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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592
use super::*;
/// Specialized expressions for [`Series`] of [`DataType::String`].
pub struct StringNameSpace(pub(crate) Expr);
impl StringNameSpace {
/// Check if a string value contains a literal substring.
#[cfg(feature = "regex")]
pub fn contains_literal(self, pat: Expr) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::Contains {
literal: true,
strict: false,
}),
&[pat],
false,
true,
)
}
/// Check if this column of strings contains a Regex. If `strict` is `true`, then it is an error if any `pat` is
/// an invalid regex, whereas if `strict` is `false`, an invalid regex will simply evaluate to `false`.
#[cfg(feature = "regex")]
pub fn contains(self, pat: Expr, strict: bool) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::Contains {
literal: false,
strict,
}),
&[pat],
false,
true,
)
}
/// Uses aho-corasick to find many patterns.
///
/// # Arguments
/// - `patterns`: an expression that evaluates to an String column
/// - `ascii_case_insensitive`: Enable ASCII-aware case insensitive matching.
/// When this option is enabled, searching will be performed without respect to case for
/// ASCII letters (a-z and A-Z) only.
#[cfg(feature = "find_many")]
pub fn contains_any(self, patterns: Expr, ascii_case_insensitive: bool) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::ContainsMany {
ascii_case_insensitive,
}),
&[patterns],
false,
false,
)
}
/// Uses aho-corasick to replace many patterns.
/// # Arguments
/// - `patterns`: an expression that evaluates to a String column
/// - `replace_with`: an expression that evaluates to a String column
/// - `ascii_case_insensitive`: Enable ASCII-aware case-insensitive matching.
/// When this option is enabled, searching will be performed without respect to case for
/// ASCII letters (a-z and A-Z) only.
#[cfg(feature = "find_many")]
pub fn replace_many(
self,
patterns: Expr,
replace_with: Expr,
ascii_case_insensitive: bool,
) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::ReplaceMany {
ascii_case_insensitive,
}),
&[patterns, replace_with],
false,
false,
)
}
/// Uses aho-corasick to replace many patterns.
/// # Arguments
/// - `patterns`: an expression that evaluates to a String column
/// - `ascii_case_insensitive`: Enable ASCII-aware case-insensitive matching.
/// When this option is enabled, searching will be performed without respect to case for
/// ASCII letters (a-z and A-Z) only.
/// - `overlapping`: Whether matches may overlap.
#[cfg(feature = "find_many")]
pub fn extract_many(
self,
patterns: Expr,
ascii_case_insensitive: bool,
overlapping: bool,
) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::ExtractMany {
ascii_case_insensitive,
overlapping,
}),
&[patterns],
false,
false,
)
}
/// Check if a string value ends with the `sub` string.
pub fn ends_with(self, sub: Expr) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::EndsWith),
&[sub],
false,
true,
)
}
/// Check if a string value starts with the `sub` string.
pub fn starts_with(self, sub: Expr) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::StartsWith),
&[sub],
false,
true,
)
}
#[cfg(feature = "string_encoding")]
pub fn hex_encode(self) -> Expr {
self.0
.map_private(FunctionExpr::StringExpr(StringFunction::HexEncode))
}
#[cfg(feature = "binary_encoding")]
pub fn hex_decode(self, strict: bool) -> Expr {
self.0
.map_private(FunctionExpr::StringExpr(StringFunction::HexDecode(strict)))
}
#[cfg(feature = "string_encoding")]
pub fn base64_encode(self) -> Expr {
self.0
.map_private(FunctionExpr::StringExpr(StringFunction::Base64Encode))
}
#[cfg(feature = "binary_encoding")]
pub fn base64_decode(self, strict: bool) -> Expr {
self.0
.map_private(FunctionExpr::StringExpr(StringFunction::Base64Decode(
strict,
)))
}
/// Extract a regex pattern from the a string value. If `group_index` is out of bounds, null is returned.
