`StringOperations`¶

Namespace for operations on strings.

This class cannot be instantiated directly. It can only be accessed using the str attribute of a cell.

Examples:

pipeline example {
    val column = Column("a", ["ab", "bc", "cd"]);
    out column.transform((cell) -> cell.str.toUppercase());
}

Stub code in StringOperations.sdsstub

class StringOperations {
    /**
     * Check if the string contains the substring.
     *
     * @param substring The substring to search for.
     *
     * @result contains Whether the string contains the substring.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["ab", "cd", null]);
     *     out column.transform((cell) -> cell.str.contains("b"));
     * }
     */
    @Pure
    fun contains(
        substring: ConvertibleToStringCell
    ) -> contains: Cell<Boolean?>

    /**
     * Check if the string ends with the suffix.
     *
     * @param suffix The expected suffix.
     *
     * @result cell Whether the string ends with the suffix.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["ab", "bc", null]);
     *     out column.transform((cell) -> cell.str.endsWith("b"));
     * }
     */
    @Pure
    @PythonName("ends_with")
    fun endsWith(
        suffix: ConvertibleToStringCell
    ) -> cell: Cell<Boolean?>

    /**
     * Get the index of the first occurrence of the substring.
     *
     * @param substring The substring to search for.
     *
     * @result cell The index of the first occurrence of the substring. If the substring is not found, null is returned.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["ab", "cd", null]);
     *     out column.transform((cell) -> cell.str.indexOf("b"));
     * }
     */
    @Pure
    @PythonName("index_of")
    fun indexOf(
        substring: ConvertibleToStringCell
    ) -> cell: Cell<Int?>

    /**
     * Get the number of characters.
     *
     * @param optimizeForAscii Greatly speed up this operation if the string is ASCII-only. If the string contains non-ASCII characters,
     * this option will return incorrect results, though.
     *
     * @result cell The number of characters.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["", "a", "abc", null]);
     *     out column.transform((cell) -> cell.str.length());
     * }
     */
    @Pure
    fun length(
        @PythonName("optimize_for_ascii") optimizeForAscii: Boolean = false
    ) -> cell: Cell<Int?>

    /**
     * Pad the end of the string with the given character until it has the given length.
     *
     * @param length The minimum length of the string. If the string is already at least as long, it is returned unchanged. Must
     * be greater than or equal to 0.
     * @param character How to pad the string. Must be a single character.
     *
     * @result cell The padded string.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["ab", "bcde", null]);
     *     out column.transform((cell) -> cell.str.padEnd(3));
     *     out column.transform((cell) -> cell.str.padEnd(3, character="~"));
     * }
     */
    @Pure
    @PythonName("pad_end")
    fun padEnd(
        const length: Int,
        character: String = " "
    ) -> cell: Cell<String?> where {
        length >= 0
    }

    /**
     * Pad the start of the string with the given character until it has the given length.
     *
     * @param length The minimum length of the string. If the string is already at least as long, it is returned unchanged. Must
     * be greater than or equal to 0.
     * @param character How to pad the string. Must be a single character.
     *
     * @result cell The padded string.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["ab", "bcde", null]);
     *     out column.transform((cell) -> cell.str.padStart(3));
     *     out column.transform((cell) -> cell.str.padStart(3, character="~"));
     * }
     */
    @Pure
    @PythonName("pad_start")
    fun padStart(
        const length: Int,
        character: String = " "
    ) -> cell: Cell<String?> where {
        length >= 0
    }

    /**
     * Remove a prefix from the string. Strings without the prefix are not changed.
     *
     * @param prefix The prefix to remove.
     *
     * @result cell The string without the prefix.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["ab", "bc", null]);
     *     out column.transform((cell) -> cell.str.removePrefix("a"));
     * }
     */
    @Pure
    @PythonName("remove_prefix")
    fun removePrefix(
        prefix: ConvertibleToStringCell
    ) -> cell: Cell<String?>

    /**
     * Remove a suffix from the string. Strings without the suffix are not changed.
     *
     * @param suffix The suffix to remove.
     *
     * @result cell The string without the suffix.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["ab", "bc", null]);
     *     out column.transform((cell) -> cell.str.removeSuffix("b"));
     * }
     */
    @Pure
    @PythonName("remove_suffix")
    fun removeSuffix(
        suffix: ConvertibleToStringCell
    ) -> cell: Cell<String?>

    /**
     * Repeat the string a number of times.
     *
     * @param count The number of times to repeat the string. Must be greater than or equal to 0.
     *
     * @result cell The repeated string.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["ab", "bc", null]);
     *     out column.transform((cell) -> cell.str.repeat(2));
     * }
     */
    @Pure
    fun repeat(
        count: ConvertibleToIntCell
    ) -> cell: Cell<String?>

    /**
     * Replace all occurrences of the old substring with the new substring.
     *
     * @param old The substring to replace.
     * @param new The substring to replace with.
     *
     * @result cell The string with all occurrences replaced.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["ab", "bc", null]);
     *     out column.transform((cell) -> cell.str.replaceAll("b", "z"));
     * }
     */
    @Pure
    @PythonName("replace_all")
    fun replaceAll(
        old: ConvertibleToStringCell,
        new: ConvertibleToStringCell
    ) -> cell: Cell<String?>

