextFragment() {
+  Fragment current_fragment;
+  while (auto line = buffered_line_info_ ? buffered_line_info_ : 
line_reader_.readNextLine()) {
+    buffered_line_info_.reset();
+    if (lineSizeWouldExceedMaxFragmentSize(*line, 
current_fragment.fragment_size)) {
+      if (current_fragment.processed_line_count == 0) {  // first fragment 
line would be bigger than maximum fragment size (we don't have any other line 
in the fragment yet)
+        addLineToFragment(current_fragment, *line);
+      } else {
+        buffered_line_info_ = line;
+      }
+
+      finalizeFragmentOffset(current_fragment);
+      return current_fragment;
+    }
+
+    ++current_fragment.processed_line_count;
+    addLineToFragment(current_fragment, *line);
+    if (split_text_config_.line_split_count == 
current_fragment.processed_line_count) {
+      finalizeFragmentOffset(current_fragment);
+      return current_fragment;
+    }
+  }
+
+  if (current_fragment.fragment_size > 0) {
+    finalizeFragmentOffset(current_fragment);
+    return current_fragment;
+  }
+  return std::nullopt;
+}
+
+ReadCallback::ReadCallback(std::shared_ptr<core::FlowFile> flow_file, const 
SplitTextConfiguration& split_text_config,
+  core::ProcessSession& session,  std::shared_ptr<core::logging::Logger> 
logger)
+    : flow_file_(std::move(flow_file)),
+      split_text_config_(split_text_config),
+      session_(session),
+      logger_(std::move(logger)) {
+}
+
+void ReadCallback::setAttributesOfDoneSegment(core::FlowFile& 
current_flow_file, uint64_t line_count) {
+  const std::string original_filename_or_uuid = 
flow_file_->getAttribute(core::SpecialFlowAttribute::FILENAME).value_or(flow_file_->getUUIDStr());
+  current_flow_file.setAttribute(core::SpecialFlowAttribute::FILENAME, 
original_filename_or_uuid + ".fragment." + fragment_identifier_ + "." + 
std::to_string(emitted_fragment_index_));
+  current_flow_file.setAttribute(SplitText::TextLineCountOutputAttribute.name, 
std::to_string(line_count));
+  current_flow_file.setAttribute(SplitText::FragmentSizeOutputAttribute.name, 
std::to_string(current_flow_file.getSize()));
+  
current_flow_file.setAttribute(SplitText::FragmentIdentifierOutputAttribute.name,
 fragment_identifier_);
+  current_flow_file.setAttribute(SplitText::FragmentIndexOutputAttribute.name, 
std::to_string(emitted_fragment_index_));
+  
current_flow_file.setAttribute(SplitText::SegmentOriginalFilenameOutputAttribute.name,
 flow_file_->getAttribute(core::SpecialFlowAttribute::FILENAME).value_or(""));
+  ++emitted_fragment_index_;
+}
+
+void ReadCallback::createHeaderOnlyFragmentFlow(const 
SplitTextFragmentGenerator::Fragment& header_fragment) {
+  gsl_Expects(split_text_config_.remove_trailing_new_lines);  // This is only 
possible if the split fragment has no content and the endlines are trimmed
+  auto header_only_flow = session_.clone(flow_file_, 
gsl::narrow<int64_t>(header_fragment.fragment_offset), 
gsl::narrow<int64_t>(header_fragment.fragment_size - 
header_fragment.endline_size));

Review Comment:
   my bad, my IDE was saying something like 240



-- 
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.

To unsubscribe, e-mail: issues-unsubscr...@nifi.apache.org

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org

Reply via email to