pub fn extract(self, pat: Expr, group_index: usize) -> Expr {
self.0.map_many_private(
StringFunction::Extract(group_index).into(),
&[pat],
false,
true,
)
}
#[cfg(feature = "extract_groups")]
// Extract all captures groups from a regex pattern as a struct
pub fn extract_groups(self, pat: &str) -> PolarsResult<Expr> {
// regex will be compiled twice, because it doesn't support serde
// and we need to compile it here to determine the output datatype
let reg = regex::Regex::new(pat)?;
let names = reg
.capture_names()
.enumerate()
.skip(1)
.map(|(idx, opt_name)| {
opt_name
.map(|name| name.to_string())
.unwrap_or_else(|| format!("{idx}"))
})
.collect::<Vec<_>>();
let dtype = DataType::Struct(
names
.iter()
.map(|name| Field::new(name.as_str(), DataType::String))
.collect(),
);
Ok(self.0.map_private(
StringFunction::ExtractGroups {
dtype,
pat: pat.to_string(),
}
.into(),
))
}
/// Pad the start of the string until it reaches the given length.
///
/// Padding is done using the specified `fill_char`.
/// Strings with length equal to or greater than the given length are
/// returned as-is.
#[cfg(feature = "string_pad")]
pub fn pad_start(self, length: usize, fill_char: char) -> Expr {
self.0
.map_private(StringFunction::PadStart { length, fill_char }.into())
}
/// Pad the end of the string until it reaches the given length.
///
/// Padding is done using the specified `fill_char`.
/// Strings with length equal to or greater than the given length are
/// returned as-is.
#[cfg(feature = "string_pad")]
pub fn pad_end(self, length: usize, fill_char: char) -> Expr {
self.0
.map_private(StringFunction::PadEnd { length, fill_char }.into())
}
/// Pad the start of the string with zeros until it reaches the given length.
///
/// A sign prefix (`-`) is handled by inserting the padding after the sign
/// character rather than before.
/// Strings with length equal to or greater than the given length are
/// returned as-is.
#[cfg(feature = "string_pad")]
pub fn zfill(self, length: Expr) -> Expr {
self.0
.map_many_private(StringFunction::ZFill.into(), &[length], false, false)
}
/// Find the index of a literal substring within another string value.
#[cfg(feature = "regex")]
pub fn find_literal(self, pat: Expr) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::Find {
literal: true,
strict: false,
}),
&[pat],
false,
true,
)
}
/// Find the index of a substring defined by a regular expressons within another string value.
#[cfg(feature = "regex")]
pub fn find(self, pat: Expr, strict: bool) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::Find {
literal: false,
strict,
}),
&[pat],
false,
true,
)
}
/// Extract each successive non-overlapping match in an individual string as an array
pub fn extract_all(self, pat: Expr) -> Expr {
self.0
.map_many_private(StringFunction::ExtractAll.into(), &[pat], false, false)
}
/// Count all successive non-overlapping regex matches.
pub fn count_matches(self, pat: Expr, literal: bool) -> Expr {
self.0.map_many_private(
StringFunction::CountMatches(literal).into(),
&[pat],
false,
false,
)
}
/// Convert a String column into a Date/Datetime/Time column.
#[cfg(feature = "temporal")]
pub fn strptime(self, dtype: DataType, options: StrptimeOptions, ambiguous: Expr) -> Expr {
self.0.map_many_private(
StringFunction::Strptime(dtype, options).into(),
&[ambiguous],
false,
false,
)
}
/// Convert a String column into a Date column.
#[cfg(feature = "dtype-date")]
pub fn to_date(self, options: StrptimeOptions) -> Expr {
self.strptime(DataType::Date, options, lit("raise"))
}
/// Convert a String column into a Datetime column.