    /**
     * Reverse the string.
     *
     * @result cell The reversed string.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["ab", "bc", null]);
     *     out column.transform((cell) -> cell.str.reverse());
     * }
     */
    @Pure
    fun reverse() -> cell: Cell<String?>

    /**
     * Get a slice of the string.
     *
     * @param start The start index of the slice. Nonnegative indices are counted from the beginning (starting at 0), negative
     * indices from the end (starting at -1).
     * @param length The length of the slice. If None, the slice contains all characters starting from `start`. Must greater than
     * or equal to 0.
     *
     * @result cell The sliced string.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["abc", "de", null]);
     *     out column.transform((cell) -> cell.str.slice(start = 1));
     *     out column.transform((cell) -> cell.str.slice(start = 1, length = 1));
     * }
     */
    @Pure
    fun slice(
        start: ConvertibleToIntCell = 0,
        length: ConvertibleToIntCell = null
    ) -> cell: Cell<String?>

    /**
     * Check if the string starts with the prefix.
     *
     * @param prefix The expected prefix.
     *
     * @result cell Whether the string starts with the prefix.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["ab", "bc", null]);
     *     out column.transform((cell) -> cell.str.startsWith("a"));
     * }
     */
    @Pure
    @PythonName("starts_with")
    fun startsWith(
        prefix: ConvertibleToStringCell
    ) -> cell: Cell<Boolean?>

    /**
     * Remove leading and trailing characters.
     *
     * @param characters The characters to remove. If None, whitespace is removed.
     *
     * @result cell The stripped string.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["  ab  ", "~ bc ~", null]);
     *     out column.transform((cell) -> cell.str.strip());
     *     out column.transform((cell) -> cell.str.strip(characters=" ~"));
     * }
     */
    @Pure
    fun strip(
        characters: ConvertibleToStringCell = null
    ) -> cell: Cell<String?>

    /**
     * Remove trailing characters.
     *
     * @param characters The characters to remove. If None, whitespace is removed.
     *
     * @result cell The stripped string.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["  ab  ", "~ bc ~", null]);
     *     out column.transform((cell) -> cell.str.stripEnd());
     *     out column.transform((cell) -> cell.str.stripEnd(characters=" ~"));
     * }
     */
    @Pure
    @PythonName("strip_end")
    fun stripEnd(
        characters: ConvertibleToStringCell = null
    ) -> cell: Cell<String?>

    /**
     * Remove leading characters.
     *
     * @param characters The characters to remove. If None, whitespace is removed.
     *
     * @result cell The stripped string.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["  ab  ", "~ bc ~", null]);
     *     out column.transform((cell) -> cell.str.stripStart());
     *     out column.transform((cell) -> cell.str.stripStart(characters=" ~"));
     * }
     */
    @Pure
    @PythonName("strip_start")
    fun stripStart(
        characters: ConvertibleToStringCell = null
    ) -> cell: Cell<String?>

    /**
     * Convert a string to a date.
     *
     * The `format` parameter controls the presentation. It can be `"iso"` to target ISO 8601 or a custom string. The
     * custom string can contain fixed specifiers (see below), which are replaced with the corresponding values. The
     * specifiers are case-sensitive and always enclosed in curly braces. Other text is included in the output
     * verbatim. To include a literal opening curly brace, use `\{`, and to include a literal backslash, use `\\`.
     *
     * The following specifiers are available:
     *
     * - `{Y}`, `{_Y}`, `{^Y}`: Year (zero-padded to four digits, space-padded to four digits, no padding).
     * - `{Y99}`, `{_Y99}`, `{^Y99}`: Year modulo 100 (zero-padded to two digits, space-padded to two digits, no
     *   padding).
     * - `{M}`, `{_M}`, `{^M}`: Month (zero-padded to two digits, space-padded to two digits, no padding).
     * - `{M-full}`: Full name of the month (e.g. "January").
     * - `{M-short}`: Abbreviated name of the month with three letters (e.g. "Jan").
     * - `{W}`, `{_W}`, `{^W}`: Week number as defined by ISO 8601 (zero-padded to two digits, space-padded to two
     *   digits, no padding).
     * - `{D}`, `{_D}`, `{^D}`: Day of the month (zero-padded to two digits, space-padded to two digits, no padding).
     * - `{DOW}`: Day of the week as defined by ISO 8601 (1 = Monday, 7 = Sunday).
     * - `{DOW-full}`: Full name of the day of the week (e.g. "Monday").
     * - `{DOW-short}`: Abbreviated name of the day of the week with three letters (e.g. "Mon").
     * - `{DOY}`, `{_DOY}`, `{^DOY}`: Day of the year, ranging from 1 to 366 (zero-padded to three digits, space-padded
     *   to three digits, no padding).
     *
     * The specifiers follow certain conventions:
     *
     * - If a component may be formatted in multiple ways, we use shorter specifiers for ISO 8601. Specifiers for
     *   other formats have a prefix (same value with different padding, see below) or suffix (other differences).
     * - By default, value are zero-padded, where applicable.
     * - A leading underscore (`_`) means the value is space-padded.
     * - A leading caret (`^`) means the value has no padding (think of the caret in regular expressions).
     *
     * @param format The format to use.
     *
     * @result cell The parsed date.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["1999-02-03", "03.02.2001", "abc", null]);
     *     out column.transform((cell) -> cell.str.toDate());
     *     out column.transform((cell) -> cell.str.toDate(format="{D}.{M}.{Y}"));
     * }
     */
    @Pure
    @PythonName("to_date")
    fun toDate(
        format: String? = "iso"
    ) -> cell: Cell<Date?>

