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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426
use std::vec;
use crate::{
add_with, error,
add::Add, add::ColSpec, flush::Flush, headers::Headers, inspect::Inspect,
reduce::Reduce, Row, RowResult, add_with::AddWith, del::Del,
adjacent_group::AdjacentGroup, MockStream, rename::Rename, select::Select,
reduce::aggregate::Aggregate,
map::{MapRow, MapCol},
group::{Group, GroupCriteria},
filter::{FilterCol, FilterRow},
};
/// This trait describes de behaviour of every component in the CSV transformation
/// chain. Functions provided by this trait help construct the chain and can be
/// _chained_.
///
/// Implement this trait to extend `csvsc` with your own processors.
pub trait RowStream: IntoIterator<Item = RowResult> {
/// Must return headers as they are in this point of the chain. For example
/// if implementor adds a column, its `headers()` function must return the
/// new headers including the one just added.
fn headers(&self) -> &Headers;
/// Add a column to each row of the stream.
///
/// New columns can be build arbitrarily from previous columns or from a
/// specific column using a regular expression.
///
/// ```
/// use csvsc::prelude::*;
/// use encoding::all::UTF_8;
///
/// let mut chain = InputStreamBuilder::from_paths(&["test/assets/1.csv"])
/// .unwrap().build().unwrap()
/// .add(
/// Column::with_name("new column")
/// .from_all_previous()
/// .definition("{old col1} - {old col2}")
/// ).unwrap();
/// ```
///
/// See [`Column`](struct.Column.html) for options.
///
/// If you want to add a constant value or have some other requirement take
/// a look at `.add_with()`.
#[inline]
fn add(self, column: ColSpec) -> error::Result<Add<Self>>
where
Self: Sized,
{
Add::new(self, column)
}
/// Deletes the specified columns from each row of the stream. If you have
/// too many columns to delete perhaps instead use [`RowStream::select`].
#[inline]
fn del(self, columns: Vec<&str>) -> Del<Self>
where
Self: Sized,
{
Del::new(self, columns)
}
/// Outputs only the selected columns, ignoring the rest.
///
/// The returned rows contain its values in the order corresponding to the
/// order in which the headers were given to this function. That means that
/// this function can be used to reorder the headers.
///
/// If you only want do delete specific columns take a look at
/// [`RowStream::del`].
#[inline]
fn select(self, columns: Vec<&str>) -> Select<Self>
where
Self: Sized,
{
Select::new(self, columns)
}
/// Adds a column to each row of the stream using a closure to compute its
/// value.
///
/// This you can use to add a constant value also.
///
/// ## Example
///
/// ```
/// use csvsc::prelude::*;
/// use encoding::all::UTF_8;
///
/// let mut chain = InputStreamBuilder::from_paths(&["test/assets/1.csv"])
/// .unwrap().build().unwrap()
/// .add_with("new col", |headers, row| {
/// Ok("value".into())
/// }).unwrap();
/// ```
#[inline]
fn add_with<F>(self, colname: &str, f: F) -> Result<AddWith<Self, F>, add_with::BuildError>
where
Self: Sized,
F: FnMut(&Headers, &Row) -> error::Result<String>,
{
AddWith::new(self, colname, f)
}
/// Reduce all the incoming stream into one row, computing some aggregates
/// in the way. All the stream collapses into one row.
///
/// The final row contains only the result of reducers and no other column
/// but you might preserve a column using the `.last()` aggregate.
///
/// You'll likely be using this inside a `.group()` or `.adjacent_group()`.
///
/// ## Example
///
/// ```
/// use csvsc::prelude::*;
/// use encoding::all::UTF_8;
///
/// let mut chain = InputStreamBuilder::from_paths(&["test/assets/chicken_north.csv"])
/// .unwrap().build().unwrap()
/// .group(["month"], |row_stream| {
/// row_stream
/// .reduce(vec![
/// Reducer::with_name("avg").of_column("eggs per week").average().unwrap(),
/// ]).unwrap()
/// });
/// ```
///
/// See [`Reducer`](./struct.Reducer.html) for built-in aggregates.
#[inline]
fn reduce(
self,
columns: Vec<Box<dyn Aggregate>>,
) -> error::Result<Reduce<Self>>
where
Self: Sized,
{
Reduce::new(self, columns)
}
/// Groups rows by the given criteria, but assuming a "group" is a set of
/// adjacent rows.
