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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452
/*!
`csvsc` is a framework for building csv file processors.
Imagine you have N csv files with the same structure and you want to use them
to make other M csv files whose information depends in some way on the original
files. This is what csvcv was built for. With this tool you can build a
processing chain (_row stream_) that will take each of the input files and
generate new output files with the modifications.
# Quickstart
Start a new binary project with cargo:
```text
$ cargo new --bin miprocesadordecsv
```
Add `csvsc` and `encoding` as a dependency in `Cargo.toml`.
```toml
[dependencies]
csvsc = "2.2"
```
Now start building your processing chain. Specify the inputs (one or more csv
files), the transformations, and the output.
```
use csvsc::prelude::*;
let mut chain = InputStreamBuilder::from_paths(&[
// Put here the path to your source files, from 1 to a million
"test/assets/chicken_north.csv",
"test/assets/chicken_south.csv",
]).unwrap().build().unwrap()
// Here is where you do the magic: add columns, remove ones, filter
// the rows, group and aggregate, even probably transpose the data
// to fit your needs.
// Specify some (zero, one or many) output targets so that results of
// your computations get stored somewhere.
.flush(Target::path("data/output.csv")).unwrap()
.into_iter();
// And finally consume the stream, reporting any errors to stderr.
while let Some(item) = chain.next() {
if let Err(e) = item {
eprintln!("{}", e);
}
}
```
## Example
Grab your input files, in this case I'll use this two:
**chicken_north.csv**
```csv
month,eggs per week
1,3
1,NaN
1,6
2,
2,4
2,8
3,5
3,1
3,8
```
**chicken_south.csv**
```csv
month,eggs per week
1,2
1,NaN
1,
2,7
2,8
2,23
3,3
3,2
3,12
```
Now build your processing chain.
```rust
// main.rs
use csvsc::prelude::*;
use encoding::all::UTF_8;
let mut chain = InputStreamBuilder::from_paths(vec![
"test/assets/chicken_north.csv",
"test/assets/chicken_south.csv",
]).unwrap()
// optionally specify the encoding
.with_encoding(UTF_8)
// optionally add a column with the path of the source file as specified
// in the builder
.with_source_col("_source")
// build the row stream
.build().unwrap()
// Filter some columns with invalid values
.filter_col("eggs per week", |value| {
value.len() > 0 && value != "NaN"
}).unwrap()
// add a column with a value obtained from the filename ¡wow!
.add(
Column::with_name("region")
.from_column("_source")
.with_regex("_([a-z]+).csv").unwrap()
.definition("$1")
).unwrap()
// group by two columns, compute some aggregates
.group(["region", "month"], |row_stream| {
row_stream.reduce(vec![
Reducer::with_name("region").of_column("region").last("").unwrap(),
Reducer::with_name("month").of_column("month").last("").unwrap(),
Reducer::with_name("avg").of_column("eggs per week").average().unwrap(),
Reducer::with_name("sum").of_column("eggs per week").sum(0.0).unwrap(),
]).unwrap()
})
// Write a report to a single file that will contain all the data
.flush(
Target::path("data/report.csv")
).unwrap()
// This column will allow us to output to multiple files, in this case
// a report by month
.add(
Column::with_name("monthly report")
.from_all_previous()
.definition("data/monthly/{month}.csv")
).unwrap()
.del(vec!["month"])
// Write every row to a file specified by its `monthly report` column added
// previously
.flush(
Target::from_column("monthly report")
).unwrap()
// Pack the processing chain into an interator that can be consumed.
.into_iter();
// Consuming the iterator actually triggers all the transformations.
while let Some(item) = chain.next() {
item.unwrap();
}
```
This is what comes as output:
**data/monthly/1.csv**
```csv
region,avg,sum
south,2,2
north,4.5,9
```
**data/monthly/2.csv**
```csv
region,avg,sum
north,6,12
south,12.666666666666666,38
```
**data/monthly/3.csv**
```csv
region,avg,sum
north,4.666666666666667,14
south,5.666666666666667,17
```
**data/report.csv**
```csv
region,month,avg,sum
north,2,6,12
south,1,2,2
south,2,12.666666666666666,38
north,3,4.666666666666667,14
south,3,5.666666666666667,17
north,1,4.5,9
```
## Dig deeper
Check [`InputStreamBuilder`](input::InputStreamBuilder) to see more options for
starting a processing chain and reading your input.
Go to the [`RowStream`] documentation to see all the transformations available
as well as options to flush the data to files or standard I/O.
*/
pub mod add;
mod add_with;
mod group;
mod adjacent_group;
mod del;
pub mod error;
mod flush;
mod headers;
pub mod input;
mod inspect;
mod mock;
mod reduce;
mod rename;
mod row_stream;
mod map;
mod filter;
mod select;
pub mod prelude;
pub use crate::input::InputStream;
pub use crate::add::Column;
pub use crate::flush::Target;
pub use crate::row_stream::RowStream;
pub use crate::headers::Headers;
pub use crate::reduce::reducer::Reducer;
pub use crate::reduce::aggregate::Aggregate;
pub use crate::group::GroupCriteria;
pub use crate::error::{Error, RowResult};
pub use crate::mock::MockStream;
/// Type alias of csv::StringRecord. Represents a row of data.
pub type Row = csv::StringRecord;
impl From<Headers> for Row {
fn from(headers: Headers) -> Row {
headers.into_row()
}
}
#[cfg(test)]
mod tests {
use std::f64;
use crate::prelude::*;
#[test]
fn test_from_paths_api() {
let mut chain = InputStreamBuilder::from_paths(&[
"test/assets/1.csv",
"test/assets/2.csv",
]).unwrap().build().unwrap().into_iter();
assert_eq!(chain.next().unwrap().unwrap(), Row::from(vec!["1", "3"]));
}
#[test]
fn test_add_api() {
InputStreamBuilder::from_paths(&["test/assets/1.csv"]).unwrap().build().unwrap()
// Add a column whose value is built from the values of other columns
.add(
Column::with_name("_target")
.from_all_previous()
.definition("data/add/output/{a}.csv")
).unwrap()
// Add a column whose value is built from parts of a previous column,
// extracted with a regular expression.