    /**
     * Convert a string to a datetime.
     *
     * The `format` parameter controls the presentation. It can be `"iso"` to target ISO 8601 or a custom string. The
     * custom string can contain fixed specifiers (see below), which are replaced with the corresponding values. The
     * specifiers are case-sensitive and always enclosed in curly braces. Other text is included in the output
     * verbatim. To include a literal opening curly brace, use `\{`, and to include a literal backslash, use `\\`.
     *
     * The following specifiers for _date components_ are available for **datetime** and **date**:
     *
     * - `{Y}`, `{_Y}`, `{^Y}`: Year (zero-padded to four digits, space-padded to four digits, no padding).
     * - `{Y99}`, `{_Y99}`, `{^Y99}`: Year modulo 100 (zero-padded to two digits, space-padded to two digits, no
     *   padding).
     * - `{M}`, `{_M}`, `{^M}`: Month (zero-padded to two digits, space-padded to two digits, no padding).
     * - `{M-full}`: Full name of the month (e.g. "January").
     * - `{M-short}`: Abbreviated name of the month with three letters (e.g. "Jan").
     * - `{W}`, `{_W}`, `{^W}`: Week number as defined by ISO 8601 (zero-padded to two digits, space-padded to two
     *   digits, no padding).
     * - `{D}`, `{_D}`, `{^D}`: Day of the month (zero-padded to two digits, space-padded to two digits, no padding).
     * - `{DOW}`: Day of the week as defined by ISO 8601 (1 = Monday, 7 = Sunday).
     * - `{DOW-full}`: Full name of the day of the week (e.g. "Monday").
     * - `{DOW-short}`: Abbreviated name of the day of the week with three letters (e.g. "Mon").
     * - `{DOY}`, `{_DOY}`, `{^DOY}`: Day of the year, ranging from 1 to 366 (zero-padded to three digits, space-padded
     *   to three digits, no padding).
     *
     * The following specifiers for _time components_ are available for **datetime** and **time**:
     *
     * - `{h}`, `{_h}`, `{^h}`: Hour (zero-padded to two digits, space-padded to two digits, no padding).
     * - `{h12}`, `{_h12}`, `{^h12}`: Hour in 12-hour format (zero-padded to two digits, space-padded to two digits, no
     *   padding).
     * - `{m}`, `{_m}`, `{^m}`: Minute (zero-padded to two digits, space-padded to two digits, no padding).
     * - `{s}`, `{_s}`, `{^s}`: Second (zero-padded to two digits, space-padded to two digits, no padding).
     * - `{.f}`: Fractional seconds with a leading decimal point.
     * - `{ms}`: Millisecond (zero-padded to three digits).
     * - `{us}`: Microsecond (zero-padded to six digits).
     * - `{ns}`: Nanosecond (zero-padded to nine digits).
     * - `{AM/PM}`: AM or PM (uppercase).
     * - `{am/pm}`: am or pm (lowercase).
     *
     * The following specifiers are available for **datetime** only:
     *
     * - `{z}`: Offset of the timezone from UTC without a colon (e.g. "+0000").
     * - `{:z}`: Offset of the timezone from UTC with a colon (e.g. "+00:00").
     * - `{u}`: The UNIX timestamp in seconds.
     *
     * The specifiers follow certain conventions:
     *
     * - Generally, date components use uppercase letters and time components use lowercase letters.
     * - If a component may be formatted in multiple ways, we use shorter specifiers for ISO 8601. Specifiers for
     *   other formats have a prefix (same value with different padding, see below) or suffix (other differences).
     * - By default, value are zero-padded, where applicable.
     * - A leading underscore (`_`) means the value is space-padded.
     * - A leading caret (`^`) means the value has no padding (think of the caret in regular expressions).
     *
     * @param format The format to use.
     *
     * @result cell The parsed datetime.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["1999-12-31T01:02:03Z", "12:30 Jan 23 2024", "abc", null]);
     *     out column.transform((cell) -> cell.str.toDatetime());
     *     out column.transform((cell) -> cell.str.toDatetime(
     *         format="{h}:{m} {M-short} {D} {Y}"
     *     ));
     * }
     */
    @Pure
    @PythonName("to_datetime")
    fun toDatetime(
        format: String? = "iso"
    ) -> cell: Cell<Datetime?>