///
/// This means that sets of rows that meet the same criteria but are not
/// adjacent will not be grouped together. Only use it if you are sure that
/// your data follows this pattern and you want to take advantage of it.
///
/// An interesting advantage of using this is that only one group is kept in
/// memory at a time.
///
/// See [`RowStream::group`] for more details.
///
/// ## Example
///
/// Consider a file `test/assets/groups.csv` with this contents. Notice that
/// there are four adjacent groups that have the same value for column
/// `name`: two with value `a` and two with `b`.
///
/// ```text
/// name,value
/// a,1
/// a,1
/// b,2
/// b,2
/// a,3
/// a,3
/// b,4
/// b,4
/// ```
///
/// Then the following code works as expected, generating an average for all
/// of the four adjacent groups that have the same value for column `name`.
///
/// ```
/// use csvsc::prelude::*;
///
/// let mut rows = InputStreamBuilder::from_paths(&["test/assets/groups.csv"]).unwrap().build().unwrap()
/// .adjacent_group(["name"], |row_stream| {
/// row_stream
/// .reduce(vec![
/// Reducer::with_name("name").of_column("name").last("").unwrap(),
/// Reducer::with_name("avg").of_column("value").average().unwrap(),
/// ]).unwrap()
/// })
/// .into_iter();
///
/// assert_eq!(rows.next().unwrap().unwrap(), Row::from(vec!["a", "1"]));
/// assert_eq!(rows.next().unwrap().unwrap(), Row::from(vec!["b", "2"]));
/// assert_eq!(rows.next().unwrap().unwrap(), Row::from(vec!["a", "3"]));
/// assert_eq!(rows.next().unwrap().unwrap(), Row::from(vec!["b", "4"]));
/// ```
#[inline]
fn adjacent_group<F, R, G>(
self,
grouping: G,
f: F,
) -> AdjacentGroup<Self, F, G>
where
F: Fn(MockStream<vec::IntoIter<RowResult>>) -> R,
R: RowStream,
G: GroupCriteria,
Self: Sized,
{
AdjacentGroup::new(self, f, grouping)
}
/// Groups rows by the given criteria. You'll be given a RowStream instance
/// as the first argument of a closure that you can use to further process
/// the grouped rows.
///
/// The first argument is the group criteria and it can be any of:
///
/// * A slice of `&str`: `&["foo", "bar"]`,
/// * an array of `&str`: `["foo", "bar"]`,
/// * a closure `Fn(&Headers, &Row) -> Hash`,
/// * any type that implements
/// [`GroupCriteria`](crate::group::GroupCriteria)
///
/// In the first two cases the `&str`s are treated as column names. Rows
/// having the same values for the specified columns will belong to the same
/// group. Strings that don't match any column name will be ignored.
///
/// In the closure case you'll be given the headers and every row and you
/// must return a hashable type that identifies the group where that row
/// belongs.
///
/// [`GroupCriteria`](crate::group::GroupCriteria) is a trait you can
/// implement for your own types if you want to use them as grouping
/// criteria.
