tustvold commented on a change in pull request #1082: URL: https://github.com/apache/arrow-rs/pull/1082#discussion_r785454423
########## File path: parquet/src/arrow/array_reader/offset_buffer.rs ########## @@ -0,0 +1,211 @@ +// 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. + +use crate::arrow::record_reader::buffer::{ + BufferQueue, ScalarBuffer, ScalarValue, ValuesBuffer, +}; +use crate::column::reader::decoder::ValuesBufferSlice; +use crate::errors::{ParquetError, Result}; +use arrow::array::{make_array, ArrayDataBuilder, ArrayRef, OffsetSizeTrait}; +use arrow::buffer::Buffer; +use arrow::datatypes::{ArrowNativeType, DataType as ArrowType}; + +pub struct OffsetBuffer<I: ScalarValue> { + pub offsets: ScalarBuffer<I>, + pub values: ScalarBuffer<u8>, +} + +impl<I: ScalarValue> Default for OffsetBuffer<I> { + fn default() -> Self { + let mut offsets = ScalarBuffer::new(); + offsets.resize(1); + Self { + offsets, + values: ScalarBuffer::new(), + } + } +} + +impl<I: OffsetSizeTrait + ScalarValue> OffsetBuffer<I> { + pub fn len(&self) -> usize { + self.offsets.len() - 1 + } + + /// If `validate_utf8` this verifies that the first character of `data` is + /// the start of a UTF-8 codepoint + /// + /// Note: This does not verify that the entirety of `data` is valid + /// UTF-8. This should be done by calling [`Self::values_as_str`] after + /// all data has been written + pub fn try_push(&mut self, data: &[u8], validate_utf8: bool) -> Result<()> { + if validate_utf8 { + if let Some(&b) = data.first() { + // A valid code-point iff it does not start with 0b10xxxxxx + // Bit-magic taken from `std::str::is_char_boundary` + if (b as i8) < -0x40 { + return Err(ParquetError::General( + "encountered non UTF-8 data".to_string(), + )); + } + } + } + + self.values.extend_from_slice(data); + + let index_offset = I::from_usize(self.values.len()) + .ok_or_else(|| general_err!("index overflow decoding byte array"))?; + + self.offsets.push(index_offset); + Ok(()) + } + + pub fn extend_from_dictionary<K: ArrowNativeType, V: ArrowNativeType>( Review comment: This is split out so that it can be used by #1180 -- 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: github-unsubscr...@arrow.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