    /**
     * Convert the string to a float.
     *
     * @result cell The float value. If the string cannot be converted to a float, null is returned.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["1", "1.5", "abc", null]);
     *     out column.transform((cell) -> cell.str.toFloat());
     * }
     */
    @Pure
    @PythonName("to_float")
    fun toFloat() -> cell: Cell<Float?>

    /**
     * Convert the string to an integer.
     *
     * @param base The base of the integer.
     *
     * @result cell The integer value. If the string cannot be converted to an integer, null is returned.
     *
     * @example
     * pipeline example {
     *     val column1 = Column("a", ["1", "10", "abc", null]);
     *     out column1.transform((cell) -> cell.str.toInt());
     * }
     *
     * @example
     * pipeline example {
     *     val column2 = Column("a", ["1", "10", "abc", null]);
     *     out column2.transform((cell) -> cell.str.toInt(base = 2));
     * }
     */
    @Pure
    @PythonName("to_int")
    fun toInt(
        base: ConvertibleToIntCell = 10
    ) -> cell: Cell<Int?>

    /**
     * Convert the string to lowercase.
     *
     * @result cell The lowercase string.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["AB", "BC", null]);
     *     out column.transform((cell) -> cell.str.toLowercase());
     * }
     */
    @Pure
    @PythonName("to_lowercase")
    fun toLowercase() -> cell: Cell<String?>

    /**
     * Convert a string to a time.
     *
     * The `format` parameter controls the presentation. It can be `"iso"` to target ISO 8601 or a custom string. The
     * custom string can contain fixed specifiers (see below), which are replaced with the corresponding values. The
     * specifiers are case-sensitive and always enclosed in curly braces. Other text is included in the output
     * verbatim. To include a literal opening curly brace, use `\{`, and to include a literal backslash, use `\\`.
     *
     * The following specifiers are available:
     *
     * - `{h}`, `{_h}`, `{^h}`: Hour (zero-padded to two digits, space-padded to two digits, no padding).
     * - `{h12}`, `{_h12}`, `{^h12}`: Hour in 12-hour format (zero-padded to two digits, space-padded to two digits, no
     *   padding).
     * - `{m}`, `{_m}`, `{^m}`: Minute (zero-padded to two digits, space-padded to two digits, no padding).
     * - `{s}`, `{_s}`, `{^s}`: Second (zero-padded to two digits, space-padded to two digits, no padding).
     * - `{.f}`: Fractional seconds with a leading decimal point.
     * - `{ms}`: Millisecond (zero-padded to three digits).
     * - `{us}`: Microsecond (zero-padded to six digits).
     * - `{ns}`: Nanosecond (zero-padded to nine digits).
     * - `{AM/PM}`: AM or PM (uppercase).
     * - `{am/pm}`: am or pm (lowercase).
     *
     * The specifiers follow certain conventions:
     *
     * - If a component may be formatted in multiple ways, we use shorter specifiers for ISO 8601. Specifiers for
     *   other formats have a prefix (same value with different padding, see below) or suffix (other differences).
     * - By default, value are zero-padded, where applicable.
     * - A leading underscore (`_`) means the value is space-padded.
     * - A leading caret (`^`) means the value has no padding (think of the caret in regular expressions).
     *
     * @param format The format to use.
     *
     * @result cell The parsed time.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["12:34", "12:34:56", "12:34:56.789", "abc", null]);
     *     out column.transform((cell) -> cell.str.toTime());
     *     out column.transform((cell) -> cell.str.toTime(format="{h}:{m}"));
     * }
     */
    @Pure
    @PythonName("to_time")
    fun toTime(
        format: String? = "iso"
    ) -> cell: Cell<Time?>

    /**
     * Convert the string to uppercase.
     *
     * @result cell The uppercase string.
     *
     * @example
     * pipeline example {
     *     val column = Column("a", ["ab", "bc", null]);
     *     out column.transform((cell) -> cell.str.toUppercase());
     * }
     */
    @Pure
    @PythonName("to_uppercase")
    fun toUppercase() -> cell: Cell<String?>
}

`contains`¶

Check if the string contains the substring.

Parameters:

Name	Type	Description	Default
`substring`	`union<String, Cell<Any?>?>`	The substring to search for.	-

Results:

Name	Type	Description
`contains`	`Cell<Boolean?>`	Whether the string contains the substring.

Examples:

pipeline example {
    val column = Column("a", ["ab", "cd", null]);
    out column.transform((cell) -> cell.str.contains("b"));
}

Stub code in StringOperations.sdsstub

@Pure
fun contains(
    substring: ConvertibleToStringCell
) -> contains: Cell<Boolean?>

`endsWith`¶

Check if the string ends with the suffix.

Parameters:

Name	Type	Description	Default
`suffix`	`union<String, Cell<Any?>?>`	The expected suffix.	-

Results:

Name	Type	Description
`cell`	`Cell<Boolean?>`	Whether the string ends with the suffix.

Examples:

pipeline example {
    val column = Column("a", ["ab", "bc", null]);
    out column.transform((cell) -> cell.str.endsWith("b"));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("ends_with")
fun endsWith(
    suffix: ConvertibleToStringCell
) -> cell: Cell<Boolean?>

`indexOf`¶

Get the index of the first occurrence of the substring.