///
/// ## Example
///
/// Consider the following file:
///
/// ```text
/// name,value
/// a,1
/// a,1
/// b,2
/// b,2
/// a,3
/// a,3
/// b,4
/// b,4
/// ```
///
/// Then we can group for example using the column `name` and get the
/// following results:
///
/// ```
/// use csvsc::prelude::*;
///
/// let mut rows: Vec<_> = InputStreamBuilder::from_paths(&["test/assets/groups.csv"]).unwrap().build().unwrap()
/// .group(["name"], |row_stream| {
/// row_stream
/// .reduce(vec![
/// Reducer::with_name("name").of_column("name").last("").unwrap(),
/// Reducer::with_name("avg").of_column("value").average().unwrap(),
/// ]).unwrap()
/// })
/// .into_iter()
/// .filter_map(|r| r.ok())
/// .collect();
///
/// rows.sort_by_key(|row| row.get(0).unwrap().to_string());
///
/// assert_eq!(rows[0], Row::from(vec!["a", "2"]));
/// assert_eq!(rows[1], Row::from(vec!["b", "3"]));
/// ```
///
/// ## Grouping by closure
///
/// If you decide that you need an arbitrary grouping criteria you can use a
/// closure that returns a hashable type like this:
///
/// ```
/// use csvsc::prelude::*;
///
/// let mut rows: Vec<_> = InputStreamBuilder::from_paths(&["test/assets/groups.csv"]).unwrap().build().unwrap()
/// .group(|headers: &Headers, row: &Row| {
/// headers.get_field(row, "name").unwrap().to_string()
/// }, |row_stream| {
/// row_stream
/// .reduce(vec![
/// Reducer::with_name("name").of_column("name").last("").unwrap(),
/// Reducer::with_name("avg").of_column("value").average().unwrap(),
/// ]).unwrap()
/// })
/// .into_iter()
/// .filter_map(|r| r.ok())
/// .collect();
///
/// rows.sort_by_key(|row| row.get(0).unwrap().to_string());
///
/// assert_eq!(rows[0], Row::from(vec!["a", "2"]));
/// assert_eq!(rows[1], Row::from(vec!["b", "3"]));
/// ```
#[inline]
fn group<F, R, G>(
self,
grouping: G,
f: F,
) -> Group<Self, F, G>
where
F: Fn(MockStream<vec::IntoIter<RowResult>>) -> R,
R: RowStream,
G: GroupCriteria,
Self: Sized,
{
Group::new(self, f, grouping)
}
/// When consumed, writes to destination specified by the column given in
/// the first argument. Other than that this behaves like an `id(x)`
/// function so you can specify more links in the chain and even more
/// flushers.
#[inline]
fn flush<T>(self, target: T) -> error::Result<Flush<Self, T>>
where
Self: Sized,
{
Flush::new(self, target)
}
/// Mostly for debugging, calls a closure on each element. Behaves like the
/// identity function on the stream returning each row untouched.
#[inline]
fn review<F>(self, f: F) -> Inspect<Self, F>
where
Self: Sized,
F: FnMut(&Headers, &RowResult),
{
Inspect::new(self, f)
}
/// Renames some columns
#[inline]
fn rename(self, old_name: &str, new_name: &str) -> Rename<Self>
where
Self: Sized,
{
Rename::new(self, old_name, new_name)
}
/// Apply a function to every row and use the return values to build the
/// row stream.
///
/// This method accepts a closure that must return an iterator over
/// RowResult values, this means that you can create more rows out of a
/// single one.
///
/// You're responsible of providing the new headers and for that you need to
/// use the second closure, that maps the old headers to the new ones.
///
/// # Example
///
/// ```
/// use csvsc::prelude::*;
/// use encoding::all::UTF_8;
///
/// InputStreamBuilder::from_paths(&["test/assets/1.csv"])
/// .unwrap().build().unwrap()
/// .map_row(|_headers, row| {
/// // Go creative here in the creation of your new row(s)
/// Ok(vec![
/// Ok(row.clone())
/// ].into_iter())
/// }, |old_headers| {
/// // be responsible and provide proper headers from the old ones
/// old_headers.clone()
/// })
/// .into_iter();
/// ```
#[inline]
fn map_row<F, H, R>(self, f: F, header_map: H) -> MapRow<Self, F>
where
Self: Sized,
F: Fn(&Headers, &Row) -> error::Result<R>,
H: Fn(&Headers) -> Headers,
R: Iterator<Item = RowResult>,
{
let new_headers = (header_map)(self.headers());
MapRow::new(self, f, new_headers)
}
/// Apply a function to a single column of the stream, this function dones't fail
/// if the column dones't exist.
#[inline]
fn map_col<F>(self, col: &str, f: F) -> MapCol<Self, F>
where
Self: Sized,
F: Fn(&str) -> error::Result<String>,
{
MapCol::new(self, col.into(), f)
}
/// filter entire rows out depending on one column's value and a
/// condition, leaving errored rows untouched.
#[inline]
fn filter_col<F>(self, col: &str, f: F) -> error::Result<FilterCol<Self, F>>
where
Self: Sized,
F: Fn(&str) -> bool,
{
FilterCol::new(self, col.into(), f)
}
/// filter entire rows out depending on one column's value and a
/// condition, leaving errored rows untouched.
#[inline]
fn filter_row<F>(self, f: F) -> FilterRow<Self, F>
where
Self: Sized,
F: Fn(&Headers, &Row) -> bool,
{
FilterRow::new(self, f)
}
}