#[cfg(feature = "dtype-datetime")]
pub fn to_datetime(
self,
time_unit: Option<TimeUnit>,
time_zone: Option<TimeZone>,
options: StrptimeOptions,
ambiguous: Expr,
) -> Expr {
// If time_unit is None, try to infer it from the format or set a default
let time_unit = match (&options.format, time_unit) {
(_, Some(time_unit)) => time_unit,
(Some(format), None) => {
if format.contains("%.9f") || format.contains("%9f") {
TimeUnit::Nanoseconds
} else if format.contains("%.3f") || format.contains("%3f") {
TimeUnit::Milliseconds
} else {
TimeUnit::Microseconds
}
},
(None, None) => TimeUnit::Microseconds,
};
self.strptime(DataType::Datetime(time_unit, time_zone), options, ambiguous)
}
/// Convert a String column into a Time column.
#[cfg(feature = "dtype-time")]
pub fn to_time(self, options: StrptimeOptions) -> Expr {
self.strptime(DataType::Time, options, lit("raise"))
}
/// Convert a String column into a Decimal column.
#[cfg(feature = "dtype-decimal")]
pub fn to_decimal(self, infer_length: usize) -> Expr {
self.0
.map_private(StringFunction::ToDecimal(infer_length).into())
}
/// Concat the values into a string array.
/// # Arguments
///
/// * `delimiter` - A string that will act as delimiter between values.
#[cfg(feature = "concat_str")]
pub fn join(self, delimiter: &str, ignore_nulls: bool) -> Expr {
self.0
.apply_private(
StringFunction::ConcatVertical {
delimiter: delimiter.to_owned(),
ignore_nulls,
}
.into(),
)
.with_function_options(|mut options| {
options.returns_scalar = true;
options.collect_groups = ApplyOptions::GroupWise;
options
})
}
/// Split the string by a substring. The resulting dtype is `List<String>`.
pub fn split(self, by: Expr) -> Expr {
self.0
.map_many_private(StringFunction::Split(false).into(), &[by], false, false)
}
/// Split the string by a substring and keep the substring. The resulting dtype is `List<String>`.
pub fn split_inclusive(self, by: Expr) -> Expr {
self.0
.map_many_private(StringFunction::Split(true).into(), &[by], false, false)
}
#[cfg(feature = "dtype-struct")]
/// Split exactly `n` times by a given substring. The resulting dtype is [`DataType::Struct`].
pub fn split_exact(self, by: Expr, n: usize) -> Expr {
self.0.map_many_private(
StringFunction::SplitExact {
n,
inclusive: false,
}
.into(),
&[by],
false,
false,
)
}
#[cfg(feature = "dtype-struct")]
/// Split exactly `n` times by a given substring and keep the substring.
/// The resulting dtype is [`DataType::Struct`].
pub fn split_exact_inclusive(self, by: Expr, n: usize) -> Expr {
self.0.map_many_private(
StringFunction::SplitExact { n, inclusive: true }.into(),
&[by],
false,
false,
)
}
#[cfg(feature = "dtype-struct")]
/// Split by a given substring, returning exactly `n` items. If there are more possible splits,
/// keeps the remainder of the string intact. The resulting dtype is [`DataType::Struct`].
pub fn splitn(self, by: Expr, n: usize) -> Expr {
self.0
.map_many_private(StringFunction::SplitN(n).into(), &[by], false, false)
}
#[cfg(feature = "regex")]
/// Replace values that match a regex `pat` with a `value`.
pub fn replace(self, pat: Expr, value: Expr, literal: bool) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::Replace { n: 1, literal }),
&[pat, value],
false,
true,
)
}
#[cfg(feature = "regex")]
/// Replace values that match a regex `pat` with a `value`.
pub fn replace_n(self, pat: Expr, value: Expr, literal: bool, n: i64) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::Replace { n, literal }),
&[pat, value],
false,
true,
)
}
#[cfg(feature = "regex")]
/// Replace all values that match a regex `pat` with a `value`.