Parameters:

Name	Type	Description	Default
`substring`	`union<String, Cell<Any?>?>`	The substring to search for.	-

Results:

Name	Type	Description
`cell`	`Cell<Int?>`	The index of the first occurrence of the substring. If the substring is not found, null is returned.

Examples:

pipeline example {
    val column = Column("a", ["ab", "cd", null]);
    out column.transform((cell) -> cell.str.indexOf("b"));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("index_of")
fun indexOf(
    substring: ConvertibleToStringCell
) -> cell: Cell<Int?>

`length`¶

Get the number of characters.

Parameters:

Name	Type	Description	Default
`optimizeForAscii`	`Boolean`	Greatly speed up this operation if the string is ASCII-only. If the string contains non-ASCII characters, this option will return incorrect results, though.	`false`

Results:

Name	Type	Description
`cell`	`Cell<Int?>`	The number of characters.

Examples:

pipeline example {
    val column = Column("a", ["", "a", "abc", null]);
    out column.transform((cell) -> cell.str.length());
}

Stub code in StringOperations.sdsstub

@Pure
fun length(
    @PythonName("optimize_for_ascii") optimizeForAscii: Boolean = false
) -> cell: Cell<Int?>

`padEnd`¶

Pad the end of the string with the given character until it has the given length.

Parameters:

Name	Type	Description	Default
`length`	`Int`	The minimum length of the string. If the string is already at least as long, it is returned unchanged. Must be greater than or equal to 0.	-
`character`	`String`	How to pad the string. Must be a single character.	`" "`

Results:

Name	Type	Description
`cell`	`Cell<String?>`	The padded string.

Examples:

pipeline example {
    val column = Column("a", ["ab", "bcde", null]);
    out column.transform((cell) -> cell.str.padEnd(3));
    out column.transform((cell) -> cell.str.padEnd(3, character="~"));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("pad_end")
fun padEnd(
    const length: Int,
    character: String = " "
) -> cell: Cell<String?> where {
    length >= 0
}

`padStart`¶

Pad the start of the string with the given character until it has the given length.

Parameters:

Name	Type	Description	Default
`length`	`Int`	The minimum length of the string. If the string is already at least as long, it is returned unchanged. Must be greater than or equal to 0.	-
`character`	`String`	How to pad the string. Must be a single character.	`" "`

Results:

Name	Type	Description
`cell`	`Cell<String?>`	The padded string.

Examples:

pipeline example {
    val column = Column("a", ["ab", "bcde", null]);
    out column.transform((cell) -> cell.str.padStart(3));
    out column.transform((cell) -> cell.str.padStart(3, character="~"));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("pad_start")
fun padStart(
    const length: Int,
    character: String = " "
) -> cell: Cell<String?> where {
    length >= 0
}

`removePrefix`¶

Remove a prefix from the string. Strings without the prefix are not changed.

Parameters:

Name	Type	Description	Default
`prefix`	`union<String, Cell<Any?>?>`	The prefix to remove.	-

Results:

Name	Type	Description
`cell`	`Cell<String?>`	The string without the prefix.

Examples:

pipeline example {
    val column = Column("a", ["ab", "bc", null]);
    out column.transform((cell) -> cell.str.removePrefix("a"));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("remove_prefix")
fun removePrefix(
    prefix: ConvertibleToStringCell
) -> cell: Cell<String?>

`removeSuffix`¶

Remove a suffix from the string. Strings without the suffix are not changed.

Parameters:

Name	Type	Description	Default
`suffix`	`union<String, Cell<Any?>?>`	The suffix to remove.	-

Results:

Name	Type	Description
`cell`	`Cell<String?>`	The string without the suffix.

Examples:

pipeline example {
    val column = Column("a", ["ab", "bc", null]);
    out column.transform((cell) -> cell.str.removeSuffix("b"));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("remove_suffix")
fun removeSuffix(
    suffix: ConvertibleToStringCell
) -> cell: Cell<String?>

`repeat`¶

Repeat the string a number of times.

Parameters:

Name	Type	Description	Default
`count`	`union<Int, Cell<Any?>?>`	The number of times to repeat the string. Must be greater than or equal to 0.	-

Results:

Name	Type	Description
`cell`	`Cell<String?>`	The repeated string.

Examples:

pipeline example {
    val column = Column("a", ["ab", "bc", null]);
    out column.transform((cell) -> cell.str.repeat(2));
}

Stub code in StringOperations.sdsstub

@Pure
fun repeat(
    count: ConvertibleToIntCell
) -> cell: Cell<String?>

`replaceAll`¶

Replace all occurrences of the old substring with the new substring.

Parameters:

Name	Type	Description	Default
`old`	`union<String, Cell<Any?>?>`	The substring to replace.	-
`new`	`union<String, Cell<Any?>?>`	The substring to replace with.	-

Results:

Name	Type	Description
`cell`	`Cell<String?>`	The string with all occurrences replaced.