.add(
Column::with_name("new_col")
.from_column("old_column")
.with_regex("regex").unwrap()
.definition("a definition")
).unwrap()
// Add a column arbitrarily. You can access the headers of the whole
// stream and the current row to compute its value.
.add_with("new_col2", |_headers, _row| {
Ok("new_value".into())
}).unwrap()
.into_iter();
}
#[test]
fn test_reduce_api() {
#[derive(Debug)]
struct Foo {
colname: String,
}
impl Aggregate for Foo {
fn update(&mut self, _headers: &Headers, _rs: &Row) -> crate::error::Result<()> {
unimplemented!()
}
fn colname(&self) -> &str {
&self.colname
}
fn value(&self) -> String {
"-".into()
}
}
InputStreamBuilder::from_paths(vec!["test/assets/1.csv"]).unwrap().build().unwrap()
.reduce(vec![
Reducer::with_name("rows").count(),
Reducer::with_name("avg").of_column("col").average().unwrap(),
Reducer::with_name("last").of_column("col").last("-").unwrap(),
Reducer::with_name("max").of_column("col").max(f64::NEG_INFINITY).unwrap(),
Reducer::with_name("min").of_column("col").min(f64::INFINITY).unwrap(),
Reducer::with_name("sum").of_column("col").sum(0.0).unwrap(),
Reducer::with_name("mul").of_column("col").product(1.0).unwrap(),
Reducer::with_name("closure").of_column("col").with_closure(|acc, cur| {
Ok(acc * cur.parse::<i32>().unwrap())
}, 1).unwrap(),
Reducer::custom(Foo { colname: String::from("custom") }),
]).unwrap()
.into_iter();
}
#[test]
fn test_filter_api() {
InputStreamBuilder::from_paths(vec!["test/assets/1.csv"]).unwrap().build().unwrap()
// filter entire rows out depending on one column's value and a
// condition, leaving errored rows untouched.
.filter_col("b", |value| {
value.is_empty() && value != "NaN"
}).unwrap()
// filter arbitrarily. You have access to the entire row
.filter_row(|headers, row| {
headers.get_field(row, "column").unwrap().is_empty()
})
.into_iter();
}
#[test]
fn test_group_api() {
InputStreamBuilder::from_paths(vec!["test/assets/1.csv"]).unwrap().build().unwrap()
.adjacent_group(["a", "b"], |stream| {
stream
})
.group(|headers: &Headers, row: &Row| {
headers.get_field(row, "b").unwrap().to_string()
}, |stream| {
stream
})
.into_iter();
}
#[test]
fn test_inspect_api() {
InputStreamBuilder::from_paths(vec!["test/assets/1.csv"]).unwrap().build().unwrap()
// pass every row through this closure. Nothing special, just to make
// debugging easier. You might want to print the value of a column
// for example.
.review(|headers, rs| {
if let Ok(row) = rs {
println!("Name: {:?}", headers.get_field(row, "name"));
}
})
.into_iter();
}
#[test]
fn test_rename_api() {
InputStreamBuilder::from_paths(vec!["test/assets/1.csv"]).unwrap().build().unwrap()
// rename a column
.rename("old_name", "new_name")
.into_iter();
}
#[test]
fn test_map_api() {
InputStreamBuilder::from_paths(vec!["test/assets/1.csv"]).unwrap().build().unwrap()
// pass every value of the specified column through this closure and
// replace it with the return value
.map_col("colname", |value| {
Ok(value.into())
})
.map_row(|_headers, row| {
Ok(vec![
Ok(row.clone())
].into_iter())
}, |headers| {
headers.clone()
})
.into_iter();
}
#[test]
fn test_del_api() {
InputStreamBuilder::from_paths(vec!["test/assets/1.csv"]).unwrap().build().unwrap()
// Delete columns by name
.del(vec!["b"])
.select(vec!["a"])
.into_iter();
}
#[test]
fn test_flush_api() {
let mut chain = InputStreamBuilder::from_paths(vec!["test/assets/1.csv"]).unwrap().build().unwrap()
.add(Column::with_name("_target").from_all_previous().definition("data/{a}.csv")).unwrap()
// Configure a flush target, this is the output of this processing
// chain, it can be a single file, multiple files or the standard
// output.
.flush(
Target::from_column("_target")
).unwrap()
.select(vec!["a", "b"])
.flush(
Target::path("data/a_path")
).unwrap()
.flush(
Target::stdout()
).unwrap()
.flush(
Target::stderr()
).unwrap()
.into_iter();
assert_eq!(chain.next().unwrap().unwrap(), Row::from(vec!["1", "3"]));
assert_eq!(chain.next().unwrap().unwrap(), Row::from(vec!["5", "2"]));
assert!(chain.next().is_none());
}
/*
#[test]
fn test_report_api() {
assert!(false, "make a report that can be flushed to a file or to stdout");
assert!(false, "this report should put every different error in a row and have a count in a different column");
}
*/
}