pub fn replace_all(self, pat: Expr, value: Expr, literal: bool) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::Replace { n: -1, literal }),
&[pat, value],
false,
true,
)
}
#[cfg(feature = "string_reverse")]
/// Reverse each string
pub fn reverse(self) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::Reverse),
&[],
false,
false,
)
}
/// Remove leading and trailing characters, or whitespace if matches is None.
pub fn strip_chars(self, matches: Expr) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::StripChars),
&[matches],
false,
false,
)
}
/// Remove leading characters, or whitespace if matches is None.
pub fn strip_chars_start(self, matches: Expr) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::StripCharsStart),
&[matches],
false,
false,
)
}
/// Remove trailing characters, or whitespace if matches is None.
pub fn strip_chars_end(self, matches: Expr) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::StripCharsEnd),
&[matches],
false,
false,
)
}
/// Remove prefix.
pub fn strip_prefix(self, prefix: Expr) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::StripPrefix),
&[prefix],
false,
false,
)
}
/// Remove suffix.
pub fn strip_suffix(self, suffix: Expr) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::StripSuffix),
&[suffix],
false,
false,
)
}
/// Convert all characters to lowercase.
pub fn to_lowercase(self) -> Expr {
self.0
.map_private(FunctionExpr::StringExpr(StringFunction::Lowercase))
}
/// Convert all characters to uppercase.
pub fn to_uppercase(self) -> Expr {
self.0
.map_private(FunctionExpr::StringExpr(StringFunction::Uppercase))
}
/// Convert all characters to titlecase.
#[cfg(feature = "nightly")]
pub fn to_titlecase(self) -> Expr {
self.0
.map_private(FunctionExpr::StringExpr(StringFunction::Titlecase))
}
#[cfg(feature = "string_to_integer")]
/// Parse string in base radix into decimal.
pub fn to_integer(self, base: Expr, strict: bool) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::ToInteger(strict)),
&[base],
false,
false,
)
}
/// Return the length of each string as the number of bytes.
///
/// When working with non-ASCII text, the length in bytes is not the same
/// as the length in characters. You may want to use
/// [`len_chars`] instead. Note that `len_bytes` is much more
/// performant (_O(1)_) than [`len_chars`] (_O(n)_).
///
/// [`len_chars`]: StringNameSpace::len_chars
pub fn len_bytes(self) -> Expr {
self.0
.map_private(FunctionExpr::StringExpr(StringFunction::LenBytes))
}
/// Return the length of each string as the number of characters.
///
/// When working with ASCII text, use [`len_bytes`] instead to achieve
/// equivalent output with much better performance:
/// [`len_bytes`] runs in _O(1)_, while `len_chars` runs in _O(n)_.
///
/// [`len_bytes`]: StringNameSpace::len_bytes
pub fn len_chars(self) -> Expr {
self.0
.map_private(FunctionExpr::StringExpr(StringFunction::LenChars))
}
/// Slice the string values.
pub fn slice(self, offset: Expr, length: Expr) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::Slice),
&[offset, length],
false,
false,
)
}
/// Take the first `n` characters of the string values.
pub fn head(self, n: Expr) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::Head),
&[n],
false,
false,
)
}
/// Take the last `n` characters of the string values.
pub fn tail(self, n: Expr) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::Tail),
&[n],
false,
false,
)
}
#[cfg(feature = "extract_jsonpath")]
pub fn json_decode(self, dtype: Option<DataType>, infer_schema_len: Option<usize>) -> Expr {
self.0
.map_private(FunctionExpr::StringExpr(StringFunction::JsonDecode {
dtype,
infer_schema_len,
}))
}
#[cfg(feature = "extract_jsonpath")]
pub fn json_path_match(self, pat: Expr) -> Expr {
self.0.map_many_private(
FunctionExpr::StringExpr(StringFunction::JsonPathMatch),
&[pat],
false,
false,
)
}
}