Examples:

pipeline example {
    val column = Column("a", ["ab", "bc", null]);
    out column.transform((cell) -> cell.str.replaceAll("b", "z"));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("replace_all")
fun replaceAll(
    old: ConvertibleToStringCell,
    new: ConvertibleToStringCell
) -> cell: Cell<String?>

`reverse`¶

Reverse the string.

Results:

Name	Type	Description
`cell`	`Cell<String?>`	The reversed string.

Examples:

pipeline example {
    val column = Column("a", ["ab", "bc", null]);
    out column.transform((cell) -> cell.str.reverse());
}

Stub code in StringOperations.sdsstub

@Pure
fun reverse() -> cell: Cell<String?>

`slice`¶

Get a slice of the string.

Parameters:

Name	Type	Description	Default
`start`	`union<Int, Cell<Any?>?>`	The start index of the slice. Nonnegative indices are counted from the beginning (starting at 0), negative indices from the end (starting at -1).	`0`
`length`	`union<Int, Cell<Any?>?>`	The length of the slice. If None, the slice contains all characters starting from `start`. Must greater than or equal to 0.	`null`

Results:

Name	Type	Description
`cell`	`Cell<String?>`	The sliced string.

Examples:

pipeline example {
    val column = Column("a", ["abc", "de", null]);
    out column.transform((cell) -> cell.str.slice(start = 1));
    out column.transform((cell) -> cell.str.slice(start = 1, length = 1));
}

Stub code in StringOperations.sdsstub

@Pure
fun slice(
    start: ConvertibleToIntCell = 0,
    length: ConvertibleToIntCell = null
) -> cell: Cell<String?>

`startsWith`¶

Check if the string starts with the prefix.

Parameters:

Name	Type	Description	Default
`prefix`	`union<String, Cell<Any?>?>`	The expected prefix.	-

Results:

Name	Type	Description
`cell`	`Cell<Boolean?>`	Whether the string starts with the prefix.

Examples:

pipeline example {
    val column = Column("a", ["ab", "bc", null]);
    out column.transform((cell) -> cell.str.startsWith("a"));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("starts_with")
fun startsWith(
    prefix: ConvertibleToStringCell
) -> cell: Cell<Boolean?>

`strip`¶

Remove leading and trailing characters.

Parameters:

Name	Type	Description	Default
`characters`	`union<String, Cell<Any?>?>`	The characters to remove. If None, whitespace is removed.	`null`

Results:

Name	Type	Description
`cell`	`Cell<String?>`	The stripped string.

Examples:

pipeline example {
    val column = Column("a", ["  ab  ", "~ bc ~", null]);
    out column.transform((cell) -> cell.str.strip());
    out column.transform((cell) -> cell.str.strip(characters=" ~"));
}

Stub code in StringOperations.sdsstub

@Pure
fun strip(
    characters: ConvertibleToStringCell = null
) -> cell: Cell<String?>

`stripEnd`¶

Remove trailing characters.

Parameters:

Name	Type	Description	Default
`characters`	`union<String, Cell<Any?>?>`	The characters to remove. If None, whitespace is removed.	`null`

Results:

Name	Type	Description
`cell`	`Cell<String?>`	The stripped string.

Examples:

pipeline example {
    val column = Column("a", ["  ab  ", "~ bc ~", null]);
    out column.transform((cell) -> cell.str.stripEnd());
    out column.transform((cell) -> cell.str.stripEnd(characters=" ~"));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("strip_end")
fun stripEnd(
    characters: ConvertibleToStringCell = null
) -> cell: Cell<String?>

`stripStart`¶

Remove leading characters.

Parameters:

Name	Type	Description	Default
`characters`	`union<String, Cell<Any?>?>`	The characters to remove. If None, whitespace is removed.	`null`

Results:

Name	Type	Description
`cell`	`Cell<String?>`	The stripped string.

Examples:

pipeline example {
    val column = Column("a", ["  ab  ", "~ bc ~", null]);
    out column.transform((cell) -> cell.str.stripStart());
    out column.transform((cell) -> cell.str.stripStart(characters=" ~"));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("strip_start")
fun stripStart(
    characters: ConvertibleToStringCell = null
) -> cell: Cell<String?>

`toDate`¶

Convert a string to a date.

The format parameter controls the presentation. It can be "iso" to target ISO 8601 or a custom string. The custom string can contain fixed specifiers (see below), which are replaced with the corresponding values. The specifiers are case-sensitive and always enclosed in curly braces. Other text is included in the output verbatim. To include a literal opening curly brace, use \{, and to include a literal backslash, use \\.

The following specifiers are available:

{Y}, {_Y}, {^Y}: Year (zero-padded to four digits, space-padded to four digits, no padding).
{Y99}, {_Y99}, {^Y99}: Year modulo 100 (zero-padded to two digits, space-padded to two digits, no padding).
{M}, {_M}, {^M}: Month (zero-padded to two digits, space-padded to two digits, no padding).
{M-full}: Full name of the month (e.g. "January").
{M-short}: Abbreviated name of the month with three letters (e.g. "Jan").
{W}, {_W}, {^W}: Week number as defined by ISO 8601 (zero-padded to two digits, space-padded to two digits, no padding).
{D}, {_D}, {^D}: Day of the month (zero-padded to two digits, space-padded to two digits, no padding).
{DOW}: Day of the week as defined by ISO 8601 (1 = Monday, 7 = Sunday).
{DOW-full}: Full name of the day of the week (e.g. "Monday").
{DOW-short}: Abbreviated name of the day of the week with three letters (e.g. "Mon").
{DOY}, {_DOY}, {^DOY}: Day of the year, ranging from 1 to 366 (zero-padded to three digits, space-padded to three digits, no padding).

