1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
// 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 std::fmt::{Display, Formatter};
use std::sync::Arc;

use arrow::array::{
    new_null_array, Array, ArrayDataBuilder, ArrayRef, GenericStringArray,
    GenericStringBuilder, OffsetSizeTrait, StringArray,
};
use arrow::buffer::{Buffer, MutableBuffer, NullBuffer};
use arrow::datatypes::DataType;

use datafusion_common::cast::as_generic_string_array;
use datafusion_common::Result;
use datafusion_common::{exec_err, ScalarValue};
use datafusion_expr::ColumnarValue;

pub(crate) enum TrimType {
    Left,
    Right,
    Both,
}

impl Display for TrimType {
    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
        match self {
            TrimType::Left => write!(f, "ltrim"),
            TrimType::Right => write!(f, "rtrim"),
            TrimType::Both => write!(f, "btrim"),
        }
    }
}

pub(crate) fn general_trim<T: OffsetSizeTrait>(
    args: &[ArrayRef],
    trim_type: TrimType,
) -> Result<ArrayRef> {
    let func = match trim_type {
        TrimType::Left => |input, pattern: &str| {
            let pattern = pattern.chars().collect::<Vec<char>>();
            str::trim_start_matches::<&[char]>(input, pattern.as_ref())
        },
        TrimType::Right => |input, pattern: &str| {
            let pattern = pattern.chars().collect::<Vec<char>>();
            str::trim_end_matches::<&[char]>(input, pattern.as_ref())
        },
        TrimType::Both => |input, pattern: &str| {
            let pattern = pattern.chars().collect::<Vec<char>>();
            str::trim_end_matches::<&[char]>(
                str::trim_start_matches::<&[char]>(input, pattern.as_ref()),
                pattern.as_ref(),
            )
        },
    };

    let string_array = as_generic_string_array::<T>(&args[0])?;

    match args.len() {
        1 => {
            let result = string_array
                .iter()
                .map(|string| string.map(|string: &str| func(string, " ")))
                .collect::<GenericStringArray<T>>();

            Ok(Arc::new(result) as ArrayRef)
        }
        2 => {
            let characters_array = as_generic_string_array::<T>(&args[1])?;

            if characters_array.len() == 1 {
                if characters_array.is_null(0) {
                    return Ok(new_null_array(args[0].data_type(), args[0].len()));
                }

                let characters = characters_array.value(0);
                let result = string_array
                    .iter()
                    .map(|item| item.map(|string| func(string, characters)))
                    .collect::<GenericStringArray<T>>();
                return Ok(Arc::new(result) as ArrayRef);
            }

            let result = string_array
                .iter()
                .zip(characters_array.iter())
                .map(|(string, characters)| match (string, characters) {
                    (Some(string), Some(characters)) => Some(func(string, characters)),
                    _ => None,
                })
                .collect::<GenericStringArray<T>>();

            Ok(Arc::new(result) as ArrayRef)
        }
        other => {
            exec_err!(
            "{trim_type} was called with {other} arguments. It requires at least 1 and at most 2."
        )
        }
    }
}

pub(crate) fn to_lower(args: &[ColumnarValue], name: &str) -> Result<ColumnarValue> {
    case_conversion(args, |string| string.to_lowercase(), name)
}

pub(crate) fn to_upper(args: &[ColumnarValue], name: &str) -> Result<ColumnarValue> {
    case_conversion(args, |string| string.to_uppercase(), name)
}

fn case_conversion<'a, F>(
    args: &'a [ColumnarValue],
    op: F,
    name: &str,
) -> Result<ColumnarValue>
where
    F: Fn(&'a str) -> String,
{
    match &args[0] {
        ColumnarValue::Array(array) => match array.data_type() {
            DataType::Utf8 => Ok(ColumnarValue::Array(case_conversion_array::<i32, _>(
                array, op,
            )?)),
            DataType::LargeUtf8 => Ok(ColumnarValue::Array(case_conversion_array::<
                i64,
                _,
            >(array, op)?)),
            other => exec_err!("Unsupported data type {other:?} for function {name}"),
        },
        ColumnarValue::Scalar(scalar) => match scalar {
            ScalarValue::Utf8(a) => {
                let result = a.as_ref().map(|x| op(x));
                Ok(ColumnarValue::Scalar(ScalarValue::Utf8(result)))
            }
            ScalarValue::LargeUtf8(a) => {
                let result = a.as_ref().map(|x| op(x));
                Ok(ColumnarValue::Scalar(ScalarValue::LargeUtf8(result)))
            }
            other => exec_err!("Unsupported data type {other:?} for function {name}"),
        },
    }
}

pub(crate) enum ColumnarValueRef<'a> {
    Scalar(&'a [u8]),
    NullableArray(&'a StringArray),
    NonNullableArray(&'a StringArray),
}

impl<'a> ColumnarValueRef<'a> {
    #[inline]
    pub fn is_valid(&self, i: usize) -> bool {
        match &self {
            Self::Scalar(_) | Self::NonNullableArray(_) => true,
            Self::NullableArray(array) => array.is_valid(i),
        }
    }

