Struct StringNameSpace

pub struct StringNameSpace(/* private fields */);

Specialized expressions for Series of DataType::String.

Implementations

impl StringNameSpace

pub fn contains_literal(self, pat: Expr) -> Expr

Check if a string value contains a literal substring.

pub fn contains(self, pat: Expr, strict: bool) -> Expr

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.

pub fn ends_with(self, sub: Expr) -> Expr

Check if a string value ends with the sub string.

pub fn starts_with(self, sub: Expr) -> Expr

Check if a string value starts with the sub string.

pub fn hex_encode(self) -> Expr

pub fn hex_decode(self, strict: bool) -> Expr

pub fn base64_encode(self) -> Expr

pub fn base64_decode(self, strict: bool) -> Expr

pub fn extract(self, pat: Expr, group_index: usize) -> Expr

Extract a regex pattern from the a string value. If group_index is out of bounds, null is returned.

pub fn extract_groups(self, pat: &str) -> Result<Expr, PolarsError>

pub fn pad_start(self, length: usize, fill_char: char) -> Expr

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.

pub fn pad_end(self, length: usize, fill_char: char) -> Expr

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.

pub fn zfill(self, length: Expr) -> Expr

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.

pub fn find_literal(self, pat: Expr) -> Expr

Find the index of a literal substring within another string value.

pub fn find(self, pat: Expr, strict: bool) -> Expr

Find the index of a substring defined by a regular expressions within another string value.

pub fn extract_all(self, pat: Expr) -> Expr

Extract each successive non-overlapping match in an individual string as an array

pub fn count_matches(self, pat: Expr, literal: bool) -> Expr

Count all successive non-overlapping regex matches.

pub fn strptime( self, dtype: DataType, options: StrptimeOptions, ambiguous: Expr, ) -> Expr

Convert a String column into a Date/Datetime/Time column.

pub fn to_date(self, options: StrptimeOptions) -> Expr

Convert a String column into a Date column.

pub fn to_datetime( self, time_unit: Option<TimeUnit>, time_zone: Option<PlSmallStr>, options: StrptimeOptions, ambiguous: Expr, ) -> Expr

Convert a String column into a Datetime column.

pub fn to_time(self, options: StrptimeOptions) -> Expr

Convert a String column into a Time column.

pub fn to_decimal(self, infer_length: usize) -> Expr

Convert a String column into a Decimal column.

pub fn join(self, delimiter: &str, ignore_nulls: bool) -> Expr

Concat the values into a string array.

Arguments

• delimiter - A string that will act as delimiter between values.

pub fn split(self, by: Expr) -> Expr

Split the string by a substring. The resulting dtype is List<String>.

pub fn split_inclusive(self, by: Expr) -> Expr

Split the string by a substring and keep the substring. The resulting dtype is List<String>.

pub fn split_exact(self, by: Expr, n: usize) -> Expr

Split exactly n times by a given substring. The resulting dtype is DataType::Struct.

pub fn split_exact_inclusive(self, by: Expr, n: usize) -> Expr

Split exactly n times by a given substring and keep the substring. The resulting dtype is DataType::Struct.

pub fn splitn(self, by: Expr, n: usize) -> Expr

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 replace(self, pat: Expr, value: Expr, literal: bool) -> Expr

Replace values that match a regex pat with a value.

pub fn replace_n(self, pat: Expr, value: Expr, literal: bool, n: i64) -> Expr

Replace values that match a regex pat with a value.

pub fn replace_all(self, pat: Expr, value: Expr, literal: bool) -> Expr

Replace all values that match a regex pat with a value.

pub fn normalize(self, form: UnicodeForm) -> Expr

Normalize each string

pub fn reverse(self) -> Expr

Reverse each string

pub fn strip_chars(self, matches: Expr) -> Expr

Remove leading and trailing characters, or whitespace if matches is None.

pub fn strip_chars_start(self, matches: Expr) -> Expr

Remove leading characters, or whitespace if matches is None.

pub fn strip_chars_end(self, matches: Expr) -> Expr

Remove trailing characters, or whitespace if matches is None.

pub fn strip_prefix(self, prefix: Expr) -> Expr

Remove prefix.

pub fn strip_suffix(self, suffix: Expr) -> Expr

Remove suffix.

pub fn to_lowercase(self) -> Expr

Convert all characters to lowercase.

pub fn to_uppercase(self) -> Expr

Convert all characters to uppercase.

pub fn to_titlecase(self) -> Expr

Convert all characters to titlecase.

pub fn to_integer(self, base: Expr, strict: bool) -> Expr

Parse string in base radix into decimal.

pub fn len_bytes(self) -> Expr

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)).

pub fn len_chars(self) -> Expr

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).

pub fn slice(self, offset: Expr, length: Expr) -> Expr

Slice the string values.

pub fn head(self, n: Expr) -> Expr

Take the first n characters of the string values.

pub fn tail(self, n: Expr) -> Expr

Take the last n characters of the string values.

pub fn json_decode( self, dtype: Option<DataType>, infer_schema_len: Option<usize>, ) -> Expr

pub fn json_path_match(self, pat: Expr) -> Expr

pub fn escape_regex(self) -> Expr