The specifiers follow certain conventions:

If a component may be formatted in multiple ways, we use shorter specifiers for ISO 8601. Specifiers for other formats have a prefix (same value with different padding, see below) or suffix (other differences).
By default, value are zero-padded, where applicable.
A leading underscore (_) means the value is space-padded.
A leading caret (^) means the value has no padding (think of the caret in regular expressions).

Parameters:

Name	Type	Description	Default
`format`	`String?`	The format to use.	`"iso"`

Results:

Name	Type	Description
`cell`	`Cell<Date?>`	The parsed date.

Examples:

pipeline example {
    val column = Column("a", ["1999-02-03", "03.02.2001", "abc", null]);
    out column.transform((cell) -> cell.str.toDate());
    out column.transform((cell) -> cell.str.toDate(format="{D}.{M}.{Y}"));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("to_date")
fun toDate(
    format: String? = "iso"
) -> cell: Cell<Date?>

`toDatetime`¶

Convert a string to a datetime.

The format parameter controls the presentation. It can be "iso" to target ISO 8601 or a custom string. The custom string can contain fixed specifiers (see below), which are replaced with the corresponding values. The specifiers are case-sensitive and always enclosed in curly braces. Other text is included in the output verbatim. To include a literal opening curly brace, use \{, and to include a literal backslash, use \\.

The following specifiers for date components are available for datetime and date:

{Y}, {_Y}, {^Y}: Year (zero-padded to four digits, space-padded to four digits, no padding).
{Y99}, {_Y99}, {^Y99}: Year modulo 100 (zero-padded to two digits, space-padded to two digits, no padding).
{M}, {_M}, {^M}: Month (zero-padded to two digits, space-padded to two digits, no padding).
{M-full}: Full name of the month (e.g. "January").
{M-short}: Abbreviated name of the month with three letters (e.g. "Jan").
{W}, {_W}, {^W}: Week number as defined by ISO 8601 (zero-padded to two digits, space-padded to two digits, no padding).
{D}, {_D}, {^D}: Day of the month (zero-padded to two digits, space-padded to two digits, no padding).
{DOW}: Day of the week as defined by ISO 8601 (1 = Monday, 7 = Sunday).
{DOW-full}: Full name of the day of the week (e.g. "Monday").
{DOW-short}: Abbreviated name of the day of the week with three letters (e.g. "Mon").
{DOY}, {_DOY}, {^DOY}: Day of the year, ranging from 1 to 366 (zero-padded to three digits, space-padded to three digits, no padding).

The following specifiers for time components are available for datetime and time:

{h}, {_h}, {^h}: Hour (zero-padded to two digits, space-padded to two digits, no padding).
{h12}, {_h12}, {^h12}: Hour in 12-hour format (zero-padded to two digits, space-padded to two digits, no padding).
{m}, {_m}, {^m}: Minute (zero-padded to two digits, space-padded to two digits, no padding).
{s}, {_s}, {^s}: Second (zero-padded to two digits, space-padded to two digits, no padding).
{.f}: Fractional seconds with a leading decimal point.
{ms}: Millisecond (zero-padded to three digits).
{us}: Microsecond (zero-padded to six digits).
{ns}: Nanosecond (zero-padded to nine digits).
{AM/PM}: AM or PM (uppercase).
{am/pm}: am or pm (lowercase).

The following specifiers are available for datetime only:

{z}: Offset of the timezone from UTC without a colon (e.g. "+0000").
{:z}: Offset of the timezone from UTC with a colon (e.g. "+00:00").
{u}: The UNIX timestamp in seconds.

The specifiers follow certain conventions:

Generally, date components use uppercase letters and time components use lowercase letters.
If a component may be formatted in multiple ways, we use shorter specifiers for ISO 8601. Specifiers for other formats have a prefix (same value with different padding, see below) or suffix (other differences).
By default, value are zero-padded, where applicable.
A leading underscore (_) means the value is space-padded.
A leading caret (^) means the value has no padding (think of the caret in regular expressions).

Parameters:

Name	Type	Description	Default
`format`	`String?`	The format to use.	`"iso"`

Results:

Name	Type	Description
`cell`	`Cell<Datetime?>`	The parsed datetime.

Examples:

pipeline example {
    val column = Column("a", ["1999-12-31T01:02:03Z", "12:30 Jan 23 2024", "abc", null]);
    out column.transform((cell) -> cell.str.toDatetime());
    out column.transform((cell) -> cell.str.toDatetime(
        format="{h}:{m} {M-short} {D} {Y}"
    ));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("to_datetime")
fun toDatetime(
    format: String? = "iso"
) -> cell: Cell<Datetime?>

`toFloat`¶

Convert the string to a float.