    #[inline]
    pub fn nulls(&self) -> Option<NullBuffer> {
        match &self {
            Self::Scalar(_) | Self::NonNullableArray(_) => None,
            Self::NullableArray(array) => array.nulls().cloned(),
        }
    }
}

/// Optimized version of the StringBuilder in Arrow that:
/// 1. Precalculating the expected length of the result, avoiding reallocations.
/// 2. Avoids creating / incrementally creating a `NullBufferBuilder`
pub(crate) struct StringArrayBuilder {
    offsets_buffer: MutableBuffer,
    value_buffer: MutableBuffer,
}

impl StringArrayBuilder {
    pub fn with_capacity(item_capacity: usize, data_capacity: usize) -> Self {
        let mut offsets_buffer = MutableBuffer::with_capacity(
            (item_capacity + 1) * std::mem::size_of::<i32>(),
        );
        // SAFETY: the first offset value is definitely not going to exceed the bounds.
        unsafe { offsets_buffer.push_unchecked(0_i32) };
        Self {
            offsets_buffer,
            value_buffer: MutableBuffer::with_capacity(data_capacity),
        }
    }

    pub fn write<const CHECK_VALID: bool>(
        &mut self,
        column: &ColumnarValueRef,
        i: usize,
    ) {
        match column {
            ColumnarValueRef::Scalar(s) => {
                self.value_buffer.extend_from_slice(s);
            }
            ColumnarValueRef::NullableArray(array) => {
                if !CHECK_VALID || array.is_valid(i) {
                    self.value_buffer
                        .extend_from_slice(array.value(i).as_bytes());
                }
            }
            ColumnarValueRef::NonNullableArray(array) => {
                self.value_buffer
                    .extend_from_slice(array.value(i).as_bytes());
            }
        }
    }

    pub fn append_offset(&mut self) {
        let next_offset: i32 = self
            .value_buffer
            .len()
            .try_into()
            .expect("byte array offset overflow");
        unsafe { self.offsets_buffer.push_unchecked(next_offset) };
    }

    pub fn finish(self, null_buffer: Option<NullBuffer>) -> StringArray {
        let array_builder = ArrayDataBuilder::new(DataType::Utf8)
            .len(self.offsets_buffer.len() / std::mem::size_of::<i32>() - 1)
            .add_buffer(self.offsets_buffer.into())
            .add_buffer(self.value_buffer.into())
            .nulls(null_buffer);
        // SAFETY: all data that was appended was valid UTF8 and the values
        // and offsets were created correctly
        let array_data = unsafe { array_builder.build_unchecked() };
        StringArray::from(array_data)
    }
}

fn case_conversion_array<'a, O, F>(array: &'a ArrayRef, op: F) -> Result<ArrayRef>
where
    O: OffsetSizeTrait,
    F: Fn(&'a str) -> String,
{
    const PRE_ALLOC_BYTES: usize = 8;

    let string_array = as_generic_string_array::<O>(array)?;
    let value_data = string_array.value_data();

    // All values are ASCII.
    if value_data.is_ascii() {
        return case_conversion_ascii_array::<O, _>(string_array, op);
    }

    // Values contain non-ASCII.
    let item_len = string_array.len();
    let capacity = string_array.value_data().len() + PRE_ALLOC_BYTES;
    let mut builder = GenericStringBuilder::<O>::with_capacity(item_len, capacity);

    if string_array.null_count() == 0 {
        let iter =
            (0..item_len).map(|i| Some(op(unsafe { string_array.value_unchecked(i) })));
        builder.extend(iter);
    } else {
        let iter = string_array.iter().map(|string| string.map(&op));
        builder.extend(iter);
    }
    Ok(Arc::new(builder.finish()))
}

/// All values of string_array are ASCII, and when converting case, there is no changes in the byte
/// array length. Therefore, the StringArray can be treated as a complete ASCII string for
/// case conversion, and we can reuse the offsets buffer and the nulls buffer.
fn case_conversion_ascii_array<'a, O, F>(
    string_array: &'a GenericStringArray<O>,
    op: F,
) -> Result<ArrayRef>
where
    O: OffsetSizeTrait,
    F: Fn(&'a str) -> String,
{
    let value_data = string_array.value_data();
    // SAFETY: all items stored in value_data satisfy UTF8.
    // ref: impl ByteArrayNativeType for str {...}
    let str_values = unsafe { std::str::from_utf8_unchecked(value_data) };

    // conversion
    let converted_values = op(str_values);
    assert_eq!(converted_values.len(), str_values.len());
    let bytes = converted_values.into_bytes();

    // build result
    let values = Buffer::from_vec(bytes);
    let offsets = string_array.offsets().clone();
    let nulls = string_array.nulls().cloned();
    // SAFETY: offsets and nulls are consistent with the input array.
    Ok(Arc::new(unsafe {
        GenericStringArray::<O>::new_unchecked(offsets, values, nulls)
    }))
}