Results:

Name	Type	Description
`cell`	`Cell<Float?>`	The float value. If the string cannot be converted to a float, null is returned.

Examples:

pipeline example {
    val column = Column("a", ["1", "1.5", "abc", null]);
    out column.transform((cell) -> cell.str.toFloat());
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("to_float")
fun toFloat() -> cell: Cell<Float?>

`toInt`¶

Convert the string to an integer.

Parameters:

Name	Type	Description	Default
`base`	`union<Int, Cell<Any?>?>`	The base of the integer.	`10`

Results:

Name	Type	Description
`cell`	`Cell<Int?>`	The integer value. If the string cannot be converted to an integer, null is returned.

Examples:

pipeline example {
    val column1 = Column("a", ["1", "10", "abc", null]);
    out column1.transform((cell) -> cell.str.toInt());
}

pipeline example {
    val column2 = Column("a", ["1", "10", "abc", null]);
    out column2.transform((cell) -> cell.str.toInt(base = 2));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("to_int")
fun toInt(
    base: ConvertibleToIntCell = 10
) -> cell: Cell<Int?>

`toLowercase`¶

Convert the string to lowercase.

Results:

Name	Type	Description
`cell`	`Cell<String?>`	The lowercase string.

Examples:

pipeline example {
    val column = Column("a", ["AB", "BC", null]);
    out column.transform((cell) -> cell.str.toLowercase());
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("to_lowercase")
fun toLowercase() -> cell: Cell<String?>

`toTime`¶

Convert a string to a time.

The format parameter controls the presentation. It can be "iso" to target ISO 8601 or a custom string. The custom string can contain fixed specifiers (see below), which are replaced with the corresponding values. The specifiers are case-sensitive and always enclosed in curly braces. Other text is included in the output verbatim. To include a literal opening curly brace, use \{, and to include a literal backslash, use \\.

The following specifiers are available:

{h}, {_h}, {^h}: Hour (zero-padded to two digits, space-padded to two digits, no padding).
{h12}, {_h12}, {^h12}: Hour in 12-hour format (zero-padded to two digits, space-padded to two digits, no padding).
{m}, {_m}, {^m}: Minute (zero-padded to two digits, space-padded to two digits, no padding).
{s}, {_s}, {^s}: Second (zero-padded to two digits, space-padded to two digits, no padding).
{.f}: Fractional seconds with a leading decimal point.
{ms}: Millisecond (zero-padded to three digits).
{us}: Microsecond (zero-padded to six digits).
{ns}: Nanosecond (zero-padded to nine digits).
{AM/PM}: AM or PM (uppercase).
{am/pm}: am or pm (lowercase).

The specifiers follow certain conventions:

If a component may be formatted in multiple ways, we use shorter specifiers for ISO 8601. Specifiers for other formats have a prefix (same value with different padding, see below) or suffix (other differences).
By default, value are zero-padded, where applicable.
A leading underscore (_) means the value is space-padded.
A leading caret (^) means the value has no padding (think of the caret in regular expressions).

Parameters:

Name	Type	Description	Default
`format`	`String?`	The format to use.	`"iso"`

Results:

Name	Type	Description
`cell`	`Cell<Time?>`	The parsed time.

Examples:

pipeline example {
    val column = Column("a", ["12:34", "12:34:56", "12:34:56.789", "abc", null]);
    out column.transform((cell) -> cell.str.toTime());
    out column.transform((cell) -> cell.str.toTime(format="{h}:{m}"));
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("to_time")
fun toTime(
    format: String? = "iso"
) -> cell: Cell<Time?>

`toUppercase`¶

Convert the string to uppercase.

Results:

Name	Type	Description
`cell`	`Cell<String?>`	The uppercase string.

Examples:

pipeline example {
    val column = Column("a", ["ab", "bc", null]);
    out column.transform((cell) -> cell.str.toUppercase());
}

Stub code in StringOperations.sdsstub

@Pure
@PythonName("to_uppercase")
fun toUppercase() -> cell: Cell<String?>

StringOperations¶

contains¶

endsWith¶

indexOf¶

length¶

padEnd¶

padStart¶

removePrefix¶

removeSuffix¶

repeat¶

replaceAll¶

reverse¶

slice¶

startsWith¶

strip¶

stripEnd¶

stripStart¶

toDate¶

toDatetime¶

toFloat¶

toInt¶

toLowercase¶

toTime¶

toUppercase¶

`StringOperations`¶

`contains`¶

`endsWith`¶

`indexOf`¶

`length`¶

`padEnd`¶

`padStart`¶

`removePrefix`¶

`removeSuffix`¶

`repeat`¶

`replaceAll`¶

`reverse`¶

`slice`¶

`startsWith`¶

`strip`¶

`stripEnd`¶

`stripStart`¶

`toDate`¶

`toDatetime`¶

`toFloat`¶

`toInt`¶

`toLowercase`¶

`toTime`¶

`toUppercase`¶